diff --git a/.editorconfig b/.editorconfig
new file mode 100644
index 0000000000000000000000000000000000000000..854773350cc5a92bf40312f8dce0f452166c19d6
--- /dev/null
+++ b/.editorconfig
@@ -0,0 +1,32 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+root = true
+
+[{*.{awk,c,dts,dtsi,dtso,h,mk,s,S},Kconfig,Makefile,Makefile.*}]
+charset = utf-8
+end_of_line = lf
+trim_trailing_whitespace = true
+insert_final_newline = true
+indent_style = tab
+indent_size = 8
+
+[*.{json,py,rs}]
+charset = utf-8
+end_of_line = lf
+trim_trailing_whitespace = true
+insert_final_newline = true
+indent_style = space
+indent_size = 4
+
+# this must be below the general *.py to overwrite it
+[tools/{perf,power,rcu,testing/kunit}/**.py,]
+indent_style = tab
+indent_size = 8
+
+[*.yaml]
+charset = utf-8
+end_of_line = lf
+trim_trailing_whitespace = unset
+insert_final_newline = true
+indent_style = space
+indent_size = 2
diff --git a/.gitignore b/.gitignore
index 98274e1160d7b11729f307df26f3e93427705f8d..689a4fa3f5477aa0fd46997eca5ee7a29cd78f8a 100644
--- a/.gitignore
+++ b/.gitignore
@@ -96,6 +96,7 @@ modules.order
#
!.clang-format
!.cocciconfig
+!.editorconfig
!.get_maintainer.ignore
!.gitattributes
!.gitignore
diff --git a/Documentation/admin-guide/cifs/todo.rst b/Documentation/admin-guide/cifs/todo.rst
index 2646ed2e2d3e32751d3eacfc89a87b73bd2d79e4..9a65c670774ee822135c6206edd7a7c1f59c723d 100644
--- a/Documentation/admin-guide/cifs/todo.rst
+++ b/Documentation/admin-guide/cifs/todo.rst
@@ -2,7 +2,8 @@
TODO
====
-Version 2.14 December 21, 2018
+As of 6.7 kernel. See https://wiki.samba.org/index.php/LinuxCIFSKernel
+for list of features added by release
A Partial List of Missing Features
==================================
@@ -12,22 +13,22 @@ for visible, important contributions to this module. Here
is a partial list of the known problems and missing features:
a) SMB3 (and SMB3.1.1) missing optional features:
+ multichannel performance optimizations, algorithmic channel selection,
+ directory leases optimizations,
+ support for faster packet signing (GMAC),
+ support for compression over the network,
+ T10 copy offload ie "ODX" (copy chunk, and "Duplicate Extents" ioctl
+ are currently the only two server side copy mechanisms supported)
- - multichannel (partially integrated), integration of multichannel with RDMA
- - directory leases (improved metadata caching). Currently only implemented for root dir
- - T10 copy offload ie "ODX" (copy chunk, and "Duplicate Extents" ioctl
- currently the only two server side copy mechanisms supported)
+b) Better optimized compounding and error handling for sparse file support,
+ perhaps addition of new optional SMB3.1.1 fsctls to make collapse range
+ and insert range more atomic
-b) improved sparse file support (fiemap and SEEK_HOLE are implemented
- but additional features would be supportable by the protocol such
- as FALLOC_FL_COLLAPSE_RANGE and FALLOC_FL_INSERT_RANGE)
-
-c) Directory entry caching relies on a 1 second timer, rather than
- using Directory Leases, currently only the root file handle is cached longer
- by leveraging Directory Leases
+c) Support for SMB3.1.1 over QUIC (and perhaps other socket based protocols
+ like SCTP)
d) quota support (needs minor kernel change since quota calls otherwise
- won't make it to network filesystems or deviceless filesystems).
+ won't make it to network filesystems or deviceless filesystems).
e) Additional use cases can be optimized to use "compounding" (e.g.
open/query/close and open/setinfo/close) to reduce the number of
@@ -92,23 +93,20 @@ t) split cifs and smb3 support into separate modules so legacy (and less
v) Additional testing of POSIX Extensions for SMB3.1.1
-w) Add support for additional strong encryption types, and additional spnego
- authentication mechanisms (see MS-SMB2). GCM-256 is now partially implemented.
+w) Support for the Mac SMB3.1.1 extensions to improve interop with Apple servers
+
+x) Support for additional authentication options (e.g. IAKERB, peer-to-peer
+ Kerberos, SCRAM and others supported by existing servers)
-x) Finish support for SMB3.1.1 compression
+y) Improved tracing, more eBPF trace points, better scripts for performance
+ analysis
Known Bugs
==========
See https://bugzilla.samba.org - search on product "CifsVFS" for
current bug list. Also check http://bugzilla.kernel.org (Product = File System, Component = CIFS)
-
-1) existing symbolic links (Windows reparse points) are recognized but
- can not be created remotely. They are implemented for Samba and those that
- support the CIFS Unix extensions, although earlier versions of Samba
- overly restrict the pathnames.
-2) follow_link and readdir code does not follow dfs junctions
- but recognizes them
+and xfstest results e.g. https://wiki.samba.org/index.php/Xfstest-results-smb3
Misc testing to do
==================
diff --git a/Documentation/admin-guide/cifs/usage.rst b/Documentation/admin-guide/cifs/usage.rst
index 5f936b4b601881d3e031b71a1cc258c5ddb9585e..aa8290a29dc88b0efdf56500ea40b1a97ddccc9c 100644
--- a/Documentation/admin-guide/cifs/usage.rst
+++ b/Documentation/admin-guide/cifs/usage.rst
@@ -81,7 +81,7 @@ much older and less secure than the default dialect SMB3 which includes
many advanced security features such as downgrade attack detection
and encrypted shares and stronger signing and authentication algorithms.
There are additional mount options that may be helpful for SMB3 to get
-improved POSIX behavior (NB: can use vers=3.0 to force only SMB3, never 2.1):
+improved POSIX behavior (NB: can use vers=3 to force SMB3 or later, never 2.1):
``mfsymlinks`` and either ``cifsacl`` or ``modefromsid`` (usually with ``idsfromsid``)
@@ -715,6 +715,7 @@ DebugData Displays information about active CIFS sessions and
Stats Lists summary resource usage information as well as per
share statistics.
open_files List all the open file handles on all active SMB sessions.
+mount_params List of all mount parameters available for the module
======================= =======================================================
Configuration pseudo-files:
@@ -864,6 +865,11 @@ i.e.::
echo "value" > /sys/module/cifs/parameters/
+More detailed descriptions of the available module parameters and their values
+can be seen by doing:
+
+ modinfo cifs (or modinfo smb3)
+
================= ==========================================================
1. enable_oplocks Enable or disable oplocks. Oplocks are enabled by default.
[Y/y/1]. To disable use any of [N/n/0].
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 2e76c3476e2ab5197a9ac73c065b132451212aca..31b3a25680d08cfac3603d58b3d3783bbf1e34bb 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -888,9 +888,9 @@
memory region [offset, offset + size] for that kernel
image. If '@offset' is omitted, then a suitable offset
is selected automatically.
- [KNL, X86-64, ARM64, RISCV] Select a region under 4G first, and
- fall back to reserve region above 4G when '@offset'
- hasn't been specified.
+ [KNL, X86-64, ARM64, RISCV, LoongArch] Select a region
+ under 4G first, and fall back to reserve region above
+ 4G when '@offset' hasn't been specified.
See Documentation/admin-guide/kdump/kdump.rst for further details.
crashkernel=range1:size1[,range2:size2,...][@offset]
@@ -901,25 +901,27 @@
Documentation/admin-guide/kdump/kdump.rst for an example.
crashkernel=size[KMG],high
- [KNL, X86-64, ARM64, RISCV] range could be above 4G.
+ [KNL, X86-64, ARM64, RISCV, LoongArch] range could be
+ above 4G.
Allow kernel to allocate physical memory region from top,
so could be above 4G if system have more than 4G ram
installed. Otherwise memory region will be allocated
below 4G, if available.
It will be ignored if crashkernel=X is specified.
crashkernel=size[KMG],low
- [KNL, X86-64, ARM64, RISCV] range under 4G. When crashkernel=X,high
- is passed, kernel could allocate physical memory region
- above 4G, that cause second kernel crash on system
- that require some amount of low memory, e.g. swiotlb
- requires at least 64M+32K low memory, also enough extra
- low memory is needed to make sure DMA buffers for 32-bit
- devices won't run out. Kernel would try to allocate
+ [KNL, X86-64, ARM64, RISCV, LoongArch] range under 4G.
+ When crashkernel=X,high is passed, kernel could allocate
+ physical memory region above 4G, that cause second kernel
+ crash on system that require some amount of low memory,
+ e.g. swiotlb requires at least 64M+32K low memory, also
+ enough extra low memory is needed to make sure DMA buffers
+ for 32-bit devices won't run out. Kernel would try to allocate
default size of memory below 4G automatically. The default
size is platform dependent.
--> x86: max(swiotlb_size_or_default() + 8MiB, 256MiB)
--> arm64: 128MiB
--> riscv: 128MiB
+ --> loongarch: 128MiB
This one lets the user specify own low range under 4G
for second kernel instead.
0: to disable low allocation.
diff --git a/Documentation/arch/arm64/silicon-errata.rst b/Documentation/arch/arm64/silicon-errata.rst
index bfdf236e2af3d4ca5dc3e6330ea6737704d43329..e8c2ce1f9df68df5976b7cc536d3f48c0501ba4b 100644
--- a/Documentation/arch/arm64/silicon-errata.rst
+++ b/Documentation/arch/arm64/silicon-errata.rst
@@ -71,6 +71,8 @@ stable kernels.
+----------------+-----------------+-----------------+-----------------------------+
| ARM | Cortex-A510 | #2658417 | ARM64_ERRATUM_2658417 |
+----------------+-----------------+-----------------+-----------------------------+
+| ARM | Cortex-A510 | #3117295 | ARM64_ERRATUM_3117295 |
++----------------+-----------------+-----------------+-----------------------------+
| ARM | Cortex-A520 | #2966298 | ARM64_ERRATUM_2966298 |
+----------------+-----------------+-----------------+-----------------------------+
| ARM | Cortex-A53 | #826319 | ARM64_ERRATUM_826319 |
@@ -235,11 +237,9 @@ stable kernels.
+----------------+-----------------+-----------------+-----------------------------+
| Rockchip | RK3588 | #3588001 | ROCKCHIP_ERRATUM_3588001 |
+----------------+-----------------+-----------------+-----------------------------+
-
+----------------+-----------------+-----------------+-----------------------------+
| Fujitsu | A64FX | E#010001 | FUJITSU_ERRATUM_010001 |
+----------------+-----------------+-----------------+-----------------------------+
-
+----------------+-----------------+-----------------+-----------------------------+
| ASR | ASR8601 | #8601001 | N/A |
+----------------+-----------------+-----------------+-----------------------------+
diff --git a/Documentation/block/ioprio.rst b/Documentation/block/ioprio.rst
index a25c6d5df87b20ff2149353adcf854b1b7965f80..4662e1ff3d81f28f57417ff70ac81f84220df88f 100644
--- a/Documentation/block/ioprio.rst
+++ b/Documentation/block/ioprio.rst
@@ -6,17 +6,16 @@ Block io priorities
Intro
-----
-With the introduction of cfq v3 (aka cfq-ts or time sliced cfq), basic io
-priorities are supported for reads on files. This enables users to io nice
-processes or process groups, similar to what has been possible with cpu
-scheduling for ages. This document mainly details the current possibilities
-with cfq; other io schedulers do not support io priorities thus far.
+The io priority feature enables users to io nice processes or process groups,
+similar to what has been possible with cpu scheduling for ages. Support for io
+priorities is io scheduler dependent and currently supported by bfq and
+mq-deadline.
Scheduling classes
------------------
-CFQ implements three generic scheduling classes that determine how io is
-served for a process.
+Three generic scheduling classes are implemented for io priorities that
+determine how io is served for a process.
IOPRIO_CLASS_RT: This is the realtime io class. This scheduling class is given
higher priority than any other in the system, processes from this class are
diff --git a/Documentation/dev-tools/checkuapi.rst b/Documentation/dev-tools/checkuapi.rst
new file mode 100644
index 0000000000000000000000000000000000000000..9072f21b50b0c0a980a948155afae59b95a0c2d3
--- /dev/null
+++ b/Documentation/dev-tools/checkuapi.rst
@@ -0,0 +1,477 @@
+.. SPDX-License-Identifier: GPL-2.0-only
+
+============
+UAPI Checker
+============
+
+The UAPI checker (``scripts/check-uapi.sh``) is a shell script which
+checks UAPI header files for userspace backwards-compatibility across
+the git tree.
+
+Options
+=======
+
+This section will describe the options with which ``check-uapi.sh``
+can be run.
+
+Usage::
+
+ check-uapi.sh [-b BASE_REF] [-p PAST_REF] [-j N] [-l ERROR_LOG] [-i] [-q] [-v]
+
+Available options::
+
+ -b BASE_REF Base git reference to use for comparison. If unspecified or empty,
+ will use any dirty changes in tree to UAPI files. If there are no
+ dirty changes, HEAD will be used.
+ -p PAST_REF Compare BASE_REF to PAST_REF (e.g. -p v6.1). If unspecified or empty,
+ will use BASE_REF^1. Must be an ancestor of BASE_REF. Only headers
+ that exist on PAST_REF will be checked for compatibility.
+ -j JOBS Number of checks to run in parallel (default: number of CPU cores).
+ -l ERROR_LOG Write error log to file (default: no error log is generated).
+ -i Ignore ambiguous changes that may or may not break UAPI compatibility.
+ -q Quiet operation.
+ -v Verbose operation (print more information about each header being checked).
+
+Environmental args::
+
+ ABIDIFF Custom path to abidiff binary
+ CC C compiler (default is "gcc")
+ ARCH Target architecture of C compiler (default is host arch)
+
+Exit codes::
+
+ 0) Success
+ 1) ABI difference detected
+ 2) Prerequisite not met
+
+Examples
+========
+
+Basic Usage
+-----------
+
+First, let's try making a change to a UAPI header file that obviously
+won't break userspace::
+
+ cat << 'EOF' | patch -l -p1
+ --- a/include/uapi/linux/acct.h
+ +++ b/include/uapi/linux/acct.h
+ @@ -21,7 +21,9 @@
+ #include
+ #include
+
+ -/*
+ +#define FOO
+ +
+ +/*
+ * comp_t is a 16-bit "floating" point number with a 3-bit base 8
+ * exponent and a 13-bit fraction.
+ * comp2_t is 24-bit with 5-bit base 2 exponent and 20 bit fraction
+ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
+ EOF
+
+Now, let's use the script to validate::
+
+ % ./scripts/check-uapi.sh
+ Installing user-facing UAPI headers from dirty tree... OK
+ Installing user-facing UAPI headers from HEAD... OK
+ Checking changes to UAPI headers between HEAD and dirty tree...
+ All 912 UAPI headers compatible with x86 appear to be backwards compatible
+
+Let's add another change that *might* break userspace::
+
+ cat << 'EOF' | patch -l -p1
+ --- a/include/uapi/linux/bpf.h
+ +++ b/include/uapi/linux/bpf.h
+ @@ -74,7 +74,7 @@ struct bpf_insn {
+ __u8 dst_reg:4; /* dest register */
+ __u8 src_reg:4; /* source register */
+ __s16 off; /* signed offset */
+ - __s32 imm; /* signed immediate constant */
+ + __u32 imm; /* unsigned immediate constant */
+ };
+
+ /* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */
+ EOF
+
+The script will catch this::
+
+ % ./scripts/check-uapi.sh
+ Installing user-facing UAPI headers from dirty tree... OK
+ Installing user-facing UAPI headers from HEAD... OK
+ Checking changes to UAPI headers between HEAD and dirty tree...
+ ==== ABI differences detected in include/linux/bpf.h from HEAD -> dirty tree ====
+ [C] 'struct bpf_insn' changed:
+ type size hasn't changed
+ 1 data member change:
+ type of '__s32 imm' changed:
+ typedef name changed from __s32 to __u32 at int-ll64.h:27:1
+ underlying type 'int' changed:
+ type name changed from 'int' to 'unsigned int'
+ type size hasn't changed
+ ==================================================================================
+
+ error - 1/912 UAPI headers compatible with x86 appear _not_ to be backwards compatible
+
+In this case, the script is reporting the type change because it could
+break a userspace program that passes in a negative number. Now, let's
+say you know that no userspace program could possibly be using a negative
+value in ``imm``, so changing to an unsigned type there shouldn't hurt
+anything. You can pass the ``-i`` flag to the script to ignore changes
+in which the userspace backwards compatibility is ambiguous::
+
+ % ./scripts/check-uapi.sh -i
+ Installing user-facing UAPI headers from dirty tree... OK
+ Installing user-facing UAPI headers from HEAD... OK
+ Checking changes to UAPI headers between HEAD and dirty tree...
+ All 912 UAPI headers compatible with x86 appear to be backwards compatible
+
+Now, let's make a similar change that *will* break userspace::
+
+ cat << 'EOF' | patch -l -p1
+ --- a/include/uapi/linux/bpf.h
+ +++ b/include/uapi/linux/bpf.h
+ @@ -71,8 +71,8 @@ enum {
+
+ struct bpf_insn {
+ __u8 code; /* opcode */
+ - __u8 dst_reg:4; /* dest register */
+ __u8 src_reg:4; /* source register */
+ + __u8 dst_reg:4; /* dest register */
+ __s16 off; /* signed offset */
+ __s32 imm; /* signed immediate constant */
+ };
+ EOF
+
+Since we're re-ordering an existing struct member, there's no ambiguity,
+and the script will report the breakage even if you pass ``-i``::
+
+ % ./scripts/check-uapi.sh -i
+ Installing user-facing UAPI headers from dirty tree... OK
+ Installing user-facing UAPI headers from HEAD... OK
+ Checking changes to UAPI headers between HEAD and dirty tree...
+ ==== ABI differences detected in include/linux/bpf.h from HEAD -> dirty tree ====
+ [C] 'struct bpf_insn' changed:
+ type size hasn't changed
+ 2 data member changes:
+ '__u8 dst_reg' offset changed from 8 to 12 (in bits) (by +4 bits)
+ '__u8 src_reg' offset changed from 12 to 8 (in bits) (by -4 bits)
+ ==================================================================================
+
+ error - 1/912 UAPI headers compatible with x86 appear _not_ to be backwards compatible
+
+Let's commit the breaking change, then commit the innocuous change::
+
+ % git commit -m 'Breaking UAPI change' include/uapi/linux/bpf.h
+ [detached HEAD f758e574663a] Breaking UAPI change
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+ % git commit -m 'Innocuous UAPI change' include/uapi/linux/acct.h
+ [detached HEAD 2e87df769081] Innocuous UAPI change
+ 1 file changed, 3 insertions(+), 1 deletion(-)
+
+Now, let's run the script again with no arguments::
+
+ % ./scripts/check-uapi.sh
+ Installing user-facing UAPI headers from HEAD... OK
+ Installing user-facing UAPI headers from HEAD^1... OK
+ Checking changes to UAPI headers between HEAD^1 and HEAD...
+ All 912 UAPI headers compatible with x86 appear to be backwards compatible
+
+It doesn't catch any breaking change because, by default, it only
+compares ``HEAD`` to ``HEAD^1``. The breaking change was committed on
+``HEAD~2``. If we wanted the search scope to go back further, we'd have to
+use the ``-p`` option to pass a different past reference. In this case,
+let's pass ``-p HEAD~2`` to the script so it checks UAPI changes between
+``HEAD~2`` and ``HEAD``::
+
+ % ./scripts/check-uapi.sh -p HEAD~2
+ Installing user-facing UAPI headers from HEAD... OK
+ Installing user-facing UAPI headers from HEAD~2... OK
+ Checking changes to UAPI headers between HEAD~2 and HEAD...
+ ==== ABI differences detected in include/linux/bpf.h from HEAD~2 -> HEAD ====
+ [C] 'struct bpf_insn' changed:
+ type size hasn't changed
+ 2 data member changes:
+ '__u8 dst_reg' offset changed from 8 to 12 (in bits) (by +4 bits)
+ '__u8 src_reg' offset changed from 12 to 8 (in bits) (by -4 bits)
+ ==============================================================================
+
+ error - 1/912 UAPI headers compatible with x86 appear _not_ to be backwards compatible
+
+Alternatively, we could have also run with ``-b HEAD~``. This would set the
+base reference to ``HEAD~`` so then the script would compare it to ``HEAD~^1``.
+
+Architecture-specific Headers
+-----------------------------
+
+Consider this change::
+
+ cat << 'EOF' | patch -l -p1
+ --- a/arch/arm64/include/uapi/asm/sigcontext.h
+ +++ b/arch/arm64/include/uapi/asm/sigcontext.h
+ @@ -70,6 +70,7 @@ struct sigcontext {
+ struct _aarch64_ctx {
+ __u32 magic;
+ __u32 size;
+ + __u32 new_var;
+ };
+
+ #define FPSIMD_MAGIC 0x46508001
+ EOF
+
+This is a change to an arm64-specific UAPI header file. In this example, I'm
+running the script from an x86 machine with an x86 compiler, so, by default,
+the script only checks x86-compatible UAPI header files::
+
+ % ./scripts/check-uapi.sh
+ Installing user-facing UAPI headers from dirty tree... OK
+ Installing user-facing UAPI headers from HEAD... OK
+ No changes to UAPI headers were applied between HEAD and dirty tree
+
+With an x86 compiler, we can't check header files in ``arch/arm64``, so the
+script doesn't even try.
+
+If we want to check the header file, we'll have to use an arm64 compiler and
+set ``ARCH`` accordingly::
+
+ % CC=aarch64-linux-gnu-gcc ARCH=arm64 ./scripts/check-uapi.sh
+ Installing user-facing UAPI headers from dirty tree... OK
+ Installing user-facing UAPI headers from HEAD... OK
+ Checking changes to UAPI headers between HEAD and dirty tree...
+ ==== ABI differences detected in include/asm/sigcontext.h from HEAD -> dirty tree ====
+ [C] 'struct _aarch64_ctx' changed:
+ type size changed from 64 to 96 (in bits)
+ 1 data member insertion:
+ '__u32 new_var', at offset 64 (in bits) at sigcontext.h:73:1
+ -- snip --
+ [C] 'struct zt_context' changed:
+ type size changed from 128 to 160 (in bits)
+ 2 data member changes (1 filtered):
+ '__u16 nregs' offset changed from 64 to 96 (in bits) (by +32 bits)
+ '__u16 __reserved[3]' offset changed from 80 to 112 (in bits) (by +32 bits)
+ =======================================================================================
+
+ error - 1/884 UAPI headers compatible with arm64 appear _not_ to be backwards compatible
+
+We can see with ``ARCH`` and ``CC`` set properly for the file, the ABI
+change is reported properly. Also notice that the total number of UAPI
+header files checked by the script changes. This is because the number
+of headers installed for arm64 platforms is different than x86.
+
+Cross-Dependency Breakages
+--------------------------
+
+Consider this change::
+
+ cat << 'EOF' | patch -l -p1
+ --- a/include/uapi/linux/types.h
+ +++ b/include/uapi/linux/types.h
+ @@ -52,7 +52,7 @@ typedef __u32 __bitwise __wsum;
+ #define __aligned_be64 __be64 __attribute__((aligned(8)))
+ #define __aligned_le64 __le64 __attribute__((aligned(8)))
+
+ -typedef unsigned __bitwise __poll_t;
+ +typedef unsigned short __bitwise __poll_t;
+
+ #endif /* __ASSEMBLY__ */
+ #endif /* _UAPI_LINUX_TYPES_H */
+ EOF
+
+Here, we're changing a ``typedef`` in ``types.h``. This doesn't break
+a UAPI in ``types.h``, but other UAPIs in the tree may break due to
+this change::
+
+ % ./scripts/check-uapi.sh
+ Installing user-facing UAPI headers from dirty tree... OK
+ Installing user-facing UAPI headers from HEAD... OK
+ Checking changes to UAPI headers between HEAD and dirty tree...
+ ==== ABI differences detected in include/linux/eventpoll.h from HEAD -> dirty tree ====
+ [C] 'struct epoll_event' changed:
+ type size changed from 96 to 80 (in bits)
+ 2 data member changes:
+ type of '__poll_t events' changed:
+ underlying type 'unsigned int' changed:
+ type name changed from 'unsigned int' to 'unsigned short int'
+ type size changed from 32 to 16 (in bits)
+ '__u64 data' offset changed from 32 to 16 (in bits) (by -16 bits)
+ ========================================================================================
+ include/linux/eventpoll.h did not change between HEAD and dirty tree...
+ It's possible a change to one of the headers it includes caused this error:
+ #include
+ #include
+
+Note that the script noticed the failing header file did not change,
+so it assumes one of its includes must have caused the breakage. Indeed,
+we can see ``linux/types.h`` is used from ``eventpoll.h``.
+
+UAPI Header Removals
+--------------------
+
+Consider this change::
+
+ cat << 'EOF' | patch -l -p1
+ diff --git a/include/uapi/asm-generic/Kbuild b/include/uapi/asm-generic/Kbuild
+ index ebb180aac74e..a9c88b0a8b3b 100644
+ --- a/include/uapi/asm-generic/Kbuild
+ +++ b/include/uapi/asm-generic/Kbuild
+ @@ -31,6 +31,6 @@ mandatory-y += stat.h
+ mandatory-y += statfs.h
+ mandatory-y += swab.h
+ mandatory-y += termbits.h
+ -mandatory-y += termios.h
+ +#mandatory-y += termios.h
+ mandatory-y += types.h
+ mandatory-y += unistd.h
+ EOF
+
+This script removes a UAPI header file from the install list. Let's run
+the script::
+
+ % ./scripts/check-uapi.sh
+ Installing user-facing UAPI headers from dirty tree... OK
+ Installing user-facing UAPI headers from HEAD... OK
+ Checking changes to UAPI headers between HEAD and dirty tree...
+ ==== UAPI header include/asm/termios.h was removed between HEAD and dirty tree ====
+
+ error - 1/912 UAPI headers compatible with x86 appear _not_ to be backwards compatible
+
+Removing a UAPI header is considered a breaking change, and the script
+will flag it as such.
+
+Checking Historic UAPI Compatibility
+------------------------------------
+
+You can use the ``-b`` and ``-p`` options to examine different chunks of your
+git tree. For example, to check all changed UAPI header files between tags
+v6.0 and v6.1, you'd run::
+
+ % ./scripts/check-uapi.sh -b v6.1 -p v6.0
+ Installing user-facing UAPI headers from v6.1... OK
+ Installing user-facing UAPI headers from v6.0... OK
+ Checking changes to UAPI headers between v6.0 and v6.1...
+
+ --- snip ---
+ error - 37/907 UAPI headers compatible with x86 appear _not_ to be backwards compatible
+
+Note: Before v5.3, a header file needed by the script is not present,
+so the script is unable to check changes before then.
+
+You'll notice that the script detected many UAPI changes that are not
+backwards compatible. Knowing that kernel UAPIs are supposed to be stable
+forever, this is an alarming result. This brings us to the next section:
+caveats.
+
+Caveats
+=======
+
+The UAPI checker makes no assumptions about the author's intention, so some
+types of changes may be flagged even though they intentionally break UAPI.
+
+Removals For Refactoring or Deprecation
+---------------------------------------
+
+Sometimes drivers for very old hardware are removed, such as in this example::
+
+ % ./scripts/check-uapi.sh -b ba47652ba655
+ Installing user-facing UAPI headers from ba47652ba655... OK
+ Installing user-facing UAPI headers from ba47652ba655^1... OK
+ Checking changes to UAPI headers between ba47652ba655^1 and ba47652ba655...
+ ==== UAPI header include/linux/meye.h was removed between ba47652ba655^1 and ba47652ba655 ====
+
+ error - 1/910 UAPI headers compatible with x86 appear _not_ to be backwards compatible
+
+The script will always flag removals (even if they're intentional).
+
+Struct Expansions
+-----------------
+
+Depending on how a structure is handled in kernelspace, a change which
+expands a struct could be non-breaking.
+
+If a struct is used as the argument to an ioctl, then the kernel driver
+must be able to handle ioctl commands of any size. Beyond that, you need
+to be careful when copying data from the user. Say, for example, that
+``struct foo`` is changed like this::
+
+ struct foo {
+ __u64 a; /* added in version 1 */
+ + __u32 b; /* added in version 2 */
+ + __u32 c; /* added in version 2 */
+ }
+
+By default, the script will flag this kind of change for further review::
+
+ [C] 'struct foo' changed:
+ type size changed from 64 to 128 (in bits)
+ 2 data member insertions:
+ '__u32 b', at offset 64 (in bits)
+ '__u32 c', at offset 96 (in bits)
+
+However, it is possible that this change was made safely.
+
+If a userspace program was built with version 1, it will think
+``sizeof(struct foo)`` is 8. That size will be encoded in the
+ioctl value that gets sent to the kernel. If the kernel is built
+with version 2, it will think the ``sizeof(struct foo)`` is 16.
+
+The kernel can use the ``_IOC_SIZE`` macro to get the size encoded
+in the ioctl code that the user passed in and then use
+``copy_struct_from_user()`` to safely copy the value::
+
+ int handle_ioctl(unsigned long cmd, unsigned long arg)
+ {
+ switch _IOC_NR(cmd) {
+ 0x01: {
+ struct foo my_cmd; /* size 16 in the kernel */
+
+ ret = copy_struct_from_user(&my_cmd, arg, sizeof(struct foo), _IOC_SIZE(cmd));
+ ...
+
+``copy_struct_from_user`` will zero the struct in the kernel and then copy
+only the bytes passed in from the user (leaving new members zeroized).
+If the user passed in a larger struct, the extra members are ignored.
+
+If you know this situation is accounted for in the kernel code, you can
+pass ``-i`` to the script, and struct expansions like this will be ignored.
+
+Flex Array Migration
+--------------------
+
+While the script handles expansion into an existing flex array, it does
+still flag initial migration to flex arrays from 1-element fake flex
+arrays. For example::
+
+ struct foo {
+ __u32 x;
+ - __u32 flex[1]; /* fake flex */
+ + __u32 flex[]; /* real flex */
+ };
+
+This change would be flagged by the script::
+
+ [C] 'struct foo' changed:
+ type size changed from 64 to 32 (in bits)
+ 1 data member change:
+ type of '__u32 flex[1]' changed:
+ type name changed from '__u32[1]' to '__u32[]'
+ array type size changed from 32 to 'unknown'
+ array type subrange 1 changed length from 1 to 'unknown'
+
+At this time, there's no way to filter these types of changes, so be
+aware of this possible false positive.
+
+Summary
+-------
+
+While many types of false positives are filtered out by the script,
+it's possible there are some cases where the script flags a change
+which does not break UAPI. It's also possible a change which *does*
+break userspace would not be flagged by this script. While the script
+has been run on much of the kernel history, there could still be corner
+cases that are not accounted for.
+
+The intention is for this script to be used as a quick check for
+maintainers or automated tooling, not as the end-all authority on
+patch compatibility. It's best to remember: use your best judgment
+(and ideally a unit test in userspace) to make sure your UAPI changes
+are backwards-compatible!
diff --git a/Documentation/dev-tools/index.rst b/Documentation/dev-tools/index.rst
index 3d2286c683bc99575b18746ee5529d5d64dceff5..efa49cdc8e2eb3cd7f104fc90c5c0e4ff4e9ad3b 100644
--- a/Documentation/dev-tools/index.rst
+++ b/Documentation/dev-tools/index.rst
@@ -31,6 +31,7 @@ Documentation/dev-tools/testing-overview.rst
kselftest
kunit/index
ktap
+ checkuapi
.. only:: subproject and html
diff --git a/Documentation/devicetree/bindings/dma/dma-controller.yaml b/Documentation/devicetree/bindings/dma/dma-controller.yaml
index 04d150d4d15d3cc74958c562ceaf921dc4bb24b0..e6afca558c2dfa4d84f5e821f519c1ad9dfa7d39 100644
--- a/Documentation/devicetree/bindings/dma/dma-controller.yaml
+++ b/Documentation/devicetree/bindings/dma/dma-controller.yaml
@@ -19,19 +19,4 @@ properties:
additionalProperties: true
-examples:
- - |
- dma: dma-controller@48000000 {
- compatible = "ti,omap-sdma";
- reg = <0x48000000 0x1000>;
- interrupts = <0 12 0x4>,
- <0 13 0x4>,
- <0 14 0x4>,
- <0 15 0x4>;
- #dma-cells = <1>;
- dma-channels = <32>;
- dma-requests = <127>;
- dma-channel-mask = <0xfffe>;
- };
-
...
diff --git a/Documentation/devicetree/bindings/dma/dma-router.yaml b/Documentation/devicetree/bindings/dma/dma-router.yaml
index 346fe0fa4460e316223d80ed0ffbd890dfd65450..5ad2febc581e23a72d862b6e22c379bbe13bbaec 100644
--- a/Documentation/devicetree/bindings/dma/dma-router.yaml
+++ b/Documentation/devicetree/bindings/dma/dma-router.yaml
@@ -40,15 +40,4 @@ required:
additionalProperties: true
-examples:
- - |
- sdma_xbar: dma-router@4a002b78 {
- compatible = "ti,dra7-dma-crossbar";
- reg = <0x4a002b78 0xfc>;
- #dma-cells = <1>;
- dma-requests = <205>;
- ti,dma-safe-map = <0>;
- dma-masters = <&sdma>;
- };
-
...
diff --git a/Documentation/devicetree/bindings/dma/loongson,ls2x-apbdma.yaml b/Documentation/devicetree/bindings/dma/loongson,ls2x-apbdma.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..6a1b49a49a646b9964e071981f9bb776dcb664d3
--- /dev/null
+++ b/Documentation/devicetree/bindings/dma/loongson,ls2x-apbdma.yaml
@@ -0,0 +1,62 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/dma/loongson,ls2x-apbdma.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Loongson LS2X APB DMA controller
+
+description:
+ The Loongson LS2X APB DMA controller is used for transferring data
+ between system memory and the peripherals on the APB bus.
+
+maintainers:
+ - Binbin Zhou
+
+allOf:
+ - $ref: dma-controller.yaml#
+
+properties:
+ compatible:
+ oneOf:
+ - const: loongson,ls2k1000-apbdma
+ - items:
+ - const: loongson,ls2k0500-apbdma
+ - const: loongson,ls2k1000-apbdma
+
+ reg:
+ maxItems: 1
+
+ interrupts:
+ maxItems: 1
+
+ clocks:
+ maxItems: 1
+
+ '#dma-cells':
+ const: 1
+
+required:
+ - compatible
+ - reg
+ - interrupts
+ - clocks
+ - '#dma-cells'
+
+additionalProperties: false
+
+examples:
+ - |
+ #include
+ #include
+
+ dma-controller@1fe00c00 {
+ compatible = "loongson,ls2k1000-apbdma";
+ reg = <0x1fe00c00 0x8>;
+ interrupt-parent = <&liointc1>;
+ interrupts = <12 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&clk LOONGSON2_APB_CLK>;
+ #dma-cells = <1>;
+ };
+
+...
diff --git a/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.yaml b/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.yaml
index 4003dbe94940c2150fc6105f9c18d5bd914aa39b..877147e95ecc5df1a34893ac88e0d83d70418347 100644
--- a/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.yaml
+++ b/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.yaml
@@ -53,6 +53,9 @@ properties:
ADMA_CHn_CTRL register.
const: 1
+ dma-channel-mask:
+ maxItems: 1
+
required:
- compatible
- reg
diff --git a/Documentation/devicetree/bindings/dma/qcom,gpi.yaml b/Documentation/devicetree/bindings/dma/qcom,gpi.yaml
index 88d0de3d1b46b8a9ff56613bd66dd3bf86034e0e..deb64cb9ca3eacf092b1f92a14407092689212d3 100644
--- a/Documentation/devicetree/bindings/dma/qcom,gpi.yaml
+++ b/Documentation/devicetree/bindings/dma/qcom,gpi.yaml
@@ -32,6 +32,8 @@ properties:
- qcom,sm8350-gpi-dma
- qcom,sm8450-gpi-dma
- qcom,sm8550-gpi-dma
+ - qcom,sm8650-gpi-dma
+ - qcom,x1e80100-gpi-dma
- const: qcom,sm6350-gpi-dma
- items:
- enum:
diff --git a/Documentation/devicetree/bindings/dma/renesas,rz-dmac.yaml b/Documentation/devicetree/bindings/dma/renesas,rz-dmac.yaml
index c284abc6784aec5439ba43f3fb3a8eab66fcbc16..a42b6a26a6d3f25874186faad8ce91995857f1a2 100644
--- a/Documentation/devicetree/bindings/dma/renesas,rz-dmac.yaml
+++ b/Documentation/devicetree/bindings/dma/renesas,rz-dmac.yaml
@@ -16,7 +16,7 @@ properties:
compatible:
items:
- enum:
- - renesas,r9a07g043-dmac # RZ/G2UL
+ - renesas,r9a07g043-dmac # RZ/G2UL and RZ/Five
- renesas,r9a07g044-dmac # RZ/G2{L,LC}
- renesas,r9a07g054-dmac # RZ/V2L
- const: renesas,rz-dmac
diff --git a/Documentation/devicetree/bindings/dma/sifive,fu540-c000-pdma.yaml b/Documentation/devicetree/bindings/dma/sifive,fu540-c000-pdma.yaml
index a1af0b9063653741f4bd6b6501339aea34cba13f..3b22183a1a379258f3c8c826dbc6597d1dc3b3a9 100644
--- a/Documentation/devicetree/bindings/dma/sifive,fu540-c000-pdma.yaml
+++ b/Documentation/devicetree/bindings/dma/sifive,fu540-c000-pdma.yaml
@@ -29,6 +29,7 @@ properties:
compatible:
items:
- enum:
+ - microchip,mpfs-pdma
- sifive,fu540-c000-pdma
- const: sifive,pdma0
description:
diff --git a/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml b/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml
index 4ca300a42a99c2f60184318d9b7e8d5906872e44..27b8e163656006b311264c242ff2aaa790c30ebb 100644
--- a/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml
+++ b/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml
@@ -37,11 +37,11 @@ properties:
reg:
minItems: 3
- maxItems: 5
+ maxItems: 9
reg-names:
minItems: 3
- maxItems: 5
+ maxItems: 9
"#dma-cells":
const: 3
@@ -141,7 +141,10 @@ allOf:
ti,sci-rm-range-tchan: false
reg:
- maxItems: 3
+ items:
+ - description: BCDMA Control /Status Registers region
+ - description: RX Channel Realtime Registers region
+ - description: Ring Realtime Registers region
reg-names:
items:
@@ -161,14 +164,29 @@ allOf:
properties:
reg:
minItems: 5
+ items:
+ - description: BCDMA Control /Status Registers region
+ - description: Block Copy Channel Realtime Registers region
+ - description: RX Channel Realtime Registers region
+ - description: TX Channel Realtime Registers region
+ - description: Ring Realtime Registers region
+ - description: Ring Configuration Registers region
+ - description: TX Channel Configuration Registers region
+ - description: RX Channel Configuration Registers region
+ - description: Block Copy Channel Configuration Registers region
reg-names:
+ minItems: 5
items:
- const: gcfg
- const: bchanrt
- const: rchanrt
- const: tchanrt
- const: ringrt
+ - const: ring
+ - const: tchan
+ - const: rchan
+ - const: bchan
required:
- ti,sci-rm-range-bchan
@@ -184,7 +202,11 @@ allOf:
ti,sci-rm-range-bchan: false
reg:
- maxItems: 4
+ items:
+ - description: BCDMA Control /Status Registers region
+ - description: RX Channel Realtime Registers region
+ - description: TX Channel Realtime Registers region
+ - description: Ring Realtime Registers region
reg-names:
items:
@@ -220,8 +242,13 @@ examples:
<0x0 0x4c000000 0x0 0x20000>,
<0x0 0x4a820000 0x0 0x20000>,
<0x0 0x4aa40000 0x0 0x20000>,
- <0x0 0x4bc00000 0x0 0x100000>;
- reg-names = "gcfg", "bchanrt", "rchanrt", "tchanrt", "ringrt";
+ <0x0 0x4bc00000 0x0 0x100000>,
+ <0x0 0x48600000 0x0 0x8000>,
+ <0x0 0x484a4000 0x0 0x2000>,
+ <0x0 0x484c2000 0x0 0x2000>,
+ <0x0 0x48420000 0x0 0x2000>;
+ reg-names = "gcfg", "bchanrt", "rchanrt", "tchanrt", "ringrt",
+ "ring", "tchan", "rchan", "bchan";
msi-parent = <&inta_main_dmss>;
#dma-cells = <3>;
diff --git a/Documentation/devicetree/bindings/dma/ti/k3-pktdma.yaml b/Documentation/devicetree/bindings/dma/ti/k3-pktdma.yaml
index a69f62f854d8c3e8d4084c4aa2c6e0f6cccd5819..11e064c029946641c8aacf5e49eb61b41477658d 100644
--- a/Documentation/devicetree/bindings/dma/ti/k3-pktdma.yaml
+++ b/Documentation/devicetree/bindings/dma/ti/k3-pktdma.yaml
@@ -45,14 +45,28 @@ properties:
The second cell is the ASEL value for the channel
reg:
- maxItems: 4
+ minItems: 4
+ items:
+ - description: Packet DMA Control /Status Registers region
+ - description: RX Channel Realtime Registers region
+ - description: TX Channel Realtime Registers region
+ - description: Ring Realtime Registers region
+ - description: Ring Configuration Registers region
+ - description: TX Configuration Registers region
+ - description: RX Configuration Registers region
+ - description: RX Flow Configuration Registers region
reg-names:
+ minItems: 4
items:
- const: gcfg
- const: rchanrt
- const: tchanrt
- const: ringrt
+ - const: ring
+ - const: tchan
+ - const: rchan
+ - const: rflow
msi-parent: true
@@ -136,8 +150,14 @@ examples:
reg = <0x0 0x485c0000 0x0 0x100>,
<0x0 0x4a800000 0x0 0x20000>,
<0x0 0x4aa00000 0x0 0x40000>,
- <0x0 0x4b800000 0x0 0x400000>;
- reg-names = "gcfg", "rchanrt", "tchanrt", "ringrt";
+ <0x0 0x4b800000 0x0 0x400000>,
+ <0x0 0x485e0000 0x0 0x20000>,
+ <0x0 0x484a0000 0x0 0x4000>,
+ <0x0 0x484c0000 0x0 0x2000>,
+ <0x0 0x48430000 0x0 0x4000>;
+ reg-names = "gcfg", "rchanrt", "tchanrt", "ringrt",
+ "ring", "tchan", "rchan", "rflow";
+
msi-parent = <&inta_main_dmss>;
#dma-cells = <2>;
diff --git a/Documentation/devicetree/bindings/dma/ti/k3-udma.yaml b/Documentation/devicetree/bindings/dma/ti/k3-udma.yaml
index 22f6c5e2f7f4b94fe92c477e8a4336b111896e50..b18cf2bfdb5b14789b0a9ff405d57cb717802ad3 100644
--- a/Documentation/devicetree/bindings/dma/ti/k3-udma.yaml
+++ b/Documentation/devicetree/bindings/dma/ti/k3-udma.yaml
@@ -69,13 +69,24 @@ properties:
- ti,j721e-navss-mcu-udmap
reg:
- maxItems: 3
+ minItems: 3
+ items:
+ - description: UDMA-P Control /Status Registers region
+ - description: RX Channel Realtime Registers region
+ - description: TX Channel Realtime Registers region
+ - description: TX Configuration Registers region
+ - description: RX Configuration Registers region
+ - description: RX Flow Configuration Registers region
reg-names:
+ minItems: 3
items:
- const: gcfg
- const: rchanrt
- const: tchanrt
+ - const: tchan
+ - const: rchan
+ - const: rflow
msi-parent: true
@@ -158,8 +169,11 @@ examples:
compatible = "ti,am654-navss-main-udmap";
reg = <0x0 0x31150000 0x0 0x100>,
<0x0 0x34000000 0x0 0x100000>,
- <0x0 0x35000000 0x0 0x100000>;
- reg-names = "gcfg", "rchanrt", "tchanrt";
+ <0x0 0x35000000 0x0 0x100000>,
+ <0x0 0x30b00000 0x0 0x20000>,
+ <0x0 0x30c00000 0x0 0x8000>,
+ <0x0 0x30d00000 0x0 0x4000>;
+ reg-names = "gcfg", "rchanrt", "tchanrt", "tchan", "rchan", "rflow";
#dma-cells = <1>;
ti,ringacc = <&ringacc>;
diff --git a/Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml b/Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml
index 00b570c82903974cbaeaba09406ff0581c61d8e0..60441f0c5d7211f24b5fa536425b351767040a2d 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml
@@ -11,8 +11,13 @@ maintainers:
description: |
This interrupt controller is found in the Loongson-3 family of chips and
- Loongson-2K1000 chip, as the primary package interrupt controller which
+ Loongson-2K series chips, as the primary package interrupt controller which
can route local I/O interrupt to interrupt lines of cores.
+ Be aware of the following points.
+ 1.The Loongson-2K0500 is a single core CPU;
+ 2.The Loongson-2K0500/2K1000 has 64 device interrupt sources as inputs, so we
+ need to define two nodes in dts{i} to describe the "0-31" and "32-61" interrupt
+ sources respectively.
allOf:
- $ref: /schemas/interrupt-controller.yaml#
@@ -33,6 +38,7 @@ properties:
- const: main
- const: isr0
- const: isr1
+ minItems: 2
interrupt-controller: true
@@ -45,11 +51,9 @@ properties:
interrupt-names:
description: List of names for the parent interrupts.
items:
- - const: int0
- - const: int1
- - const: int2
- - const: int3
+ pattern: int[0-3]
minItems: 1
+ maxItems: 4
'#interrupt-cells':
const: 2
@@ -69,6 +73,7 @@ required:
- compatible
- reg
- interrupts
+ - interrupt-names
- interrupt-controller
- '#interrupt-cells'
- loongson,parent_int_map
@@ -86,7 +91,8 @@ if:
then:
properties:
reg:
- minItems: 3
+ minItems: 2
+ maxItems: 3
required:
- reg-names
diff --git a/Documentation/devicetree/bindings/loongarch/cpus.yaml b/Documentation/devicetree/bindings/loongarch/cpus.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..f175872995e117b18b3cc141d7044d1a390e0f06
--- /dev/null
+++ b/Documentation/devicetree/bindings/loongarch/cpus.yaml
@@ -0,0 +1,61 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/loongarch/cpus.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: LoongArch CPUs
+
+maintainers:
+ - Binbin Zhou
+
+description:
+ This document describes the list of LoongArch CPU cores that support FDT,
+ it describe the layout of CPUs in a system through the "cpus" node.
+
+allOf:
+ - $ref: /schemas/cpu.yaml#
+
+properties:
+ compatible:
+ enum:
+ - loongson,la264
+ - loongson,la364
+
+ reg:
+ maxItems: 1
+
+ clocks:
+ maxItems: 1
+
+required:
+ - compatible
+ - reg
+ - clocks
+
+unevaluatedProperties: false
+
+examples:
+ - |
+ #include
+
+ cpus {
+ #size-cells = <0>;
+ #address-cells = <1>;
+
+ cpu@0 {
+ compatible = "loongson,la264";
+ device_type = "cpu";
+ reg = <0>;
+ clocks = <&clk LOONGSON2_NODE_CLK>;
+ };
+
+ cpu@1 {
+ compatible = "loongson,la264";
+ device_type = "cpu";
+ reg = <1>;
+ clocks = <&clk LOONGSON2_NODE_CLK>;
+ };
+ };
+
+...
diff --git a/Documentation/devicetree/bindings/loongarch/loongson.yaml b/Documentation/devicetree/bindings/loongarch/loongson.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..e1a4a97b7576c9401e746e6d7a06456282b5287a
--- /dev/null
+++ b/Documentation/devicetree/bindings/loongarch/loongson.yaml
@@ -0,0 +1,34 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/loongarch/loongson.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Loongson SoC-based boards
+
+maintainers:
+ - Binbin Zhou
+
+properties:
+ $nodename:
+ const: '/'
+ compatible:
+ oneOf:
+ - description: Loongson-2K0500 processor based boards
+ items:
+ - const: loongson,ls2k0500-ref
+ - const: loongson,ls2k0500
+
+ - description: Loongson-2K1000 processor based boards
+ items:
+ - const: loongson,ls2k1000-ref
+ - const: loongson,ls2k1000
+
+ - description: Loongson-2K2000 processor based boards
+ items:
+ - const: loongson,ls2k2000-ref
+ - const: loongson,ls2k2000
+
+additionalProperties: true
+
+...
diff --git a/Documentation/devicetree/bindings/power/reset/nvmem-reboot-mode.yaml b/Documentation/devicetree/bindings/power/reset/nvmem-reboot-mode.yaml
index 14a262bcbf7cd21ebf62ee02f738bf82cbde80e1..627f8a6078c299e32e4bc7597509a6ef52d119d7 100644
--- a/Documentation/devicetree/bindings/power/reset/nvmem-reboot-mode.yaml
+++ b/Documentation/devicetree/bindings/power/reset/nvmem-reboot-mode.yaml
@@ -28,17 +28,15 @@ properties:
items:
- const: reboot-mode
-patternProperties:
- "^mode-.+":
- $ref: /schemas/types.yaml#/definitions/uint32
- description: Vendor-specific mode value written to the mode register
+allOf:
+ - $ref: reboot-mode.yaml#
required:
- compatible
- nvmem-cells
- nvmem-cell-names
-additionalProperties: false
+unevaluatedProperties: false
examples:
- |
diff --git a/Documentation/devicetree/bindings/power/reset/qcom,pon.yaml b/Documentation/devicetree/bindings/power/reset/qcom,pon.yaml
index 5e460128b0d10911a541c959a9581efcb8b4d393..fc8105a7b9b268df5cb08ad32cde26c50ea955ce 100644
--- a/Documentation/devicetree/bindings/power/reset/qcom,pon.yaml
+++ b/Documentation/devicetree/bindings/power/reset/qcom,pon.yaml
@@ -111,21 +111,24 @@ examples:
#include
#include
#include
- spmi_bus: spmi@c440000 {
+
+ spmi@c440000 {
reg = <0x0c440000 0x1100>;
#address-cells = <2>;
#size-cells = <0>;
- pmk8350: pmic@0 {
+
+ pmic@0 {
reg = <0x0 SPMI_USID>;
#address-cells = <1>;
#size-cells = <0>;
- pmk8350_pon: pon_hlos@1300 {
- reg = <0x1300>;
+
+ pon@800 {
compatible = "qcom,pm8998-pon";
+ reg = <0x800>;
pwrkey {
compatible = "qcom,pm8941-pwrkey";
- interrupts = < 0x0 0x8 0 IRQ_TYPE_EDGE_BOTH >;
+ interrupts = <0x0 0x8 0 IRQ_TYPE_EDGE_BOTH>;
debounce = <15625>;
bias-pull-up;
linux,code = ;
diff --git a/Documentation/devicetree/bindings/power/reset/syscon-reboot-mode.yaml b/Documentation/devicetree/bindings/power/reset/syscon-reboot-mode.yaml
index 9b1ffceefe3dec86250dc235f92545bb123ea3cf..b6acff199cdecea08c1243ed5e8ad71240d65e9a 100644
--- a/Documentation/devicetree/bindings/power/reset/syscon-reboot-mode.yaml
+++ b/Documentation/devicetree/bindings/power/reset/syscon-reboot-mode.yaml
@@ -29,12 +29,10 @@ properties:
$ref: /schemas/types.yaml#/definitions/uint32
description: Offset in the register map for the mode register (in bytes)
-patternProperties:
- "^mode-.+":
- $ref: /schemas/types.yaml#/definitions/uint32
- description: Vendor-specific mode value written to the mode register
+allOf:
+ - $ref: reboot-mode.yaml#
-additionalProperties: false
+unevaluatedProperties: false
required:
- compatible
diff --git a/Documentation/devicetree/bindings/power/reset/xlnx,zynqmp-power.yaml b/Documentation/devicetree/bindings/power/reset/xlnx,zynqmp-power.yaml
index 45792e216981a99de457cc99ea2d8f2dfd130136..799831636194f50ffdb139bd146d8905802bd474 100644
--- a/Documentation/devicetree/bindings/power/reset/xlnx,zynqmp-power.yaml
+++ b/Documentation/devicetree/bindings/power/reset/xlnx,zynqmp-power.yaml
@@ -57,7 +57,7 @@ examples:
firmware {
zynqmp-firmware {
- zynqmp-power {
+ power-management {
compatible = "xlnx,zynqmp-power";
interrupts = <0 35 4>;
};
@@ -70,7 +70,7 @@ examples:
firmware {
zynqmp-firmware {
- zynqmp-power {
+ power-management {
compatible = "xlnx,zynqmp-power";
interrupt-parent = <&gic>;
interrupts = <0 35 4>;
diff --git a/Documentation/devicetree/bindings/power/supply/bq24190.yaml b/Documentation/devicetree/bindings/power/supply/bq24190.yaml
index d3ebc9de8c0b49734cb5ce2b138a2d4b67bed7f9..131b7e57d22f46d28a9501c5641fd3c03b7e6ca0 100644
--- a/Documentation/devicetree/bindings/power/supply/bq24190.yaml
+++ b/Documentation/devicetree/bindings/power/supply/bq24190.yaml
@@ -20,6 +20,7 @@ properties:
- ti,bq24192
- ti,bq24192i
- ti,bq24196
+ - ti,bq24296
reg:
maxItems: 1
diff --git a/Documentation/devicetree/bindings/riscv/cpus.yaml b/Documentation/devicetree/bindings/riscv/cpus.yaml
index 23646b684ea279b1962e555736683c906135f569..9d8670c00e3b3bdea5d2196b98538d97465abf0d 100644
--- a/Documentation/devicetree/bindings/riscv/cpus.yaml
+++ b/Documentation/devicetree/bindings/riscv/cpus.yaml
@@ -63,8 +63,8 @@ properties:
mmu-type:
description:
- Identifies the MMU address translation mode used on this
- hart. These values originate from the RISC-V Privileged
+ Identifies the largest MMU address translation mode supported by
+ this hart. These values originate from the RISC-V Privileged
Specification document, available from
https://riscv.org/specifications/
$ref: /schemas/types.yaml#/definitions/string
@@ -80,6 +80,11 @@ properties:
description:
The blocksize in bytes for the Zicbom cache operations.
+ riscv,cbop-block-size:
+ $ref: /schemas/types.yaml#/definitions/uint32
+ description:
+ The blocksize in bytes for the Zicbop cache operations.
+
riscv,cboz-block-size:
$ref: /schemas/types.yaml#/definitions/uint32
description:
diff --git a/Documentation/devicetree/bindings/riscv/extensions.yaml b/Documentation/devicetree/bindings/riscv/extensions.yaml
index 27beedb9819879180412fbd5bea753ef4a43df34..63d81dc895e5ce4c08715ce1d6bf0958a757ca86 100644
--- a/Documentation/devicetree/bindings/riscv/extensions.yaml
+++ b/Documentation/devicetree/bindings/riscv/extensions.yaml
@@ -48,7 +48,7 @@ properties:
insensitive, letters in the riscv,isa string must be all
lowercase.
$ref: /schemas/types.yaml#/definitions/string
- pattern: ^rv(?:64|32)imaf?d?q?c?b?k?j?p?v?h?(?:[hsxz](?:[a-z])+)?(?:_[hsxz](?:[a-z])+)*$
+ pattern: ^rv(?:64|32)imaf?d?q?c?b?k?j?p?v?h?(?:[hsxz](?:[0-9a-z])+)?(?:_[hsxz](?:[0-9a-z])+)*$
deprecated: true
riscv,isa-base:
diff --git a/Documentation/devicetree/bindings/sound/tas2562.yaml b/Documentation/devicetree/bindings/sound/tas2562.yaml
index f01c0dde0cf740e6ff9d500ddedb1e27d320f919..d28c102c0ce7f0fe94577e45b54daa7496331e7f 100644
--- a/Documentation/devicetree/bindings/sound/tas2562.yaml
+++ b/Documentation/devicetree/bindings/sound/tas2562.yaml
@@ -18,7 +18,6 @@ description: |
Specifications about the audio amplifier can be found at:
https://www.ti.com/lit/gpn/tas2562
- https://www.ti.com/lit/gpn/tas2563
https://www.ti.com/lit/gpn/tas2564
https://www.ti.com/lit/gpn/tas2110
@@ -29,7 +28,6 @@ properties:
compatible:
enum:
- ti,tas2562
- - ti,tas2563
- ti,tas2564
- ti,tas2110
diff --git a/Documentation/devicetree/bindings/sound/ti,tas2781.yaml b/Documentation/devicetree/bindings/sound/ti,tas2781.yaml
index a69e6c223308e637de51d512cb18f210441dcc9e..9762386892495149c00259c59be3e04a3a09d2c6 100644
--- a/Documentation/devicetree/bindings/sound/ti,tas2781.yaml
+++ b/Documentation/devicetree/bindings/sound/ti,tas2781.yaml
@@ -5,36 +5,46 @@
$id: http://devicetree.org/schemas/sound/ti,tas2781.yaml#
$schema: http://devicetree.org/meta-schemas/core.yaml#
-title: Texas Instruments TAS2781 SmartAMP
+title: Texas Instruments TAS2563/TAS2781 SmartAMP
maintainers:
- Shenghao Ding
-description:
- The TAS2781 is a mono, digital input Class-D audio amplifier
- optimized for efficiently driving high peak power into small
- loudspeakers. An integrated on-chip DSP supports Texas Instruments
- Smart Amp speaker protection algorithm. The integrated speaker
- voltage and current sense provides for real time
+description: |
+ The TAS2563/TAS2781 is a mono, digital input Class-D audio
+ amplifier optimized for efficiently driving high peak power into
+ small loudspeakers. An integrated on-chip DSP supports Texas
+ Instruments Smart Amp speaker protection algorithm. The
+ integrated speaker voltage and current sense provides for real time
monitoring of loudspeaker behavior.
-allOf:
- - $ref: dai-common.yaml#
+ Specifications about the audio amplifier can be found at:
+ https://www.ti.com/lit/gpn/tas2563
+ https://www.ti.com/lit/gpn/tas2781
properties:
compatible:
- enum:
- - ti,tas2781
+ description: |
+ ti,tas2563: 6.1-W Boosted Class-D Audio Amplifier With Integrated
+ DSP and IV Sense, 16/20/24/32bit stereo I2S or multichannel TDM.
+
+ ti,tas2781: 24-V Class-D Amplifier with Real Time Integrated Speaker
+ Protection and Audio Processing, 16/20/24/32bit stereo I2S or
+ multichannel TDM.
+ oneOf:
+ - items:
+ - enum:
+ - ti,tas2563
+ - const: ti,tas2781
+ - enum:
+ - ti,tas2781
reg:
description:
- I2C address, in multiple tas2781s case, all the i2c address
+ I2C address, in multiple-AMP case, all the i2c address
aggregate as one Audio Device to support multiple audio slots.
maxItems: 8
minItems: 1
- items:
- minimum: 0x38
- maximum: 0x3f
reset-gpios:
maxItems: 1
@@ -49,6 +59,44 @@ required:
- compatible
- reg
+allOf:
+ - $ref: dai-common.yaml#
+ - if:
+ properties:
+ compatible:
+ contains:
+ enum:
+ - ti,tas2563
+ then:
+ properties:
+ reg:
+ description:
+ I2C address, in multiple-AMP case, all the i2c address
+ aggregate as one Audio Device to support multiple audio slots.
+ maxItems: 4
+ minItems: 1
+ items:
+ minimum: 0x4c
+ maximum: 0x4f
+
+ - if:
+ properties:
+ compatible:
+ contains:
+ enum:
+ - ti,tas2781
+ then:
+ properties:
+ reg:
+ description:
+ I2C address, in multiple-AMP case, all the i2c address
+ aggregate as one Audio Device to support multiple audio slots.
+ maxItems: 8
+ minItems: 1
+ items:
+ minimum: 0x38
+ maximum: 0x3f
+
additionalProperties: false
examples:
diff --git a/Documentation/devicetree/bindings/timer/sifive,clint.yaml b/Documentation/devicetree/bindings/timer/sifive,clint.yaml
index 4b6c20fc819434883fc68ba79c153f67ac807344..fced6f2d8ecbb35955e3800f19d58980b792a764 100644
--- a/Documentation/devicetree/bindings/timer/sifive,clint.yaml
+++ b/Documentation/devicetree/bindings/timer/sifive,clint.yaml
@@ -33,6 +33,7 @@ properties:
- sifive,fu540-c000-clint # SiFive FU540
- starfive,jh7100-clint # StarFive JH7100
- starfive,jh7110-clint # StarFive JH7110
+ - starfive,jh8100-clint # StarFive JH8100
- const: sifive,clint0 # SiFive CLINT v0 IP block
- items:
- enum:
diff --git a/Documentation/devicetree/bindings/timer/thead,c900-aclint-mtimer.yaml b/Documentation/devicetree/bindings/timer/thead,c900-aclint-mtimer.yaml
index fbd235650e52cca3dc3e43792e0c730aab65699c..2e92bcdeb423abeca98da6868d5a116615c13bbc 100644
--- a/Documentation/devicetree/bindings/timer/thead,c900-aclint-mtimer.yaml
+++ b/Documentation/devicetree/bindings/timer/thead,c900-aclint-mtimer.yaml
@@ -17,7 +17,12 @@ properties:
- const: thead,c900-aclint-mtimer
reg:
- maxItems: 1
+ items:
+ - description: MTIMECMP Registers
+
+ reg-names:
+ items:
+ - const: mtimecmp
interrupts-extended:
minItems: 1
@@ -28,6 +33,7 @@ additionalProperties: false
required:
- compatible
- reg
+ - reg-names
- interrupts-extended
examples:
@@ -39,5 +45,6 @@ examples:
<&cpu3intc 7>,
<&cpu4intc 7>;
reg = <0xac000000 0x00010000>;
+ reg-names = "mtimecmp";
};
...
diff --git a/Documentation/features/vm/TLB/arch-support.txt b/Documentation/features/vm/TLB/arch-support.txt
index 8fd22073a847e9d1bbed3ccc5b9b59a5e71db300..d222bd3ee7495b86f711056aef5ccf5a180c5e20 100644
--- a/Documentation/features/vm/TLB/arch-support.txt
+++ b/Documentation/features/vm/TLB/arch-support.txt
@@ -20,7 +20,7 @@
| openrisc: | .. |
| parisc: | TODO |
| powerpc: | TODO |
- | riscv: | TODO |
+ | riscv: | ok |
| s390: | TODO |
| sh: | TODO |
| sparc: | TODO |
diff --git a/Documentation/filesystems/netfs_library.rst b/Documentation/filesystems/netfs_library.rst
index 48b95d04f72d5a25df0de37ac87a52d8f7471998..4cc657d743f7f3b24b9a3a15efd9608ee5775554 100644
--- a/Documentation/filesystems/netfs_library.rst
+++ b/Documentation/filesystems/netfs_library.rst
@@ -295,7 +295,6 @@ through which it can issue requests and negotiate::
struct netfs_request_ops {
void (*init_request)(struct netfs_io_request *rreq, struct file *file);
void (*free_request)(struct netfs_io_request *rreq);
- int (*begin_cache_operation)(struct netfs_io_request *rreq);
void (*expand_readahead)(struct netfs_io_request *rreq);
bool (*clamp_length)(struct netfs_io_subrequest *subreq);
void (*issue_read)(struct netfs_io_subrequest *subreq);
@@ -317,20 +316,6 @@ The operations are as follows:
[Optional] This is called as the request is being deallocated so that the
filesystem can clean up any state it has attached there.
- * ``begin_cache_operation()``
-
- [Optional] This is called to ask the network filesystem to call into the
- cache (if present) to initialise the caching state for this read. The netfs
- library module cannot access the cache directly, so the cache should call
- something like fscache_begin_read_operation() to do this.
-
- The cache gets to store its state in ->cache_resources and must set a table
- of operations of its own there (though of a different type).
-
- This should return 0 on success and an error code otherwise. If an error is
- reported, the operation may proceed anyway, just without local caching (only
- out of memory and interruption errors cause failure here).
-
* ``expand_readahead()``
[Optional] This is called to allow the filesystem to expand the size of a
@@ -460,14 +445,14 @@ When implementing a local cache to be used by the read helpers, two things are
required: some way for the network filesystem to initialise the caching for a
read request and a table of operations for the helpers to call.
-The network filesystem's ->begin_cache_operation() method is called to set up a
-cache and this must call into the cache to do the work. If using fscache, for
-example, the cache would call::
+To begin a cache operation on an fscache object, the following function is
+called::
int fscache_begin_read_operation(struct netfs_io_request *rreq,
struct fscache_cookie *cookie);
-passing in the request pointer and the cookie corresponding to the file.
+passing in the request pointer and the cookie corresponding to the file. This
+fills in the cache resources mentioned below.
The netfs_io_request object contains a place for the cache to hang its
state::
diff --git a/Documentation/filesystems/overlayfs.rst b/Documentation/filesystems/overlayfs.rst
index 1c244866041a3cb985568ce5f19e67d947eed5e6..16551440144183c58517fe27e750233619ebf89d 100644
--- a/Documentation/filesystems/overlayfs.rst
+++ b/Documentation/filesystems/overlayfs.rst
@@ -145,7 +145,9 @@ filesystem, an overlay filesystem needs to record in the upper filesystem
that files have been removed. This is done using whiteouts and opaque
directories (non-directories are always opaque).
-A whiteout is created as a character device with 0/0 device number.
+A whiteout is created as a character device with 0/0 device number or
+as a zero-size regular file with the xattr "trusted.overlay.whiteout".
+
When a whiteout is found in the upper level of a merged directory, any
matching name in the lower level is ignored, and the whiteout itself
is also hidden.
@@ -154,6 +156,13 @@ A directory is made opaque by setting the xattr "trusted.overlay.opaque"
to "y". Where the upper filesystem contains an opaque directory, any
directory in the lower filesystem with the same name is ignored.
+An opaque directory should not conntain any whiteouts, because they do not
+serve any purpose. A merge directory containing regular files with the xattr
+"trusted.overlay.whiteout", should be additionally marked by setting the xattr
+"trusted.overlay.opaque" to "x" on the merge directory itself.
+This is needed to avoid the overhead of checking the "trusted.overlay.whiteout"
+on all entries during readdir in the common case.
+
readdir
-------
@@ -534,8 +543,9 @@ A lower dir with a regular whiteout will always be handled by the overlayfs
mount, so to support storing an effective whiteout file in an overlayfs mount an
alternative form of whiteout is supported. This form is a regular, zero-size
file with the "overlay.whiteout" xattr set, inside a directory with the
-"overlay.whiteouts" xattr set. Such whiteouts are never created by overlayfs,
-but can be used by userspace tools (like containers) that generate lower layers.
+"overlay.opaque" xattr set to "x" (see `whiteouts and opaque directories`_).
+These alternative whiteouts are never created by overlayfs, but can be used by
+userspace tools (like containers) that generate lower layers.
These alternative whiteouts can be escaped using the standard xattr escape
mechanism in order to properly nest to any depth.
diff --git a/Documentation/filesystems/smb/ksmbd.rst b/Documentation/filesystems/smb/ksmbd.rst
index 7bed96d794fc2656d3bb9d69cbca3feef97ea6c8..6b30e43a0d11f49959d700e38fbfe115d71fd40c 100644
--- a/Documentation/filesystems/smb/ksmbd.rst
+++ b/Documentation/filesystems/smb/ksmbd.rst
@@ -73,15 +73,14 @@ Auto Negotiation Supported.
Compound Request Supported.
Oplock Cache Mechanism Supported.
SMB2 leases(v1 lease) Supported.
-Directory leases(v2 lease) Planned for future.
+Directory leases(v2 lease) Supported.
Multi-credits Supported.
NTLM/NTLMv2 Supported.
HMAC-SHA256 Signing Supported.
Secure negotiate Supported.
Signing Update Supported.
Pre-authentication integrity Supported.
-SMB3 encryption(CCM, GCM) Supported. (CCM and GCM128 supported, GCM256 in
- progress)
+SMB3 encryption(CCM, GCM) Supported. (CCM/GCM128 and CCM/GCM256 supported)
SMB direct(RDMA) Supported.
SMB3 Multi-channel Partially Supported. Planned to implement
replay/retry mechanisms for future.
@@ -112,6 +111,10 @@ DCE/RPC support Partially Supported. a few calls(NetShareEnumAll,
for Witness protocol e.g.)
ksmbd/nfsd interoperability Planned for future. The features that ksmbd
support are Leases, Notify, ACLs and Share modes.
+SMB3.1.1 Compression Planned for future.
+SMB3.1.1 over QUIC Planned for future.
+Signing/Encryption over RDMA Planned for future.
+SMB3.1.1 GMAC signing support Planned for future.
============================== =================================================
diff --git a/Documentation/process/4.Coding.rst b/Documentation/process/4.Coding.rst
index 1f0d81f44e14b25981dbb8c65c972fa9f20b55ce..c2046dec0c2f4065d81953e4164e706cb73d3d2c 100644
--- a/Documentation/process/4.Coding.rst
+++ b/Documentation/process/4.Coding.rst
@@ -66,6 +66,10 @@ for aligning variables/macros, for reflowing text and other similar tasks.
See the file :ref:`Documentation/process/clang-format.rst `
for more details.
+Some basic editor settings, such as indentation and line endings, will be
+set automatically if you are using an editor that is compatible with
+EditorConfig. See the official EditorConfig website for more information:
+https://editorconfig.org/
Abstraction layers
******************
diff --git a/Documentation/process/coding-style.rst b/Documentation/process/coding-style.rst
index 6db37a46d3059ee8e3fe6c3ee80711b6bff26e0d..c48382c6b47746f57a090d7af838916a419ff481 100644
--- a/Documentation/process/coding-style.rst
+++ b/Documentation/process/coding-style.rst
@@ -735,6 +735,10 @@ for aligning variables/macros, for reflowing text and other similar tasks.
See the file :ref:`Documentation/process/clang-format.rst `
for more details.
+Some basic editor settings, such as indentation and line endings, will be
+set automatically if you are using an editor that is compatible with
+EditorConfig. See the official EditorConfig website for more information:
+https://editorconfig.org/
10) Kconfig configuration files
-------------------------------
diff --git a/Documentation/rust/arch-support.rst b/Documentation/rust/arch-support.rst
index b91e9ef4d0c21e45a4beb27eb8ac9f32a4d6669a..73203ba1e9011e3a5eb5d58f598f00f34b4ece80 100644
--- a/Documentation/rust/arch-support.rst
+++ b/Documentation/rust/arch-support.rst
@@ -12,10 +12,11 @@ which uses ``libclang``.
Below is a general summary of architectures that currently work. Level of
support corresponds to ``S`` values in the ``MAINTAINERS`` file.
-============ ================ ==============================================
-Architecture Level of support Constraints
-============ ================ ==============================================
-``um`` Maintained ``x86_64`` only.
-``x86`` Maintained ``x86_64`` only.
-============ ================ ==============================================
+============= ================ ==============================================
+Architecture Level of support Constraints
+============= ================ ==============================================
+``loongarch`` Maintained -
+``um`` Maintained ``x86_64`` only.
+``x86`` Maintained ``x86_64`` only.
+============= ================ ==============================================
diff --git a/MAINTAINERS b/MAINTAINERS
index 8709c7cd3656ab505ba52acbf4976d68617cc3f6..92152ac346c8de27da07a57f695c170db771bc61 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3692,6 +3692,13 @@ L: bpf@vger.kernel.org
S: Supported
F: arch/arm64/net/
+BPF JIT for LOONGARCH
+M: Tiezhu Yang
+R: Hengqi Chen
+L: bpf@vger.kernel.org
+S: Maintained
+F: arch/loongarch/net/
+
BPF JIT for MIPS (32-BIT AND 64-BIT)
M: Johan Almbladh
M: Paul Burton
@@ -4540,7 +4547,7 @@ F: drivers/net/ieee802154/ca8210.c
CACHEFILES: FS-CACHE BACKEND FOR CACHING ON MOUNTED FILESYSTEMS
M: David Howells
-L: linux-cachefs@redhat.com (moderated for non-subscribers)
+L: netfs@lists.linux.dev
S: Supported
F: Documentation/filesystems/caching/cachefiles.rst
F: fs/cachefiles/
@@ -5229,7 +5236,7 @@ X: drivers/clk/clkdev.c
COMMON INTERNET FILE SYSTEM CLIENT (CIFS and SMB3)
M: Steve French
R: Paulo Alcantara (DFS, global name space)
-R: Ronnie Sahlberg (directory leases, sparse files)
+R: Ronnie Sahlberg (directory leases, sparse files)
R: Shyam Prasad N (multichannel)
R: Tom Talpey (RDMA, smbdirect)
L: linux-cifs@vger.kernel.org
@@ -7948,12 +7955,13 @@ L: rust-for-linux@vger.kernel.org
S: Maintained
F: rust/kernel/net/phy.rs
-EXEC & BINFMT API
+EXEC & BINFMT API, ELF
R: Eric Biederman
R: Kees Cook
L: linux-mm@kvack.org
S: Supported
T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/execve
+F: Documentation/userspace-api/ELF.rst
F: fs/*binfmt_*.c
F: fs/exec.c
F: include/linux/binfmts.h
@@ -8214,6 +8222,20 @@ S: Supported
F: fs/iomap/
F: include/linux/iomap.h
+FILESYSTEMS [NETFS LIBRARY]
+M: David Howells
+R: Jeff Layton
+L: netfs@lists.linux.dev
+L: linux-fsdevel@vger.kernel.org
+S: Supported
+F: Documentation/filesystems/caching/
+F: Documentation/filesystems/netfs_library.rst
+F: fs/netfs/
+F: include/linux/fscache*.h
+F: include/linux/netfs.h
+F: include/trace/events/fscache.h
+F: include/trace/events/netfs.h
+
FILESYSTEMS [STACKABLE]
M: Miklos Szeredi
M: Amir Goldstein
@@ -8659,14 +8681,6 @@ F: Documentation/power/freezing-of-tasks.rst
F: include/linux/freezer.h
F: kernel/freezer.c
-FS-CACHE: LOCAL CACHING FOR NETWORK FILESYSTEMS
-M: David Howells
-L: linux-cachefs@redhat.com (moderated for non-subscribers)
-S: Supported
-F: Documentation/filesystems/caching/
-F: fs/fscache/
-F: include/linux/fscache*.h
-
FSCRYPT: FILE SYSTEM LEVEL ENCRYPTION SUPPORT
M: Eric Biggers
M: Theodore Y. Ts'o
@@ -12627,6 +12641,13 @@ S: Maintained
F: Documentation/devicetree/bindings/gpio/loongson,ls-gpio.yaml
F: drivers/gpio/gpio-loongson-64bit.c
+LOONGSON LS2X APB DMA DRIVER
+M: Binbin Zhou
+L: dmaengine@vger.kernel.org
+S: Maintained
+F: Documentation/devicetree/bindings/dma/loongson,ls2x-apbdma.yaml
+F: drivers/dma/ls2x-apb-dma.c
+
LOONGSON LS2X I2C DRIVER
M: Binbin Zhou
L: linux-i2c@vger.kernel.org
@@ -17128,10 +17149,10 @@ PERFORMANCE EVENTS SUBSYSTEM
M: Peter Zijlstra
M: Ingo Molnar
M: Arnaldo Carvalho de Melo
+M: Namhyung Kim
R: Mark Rutland
R: Alexander Shishkin
R: Jiri Olsa
-R: Namhyung Kim
R: Ian Rogers
R: Adrian Hunter
L: linux-perf-users@vger.kernel.org
diff --git a/Makefile b/Makefile
index f1b2fd97727506a8a79d57fe10ff4603f3fd7db6..9f9b76d3a4b7de903e02fb6723dd03e9b31867d6 100644
--- a/Makefile
+++ b/Makefile
@@ -1,8 +1,8 @@
# SPDX-License-Identifier: GPL-2.0
VERSION = 6
-PATCHLEVEL = 7
+PATCHLEVEL = 8
SUBLEVEL = 0
-EXTRAVERSION =
+EXTRAVERSION = -rc1
NAME = Hurr durr I'ma ninja sloth
# *DOCUMENTATION*
@@ -155,6 +155,15 @@ endif
export KBUILD_EXTMOD
+# backward compatibility
+KBUILD_EXTRA_WARN ?= $(KBUILD_ENABLE_EXTRA_GCC_CHECKS)
+
+ifeq ("$(origin W)", "command line")
+ KBUILD_EXTRA_WARN := $(W)
+endif
+
+export KBUILD_EXTRA_WARN
+
# Kbuild will save output files in the current working directory.
# This does not need to match to the root of the kernel source tree.
#
@@ -181,14 +190,11 @@ ifeq ("$(origin O)", "command line")
endif
ifneq ($(KBUILD_OUTPUT),)
-# Make's built-in functions such as $(abspath ...), $(realpath ...) cannot
-# expand a shell special character '~'. We use a somewhat tedious way here.
-abs_objtree := $(shell mkdir -p $(KBUILD_OUTPUT) && cd $(KBUILD_OUTPUT) && pwd)
-$(if $(abs_objtree),, \
- $(error failed to create output directory "$(KBUILD_OUTPUT)"))
-
+# $(realpath ...) gets empty if the path does not exist. Run 'mkdir -p' first.
+$(shell mkdir -p "$(KBUILD_OUTPUT)")
# $(realpath ...) resolves symlinks
-abs_objtree := $(realpath $(abs_objtree))
+abs_objtree := $(realpath $(KBUILD_OUTPUT))
+$(if $(abs_objtree),,$(error failed to create output directory "$(KBUILD_OUTPUT)"))
endif # ifneq ($(KBUILD_OUTPUT),)
ifneq ($(words $(subst :, ,$(abs_srctree))), 1)
@@ -609,8 +615,6 @@ export KBUILD_AFLAGS_KERNEL KBUILD_CFLAGS_KERNEL KBUILD_RUSTFLAGS_KERNEL
export RCS_FIND_IGNORE := \( -name SCCS -o -name BitKeeper -o -name .svn -o \
-name CVS -o -name .pc -o -name .hg -o -name .git \) \
-prune -o
-export RCS_TAR_IGNORE := --exclude SCCS --exclude BitKeeper --exclude .svn \
- --exclude CVS --exclude .pc --exclude .hg --exclude .git
# ===========================================================================
# Rules shared between *config targets and build targets
@@ -982,6 +986,10 @@ NOSTDINC_FLAGS += -nostdinc
# perform bounds checking.
KBUILD_CFLAGS += $(call cc-option, -fstrict-flex-arrays=3)
+#Currently, disable -Wstringop-overflow for GCC 11, globally.
+KBUILD_CFLAGS-$(CONFIG_CC_NO_STRINGOP_OVERFLOW) += $(call cc-option, -Wno-stringop-overflow)
+KBUILD_CFLAGS-$(CONFIG_CC_STRINGOP_OVERFLOW) += $(call cc-option, -Wstringop-overflow)
+
# disable invalid "can't wrap" optimizations for signed / pointers
KBUILD_CFLAGS += -fno-strict-overflow
@@ -1662,6 +1670,7 @@ help:
@echo ' 1: warnings which may be relevant and do not occur too often'
@echo ' 2: warnings which occur quite often but may still be relevant'
@echo ' 3: more obscure warnings, can most likely be ignored'
+ @echo ' c: extra checks in the configuration stage (Kconfig)'
@echo ' e: warnings are being treated as errors'
@echo ' Multiple levels can be combined with W=12 or W=123'
@$(if $(dtstree), \
diff --git a/arch/arm/configs/mxs_defconfig b/arch/arm/configs/mxs_defconfig
index feb38a94c1a70a49c3d3d997957d493585bff54f..43bc1255a5db9f4ed8f65a98a69284e1439e44d2 100644
--- a/arch/arm/configs/mxs_defconfig
+++ b/arch/arm/configs/mxs_defconfig
@@ -138,7 +138,8 @@ CONFIG_PWM_MXS=y
CONFIG_NVMEM_MXS_OCOTP=y
CONFIG_EXT4_FS=y
# CONFIG_DNOTIFY is not set
-CONFIG_FSCACHE=m
+CONFIG_NETFS_SUPPORT=m
+CONFIG_FSCACHE=y
CONFIG_FSCACHE_STATS=y
CONFIG_CACHEFILES=m
CONFIG_VFAT_FS=y
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index ea01a2c43efaf6fd1fd1d19529d40279c4c91102..aa7c1d435139684d7b56f96f3f93945d331d64d6 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1039,8 +1039,12 @@ config ARM64_ERRATUM_2645198
If unsure, say Y.
+config ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD
+ bool
+
config ARM64_ERRATUM_2966298
bool "Cortex-A520: 2966298: workaround for speculatively executed unprivileged load"
+ select ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD
default y
help
This option adds the workaround for ARM Cortex-A520 erratum 2966298.
@@ -1052,6 +1056,20 @@ config ARM64_ERRATUM_2966298
If unsure, say Y.
+config ARM64_ERRATUM_3117295
+ bool "Cortex-A510: 3117295: workaround for speculatively executed unprivileged load"
+ select ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD
+ default y
+ help
+ This option adds the workaround for ARM Cortex-A510 erratum 3117295.
+
+ On an affected Cortex-A510 core, a speculatively executed unprivileged
+ load might leak data from a privileged level via a cache side channel.
+
+ Work around this problem by executing a TLBI before returning to EL0.
+
+ If unsure, say Y.
+
config CAVIUM_ERRATUM_22375
bool "Cavium erratum 22375, 24313"
default y
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 7b1975bf4b90e7a999de178140bc92aeb63f1c02..513787e4332993e18ec82db1a47f7814ca553d4c 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -760,32 +760,25 @@ alternative_endif
.endm
/*
- * Check whether preempt/bh-disabled asm code should yield as soon as
- * it is able. This is the case if we are currently running in task
- * context, and either a softirq is pending, or the TIF_NEED_RESCHED
- * flag is set and re-enabling preemption a single time would result in
- * a preempt count of zero. (Note that the TIF_NEED_RESCHED flag is
- * stored negated in the top word of the thread_info::preempt_count
+ * Check whether asm code should yield as soon as it is able. This is
+ * the case if we are currently running in task context, and the
+ * TIF_NEED_RESCHED flag is set. (Note that the TIF_NEED_RESCHED flag
+ * is stored negated in the top word of the thread_info::preempt_count
* field)
*/
- .macro cond_yield, lbl:req, tmp:req, tmp2:req
+ .macro cond_yield, lbl:req, tmp:req, tmp2
+#ifdef CONFIG_PREEMPT_VOLUNTARY
get_current_task \tmp
ldr \tmp, [\tmp, #TSK_TI_PREEMPT]
/*
* If we are serving a softirq, there is no point in yielding: the
* softirq will not be preempted no matter what we do, so we should
- * run to completion as quickly as we can.
+ * run to completion as quickly as we can. The preempt_count field will
+ * have BIT(SOFTIRQ_SHIFT) set in this case, so the zero check will
+ * catch this case too.
*/
- tbnz \tmp, #SOFTIRQ_SHIFT, .Lnoyield_\@
-#ifdef CONFIG_PREEMPTION
- sub \tmp, \tmp, #PREEMPT_DISABLE_OFFSET
cbz \tmp, \lbl
#endif
- adr_l \tmp, irq_stat + IRQ_CPUSTAT_SOFTIRQ_PENDING
- get_this_cpu_offset \tmp2
- ldr w\tmp, [\tmp, \tmp2]
- cbnz w\tmp, \lbl // yield on pending softirq in task context
-.Lnoyield_\@:
.endm
/*
diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h
index 50ce8b697ff361be7ee7fe571144b6a9e12ad374..e93548914c366f3476aea04c3bc35ff4b92c083d 100644
--- a/arch/arm64/include/asm/irq.h
+++ b/arch/arm64/include/asm/irq.h
@@ -4,6 +4,8 @@
#ifndef __ASSEMBLER__
+#include
+
#include
void arch_trigger_cpumask_backtrace(const cpumask_t *mask, int exclude_cpu);
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index d95b3d6b471a7d63957c47151fd6cb404ca0f4c7..e5d03a7039b4bf9cce893b1ea39712eef3e2f4ad 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -73,7 +73,13 @@ obj-$(CONFIG_ARM64_MTE) += mte.o
obj-y += vdso-wrap.o
obj-$(CONFIG_COMPAT_VDSO) += vdso32-wrap.o
obj-$(CONFIG_UNWIND_PATCH_PAC_INTO_SCS) += patch-scs.o
-CFLAGS_patch-scs.o += -mbranch-protection=none
+
+# We need to prevent the SCS patching code from patching itself. Using
+# -mbranch-protection=none here to avoid the patchable PAC opcodes from being
+# generated triggers an issue with full LTO on Clang, which stops emitting PAC
+# instructions altogether. So instead, omit the unwind tables used by the
+# patching code, so it will not be able to locate its own PAC instructions.
+CFLAGS_patch-scs.o += -fno-asynchronous-unwind-tables -fno-unwind-tables
# Force dependency (vdso*-wrap.S includes vdso.so through incbin)
$(obj)/vdso-wrap.o: $(obj)/vdso/vdso.so
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 5ff1942b04fcfd94e334b6b204f7f3885647c68d..5a7dbbe0ce639a8b7a74012c957b3c7335e8f160 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -117,8 +117,6 @@ int main(void)
DEFINE(DMA_FROM_DEVICE, DMA_FROM_DEVICE);
BLANK();
DEFINE(PREEMPT_DISABLE_OFFSET, PREEMPT_DISABLE_OFFSET);
- DEFINE(SOFTIRQ_SHIFT, SOFTIRQ_SHIFT);
- DEFINE(IRQ_CPUSTAT_SOFTIRQ_PENDING, offsetof(irq_cpustat_t, __softirq_pending));
BLANK();
DEFINE(CPU_BOOT_TASK, offsetof(struct secondary_data, task));
BLANK();
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index e29e0fea63fb626bea3abd2ad707b3eb08df7f5b..967c7c7a4e7db3db7e3d05a7637e8e7d13e0d273 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -416,6 +416,19 @@ static struct midr_range broken_aarch32_aes[] = {
};
#endif /* CONFIG_ARM64_WORKAROUND_TRBE_WRITE_OUT_OF_RANGE */
+#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD
+static const struct midr_range erratum_spec_unpriv_load_list[] = {
+#ifdef CONFIG_ARM64_ERRATUM_3117295
+ MIDR_ALL_VERSIONS(MIDR_CORTEX_A510),
+#endif
+#ifdef CONFIG_ARM64_ERRATUM_2966298
+ /* Cortex-A520 r0p0 to r0p1 */
+ MIDR_REV_RANGE(MIDR_CORTEX_A520, 0, 0, 1),
+#endif
+ {},
+};
+#endif
+
const struct arm64_cpu_capabilities arm64_errata[] = {
#ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE
{
@@ -713,12 +726,12 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
MIDR_FIXED(MIDR_CPU_VAR_REV(1,1), BIT(25)),
},
#endif
-#ifdef CONFIG_ARM64_ERRATUM_2966298
+#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD
{
- .desc = "ARM erratum 2966298",
- .capability = ARM64_WORKAROUND_2966298,
+ .desc = "ARM errata 2966298, 3117295",
+ .capability = ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD,
/* Cortex-A520 r0p0 - r0p1 */
- ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A520, 0, 0, 1),
+ ERRATA_MIDR_RANGE_LIST(erratum_spec_unpriv_load_list),
},
#endif
#ifdef CONFIG_AMPERE_ERRATUM_AC03_CPU_38
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index a6030913cd58c44f1ce5cd7077fe61dac02c86db..7ef0e127b149fcb68ce4aaf83e1403c0648f289f 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -428,16 +428,9 @@ alternative_else_nop_endif
ldp x28, x29, [sp, #16 * 14]
.if \el == 0
-alternative_if ARM64_WORKAROUND_2966298
- tlbi vale1, xzr
- dsb nsh
-alternative_else_nop_endif
-alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0
- ldr lr, [sp, #S_LR]
- add sp, sp, #PT_REGS_SIZE // restore sp
- eret
-alternative_else_nop_endif
#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+ alternative_insn "b .L_skip_tramp_exit_\@", nop, ARM64_UNMAP_KERNEL_AT_EL0
+
msr far_el1, x29
ldr_this_cpu x30, this_cpu_vector, x29
@@ -446,16 +439,26 @@ alternative_else_nop_endif
ldr lr, [sp, #S_LR] // restore x30
add sp, sp, #PT_REGS_SIZE // restore sp
br x29
+
+.L_skip_tramp_exit_\@:
#endif
- .else
+ .endif
+
ldr lr, [sp, #S_LR]
add sp, sp, #PT_REGS_SIZE // restore sp
+ .if \el == 0
+ /* This must be after the last explicit memory access */
+alternative_if ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD
+ tlbi vale1, xzr
+ dsb nsh
+alternative_else_nop_endif
+ .else
/* Ensure any device/NC reads complete */
alternative_insn nop, "dmb sy", ARM64_WORKAROUND_1508412
+ .endif
eret
- .endif
sb
.endm
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 505f389be3e0df09d5afa2c803a7e8b235d02e2a..a5dc6f764195847251dc25c196304cbef44d8850 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -898,10 +898,8 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type,
* allocate SVE now in case it is needed for use in streaming
* mode.
*/
- if (system_supports_sve()) {
- sve_free(task);
- sve_alloc(task, true);
- }
+ sve_free(task);
+ sve_alloc(task, true);
if (free_sme)
sme_free(task);
@@ -1219,8 +1217,10 @@ void fpsimd_release_task(struct task_struct *dead_task)
*/
void sme_alloc(struct task_struct *task, bool flush)
{
- if (task->thread.sme_state && flush) {
- memset(task->thread.sme_state, 0, sme_state_size(task));
+ if (task->thread.sme_state) {
+ if (flush)
+ memset(task->thread.sme_state, 0,
+ sme_state_size(task));
return;
}
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 09bb7fc7d3c2513b3bc8cb2e5545f8c31935e30a..dc6cf0e37194e428519d7d58524ad0f624f4bebb 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1108,12 +1108,13 @@ static int za_set(struct task_struct *target,
}
}
- /* Allocate/reinit ZA storage */
- sme_alloc(target, true);
- if (!target->thread.sme_state) {
- ret = -ENOMEM;
- goto out;
- }
+ /*
+ * Only flush the storage if PSTATE.ZA was not already set,
+ * otherwise preserve any existing data.
+ */
+ sme_alloc(target, !thread_za_enabled(&target->thread));
+ if (!target->thread.sme_state)
+ return -ENOMEM;
/* If there is no data then disable ZA */
if (!count) {
diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index 1e07d74d7a6c93baa2a01e7f63a5801c5fe3da0d..b912b1409fc09aaf08705b8d75b5d221ae0d020e 100644
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -84,7 +84,6 @@ WORKAROUND_2077057
WORKAROUND_2457168
WORKAROUND_2645198
WORKAROUND_2658417
-WORKAROUND_2966298
WORKAROUND_AMPERE_AC03_CPU_38
WORKAROUND_TRBE_OVERWRITE_FILL_MODE
WORKAROUND_TSB_FLUSH_FAILURE
@@ -100,3 +99,4 @@ WORKAROUND_NVIDIA_CARMEL_CNP
WORKAROUND_QCOM_FALKOR_E1003
WORKAROUND_REPEAT_TLBI
WORKAROUND_SPECULATIVE_AT
+WORKAROUND_SPECULATIVE_UNPRIV_LOAD
diff --git a/arch/csky/configs/defconfig b/arch/csky/configs/defconfig
index af722e4dfb47d8239c969b25834e9b231a9b4244..ff559e5162aa1cad8da170adc5d047672f849222 100644
--- a/arch/csky/configs/defconfig
+++ b/arch/csky/configs/defconfig
@@ -34,7 +34,8 @@ CONFIG_GENERIC_PHY=y
CONFIG_EXT4_FS=y
CONFIG_FANOTIFY=y
CONFIG_QUOTA=y
-CONFIG_FSCACHE=m
+CONFIG_NETFS_SUPPORT=m
+CONFIG_FSCACHE=y
CONFIG_FSCACHE_STATS=y
CONFIG_CACHEFILES=m
CONFIG_MSDOS_FS=y
diff --git a/arch/loongarch/Kbuild b/arch/loongarch/Kbuild
index beb8499dd8ed84330beecbcd61977df0aa3474f8..bfa21465d83afcd4908cc000e49a8c47aea0d165 100644
--- a/arch/loongarch/Kbuild
+++ b/arch/loongarch/Kbuild
@@ -4,6 +4,7 @@ obj-y += net/
obj-y += vdso/
obj-$(CONFIG_KVM) += kvm/
+obj-$(CONFIG_BUILTIN_DTB) += boot/dts/
# for cleaning
subdir- += boot
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 15d05dd2b7f3de828c2aedfec7aa7fd917ddb300..10959e6c3583255264aef0ea7de6e6477a003418 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -142,6 +142,7 @@ config LOONGARCH
select HAVE_REGS_AND_STACK_ACCESS_API
select HAVE_RETHOOK
select HAVE_RSEQ
+ select HAVE_RUST
select HAVE_SAMPLE_FTRACE_DIRECT
select HAVE_SAMPLE_FTRACE_DIRECT_MULTI
select HAVE_SETUP_PER_CPU_AREA if NUMA
@@ -376,6 +377,24 @@ config CMDLINE_FORCE
endchoice
+config BUILTIN_DTB
+ bool "Enable built-in dtb in kernel"
+ depends on OF
+ help
+ Some existing systems do not provide a canonical device tree to
+ the kernel at boot time. Let's provide a device tree table in the
+ kernel, keyed by the dts filename, containing the relevant DTBs.
+
+ Built-in DTBs are generic enough and can be used as references.
+
+config BUILTIN_DTB_NAME
+ string "Source file for built-in dtb"
+ depends on BUILTIN_DTB
+ help
+ Base name (without suffix, relative to arch/loongarch/boot/dts/)
+ for the DTS file that will be used to produce the DTB linked into
+ the kernel.
+
config DMI
bool "Enable DMI scanning"
select DMI_SCAN_MACHINE_NON_EFI_FALLBACK
@@ -577,6 +596,9 @@ config ARCH_SELECTS_CRASH_DUMP
depends on CRASH_DUMP
select RELOCATABLE
+config ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION
+ def_bool CRASH_CORE
+
config RELOCATABLE
bool "Relocatable kernel"
help
diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile
index 4ba8d67ddb097743be4e68493604579142eee2d5..983aa2b1629a69fe74c4c8358d094fbd424283b9 100644
--- a/arch/loongarch/Makefile
+++ b/arch/loongarch/Makefile
@@ -6,6 +6,7 @@
boot := arch/loongarch/boot
KBUILD_DEFCONFIG := loongson3_defconfig
+KBUILD_DTBS := dtbs
image-name-y := vmlinux
image-name-$(CONFIG_EFI_ZBOOT) := vmlinuz
@@ -81,8 +82,11 @@ KBUILD_AFLAGS_MODULE += -Wa,-mla-global-with-abs
KBUILD_CFLAGS_MODULE += -fplt -Wa,-mla-global-with-abs,-mla-local-with-abs
endif
+KBUILD_RUSTFLAGS_MODULE += -Crelocation-model=pic
+
ifeq ($(CONFIG_RELOCATABLE),y)
KBUILD_CFLAGS_KERNEL += -fPIE
+KBUILD_RUSTFLAGS_KERNEL += -Crelocation-model=pie
LDFLAGS_vmlinux += -static -pie --no-dynamic-linker -z notext $(call ld-option, --apply-dynamic-relocs)
endif
@@ -141,7 +145,7 @@ endif
vdso-install-y += arch/loongarch/vdso/vdso.so.dbg
-all: $(notdir $(KBUILD_IMAGE))
+all: $(notdir $(KBUILD_IMAGE)) $(KBUILD_DTBS)
vmlinuz.efi: vmlinux.efi
diff --git a/arch/loongarch/boot/dts/Makefile b/arch/loongarch/boot/dts/Makefile
index 5f1f55e911adf543ab5c113b06f81488ee984e59..747d0c3f63892926757b28fc29119069767e2310 100644
--- a/arch/loongarch/boot/dts/Makefile
+++ b/arch/loongarch/boot/dts/Makefile
@@ -1,4 +1,5 @@
# SPDX-License-Identifier: GPL-2.0-only
-dtstree := $(srctree)/$(src)
-dtb-y := $(patsubst $(dtstree)/%.dts,%.dtb, $(wildcard $(dtstree)/*.dts))
+dtb-y = loongson-2k0500-ref.dtb loongson-2k1000-ref.dtb loongson-2k2000-ref.dtb
+
+obj-$(CONFIG_BUILTIN_DTB) += $(addsuffix .dtb.o, $(CONFIG_BUILTIN_DTB_NAME))
diff --git a/arch/loongarch/boot/dts/loongson-2k0500-ref.dts b/arch/loongarch/boot/dts/loongson-2k0500-ref.dts
new file mode 100644
index 0000000000000000000000000000000000000000..b38071a4d0b023c7faf29935d3bb6d5e0c65ca76
--- /dev/null
+++ b/arch/loongarch/boot/dts/loongson-2k0500-ref.dts
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 Loongson Technology Corporation Limited
+ */
+
+/dts-v1/;
+
+#include "loongson-2k0500.dtsi"
+
+/ {
+ compatible = "loongson,ls2k0500-ref", "loongson,ls2k0500";
+ model = "Loongson-2K0500 Reference Board";
+
+ aliases {
+ ethernet0 = &gmac0;
+ ethernet1 = &gmac1;
+ serial0 = &uart0;
+ };
+
+ chosen {
+ stdout-path = "serial0:115200n8";
+ };
+
+ memory@200000 {
+ device_type = "memory";
+ reg = <0x0 0x00200000 0x0 0x0ee00000>,
+ <0x0 0x90000000 0x0 0x60000000>;
+ };
+
+ reserved-memory {
+ #address-cells = <2>;
+ #size-cells = <2>;
+ ranges;
+
+ linux,cma {
+ compatible = "shared-dma-pool";
+ reusable;
+ size = <0x0 0x2000000>;
+ linux,cma-default;
+ };
+ };
+};
+
+&gmac0 {
+ status = "okay";
+
+ phy-mode = "rgmii";
+ bus_id = <0x0>;
+};
+
+&gmac1 {
+ status = "okay";
+
+ phy-mode = "rgmii";
+ bus_id = <0x1>;
+};
+
+&i2c0 {
+ status = "okay";
+
+ #address-cells = <1>;
+ #size-cells = <0>;
+ eeprom@57{
+ compatible = "atmel,24c16";
+ reg = <0x57>;
+ pagesize = <16>;
+ };
+};
+
+&ehci0 {
+ status = "okay";
+};
+
+&ohci0 {
+ status = "okay";
+};
+
+&sata {
+ status = "okay";
+};
+
+&uart0 {
+ status = "okay";
+};
+
+&rtc0 {
+ status = "okay";
+};
diff --git a/arch/loongarch/boot/dts/loongson-2k0500.dtsi b/arch/loongarch/boot/dts/loongson-2k0500.dtsi
new file mode 100644
index 0000000000000000000000000000000000000000..444779c21034b5aecd2faa6129ff3dd0dd670fe1
--- /dev/null
+++ b/arch/loongarch/boot/dts/loongson-2k0500.dtsi
@@ -0,0 +1,266 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 Loongson Technology Corporation Limited
+ */
+
+/dts-v1/;
+
+#include
+
+/ {
+ #address-cells = <2>;
+ #size-cells = <2>;
+
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cpu0: cpu@0 {
+ compatible = "loongson,la264";
+ device_type = "cpu";
+ reg = <0x0>;
+ clocks = <&cpu_clk>;
+ };
+ };
+
+ cpu_clk: cpu-clk {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <500000000>;
+ };
+
+ cpuintc: interrupt-controller {
+ compatible = "loongson,cpu-interrupt-controller";
+ #interrupt-cells = <1>;
+ interrupt-controller;
+ };
+
+ bus@10000000 {
+ compatible = "simple-bus";
+ ranges = <0x0 0x10000000 0x0 0x10000000 0x0 0x10000000>,
+ <0x0 0x02000000 0x0 0x02000000 0x0 0x02000000>,
+ <0x0 0x20000000 0x0 0x20000000 0x0 0x10000000>,
+ <0x0 0x40000000 0x0 0x40000000 0x0 0x40000000>,
+ <0xfe 0x0 0xfe 0x0 0x0 0x40000000>;
+ #address-cells = <2>;
+ #size-cells = <2>;
+
+ isa@16400000 {
+ compatible = "isa";
+ #size-cells = <1>;
+ #address-cells = <2>;
+ ranges = <1 0x0 0x0 0x16400000 0x4000>;
+ };
+
+ liointc0: interrupt-controller@1fe11400 {
+ compatible = "loongson,liointc-2.0";
+ reg = <0x0 0x1fe11400 0x0 0x40>,
+ <0x0 0x1fe11040 0x0 0x8>;
+ reg-names = "main", "isr0";
+
+ interrupt-controller;
+ #interrupt-cells = <2>;
+ interrupt-parent = <&cpuintc>;
+ interrupts = <2>;
+ interrupt-names = "int0";
+
+ loongson,parent_int_map = <0xffffffff>, /* int0 */
+ <0x00000000>, /* int1 */
+ <0x00000000>, /* int2 */
+ <0x00000000>; /* int3 */
+ };
+
+ liointc1: interrupt-controller@1fe11440 {
+ compatible = "loongson,liointc-2.0";
+ reg = <0x0 0x1fe11440 0x0 0x40>,
+ <0x0 0x1fe11048 0x0 0x8>;
+ reg-names = "main", "isr0";
+
+ interrupt-controller;
+ #interrupt-cells = <2>;
+ interrupt-parent = <&cpuintc>;
+ interrupts = <4>;
+ interrupt-names = "int2";
+
+ loongson,parent_int_map = <0x00000000>, /* int0 */
+ <0x00000000>, /* int1 */
+ <0xffffffff>, /* int2 */
+ <0x00000000>; /* int3 */
+ };
+
+ eiointc: interrupt-controller@1fe11600 {
+ compatible = "loongson,ls2k0500-eiointc";
+ reg = <0x0 0x1fe11600 0x0 0xea00>;
+ interrupt-controller;
+ #interrupt-cells = <1>;
+ interrupt-parent = <&cpuintc>;
+ interrupts = <3>;
+ };
+
+ gmac0: ethernet@1f020000 {
+ compatible = "snps,dwmac-3.70a";
+ reg = <0x0 0x1f020000 0x0 0x10000>;
+ interrupt-parent = <&liointc0>;
+ interrupts = <12 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-names = "macirq";
+ status = "disabled";
+ };
+
+ gmac1: ethernet@1f030000 {
+ compatible = "snps,dwmac-3.70a";
+ reg = <0x0 0x1f030000 0x0 0x10000>;
+ interrupt-parent = <&liointc0>;
+ interrupts = <14 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-names = "macirq";
+ status = "disabled";
+ };
+
+ sata: sata@1f040000 {
+ compatible = "snps,spear-ahci";
+ reg = <0x0 0x1f040000 0x0 0x10000>;
+ interrupt-parent = <&eiointc>;
+ interrupts = <75>;
+ status = "disabled";
+ };
+
+ ehci0: usb@1f050000 {
+ compatible = "generic-ehci";
+ reg = <0x0 0x1f050000 0x0 0x8000>;
+ interrupt-parent = <&eiointc>;
+ interrupts = <71>;
+ status = "disabled";
+ };
+
+ ohci0: usb@1f058000 {
+ compatible = "generic-ohci";
+ reg = <0x0 0x1f058000 0x0 0x8000>;
+ interrupt-parent = <&eiointc>;
+ interrupts = <72>;
+ status = "disabled";
+ };
+
+ uart0: serial@1ff40800 {
+ compatible = "ns16550a";
+ reg = <0x0 0x1ff40800 0x0 0x10>;
+ clock-frequency = <100000000>;
+ interrupt-parent = <&eiointc>;
+ interrupts = <2>;
+ no-loopback-test;
+ status = "disabled";
+ };
+
+ i2c0: i2c@1ff48000 {
+ compatible = "loongson,ls2k-i2c";
+ reg = <0x0 0x1ff48000 0x0 0x0800>;
+ interrupt-parent = <&eiointc>;
+ interrupts = <14>;
+ status = "disabled";
+ };
+
+ i2c@1ff48800 {
+ compatible = "loongson,ls2k-i2c";
+ reg = <0x0 0x1ff48800 0x0 0x0800>;
+ interrupt-parent = <&eiointc>;
+ interrupts = <15>;
+ status = "disabled";
+ };
+
+ i2c@1ff49000 {
+ compatible = "loongson,ls2k-i2c";
+ reg = <0x0 0x1ff49000 0x0 0x0800>;
+ interrupt-parent = <&eiointc>;
+ interrupts = <16>;
+ status = "disabled";
+ };
+
+ i2c@1ff49800 {
+ compatible = "loongson,ls2k-i2c";
+ reg = <0x0 0x1ff49800 0x0 0x0800>;
+ interrupt-parent = <&eiointc>;
+ interrupts = <17>;
+ status = "disabled";
+ };
+
+ i2c@1ff4a000 {
+ compatible = "loongson,ls2k-i2c";
+ reg = <0x0 0x1ff4a000 0x0 0x0800>;
+ interrupt-parent = <&eiointc>;
+ interrupts = <18>;
+ status = "disabled";
+ };
+
+ i2c@1ff4a800 {
+ compatible = "loongson,ls2k-i2c";
+ reg = <0x0 0x1ff4a800 0x0 0x0800>;
+ interrupt-parent = <&eiointc>;
+ interrupts = <19>;
+ status = "disabled";
+ };
+
+ pmc: power-management@1ff6c000 {
+ compatible = "loongson,ls2k0500-pmc", "syscon";
+ reg = <0x0 0x1ff6c000 0x0 0x58>;
+ interrupt-parent = <&eiointc>;
+ interrupts = <56>;
+ loongson,suspend-address = <0x0 0x1c000500>;
+
+ syscon-reboot {
+ compatible = "syscon-reboot";
+ offset = <0x30>;
+ mask = <0x1>;
+ };
+
+ syscon-poweroff {
+ compatible = "syscon-poweroff";
+ regmap = <&pmc>;
+ offset = <0x14>;
+ mask = <0x3c00>;
+ value = <0x3c00>;
+ };
+ };
+
+ rtc0: rtc@1ff6c100 {
+ compatible = "loongson,ls2k0500-rtc", "loongson,ls7a-rtc";
+ reg = <0x0 0x1ff6c100 0x0 0x100>;
+ interrupt-parent = <&eiointc>;
+ interrupts = <35>;
+ status = "disabled";
+ };
+
+ pcie@1a000000 {
+ compatible = "loongson,ls2k-pci";
+ reg = <0x0 0x1a000000 0x0 0x02000000>,
+ <0xfe 0x0 0x0 0x20000000>;
+ #address-cells = <3>;
+ #size-cells = <2>;
+ device_type = "pci";
+ bus-range = <0x0 0x5>;
+ ranges = <0x01000000 0x0 0x00004000 0x0 0x16404000 0x0 0x00004000>,
+ <0x02000000 0x0 0x40000000 0x0 0x40000000 0x0 0x40000000>;
+
+ pcie@0,0 {
+ reg = <0x0000 0x0 0x0 0x0 0x0>;
+ #address-cells = <3>;
+ #size-cells = <2>;
+ device_type = "pci";
+ interrupt-parent = <&eiointc>;
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+ interrupt-map = <0x0 0x0 0x0 0x0 &eiointc 81>;
+ ranges;
+ };
+
+ pcie@1,0 {
+ reg = <0x0800 0x0 0x0 0x0 0x0>;
+ #address-cells = <3>;
+ #size-cells = <2>;
+ device_type = "pci";
+ interrupt-parent = <&eiointc>;
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+ interrupt-map = <0x0 0x0 0x0 0x0 &eiointc 82>;
+ ranges;
+ };
+ };
+ };
+};
diff --git a/arch/loongarch/boot/dts/loongson-2k1000-ref.dts b/arch/loongarch/boot/dts/loongson-2k1000-ref.dts
new file mode 100644
index 0000000000000000000000000000000000000000..132a2d1ea8bce1ac95222875b6ad74d5ebf06b14
--- /dev/null
+++ b/arch/loongarch/boot/dts/loongson-2k1000-ref.dts
@@ -0,0 +1,183 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 Loongson Technology Corporation Limited
+ */
+
+/dts-v1/;
+
+#include "loongson-2k1000.dtsi"
+
+/ {
+ compatible = "loongson,ls2k1000-ref", "loongson,ls2k1000";
+ model = "Loongson-2K1000 Reference Board";
+
+ aliases {
+ serial0 = &uart0;
+ };
+
+ chosen {
+ stdout-path = "serial0:115200n8";
+ };
+
+ memory@200000 {
+ device_type = "memory";
+ reg = <0x0 0x00200000 0x0 0x06e00000>,
+ <0x0 0x08000000 0x0 0x07000000>,
+ <0x0 0x90000000 0x1 0xe0000000>;
+ };
+
+ reserved-memory {
+ #address-cells = <2>;
+ #size-cells = <2>;
+ ranges;
+
+ linux,cma {
+ compatible = "shared-dma-pool";
+ reusable;
+ size = <0x0 0x2000000>;
+ linux,cma-default;
+ };
+ };
+};
+
+&gmac0 {
+ status = "okay";
+
+ phy-mode = "rgmii";
+ phy-handle = <&phy0>;
+ mdio {
+ compatible = "snps,dwmac-mdio";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ phy0: ethernet-phy@0 {
+ reg = <0>;
+ };
+ };
+};
+
+&gmac1 {
+ status = "okay";
+
+ phy-mode = "rgmii";
+ phy-handle = <&phy1>;
+ mdio {
+ compatible = "snps,dwmac-mdio";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ phy1: ethernet-phy@1 {
+ reg = <16>;
+ };
+ };
+};
+
+&i2c2 {
+ status = "okay";
+
+ pinctrl-0 = <&i2c0_pins_default>;
+ pinctrl-names = "default";
+
+ #address-cells = <1>;
+ #size-cells = <0>;
+ eeprom@57{
+ compatible = "atmel,24c16";
+ reg = <0x57>;
+ pagesize = <16>;
+ };
+};
+
+&spi0 {
+ status = "okay";
+
+ #address-cells = <1>;
+ #size-cells = <0>;
+ spidev@0 {
+ compatible = "rohm,dh2228fv";
+ spi-max-frequency = <100000000>;
+ reg = <0>;
+ };
+};
+
+&ehci0 {
+ status = "okay";
+};
+
+&ohci0 {
+ status = "okay";
+};
+
+&sata {
+ status = "okay";
+};
+
+&uart0 {
+ status = "okay";
+};
+
+&clk {
+ status = "okay";
+};
+
+&rtc0 {
+ status = "okay";
+};
+
+&pctrl {
+ status = "okay";
+
+ sdio_pins_default: sdio-pins {
+ sdio-pinmux {
+ groups = "sdio";
+ function = "sdio";
+ };
+ sdio-det-pinmux {
+ groups = "pwm2";
+ function = "gpio";
+ };
+ };
+
+ pwm1_pins_default: pwm1-pins {
+ pinmux {
+ groups = "pwm1";
+ function = "pwm1";
+ };
+ };
+
+ pwm0_pins_default: pwm0-pins {
+ pinmux {
+ groups = "pwm0";
+ function = "pwm0";
+ };
+ };
+
+ i2c1_pins_default: i2c1-pins {
+ pinmux {
+ groups = "i2c1";
+ function = "i2c1";
+ };
+ };
+
+ i2c0_pins_default: i2c0-pins {
+ pinmux {
+ groups = "i2c0";
+ function = "i2c0";
+ };
+ };
+
+ nand_pins_default: nand-pins {
+ pinmux {
+ groups = "nand";
+ function = "nand";
+ };
+ };
+
+ hda_pins_default: hda-pins {
+ grp0-pinmux {
+ groups = "hda";
+ function = "hda";
+ };
+ grp1-pinmux {
+ groups = "i2s";
+ function = "gpio";
+ };
+ };
+};
diff --git a/arch/loongarch/boot/dts/loongson-2k1000.dtsi b/arch/loongarch/boot/dts/loongson-2k1000.dtsi
new file mode 100644
index 0000000000000000000000000000000000000000..49a70f8c3cab22b758dd290a9fab2374a62abae9
--- /dev/null
+++ b/arch/loongarch/boot/dts/loongson-2k1000.dtsi
@@ -0,0 +1,492 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 Loongson Technology Corporation Limited
+ */
+
+/dts-v1/;
+
+#include
+#include
+#include
+
+/ {
+ #address-cells = <2>;
+ #size-cells = <2>;
+
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cpu0: cpu@0 {
+ compatible = "loongson,la264";
+ device_type = "cpu";
+ reg= <0x0>;
+ clocks = <&clk LOONGSON2_NODE_CLK>;
+ };
+
+ cpu1: cpu@1 {
+ compatible = "loongson,la264";
+ device_type = "cpu";
+ reg = <0x1>;
+ clocks = <&clk LOONGSON2_NODE_CLK>;
+ };
+ };
+
+ ref_100m: clock-ref-100m {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <100000000>;
+ clock-output-names = "ref_100m";
+ };
+
+ cpuintc: interrupt-controller {
+ compatible = "loongson,cpu-interrupt-controller";
+ #interrupt-cells = <1>;
+ interrupt-controller;
+ };
+
+ /* i2c of the dvi eeprom edid */
+ i2c-gpio-0 {
+ compatible = "i2c-gpio";
+ scl-gpios = <&gpio0 0 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+ sda-gpios = <&gpio0 1 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+ i2c-gpio,delay-us = <5>; /* ~100 kHz */
+ #address-cells = <1>;
+ #size-cells = <0>;
+ status = "disabled";
+ };
+
+ /* i2c of the eeprom edid */
+ i2c-gpio-1 {
+ compatible = "i2c-gpio";
+ scl-gpios = <&gpio0 33 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+ sda-gpios = <&gpio0 32 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+ i2c-gpio,delay-us = <5>; /* ~100 kHz */
+ #address-cells = <1>;
+ #size-cells = <0>;
+ status = "disabled";
+ };
+
+ thermal-zones {
+ cpu-thermal {
+ polling-delay-passive = <1000>;
+ polling-delay = <5000>;
+ thermal-sensors = <&tsensor 0>;
+
+ trips {
+ cpu_alert: cpu-alert {
+ temperature = <33000>;
+ hysteresis = <2000>;
+ type = "active";
+ };
+
+ cpu_crit: cpu-crit {
+ temperature = <85000>;
+ hysteresis = <5000>;
+ type = "critical";
+ };
+ };
+ };
+ };
+
+ bus@10000000 {
+ compatible = "simple-bus";
+ ranges = <0x0 0x10000000 0x0 0x10000000 0x0 0x10000000>,
+ <0x0 0x02000000 0x0 0x02000000 0x0 0x02000000>,
+ <0x0 0x20000000 0x0 0x20000000 0x0 0x10000000>,
+ <0x0 0x40000000 0x0 0x40000000 0x0 0x40000000>,
+ <0xfe 0x0 0xfe 0x0 0x0 0x40000000>;
+ #address-cells = <2>;
+ #size-cells = <2>;
+ dma-coherent;
+
+ liointc0: interrupt-controller@1fe01400 {
+ compatible = "loongson,liointc-2.0";
+ reg = <0x0 0x1fe01400 0x0 0x40>,
+ <0x0 0x1fe01040 0x0 0x8>,
+ <0x0 0x1fe01140 0x0 0x8>;
+ reg-names = "main", "isr0", "isr1";
+ interrupt-controller;
+ #interrupt-cells = <2>;
+ interrupt-parent = <&cpuintc>;
+ interrupts = <2>;
+ interrupt-names = "int0";
+ loongson,parent_int_map = <0xffffffff>, /* int0 */
+ <0x00000000>, /* int1 */
+ <0x00000000>, /* int2 */
+ <0x00000000>; /* int3 */
+ };
+
+ liointc1: interrupt-controller@1fe01440 {
+ compatible = "loongson,liointc-2.0";
+ reg = <0x0 0x1fe01440 0x0 0x40>,
+ <0x0 0x1fe01048 0x0 0x8>,
+ <0x0 0x1fe01148 0x0 0x8>;
+ reg-names = "main", "isr0", "isr1";
+ interrupt-controller;
+ #interrupt-cells = <2>;
+ interrupt-parent = <&cpuintc>;
+ interrupts = <3>;
+ interrupt-names = "int1";
+ loongson,parent_int_map = <0x00000000>, /* int0 */
+ <0xffffffff>, /* int1 */
+ <0x00000000>, /* int2 */
+ <0x00000000>; /* int3 */
+ };
+
+ chipid@1fe00000 {
+ compatible = "loongson,ls2k-chipid";
+ reg = <0x0 0x1fe00000 0x0 0x30>;
+ little-endian;
+ };
+
+ pctrl: pinctrl@1fe00420 {
+ compatible = "loongson,ls2k-pinctrl";
+ reg = <0x0 0x1fe00420 0x0 0x18>;
+ status = "disabled";
+ };
+
+ clk: clock-controller@1fe00480 {
+ compatible = "loongson,ls2k-clk";
+ reg = <0x0 0x1fe00480 0x0 0x58>;
+ #clock-cells = <1>;
+ clocks = <&ref_100m>;
+ clock-names = "ref_100m";
+ status = "disabled";
+ };
+
+ gpio0: gpio@1fe00500 {
+ compatible = "loongson,ls2k-gpio";
+ reg = <0x0 0x1fe00500 0x0 0x38>;
+ ngpios = <64>;
+ #gpio-cells = <2>;
+ gpio-controller;
+ gpio-ranges = <&pctrl 0x0 0x0 15>,
+ <&pctrl 16 16 15>,
+ <&pctrl 32 32 10>,
+ <&pctrl 44 44 20>;
+ interrupt-parent = <&liointc1>;
+ interrupts = <28 IRQ_TYPE_LEVEL_HIGH>,
+ <29 IRQ_TYPE_LEVEL_HIGH>,
+ <30 IRQ_TYPE_LEVEL_HIGH>,
+ <30 IRQ_TYPE_LEVEL_HIGH>,
+ <26 IRQ_TYPE_LEVEL_HIGH>,
+ <26 IRQ_TYPE_LEVEL_HIGH>,
+ <26 IRQ_TYPE_LEVEL_HIGH>,
+ <26 IRQ_TYPE_LEVEL_HIGH>,
+ <26 IRQ_TYPE_LEVEL_HIGH>,
+ <26 IRQ_TYPE_LEVEL_HIGH>,
+ <26 IRQ_TYPE_LEVEL_HIGH>,
+ <26 IRQ_TYPE_LEVEL_HIGH>,
+ <26 IRQ_TYPE_LEVEL_HIGH>,
+ <26 IRQ_TYPE_LEVEL_HIGH>,
+ <26 IRQ_TYPE_LEVEL_HIGH>,
+ <>,
+ <26 IRQ_TYPE_LEVEL_HIGH>,
+ <26 IRQ_TYPE_LEVEL_HIGH>,
+ <26 IRQ_TYPE_LEVEL_HIGH>,
+ <26 IRQ_TYPE_LEVEL_HIGH>,
+ <26 IRQ_TYPE_LEVEL_HIGH>,
+ <26 IRQ_TYPE_LEVEL_HIGH>,
+ <26 IRQ_TYPE_LEVEL_HIGH>,
+ <26 IRQ_TYPE_LEVEL_HIGH>,
+ <26 IRQ_TYPE_LEVEL_HIGH>,
+ <26 IRQ_TYPE_LEVEL_HIGH>,
+ <26 IRQ_TYPE_LEVEL_HIGH>,
+ <26 IRQ_TYPE_LEVEL_HIGH>,
+ <26 IRQ_TYPE_LEVEL_HIGH>,
+ <26 IRQ_TYPE_LEVEL_HIGH>,
+ <26 IRQ_TYPE_LEVEL_HIGH>,
+ <26 IRQ_TYPE_LEVEL_HIGH>,
+ <27 IRQ_TYPE_LEVEL_HIGH>,
+ <27 IRQ_TYPE_LEVEL_HIGH>,
+ <27 IRQ_TYPE_LEVEL_HIGH>,
+ <27 IRQ_TYPE_LEVEL_HIGH>,
+ <27 IRQ_TYPE_LEVEL_HIGH>,
+ <>,
+ <27 IRQ_TYPE_LEVEL_HIGH>,
+ <27 IRQ_TYPE_LEVEL_HIGH>,
+ <27 IRQ_TYPE_LEVEL_HIGH>,
+ <27 IRQ_TYPE_LEVEL_HIGH>,
+ <>,
+ <>,
+ <27 IRQ_TYPE_LEVEL_HIGH>,
+ <27 IRQ_TYPE_LEVEL_HIGH>,
+ <27 IRQ_TYPE_LEVEL_HIGH>,
+ <27 IRQ_TYPE_LEVEL_HIGH>,
+ <27 IRQ_TYPE_LEVEL_HIGH>,
+ <27 IRQ_TYPE_LEVEL_HIGH>,
+ <27 IRQ_TYPE_LEVEL_HIGH>,
+ <27 IRQ_TYPE_LEVEL_HIGH>,
+ <27 IRQ_TYPE_LEVEL_HIGH>,
+ <27 IRQ_TYPE_LEVEL_HIGH>,
+ <27 IRQ_TYPE_LEVEL_HIGH>,
+ <27 IRQ_TYPE_LEVEL_HIGH>,
+ <27 IRQ_TYPE_LEVEL_HIGH>,
+ <27 IRQ_TYPE_LEVEL_HIGH>,
+ <27 IRQ_TYPE_LEVEL_HIGH>,
+ <27 IRQ_TYPE_LEVEL_HIGH>,
+ <27 IRQ_TYPE_LEVEL_HIGH>,
+ <27 IRQ_TYPE_LEVEL_HIGH>,
+ <27 IRQ_TYPE_LEVEL_HIGH>,
+ <27 IRQ_TYPE_LEVEL_HIGH>;
+ };
+
+ tsensor: thermal-sensor@1fe01500 {
+ compatible = "loongson,ls2k1000-thermal";
+ reg = <0x0 0x1fe01500 0x0 0x30>;
+ interrupt-parent = <&liointc0>;
+ interrupts = <7 IRQ_TYPE_LEVEL_HIGH>;
+ #thermal-sensor-cells = <1>;
+ };
+
+ dma-controller@1fe00c00 {
+ compatible = "loongson,ls2k1000-apbdma";
+ reg = <0x0 0x1fe00c00 0x0 0x8>;
+ interrupt-parent = <&liointc1>;
+ interrupts = <12 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&clk LOONGSON2_APB_CLK>;
+ #dma-cells = <1>;
+ status = "disabled";
+ };
+
+ dma-controller@1fe00c10 {
+ compatible = "loongson,ls2k1000-apbdma";
+ reg = <0x0 0x1fe00c10 0x0 0x8>;
+ interrupt-parent = <&liointc1>;
+ interrupts = <13 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&clk LOONGSON2_APB_CLK>;
+ #dma-cells = <1>;
+ status = "disabled";
+ };
+
+ dma-controller@1fe00c20 {
+ compatible = "loongson,ls2k1000-apbdma";
+ reg = <0x0 0x1fe00c20 0x0 0x8>;
+ interrupt-parent = <&liointc1>;
+ interrupts = <14 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&clk LOONGSON2_APB_CLK>;
+ #dma-cells = <1>;
+ status = "disabled";
+ };
+
+ dma-controller@1fe00c30 {
+ compatible = "loongson,ls2k1000-apbdma";
+ reg = <0x0 0x1fe00c30 0x0 0x8>;
+ interrupt-parent = <&liointc1>;
+ interrupts = <15 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&clk LOONGSON2_APB_CLK>;
+ #dma-cells = <1>;
+ status = "disabled";
+ };
+
+ dma-controller@1fe00c40 {
+ compatible = "loongson,ls2k1000-apbdma";
+ reg = <0x0 0x1fe00c40 0x0 0x8>;
+ interrupt-parent = <&liointc1>;
+ interrupts = <16 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&clk LOONGSON2_APB_CLK>;
+ #dma-cells = <1>;
+ status = "disabled";
+ };
+
+ uart0: serial@1fe20000 {
+ compatible = "ns16550a";
+ reg = <0x0 0x1fe20000 0x0 0x10>;
+ clock-frequency = <125000000>;
+ interrupt-parent = <&liointc0>;
+ interrupts = <0x0 IRQ_TYPE_LEVEL_HIGH>;
+ no-loopback-test;
+ status = "disabled";
+ };
+
+ i2c2: i2c@1fe21000 {
+ compatible = "loongson,ls2k-i2c";
+ reg = <0x0 0x1fe21000 0x0 0x8>;
+ interrupt-parent = <&liointc0>;
+ interrupts = <22 IRQ_TYPE_LEVEL_HIGH>;
+ status = "disabled";
+ };
+
+ i2c3: i2c@1fe21800 {
+ compatible = "loongson,ls2k-i2c";
+ reg = <0x0 0x1fe21800 0x0 0x8>;
+ interrupt-parent = <&liointc0>;
+ interrupts = <23 IRQ_TYPE_LEVEL_HIGH>;
+ status = "disabled";
+ };
+
+ pmc: power-management@1fe27000 {
+ compatible = "loongson,ls2k1000-pmc", "loongson,ls2k0500-pmc", "syscon";
+ reg = <0x0 0x1fe27000 0x0 0x58>;
+ interrupt-parent = <&liointc1>;
+ interrupts = <11 IRQ_TYPE_LEVEL_HIGH>;
+ loongson,suspend-address = <0x0 0x1c000500>;
+
+ syscon-reboot {
+ compatible = "syscon-reboot";
+ offset = <0x30>;
+ mask = <0x1>;
+ };
+
+ syscon-poweroff {
+ compatible = "syscon-poweroff";
+ regmap = <&pmc>;
+ offset = <0x14>;
+ mask = <0x3c00>;
+ value = <0x3c00>;
+ };
+ };
+
+ rtc0: rtc@1fe27800 {
+ compatible = "loongson,ls2k1000-rtc";
+ reg = <0x0 0x1fe27800 0x0 0x100>;
+ interrupt-parent = <&liointc1>;
+ interrupts = <8 IRQ_TYPE_LEVEL_HIGH>;
+ status = "disabled";
+ };
+
+ spi0: spi@1fff0220 {
+ compatible = "loongson,ls2k1000-spi";
+ reg = <0x0 0x1fff0220 0x0 0x10>;
+ clocks = <&clk LOONGSON2_BOOT_CLK>;
+ status = "disabled";
+ };
+
+ pcie@1a000000 {
+ compatible = "loongson,ls2k-pci";
+ reg = <0x0 0x1a000000 0x0 0x02000000>,
+ <0xfe 0x0 0x0 0x20000000>;
+ #address-cells = <3>;
+ #size-cells = <2>;
+ device_type = "pci";
+ bus-range = <0x0 0xff>;
+ ranges = <0x01000000 0x0 0x00008000 0x0 0x18008000 0x0 0x00008000>,
+ <0x02000000 0x0 0x60000000 0x0 0x60000000 0x0 0x20000000>;
+
+ gmac0: ethernet@3,0 {
+ reg = <0x1800 0x0 0x0 0x0 0x0>;
+ interrupt-parent = <&liointc0>;
+ interrupts = <12 IRQ_TYPE_LEVEL_HIGH>,
+ <13 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-names = "macirq", "eth_lpi";
+ status = "disabled";
+ };
+
+ gmac1: ethernet@3,1 {
+ reg = <0x1900 0x0 0x0 0x0 0x0>;
+ interrupt-parent = <&liointc0>;
+ interrupts = <14 IRQ_TYPE_LEVEL_HIGH>,
+ <15 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-names = "macirq", "eth_lpi";
+ status = "disabled";
+ };
+
+ ehci0: usb@4,1 {
+ reg = <0x2100 0x0 0x0 0x0 0x0>;
+ interrupt-parent = <&liointc1>;
+ interrupts = <18 IRQ_TYPE_LEVEL_HIGH>;
+ status = "disabled";
+ };
+
+ ohci0: usb@4,2 {
+ reg = <0x2200 0x0 0x0 0x0 0x0>;
+ interrupt-parent = <&liointc1>;
+ interrupts = <19 IRQ_TYPE_LEVEL_HIGH>;
+ status = "disabled";
+ };
+
+ display@6,0 {
+ reg = <0x3000 0x0 0x0 0x0 0x0>;
+ interrupt-parent = <&liointc0>;
+ interrupts = <28 IRQ_TYPE_LEVEL_HIGH>;
+ status = "disabled";
+ };
+
+ hda@7,0 {
+ reg = <0x3800 0x0 0x0 0x0 0x0>;
+ interrupt-parent = <&liointc0>;
+ interrupts = <4 IRQ_TYPE_LEVEL_HIGH>;
+ status = "disabled";
+ };
+
+ sata: sata@8,0 {
+ reg = <0x4000 0x0 0x0 0x0 0x0>;
+ interrupt-parent = <&liointc0>;
+ interrupts = <19 IRQ_TYPE_LEVEL_HIGH>;
+ status = "disabled";
+ };
+
+ pcie@9,0 {
+ reg = <0x4800 0x0 0x0 0x0 0x0>;
+ #address-cells = <3>;
+ #size-cells = <2>;
+ device_type = "pci";
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+ interrupt-map = <0x0 0x0 0x0 0x0 &liointc1 0x0 IRQ_TYPE_LEVEL_HIGH>;
+ ranges;
+ };
+
+ pcie@a,0 {
+ reg = <0x5000 0x0 0x0 0x0 0x0>;
+ #address-cells = <3>;
+ #size-cells = <2>;
+ device_type = "pci";
+ interrupt-parent = <&liointc1>;
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+ interrupt-map = <0x0 0x0 0x0 0x0 &liointc1 1 IRQ_TYPE_LEVEL_HIGH>;
+ ranges;
+ };
+
+ pcie@b,0 {
+ reg = <0x5800 0x0 0x0 0x0 0x0>;
+ #address-cells = <3>;
+ #size-cells = <2>;
+ device_type = "pci";
+ interrupt-parent = <&liointc1>;
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+ interrupt-map = <0x0 0x0 0x0 0x0 &liointc1 2 IRQ_TYPE_LEVEL_HIGH>;
+ ranges;
+ };
+
+ pcie@c,0 {
+ reg = <0x6000 0x0 0x0 0x0 0x0>;
+ #address-cells = <3>;
+ #size-cells = <2>;
+ device_type = "pci";
+ interrupt-parent = <&liointc1>;
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+ interrupt-map = <0x0 0x0 0x0 0x0 &liointc1 3 IRQ_TYPE_LEVEL_HIGH>;
+ ranges;
+ };
+
+ pcie@d,0 {
+ reg = <0x6800 0x0 0x0 0x0 0x0>;
+ #address-cells = <3>;
+ #size-cells = <2>;
+ device_type = "pci";
+ interrupt-parent = <&liointc1>;
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+ interrupt-map = <0x0 0x0 0x0 0x0 &liointc1 4 IRQ_TYPE_LEVEL_HIGH>;
+ ranges;
+ };
+
+ pcie@e,0 {
+ reg = <0x7000 0x0 0x0 0x0 0x0>;
+ #address-cells = <3>;
+ #size-cells = <2>;
+ device_type = "pci";
+ interrupt-parent = <&liointc1>;
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+ interrupt-map = <0x0 0x0 0x0 0x0 &liointc1 5 IRQ_TYPE_LEVEL_HIGH>;
+ ranges;
+ };
+ };
+ };
+};
diff --git a/arch/loongarch/boot/dts/loongson-2k2000-ref.dts b/arch/loongarch/boot/dts/loongson-2k2000-ref.dts
new file mode 100644
index 0000000000000000000000000000000000000000..dca91caf895e3cd9e428e75b91da9392bfb49d82
--- /dev/null
+++ b/arch/loongarch/boot/dts/loongson-2k2000-ref.dts
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 Loongson Technology Corporation Limited
+ */
+
+/dts-v1/;
+
+#include "loongson-2k2000.dtsi"
+
+/ {
+ compatible = "loongson,ls2k2000-ref", "loongson,ls2k2000";
+ model = "Loongson-2K2000 Reference Board";
+
+ aliases {
+ serial0 = &uart0;
+ };
+
+ chosen {
+ stdout-path = "serial0:115200n8";
+ };
+
+ memory@200000 {
+ device_type = "memory";
+ reg = <0x0 0x00200000 0x0 0x0ee00000>,
+ <0x0 0x90000000 0x0 0x70000000>;
+ };
+
+ reserved-memory {
+ #address-cells = <2>;
+ #size-cells = <2>;
+ ranges;
+
+ linux,cma {
+ compatible = "shared-dma-pool";
+ reusable;
+ size = <0x0 0x2000000>;
+ linux,cma-default;
+ };
+ };
+};
+
+&sata {
+ status = "okay";
+};
+
+&uart0 {
+ status = "okay";
+};
+
+&rtc0 {
+ status = "okay";
+};
+
+&xhci0 {
+ status = "okay";
+};
+
+&xhci1 {
+ status = "okay";
+};
+
+&gmac0 {
+ status = "okay";
+};
+
+&gmac1 {
+ status = "okay";
+};
+
+&gmac2 {
+ status = "okay";
+};
diff --git a/arch/loongarch/boot/dts/loongson-2k2000.dtsi b/arch/loongarch/boot/dts/loongson-2k2000.dtsi
new file mode 100644
index 0000000000000000000000000000000000000000..a231949b5f553a3814f48f6875e65ac2ed73d09a
--- /dev/null
+++ b/arch/loongarch/boot/dts/loongson-2k2000.dtsi
@@ -0,0 +1,300 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 Loongson Technology Corporation Limited
+ */
+
+/dts-v1/;
+
+#include
+
+/ {
+ #address-cells = <2>;
+ #size-cells = <2>;
+
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cpu0: cpu@1 {
+ compatible = "loongson,la364";
+ device_type = "cpu";
+ reg = <0x0>;
+ clocks = <&cpu_clk>;
+ };
+
+ cpu1: cpu@2 {
+ compatible = "loongson,la364";
+ device_type = "cpu";
+ reg = <0x1>;
+ clocks = <&cpu_clk>;
+ };
+ };
+
+ cpu_clk: cpu-clk {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <1400000000>;
+ };
+
+ cpuintc: interrupt-controller {
+ compatible = "loongson,cpu-interrupt-controller";
+ #interrupt-cells = <1>;
+ interrupt-controller;
+ };
+
+ bus@10000000 {
+ compatible = "simple-bus";
+ ranges = <0x0 0x10000000 0x0 0x10000000 0x0 0x10000000>,
+ <0x0 0x02000000 0x0 0x02000000 0x0 0x02000000>,
+ <0x0 0x40000000 0x0 0x40000000 0x0 0x40000000>,
+ <0xfe 0x0 0xfe 0x0 0x0 0x40000000>;
+ #address-cells = <2>;
+ #size-cells = <2>;
+
+ pmc: power-management@100d0000 {
+ compatible = "loongson,ls2k2000-pmc", "loongson,ls2k0500-pmc", "syscon";
+ reg = <0x0 0x100d0000 0x0 0x58>;
+ interrupt-parent = <&eiointc>;
+ interrupts = <47>;
+ loongson,suspend-address = <0x0 0x1c000500>;
+
+ syscon-reboot {
+ compatible = "syscon-reboot";
+ offset = <0x30>;
+ mask = <0x1>;
+ };
+
+ syscon-poweroff {
+ compatible = "syscon-poweroff";
+ regmap = <&pmc>;
+ offset = <0x14>;
+ mask = <0x3c00>;
+ value = <0x3c00>;
+ };
+ };
+
+ liointc: interrupt-controller@1fe01400 {
+ compatible = "loongson,liointc-1.0";
+ reg = <0x0 0x1fe01400 0x0 0x64>;
+
+ interrupt-controller;
+ #interrupt-cells = <2>;
+ interrupt-parent = <&cpuintc>;
+ interrupts = <2>;
+ interrupt-names = "int0";
+ loongson,parent_int_map = <0xffffffff>, /* int0 */
+ <0x00000000>, /* int1 */
+ <0x00000000>, /* int2 */
+ <0x00000000>; /* int3 */
+ };
+
+ eiointc: interrupt-controller@1fe01600 {
+ compatible = "loongson,ls2k2000-eiointc";
+ reg = <0x0 0x1fe01600 0x0 0xea00>;
+ interrupt-controller;
+ #interrupt-cells = <1>;
+ interrupt-parent = <&cpuintc>;
+ interrupts = <3>;
+ };
+
+ pic: interrupt-controller@10000000 {
+ compatible = "loongson,pch-pic-1.0";
+ reg = <0x0 0x10000000 0x0 0x400>;
+ interrupt-controller;
+ #interrupt-cells = <2>;
+ loongson,pic-base-vec = <0>;
+ interrupt-parent = <&eiointc>;
+ };
+
+ msi: msi-controller@1fe01140 {
+ compatible = "loongson,pch-msi-1.0";
+ reg = <0x0 0x1fe01140 0x0 0x8>;
+ msi-controller;
+ loongson,msi-base-vec = <64>;
+ loongson,msi-num-vecs = <192>;
+ interrupt-parent = <&eiointc>;
+ };
+
+ rtc0: rtc@100d0100 {
+ compatible = "loongson,ls2k2000-rtc", "loongson,ls7a-rtc";
+ reg = <0x0 0x100d0100 0x0 0x100>;
+ interrupt-parent = <&pic>;
+ interrupts = <52 IRQ_TYPE_LEVEL_HIGH>;
+ status = "disabled";
+ };
+
+ uart0: serial@1fe001e0 {
+ compatible = "ns16550a";
+ reg = <0x0 0x1fe001e0 0x0 0x10>;
+ clock-frequency = <100000000>;
+ interrupt-parent = <&liointc>;
+ interrupts = <10 IRQ_TYPE_LEVEL_HIGH>;
+ no-loopback-test;
+ status = "disabled";
+ };
+
+ pcie@1a000000 {
+ compatible = "loongson,ls2k-pci";
+ reg = <0x0 0x1a000000 0x0 0x02000000>,
+ <0xfe 0x0 0x0 0x20000000>;
+ #address-cells = <3>;
+ #size-cells = <2>;
+ device_type = "pci";
+ bus-range = <0x0 0xff>;
+ ranges = <0x01000000 0x0 0x00008000 0x0 0x18400000 0x0 0x00008000>,
+ <0x02000000 0x0 0x60000000 0x0 0x60000000 0x0 0x20000000>;
+
+ gmac0: ethernet@3,0 {
+ reg = <0x1800 0x0 0x0 0x0 0x0>;
+ interrupts = <12 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-parent = <&pic>;
+ status = "disabled";
+ };
+
+ gmac1: ethernet@3,1 {
+ reg = <0x1900 0x0 0x0 0x0 0x0>;
+ interrupts = <14 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-parent = <&pic>;
+ status = "disabled";
+ };
+
+ gmac2: ethernet@3,2 {
+ reg = <0x1a00 0x0 0x0 0x0 0x0>;
+ interrupts = <17 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-parent = <&pic>;
+ status = "disabled";
+ };
+
+ xhci0: usb@4,0 {
+ reg = <0x2000 0x0 0x0 0x0 0x0>;
+ interrupts = <48 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-parent = <&pic>;
+ status = "disabled";
+ };
+
+ xhci1: usb@19,0 {
+ reg = <0xc800 0x0 0x0 0x0 0x0>;
+ interrupts = <22 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-parent = <&pic>;
+ status = "disabled";
+ };
+
+ display@6,1 {
+ reg = <0x3100 0x0 0x0 0x0 0x0>;
+ interrupts = <28 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-parent = <&pic>;
+ status = "disabled";
+ };
+
+ hda@7,0 {
+ reg = <0x3800 0x0 0x0 0x0 0x0>;
+ interrupts = <58 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-parent = <&pic>;
+ status = "disabled";
+ };
+
+ sata: sata@8,0 {
+ reg = <0x4000 0x0 0x0 0x0 0x0>;
+ interrupts = <16 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-parent = <&pic>;
+ status = "disabled";
+ };
+
+ pcie@9,0 {
+ reg = <0x4800 0x0 0x0 0x0 0x0>;
+ #address-cells = <3>;
+ #size-cells = <2>;
+ device_type = "pci";
+ interrupt-parent = <&pic>;
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+ interrupt-map = <0x0 0x0 0x0 0x0 &pic 32 IRQ_TYPE_LEVEL_HIGH>;
+ ranges;
+ };
+
+ pcie@a,0 {
+ reg = <0x5000 0x0 0x0 0x0 0x0>;
+ #address-cells = <3>;
+ #size-cells = <2>;
+ device_type = "pci";
+ interrupt-parent = <&pic>;
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+ interrupt-map = <0x0 0x0 0x0 0x0 &pic 33 IRQ_TYPE_LEVEL_HIGH>;
+ ranges;
+ };
+
+ pcie@b,0 {
+ reg = <0x5800 0x0 0x0 0x0 0x0>;
+ #address-cells = <3>;
+ #size-cells = <2>;
+ device_type = "pci";
+ interrupt-parent = <&pic>;
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+ interrupt-map = <0x0 0x0 0x0 0x0 &pic 34 IRQ_TYPE_LEVEL_HIGH>;
+ ranges;
+ };
+
+ pcie@c,0 {
+ reg = <0x6000 0x0 0x0 0x0 0x0>;
+ #address-cells = <3>;
+ #size-cells = <2>;
+ device_type = "pci";
+ interrupt-parent = <&pic>;
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+ interrupt-map = <0x0 0x0 0x0 0x0 &pic 35 IRQ_TYPE_LEVEL_HIGH>;
+ ranges;
+ };
+
+ pcie@d,0 {
+ reg = <0x6800 0x0 0x0 0x0 0x0>;
+ #address-cells = <3>;
+ #size-cells = <2>;
+ device_type = "pci";
+ interrupt-parent = <&pic>;
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+ interrupt-map = <0x0 0x0 0x0 0x0 &pic 36 IRQ_TYPE_LEVEL_HIGH>;
+ ranges;
+ };
+
+ pcie@e,0 {
+ reg = <0x7000 0x0 0x0 0x0 0x0>;
+ #address-cells = <3>;
+ #size-cells = <2>;
+ device_type = "pci";
+ interrupt-parent = <&pic>;
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+ interrupt-map = <0x0 0x0 0x0 0x0 &pic 37 IRQ_TYPE_LEVEL_HIGH>;
+ ranges;
+ };
+
+ pcie@f,0 {
+ reg = <0x7800 0x0 0x0 0x0 0x0>;
+ #address-cells = <3>;
+ #size-cells = <2>;
+ device_type = "pci";
+ interrupt-parent = <&pic>;
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+ interrupt-map = <0x0 0x0 0x0 0x0 &pic 40 IRQ_TYPE_LEVEL_HIGH>;
+ ranges;
+ };
+
+ pcie@10,0 {
+ reg = <0x8000 0x0 0x0 0x0 0x0>;
+ #address-cells = <3>;
+ #size-cells = <2>;
+ device_type = "pci";
+ interrupt-parent = <&pic>;
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+ interrupt-map = <0x0 0x0 0x0 0x0 &pic 30 IRQ_TYPE_LEVEL_HIGH>;
+ ranges;
+ };
+ };
+ };
+};
diff --git a/arch/loongarch/configs/loongson3_defconfig b/arch/loongarch/configs/loongson3_defconfig
index 60e331af98398149df56cfed7bc7b27abe21c526..f18c2ba871eff6c6c1b84808f0e9f7296c854db3 100644
--- a/arch/loongarch/configs/loongson3_defconfig
+++ b/arch/loongarch/configs/loongson3_defconfig
@@ -6,6 +6,8 @@ CONFIG_HIGH_RES_TIMERS=y
CONFIG_BPF_SYSCALL=y
CONFIG_BPF_JIT=y
CONFIG_PREEMPT=y
+CONFIG_PREEMPT_DYNAMIC=y
+CONFIG_SCHED_CORE=y
CONFIG_BSD_PROCESS_ACCT=y
CONFIG_BSD_PROCESS_ACCT_V3=y
CONFIG_TASKSTATS=y
@@ -19,6 +21,7 @@ CONFIG_BLK_CGROUP=y
CONFIG_CFS_BANDWIDTH=y
CONFIG_RT_GROUP_SCHED=y
CONFIG_CGROUP_PIDS=y
+CONFIG_CGROUP_RDMA=y
CONFIG_CGROUP_FREEZER=y
CONFIG_CGROUP_HUGETLB=y
CONFIG_CPUSETS=y
@@ -26,6 +29,7 @@ CONFIG_CGROUP_DEVICE=y
CONFIG_CGROUP_CPUACCT=y
CONFIG_CGROUP_PERF=y
CONFIG_CGROUP_BPF=y
+CONFIG_CGROUP_MISC=y
CONFIG_NAMESPACES=y
CONFIG_USER_NS=y
CONFIG_CHECKPOINT_RESTORE=y
@@ -35,6 +39,8 @@ CONFIG_BLK_DEV_INITRD=y
CONFIG_EXPERT=y
CONFIG_KALLSYMS_ALL=y
CONFIG_PERF_EVENTS=y
+CONFIG_KEXEC=y
+CONFIG_CRASH_DUMP=y
CONFIG_LOONGARCH=y
CONFIG_64BIT=y
CONFIG_MACH_LOONGSON64=y
@@ -44,13 +50,11 @@ CONFIG_DMI=y
CONFIG_EFI=y
CONFIG_SMP=y
CONFIG_HOTPLUG_CPU=y
-CONFIG_NR_CPUS=64
+CONFIG_NR_CPUS=256
CONFIG_NUMA=y
CONFIG_CPU_HAS_FPU=y
CONFIG_CPU_HAS_LSX=y
CONFIG_CPU_HAS_LASX=y
-CONFIG_KEXEC=y
-CONFIG_CRASH_DUMP=y
CONFIG_RANDOMIZE_BASE=y
CONFIG_SUSPEND=y
CONFIG_HIBERNATION=y
@@ -62,10 +66,6 @@ CONFIG_ACPI_IPMI=m
CONFIG_ACPI_HOTPLUG_CPU=y
CONFIG_ACPI_PCI_SLOT=y
CONFIG_ACPI_HOTPLUG_MEMORY=y
-CONFIG_EFI_ZBOOT=y
-CONFIG_EFI_GENERIC_STUB_INITRD_CMDLINE_LOADER=y
-CONFIG_EFI_CAPSULE_LOADER=m
-CONFIG_EFI_TEST=m
CONFIG_VIRTUALIZATION=y
CONFIG_KVM=m
CONFIG_JUMP_LABEL=y
@@ -74,10 +74,18 @@ CONFIG_MODULE_FORCE_LOAD=y
CONFIG_MODULE_UNLOAD=y
CONFIG_MODULE_FORCE_UNLOAD=y
CONFIG_MODVERSIONS=y
+CONFIG_BLK_DEV_ZONED=y
CONFIG_BLK_DEV_THROTTLING=y
+CONFIG_BLK_DEV_THROTTLING_LOW=y
+CONFIG_BLK_WBT=y
+CONFIG_BLK_CGROUP_IOLATENCY=y
+CONFIG_BLK_CGROUP_FC_APPID=y
+CONFIG_BLK_CGROUP_IOCOST=y
+CONFIG_BLK_CGROUP_IOPRIO=y
CONFIG_PARTITION_ADVANCED=y
CONFIG_BSD_DISKLABEL=y
CONFIG_UNIXWARE_DISKLABEL=y
+CONFIG_CMDLINE_PARTITION=y
CONFIG_IOSCHED_BFQ=y
CONFIG_BFQ_GROUP_IOSCHED=y
CONFIG_BINFMT_MISC=m
@@ -93,6 +101,8 @@ CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE=y
CONFIG_MEMORY_HOTREMOVE=y
CONFIG_KSM=y
CONFIG_TRANSPARENT_HUGEPAGE=y
+CONFIG_CMA=y
+CONFIG_CMA_SYSFS=y
CONFIG_USERFAULTFD=y
CONFIG_NET=y
CONFIG_PACKET=y
@@ -128,6 +138,7 @@ CONFIG_IPV6_ROUTER_PREF=y
CONFIG_IPV6_ROUTE_INFO=y
CONFIG_INET6_ESP=m
CONFIG_IPV6_MROUTE=y
+CONFIG_MPTCP=y
CONFIG_NETWORK_PHY_TIMESTAMPING=y
CONFIG_NETFILTER=y
CONFIG_BRIDGE_NETFILTER=m
@@ -352,6 +363,7 @@ CONFIG_PCIEAER=y
CONFIG_PCI_IOV=y
CONFIG_HOTPLUG_PCI=y
CONFIG_HOTPLUG_PCI_SHPC=y
+CONFIG_PCI_HOST_GENERIC=y
CONFIG_PCCARD=m
CONFIG_YENTA=m
CONFIG_RAPIDIO=y
@@ -365,6 +377,10 @@ CONFIG_DEVTMPFS=y
CONFIG_DEVTMPFS_MOUNT=y
CONFIG_FW_LOADER_COMPRESS=y
CONFIG_FW_LOADER_COMPRESS_ZSTD=y
+CONFIG_EFI_ZBOOT=y
+CONFIG_EFI_BOOTLOADER_CONTROL=m
+CONFIG_EFI_CAPSULE_LOADER=m
+CONFIG_EFI_TEST=m
CONFIG_MTD=m
CONFIG_MTD_BLOCK=m
CONFIG_MTD_CFI=m
@@ -586,6 +602,7 @@ CONFIG_RTW89_8852AE=m
CONFIG_RTW89_8852CE=m
CONFIG_ZD1211RW=m
CONFIG_USB_NET_RNDIS_WLAN=m
+CONFIG_USB4_NET=m
CONFIG_INPUT_MOUSEDEV=y
CONFIG_INPUT_MOUSEDEV_PSAUX=y
CONFIG_INPUT_EVDEV=y
@@ -691,6 +708,9 @@ CONFIG_SND_HDA_CODEC_SIGMATEL=y
CONFIG_SND_HDA_CODEC_HDMI=y
CONFIG_SND_HDA_CODEC_CONEXANT=y
CONFIG_SND_USB_AUDIO=m
+CONFIG_SND_SOC=m
+CONFIG_SND_SOC_LOONGSON_CARD=m
+CONFIG_SND_VIRTIO=m
CONFIG_HIDRAW=y
CONFIG_UHID=m
CONFIG_HID_A4TECH=m
@@ -738,6 +758,11 @@ CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_EFI=y
CONFIG_RTC_DRV_LOONGSON=y
CONFIG_DMADEVICES=y
+CONFIG_LS2X_APB_DMA=y
+CONFIG_UDMABUF=y
+CONFIG_DMABUF_HEAPS=y
+CONFIG_DMABUF_HEAPS_SYSTEM=y
+CONFIG_DMABUF_HEAPS_CMA=y
CONFIG_UIO=m
CONFIG_UIO_PDRV_GENIRQ=m
CONFIG_UIO_DMEM_GENIRQ=m
@@ -778,7 +803,15 @@ CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND=y
CONFIG_DEVFREQ_GOV_PERFORMANCE=y
CONFIG_DEVFREQ_GOV_POWERSAVE=y
CONFIG_DEVFREQ_GOV_USERSPACE=y
+CONFIG_NTB=m
+CONFIG_NTB_MSI=y
+CONFIG_NTB_IDT=m
+CONFIG_NTB_EPF=m
+CONFIG_NTB_SWITCHTEC=m
+CONFIG_NTB_PERF=m
+CONFIG_NTB_TRANSPORT=m
CONFIG_PWM=y
+CONFIG_USB4=y
CONFIG_EXT2_FS=y
CONFIG_EXT2_FS_XATTR=y
CONFIG_EXT2_FS_POSIX_ACL=y
@@ -797,6 +830,10 @@ CONFIG_GFS2_FS_LOCKING_DLM=y
CONFIG_OCFS2_FS=m
CONFIG_BTRFS_FS=y
CONFIG_BTRFS_FS_POSIX_ACL=y
+CONFIG_F2FS_FS=m
+CONFIG_F2FS_FS_SECURITY=y
+CONFIG_F2FS_CHECK_FS=y
+CONFIG_F2FS_FS_COMPRESSION=y
CONFIG_FANOTIFY=y
CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y
CONFIG_QUOTA=y
@@ -883,7 +920,6 @@ CONFIG_KEY_DH_OPERATIONS=y
CONFIG_SECURITY=y
CONFIG_SECURITY_SELINUX=y
CONFIG_SECURITY_SELINUX_BOOTPARAM=y
-CONFIG_SECURITY_SELINUX_DISABLE=y
CONFIG_SECURITY_APPARMOR=y
CONFIG_SECURITY_YAMA=y
CONFIG_DEFAULT_SECURITY_DAC=y
@@ -914,6 +950,9 @@ CONFIG_CRYPTO_USER_API_RNG=m
CONFIG_CRYPTO_USER_API_AEAD=m
CONFIG_CRYPTO_CRC32_LOONGARCH=m
CONFIG_CRYPTO_DEV_VIRTIO=m
+CONFIG_DMA_CMA=y
+CONFIG_DMA_NUMA_CMA=y
+CONFIG_CMA_SIZE_MBYTES=0
CONFIG_PRINTK_TIME=y
CONFIG_STRIP_ASM_SYMS=y
CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/loongarch/include/asm/bootinfo.h b/arch/loongarch/include/asm/bootinfo.h
index c60796869b2b80377d9d6afca9c8705f8d2433e1..6d5846dd075cbdde654760422fac5d9536605d4a 100644
--- a/arch/loongarch/include/asm/bootinfo.h
+++ b/arch/loongarch/include/asm/bootinfo.h
@@ -24,13 +24,15 @@ struct loongson_board_info {
const char *board_vendor;
};
+#define NR_WORDS DIV_ROUND_UP(NR_CPUS, BITS_PER_LONG)
+
struct loongson_system_configuration {
int nr_cpus;
int nr_nodes;
int boot_cpu_id;
int cores_per_node;
int cores_per_package;
- unsigned long cores_io_master;
+ unsigned long cores_io_master[NR_WORDS];
unsigned long suspend_addr;
const char *cpuname;
};
@@ -42,7 +44,7 @@ extern struct loongson_system_configuration loongson_sysconf;
static inline bool io_master(int cpu)
{
- return test_bit(cpu, &loongson_sysconf.cores_io_master);
+ return test_bit(cpu, loongson_sysconf.cores_io_master);
}
#endif /* _ASM_BOOTINFO_H */
diff --git a/arch/loongarch/include/asm/crash_core.h b/arch/loongarch/include/asm/crash_core.h
new file mode 100644
index 0000000000000000000000000000000000000000..218bdbfa527ba861364cbbb6601369036ee293bf
--- /dev/null
+++ b/arch/loongarch/include/asm/crash_core.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _LOONGARCH_CRASH_CORE_H
+#define _LOONGARCH_CRASH_CORE_H
+
+#define CRASH_ALIGN SZ_2M
+
+#define CRASH_ADDR_LOW_MAX SZ_4G
+#define CRASH_ADDR_HIGH_MAX memblock_end_of_DRAM()
+
+extern phys_addr_t memblock_end_of_DRAM(void);
+
+#endif
diff --git a/arch/loongarch/include/asm/elf.h b/arch/loongarch/include/asm/elf.h
index 9b16a3b8e70608c8765f838cfd21925d4fe51145..f16bd42456e4ccf3ad6c8917165176b8ef5d8f05 100644
--- a/arch/loongarch/include/asm/elf.h
+++ b/arch/loongarch/include/asm/elf.h
@@ -241,8 +241,6 @@ void loongarch_dump_regs64(u64 *uregs, const struct pt_regs *regs);
do { \
current->thread.vdso = &vdso_info; \
\
- loongarch_set_personality_fcsr(state); \
- \
if (personality(current->personality) != PER_LINUX) \
set_personality(PER_LINUX); \
} while (0)
@@ -259,7 +257,6 @@ do { \
clear_thread_flag(TIF_32BIT_ADDR); \
\
current->thread.vdso = &vdso_info; \
- loongarch_set_personality_fcsr(state); \
\
p = personality(current->personality); \
if (p != PER_LINUX32 && p != PER_LINUX) \
@@ -340,6 +337,4 @@ extern int arch_elf_pt_proc(void *ehdr, void *phdr, struct file *elf,
extern int arch_check_elf(void *ehdr, bool has_interpreter, void *interp_ehdr,
struct arch_elf_state *state);
-extern void loongarch_set_personality_fcsr(struct arch_elf_state *state);
-
#endif /* _ASM_ELF_H */
diff --git a/arch/loongarch/include/asm/ftrace.h b/arch/loongarch/include/asm/ftrace.h
index a11996eb5892dd169a1e5a0ba9ad20fb854f4be8..de891c2c83d4a980284cc5376dbc0934b7233a13 100644
--- a/arch/loongarch/include/asm/ftrace.h
+++ b/arch/loongarch/include/asm/ftrace.h
@@ -63,7 +63,7 @@ ftrace_regs_get_instruction_pointer(struct ftrace_regs *fregs)
static __always_inline void
ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, unsigned long ip)
{
- regs_set_return_value(&fregs->regs, ip);
+ instruction_pointer_set(&fregs->regs, ip);
}
#define ftrace_regs_get_argument(fregs, n) \
diff --git a/arch/loongarch/include/asm/shmparam.h b/arch/loongarch/include/asm/shmparam.h
deleted file mode 100644
index c9554f48d2dfab400add2d2c4e30ff6e44f1db14..0000000000000000000000000000000000000000
--- a/arch/loongarch/include/asm/shmparam.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
- */
-#ifndef _ASM_SHMPARAM_H
-#define _ASM_SHMPARAM_H
-
-#define __ARCH_FORCE_SHMLBA 1
-
-#define SHMLBA SZ_64K /* attach addr a multiple of this */
-
-#endif /* _ASM_SHMPARAM_H */
diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c
index 8e00a754e548943ae4dba5d330a1354426c713d1..b6b097bbf8668a400105dd408c696e4135c824d8 100644
--- a/arch/loongarch/kernel/acpi.c
+++ b/arch/loongarch/kernel/acpi.c
@@ -119,7 +119,7 @@ acpi_parse_eio_master(union acpi_subtable_headers *header, const unsigned long e
return -EINVAL;
core = eiointc->node * CORES_PER_EIO_NODE;
- set_bit(core, &(loongson_sysconf.cores_io_master));
+ set_bit(core, loongson_sysconf.cores_io_master);
return 0;
}
diff --git a/arch/loongarch/kernel/efi.c b/arch/loongarch/kernel/efi.c
index acb5d3385675c974d98a71b8b659ed1088914acd..000825406c1f62cdebd32e79714738987d20d5cc 100644
--- a/arch/loongarch/kernel/efi.c
+++ b/arch/loongarch/kernel/efi.c
@@ -140,4 +140,6 @@ void __init efi_init(void)
early_memunmap(tbl, sizeof(*tbl));
}
+
+ efi_esrt_init();
}
diff --git a/arch/loongarch/kernel/elf.c b/arch/loongarch/kernel/elf.c
index 183e94fc9c69ce8761f3d70b730558bd7f26ff55..0fa81ced28dcdd053cf79f0aaffa8b127df482e1 100644
--- a/arch/loongarch/kernel/elf.c
+++ b/arch/loongarch/kernel/elf.c
@@ -23,8 +23,3 @@ int arch_check_elf(void *_ehdr, bool has_interpreter, void *_interp_ehdr,
{
return 0;
}
-
-void loongarch_set_personality_fcsr(struct arch_elf_state *state)
-{
- current->thread.fpu.fcsr = boot_cpu_data.fpu_csr0;
-}
diff --git a/arch/loongarch/kernel/env.c b/arch/loongarch/kernel/env.c
index 6b3bfb0092e60b34946490415ff7cd2a51287886..2f1f5b08638f818c2abb7a617b3b79250812b3b8 100644
--- a/arch/loongarch/kernel/env.c
+++ b/arch/loongarch/kernel/env.c
@@ -5,13 +5,16 @@
* Copyright (C) 2020-2022 Loongson Technology Corporation Limited
*/
#include
+#include
#include
#include
#include
+#include
#include
#include
#include
#include
+#include
u64 efi_system_table;
struct loongson_system_configuration loongson_sysconf;
@@ -36,7 +39,16 @@ void __init init_environ(void)
static int __init init_cpu_fullname(void)
{
- int cpu;
+ struct device_node *root;
+ int cpu, ret;
+ char *model;
+
+ /* Parsing cpuname from DTS model property */
+ root = of_find_node_by_path("/");
+ ret = of_property_read_string(root, "model", (const char **)&model);
+ of_node_put(root);
+ if (ret == 0)
+ loongson_sysconf.cpuname = strsep(&model, " ");
if (loongson_sysconf.cpuname && !strncmp(loongson_sysconf.cpuname, "Loongson", 8)) {
for (cpu = 0; cpu < NR_CPUS; cpu++)
@@ -46,6 +58,26 @@ static int __init init_cpu_fullname(void)
}
arch_initcall(init_cpu_fullname);
+static int __init fdt_cpu_clk_init(void)
+{
+ struct clk *clk;
+ struct device_node *np;
+
+ np = of_get_cpu_node(0, NULL);
+ if (!np)
+ return -ENODEV;
+
+ clk = of_clk_get(np, 0);
+ if (IS_ERR(clk))
+ return -ENODEV;
+
+ cpu_clock_freq = clk_get_rate(clk);
+ clk_put(clk);
+
+ return 0;
+}
+late_initcall(fdt_cpu_clk_init);
+
static ssize_t boardinfo_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S
index 0ecab4216392899cf8655d0d67228cb280c6df02..c4f7de2e28054ceb6458c964c26e86596cea8602 100644
--- a/arch/loongarch/kernel/head.S
+++ b/arch/loongarch/kernel/head.S
@@ -74,6 +74,11 @@ SYM_CODE_START(kernel_entry) # kernel entry point
la.pcrel t0, fw_arg2
st.d a2, t0, 0
+#ifdef CONFIG_PAGE_SIZE_4KB
+ li.d t0, 0
+ li.d t1, CSR_STFILL
+ csrxchg t0, t1, LOONGARCH_CSR_IMPCTL1
+#endif
/* KSave3 used for percpu base, initialized as 0 */
csrwr zero, PERCPU_BASE_KS
/* GPR21 used for percpu base (runtime), initialized as 0 */
@@ -126,6 +131,11 @@ SYM_CODE_START(smpboot_entry)
JUMP_VIRT_ADDR t0, t1
+#ifdef CONFIG_PAGE_SIZE_4KB
+ li.d t0, 0
+ li.d t1, CSR_STFILL
+ csrxchg t0, t1, LOONGARCH_CSR_IMPCTL1
+#endif
/* Enable PG */
li.w t0, 0xb0 # PLV=0, IE=0, PG=1
csrwr t0, LOONGARCH_CSR_CRMD
diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c
index 767d94cce0de07d74892733b339a55dd5e6ded0e..f2ff8b5d591e4fd638109d2c98d75543c01a112c 100644
--- a/arch/loongarch/kernel/process.c
+++ b/arch/loongarch/kernel/process.c
@@ -85,6 +85,7 @@ void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp)
regs->csr_euen = euen;
lose_fpu(0);
lose_lbt(0);
+ current->thread.fpu.fcsr = boot_cpu_data.fpu_csr0;
clear_thread_flag(TIF_LSX_CTX_LIVE);
clear_thread_flag(TIF_LASX_CTX_LIVE);
diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index d183a745fb85d4efcef51bbdab6d09a1e047b966..edf2bba80130670364e144ad301868a7dfd3bf93 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -252,38 +252,23 @@ static void __init arch_reserve_vmcore(void)
#endif
}
-/* 2MB alignment for crash kernel regions */
-#define CRASH_ALIGN SZ_2M
-#define CRASH_ADDR_MAX SZ_4G
-
-static void __init arch_parse_crashkernel(void)
+static void __init arch_reserve_crashkernel(void)
{
-#ifdef CONFIG_KEXEC
int ret;
- unsigned long long total_mem;
+ unsigned long long low_size = 0;
unsigned long long crash_base, crash_size;
+ char *cmdline = boot_command_line;
+ bool high = false;
- total_mem = memblock_phys_mem_size();
- ret = parse_crashkernel(boot_command_line, total_mem,
- &crash_size, &crash_base,
- NULL, NULL);
- if (ret < 0 || crash_size <= 0)
+ if (!IS_ENABLED(CONFIG_KEXEC_CORE))
return;
- if (crash_base <= 0) {
- crash_base = memblock_phys_alloc_range(crash_size, CRASH_ALIGN, CRASH_ALIGN, CRASH_ADDR_MAX);
- if (!crash_base) {
- pr_warn("crashkernel reservation failed - No suitable area found.\n");
- return;
- }
- } else if (!memblock_phys_alloc_range(crash_size, CRASH_ALIGN, crash_base, crash_base + crash_size)) {
- pr_warn("Invalid memory region reserved for crash kernel\n");
+ ret = parse_crashkernel(cmdline, memblock_phys_mem_size(),
+ &crash_size, &crash_base, &low_size, &high);
+ if (ret)
return;
- }
- crashk_res.start = crash_base;
- crashk_res.end = crash_base + crash_size - 1;
-#endif
+ reserve_crashkernel_generic(cmdline, crash_size, crash_base, low_size, high);
}
static void __init fdt_setup(void)
@@ -295,8 +280,12 @@ static void __init fdt_setup(void)
if (acpi_os_get_root_pointer())
return;
- /* Look for a device tree configuration table entry */
- fdt_pointer = efi_fdt_pointer();
+ /* Prefer to use built-in dtb, checking its legality first. */
+ if (!fdt_check_header(__dtb_start))
+ fdt_pointer = __dtb_start;
+ else
+ fdt_pointer = efi_fdt_pointer(); /* Fallback to firmware dtb */
+
if (!fdt_pointer || fdt_check_header(fdt_pointer))
return;
@@ -330,7 +319,9 @@ static void __init bootcmdline_init(char **cmdline_p)
if (boot_command_line[0])
strlcat(boot_command_line, " ", COMMAND_LINE_SIZE);
- strlcat(boot_command_line, init_command_line, COMMAND_LINE_SIZE);
+ if (!strstr(boot_command_line, init_command_line))
+ strlcat(boot_command_line, init_command_line, COMMAND_LINE_SIZE);
+
goto out;
}
#endif
@@ -357,7 +348,7 @@ static void __init bootcmdline_init(char **cmdline_p)
void __init platform_init(void)
{
arch_reserve_vmcore();
- arch_parse_crashkernel();
+ arch_reserve_crashkernel();
#ifdef CONFIG_ACPI_TABLE_UPGRADE
acpi_table_upgrade();
@@ -467,15 +458,6 @@ static void __init resource_init(void)
request_resource(res, &data_resource);
request_resource(res, &bss_resource);
}
-
-#ifdef CONFIG_KEXEC
- if (crashk_res.start < crashk_res.end) {
- insert_resource(&iomem_resource, &crashk_res);
- pr_info("Reserving %ldMB of memory at %ldMB for crashkernel\n",
- (unsigned long)((crashk_res.end - crashk_res.start + 1) >> 20),
- (unsigned long)(crashk_res.start >> 20));
- }
-#endif
}
static int __init add_legacy_isa_io(struct fwnode_handle *fwnode,
diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c
index 5bca12d16e0691c8e9511f6043a7a5af9655af20..a16e3dbe9f09eb2fbf1b239b982b727330f7c233 100644
--- a/arch/loongarch/kernel/smp.c
+++ b/arch/loongarch/kernel/smp.c
@@ -208,7 +208,7 @@ static void __init fdt_smp_setup(void)
}
loongson_sysconf.nr_cpus = num_processors;
- set_bit(0, &(loongson_sysconf.cores_io_master));
+ set_bit(0, loongson_sysconf.cores_io_master);
#endif
}
@@ -216,6 +216,9 @@ void __init loongson_smp_setup(void)
{
fdt_smp_setup();
+ if (loongson_sysconf.cores_per_package == 0)
+ loongson_sysconf.cores_per_package = num_processors;
+
cpu_data[0].core = cpu_logical_map(0) % loongson_sysconf.cores_per_package;
cpu_data[0].package = cpu_logical_map(0) / loongson_sysconf.cores_per_package;
diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c
index 4fcd6cd6da234d4dc4120cb2c4b95a69e2577358..e73323d759d0b85b275aa389fc684b74d12cb13e 100644
--- a/arch/loongarch/net/bpf_jit.c
+++ b/arch/loongarch/net/bpf_jit.c
@@ -201,6 +201,11 @@ bool bpf_jit_supports_kfunc_call(void)
return true;
}
+bool bpf_jit_supports_far_kfunc_call(void)
+{
+ return true;
+}
+
/* initialized on the first pass of build_body() */
static int out_offset = -1;
static int emit_bpf_tail_call(struct jit_ctx *ctx)
@@ -465,7 +470,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
const u8 dst = regmap[insn->dst_reg];
const s16 off = insn->off;
const s32 imm = insn->imm;
- const u64 imm64 = (u64)(insn + 1)->imm << 32 | (u32)insn->imm;
const bool is32 = BPF_CLASS(insn->code) == BPF_ALU || BPF_CLASS(insn->code) == BPF_JMP32;
switch (code) {
@@ -923,8 +927,12 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
/* dst = imm64 */
case BPF_LD | BPF_IMM | BPF_DW:
+ {
+ const u64 imm64 = (u64)(insn + 1)->imm << 32 | (u32)insn->imm;
+
move_imm(ctx, dst, imm64, is32);
return 1;
+ }
/* dst = *(size *)(src + off) */
case BPF_LDX | BPF_MEM | BPF_B:
diff --git a/arch/mips/configs/ip27_defconfig b/arch/mips/configs/ip27_defconfig
index b51f738a39a05ad9bd4c41971027774365ec30da..4714074c8bd7f557ee57e7f0354d1f411bb1e04d 100644
--- a/arch/mips/configs/ip27_defconfig
+++ b/arch/mips/configs/ip27_defconfig
@@ -287,7 +287,8 @@ CONFIG_BTRFS_FS_POSIX_ACL=y
CONFIG_QUOTA_NETLINK_INTERFACE=y
CONFIG_FUSE_FS=m
CONFIG_CUSE=m
-CONFIG_FSCACHE=m
+CONFIG_NETFS_SUPPORT=m
+CONFIG_FSCACHE=y
CONFIG_FSCACHE_STATS=y
CONFIG_CACHEFILES=m
CONFIG_PROC_KCORE=y
diff --git a/arch/mips/configs/lemote2f_defconfig b/arch/mips/configs/lemote2f_defconfig
index 38f17b6584218739adbe4c8139f21be774101cf5..3389e6e885d9fa104a5342cd1d5a22fe5639c36c 100644
--- a/arch/mips/configs/lemote2f_defconfig
+++ b/arch/mips/configs/lemote2f_defconfig
@@ -238,7 +238,8 @@ CONFIG_BTRFS_FS=m
CONFIG_QUOTA=y
CONFIG_QFMT_V2=m
CONFIG_AUTOFS_FS=m
-CONFIG_FSCACHE=m
+CONFIG_NETFS_SUPPORT=m
+CONFIG_FSCACHE=y
CONFIG_CACHEFILES=m
CONFIG_ISO9660_FS=m
CONFIG_JOLIET=y
diff --git a/arch/mips/configs/loongson3_defconfig b/arch/mips/configs/loongson3_defconfig
index 07839a4b397e5bcc006a68d06286a3d9d8d11875..78f4987520664b4e606e85ef3a7d78183a205aa0 100644
--- a/arch/mips/configs/loongson3_defconfig
+++ b/arch/mips/configs/loongson3_defconfig
@@ -356,7 +356,8 @@ CONFIG_QFMT_V2=m
CONFIG_AUTOFS_FS=y
CONFIG_FUSE_FS=m
CONFIG_VIRTIO_FS=m
-CONFIG_FSCACHE=m
+CONFIG_NETFS_SUPPORT=m
+CONFIG_FSCACHE=y
CONFIG_ISO9660_FS=m
CONFIG_JOLIET=y
CONFIG_MSDOS_FS=m
diff --git a/arch/mips/configs/pic32mzda_defconfig b/arch/mips/configs/pic32mzda_defconfig
index 166d2ad372d142d9a919d83d073588f4f02ea80a..54774f90c23eafa397784f15d8f38b40c5a1254b 100644
--- a/arch/mips/configs/pic32mzda_defconfig
+++ b/arch/mips/configs/pic32mzda_defconfig
@@ -68,7 +68,8 @@ CONFIG_EXT4_FS_POSIX_ACL=y
CONFIG_EXT4_FS_SECURITY=y
CONFIG_AUTOFS_FS=m
CONFIG_FUSE_FS=m
-CONFIG_FSCACHE=m
+CONFIG_NETFS_SUPPORT=m
+CONFIG_FSCACHE=y
CONFIG_ISO9660_FS=m
CONFIG_JOLIET=y
CONFIG_ZISOFS=y
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 414b978b8010b0cbac4511b606ee16c1a5236cc8..b9fc064d38d281f1c32584e79edd705c670b1731 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -859,6 +859,7 @@ config THREAD_SHIFT
int "Thread shift" if EXPERT
range 13 15
default "15" if PPC_256K_PAGES
+ default "15" if PPC_PSERIES || PPC_POWERNV
default "14" if PPC64
default "13"
help
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index b549499eb3632c1da07b1a2b82b9d24b77e56eb5..bffbd869a0682842883591788da784648acf1626 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -53,6 +53,7 @@ config RISCV
select ARCH_USE_MEMTEST
select ARCH_USE_QUEUED_RWLOCKS
select ARCH_USES_CFI_TRAPS if CFI_CLANG
+ select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH if SMP && MMU
select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU
select ARCH_WANT_FRAME_POINTERS
select ARCH_WANT_GENERAL_HUGETLB if !RISCV_ISA_SVNAPOT
@@ -66,9 +67,10 @@ config RISCV
select CLINT_TIMER if !MMU
select CLONE_BACKWARDS
select COMMON_CLK
- select CPU_PM if CPU_IDLE || HIBERNATION
+ select CPU_PM if CPU_IDLE || HIBERNATION || SUSPEND
select EDAC_SUPPORT
select FRAME_POINTER if PERF_EVENTS || (FUNCTION_TRACER && !DYNAMIC_FTRACE)
+ select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY if DYNAMIC_FTRACE
select GENERIC_ARCH_TOPOLOGY
select GENERIC_ATOMIC64 if !64BIT
select GENERIC_CLOCKEVENTS_BROADCAST if SMP
@@ -115,6 +117,7 @@ config RISCV
select HAVE_DEBUG_KMEMLEAK
select HAVE_DMA_CONTIGUOUS if MMU
select HAVE_DYNAMIC_FTRACE if !XIP_KERNEL && MMU && (CLANG_SUPPORTS_DYNAMIC_FTRACE || GCC_SUPPORTS_DYNAMIC_FTRACE)
+ select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
select HAVE_DYNAMIC_FTRACE_WITH_REGS if HAVE_DYNAMIC_FTRACE
select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
select HAVE_FUNCTION_GRAPH_TRACER
@@ -142,6 +145,8 @@ config RISCV
select HAVE_REGS_AND_STACK_ACCESS_API
select HAVE_RETHOOK if !XIP_KERNEL
select HAVE_RSEQ
+ select HAVE_SAMPLE_FTRACE_DIRECT
+ select HAVE_SAMPLE_FTRACE_DIRECT_MULTI
select HAVE_STACKPROTECTOR
select HAVE_SYSCALL_TRACEPOINTS
select HOTPLUG_CORE_SYNC_DEAD if HOTPLUG_CPU
@@ -183,6 +188,20 @@ config HAVE_SHADOW_CALL_STACK
# https://github.com/riscv-non-isa/riscv-elf-psabi-doc/commit/a484e843e6eeb51f0cb7b8819e50da6d2444d769
depends on $(ld-option,--no-relax-gp)
+config RISCV_USE_LINKER_RELAXATION
+ def_bool y
+ # https://github.com/llvm/llvm-project/commit/6611d58f5bbcbec77262d392e2923e1d680f6985
+ depends on !LD_IS_LLD || LLD_VERSION >= 150000
+
+# https://github.com/llvm/llvm-project/commit/bbc0f99f3bc96f1db16f649fc21dd18e5b0918f6
+config ARCH_HAS_BROKEN_DWARF5
+ def_bool y
+ depends on RISCV_USE_LINKER_RELAXATION
+ # https://github.com/llvm/llvm-project/commit/1df5ea29b43690b6622db2cad7b745607ca4de6a
+ depends on AS_IS_LLVM && AS_VERSION < 180000
+ # https://github.com/llvm/llvm-project/commit/7ffabb61a5569444b5ac9322e22e5471cc5e4a77
+ depends on LD_IS_LLD && LLD_VERSION < 180000
+
config ARCH_MMAP_RND_BITS_MIN
default 18 if 64BIT
default 8
@@ -529,6 +548,28 @@ config RISCV_ISA_V_DEFAULT_ENABLE
If you don't know what to do here, say Y.
+config RISCV_ISA_V_UCOPY_THRESHOLD
+ int "Threshold size for vectorized user copies"
+ depends on RISCV_ISA_V
+ default 768
+ help
+ Prefer using vectorized copy_to_user()/copy_from_user() when the
+ workload size exceeds this value.
+
+config RISCV_ISA_V_PREEMPTIVE
+ bool "Run kernel-mode Vector with kernel preemption"
+ depends on PREEMPTION
+ depends on RISCV_ISA_V
+ default y
+ help
+ Usually, in-kernel SIMD routines are run with preemption disabled.
+ Functions which envoke long running SIMD thus must yield core's
+ vector unit to prevent blocking other tasks for too long.
+
+ This config allows kernel to run SIMD without explicitly disable
+ preemption. Enabling this config will result in higher memory
+ consumption due to the allocation of per-task's kernel Vector context.
+
config TOOLCHAIN_HAS_ZBB
bool
default y
@@ -655,6 +696,20 @@ config RISCV_MISALIGNED
load/store for both kernel and userspace. When disable, misaligned
accesses will generate SIGBUS in userspace and panic in kernel.
+config RISCV_EFFICIENT_UNALIGNED_ACCESS
+ bool "Assume the CPU supports fast unaligned memory accesses"
+ depends on NONPORTABLE
+ select DCACHE_WORD_ACCESS if MMU
+ select HAVE_EFFICIENT_UNALIGNED_ACCESS
+ help
+ Say Y here if you want the kernel to assume that the CPU supports
+ efficient unaligned memory accesses. When enabled, this option
+ improves the performance of the kernel on such CPUs. However, the
+ kernel will run much more slowly, or will not be able to run at all,
+ on CPUs that do not support efficient unaligned memory accesses.
+
+ If unsure what to do here, say N.
+
endmenu # "Platform type"
menu "Kernel features"
diff --git a/arch/riscv/Kconfig.errata b/arch/riscv/Kconfig.errata
index f5c432b005e77a46b4cdc1ed3f8b8ae160d2b1a0..910ba8837add866f622fba84f7c0c3535ee175e6 100644
--- a/arch/riscv/Kconfig.errata
+++ b/arch/riscv/Kconfig.errata
@@ -98,6 +98,7 @@ config ERRATA_THEAD_CMO
depends on ERRATA_THEAD && MMU
select DMA_DIRECT_REMAP
select RISCV_DMA_NONCOHERENT
+ select RISCV_NONSTANDARD_CACHE_OPS
default y
help
This will apply the cache management errata to handle the
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index a74be78678eb0bcabf3d9571669a125401adb64d..0b7d109258e7d850846bb3c5f084a0482f07d02b 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -43,8 +43,7 @@ else
KBUILD_LDFLAGS += -melf32lriscv
endif
-ifeq ($(CONFIG_LD_IS_LLD),y)
-ifeq ($(call test-lt, $(CONFIG_LLD_VERSION), 150000),y)
+ifndef CONFIG_RISCV_USE_LINKER_RELAXATION
KBUILD_CFLAGS += -mno-relax
KBUILD_AFLAGS += -mno-relax
ifndef CONFIG_AS_IS_LLVM
@@ -52,7 +51,6 @@ ifndef CONFIG_AS_IS_LLVM
KBUILD_AFLAGS += -Wa,-mno-relax
endif
endif
-endif
ifeq ($(CONFIG_SHADOW_CALL_STACK),y)
KBUILD_LDFLAGS += --no-relax-gp
@@ -108,7 +106,9 @@ KBUILD_AFLAGS_MODULE += $(call as-option,-Wa$(comma)-mno-relax)
# unaligned accesses. While unaligned accesses are explicitly allowed in the
# RISC-V ISA, they're emulated by machine mode traps on all extant
# architectures. It's faster to have GCC emit only aligned accesses.
+ifneq ($(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS),y)
KBUILD_CFLAGS += $(call cc-option,-mstrict-align)
+endif
ifeq ($(CONFIG_STACKPROTECTOR_PER_TASK),y)
prepare: stack_protector_prepare
@@ -163,6 +163,8 @@ BOOT_TARGETS := Image Image.gz loader loader.bin xipImage vmlinuz.efi
all: $(notdir $(KBUILD_IMAGE))
+loader.bin: loader
+Image.gz loader vmlinuz.efi: Image
$(BOOT_TARGETS): vmlinux
$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
@$(kecho) ' Kernel: $(boot)/$@ is ready'
diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig
index 905881282a7cd115fa222a68faab57545e868e10..eaf34e871e308f0db7a0a578b34940d8d551b163 100644
--- a/arch/riscv/configs/defconfig
+++ b/arch/riscv/configs/defconfig
@@ -149,6 +149,7 @@ CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_SERIAL_8250_DW=y
CONFIG_SERIAL_OF_PLATFORM=y
CONFIG_SERIAL_SH_SCI=y
+CONFIG_SERIAL_EARLYCON_RISCV_SBI=y
CONFIG_VIRTIO_CONSOLE=y
CONFIG_HW_RANDOM=y
CONFIG_HW_RANDOM_VIRTIO=y
diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c
index 0554ed4bf087cf6cd06dc2967c0c2c38e9784887..b1c410bbc1aece3c1fe0bea8cbd68271c8c0e29a 100644
--- a/arch/riscv/errata/thead/errata.c
+++ b/arch/riscv/errata/thead/errata.c
@@ -12,8 +12,10 @@
#include
#include
#include
+#include
#include
#include
+#include
#include
#include
@@ -33,6 +35,69 @@ static bool errata_probe_pbmt(unsigned int stage,
return false;
}
+/*
+ * th.dcache.ipa rs1 (invalidate, physical address)
+ * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
+ * 0000001 01010 rs1 000 00000 0001011
+ * th.dcache.iva rs1 (invalidate, virtual address)
+ * 0000001 00110 rs1 000 00000 0001011
+ *
+ * th.dcache.cpa rs1 (clean, physical address)
+ * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
+ * 0000001 01001 rs1 000 00000 0001011
+ * th.dcache.cva rs1 (clean, virtual address)
+ * 0000001 00101 rs1 000 00000 0001011
+ *
+ * th.dcache.cipa rs1 (clean then invalidate, physical address)
+ * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
+ * 0000001 01011 rs1 000 00000 0001011
+ * th.dcache.civa rs1 (clean then invalidate, virtual address)
+ * 0000001 00111 rs1 000 00000 0001011
+ *
+ * th.sync.s (make sure all cache operations finished)
+ * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
+ * 0000000 11001 00000 000 00000 0001011
+ */
+#define THEAD_INVAL_A0 ".long 0x02a5000b"
+#define THEAD_CLEAN_A0 ".long 0x0295000b"
+#define THEAD_FLUSH_A0 ".long 0x02b5000b"
+#define THEAD_SYNC_S ".long 0x0190000b"
+
+#define THEAD_CMO_OP(_op, _start, _size, _cachesize) \
+asm volatile("mv a0, %1\n\t" \
+ "j 2f\n\t" \
+ "3:\n\t" \
+ THEAD_##_op##_A0 "\n\t" \
+ "add a0, a0, %0\n\t" \
+ "2:\n\t" \
+ "bltu a0, %2, 3b\n\t" \
+ THEAD_SYNC_S \
+ : : "r"(_cachesize), \
+ "r"((unsigned long)(_start) & ~((_cachesize) - 1UL)), \
+ "r"((unsigned long)(_start) + (_size)) \
+ : "a0")
+
+static void thead_errata_cache_inv(phys_addr_t paddr, size_t size)
+{
+ THEAD_CMO_OP(INVAL, paddr, size, riscv_cbom_block_size);
+}
+
+static void thead_errata_cache_wback(phys_addr_t paddr, size_t size)
+{
+ THEAD_CMO_OP(CLEAN, paddr, size, riscv_cbom_block_size);
+}
+
+static void thead_errata_cache_wback_inv(phys_addr_t paddr, size_t size)
+{
+ THEAD_CMO_OP(FLUSH, paddr, size, riscv_cbom_block_size);
+}
+
+static const struct riscv_nonstd_cache_ops thead_errata_cmo_ops = {
+ .wback = &thead_errata_cache_wback,
+ .inv = &thead_errata_cache_inv,
+ .wback_inv = &thead_errata_cache_wback_inv,
+};
+
static bool errata_probe_cmo(unsigned int stage,
unsigned long arch_id, unsigned long impid)
{
@@ -48,6 +113,7 @@ static bool errata_probe_cmo(unsigned int stage,
if (stage == RISCV_ALTERNATIVES_BOOT) {
riscv_cbom_block_size = L1_CACHE_BYTES;
riscv_noncoherent_supported();
+ riscv_noncoherent_register_cache_ops(&thead_errata_cmo_ops);
}
return true;
@@ -77,8 +143,7 @@ static u32 thead_errata_probe(unsigned int stage,
if (errata_probe_pbmt(stage, archid, impid))
cpu_req_errata |= BIT(ERRATA_THEAD_PBMT);
- if (errata_probe_cmo(stage, archid, impid))
- cpu_req_errata |= BIT(ERRATA_THEAD_CMO);
+ errata_probe_cmo(stage, archid, impid);
if (errata_probe_pmu(stage, archid, impid))
cpu_req_errata |= BIT(ERRATA_THEAD_PMU);
diff --git a/arch/riscv/include/asm/arch_hweight.h b/arch/riscv/include/asm/arch_hweight.h
new file mode 100644
index 0000000000000000000000000000000000000000..c20236a0725b9e27a31d28b580db1bd1ad2c945a
--- /dev/null
+++ b/arch/riscv/include/asm/arch_hweight.h
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Based on arch/x86/include/asm/arch_hweight.h
+ */
+
+#ifndef _ASM_RISCV_HWEIGHT_H
+#define _ASM_RISCV_HWEIGHT_H
+
+#include
+#include
+
+#if (BITS_PER_LONG == 64)
+#define CPOPW "cpopw "
+#elif (BITS_PER_LONG == 32)
+#define CPOPW "cpop "
+#else
+#error "Unexpected BITS_PER_LONG"
+#endif
+
+static __always_inline unsigned int __arch_hweight32(unsigned int w)
+{
+#ifdef CONFIG_RISCV_ISA_ZBB
+ asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+ RISCV_ISA_EXT_ZBB, 1)
+ : : : : legacy);
+
+ asm (".option push\n"
+ ".option arch,+zbb\n"
+ CPOPW "%0, %0\n"
+ ".option pop\n"
+ : "+r" (w) : :);
+
+ return w;
+
+legacy:
+#endif
+ return __sw_hweight32(w);
+}
+
+static inline unsigned int __arch_hweight16(unsigned int w)
+{
+ return __arch_hweight32(w & 0xffff);
+}
+
+static inline unsigned int __arch_hweight8(unsigned int w)
+{
+ return __arch_hweight32(w & 0xff);
+}
+
+#if BITS_PER_LONG == 64
+static __always_inline unsigned long __arch_hweight64(__u64 w)
+{
+# ifdef CONFIG_RISCV_ISA_ZBB
+ asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+ RISCV_ISA_EXT_ZBB, 1)
+ : : : : legacy);
+
+ asm (".option push\n"
+ ".option arch,+zbb\n"
+ "cpop %0, %0\n"
+ ".option pop\n"
+ : "+r" (w) : :);
+
+ return w;
+
+legacy:
+# endif
+ return __sw_hweight64(w);
+}
+#else /* BITS_PER_LONG == 64 */
+static inline unsigned long __arch_hweight64(__u64 w)
+{
+ return __arch_hweight32((u32)w) +
+ __arch_hweight32((u32)(w >> 32));
+}
+#endif /* !(BITS_PER_LONG == 64) */
+
+#endif /* _ASM_RISCV_HWEIGHT_H */
diff --git a/arch/riscv/include/asm/archrandom.h b/arch/riscv/include/asm/archrandom.h
new file mode 100644
index 0000000000000000000000000000000000000000..5345360adfb9cf183b831e41191a828bc87049b5
--- /dev/null
+++ b/arch/riscv/include/asm/archrandom.h
@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Kernel interface for the RISCV arch_random_* functions
+ *
+ * Copyright (c) 2023 Rivos Inc.
+ *
+ */
+
+#ifndef ASM_RISCV_ARCHRANDOM_H
+#define ASM_RISCV_ARCHRANDOM_H
+
+#include
+#include
+
+#define SEED_RETRY_LOOPS 100
+
+static inline bool __must_check csr_seed_long(unsigned long *v)
+{
+ unsigned int retry = SEED_RETRY_LOOPS, valid_seeds = 0;
+ const int needed_seeds = sizeof(long) / sizeof(u16);
+ u16 *entropy = (u16 *)v;
+
+ do {
+ /*
+ * The SEED CSR must be accessed with a read-write instruction.
+ */
+ unsigned long csr_seed = csr_swap(CSR_SEED, 0);
+ unsigned long opst = csr_seed & SEED_OPST_MASK;
+
+ switch (opst) {
+ case SEED_OPST_ES16:
+ entropy[valid_seeds++] = csr_seed & SEED_ENTROPY_MASK;
+ if (valid_seeds == needed_seeds)
+ return true;
+ break;
+
+ case SEED_OPST_DEAD:
+ pr_err_once("archrandom: Unrecoverable error\n");
+ return false;
+
+ case SEED_OPST_BIST:
+ case SEED_OPST_WAIT:
+ default:
+ cpu_relax();
+ continue;
+ }
+ } while (--retry);
+
+ return false;
+}
+
+static inline size_t __must_check arch_get_random_longs(unsigned long *v, size_t max_longs)
+{
+ return 0;
+}
+
+static inline size_t __must_check arch_get_random_seed_longs(unsigned long *v, size_t max_longs)
+{
+ if (!max_longs)
+ return 0;
+
+ /*
+ * If Zkr is supported and csr_seed_long succeeds, we return one long
+ * worth of entropy.
+ */
+ if (riscv_has_extension_likely(RISCV_ISA_EXT_ZKR) && csr_seed_long(v))
+ return 1;
+
+ return 0;
+}
+
+#endif /* ASM_RISCV_ARCHRANDOM_H */
diff --git a/arch/riscv/include/asm/asm-extable.h b/arch/riscv/include/asm/asm-extable.h
index 00a96e7a966445175a687d481efa29f6862b3675..0c8bfd54fc4e05beec2fed22fc7f73ddcc997ab7 100644
--- a/arch/riscv/include/asm/asm-extable.h
+++ b/arch/riscv/include/asm/asm-extable.h
@@ -6,6 +6,7 @@
#define EX_TYPE_FIXUP 1
#define EX_TYPE_BPF 2
#define EX_TYPE_UACCESS_ERR_ZERO 3
+#define EX_TYPE_LOAD_UNALIGNED_ZEROPAD 4
#ifdef CONFIG_MMU
@@ -47,6 +48,11 @@
#define EX_DATA_REG_ZERO_SHIFT 5
#define EX_DATA_REG_ZERO GENMASK(9, 5)
+#define EX_DATA_REG_DATA_SHIFT 0
+#define EX_DATA_REG_DATA GENMASK(4, 0)
+#define EX_DATA_REG_ADDR_SHIFT 5
+#define EX_DATA_REG_ADDR GENMASK(9, 5)
+
#define EX_DATA_REG(reg, gpr) \
"((.L__gpr_num_" #gpr ") << " __stringify(EX_DATA_REG_##reg##_SHIFT) ")"
@@ -62,6 +68,15 @@
#define _ASM_EXTABLE_UACCESS_ERR(insn, fixup, err) \
_ASM_EXTABLE_UACCESS_ERR_ZERO(insn, fixup, err, zero)
+#define _ASM_EXTABLE_LOAD_UNALIGNED_ZEROPAD(insn, fixup, data, addr) \
+ __DEFINE_ASM_GPR_NUMS \
+ __ASM_EXTABLE_RAW(#insn, #fixup, \
+ __stringify(EX_TYPE_LOAD_UNALIGNED_ZEROPAD), \
+ "(" \
+ EX_DATA_REG(DATA, data) " | " \
+ EX_DATA_REG(ADDR, addr) \
+ ")")
+
#endif /* __ASSEMBLY__ */
#else /* CONFIG_MMU */
diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h
index 36b955c762ba08e92ca0441ee8fbae9219c1f2fa..cd627ec289f163a630b73dd03dd52a6b28692997 100644
--- a/arch/riscv/include/asm/asm-prototypes.h
+++ b/arch/riscv/include/asm/asm-prototypes.h
@@ -9,6 +9,33 @@ long long __lshrti3(long long a, int b);
long long __ashrti3(long long a, int b);
long long __ashlti3(long long a, int b);
+#ifdef CONFIG_RISCV_ISA_V
+
+#ifdef CONFIG_MMU
+asmlinkage int enter_vector_usercopy(void *dst, void *src, size_t n);
+#endif /* CONFIG_MMU */
+
+void xor_regs_2_(unsigned long bytes, unsigned long *__restrict p1,
+ const unsigned long *__restrict p2);
+void xor_regs_3_(unsigned long bytes, unsigned long *__restrict p1,
+ const unsigned long *__restrict p2,
+ const unsigned long *__restrict p3);
+void xor_regs_4_(unsigned long bytes, unsigned long *__restrict p1,
+ const unsigned long *__restrict p2,
+ const unsigned long *__restrict p3,
+ const unsigned long *__restrict p4);
+void xor_regs_5_(unsigned long bytes, unsigned long *__restrict p1,
+ const unsigned long *__restrict p2,
+ const unsigned long *__restrict p3,
+ const unsigned long *__restrict p4,
+ const unsigned long *__restrict p5);
+
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+asmlinkage void riscv_v_context_nesting_start(struct pt_regs *regs);
+asmlinkage void riscv_v_context_nesting_end(struct pt_regs *regs);
+#endif /* CONFIG_RISCV_ISA_V_PREEMPTIVE */
+
+#endif /* CONFIG_RISCV_ISA_V */
#define DECLARE_DO_ERROR_INFO(name) asmlinkage void name(struct pt_regs *regs)
diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h
index 224b4dc02b50bc6761cbef064445e472ef053ce2..9ffc355370248aed22dbe690ba1cde8e682a3588 100644
--- a/arch/riscv/include/asm/bitops.h
+++ b/arch/riscv/include/asm/bitops.h
@@ -271,7 +271,9 @@ static __always_inline int variable_fls(unsigned int x)
#include
#include
-#include
+#include
+
+#include
#if (BITS_PER_LONG == 64)
#define __AMO(op) "amo" #op ".d"
diff --git a/arch/riscv/include/asm/checksum.h b/arch/riscv/include/asm/checksum.h
new file mode 100644
index 0000000000000000000000000000000000000000..a5b60b54b101c3ba1e550b3e16e7096a6bfc8357
--- /dev/null
+++ b/arch/riscv/include/asm/checksum.h
@@ -0,0 +1,93 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Checksum routines
+ *
+ * Copyright (C) 2023 Rivos Inc.
+ */
+#ifndef __ASM_RISCV_CHECKSUM_H
+#define __ASM_RISCV_CHECKSUM_H
+
+#include
+#include
+
+#define ip_fast_csum ip_fast_csum
+
+extern unsigned int do_csum(const unsigned char *buff, int len);
+#define do_csum do_csum
+
+/* Default version is sufficient for 32 bit */
+#ifndef CONFIG_32BIT
+#define _HAVE_ARCH_IPV6_CSUM
+__sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+ const struct in6_addr *daddr,
+ __u32 len, __u8 proto, __wsum sum);
+#endif
+
+/* Define riscv versions of functions before importing asm-generic/checksum.h */
+#include
+
+/**
+ * Quickly compute an IP checksum with the assumption that IPv4 headers will
+ * always be in multiples of 32-bits, and have an ihl of at least 5.
+ *
+ * @ihl: the number of 32 bit segments and must be greater than or equal to 5.
+ * @iph: assumed to be word aligned given that NET_IP_ALIGN is set to 2 on
+ * riscv, defining IP headers to be aligned.
+ */
+static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
+{
+ unsigned long csum = 0;
+ int pos = 0;
+
+ do {
+ csum += ((const unsigned int *)iph)[pos];
+ if (IS_ENABLED(CONFIG_32BIT))
+ csum += csum < ((const unsigned int *)iph)[pos];
+ } while (++pos < ihl);
+
+ /*
+ * ZBB only saves three instructions on 32-bit and five on 64-bit so not
+ * worth checking if supported without Alternatives.
+ */
+ if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) &&
+ IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
+ unsigned long fold_temp;
+
+ asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
+ RISCV_ISA_EXT_ZBB, 1)
+ :
+ :
+ :
+ : no_zbb);
+
+ if (IS_ENABLED(CONFIG_32BIT)) {
+ asm(".option push \n\
+ .option arch,+zbb \n\
+ not %[fold_temp], %[csum] \n\
+ rori %[csum], %[csum], 16 \n\
+ sub %[csum], %[fold_temp], %[csum] \n\
+ .option pop"
+ : [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp));
+ } else {
+ asm(".option push \n\
+ .option arch,+zbb \n\
+ rori %[fold_temp], %[csum], 32 \n\
+ add %[csum], %[fold_temp], %[csum] \n\
+ srli %[csum], %[csum], 32 \n\
+ not %[fold_temp], %[csum] \n\
+ roriw %[csum], %[csum], 16 \n\
+ subw %[csum], %[fold_temp], %[csum] \n\
+ .option pop"
+ : [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp));
+ }
+ return (__force __sum16)(csum >> 16);
+ }
+no_zbb:
+#ifndef CONFIG_32BIT
+ csum += ror64(csum, 32);
+ csum >>= 32;
+#endif
+ return csum_fold((__force __wsum)csum);
+}
+
+#endif /* __ASM_RISCV_CHECKSUM_H */
diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
index fbdde8b8a47edf7c1c2fae9249dd1712471c01dc..5a626ed2c47a8915b3848df2e7f4a7ea0601bd71 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -135,4 +135,6 @@ static __always_inline bool riscv_cpu_has_extension_unlikely(int cpu, const unsi
return __riscv_isa_extension_available(hart_isa[cpu].isa, ext);
}
+DECLARE_STATIC_KEY_FALSE(fast_misaligned_access_speed_key);
+
#endif
diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h
index 306a19a5509c10e63663330b04e1118abb054b74..510014051f5dbb1aa61098e4974e7e7ac02145ee 100644
--- a/arch/riscv/include/asm/csr.h
+++ b/arch/riscv/include/asm/csr.h
@@ -411,6 +411,15 @@
#define CSR_VTYPE 0xc21
#define CSR_VLENB 0xc22
+/* Scalar Crypto Extension - Entropy */
+#define CSR_SEED 0x015
+#define SEED_OPST_MASK _AC(0xC0000000, UL)
+#define SEED_OPST_BIST _AC(0x00000000, UL)
+#define SEED_OPST_WAIT _AC(0x40000000, UL)
+#define SEED_OPST_ES16 _AC(0x80000000, UL)
+#define SEED_OPST_DEAD _AC(0xC0000000, UL)
+#define SEED_ENTROPY_MASK _AC(0xFFFF, UL)
+
#ifdef CONFIG_RISCV_M_MODE
# define CSR_STATUS CSR_MSTATUS
# define CSR_IE CSR_MIE
diff --git a/arch/riscv/include/asm/entry-common.h b/arch/riscv/include/asm/entry-common.h
index 7ab5e34318c85fe05df525a5f80a49d25051bcd7..2293e535f8659af02ef2e52ce1752827c415532e 100644
--- a/arch/riscv/include/asm/entry-common.h
+++ b/arch/riscv/include/asm/entry-common.h
@@ -4,6 +4,23 @@
#define _ASM_RISCV_ENTRY_COMMON_H
#include
+#include
+#include
+
+static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
+ unsigned long ti_work)
+{
+ if (ti_work & _TIF_RISCV_V_DEFER_RESTORE) {
+ clear_thread_flag(TIF_RISCV_V_DEFER_RESTORE);
+ /*
+ * We are already called with irq disabled, so go without
+ * keeping track of riscv_v_flags.
+ */
+ riscv_v_vstate_restore(¤t->thread.vstate, regs);
+ }
+}
+
+#define arch_exit_to_user_mode_prepare arch_exit_to_user_mode_prepare
void handle_page_fault(struct pt_regs *regs);
void handle_break(struct pt_regs *regs);
diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h
index 83ed25e4355343c25101882b7c0b31cf462af542..ea33288f8a25b4f76e59bd65e8f869ee842c6e14 100644
--- a/arch/riscv/include/asm/errata_list.h
+++ b/arch/riscv/include/asm/errata_list.h
@@ -24,9 +24,8 @@
#ifdef CONFIG_ERRATA_THEAD
#define ERRATA_THEAD_PBMT 0
-#define ERRATA_THEAD_CMO 1
-#define ERRATA_THEAD_PMU 2
-#define ERRATA_THEAD_NUMBER 3
+#define ERRATA_THEAD_PMU 1
+#define ERRATA_THEAD_NUMBER 2
#endif
#ifdef __ASSEMBLY__
@@ -94,54 +93,17 @@ asm volatile(ALTERNATIVE( \
#define ALT_THEAD_PMA(_val)
#endif
-/*
- * th.dcache.ipa rs1 (invalidate, physical address)
- * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
- * 0000001 01010 rs1 000 00000 0001011
- * th.dache.iva rs1 (invalida, virtual address)
- * 0000001 00110 rs1 000 00000 0001011
- *
- * th.dcache.cpa rs1 (clean, physical address)
- * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
- * 0000001 01001 rs1 000 00000 0001011
- * th.dcache.cva rs1 (clean, virtual address)
- * 0000001 00101 rs1 000 00000 0001011
- *
- * th.dcache.cipa rs1 (clean then invalidate, physical address)
- * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
- * 0000001 01011 rs1 000 00000 0001011
- * th.dcache.civa rs1 (... virtual address)
- * 0000001 00111 rs1 000 00000 0001011
- *
- * th.sync.s (make sure all cache operations finished)
- * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
- * 0000000 11001 00000 000 00000 0001011
- */
-#define THEAD_INVAL_A0 ".long 0x0265000b"
-#define THEAD_CLEAN_A0 ".long 0x0255000b"
-#define THEAD_FLUSH_A0 ".long 0x0275000b"
-#define THEAD_SYNC_S ".long 0x0190000b"
-
#define ALT_CMO_OP(_op, _start, _size, _cachesize) \
-asm volatile(ALTERNATIVE_2( \
- __nops(6), \
+asm volatile(ALTERNATIVE( \
+ __nops(5), \
"mv a0, %1\n\t" \
"j 2f\n\t" \
"3:\n\t" \
CBO_##_op(a0) \
"add a0, a0, %0\n\t" \
"2:\n\t" \
- "bltu a0, %2, 3b\n\t" \
- "nop", 0, RISCV_ISA_EXT_ZICBOM, CONFIG_RISCV_ISA_ZICBOM, \
- "mv a0, %1\n\t" \
- "j 2f\n\t" \
- "3:\n\t" \
- THEAD_##_op##_A0 "\n\t" \
- "add a0, a0, %0\n\t" \
- "2:\n\t" \
- "bltu a0, %2, 3b\n\t" \
- THEAD_SYNC_S, THEAD_VENDOR_ID, \
- ERRATA_THEAD_CMO, CONFIG_ERRATA_THEAD_CMO) \
+ "bltu a0, %2, 3b\n\t", \
+ 0, RISCV_ISA_EXT_ZICBOM, CONFIG_RISCV_ISA_ZICBOM) \
: : "r"(_cachesize), \
"r"((unsigned long)(_start) & ~((_cachesize) - 1UL)), \
"r"((unsigned long)(_start) + (_size)) \
diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h
index 2b2f5df7ef2c7de42216b4166ae3d1f4a789731f..3291721229523456247532009bc2ed2ddc444540 100644
--- a/arch/riscv/include/asm/ftrace.h
+++ b/arch/riscv/include/asm/ftrace.h
@@ -128,7 +128,23 @@ do { \
struct dyn_ftrace;
int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec);
#define ftrace_init_nop ftrace_init_nop
-#endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+struct ftrace_ops;
+struct ftrace_regs;
+void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *op, struct ftrace_regs *fregs);
+#define ftrace_graph_func ftrace_graph_func
+
+static inline void __arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr)
+{
+ regs->t1 = addr;
+}
+#define arch_ftrace_set_direct_caller(fregs, addr) \
+ __arch_ftrace_set_direct_caller(&(fregs)->regs, addr)
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
+
+#endif /* __ASSEMBLY__ */
#endif /* CONFIG_DYNAMIC_FTRACE */
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index e3ffef1c61193228c3b2f72794bb6289c188f57d..0c94260b5d0c126f6302f39a59507f19eed48dac 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -865,7 +865,7 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
#define TASK_SIZE_MIN (PGDIR_SIZE_L3 * PTRS_PER_PGD / 2)
#ifdef CONFIG_COMPAT
-#define TASK_SIZE_32 (_AC(0x80000000, UL) - PAGE_SIZE)
+#define TASK_SIZE_32 (_AC(0x80000000, UL))
#define TASK_SIZE (test_thread_flag(TIF_32BIT) ? \
TASK_SIZE_32 : TASK_SIZE_64)
#else
diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
index f19f861cda549014eee042efb651709f5da00475..a8509cc31ab25a5dcc75765bdb99e43e87dded3b 100644
--- a/arch/riscv/include/asm/processor.h
+++ b/arch/riscv/include/asm/processor.h
@@ -16,7 +16,7 @@
#ifdef CONFIG_64BIT
#define DEFAULT_MAP_WINDOW (UL(1) << (MMAP_VA_BITS - 1))
-#define STACK_TOP_MAX TASK_SIZE_64
+#define STACK_TOP_MAX TASK_SIZE
#define arch_get_mmap_end(addr, len, flags) \
({ \
@@ -73,6 +73,43 @@
struct task_struct;
struct pt_regs;
+/*
+ * We use a flag to track in-kernel Vector context. Currently the flag has the
+ * following meaning:
+ *
+ * - bit 0: indicates whether the in-kernel Vector context is active. The
+ * activation of this state disables the preemption. On a non-RT kernel, it
+ * also disable bh.
+ * - bits 8: is used for tracking preemptible kernel-mode Vector, when
+ * RISCV_ISA_V_PREEMPTIVE is enabled. Calling kernel_vector_begin() does not
+ * disable the preemption if the thread's kernel_vstate.datap is allocated.
+ * Instead, the kernel set this bit field. Then the trap entry/exit code
+ * knows if we are entering/exiting the context that owns preempt_v.
+ * - 0: the task is not using preempt_v
+ * - 1: the task is actively using preempt_v. But whether does the task own
+ * the preempt_v context is decided by bits in RISCV_V_CTX_DEPTH_MASK.
+ * - bit 16-23 are RISCV_V_CTX_DEPTH_MASK, used by context tracking routine
+ * when preempt_v starts:
+ * - 0: the task is actively using, and own preempt_v context.
+ * - non-zero: the task was using preempt_v, but then took a trap within.
+ * Thus, the task does not own preempt_v. Any use of Vector will have to
+ * save preempt_v, if dirty, and fallback to non-preemptible kernel-mode
+ * Vector.
+ * - bit 30: The in-kernel preempt_v context is saved, and requries to be
+ * restored when returning to the context that owns the preempt_v.
+ * - bit 31: The in-kernel preempt_v context is dirty, as signaled by the
+ * trap entry code. Any context switches out-of current task need to save
+ * it to the task's in-kernel V context. Also, any traps nesting on-top-of
+ * preempt_v requesting to use V needs a save.
+ */
+#define RISCV_V_CTX_DEPTH_MASK 0x00ff0000
+
+#define RISCV_V_CTX_UNIT_DEPTH 0x00010000
+#define RISCV_KERNEL_MODE_V 0x00000001
+#define RISCV_PREEMPT_V 0x00000100
+#define RISCV_PREEMPT_V_DIRTY 0x80000000
+#define RISCV_PREEMPT_V_NEED_RESTORE 0x40000000
+
/* CPU-specific state of a task */
struct thread_struct {
/* Callee-saved registers */
@@ -81,9 +118,11 @@ struct thread_struct {
unsigned long s[12]; /* s[0]: frame pointer */
struct __riscv_d_ext_state fstate;
unsigned long bad_cause;
- unsigned long vstate_ctrl;
+ u32 riscv_v_flags;
+ u32 vstate_ctrl;
struct __riscv_v_ext_state vstate;
unsigned long align_ctl;
+ struct __riscv_v_ext_state kernel_vstate;
};
/* Whitelist the fstate from the task_struct for hardened usercopy */
diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h
index b6f898c56940a2d3626d90436185279d01f288b8..6e68f8dff76bc6d09f7a5e555e54474587021ed9 100644
--- a/arch/riscv/include/asm/sbi.h
+++ b/arch/riscv/include/asm/sbi.h
@@ -29,6 +29,7 @@ enum sbi_ext_id {
SBI_EXT_RFENCE = 0x52464E43,
SBI_EXT_HSM = 0x48534D,
SBI_EXT_SRST = 0x53525354,
+ SBI_EXT_SUSP = 0x53555350,
SBI_EXT_PMU = 0x504D55,
SBI_EXT_DBCN = 0x4442434E,
SBI_EXT_STA = 0x535441,
@@ -115,6 +116,14 @@ enum sbi_srst_reset_reason {
SBI_SRST_RESET_REASON_SYS_FAILURE,
};
+enum sbi_ext_susp_fid {
+ SBI_EXT_SUSP_SYSTEM_SUSPEND = 0,
+};
+
+enum sbi_ext_susp_sleep_type {
+ SBI_SUSP_SLEEP_TYPE_SUSPEND_TO_RAM = 0,
+};
+
enum sbi_ext_pmu_fid {
SBI_EXT_PMU_NUM_COUNTERS = 0,
SBI_EXT_PMU_COUNTER_GET_INFO,
@@ -288,8 +297,13 @@ struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
unsigned long arg3, unsigned long arg4,
unsigned long arg5);
+#ifdef CONFIG_RISCV_SBI_V01
void sbi_console_putchar(int ch);
int sbi_console_getchar(void);
+#else
+static inline void sbi_console_putchar(int ch) { }
+static inline int sbi_console_getchar(void) { return -ENOENT; }
+#endif
long sbi_get_mvendorid(void);
long sbi_get_marchid(void);
long sbi_get_mimpid(void);
@@ -346,6 +360,11 @@ static inline unsigned long sbi_mk_version(unsigned long major,
}
int sbi_err_map_linux_errno(int err);
+
+extern bool sbi_debug_console_available;
+int sbi_debug_console_write(const char *bytes, unsigned int num_bytes);
+int sbi_debug_console_read(char *bytes, unsigned int num_bytes);
+
#else /* CONFIG_RISCV_SBI */
static inline int sbi_remote_fence_i(const struct cpumask *cpu_mask) { return -1; }
static inline void sbi_init(void) {}
diff --git a/arch/riscv/include/asm/simd.h b/arch/riscv/include/asm/simd.h
new file mode 100644
index 0000000000000000000000000000000000000000..54efbf523d49c67d75921c7f8454efc87ad0f257
--- /dev/null
+++ b/arch/riscv/include/asm/simd.h
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2017 Linaro Ltd.
+ * Copyright (C) 2023 SiFive
+ */
+
+#ifndef __ASM_SIMD_H
+#define __ASM_SIMD_H
+
+#include
+#include
+#include
+#include
+#include
+#include
+
+#include
+
+#ifdef CONFIG_RISCV_ISA_V
+/*
+ * may_use_simd - whether it is allowable at this time to issue vector
+ * instructions or access the vector register file
+ *
+ * Callers must not assume that the result remains true beyond the next
+ * preempt_enable() or return from softirq context.
+ */
+static __must_check inline bool may_use_simd(void)
+{
+ /*
+ * RISCV_KERNEL_MODE_V is only set while preemption is disabled,
+ * and is clear whenever preemption is enabled.
+ */
+ if (in_hardirq() || in_nmi())
+ return false;
+
+ /*
+ * Nesting is acheived in preempt_v by spreading the control for
+ * preemptible and non-preemptible kernel-mode Vector into two fields.
+ * Always try to match with prempt_v if kernel V-context exists. Then,
+ * fallback to check non preempt_v if nesting happens, or if the config
+ * is not set.
+ */
+ if (IS_ENABLED(CONFIG_RISCV_ISA_V_PREEMPTIVE) && current->thread.kernel_vstate.datap) {
+ if (!riscv_preempt_v_started(current))
+ return true;
+ }
+ /*
+ * Non-preemptible kernel-mode Vector temporarily disables bh. So we
+ * must not return true on irq_disabled(). Otherwise we would fail the
+ * lockdep check calling local_bh_enable()
+ */
+ return !irqs_disabled() && !(riscv_v_flags() & RISCV_KERNEL_MODE_V);
+}
+
+#else /* ! CONFIG_RISCV_ISA_V */
+
+static __must_check inline bool may_use_simd(void)
+{
+ return false;
+}
+
+#endif /* ! CONFIG_RISCV_ISA_V */
+
+#endif
diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
index f90d8e42f3c7911908ec1f5f19929ab5ba67ff3a..7efdb0584d47ac9887126a00dcfcc045619b27b5 100644
--- a/arch/riscv/include/asm/switch_to.h
+++ b/arch/riscv/include/asm/switch_to.h
@@ -53,8 +53,7 @@ static inline void __switch_to_fpu(struct task_struct *prev,
struct pt_regs *regs;
regs = task_pt_regs(prev);
- if (unlikely(regs->status & SR_SD))
- fstate_save(prev, regs);
+ fstate_save(prev, regs);
fstate_restore(next, task_pt_regs(next));
}
diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h
index 4856697c5f25a99d680c57e40b280372fa26509b..5d473343634b9d3af3c1f1872da25e6e60f77162 100644
--- a/arch/riscv/include/asm/thread_info.h
+++ b/arch/riscv/include/asm/thread_info.h
@@ -102,12 +102,14 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
#define TIF_NOTIFY_SIGNAL 9 /* signal notifications exist */
#define TIF_UPROBE 10 /* uprobe breakpoint or singlestep */
#define TIF_32BIT 11 /* compat-mode 32bit process */
+#define TIF_RISCV_V_DEFER_RESTORE 12 /* restore Vector before returing to user */
#define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME)
#define _TIF_SIGPENDING (1 << TIF_SIGPENDING)
#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED)
#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL)
#define _TIF_UPROBE (1 << TIF_UPROBE)
+#define _TIF_RISCV_V_DEFER_RESTORE (1 << TIF_RISCV_V_DEFER_RESTORE)
#define _TIF_WORK_MASK \
(_TIF_NOTIFY_RESUME | _TIF_SIGPENDING | _TIF_NEED_RESCHED | \
diff --git a/arch/riscv/include/asm/tlbbatch.h b/arch/riscv/include/asm/tlbbatch.h
new file mode 100644
index 0000000000000000000000000000000000000000..46014f70b9daa19348e6b9d7162b5628dbd1e7b9
--- /dev/null
+++ b/arch/riscv/include/asm/tlbbatch.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2023 Rivos Inc.
+ */
+
+#ifndef _ASM_RISCV_TLBBATCH_H
+#define _ASM_RISCV_TLBBATCH_H
+
+#include
+
+struct arch_tlbflush_unmap_batch {
+ struct cpumask cpumask;
+};
+
+#endif /* _ASM_RISCV_TLBBATCH_H */
diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
index a60416bbe19046a4aa2c303d6eb29d9bf1c0f2b6..928f096dca21b4e6cbafc009595cd34bb9917109 100644
--- a/arch/riscv/include/asm/tlbflush.h
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -47,6 +47,14 @@ void local_flush_tlb_kernel_range(unsigned long start, unsigned long end);
void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
unsigned long end);
#endif
+
+bool arch_tlbbatch_should_defer(struct mm_struct *mm);
+void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
+ struct mm_struct *mm,
+ unsigned long uaddr);
+void arch_flush_tlb_batched_pending(struct mm_struct *mm);
+void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch);
+
#else /* CONFIG_SMP && CONFIG_MMU */
#define flush_tlb_all() local_flush_tlb_all()
diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h
index 87aaef656257cbde40331aadaf1cb0b1ea374455..0cd6f0a027d1f7ae7bb95b509bad3400c9fa71a5 100644
--- a/arch/riscv/include/asm/vector.h
+++ b/arch/riscv/include/asm/vector.h
@@ -22,6 +22,18 @@
extern unsigned long riscv_v_vsize;
int riscv_v_setup_vsize(void);
bool riscv_v_first_use_handler(struct pt_regs *regs);
+void kernel_vector_begin(void);
+void kernel_vector_end(void);
+void get_cpu_vector_context(void);
+void put_cpu_vector_context(void);
+void riscv_v_thread_free(struct task_struct *tsk);
+void __init riscv_v_setup_ctx_cache(void);
+void riscv_v_thread_alloc(struct task_struct *tsk);
+
+static inline u32 riscv_v_flags(void)
+{
+ return READ_ONCE(current->thread.riscv_v_flags);
+}
static __always_inline bool has_vector(void)
{
@@ -162,36 +174,89 @@ static inline void riscv_v_vstate_discard(struct pt_regs *regs)
__riscv_v_vstate_dirty(regs);
}
-static inline void riscv_v_vstate_save(struct task_struct *task,
+static inline void riscv_v_vstate_save(struct __riscv_v_ext_state *vstate,
struct pt_regs *regs)
{
if ((regs->status & SR_VS) == SR_VS_DIRTY) {
- struct __riscv_v_ext_state *vstate = &task->thread.vstate;
-
__riscv_v_vstate_save(vstate, vstate->datap);
__riscv_v_vstate_clean(regs);
}
}
-static inline void riscv_v_vstate_restore(struct task_struct *task,
+static inline void riscv_v_vstate_restore(struct __riscv_v_ext_state *vstate,
struct pt_regs *regs)
{
if ((regs->status & SR_VS) != SR_VS_OFF) {
- struct __riscv_v_ext_state *vstate = &task->thread.vstate;
-
__riscv_v_vstate_restore(vstate, vstate->datap);
__riscv_v_vstate_clean(regs);
}
}
+static inline void riscv_v_vstate_set_restore(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ if ((regs->status & SR_VS) != SR_VS_OFF) {
+ set_tsk_thread_flag(task, TIF_RISCV_V_DEFER_RESTORE);
+ riscv_v_vstate_on(regs);
+ }
+}
+
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+static inline bool riscv_preempt_v_dirty(struct task_struct *task)
+{
+ return !!(task->thread.riscv_v_flags & RISCV_PREEMPT_V_DIRTY);
+}
+
+static inline bool riscv_preempt_v_restore(struct task_struct *task)
+{
+ return !!(task->thread.riscv_v_flags & RISCV_PREEMPT_V_NEED_RESTORE);
+}
+
+static inline void riscv_preempt_v_clear_dirty(struct task_struct *task)
+{
+ barrier();
+ task->thread.riscv_v_flags &= ~RISCV_PREEMPT_V_DIRTY;
+}
+
+static inline void riscv_preempt_v_set_restore(struct task_struct *task)
+{
+ barrier();
+ task->thread.riscv_v_flags |= RISCV_PREEMPT_V_NEED_RESTORE;
+}
+
+static inline bool riscv_preempt_v_started(struct task_struct *task)
+{
+ return !!(task->thread.riscv_v_flags & RISCV_PREEMPT_V);
+}
+
+#else /* !CONFIG_RISCV_ISA_V_PREEMPTIVE */
+static inline bool riscv_preempt_v_dirty(struct task_struct *task) { return false; }
+static inline bool riscv_preempt_v_restore(struct task_struct *task) { return false; }
+static inline bool riscv_preempt_v_started(struct task_struct *task) { return false; }
+#define riscv_preempt_v_clear_dirty(tsk) do {} while (0)
+#define riscv_preempt_v_set_restore(tsk) do {} while (0)
+#endif /* CONFIG_RISCV_ISA_V_PREEMPTIVE */
+
static inline void __switch_to_vector(struct task_struct *prev,
struct task_struct *next)
{
struct pt_regs *regs;
- regs = task_pt_regs(prev);
- riscv_v_vstate_save(prev, regs);
- riscv_v_vstate_restore(next, task_pt_regs(next));
+ if (riscv_preempt_v_started(prev)) {
+ if (riscv_preempt_v_dirty(prev)) {
+ __riscv_v_vstate_save(&prev->thread.kernel_vstate,
+ prev->thread.kernel_vstate.datap);
+ riscv_preempt_v_clear_dirty(prev);
+ }
+ } else {
+ regs = task_pt_regs(prev);
+ riscv_v_vstate_save(&prev->thread.vstate, regs);
+ }
+
+ if (riscv_preempt_v_started(next))
+ riscv_preempt_v_set_restore(next);
+ else
+ riscv_v_vstate_set_restore(next, task_pt_regs(next));
}
void riscv_v_vstate_ctrl_init(struct task_struct *tsk);
@@ -208,11 +273,14 @@ static inline bool riscv_v_vstate_query(struct pt_regs *regs) { return false; }
static inline bool riscv_v_vstate_ctrl_user_allowed(void) { return false; }
#define riscv_v_vsize (0)
#define riscv_v_vstate_discard(regs) do {} while (0)
-#define riscv_v_vstate_save(task, regs) do {} while (0)
-#define riscv_v_vstate_restore(task, regs) do {} while (0)
+#define riscv_v_vstate_save(vstate, regs) do {} while (0)
+#define riscv_v_vstate_restore(vstate, regs) do {} while (0)
#define __switch_to_vector(__prev, __next) do {} while (0)
#define riscv_v_vstate_off(regs) do {} while (0)
#define riscv_v_vstate_on(regs) do {} while (0)
+#define riscv_v_thread_free(tsk) do {} while (0)
+#define riscv_v_setup_ctx_cache() do {} while (0)
+#define riscv_v_thread_alloc(tsk) do {} while (0)
#endif /* CONFIG_RISCV_ISA_V */
diff --git a/arch/riscv/include/asm/word-at-a-time.h b/arch/riscv/include/asm/word-at-a-time.h
index 7c086ac6ecd4a82e11b9cd7cbd8d6944fb68ae1f..f3f031e34191d6fb993f650126be4dc793fee3ed 100644
--- a/arch/riscv/include/asm/word-at-a-time.h
+++ b/arch/riscv/include/asm/word-at-a-time.h
@@ -9,6 +9,7 @@
#define _ASM_RISCV_WORD_AT_A_TIME_H
+#include
#include
struct word_at_a_time {
@@ -45,4 +46,30 @@ static inline unsigned long find_zero(unsigned long mask)
/* The mask we created is directly usable as a bytemask */
#define zero_bytemask(mask) (mask)
+#ifdef CONFIG_DCACHE_WORD_ACCESS
+
+/*
+ * Load an unaligned word from kernel space.
+ *
+ * In the (very unlikely) case of the word being a page-crosser
+ * and the next page not being mapped, take the exception and
+ * return zeroes in the non-existing part.
+ */
+static inline unsigned long load_unaligned_zeropad(const void *addr)
+{
+ unsigned long ret;
+
+ /* Load word from unaligned pointer addr */
+ asm(
+ "1: " REG_L " %0, %2\n"
+ "2:\n"
+ _ASM_EXTABLE_LOAD_UNALIGNED_ZEROPAD(1b, 2b, %0, %1)
+ : "=&r" (ret)
+ : "r" (addr), "m" (*(unsigned long *)addr));
+
+ return ret;
+}
+
+#endif /* CONFIG_DCACHE_WORD_ACCESS */
+
#endif /* _ASM_RISCV_WORD_AT_A_TIME_H */
diff --git a/arch/riscv/include/asm/xor.h b/arch/riscv/include/asm/xor.h
new file mode 100644
index 0000000000000000000000000000000000000000..96011861e46b4df24cb973a9066324283ad17b60
--- /dev/null
+++ b/arch/riscv/include/asm/xor.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2021 SiFive
+ */
+
+#include
+#include
+#ifdef CONFIG_RISCV_ISA_V
+#include
+#include
+#include
+
+static void xor_vector_2(unsigned long bytes, unsigned long *__restrict p1,
+ const unsigned long *__restrict p2)
+{
+ kernel_vector_begin();
+ xor_regs_2_(bytes, p1, p2);
+ kernel_vector_end();
+}
+
+static void xor_vector_3(unsigned long bytes, unsigned long *__restrict p1,
+ const unsigned long *__restrict p2,
+ const unsigned long *__restrict p3)
+{
+ kernel_vector_begin();
+ xor_regs_3_(bytes, p1, p2, p3);
+ kernel_vector_end();
+}
+
+static void xor_vector_4(unsigned long bytes, unsigned long *__restrict p1,
+ const unsigned long *__restrict p2,
+ const unsigned long *__restrict p3,
+ const unsigned long *__restrict p4)
+{
+ kernel_vector_begin();
+ xor_regs_4_(bytes, p1, p2, p3, p4);
+ kernel_vector_end();
+}
+
+static void xor_vector_5(unsigned long bytes, unsigned long *__restrict p1,
+ const unsigned long *__restrict p2,
+ const unsigned long *__restrict p3,
+ const unsigned long *__restrict p4,
+ const unsigned long *__restrict p5)
+{
+ kernel_vector_begin();
+ xor_regs_5_(bytes, p1, p2, p3, p4, p5);
+ kernel_vector_end();
+}
+
+static struct xor_block_template xor_block_rvv = {
+ .name = "rvv",
+ .do_2 = xor_vector_2,
+ .do_3 = xor_vector_3,
+ .do_4 = xor_vector_4,
+ .do_5 = xor_vector_5
+};
+
+#undef XOR_TRY_TEMPLATES
+#define XOR_TRY_TEMPLATES \
+ do { \
+ xor_speed(&xor_block_8regs); \
+ xor_speed(&xor_block_32regs); \
+ if (has_vector()) { \
+ xor_speed(&xor_block_rvv);\
+ } \
+ } while (0)
+#endif
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index c92c623b311e7b78b8e5055f66d780d328025b60..f71910718053d841a361fd97e7d62da4f86bebcf 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -64,6 +64,7 @@ obj-$(CONFIG_MMU) += vdso.o vdso/
obj-$(CONFIG_RISCV_MISALIGNED) += traps_misaligned.o
obj-$(CONFIG_FPU) += fpu.o
obj-$(CONFIG_RISCV_ISA_V) += vector.o
+obj-$(CONFIG_RISCV_ISA_V) += kernel_mode_vector.o
obj-$(CONFIG_SMP) += smpboot.o
obj-$(CONFIG_SMP) += smp.o
obj-$(CONFIG_SMP) += cpu_ops.o
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index e32591e9da90867b6b0760c6f553b5c146fba847..89920f84d0a34385471e9afbf9c26d287cbbd838 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -8,8 +8,10 @@
#include
#include
+#include
#include
#include
+#include
#include
#include
#include
@@ -44,6 +46,8 @@ struct riscv_isainfo hart_isa[NR_CPUS];
/* Performance information */
DEFINE_PER_CPU(long, misaligned_access_speed);
+static cpumask_t fast_misaligned_access;
+
/**
* riscv_isa_extension_base() - Get base extension word
*
@@ -784,6 +788,16 @@ static int check_unaligned_access(void *param)
(speed == RISCV_HWPROBE_MISALIGNED_FAST) ? "fast" : "slow");
per_cpu(misaligned_access_speed, cpu) = speed;
+
+ /*
+ * Set the value of fast_misaligned_access of a CPU. These operations
+ * are atomic to avoid race conditions.
+ */
+ if (speed == RISCV_HWPROBE_MISALIGNED_FAST)
+ cpumask_set_cpu(cpu, &fast_misaligned_access);
+ else
+ cpumask_clear_cpu(cpu, &fast_misaligned_access);
+
return 0;
}
@@ -796,13 +810,69 @@ static void check_unaligned_access_nonboot_cpu(void *param)
check_unaligned_access(pages[cpu]);
}
+DEFINE_STATIC_KEY_FALSE(fast_misaligned_access_speed_key);
+
+static void modify_unaligned_access_branches(cpumask_t *mask, int weight)
+{
+ if (cpumask_weight(mask) == weight)
+ static_branch_enable_cpuslocked(&fast_misaligned_access_speed_key);
+ else
+ static_branch_disable_cpuslocked(&fast_misaligned_access_speed_key);
+}
+
+static void set_unaligned_access_static_branches_except_cpu(int cpu)
+{
+ /*
+ * Same as set_unaligned_access_static_branches, except excludes the
+ * given CPU from the result. When a CPU is hotplugged into an offline
+ * state, this function is called before the CPU is set to offline in
+ * the cpumask, and thus the CPU needs to be explicitly excluded.
+ */
+
+ cpumask_t fast_except_me;
+
+ cpumask_and(&fast_except_me, &fast_misaligned_access, cpu_online_mask);
+ cpumask_clear_cpu(cpu, &fast_except_me);
+
+ modify_unaligned_access_branches(&fast_except_me, num_online_cpus() - 1);
+}
+
+static void set_unaligned_access_static_branches(void)
+{
+ /*
+ * This will be called after check_unaligned_access_all_cpus so the
+ * result of unaligned access speed for all CPUs will be available.
+ *
+ * To avoid the number of online cpus changing between reading
+ * cpu_online_mask and calling num_online_cpus, cpus_read_lock must be
+ * held before calling this function.
+ */
+
+ cpumask_t fast_and_online;
+
+ cpumask_and(&fast_and_online, &fast_misaligned_access, cpu_online_mask);
+
+ modify_unaligned_access_branches(&fast_and_online, num_online_cpus());
+}
+
+static int lock_and_set_unaligned_access_static_branch(void)
+{
+ cpus_read_lock();
+ set_unaligned_access_static_branches();
+ cpus_read_unlock();
+
+ return 0;
+}
+
+arch_initcall_sync(lock_and_set_unaligned_access_static_branch);
+
static int riscv_online_cpu(unsigned int cpu)
{
static struct page *buf;
/* We are already set since the last check */
if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_UNKNOWN)
- return 0;
+ goto exit;
buf = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER);
if (!buf) {
@@ -812,6 +882,17 @@ static int riscv_online_cpu(unsigned int cpu)
check_unaligned_access(buf);
__free_pages(buf, MISALIGNED_BUFFER_ORDER);
+
+exit:
+ set_unaligned_access_static_branches();
+
+ return 0;
+}
+
+static int riscv_offline_cpu(unsigned int cpu)
+{
+ set_unaligned_access_static_branches_except_cpu(cpu);
+
return 0;
}
@@ -846,9 +927,12 @@ static int check_unaligned_access_all_cpus(void)
/* Check core 0. */
smp_call_on_cpu(0, check_unaligned_access, bufs[0], true);
- /* Setup hotplug callback for any new CPUs that come online. */
+ /*
+ * Setup hotplug callbacks for any new CPUs that come online or go
+ * offline.
+ */
cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "riscv:online",
- riscv_online_cpu, NULL);
+ riscv_online_cpu, riscv_offline_cpu);
out:
unaligned_emulation_finish();
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 54ca4564a92631388783a7978e8f49f40e556364..9d1a305d55087bb3a6bdc73f8ed8ebe3206775b1 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -83,6 +83,10 @@ SYM_CODE_START(handle_exception)
/* Load the kernel shadow call stack pointer if coming from userspace */
scs_load_current_if_task_changed s5
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+ move a0, sp
+ call riscv_v_context_nesting_start
+#endif
move a0, sp /* pt_regs */
la ra, ret_from_exception
@@ -138,6 +142,10 @@ SYM_CODE_START_NOALIGN(ret_from_exception)
*/
csrw CSR_SCRATCH, tp
1:
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+ move a0, sp
+ call riscv_v_context_nesting_end
+#endif
REG_L a0, PT_STATUS(sp)
/*
* The current load reservation is effectively part of the processor's
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index 03a6434a8cdd0035bbc59629b1751c00df24b918..f5aa24d9e1c150e651f5eeb144da8671e9ac5ddc 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -178,32 +178,28 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
}
#ifdef CONFIG_DYNAMIC_FTRACE
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *op, struct ftrace_regs *fregs)
+{
+ struct pt_regs *regs = arch_ftrace_get_regs(fregs);
+ unsigned long *parent = (unsigned long *)®s->ra;
+
+ prepare_ftrace_return(parent, ip, frame_pointer(regs));
+}
+#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
extern void ftrace_graph_call(void);
-extern void ftrace_graph_regs_call(void);
int ftrace_enable_ftrace_graph_caller(void)
{
- int ret;
-
- ret = __ftrace_modify_call((unsigned long)&ftrace_graph_call,
- (unsigned long)&prepare_ftrace_return, true, true);
- if (ret)
- return ret;
-
- return __ftrace_modify_call((unsigned long)&ftrace_graph_regs_call,
+ return __ftrace_modify_call((unsigned long)&ftrace_graph_call,
(unsigned long)&prepare_ftrace_return, true, true);
}
int ftrace_disable_ftrace_graph_caller(void)
{
- int ret;
-
- ret = __ftrace_modify_call((unsigned long)&ftrace_graph_call,
- (unsigned long)&prepare_ftrace_return, false, true);
- if (ret)
- return ret;
-
- return __ftrace_modify_call((unsigned long)&ftrace_graph_regs_call,
+ return __ftrace_modify_call((unsigned long)&ftrace_graph_call,
(unsigned long)&prepare_ftrace_return, false, true);
}
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
#endif /* CONFIG_DYNAMIC_FTRACE */
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/riscv/kernel/kernel_mode_vector.c b/arch/riscv/kernel/kernel_mode_vector.c
new file mode 100644
index 0000000000000000000000000000000000000000..6afe80c7f03ab0c195ee43725d6dfd041dc0464b
--- /dev/null
+++ b/arch/riscv/kernel/kernel_mode_vector.c
@@ -0,0 +1,247 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Author: Catalin Marinas
+ * Copyright (C) 2017 Linaro Ltd.
+ * Copyright (C) 2021 SiFive
+ */
+#include
+#include
+#include
+#include
+#include
+
+#include
+#include
+#include
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+#include
+#endif
+
+static inline void riscv_v_flags_set(u32 flags)
+{
+ WRITE_ONCE(current->thread.riscv_v_flags, flags);
+}
+
+static inline void riscv_v_start(u32 flags)
+{
+ int orig;
+
+ orig = riscv_v_flags();
+ BUG_ON((orig & flags) != 0);
+ riscv_v_flags_set(orig | flags);
+ barrier();
+}
+
+static inline void riscv_v_stop(u32 flags)
+{
+ int orig;
+
+ barrier();
+ orig = riscv_v_flags();
+ BUG_ON((orig & flags) == 0);
+ riscv_v_flags_set(orig & ~flags);
+}
+
+/*
+ * Claim ownership of the CPU vector context for use by the calling context.
+ *
+ * The caller may freely manipulate the vector context metadata until
+ * put_cpu_vector_context() is called.
+ */
+void get_cpu_vector_context(void)
+{
+ /*
+ * disable softirqs so it is impossible for softirqs to nest
+ * get_cpu_vector_context() when kernel is actively using Vector.
+ */
+ if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+ local_bh_disable();
+ else
+ preempt_disable();
+
+ riscv_v_start(RISCV_KERNEL_MODE_V);
+}
+
+/*
+ * Release the CPU vector context.
+ *
+ * Must be called from a context in which get_cpu_vector_context() was
+ * previously called, with no call to put_cpu_vector_context() in the
+ * meantime.
+ */
+void put_cpu_vector_context(void)
+{
+ riscv_v_stop(RISCV_KERNEL_MODE_V);
+
+ if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+ local_bh_enable();
+ else
+ preempt_enable();
+}
+
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+static __always_inline u32 *riscv_v_flags_ptr(void)
+{
+ return ¤t->thread.riscv_v_flags;
+}
+
+static inline void riscv_preempt_v_set_dirty(void)
+{
+ *riscv_v_flags_ptr() |= RISCV_PREEMPT_V_DIRTY;
+}
+
+static inline void riscv_preempt_v_reset_flags(void)
+{
+ *riscv_v_flags_ptr() &= ~(RISCV_PREEMPT_V_DIRTY | RISCV_PREEMPT_V_NEED_RESTORE);
+}
+
+static inline void riscv_v_ctx_depth_inc(void)
+{
+ *riscv_v_flags_ptr() += RISCV_V_CTX_UNIT_DEPTH;
+}
+
+static inline void riscv_v_ctx_depth_dec(void)
+{
+ *riscv_v_flags_ptr() -= RISCV_V_CTX_UNIT_DEPTH;
+}
+
+static inline u32 riscv_v_ctx_get_depth(void)
+{
+ return *riscv_v_flags_ptr() & RISCV_V_CTX_DEPTH_MASK;
+}
+
+static int riscv_v_stop_kernel_context(void)
+{
+ if (riscv_v_ctx_get_depth() != 0 || !riscv_preempt_v_started(current))
+ return 1;
+
+ riscv_preempt_v_clear_dirty(current);
+ riscv_v_stop(RISCV_PREEMPT_V);
+ return 0;
+}
+
+static int riscv_v_start_kernel_context(bool *is_nested)
+{
+ struct __riscv_v_ext_state *kvstate, *uvstate;
+
+ kvstate = ¤t->thread.kernel_vstate;
+ if (!kvstate->datap)
+ return -ENOENT;
+
+ if (riscv_preempt_v_started(current)) {
+ WARN_ON(riscv_v_ctx_get_depth() == 0);
+ *is_nested = true;
+ get_cpu_vector_context();
+ if (riscv_preempt_v_dirty(current)) {
+ __riscv_v_vstate_save(kvstate, kvstate->datap);
+ riscv_preempt_v_clear_dirty(current);
+ }
+ riscv_preempt_v_set_restore(current);
+ return 0;
+ }
+
+ /* Transfer the ownership of V from user to kernel, then save */
+ riscv_v_start(RISCV_PREEMPT_V | RISCV_PREEMPT_V_DIRTY);
+ if ((task_pt_regs(current)->status & SR_VS) == SR_VS_DIRTY) {
+ uvstate = ¤t->thread.vstate;
+ __riscv_v_vstate_save(uvstate, uvstate->datap);
+ }
+ riscv_preempt_v_clear_dirty(current);
+ return 0;
+}
+
+/* low-level V context handling code, called with irq disabled */
+asmlinkage void riscv_v_context_nesting_start(struct pt_regs *regs)
+{
+ int depth;
+
+ if (!riscv_preempt_v_started(current))
+ return;
+
+ depth = riscv_v_ctx_get_depth();
+ if (depth == 0 && (regs->status & SR_VS) == SR_VS_DIRTY)
+ riscv_preempt_v_set_dirty();
+
+ riscv_v_ctx_depth_inc();
+}
+
+asmlinkage void riscv_v_context_nesting_end(struct pt_regs *regs)
+{
+ struct __riscv_v_ext_state *vstate = ¤t->thread.kernel_vstate;
+ u32 depth;
+
+ WARN_ON(!irqs_disabled());
+
+ if (!riscv_preempt_v_started(current))
+ return;
+
+ riscv_v_ctx_depth_dec();
+ depth = riscv_v_ctx_get_depth();
+ if (depth == 0) {
+ if (riscv_preempt_v_restore(current)) {
+ __riscv_v_vstate_restore(vstate, vstate->datap);
+ __riscv_v_vstate_clean(regs);
+ riscv_preempt_v_reset_flags();
+ }
+ }
+}
+#else
+#define riscv_v_start_kernel_context(nested) (-ENOENT)
+#define riscv_v_stop_kernel_context() (-ENOENT)
+#endif /* CONFIG_RISCV_ISA_V_PREEMPTIVE */
+
+/*
+ * kernel_vector_begin(): obtain the CPU vector registers for use by the calling
+ * context
+ *
+ * Must not be called unless may_use_simd() returns true.
+ * Task context in the vector registers is saved back to memory as necessary.
+ *
+ * A matching call to kernel_vector_end() must be made before returning from the
+ * calling context.
+ *
+ * The caller may freely use the vector registers until kernel_vector_end() is
+ * called.
+ */
+void kernel_vector_begin(void)
+{
+ bool nested = false;
+
+ if (WARN_ON(!has_vector()))
+ return;
+
+ BUG_ON(!may_use_simd());
+
+ if (riscv_v_start_kernel_context(&nested)) {
+ get_cpu_vector_context();
+ riscv_v_vstate_save(¤t->thread.vstate, task_pt_regs(current));
+ }
+
+ if (!nested)
+ riscv_v_vstate_set_restore(current, task_pt_regs(current));
+
+ riscv_v_enable();
+}
+EXPORT_SYMBOL_GPL(kernel_vector_begin);
+
+/*
+ * kernel_vector_end(): give the CPU vector registers back to the current task
+ *
+ * Must be called from a context in which kernel_vector_begin() was previously
+ * called, with no call to kernel_vector_end() in the meantime.
+ *
+ * The caller must not use the vector registers after this function is called,
+ * unless kernel_vector_begin() is called again in the meantime.
+ */
+void kernel_vector_end(void)
+{
+ if (WARN_ON(!has_vector()))
+ return;
+
+ riscv_v_disable();
+
+ if (riscv_v_stop_kernel_context())
+ put_cpu_vector_context();
+}
+EXPORT_SYMBOL_GPL(kernel_vector_end);
diff --git a/arch/riscv/kernel/mcount-dyn.S b/arch/riscv/kernel/mcount-dyn.S
index 79dc81223238232a453aac10d6a5b87a06df0725..b7561288e8da616de4e2082622207a0f33e9b7f4 100644
--- a/arch/riscv/kernel/mcount-dyn.S
+++ b/arch/riscv/kernel/mcount-dyn.S
@@ -57,31 +57,150 @@
.endm
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
- .macro SAVE_ALL
+
+/**
+* SAVE_ABI_REGS - save regs against the pt_regs struct
+*
+* @all: tell if saving all the regs
+*
+* If all is set, all the regs will be saved, otherwise only ABI
+* related regs (a0-a7,epc,ra and optional s0) will be saved.
+*
+* After the stack is established,
+*
+* 0(sp) stores the PC of the traced function which can be accessed
+* by &(fregs)->regs->epc in tracing function. Note that the real
+* function entry address should be computed with -FENTRY_RA_OFFSET.
+*
+* 8(sp) stores the function return address (i.e. parent IP) that
+* can be accessed by &(fregs)->regs->ra in tracing function.
+*
+* The other regs are saved at the respective localtion and accessed
+* by the respective pt_regs member.
+*
+* Here is the layout of stack for your reference.
+*
+* PT_SIZE_ON_STACK -> +++++++++
+* + ..... +
+* + t3-t6 +
+* + s2-s11+
+* + a0-a7 + --++++-> ftrace_caller saved
+* + s1 + +
+* + s0 + --+
+* + t0-t2 + +
+* + tp + +
+* + gp + +
+* + sp + +
+* + ra + --+ // parent IP
+* sp -> + epc + --+ // PC
+* +++++++++
+**/
+ .macro SAVE_ABI_REGS, all=0
addi sp, sp, -PT_SIZE_ON_STACK
- REG_S t0, PT_EPC(sp)
- REG_S x1, PT_RA(sp)
- REG_S x2, PT_SP(sp)
- REG_S x3, PT_GP(sp)
- REG_S x4, PT_TP(sp)
- REG_S x5, PT_T0(sp)
- save_from_x6_to_x31
+ REG_S t0, PT_EPC(sp)
+ REG_S x1, PT_RA(sp)
+
+ // save the ABI regs
+
+ REG_S x10, PT_A0(sp)
+ REG_S x11, PT_A1(sp)
+ REG_S x12, PT_A2(sp)
+ REG_S x13, PT_A3(sp)
+ REG_S x14, PT_A4(sp)
+ REG_S x15, PT_A5(sp)
+ REG_S x16, PT_A6(sp)
+ REG_S x17, PT_A7(sp)
+
+ // save the leftover regs
+
+ .if \all == 1
+ REG_S x2, PT_SP(sp)
+ REG_S x3, PT_GP(sp)
+ REG_S x4, PT_TP(sp)
+ REG_S x5, PT_T0(sp)
+ REG_S x6, PT_T1(sp)
+ REG_S x7, PT_T2(sp)
+ REG_S x8, PT_S0(sp)
+ REG_S x9, PT_S1(sp)
+ REG_S x18, PT_S2(sp)
+ REG_S x19, PT_S3(sp)
+ REG_S x20, PT_S4(sp)
+ REG_S x21, PT_S5(sp)
+ REG_S x22, PT_S6(sp)
+ REG_S x23, PT_S7(sp)
+ REG_S x24, PT_S8(sp)
+ REG_S x25, PT_S9(sp)
+ REG_S x26, PT_S10(sp)
+ REG_S x27, PT_S11(sp)
+ REG_S x28, PT_T3(sp)
+ REG_S x29, PT_T4(sp)
+ REG_S x30, PT_T5(sp)
+ REG_S x31, PT_T6(sp)
+
+ // save s0 if FP_TEST defined
+
+ .else
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
+ REG_S x8, PT_S0(sp)
+#endif
+ .endif
.endm
- .macro RESTORE_ALL
- REG_L x1, PT_RA(sp)
- REG_L x2, PT_SP(sp)
- REG_L x3, PT_GP(sp)
- REG_L x4, PT_TP(sp)
- /* Restore t0 with PT_EPC */
- REG_L x5, PT_EPC(sp)
- restore_from_x6_to_x31
+ .macro RESTORE_ABI_REGS, all=0
+ REG_L t0, PT_EPC(sp)
+ REG_L x1, PT_RA(sp)
+ REG_L x10, PT_A0(sp)
+ REG_L x11, PT_A1(sp)
+ REG_L x12, PT_A2(sp)
+ REG_L x13, PT_A3(sp)
+ REG_L x14, PT_A4(sp)
+ REG_L x15, PT_A5(sp)
+ REG_L x16, PT_A6(sp)
+ REG_L x17, PT_A7(sp)
+ .if \all == 1
+ REG_L x2, PT_SP(sp)
+ REG_L x3, PT_GP(sp)
+ REG_L x4, PT_TP(sp)
+ REG_L x6, PT_T1(sp)
+ REG_L x7, PT_T2(sp)
+ REG_L x8, PT_S0(sp)
+ REG_L x9, PT_S1(sp)
+ REG_L x18, PT_S2(sp)
+ REG_L x19, PT_S3(sp)
+ REG_L x20, PT_S4(sp)
+ REG_L x21, PT_S5(sp)
+ REG_L x22, PT_S6(sp)
+ REG_L x23, PT_S7(sp)
+ REG_L x24, PT_S8(sp)
+ REG_L x25, PT_S9(sp)
+ REG_L x26, PT_S10(sp)
+ REG_L x27, PT_S11(sp)
+ REG_L x28, PT_T3(sp)
+ REG_L x29, PT_T4(sp)
+ REG_L x30, PT_T5(sp)
+ REG_L x31, PT_T6(sp)
+
+ .else
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
+ REG_L x8, PT_S0(sp)
+#endif
+ .endif
addi sp, sp, PT_SIZE_ON_STACK
.endm
+
+ .macro PREPARE_ARGS
+ addi a0, t0, -FENTRY_RA_OFFSET
+ la a1, function_trace_op
+ REG_L a2, 0(a1)
+ mv a1, ra
+ mv a3, sp
+ .endm
+
#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
+#ifndef CONFIG_DYNAMIC_FTRACE_WITH_REGS
SYM_FUNC_START(ftrace_caller)
SAVE_ABI
@@ -105,34 +224,39 @@ SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL)
call ftrace_stub
#endif
RESTORE_ABI
- jr t0
+ jr t0
SYM_FUNC_END(ftrace_caller)
-#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
SYM_FUNC_START(ftrace_regs_caller)
- SAVE_ALL
-
- addi a0, t0, -FENTRY_RA_OFFSET
- la a1, function_trace_op
- REG_L a2, 0(a1)
- mv a1, ra
- mv a3, sp
+ mv t1, zero
+ SAVE_ABI_REGS 1
+ PREPARE_ARGS
SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL)
call ftrace_stub
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- addi a0, sp, PT_RA
- REG_L a1, PT_EPC(sp)
- addi a1, a1, -FENTRY_RA_OFFSET
-#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
- mv a2, s0
-#endif
-SYM_INNER_LABEL(ftrace_graph_regs_call, SYM_L_GLOBAL)
+ RESTORE_ABI_REGS 1
+ bnez t1, .Ldirect
+ jr t0
+.Ldirect:
+ jr t1
+SYM_FUNC_END(ftrace_regs_caller)
+
+SYM_FUNC_START(ftrace_caller)
+ SAVE_ABI_REGS 0
+ PREPARE_ARGS
+
+SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
call ftrace_stub
-#endif
- RESTORE_ALL
- jr t0
-SYM_FUNC_END(ftrace_regs_caller)
+ RESTORE_ABI_REGS 0
+ jr t0
+SYM_FUNC_END(ftrace_caller)
#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+SYM_CODE_START(ftrace_stub_direct_tramp)
+ jr t0
+SYM_CODE_END(ftrace_stub_direct_tramp)
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
index 862834bb1d64387d161ec0ef6ab0c3debfc9fa1b..5e5a82644451e16d8bdfe229e2ce89b4c389c31e 100644
--- a/arch/riscv/kernel/module.c
+++ b/arch/riscv/kernel/module.c
@@ -723,8 +723,8 @@ static int add_relocation_to_accumulate(struct module *me, int type,
if (!bucket) {
kfree(entry);
- kfree(rel_head);
kfree(rel_head->rel_entry);
+ kfree(rel_head);
return -ENOMEM;
}
@@ -747,6 +747,10 @@ initialize_relocation_hashtable(unsigned int num_relocations,
{
/* Can safely assume that bits is not greater than sizeof(long) */
unsigned long hashtable_size = roundup_pow_of_two(num_relocations);
+ /*
+ * When hashtable_size == 1, hashtable_bits == 0.
+ * This is valid because the hashing algorithm returns 0 in this case.
+ */
unsigned int hashtable_bits = ilog2(hashtable_size);
/*
@@ -760,10 +764,10 @@ initialize_relocation_hashtable(unsigned int num_relocations,
hashtable_size <<= should_double_size;
*relocation_hashtable = kmalloc_array(hashtable_size,
- sizeof(*relocation_hashtable),
+ sizeof(**relocation_hashtable),
GFP_KERNEL);
if (!*relocation_hashtable)
- return -ENOMEM;
+ return 0;
__hash_init(*relocation_hashtable, hashtable_size);
@@ -779,6 +783,7 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
Elf_Sym *sym;
void *location;
unsigned int i, type;
+ unsigned int j_idx = 0;
Elf_Addr v;
int res;
unsigned int num_relocations = sechdrs[relsec].sh_size / sizeof(*rel);
@@ -789,8 +794,8 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
hashtable_bits = initialize_relocation_hashtable(num_relocations,
&relocation_hashtable);
- if (hashtable_bits < 0)
- return hashtable_bits;
+ if (!relocation_hashtable)
+ return -ENOMEM;
INIT_LIST_HEAD(&used_buckets_list);
@@ -829,9 +834,10 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
v = sym->st_value + rel[i].r_addend;
if (type == R_RISCV_PCREL_LO12_I || type == R_RISCV_PCREL_LO12_S) {
- unsigned int j;
+ unsigned int j = j_idx;
+ bool found = false;
- for (j = 0; j < sechdrs[relsec].sh_size / sizeof(*rel); j++) {
+ do {
unsigned long hi20_loc =
sechdrs[sechdrs[relsec].sh_info].sh_addr
+ rel[j].r_offset;
@@ -860,16 +866,26 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
hi20 = (offset + 0x800) & 0xfffff000;
lo12 = offset - hi20;
v = lo12;
+ found = true;
break;
}
- }
- if (j == sechdrs[relsec].sh_size / sizeof(*rel)) {
+
+ j++;
+ if (j > sechdrs[relsec].sh_size / sizeof(*rel))
+ j = 0;
+
+ } while (j_idx != j);
+
+ if (!found) {
pr_err(
"%s: Can not find HI20 relocation information\n",
me->name);
return -EINVAL;
}
+
+ /* Record the previous j-loop end index */
+ j_idx = j;
}
if (reloc_handlers[type].accumulate_handler)
diff --git a/arch/riscv/kernel/pi/cmdline_early.c b/arch/riscv/kernel/pi/cmdline_early.c
index 68e786c84c949b23b9fa529686fc21ce89e94d64..f6d4dedffb8422051a3598ead6cea3d0bac96d7a 100644
--- a/arch/riscv/kernel/pi/cmdline_early.c
+++ b/arch/riscv/kernel/pi/cmdline_early.c
@@ -38,8 +38,7 @@ static char *get_early_cmdline(uintptr_t dtb_pa)
if (IS_ENABLED(CONFIG_CMDLINE_EXTEND) ||
IS_ENABLED(CONFIG_CMDLINE_FORCE) ||
fdt_cmdline_size == 0 /* CONFIG_CMDLINE_FALLBACK */) {
- strncat(early_cmdline, CONFIG_CMDLINE,
- COMMAND_LINE_SIZE - fdt_cmdline_size);
+ strlcat(early_cmdline, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
}
return early_cmdline;
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 4f21d970a1292b06be357b8b33ed541751bbb091..92922dbd5b5c1f9b5d57643ecbd7a1599c5ac4c3 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -171,6 +171,7 @@ void flush_thread(void)
riscv_v_vstate_off(task_pt_regs(current));
kfree(current->thread.vstate.datap);
memset(¤t->thread.vstate, 0, sizeof(struct __riscv_v_ext_state));
+ clear_tsk_thread_flag(current, TIF_RISCV_V_DEFER_RESTORE);
#endif
}
@@ -178,7 +179,7 @@ void arch_release_task_struct(struct task_struct *tsk)
{
/* Free the vector context of datap. */
if (has_vector())
- kfree(tsk->thread.vstate.datap);
+ riscv_v_thread_free(tsk);
}
int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
@@ -187,6 +188,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
*dst = *src;
/* clear entire V context, including datap for a new task */
memset(&dst->thread.vstate, 0, sizeof(struct __riscv_v_ext_state));
+ memset(&dst->thread.kernel_vstate, 0, sizeof(struct __riscv_v_ext_state));
+ clear_tsk_thread_flag(dst, TIF_RISCV_V_DEFER_RESTORE);
return 0;
}
@@ -221,7 +224,15 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
childregs->a0 = 0; /* Return value of fork() */
p->thread.s[0] = 0;
}
+ p->thread.riscv_v_flags = 0;
+ if (has_vector())
+ riscv_v_thread_alloc(p);
p->thread.ra = (unsigned long)ret_from_fork;
p->thread.sp = (unsigned long)childregs; /* kernel sp */
return 0;
}
+
+void __init arch_task_cache_init(void)
+{
+ riscv_v_setup_ctx_cache();
+}
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
index 2afe460de16a62ba21cf3c7db4a96c5ec8f7d3a5..e8515aa9d80bf82fd6ff2598664b9fe18a6b1de3 100644
--- a/arch/riscv/kernel/ptrace.c
+++ b/arch/riscv/kernel/ptrace.c
@@ -99,8 +99,11 @@ static int riscv_vr_get(struct task_struct *target,
* Ensure the vector registers have been saved to the memory before
* copying them to membuf.
*/
- if (target == current)
- riscv_v_vstate_save(current, task_pt_regs(current));
+ if (target == current) {
+ get_cpu_vector_context();
+ riscv_v_vstate_save(¤t->thread.vstate, task_pt_regs(current));
+ put_cpu_vector_context();
+ }
ptrace_vstate.vstart = vstate->vstart;
ptrace_vstate.vl = vstate->vl;
diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c
index 5a62ed1da45332c85820fdfdd7e90046b1ae3380..e66e0999a80057058c66c71fa907a0fb0152bc00 100644
--- a/arch/riscv/kernel/sbi.c
+++ b/arch/riscv/kernel/sbi.c
@@ -7,6 +7,7 @@
#include
#include
+#include
#include
#include
#include
@@ -571,6 +572,66 @@ long sbi_get_mimpid(void)
}
EXPORT_SYMBOL_GPL(sbi_get_mimpid);
+bool sbi_debug_console_available;
+
+int sbi_debug_console_write(const char *bytes, unsigned int num_bytes)
+{
+ phys_addr_t base_addr;
+ struct sbiret ret;
+
+ if (!sbi_debug_console_available)
+ return -EOPNOTSUPP;
+
+ if (is_vmalloc_addr(bytes))
+ base_addr = page_to_phys(vmalloc_to_page(bytes)) +
+ offset_in_page(bytes);
+ else
+ base_addr = __pa(bytes);
+ if (PAGE_SIZE < (offset_in_page(bytes) + num_bytes))
+ num_bytes = PAGE_SIZE - offset_in_page(bytes);
+
+ if (IS_ENABLED(CONFIG_32BIT))
+ ret = sbi_ecall(SBI_EXT_DBCN, SBI_EXT_DBCN_CONSOLE_WRITE,
+ num_bytes, lower_32_bits(base_addr),
+ upper_32_bits(base_addr), 0, 0, 0);
+ else
+ ret = sbi_ecall(SBI_EXT_DBCN, SBI_EXT_DBCN_CONSOLE_WRITE,
+ num_bytes, base_addr, 0, 0, 0, 0);
+
+ if (ret.error == SBI_ERR_FAILURE)
+ return -EIO;
+ return ret.error ? sbi_err_map_linux_errno(ret.error) : ret.value;
+}
+
+int sbi_debug_console_read(char *bytes, unsigned int num_bytes)
+{
+ phys_addr_t base_addr;
+ struct sbiret ret;
+
+ if (!sbi_debug_console_available)
+ return -EOPNOTSUPP;
+
+ if (is_vmalloc_addr(bytes))
+ base_addr = page_to_phys(vmalloc_to_page(bytes)) +
+ offset_in_page(bytes);
+ else
+ base_addr = __pa(bytes);
+ if (PAGE_SIZE < (offset_in_page(bytes) + num_bytes))
+ num_bytes = PAGE_SIZE - offset_in_page(bytes);
+
+ if (IS_ENABLED(CONFIG_32BIT))
+ ret = sbi_ecall(SBI_EXT_DBCN, SBI_EXT_DBCN_CONSOLE_READ,
+ num_bytes, lower_32_bits(base_addr),
+ upper_32_bits(base_addr), 0, 0, 0);
+ else
+ ret = sbi_ecall(SBI_EXT_DBCN, SBI_EXT_DBCN_CONSOLE_READ,
+ num_bytes, base_addr, 0, 0, 0, 0);
+
+ if (ret.error == SBI_ERR_FAILURE)
+ return -EIO;
+ return ret.error ? sbi_err_map_linux_errno(ret.error) : ret.value;
+}
+
void __init sbi_init(void)
{
int ret;
@@ -612,6 +673,11 @@ void __init sbi_init(void)
sbi_srst_reboot_nb.priority = 192;
register_restart_handler(&sbi_srst_reboot_nb);
}
+ if ((sbi_spec_version >= sbi_mk_version(2, 0)) &&
+ (sbi_probe_extension(SBI_EXT_DBCN) > 0)) {
+ pr_info("SBI DBCN extension detected\n");
+ sbi_debug_console_available = true;
+ }
} else {
__sbi_set_timer = __sbi_set_timer_v01;
__sbi_send_ipi = __sbi_send_ipi_v01;
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index 33dfb507830100c73efd168f244006b90ff7525a..501e66debf69721d53db2515cea4df970a6b2784 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -86,7 +86,10 @@ static long save_v_state(struct pt_regs *regs, void __user **sc_vec)
/* datap is designed to be 16 byte aligned for better performance */
WARN_ON(unlikely(!IS_ALIGNED((unsigned long)datap, 16)));
- riscv_v_vstate_save(current, regs);
+ get_cpu_vector_context();
+ riscv_v_vstate_save(¤t->thread.vstate, regs);
+ put_cpu_vector_context();
+
/* Copy everything of vstate but datap. */
err = __copy_to_user(&state->v_state, ¤t->thread.vstate,
offsetof(struct __riscv_v_ext_state, datap));
@@ -134,7 +137,7 @@ static long __restore_v_state(struct pt_regs *regs, void __user *sc_vec)
if (unlikely(err))
return err;
- riscv_v_vstate_restore(current, regs);
+ riscv_v_vstate_set_restore(current, regs);
return err;
}
diff --git a/arch/riscv/kernel/suspend.c b/arch/riscv/kernel/suspend.c
index 3c89b8ec69c49cce4809986f51784fcbfff53630..239509367e4233336806c19da964a06537d5a9b5 100644
--- a/arch/riscv/kernel/suspend.c
+++ b/arch/riscv/kernel/suspend.c
@@ -4,8 +4,12 @@
* Copyright (c) 2022 Ventana Micro Systems Inc.
*/
+#define pr_fmt(fmt) "suspend: " fmt
+
#include
+#include
#include
+#include
#include
void suspend_save_csrs(struct suspend_context *context)
@@ -85,3 +89,43 @@ int cpu_suspend(unsigned long arg,
return rc;
}
+
+#ifdef CONFIG_RISCV_SBI
+static int sbi_system_suspend(unsigned long sleep_type,
+ unsigned long resume_addr,
+ unsigned long opaque)
+{
+ struct sbiret ret;
+
+ ret = sbi_ecall(SBI_EXT_SUSP, SBI_EXT_SUSP_SYSTEM_SUSPEND,
+ sleep_type, resume_addr, opaque, 0, 0, 0);
+ if (ret.error)
+ return sbi_err_map_linux_errno(ret.error);
+
+ return ret.value;
+}
+
+static int sbi_system_suspend_enter(suspend_state_t state)
+{
+ return cpu_suspend(SBI_SUSP_SLEEP_TYPE_SUSPEND_TO_RAM, sbi_system_suspend);
+}
+
+static const struct platform_suspend_ops sbi_system_suspend_ops = {
+ .valid = suspend_valid_only_mem,
+ .enter = sbi_system_suspend_enter,
+};
+
+static int __init sbi_system_suspend_init(void)
+{
+ if (sbi_spec_version >= sbi_mk_version(2, 0) &&
+ sbi_probe_extension(SBI_EXT_SUSP) > 0) {
+ pr_info("SBI SUSP extension detected\n");
+ if (IS_ENABLED(CONFIG_SUSPEND))
+ suspend_set_ops(&sbi_system_suspend_ops);
+ }
+
+ return 0;
+}
+
+arch_initcall(sbi_system_suspend_init);
+#endif /* CONFIG_RISCV_SBI */
diff --git a/arch/riscv/kernel/vector.c b/arch/riscv/kernel/vector.c
index 578b6292487e1bb5e32309ee6874b8ba7a0c8315..6727d1d3b8f282c16a161c96ba898a17db87176e 100644
--- a/arch/riscv/kernel/vector.c
+++ b/arch/riscv/kernel/vector.c
@@ -21,6 +21,10 @@
#include
static bool riscv_v_implicit_uacc = IS_ENABLED(CONFIG_RISCV_ISA_V_DEFAULT_ENABLE);
+static struct kmem_cache *riscv_v_user_cachep;
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+static struct kmem_cache *riscv_v_kernel_cachep;
+#endif
unsigned long riscv_v_vsize __read_mostly;
EXPORT_SYMBOL_GPL(riscv_v_vsize);
@@ -47,6 +51,21 @@ int riscv_v_setup_vsize(void)
return 0;
}
+void __init riscv_v_setup_ctx_cache(void)
+{
+ if (!has_vector())
+ return;
+
+ riscv_v_user_cachep = kmem_cache_create_usercopy("riscv_vector_ctx",
+ riscv_v_vsize, 16, SLAB_PANIC,
+ 0, riscv_v_vsize, NULL);
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+ riscv_v_kernel_cachep = kmem_cache_create("riscv_vector_kctx",
+ riscv_v_vsize, 16,
+ SLAB_PANIC, NULL);
+#endif
+}
+
static bool insn_is_vector(u32 insn_buf)
{
u32 opcode = insn_buf & __INSN_OPCODE_MASK;
@@ -80,20 +99,37 @@ static bool insn_is_vector(u32 insn_buf)
return false;
}
-static int riscv_v_thread_zalloc(void)
+static int riscv_v_thread_zalloc(struct kmem_cache *cache,
+ struct __riscv_v_ext_state *ctx)
{
void *datap;
- datap = kzalloc(riscv_v_vsize, GFP_KERNEL);
+ datap = kmem_cache_zalloc(cache, GFP_KERNEL);
if (!datap)
return -ENOMEM;
- current->thread.vstate.datap = datap;
- memset(¤t->thread.vstate, 0, offsetof(struct __riscv_v_ext_state,
- datap));
+ ctx->datap = datap;
+ memset(ctx, 0, offsetof(struct __riscv_v_ext_state, datap));
return 0;
}
+void riscv_v_thread_alloc(struct task_struct *tsk)
+{
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+ riscv_v_thread_zalloc(riscv_v_kernel_cachep, &tsk->thread.kernel_vstate);
+#endif
+}
+
+void riscv_v_thread_free(struct task_struct *tsk)
+{
+ if (tsk->thread.vstate.datap)
+ kmem_cache_free(riscv_v_user_cachep, tsk->thread.vstate.datap);
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+ if (tsk->thread.kernel_vstate.datap)
+ kmem_cache_free(riscv_v_kernel_cachep, tsk->thread.kernel_vstate.datap);
+#endif
+}
+
#define VSTATE_CTRL_GET_CUR(x) ((x) & PR_RISCV_V_VSTATE_CTRL_CUR_MASK)
#define VSTATE_CTRL_GET_NEXT(x) (((x) & PR_RISCV_V_VSTATE_CTRL_NEXT_MASK) >> 2)
#define VSTATE_CTRL_MAKE_NEXT(x) (((x) << 2) & PR_RISCV_V_VSTATE_CTRL_NEXT_MASK)
@@ -122,7 +158,8 @@ static inline void riscv_v_ctrl_set(struct task_struct *tsk, int cur, int nxt,
ctrl |= VSTATE_CTRL_MAKE_NEXT(nxt);
if (inherit)
ctrl |= PR_RISCV_V_VSTATE_CTRL_INHERIT;
- tsk->thread.vstate_ctrl = ctrl;
+ tsk->thread.vstate_ctrl &= ~PR_RISCV_V_VSTATE_CTRL_MASK;
+ tsk->thread.vstate_ctrl |= ctrl;
}
bool riscv_v_vstate_ctrl_user_allowed(void)
@@ -162,12 +199,12 @@ bool riscv_v_first_use_handler(struct pt_regs *regs)
* context where VS has been off. So, try to allocate the user's V
* context and resume execution.
*/
- if (riscv_v_thread_zalloc()) {
+ if (riscv_v_thread_zalloc(riscv_v_user_cachep, ¤t->thread.vstate)) {
force_sig(SIGBUS);
return true;
}
riscv_v_vstate_on(regs);
- riscv_v_vstate_restore(current, regs);
+ riscv_v_vstate_set_restore(current, regs);
return true;
}
diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile
index 26cb2502ecf8969b76a47e874f6be9e90219887b..bd6e6c1b0497b48419bedb70eb451010c6128eb9 100644
--- a/arch/riscv/lib/Makefile
+++ b/arch/riscv/lib/Makefile
@@ -6,8 +6,14 @@ lib-y += memmove.o
lib-y += strcmp.o
lib-y += strlen.o
lib-y += strncmp.o
+lib-y += csum.o
+ifeq ($(CONFIG_MMU), y)
+lib-$(CONFIG_RISCV_ISA_V) += uaccess_vector.o
+endif
lib-$(CONFIG_MMU) += uaccess.o
lib-$(CONFIG_64BIT) += tishift.o
lib-$(CONFIG_RISCV_ISA_ZICBOZ) += clear_page.o
obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
+lib-$(CONFIG_RISCV_ISA_V) += xor.o
+lib-$(CONFIG_RISCV_ISA_V) += riscv_v_helpers.o
diff --git a/arch/riscv/lib/csum.c b/arch/riscv/lib/csum.c
new file mode 100644
index 0000000000000000000000000000000000000000..af3df5274ccbae0118488080040f45881a3e025a
--- /dev/null
+++ b/arch/riscv/lib/csum.c
@@ -0,0 +1,328 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Checksum library
+ *
+ * Influenced by arch/arm64/lib/csum.c
+ * Copyright (C) 2023 Rivos Inc.
+ */
+#include
+#include
+#include
+#include
+#include
+
+#include
+
+#include
+
+/* Default version is sufficient for 32 bit */
+#ifndef CONFIG_32BIT
+__sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+ const struct in6_addr *daddr,
+ __u32 len, __u8 proto, __wsum csum)
+{
+ unsigned int ulen, uproto;
+ unsigned long sum = (__force unsigned long)csum;
+
+ sum += (__force unsigned long)saddr->s6_addr32[0];
+ sum += (__force unsigned long)saddr->s6_addr32[1];
+ sum += (__force unsigned long)saddr->s6_addr32[2];
+ sum += (__force unsigned long)saddr->s6_addr32[3];
+
+ sum += (__force unsigned long)daddr->s6_addr32[0];
+ sum += (__force unsigned long)daddr->s6_addr32[1];
+ sum += (__force unsigned long)daddr->s6_addr32[2];
+ sum += (__force unsigned long)daddr->s6_addr32[3];
+
+ ulen = (__force unsigned int)htonl((unsigned int)len);
+ sum += ulen;
+
+ uproto = (__force unsigned int)htonl(proto);
+ sum += uproto;
+
+ /*
+ * Zbb support saves 4 instructions, so not worth checking without
+ * alternatives if supported
+ */
+ if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) &&
+ IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
+ unsigned long fold_temp;
+
+ /*
+ * Zbb is likely available when the kernel is compiled with Zbb
+ * support, so nop when Zbb is available and jump when Zbb is
+ * not available.
+ */
+ asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
+ RISCV_ISA_EXT_ZBB, 1)
+ :
+ :
+ :
+ : no_zbb);
+ asm(".option push \n\
+ .option arch,+zbb \n\
+ rori %[fold_temp], %[sum], 32 \n\
+ add %[sum], %[fold_temp], %[sum] \n\
+ srli %[sum], %[sum], 32 \n\
+ not %[fold_temp], %[sum] \n\
+ roriw %[sum], %[sum], 16 \n\
+ subw %[sum], %[fold_temp], %[sum] \n\
+ .option pop"
+ : [sum] "+r" (sum), [fold_temp] "=&r" (fold_temp));
+ return (__force __sum16)(sum >> 16);
+ }
+no_zbb:
+ sum += ror64(sum, 32);
+ sum >>= 32;
+ return csum_fold((__force __wsum)sum);
+}
+EXPORT_SYMBOL(csum_ipv6_magic);
+#endif /* !CONFIG_32BIT */
+
+#ifdef CONFIG_32BIT
+#define OFFSET_MASK 3
+#elif CONFIG_64BIT
+#define OFFSET_MASK 7
+#endif
+
+static inline __no_sanitize_address unsigned long
+do_csum_common(const unsigned long *ptr, const unsigned long *end,
+ unsigned long data)
+{
+ unsigned int shift;
+ unsigned long csum = 0, carry = 0;
+
+ /*
+ * Do 32-bit reads on RV32 and 64-bit reads otherwise. This should be
+ * faster than doing 32-bit reads on architectures that support larger
+ * reads.
+ */
+ while (ptr < end) {
+ csum += data;
+ carry += csum < data;
+ data = *(ptr++);
+ }
+
+ /*
+ * Perform alignment (and over-read) bytes on the tail if any bytes
+ * leftover.
+ */
+ shift = ((long)ptr - (long)end) * 8;
+#ifdef __LITTLE_ENDIAN
+ data = (data << shift) >> shift;
+#else
+ data = (data >> shift) << shift;
+#endif
+ csum += data;
+ carry += csum < data;
+ csum += carry;
+ csum += csum < carry;
+
+ return csum;
+}
+
+/*
+ * Algorithm accounts for buff being misaligned.
+ * If buff is not aligned, will over-read bytes but not use the bytes that it
+ * shouldn't. The same thing will occur on the tail-end of the read.
+ */
+static inline __no_sanitize_address unsigned int
+do_csum_with_alignment(const unsigned char *buff, int len)
+{
+ unsigned int offset, shift;
+ unsigned long csum, data;
+ const unsigned long *ptr, *end;
+
+ /*
+ * Align address to closest word (double word on rv64) that comes before
+ * buff. This should always be in the same page and cache line.
+ * Directly call KASAN with the alignment we will be using.
+ */
+ offset = (unsigned long)buff & OFFSET_MASK;
+ kasan_check_read(buff, len);
+ ptr = (const unsigned long *)(buff - offset);
+
+ /*
+ * Clear the most significant bytes that were over-read if buff was not
+ * aligned.
+ */
+ shift = offset * 8;
+ data = *(ptr++);
+#ifdef __LITTLE_ENDIAN
+ data = (data >> shift) << shift;
+#else
+ data = (data << shift) >> shift;
+#endif
+ end = (const unsigned long *)(buff + len);
+ csum = do_csum_common(ptr, end, data);
+
+#ifdef CC_HAS_ASM_GOTO_TIED_OUTPUT
+ /*
+ * Zbb support saves 6 instructions, so not worth checking without
+ * alternatives if supported
+ */
+ if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) &&
+ IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
+ unsigned long fold_temp;
+
+ /*
+ * Zbb is likely available when the kernel is compiled with Zbb
+ * support, so nop when Zbb is available and jump when Zbb is
+ * not available.
+ */
+ asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
+ RISCV_ISA_EXT_ZBB, 1)
+ :
+ :
+ :
+ : no_zbb);
+
+#ifdef CONFIG_32BIT
+ asm_volatile_goto(".option push \n\
+ .option arch,+zbb \n\
+ rori %[fold_temp], %[csum], 16 \n\
+ andi %[offset], %[offset], 1 \n\
+ add %[csum], %[fold_temp], %[csum] \n\
+ beq %[offset], zero, %l[end] \n\
+ rev8 %[csum], %[csum] \n\
+ .option pop"
+ : [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp)
+ : [offset] "r" (offset)
+ :
+ : end);
+
+ return (unsigned short)csum;
+#else /* !CONFIG_32BIT */
+ asm_volatile_goto(".option push \n\
+ .option arch,+zbb \n\
+ rori %[fold_temp], %[csum], 32 \n\
+ add %[csum], %[fold_temp], %[csum] \n\
+ srli %[csum], %[csum], 32 \n\
+ roriw %[fold_temp], %[csum], 16 \n\
+ addw %[csum], %[fold_temp], %[csum] \n\
+ andi %[offset], %[offset], 1 \n\
+ beq %[offset], zero, %l[end] \n\
+ rev8 %[csum], %[csum] \n\
+ .option pop"
+ : [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp)
+ : [offset] "r" (offset)
+ :
+ : end);
+
+ return (csum << 16) >> 48;
+#endif /* !CONFIG_32BIT */
+end:
+ return csum >> 16;
+ }
+no_zbb:
+#endif /* CC_HAS_ASM_GOTO_TIED_OUTPUT */
+#ifndef CONFIG_32BIT
+ csum += ror64(csum, 32);
+ csum >>= 32;
+#endif
+ csum = (u32)csum + ror32((u32)csum, 16);
+ if (offset & 1)
+ return (u16)swab32(csum);
+ return csum >> 16;
+}
+
+/*
+ * Does not perform alignment, should only be used if machine has fast
+ * misaligned accesses, or when buff is known to be aligned.
+ */
+static inline __no_sanitize_address unsigned int
+do_csum_no_alignment(const unsigned char *buff, int len)
+{
+ unsigned long csum, data;
+ const unsigned long *ptr, *end;
+
+ ptr = (const unsigned long *)(buff);
+ data = *(ptr++);
+
+ kasan_check_read(buff, len);
+
+ end = (const unsigned long *)(buff + len);
+ csum = do_csum_common(ptr, end, data);
+
+ /*
+ * Zbb support saves 6 instructions, so not worth checking without
+ * alternatives if supported
+ */
+ if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) &&
+ IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
+ unsigned long fold_temp;
+
+ /*
+ * Zbb is likely available when the kernel is compiled with Zbb
+ * support, so nop when Zbb is available and jump when Zbb is
+ * not available.
+ */
+ asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
+ RISCV_ISA_EXT_ZBB, 1)
+ :
+ :
+ :
+ : no_zbb);
+
+#ifdef CONFIG_32BIT
+ asm (".option push \n\
+ .option arch,+zbb \n\
+ rori %[fold_temp], %[csum], 16 \n\
+ add %[csum], %[fold_temp], %[csum] \n\
+ .option pop"
+ : [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp)
+ :
+ : );
+
+#else /* !CONFIG_32BIT */
+ asm (".option push \n\
+ .option arch,+zbb \n\
+ rori %[fold_temp], %[csum], 32 \n\
+ add %[csum], %[fold_temp], %[csum] \n\
+ srli %[csum], %[csum], 32 \n\
+ roriw %[fold_temp], %[csum], 16 \n\
+ addw %[csum], %[fold_temp], %[csum] \n\
+ .option pop"
+ : [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp)
+ :
+ : );
+#endif /* !CONFIG_32BIT */
+ return csum >> 16;
+ }
+no_zbb:
+#ifndef CONFIG_32BIT
+ csum += ror64(csum, 32);
+ csum >>= 32;
+#endif
+ csum = (u32)csum + ror32((u32)csum, 16);
+ return csum >> 16;
+}
+
+/*
+ * Perform a checksum on an arbitrary memory address.
+ * Will do a light-weight address alignment if buff is misaligned, unless
+ * cpu supports fast misaligned accesses.
+ */
+unsigned int do_csum(const unsigned char *buff, int len)
+{
+ if (unlikely(len <= 0))
+ return 0;
+
+ /*
+ * Significant performance gains can be seen by not doing alignment
+ * on machines with fast misaligned accesses.
+ *
+ * There is some duplicate code between the "with_alignment" and
+ * "no_alignment" implmentations, but the overlap is too awkward to be
+ * able to fit in one function without introducing multiple static
+ * branches. The largest chunk of overlap was delegated into the
+ * do_csum_common function.
+ */
+ if (static_branch_likely(&fast_misaligned_access_speed_key))
+ return do_csum_no_alignment(buff, len);
+
+ if (((unsigned long)buff & OFFSET_MASK) == 0)
+ return do_csum_no_alignment(buff, len);
+
+ return do_csum_with_alignment(buff, len);
+}
diff --git a/arch/riscv/lib/riscv_v_helpers.c b/arch/riscv/lib/riscv_v_helpers.c
new file mode 100644
index 0000000000000000000000000000000000000000..be38a93cedaec5dafcd15d2f855df11474d2f383
--- /dev/null
+++ b/arch/riscv/lib/riscv_v_helpers.c
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2023 SiFive
+ * Author: Andy Chiu
+ */
+#include
+#include
+
+#include
+#include
+
+#ifdef CONFIG_MMU
+#include
+#endif
+
+#ifdef CONFIG_MMU
+size_t riscv_v_usercopy_threshold = CONFIG_RISCV_ISA_V_UCOPY_THRESHOLD;
+int __asm_vector_usercopy(void *dst, void *src, size_t n);
+int fallback_scalar_usercopy(void *dst, void *src, size_t n);
+asmlinkage int enter_vector_usercopy(void *dst, void *src, size_t n)
+{
+ size_t remain, copied;
+
+ /* skip has_vector() check because it has been done by the asm */
+ if (!may_use_simd())
+ goto fallback;
+
+ kernel_vector_begin();
+ remain = __asm_vector_usercopy(dst, src, n);
+ kernel_vector_end();
+
+ if (remain) {
+ copied = n - remain;
+ dst += copied;
+ src += copied;
+ n = remain;
+ goto fallback;
+ }
+
+ return remain;
+
+fallback:
+ return fallback_scalar_usercopy(dst, src, n);
+}
+#endif
diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S
index a9d356d6c03cda8350717c7bb1d81cdae88d6362..bc22c078aba81a8170506eddb8642d3353ac461c 100644
--- a/arch/riscv/lib/uaccess.S
+++ b/arch/riscv/lib/uaccess.S
@@ -3,6 +3,8 @@
#include
#include
#include
+#include
+#include
.macro fixup op reg addr lbl
100:
@@ -11,6 +13,13 @@
.endm
SYM_FUNC_START(__asm_copy_to_user)
+#ifdef CONFIG_RISCV_ISA_V
+ ALTERNATIVE("j fallback_scalar_usercopy", "nop", 0, RISCV_ISA_EXT_v, CONFIG_RISCV_ISA_V)
+ REG_L t0, riscv_v_usercopy_threshold
+ bltu a2, t0, fallback_scalar_usercopy
+ tail enter_vector_usercopy
+#endif
+SYM_FUNC_START(fallback_scalar_usercopy)
/* Enable access to user memory */
li t6, SR_SUM
@@ -181,6 +190,7 @@ SYM_FUNC_START(__asm_copy_to_user)
sub a0, t5, a0
ret
SYM_FUNC_END(__asm_copy_to_user)
+SYM_FUNC_END(fallback_scalar_usercopy)
EXPORT_SYMBOL(__asm_copy_to_user)
SYM_FUNC_ALIAS(__asm_copy_from_user, __asm_copy_to_user)
EXPORT_SYMBOL(__asm_copy_from_user)
diff --git a/arch/riscv/lib/uaccess_vector.S b/arch/riscv/lib/uaccess_vector.S
new file mode 100644
index 0000000000000000000000000000000000000000..51ab5588e9ff36b8b7dc80096be587d09da2881f
--- /dev/null
+++ b/arch/riscv/lib/uaccess_vector.S
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#include
+#include
+#include
+#include
+#include
+
+#define pDst a0
+#define pSrc a1
+#define iNum a2
+
+#define iVL a3
+
+#define ELEM_LMUL_SETTING m8
+#define vData v0
+
+ .macro fixup op reg addr lbl
+100:
+ \op \reg, \addr
+ _asm_extable 100b, \lbl
+ .endm
+
+SYM_FUNC_START(__asm_vector_usercopy)
+ /* Enable access to user memory */
+ li t6, SR_SUM
+ csrs CSR_STATUS, t6
+
+loop:
+ vsetvli iVL, iNum, e8, ELEM_LMUL_SETTING, ta, ma
+ fixup vle8.v vData, (pSrc), 10f
+ sub iNum, iNum, iVL
+ add pSrc, pSrc, iVL
+ fixup vse8.v vData, (pDst), 11f
+ add pDst, pDst, iVL
+ bnez iNum, loop
+
+ /* Exception fixup for vector load is shared with normal exit */
+10:
+ /* Disable access to user memory */
+ csrc CSR_STATUS, t6
+ mv a0, iNum
+ ret
+
+ /* Exception fixup code for vector store. */
+11:
+ /* Undo the subtraction after vle8.v */
+ add iNum, iNum, iVL
+ /* Make sure the scalar fallback skip already processed bytes */
+ csrr t2, CSR_VSTART
+ sub iNum, iNum, t2
+ j 10b
+SYM_FUNC_END(__asm_vector_usercopy)
diff --git a/arch/riscv/lib/xor.S b/arch/riscv/lib/xor.S
new file mode 100644
index 0000000000000000000000000000000000000000..b28f2430e52fa50c199cd80153647fde33088e4c
--- /dev/null
+++ b/arch/riscv/lib/xor.S
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2021 SiFive
+ */
+#include
+#include
+#include
+
+SYM_FUNC_START(xor_regs_2_)
+ vsetvli a3, a0, e8, m8, ta, ma
+ vle8.v v0, (a1)
+ vle8.v v8, (a2)
+ sub a0, a0, a3
+ vxor.vv v16, v0, v8
+ add a2, a2, a3
+ vse8.v v16, (a1)
+ add a1, a1, a3
+ bnez a0, xor_regs_2_
+ ret
+SYM_FUNC_END(xor_regs_2_)
+EXPORT_SYMBOL(xor_regs_2_)
+
+SYM_FUNC_START(xor_regs_3_)
+ vsetvli a4, a0, e8, m8, ta, ma
+ vle8.v v0, (a1)
+ vle8.v v8, (a2)
+ sub a0, a0, a4
+ vxor.vv v0, v0, v8
+ vle8.v v16, (a3)
+ add a2, a2, a4
+ vxor.vv v16, v0, v16
+ add a3, a3, a4
+ vse8.v v16, (a1)
+ add a1, a1, a4
+ bnez a0, xor_regs_3_
+ ret
+SYM_FUNC_END(xor_regs_3_)
+EXPORT_SYMBOL(xor_regs_3_)
+
+SYM_FUNC_START(xor_regs_4_)
+ vsetvli a5, a0, e8, m8, ta, ma
+ vle8.v v0, (a1)
+ vle8.v v8, (a2)
+ sub a0, a0, a5
+ vxor.vv v0, v0, v8
+ vle8.v v16, (a3)
+ add a2, a2, a5
+ vxor.vv v0, v0, v16
+ vle8.v v24, (a4)
+ add a3, a3, a5
+ vxor.vv v16, v0, v24
+ add a4, a4, a5
+ vse8.v v16, (a1)
+ add a1, a1, a5
+ bnez a0, xor_regs_4_
+ ret
+SYM_FUNC_END(xor_regs_4_)
+EXPORT_SYMBOL(xor_regs_4_)
+
+SYM_FUNC_START(xor_regs_5_)
+ vsetvli a6, a0, e8, m8, ta, ma
+ vle8.v v0, (a1)
+ vle8.v v8, (a2)
+ sub a0, a0, a6
+ vxor.vv v0, v0, v8
+ vle8.v v16, (a3)
+ add a2, a2, a6
+ vxor.vv v0, v0, v16
+ vle8.v v24, (a4)
+ add a3, a3, a6
+ vxor.vv v0, v0, v24
+ vle8.v v8, (a5)
+ add a4, a4, a6
+ vxor.vv v16, v0, v8
+ add a5, a5, a6
+ vse8.v v16, (a1)
+ add a1, a1, a6
+ bnez a0, xor_regs_5_
+ ret
+SYM_FUNC_END(xor_regs_5_)
+EXPORT_SYMBOL(xor_regs_5_)
diff --git a/arch/riscv/mm/extable.c b/arch/riscv/mm/extable.c
index 35484d830fd6d7fe0a2a521bc736b1c5883afa51..dd1530af3ef15bf74cec58b5a4394918f6a8beb0 100644
--- a/arch/riscv/mm/extable.c
+++ b/arch/riscv/mm/extable.c
@@ -27,6 +27,14 @@ static bool ex_handler_fixup(const struct exception_table_entry *ex,
return true;
}
+static inline unsigned long regs_get_gpr(struct pt_regs *regs, unsigned int offset)
+{
+ if (unlikely(!offset || offset > MAX_REG_OFFSET))
+ return 0;
+
+ return *(unsigned long *)((unsigned long)regs + offset);
+}
+
static inline void regs_set_gpr(struct pt_regs *regs, unsigned int offset,
unsigned long val)
{
@@ -50,6 +58,27 @@ static bool ex_handler_uaccess_err_zero(const struct exception_table_entry *ex,
return true;
}
+static bool
+ex_handler_load_unaligned_zeropad(const struct exception_table_entry *ex,
+ struct pt_regs *regs)
+{
+ int reg_data = FIELD_GET(EX_DATA_REG_DATA, ex->data);
+ int reg_addr = FIELD_GET(EX_DATA_REG_ADDR, ex->data);
+ unsigned long data, addr, offset;
+
+ addr = regs_get_gpr(regs, reg_addr * sizeof(unsigned long));
+
+ offset = addr & 0x7UL;
+ addr &= ~0x7UL;
+
+ data = *(unsigned long *)addr >> (offset * 8);
+
+ regs_set_gpr(regs, reg_data * sizeof(unsigned long), data);
+
+ regs->epc = get_ex_fixup(ex);
+ return true;
+}
+
bool fixup_exception(struct pt_regs *regs)
{
const struct exception_table_entry *ex;
@@ -65,6 +94,8 @@ bool fixup_exception(struct pt_regs *regs)
return ex_handler_bpf(ex, regs);
case EX_TYPE_UACCESS_ERR_ZERO:
return ex_handler_uaccess_err_zero(ex, regs);
+ case EX_TYPE_LOAD_UNALIGNED_ZEROPAD:
+ return ex_handler_load_unaligned_zeropad(ex, regs);
}
BUG();
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index a65937336cdc8840f6f8997f6a320cf97cf31577..32cad6a65ccd23431d63097a0906ca5b8de485f8 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -1060,7 +1060,11 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
kernel_map.virt_addr = KERNEL_LINK_ADDR + kernel_map.virt_offset;
#ifdef CONFIG_XIP_KERNEL
+#ifdef CONFIG_64BIT
kernel_map.page_offset = PAGE_OFFSET_L3;
+#else
+ kernel_map.page_offset = _AC(CONFIG_PAGE_OFFSET, UL);
+#endif
kernel_map.xiprom = (uintptr_t)CONFIG_XIP_PHYS_ADDR;
kernel_map.xiprom_sz = (uintptr_t)(&_exiprom) - (uintptr_t)(&_xiprom);
@@ -1387,10 +1391,29 @@ void __init misc_mem_init(void)
}
#ifdef CONFIG_SPARSEMEM_VMEMMAP
+void __meminit vmemmap_set_pmd(pmd_t *pmd, void *p, int node,
+ unsigned long addr, unsigned long next)
+{
+ pmd_set_huge(pmd, virt_to_phys(p), PAGE_KERNEL);
+}
+
+int __meminit vmemmap_check_pmd(pmd_t *pmdp, int node,
+ unsigned long addr, unsigned long next)
+{
+ vmemmap_verify((pte_t *)pmdp, node, addr, next);
+ return 1;
+}
+
int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
struct vmem_altmap *altmap)
{
- return vmemmap_populate_basepages(start, end, node, NULL);
+ /*
+ * Note that SPARSEMEM_VMEMMAP is only selected for rv64 and that we
+ * can't use hugepage mappings for 2-level page table because in case of
+ * memory hotplug, we are not able to update all the page tables with
+ * the new PMDs.
+ */
+ return vmemmap_populate_hugepages(start, end, node, NULL);
}
#endif
diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index 8aadc5f71c93bedf88c3618a531141de49d6b5a2..8d12b26f5ac37b659687981c2046f3d5b590753c 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -98,29 +98,23 @@ static void __ipi_flush_tlb_range_asid(void *info)
local_flush_tlb_range_asid(d->start, d->size, d->stride, d->asid);
}
-static void __flush_tlb_range(struct mm_struct *mm, unsigned long start,
- unsigned long size, unsigned long stride)
+static void __flush_tlb_range(struct cpumask *cmask, unsigned long asid,
+ unsigned long start, unsigned long size,
+ unsigned long stride)
{
struct flush_tlb_range_data ftd;
- const struct cpumask *cmask;
- unsigned long asid = FLUSH_TLB_NO_ASID;
bool broadcast;
- if (mm) {
- unsigned int cpuid;
+ if (cpumask_empty(cmask))
+ return;
- cmask = mm_cpumask(mm);
- if (cpumask_empty(cmask))
- return;
+ if (cmask != cpu_online_mask) {
+ unsigned int cpuid;
cpuid = get_cpu();
/* check if the tlbflush needs to be sent to other CPUs */
broadcast = cpumask_any_but(cmask, cpuid) < nr_cpu_ids;
-
- if (static_branch_unlikely(&use_asid_allocator))
- asid = atomic_long_read(&mm->context.id) & asid_mask;
} else {
- cmask = cpu_online_mask;
broadcast = true;
}
@@ -140,25 +134,34 @@ static void __flush_tlb_range(struct mm_struct *mm, unsigned long start,
local_flush_tlb_range_asid(start, size, stride, asid);
}
- if (mm)
+ if (cmask != cpu_online_mask)
put_cpu();
}
+static inline unsigned long get_mm_asid(struct mm_struct *mm)
+{
+ return static_branch_unlikely(&use_asid_allocator) ?
+ atomic_long_read(&mm->context.id) & asid_mask : FLUSH_TLB_NO_ASID;
+}
+
void flush_tlb_mm(struct mm_struct *mm)
{
- __flush_tlb_range(mm, 0, FLUSH_TLB_MAX_SIZE, PAGE_SIZE);
+ __flush_tlb_range(mm_cpumask(mm), get_mm_asid(mm),
+ 0, FLUSH_TLB_MAX_SIZE, PAGE_SIZE);
}
void flush_tlb_mm_range(struct mm_struct *mm,
unsigned long start, unsigned long end,
unsigned int page_size)
{
- __flush_tlb_range(mm, start, end - start, page_size);
+ __flush_tlb_range(mm_cpumask(mm), get_mm_asid(mm),
+ start, end - start, page_size);
}
void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
{
- __flush_tlb_range(vma->vm_mm, addr, PAGE_SIZE, PAGE_SIZE);
+ __flush_tlb_range(mm_cpumask(vma->vm_mm), get_mm_asid(vma->vm_mm),
+ addr, PAGE_SIZE, PAGE_SIZE);
}
void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
@@ -190,18 +193,44 @@ void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
}
}
- __flush_tlb_range(vma->vm_mm, start, end - start, stride_size);
+ __flush_tlb_range(mm_cpumask(vma->vm_mm), get_mm_asid(vma->vm_mm),
+ start, end - start, stride_size);
}
void flush_tlb_kernel_range(unsigned long start, unsigned long end)
{
- __flush_tlb_range(NULL, start, end - start, PAGE_SIZE);
+ __flush_tlb_range((struct cpumask *)cpu_online_mask, FLUSH_TLB_NO_ASID,
+ start, end - start, PAGE_SIZE);
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
unsigned long end)
{
- __flush_tlb_range(vma->vm_mm, start, end - start, PMD_SIZE);
+ __flush_tlb_range(mm_cpumask(vma->vm_mm), get_mm_asid(vma->vm_mm),
+ start, end - start, PMD_SIZE);
}
#endif
+
+bool arch_tlbbatch_should_defer(struct mm_struct *mm)
+{
+ return true;
+}
+
+void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
+ struct mm_struct *mm,
+ unsigned long uaddr)
+{
+ cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm));
+}
+
+void arch_flush_tlb_batched_pending(struct mm_struct *mm)
+{
+ flush_tlb_mm(mm);
+}
+
+void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
+{
+ __flush_tlb_range(&batch->cpumask, FLUSH_TLB_NO_ASID, 0,
+ FLUSH_TLB_MAX_SIZE, PAGE_SIZE);
+}
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 58dc64dd94a82c8d8cc42a71ec69954dc548934a..719a97e7edb2c12277a8e08dd214e0eb03be094a 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -795,6 +795,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY];
struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT];
struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN];
+ bool is_struct_ops = flags & BPF_TRAMP_F_INDIRECT;
void *orig_call = func_addr;
bool save_ret;
u32 insn;
@@ -878,7 +879,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
stack_size = round_up(stack_size, 16);
- if (func_addr) {
+ if (!is_struct_ops) {
/* For the trampoline called from function entry,
* the frame of traced function and the frame of
* trampoline need to be considered.
@@ -998,7 +999,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
emit_ld(RV_REG_S1, -sreg_off, RV_REG_FP, ctx);
- if (func_addr) {
+ if (!is_struct_ops) {
/* trampoline called from function entry */
emit_ld(RV_REG_T0, stack_size - 8, RV_REG_SP, ctx);
emit_ld(RV_REG_FP, stack_size - 16, RV_REG_SP, ctx);
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 67ba0157fbdbb88079566d4fbfca36fff82ff9e4..cae2dd34fbb49d16ee020e72fb669010dca832f8 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -637,8 +637,9 @@ CONFIG_FUSE_FS=y
CONFIG_CUSE=m
CONFIG_VIRTIO_FS=m
CONFIG_OVERLAY_FS=m
+CONFIG_NETFS_SUPPORT=m
CONFIG_NETFS_STATS=y
-CONFIG_FSCACHE=m
+CONFIG_FSCACHE=y
CONFIG_CACHEFILES=m
CONFIG_ISO9660_FS=y
CONFIG_JOLIET=y
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index 4c2650c1fbdd36edfa3918d8ac867ef2421bd4e5..42b988873e5443df15b054d78610697fdf769293 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -622,8 +622,9 @@ CONFIG_FUSE_FS=y
CONFIG_CUSE=m
CONFIG_VIRTIO_FS=m
CONFIG_OVERLAY_FS=m
+CONFIG_NETFS_SUPPORT=m
CONFIG_NETFS_STATS=y
-CONFIG_FSCACHE=m
+CONFIG_FSCACHE=y
CONFIG_CACHEFILES=m
CONFIG_ISO9660_FS=y
CONFIG_JOLIET=y
diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c
index 0f279360838a4a7492c1ad86d38ac1f43173fc9f..30d117f9ad7eeafbc43bcaf921b94c941bb1cd8c 100644
--- a/arch/sh/boards/mach-ecovec24/setup.c
+++ b/arch/sh/boards/mach-ecovec24/setup.c
@@ -1220,7 +1220,7 @@ static int __init arch_setup(void)
lcdc_info.ch[0].num_modes = ARRAY_SIZE(ecovec_dvi_modes);
/* No backlight */
- gpio_backlight_data.fbdev = NULL;
+ gpio_backlight_data.dev = NULL;
gpio_set_value(GPIO_PTA2, 1);
gpio_set_value(GPIO_PTU1, 1);
diff --git a/arch/sh/configs/sdk7786_defconfig b/arch/sh/configs/sdk7786_defconfig
index cf59b98446e4d3e87c7fc9837ab5b06e9016f153..7b427c17fbfecb24d63e717023aad19ce1c953e8 100644
--- a/arch/sh/configs/sdk7786_defconfig
+++ b/arch/sh/configs/sdk7786_defconfig
@@ -171,7 +171,8 @@ CONFIG_BTRFS_FS=y
CONFIG_AUTOFS_FS=m
CONFIG_FUSE_FS=y
CONFIG_CUSE=m
-CONFIG_FSCACHE=m
+CONFIG_NETFS_SUPPORT=m
+CONFIG_FSCACHE=y
CONFIG_CACHEFILES=m
CONFIG_ISO9660_FS=m
CONFIG_JOLIET=y
diff --git a/arch/sh/kernel/vsyscall/Makefile b/arch/sh/kernel/vsyscall/Makefile
index 6e86644480488f692753a84950ea25e8235985c7..118744d349e21e43175017296ea978269a5a7ef4 100644
--- a/arch/sh/kernel/vsyscall/Makefile
+++ b/arch/sh/kernel/vsyscall/Makefile
@@ -1,11 +1,10 @@
# SPDX-License-Identifier: GPL-2.0
obj-y += vsyscall.o vsyscall-syscall.o vsyscall-syms.o
-$(obj)/vsyscall-syscall.o: \
- $(foreach F,trapa,$(obj)/vsyscall-$F.so)
+$(obj)/vsyscall-syscall.o: $(obj)/vsyscall-trapa.so
# Teach kbuild about targets
-targets += $(foreach F,trapa,vsyscall-$F.o vsyscall-$F.so)
+targets += vsyscall-trapa.o vsyscall-traps.so
targets += vsyscall-note.o vsyscall.lds vsyscall-dummy.o
# The DSO images are built using a special linker script
diff --git a/arch/sparc/kernel/pci_sabre.c b/arch/sparc/kernel/pci_sabre.c
index 3c38ca40a22bace28681258759f98f38b334c4bf..a84598568300d331e035f25a78977b515cb9fbc5 100644
--- a/arch/sparc/kernel/pci_sabre.c
+++ b/arch/sparc/kernel/pci_sabre.c
@@ -13,7 +13,10 @@
#include
#include
#include
-#include
+#include
+#include
+#include
+#include
#include
#include
@@ -456,7 +459,6 @@ static void sabre_pbm_init(struct pci_pbm_info *pbm,
static const struct of_device_id sabre_match[];
static int sabre_probe(struct platform_device *op)
{
- const struct of_device_id *match;
const struct linux_prom64_registers *pr_regs;
struct device_node *dp = op->dev.of_node;
struct pci_pbm_info *pbm;
@@ -466,8 +468,7 @@ static int sabre_probe(struct platform_device *op)
const u32 *vdma;
u64 clear_irq;
- match = of_match_device(sabre_match, &op->dev);
- hummingbird_p = match && (match->data != NULL);
+ hummingbird_p = (uintptr_t)device_get_match_data(&op->dev);
if (!hummingbird_p) {
struct device_node *cpu_dp;
diff --git a/arch/sparc/kernel/pci_schizo.c b/arch/sparc/kernel/pci_schizo.c
index 23b47f7fdb1d5290dd97377b5eb283dc34fa3b9b..5d8dd49495863dc64d03809373e32887102f7baa 100644
--- a/arch/sparc/kernel/pci_schizo.c
+++ b/arch/sparc/kernel/pci_schizo.c
@@ -11,7 +11,10 @@
#include
#include
#include
-#include
+#include
+#include
+#include
+#include
#include
#include
@@ -1459,15 +1462,13 @@ static int __schizo_init(struct platform_device *op, unsigned long chip_type)
return err;
}
-static const struct of_device_id schizo_match[];
static int schizo_probe(struct platform_device *op)
{
- const struct of_device_id *match;
+ unsigned long chip_type = (unsigned long)device_get_match_data(&op->dev);
- match = of_match_device(schizo_match, &op->dev);
- if (!match)
+ if (!chip_type)
return -EINVAL;
- return __schizo_init(op, (unsigned long)match->data);
+ return __schizo_init(op, chip_type);
}
/* The ordering of this table is very important. Some Tomatillo
diff --git a/arch/sparc/vdso/Makefile b/arch/sparc/vdso/Makefile
index d08c3a0443f3a77f8fe8cb388c09ca2f5e16f67c..7f5eedf1f5e0ad3ff23fcdbcf882ece7eced120c 100644
--- a/arch/sparc/vdso/Makefile
+++ b/arch/sparc/vdso/Makefile
@@ -3,9 +3,6 @@
# Building vDSO images for sparc.
#
-VDSO64-$(CONFIG_SPARC64) := y
-VDSOCOMPAT-$(CONFIG_COMPAT) := y
-
# files to link into the vdso
vobjs-y := vdso-note.o vclock_gettime.o
@@ -13,22 +10,15 @@ vobjs-y := vdso-note.o vclock_gettime.o
obj-y += vma.o
# vDSO images to build
-vdso_img-$(VDSO64-y) += 64
-vdso_img-$(VDSOCOMPAT-y) += 32
+obj-$(CONFIG_SPARC64) += vdso-image-64.o
+obj-$(CONFIG_COMPAT) += vdso-image-32.o
-vobjs := $(foreach F,$(vobjs-y),$(obj)/$F)
+vobjs := $(addprefix $(obj)/, $(vobjs-y))
$(obj)/vdso.o: $(obj)/vdso.so
targets += vdso.lds $(vobjs-y)
-
-# Build the vDSO image C files and link them in.
-vdso_img_objs := $(vdso_img-y:%=vdso-image-%.o)
-vdso_img_cfiles := $(vdso_img-y:%=vdso-image-%.c)
-vdso_img_sodbg := $(vdso_img-y:%=vdso%.so.dbg)
-obj-y += $(vdso_img_objs)
-targets += $(vdso_img_cfiles)
-targets += $(vdso_img_sodbg) $(vdso_img-y:%=vdso%.so)
+targets += $(foreach x, 32 64, vdso-image-$(x).c vdso$(x).so vdso$(x).so.dbg)
CPPFLAGS_vdso.lds += -P -C
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index feef615e2c9c8935e2cd11a4b1e09f115171d328..c9a16fba58b9c47f5424be9a8c7c6681d176b986 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -336,7 +336,7 @@ int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t bytes,
if (nr_vecs > BIO_MAX_VECS)
return -E2BIG;
if (nr_vecs > UIO_FASTIOV) {
- bvec = kcalloc(sizeof(*bvec), nr_vecs, GFP_KERNEL);
+ bvec = kcalloc(nr_vecs, sizeof(*bvec), GFP_KERNEL);
if (!bvec)
return -ENOMEM;
pages = NULL;
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index e303fd31731377cae25738cd82beea6b96a4d1b9..ff93c385ba5afb6920b53fdbcf96bd5d3970d17a 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -300,7 +300,7 @@ static inline struct blkcg *blkcg_parent(struct blkcg *blkcg)
* @disk: gendisk the new blkg is associated with
* @gfp_mask: allocation mask to use
*
- * Allocate a new blkg assocating @blkcg and @q.
+ * Allocate a new blkg associating @blkcg and @disk.
*/
static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk,
gfp_t gfp_mask)
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index 089fcb9cfce37011f4cf6ec1f86ba36853fed381..c8beec6d7df0863bb4811c12f5ff576e7a5121c7 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -1261,7 +1261,7 @@ static void weight_updated(struct ioc_gq *iocg, struct ioc_now *now)
static bool iocg_activate(struct ioc_gq *iocg, struct ioc_now *now)
{
struct ioc *ioc = iocg->ioc;
- u64 last_period, cur_period;
+ u64 __maybe_unused last_period, cur_period;
u64 vtime, vtarget;
int i;
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 5cbeb9344f2f5cea3121197892a412deab777838..94668e72ab09bf0922c8d79846a87d91fdbeb1ba 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -479,23 +479,6 @@ static int hctx_sched_tags_bitmap_show(void *data, struct seq_file *m)
return res;
}
-static int hctx_run_show(void *data, struct seq_file *m)
-{
- struct blk_mq_hw_ctx *hctx = data;
-
- seq_printf(m, "%lu\n", hctx->run);
- return 0;
-}
-
-static ssize_t hctx_run_write(void *data, const char __user *buf, size_t count,
- loff_t *ppos)
-{
- struct blk_mq_hw_ctx *hctx = data;
-
- hctx->run = 0;
- return count;
-}
-
static int hctx_active_show(void *data, struct seq_file *m)
{
struct blk_mq_hw_ctx *hctx = data;
@@ -624,7 +607,6 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = {
{"tags_bitmap", 0400, hctx_tags_bitmap_show},
{"sched_tags", 0400, hctx_sched_tags_show},
{"sched_tags_bitmap", 0400, hctx_sched_tags_bitmap_show},
- {"run", 0600, hctx_run_show, hctx_run_write},
{"active", 0400, hctx_active_show},
{"dispatch_busy", 0400, hctx_dispatch_busy_show},
{"type", 0400, hctx_type_show},
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 67c95f31b15bb1e16c022efe644dcb0900ef12f6..451a2c1f1f32186989160ed6e77e87cb8d14f4f1 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -324,8 +324,6 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
if (unlikely(blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)))
return;
- hctx->run++;
-
/*
* A return of -EAGAIN is an indication that hctx->dispatch is not
* empty and we must run again in order to avoid starving flushes.
diff --git a/block/blk-mq.c b/block/blk-mq.c
index c11c97afa0bc1de400a68cff21e48d7f420e6bab..aa87fcfda1ecfc875c86a0258fe16e707ce3f167 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -772,11 +772,16 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
/*
* Partial zone append completions cannot be supported as the
* BIO fragments may end up not being written sequentially.
+ * For such case, force the completed nbytes to be equal to
+ * the BIO size so that bio_advance() sets the BIO remaining
+ * size to 0 and we end up calling bio_endio() before returning.
*/
- if (bio->bi_iter.bi_size != nbytes)
+ if (bio->bi_iter.bi_size != nbytes) {
bio->bi_status = BLK_STS_IOERR;
- else
+ nbytes = bio->bi_iter.bi_size;
+ } else {
bio->bi_iter.bi_sector = rq->__sector;
+ }
}
bio_advance(bio, nbytes);
@@ -1859,6 +1864,22 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
wait->flags &= ~WQ_FLAG_EXCLUSIVE;
__add_wait_queue(wq, wait);
+ /*
+ * Add one explicit barrier since blk_mq_get_driver_tag() may
+ * not imply barrier in case of failure.
+ *
+ * Order adding us to wait queue and allocating driver tag.
+ *
+ * The pair is the one implied in sbitmap_queue_wake_up() which
+ * orders clearing sbitmap tag bits and waitqueue_active() in
+ * __sbitmap_queue_wake_up(), since waitqueue_active() is lockless
+ *
+ * Otherwise, re-order of adding wait queue and getting driver tag
+ * may cause __sbitmap_queue_wake_up() to wake up nothing because
+ * the waitqueue_active() may not observe us in wait queue.
+ */
+ smp_mb();
+
/*
* It's possible that a tag was freed in the window between the
* allocation failure and adding the hardware queue to the wait
@@ -2891,8 +2912,11 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q,
return NULL;
}
-/* return true if this @rq can be used for @bio */
-static bool blk_mq_can_use_cached_rq(struct request *rq, struct blk_plug *plug,
+/*
+ * Check if we can use the passed on request for submitting the passed in bio,
+ * and remove it from the request list if it can be used.
+ */
+static bool blk_mq_use_cached_rq(struct request *rq, struct blk_plug *plug,
struct bio *bio)
{
enum hctx_type type = blk_mq_get_hctx_type(bio->bi_opf);
@@ -2952,12 +2976,6 @@ void blk_mq_submit_bio(struct bio *bio)
blk_status_t ret;
bio = blk_queue_bounce(bio, q);
- if (bio_may_exceed_limits(bio, &q->limits)) {
- bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
- if (!bio)
- return;
- }
-
bio_set_ioprio(bio);
if (plug) {
@@ -2966,16 +2984,26 @@ void blk_mq_submit_bio(struct bio *bio)
rq = NULL;
}
if (rq) {
+ if (unlikely(bio_may_exceed_limits(bio, &q->limits))) {
+ bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
+ if (!bio)
+ return;
+ }
if (!bio_integrity_prep(bio))
return;
if (blk_mq_attempt_bio_merge(q, bio, nr_segs))
return;
- if (blk_mq_can_use_cached_rq(rq, plug, bio))
+ if (blk_mq_use_cached_rq(rq, plug, bio))
goto done;
percpu_ref_get(&q->q_usage_counter);
} else {
if (unlikely(bio_queue_enter(bio)))
return;
+ if (unlikely(bio_may_exceed_limits(bio, &q->limits))) {
+ bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
+ if (!bio)
+ goto fail;
+ }
if (!bio_integrity_prep(bio))
goto fail;
}
diff --git a/block/ioprio.c b/block/ioprio.c
index b5a942519a797ceab4729231dd7c673e50ab0613..73301a261429ff9e04a166aefa5c72df55eaee57 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -139,32 +139,6 @@ SYSCALL_DEFINE3(ioprio_set, int, which, int, who, int, ioprio)
return ret;
}
-/*
- * If the task has set an I/O priority, use that. Otherwise, return
- * the default I/O priority.
- *
- * Expected to be called for current task or with task_lock() held to keep
- * io_context stable.
- */
-int __get_task_ioprio(struct task_struct *p)
-{
- struct io_context *ioc = p->io_context;
- int prio;
-
- if (p != current)
- lockdep_assert_held(&p->alloc_lock);
- if (ioc)
- prio = ioc->ioprio;
- else
- prio = IOPRIO_DEFAULT;
-
- if (IOPRIO_PRIO_CLASS(prio) == IOPRIO_CLASS_NONE)
- prio = IOPRIO_PRIO_VALUE(task_nice_ioclass(p),
- task_nice_ioprio(p));
- return prio;
-}
-EXPORT_SYMBOL_GPL(__get_task_ioprio);
-
static int get_task_ioprio(struct task_struct *p)
{
int ret;
diff --git a/block/partitions/core.c b/block/partitions/core.c
index e6ac73617f3e12db18d7bc9f4ade561494739cd6..cab0d76a828e37eb90e38d91b4e92a61e703717e 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -562,8 +562,8 @@ static bool blk_add_partition(struct gendisk *disk,
part = add_partition(disk, p, from, size, state->parts[p].flags,
&state->parts[p].info);
if (IS_ERR(part) && PTR_ERR(part) != -ENXIO) {
- printk(KERN_ERR " %s: p%d could not be added: %ld\n",
- disk->disk_name, p, -PTR_ERR(part));
+ printk(KERN_ERR " %s: p%d could not be added: %pe\n",
+ disk->disk_name, p, part);
return true;
}
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 146b32fa7b47ade338d0379e021aa224412ec657..f8145499da38c834225b8f2d2ee0448d19adc8e1 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -165,39 +165,37 @@ static loff_t get_loop_size(struct loop_device *lo, struct file *file)
return get_size(lo->lo_offset, lo->lo_sizelimit, file);
}
+/*
+ * We support direct I/O only if lo_offset is aligned with the logical I/O size
+ * of backing device, and the logical block size of loop is bigger than that of
+ * the backing device.
+ */
+static bool lo_bdev_can_use_dio(struct loop_device *lo,
+ struct block_device *backing_bdev)
+{
+ unsigned short sb_bsize = bdev_logical_block_size(backing_bdev);
+
+ if (queue_logical_block_size(lo->lo_queue) < sb_bsize)
+ return false;
+ if (lo->lo_offset & (sb_bsize - 1))
+ return false;
+ return true;
+}
+
static void __loop_update_dio(struct loop_device *lo, bool dio)
{
struct file *file = lo->lo_backing_file;
- struct address_space *mapping = file->f_mapping;
- struct inode *inode = mapping->host;
- unsigned short sb_bsize = 0;
- unsigned dio_align = 0;
+ struct inode *inode = file->f_mapping->host;
+ struct block_device *backing_bdev = NULL;
bool use_dio;
- if (inode->i_sb->s_bdev) {
- sb_bsize = bdev_logical_block_size(inode->i_sb->s_bdev);
- dio_align = sb_bsize - 1;
- }
+ if (S_ISBLK(inode->i_mode))
+ backing_bdev = I_BDEV(inode);
+ else if (inode->i_sb->s_bdev)
+ backing_bdev = inode->i_sb->s_bdev;
- /*
- * We support direct I/O only if lo_offset is aligned with the
- * logical I/O size of backing device, and the logical block
- * size of loop is bigger than the backing device's.
- *
- * TODO: the above condition may be loosed in the future, and
- * direct I/O may be switched runtime at that time because most
- * of requests in sane applications should be PAGE_SIZE aligned
- */
- if (dio) {
- if (queue_logical_block_size(lo->lo_queue) >= sb_bsize &&
- !(lo->lo_offset & dio_align) &&
- (file->f_mode & FMODE_CAN_ODIRECT))
- use_dio = true;
- else
- use_dio = false;
- } else {
- use_dio = false;
- }
+ use_dio = dio && (file->f_mode & FMODE_CAN_ODIRECT) &&
+ (!backing_bdev || lo_bdev_can_use_dio(lo, backing_bdev));
if (lo->use_dio == use_dio)
return;
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 4e72ec4e25ac5a0f41bca299e7efaecf6503c451..33a8f37bb6a1f504060f783c6d727e4c76026a2e 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -508,7 +508,7 @@ static int __sock_xmit(struct nbd_device *nbd, struct socket *sock, int send,
struct iov_iter *iter, int msg_flags, int *sent)
{
int result;
- struct msghdr msg;
+ struct msghdr msg = {} ;
unsigned int noreclaim_flag;
if (unlikely(!sock)) {
@@ -524,10 +524,6 @@ static int __sock_xmit(struct nbd_device *nbd, struct socket *sock, int send,
do {
sock->sk->sk_allocation = GFP_NOIO | __GFP_MEMALLOC;
sock->sk->sk_use_task_frag = false;
- msg.msg_name = NULL;
- msg.msg_namelen = 0;
- msg.msg_control = NULL;
- msg.msg_controllen = 0;
msg.msg_flags = msg_flags | MSG_NOSIGNAL;
if (send)
diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index 9f7695f00c2db8494a0230f2337a64d2fb4d3a14..36755f263e8ec03b1828bf44a05cc3b54bb6a03f 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -1840,7 +1840,7 @@ static void null_del_dev(struct nullb *nullb)
dev = nullb->dev;
- ida_simple_remove(&nullb_indexes, nullb->index);
+ ida_free(&nullb_indexes, nullb->index);
list_del_init(&nullb->list);
@@ -2174,7 +2174,7 @@ static int null_add_dev(struct nullb_device *dev)
blk_queue_flag_set(QUEUE_FLAG_NONROT, nullb->q);
mutex_lock(&lock);
- rv = ida_simple_get(&nullb_indexes, 0, 0, GFP_KERNEL);
+ rv = ida_alloc(&nullb_indexes, GFP_KERNEL);
if (rv < 0) {
mutex_unlock(&lock);
goto out_cleanup_zone;
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index a999b698b131f7763916c3bd0de5c87478fd0df4..12b5d53ec85645fb22395d41adef81d13cdb7292 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -3452,14 +3452,15 @@ static bool rbd_lock_add_request(struct rbd_img_request *img_req)
static void rbd_lock_del_request(struct rbd_img_request *img_req)
{
struct rbd_device *rbd_dev = img_req->rbd_dev;
- bool need_wakeup;
+ bool need_wakeup = false;
lockdep_assert_held(&rbd_dev->lock_rwsem);
spin_lock(&rbd_dev->lock_lists_lock);
- rbd_assert(!list_empty(&img_req->lock_item));
- list_del_init(&img_req->lock_item);
- need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING &&
- list_empty(&rbd_dev->running_list));
+ if (!list_empty(&img_req->lock_item)) {
+ list_del_init(&img_req->lock_item);
+ need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING &&
+ list_empty(&rbd_dev->running_list));
+ }
spin_unlock(&rbd_dev->lock_lists_lock);
if (need_wakeup)
complete(&rbd_dev->releasing_wait);
@@ -3842,14 +3843,19 @@ static void wake_lock_waiters(struct rbd_device *rbd_dev, int result)
return;
}
- list_for_each_entry(img_req, &rbd_dev->acquiring_list, lock_item) {
+ while (!list_empty(&rbd_dev->acquiring_list)) {
+ img_req = list_first_entry(&rbd_dev->acquiring_list,
+ struct rbd_img_request, lock_item);
mutex_lock(&img_req->state_mutex);
rbd_assert(img_req->state == RBD_IMG_EXCLUSIVE_LOCK);
+ if (!result)
+ list_move_tail(&img_req->lock_item,
+ &rbd_dev->running_list);
+ else
+ list_del_init(&img_req->lock_item);
rbd_img_schedule(img_req, result);
mutex_unlock(&img_req->state_mutex);
}
-
- list_splice_tail_init(&rbd_dev->acquiring_list, &rbd_dev->running_list);
}
static bool locker_equal(const struct ceph_locker *lhs,
@@ -5326,7 +5332,7 @@ static void rbd_dev_release(struct device *dev)
if (need_put) {
destroy_workqueue(rbd_dev->task_wq);
- ida_simple_remove(&rbd_dev_id_ida, rbd_dev->dev_id);
+ ida_free(&rbd_dev_id_ida, rbd_dev->dev_id);
}
rbd_dev_free(rbd_dev);
@@ -5402,9 +5408,9 @@ static struct rbd_device *rbd_dev_create(struct rbd_client *rbdc,
return NULL;
/* get an id and fill in device name */
- rbd_dev->dev_id = ida_simple_get(&rbd_dev_id_ida, 0,
- minor_to_rbd_dev_id(1 << MINORBITS),
- GFP_KERNEL);
+ rbd_dev->dev_id = ida_alloc_max(&rbd_dev_id_ida,
+ minor_to_rbd_dev_id(1 << MINORBITS) - 1,
+ GFP_KERNEL);
if (rbd_dev->dev_id < 0)
goto fail_rbd_dev;
@@ -5425,7 +5431,7 @@ static struct rbd_device *rbd_dev_create(struct rbd_client *rbdc,
return rbd_dev;
fail_dev_id:
- ida_simple_remove(&rbd_dev_id_ida, rbd_dev->dev_id);
+ ida_free(&rbd_dev_id_ida, rbd_dev->dev_id);
fail_rbd_dev:
rbd_dev_free(rbd_dev);
return NULL;
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 3b6b9abb8ce1f4d90f66b5ff94c1499b98208fd8..5bf98fd6a651a506ff294545d6241f608af34568 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -367,8 +367,6 @@ static void virtblk_done(struct virtqueue *vq)
blk_mq_complete_request(req);
req_done = true;
}
- if (unlikely(virtqueue_is_broken(vq)))
- break;
} while (!virtqueue_enable_cb(vq));
/* In case queue is stopped waiting for more buffers. */
diff --git a/drivers/clk/qcom/gcc-x1e80100.c b/drivers/clk/qcom/gcc-x1e80100.c
index 74db7fef237b4d3f11e758d6be2bf0744056aa86..d7182d6e978372ce467da5d0c7b4fd0613eb0d8b 100644
--- a/drivers/clk/qcom/gcc-x1e80100.c
+++ b/drivers/clk/qcom/gcc-x1e80100.c
@@ -4,8 +4,9 @@
*/
#include
+#include
#include
-#include
+#include
#include
#include
diff --git a/drivers/clocksource/timer-cadence-ttc.c b/drivers/clocksource/timer-cadence-ttc.c
index 32daaac9b13208fc92604c89b625ec914ef3e357..ca7a06489c405f1d013e0fedd997413c43a19d65 100644
--- a/drivers/clocksource/timer-cadence-ttc.c
+++ b/drivers/clocksource/timer-cadence-ttc.c
@@ -69,7 +69,7 @@
* @base_addr: Base address of timer
* @freq: Timer input clock frequency
* @clk: Associated clock source
- * @clk_rate_change_nb Notifier block for clock rate changes
+ * @clk_rate_change_nb: Notifier block for clock rate changes
*/
struct ttc_timer {
void __iomem *base_addr;
@@ -134,7 +134,7 @@ static void ttc_set_interval(struct ttc_timer *timer,
* @irq: IRQ number of the Timer
* @dev_id: void pointer to the ttc_timer instance
*
- * returns: Always IRQ_HANDLED - success
+ * Returns: Always IRQ_HANDLED - success
**/
static irqreturn_t ttc_clock_event_interrupt(int irq, void *dev_id)
{
@@ -151,8 +151,9 @@ static irqreturn_t ttc_clock_event_interrupt(int irq, void *dev_id)
/**
* __ttc_clocksource_read - Reads the timer counter register
+ * @cs: &clocksource to read from
*
- * returns: Current timer counter register value
+ * Returns: Current timer counter register value
**/
static u64 __ttc_clocksource_read(struct clocksource *cs)
{
@@ -173,7 +174,7 @@ static u64 notrace ttc_sched_clock_read(void)
* @cycles: Timer interval ticks
* @evt: Address of clock event instance
*
- * returns: Always 0 - success
+ * Returns: Always %0 - success
**/
static int ttc_set_next_event(unsigned long cycles,
struct clock_event_device *evt)
@@ -186,9 +187,12 @@ static int ttc_set_next_event(unsigned long cycles,
}
/**
- * ttc_set_{shutdown|oneshot|periodic} - Sets the state of timer
- *
+ * ttc_shutdown - Sets the state of timer
* @evt: Address of clock event instance
+ *
+ * Used for shutdown or oneshot.
+ *
+ * Returns: Always %0 - success
**/
static int ttc_shutdown(struct clock_event_device *evt)
{
@@ -202,6 +206,12 @@ static int ttc_shutdown(struct clock_event_device *evt)
return 0;
}
+/**
+ * ttc_set_periodic - Sets the state of timer
+ * @evt: Address of clock event instance
+ *
+ * Returns: Always %0 - success
+ */
static int ttc_set_periodic(struct clock_event_device *evt)
{
struct ttc_timer_clockevent *ttce = to_ttc_timer_clkevent(evt);
diff --git a/drivers/clocksource/timer-ep93xx.c b/drivers/clocksource/timer-ep93xx.c
index bc0ca6e12334903dd8ac17364e96469a42bbf5ab..6981ff3ac8a940be37b8dc247e59e32c2604f992 100644
--- a/drivers/clocksource/timer-ep93xx.c
+++ b/drivers/clocksource/timer-ep93xx.c
@@ -155,9 +155,8 @@ static int __init ep93xx_timer_of_init(struct device_node *np)
ep93xx_tcu = tcu;
irq = irq_of_parse_and_map(np, 0);
- if (irq == 0)
- irq = -EINVAL;
- if (irq < 0) {
+ if (!irq) {
+ ret = -EINVAL;
pr_err("EP93XX Timer Can't parse IRQ %d", irq);
goto out_free;
}
diff --git a/drivers/clocksource/timer-riscv.c b/drivers/clocksource/timer-riscv.c
index 57857c0dfba97e0bfdcd5190e8aee31e11028667..e66dcbd6656658dd32f913189fceebda87e8ccbf 100644
--- a/drivers/clocksource/timer-riscv.c
+++ b/drivers/clocksource/timer-riscv.c
@@ -61,12 +61,19 @@ static int riscv_clock_next_event(unsigned long delta,
return 0;
}
+static int riscv_clock_shutdown(struct clock_event_device *evt)
+{
+ riscv_clock_event_stop();
+ return 0;
+}
+
static unsigned int riscv_clock_event_irq;
static DEFINE_PER_CPU(struct clock_event_device, riscv_clock_event) = {
.name = "riscv_timer_clockevent",
.features = CLOCK_EVT_FEAT_ONESHOT,
.rating = 100,
.set_next_event = riscv_clock_next_event,
+ .set_state_shutdown = riscv_clock_shutdown,
};
/*
diff --git a/drivers/clocksource/timer-ti-dm.c b/drivers/clocksource/timer-ti-dm.c
index 5f60f6bd33866b4edc3ee2e248acb6d510f468e0..56acf26172621ffb96a14af47ccf92d31af15501 100644
--- a/drivers/clocksource/timer-ti-dm.c
+++ b/drivers/clocksource/timer-ti-dm.c
@@ -183,7 +183,7 @@ static inline u32 dmtimer_read(struct dmtimer *timer, u32 reg)
* dmtimer_write - write timer registers in posted and non-posted mode
* @timer: timer pointer over which write operation is to perform
* @reg: lowest byte holds the register offset
- * @value: data to write into the register
+ * @val: data to write into the register
*
* The posted mode bit is encoded in reg. Note that in posted mode, the write
* pending bit must be checked. Otherwise a write on a register which has a
@@ -949,7 +949,7 @@ static int omap_dm_timer_set_int_enable(struct omap_dm_timer *cookie,
/**
* omap_dm_timer_set_int_disable - disable timer interrupts
- * @timer: pointer to timer handle
+ * @cookie: pointer to timer cookie
* @mask: bit mask of interrupts to be disabled
*
* Disables the specified timer interrupts for a timer.
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 70ba506dabab5f7aa9eb95741bd40636d1535c86..e928f2ca0f1e9adc58594d6b4552d64dae29df34 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -378,6 +378,20 @@ config LPC18XX_DMAMUX
Enable support for DMA on NXP LPC18xx/43xx platforms
with PL080 and multiplexed DMA request lines.
+config LS2X_APB_DMA
+ tristate "Loongson LS2X APB DMA support"
+ depends on LOONGARCH || COMPILE_TEST
+ select DMA_ENGINE
+ select DMA_VIRTUAL_CHANNELS
+ help
+ Support for the Loongson LS2X APB DMA controller driver. The
+ DMA controller is having single DMA channel which can be
+ configured for different peripherals like audio, nand, sdio
+ etc which is in APB bus.
+
+ This DMA controller transfers data from memory to peripheral fifo.
+ It does not support memory to memory data transfer.
+
config MCF_EDMA
tristate "Freescale eDMA engine support, ColdFire mcf5441x SoCs"
depends on M5441x || COMPILE_TEST
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index 83553a97a010e157b285ad6c47557df31c8bc835..dfd40d14e4089d81ce489429f141a896bfc549e7 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -48,6 +48,7 @@ obj-$(CONFIG_INTEL_IOATDMA) += ioat/
obj-y += idxd/
obj-$(CONFIG_K3_DMA) += k3dma.o
obj-$(CONFIG_LPC18XX_DMAMUX) += lpc18xx-dmamux.o
+obj-$(CONFIG_LS2X_APB_DMA) += ls2x-apb-dma.o
obj-$(CONFIG_MILBEAUT_HDMAC) += milbeaut-hdmac.o
obj-$(CONFIG_MILBEAUT_XDMAC) += milbeaut-xdmac.o
obj-$(CONFIG_MMP_PDMA) += mmp_pdma.o
diff --git a/drivers/dma/apple-admac.c b/drivers/dma/apple-admac.c
index 5b63996640d9d3a210f789a89b6e7ffa054d96e2..9588773dd2eb670a2f6115fdaef39a0e88248015 100644
--- a/drivers/dma/apple-admac.c
+++ b/drivers/dma/apple-admac.c
@@ -57,6 +57,8 @@
#define REG_BUS_WIDTH(ch) (0x8040 + (ch) * 0x200)
+#define BUS_WIDTH_WORD_SIZE GENMASK(3, 0)
+#define BUS_WIDTH_FRAME_SIZE GENMASK(7, 4)
#define BUS_WIDTH_8BIT 0x00
#define BUS_WIDTH_16BIT 0x01
#define BUS_WIDTH_32BIT 0x02
@@ -740,7 +742,8 @@ static int admac_device_config(struct dma_chan *chan,
struct admac_data *ad = adchan->host;
bool is_tx = admac_chan_direction(adchan->no) == DMA_MEM_TO_DEV;
int wordsize = 0;
- u32 bus_width = 0;
+ u32 bus_width = readl_relaxed(ad->base + REG_BUS_WIDTH(adchan->no)) &
+ ~(BUS_WIDTH_WORD_SIZE | BUS_WIDTH_FRAME_SIZE);
switch (is_tx ? config->dst_addr_width : config->src_addr_width) {
case DMA_SLAVE_BUSWIDTH_1_BYTE:
diff --git a/drivers/dma/dma-axi-dmac.c b/drivers/dma/dma-axi-dmac.c
index 2457a420c13d72cde2509f6a446269b166b06cdc..4e339c04fc1ea1e973a385250a144945984ae1fd 100644
--- a/drivers/dma/dma-axi-dmac.c
+++ b/drivers/dma/dma-axi-dmac.c
@@ -81,9 +81,13 @@
#define AXI_DMAC_REG_CURRENT_DEST_ADDR 0x438
#define AXI_DMAC_REG_PARTIAL_XFER_LEN 0x44c
#define AXI_DMAC_REG_PARTIAL_XFER_ID 0x450
+#define AXI_DMAC_REG_CURRENT_SG_ID 0x454
+#define AXI_DMAC_REG_SG_ADDRESS 0x47c
+#define AXI_DMAC_REG_SG_ADDRESS_HIGH 0x4bc
#define AXI_DMAC_CTRL_ENABLE BIT(0)
#define AXI_DMAC_CTRL_PAUSE BIT(1)
+#define AXI_DMAC_CTRL_ENABLE_SG BIT(2)
#define AXI_DMAC_IRQ_SOT BIT(0)
#define AXI_DMAC_IRQ_EOT BIT(1)
@@ -97,20 +101,35 @@
/* The maximum ID allocated by the hardware is 31 */
#define AXI_DMAC_SG_UNUSED 32U
+/* Flags for axi_dmac_hw_desc.flags */
+#define AXI_DMAC_HW_FLAG_LAST BIT(0)
+#define AXI_DMAC_HW_FLAG_IRQ BIT(1)
+
+struct axi_dmac_hw_desc {
+ u32 flags;
+ u32 id;
+ u64 dest_addr;
+ u64 src_addr;
+ u64 next_sg_addr;
+ u32 y_len;
+ u32 x_len;
+ u32 src_stride;
+ u32 dst_stride;
+ u64 __pad[2];
+};
+
struct axi_dmac_sg {
- dma_addr_t src_addr;
- dma_addr_t dest_addr;
- unsigned int x_len;
- unsigned int y_len;
- unsigned int dest_stride;
- unsigned int src_stride;
- unsigned int id;
unsigned int partial_len;
bool schedule_when_free;
+
+ struct axi_dmac_hw_desc *hw;
+ dma_addr_t hw_phys;
};
struct axi_dmac_desc {
struct virt_dma_desc vdesc;
+ struct axi_dmac_chan *chan;
+
bool cyclic;
bool have_partial_xfer;
@@ -139,6 +158,7 @@ struct axi_dmac_chan {
bool hw_partial_xfer;
bool hw_cyclic;
bool hw_2d;
+ bool hw_sg;
};
struct axi_dmac {
@@ -213,9 +233,11 @@ static void axi_dmac_start_transfer(struct axi_dmac_chan *chan)
unsigned int flags = 0;
unsigned int val;
- val = axi_dmac_read(dmac, AXI_DMAC_REG_START_TRANSFER);
- if (val) /* Queue is full, wait for the next SOT IRQ */
- return;
+ if (!chan->hw_sg) {
+ val = axi_dmac_read(dmac, AXI_DMAC_REG_START_TRANSFER);
+ if (val) /* Queue is full, wait for the next SOT IRQ */
+ return;
+ }
desc = chan->next_desc;
@@ -229,14 +251,15 @@ static void axi_dmac_start_transfer(struct axi_dmac_chan *chan)
sg = &desc->sg[desc->num_submitted];
/* Already queued in cyclic mode. Wait for it to finish */
- if (sg->id != AXI_DMAC_SG_UNUSED) {
+ if (sg->hw->id != AXI_DMAC_SG_UNUSED) {
sg->schedule_when_free = true;
return;
}
- desc->num_submitted++;
- if (desc->num_submitted == desc->num_sgs ||
- desc->have_partial_xfer) {
+ if (chan->hw_sg) {
+ chan->next_desc = NULL;
+ } else if (++desc->num_submitted == desc->num_sgs ||
+ desc->have_partial_xfer) {
if (desc->cyclic)
desc->num_submitted = 0; /* Start again */
else
@@ -246,32 +269,42 @@ static void axi_dmac_start_transfer(struct axi_dmac_chan *chan)
chan->next_desc = desc;
}
- sg->id = axi_dmac_read(dmac, AXI_DMAC_REG_TRANSFER_ID);
+ sg->hw->id = axi_dmac_read(dmac, AXI_DMAC_REG_TRANSFER_ID);
- if (axi_dmac_dest_is_mem(chan)) {
- axi_dmac_write(dmac, AXI_DMAC_REG_DEST_ADDRESS, sg->dest_addr);
- axi_dmac_write(dmac, AXI_DMAC_REG_DEST_STRIDE, sg->dest_stride);
- }
+ if (!chan->hw_sg) {
+ if (axi_dmac_dest_is_mem(chan)) {
+ axi_dmac_write(dmac, AXI_DMAC_REG_DEST_ADDRESS, sg->hw->dest_addr);
+ axi_dmac_write(dmac, AXI_DMAC_REG_DEST_STRIDE, sg->hw->dst_stride);
+ }
- if (axi_dmac_src_is_mem(chan)) {
- axi_dmac_write(dmac, AXI_DMAC_REG_SRC_ADDRESS, sg->src_addr);
- axi_dmac_write(dmac, AXI_DMAC_REG_SRC_STRIDE, sg->src_stride);
+ if (axi_dmac_src_is_mem(chan)) {
+ axi_dmac_write(dmac, AXI_DMAC_REG_SRC_ADDRESS, sg->hw->src_addr);
+ axi_dmac_write(dmac, AXI_DMAC_REG_SRC_STRIDE, sg->hw->src_stride);
+ }
}
/*
* If the hardware supports cyclic transfers and there is no callback to
- * call and only a single segment, enable hw cyclic mode to avoid
- * unnecessary interrupts.
+ * call, enable hw cyclic mode to avoid unnecessary interrupts.
*/
- if (chan->hw_cyclic && desc->cyclic && !desc->vdesc.tx.callback &&
- desc->num_sgs == 1)
- flags |= AXI_DMAC_FLAG_CYCLIC;
+ if (chan->hw_cyclic && desc->cyclic && !desc->vdesc.tx.callback) {
+ if (chan->hw_sg)
+ desc->sg[desc->num_sgs - 1].hw->flags &= ~AXI_DMAC_HW_FLAG_IRQ;
+ else if (desc->num_sgs == 1)
+ flags |= AXI_DMAC_FLAG_CYCLIC;
+ }
if (chan->hw_partial_xfer)
flags |= AXI_DMAC_FLAG_PARTIAL_REPORT;
- axi_dmac_write(dmac, AXI_DMAC_REG_X_LENGTH, sg->x_len - 1);
- axi_dmac_write(dmac, AXI_DMAC_REG_Y_LENGTH, sg->y_len - 1);
+ if (chan->hw_sg) {
+ axi_dmac_write(dmac, AXI_DMAC_REG_SG_ADDRESS, (u32)sg->hw_phys);
+ axi_dmac_write(dmac, AXI_DMAC_REG_SG_ADDRESS_HIGH,
+ (u64)sg->hw_phys >> 32);
+ } else {
+ axi_dmac_write(dmac, AXI_DMAC_REG_X_LENGTH, sg->hw->x_len);
+ axi_dmac_write(dmac, AXI_DMAC_REG_Y_LENGTH, sg->hw->y_len);
+ }
axi_dmac_write(dmac, AXI_DMAC_REG_FLAGS, flags);
axi_dmac_write(dmac, AXI_DMAC_REG_START_TRANSFER, 1);
}
@@ -286,9 +319,9 @@ static inline unsigned int axi_dmac_total_sg_bytes(struct axi_dmac_chan *chan,
struct axi_dmac_sg *sg)
{
if (chan->hw_2d)
- return sg->x_len * sg->y_len;
+ return (sg->hw->x_len + 1) * (sg->hw->y_len + 1);
else
- return sg->x_len;
+ return (sg->hw->x_len + 1);
}
static void axi_dmac_dequeue_partial_xfers(struct axi_dmac_chan *chan)
@@ -307,9 +340,9 @@ static void axi_dmac_dequeue_partial_xfers(struct axi_dmac_chan *chan)
list_for_each_entry(desc, &chan->active_descs, vdesc.node) {
for (i = 0; i < desc->num_sgs; i++) {
sg = &desc->sg[i];
- if (sg->id == AXI_DMAC_SG_UNUSED)
+ if (sg->hw->id == AXI_DMAC_SG_UNUSED)
continue;
- if (sg->id == id) {
+ if (sg->hw->id == id) {
desc->have_partial_xfer = true;
sg->partial_len = len;
found_sg = true;
@@ -348,6 +381,9 @@ static void axi_dmac_compute_residue(struct axi_dmac_chan *chan,
rslt->result = DMA_TRANS_NOERROR;
rslt->residue = 0;
+ if (chan->hw_sg)
+ return;
+
/*
* We get here if the last completed segment is partial, which
* means we can compute the residue from that segment onwards
@@ -374,36 +410,47 @@ static bool axi_dmac_transfer_done(struct axi_dmac_chan *chan,
(completed_transfers & AXI_DMAC_FLAG_PARTIAL_XFER_DONE))
axi_dmac_dequeue_partial_xfers(chan);
- do {
- sg = &active->sg[active->num_completed];
- if (sg->id == AXI_DMAC_SG_UNUSED) /* Not yet submitted */
- break;
- if (!(BIT(sg->id) & completed_transfers))
- break;
- active->num_completed++;
- sg->id = AXI_DMAC_SG_UNUSED;
- if (sg->schedule_when_free) {
- sg->schedule_when_free = false;
- start_next = true;
+ if (chan->hw_sg) {
+ if (active->cyclic) {
+ vchan_cyclic_callback(&active->vdesc);
+ } else {
+ list_del(&active->vdesc.node);
+ vchan_cookie_complete(&active->vdesc);
+ active = axi_dmac_active_desc(chan);
+ start_next = !!active;
}
+ } else {
+ do {
+ sg = &active->sg[active->num_completed];
+ if (sg->hw->id == AXI_DMAC_SG_UNUSED) /* Not yet submitted */
+ break;
+ if (!(BIT(sg->hw->id) & completed_transfers))
+ break;
+ active->num_completed++;
+ sg->hw->id = AXI_DMAC_SG_UNUSED;
+ if (sg->schedule_when_free) {
+ sg->schedule_when_free = false;
+ start_next = true;
+ }
- if (sg->partial_len)
- axi_dmac_compute_residue(chan, active);
+ if (sg->partial_len)
+ axi_dmac_compute_residue(chan, active);
- if (active->cyclic)
- vchan_cyclic_callback(&active->vdesc);
+ if (active->cyclic)
+ vchan_cyclic_callback(&active->vdesc);
- if (active->num_completed == active->num_sgs ||
- sg->partial_len) {
- if (active->cyclic) {
- active->num_completed = 0; /* wrap around */
- } else {
- list_del(&active->vdesc.node);
- vchan_cookie_complete(&active->vdesc);
- active = axi_dmac_active_desc(chan);
+ if (active->num_completed == active->num_sgs ||
+ sg->partial_len) {
+ if (active->cyclic) {
+ active->num_completed = 0; /* wrap around */
+ } else {
+ list_del(&active->vdesc.node);
+ vchan_cookie_complete(&active->vdesc);
+ active = axi_dmac_active_desc(chan);
+ }
}
- }
- } while (active);
+ } while (active);
+ }
return start_next;
}
@@ -467,8 +514,12 @@ static void axi_dmac_issue_pending(struct dma_chan *c)
struct axi_dmac_chan *chan = to_axi_dmac_chan(c);
struct axi_dmac *dmac = chan_to_axi_dmac(chan);
unsigned long flags;
+ u32 ctrl = AXI_DMAC_CTRL_ENABLE;
- axi_dmac_write(dmac, AXI_DMAC_REG_CTRL, AXI_DMAC_CTRL_ENABLE);
+ if (chan->hw_sg)
+ ctrl |= AXI_DMAC_CTRL_ENABLE_SG;
+
+ axi_dmac_write(dmac, AXI_DMAC_REG_CTRL, ctrl);
spin_lock_irqsave(&chan->vchan.lock, flags);
if (vchan_issue_pending(&chan->vchan))
@@ -476,22 +527,58 @@ static void axi_dmac_issue_pending(struct dma_chan *c)
spin_unlock_irqrestore(&chan->vchan.lock, flags);
}
-static struct axi_dmac_desc *axi_dmac_alloc_desc(unsigned int num_sgs)
+static struct axi_dmac_desc *
+axi_dmac_alloc_desc(struct axi_dmac_chan *chan, unsigned int num_sgs)
{
+ struct axi_dmac *dmac = chan_to_axi_dmac(chan);
+ struct device *dev = dmac->dma_dev.dev;
+ struct axi_dmac_hw_desc *hws;
struct axi_dmac_desc *desc;
+ dma_addr_t hw_phys;
unsigned int i;
desc = kzalloc(struct_size(desc, sg, num_sgs), GFP_NOWAIT);
if (!desc)
return NULL;
desc->num_sgs = num_sgs;
+ desc->chan = chan;
+
+ hws = dma_alloc_coherent(dev, PAGE_ALIGN(num_sgs * sizeof(*hws)),
+ &hw_phys, GFP_ATOMIC);
+ if (!hws) {
+ kfree(desc);
+ return NULL;
+ }
- for (i = 0; i < num_sgs; i++)
- desc->sg[i].id = AXI_DMAC_SG_UNUSED;
+ for (i = 0; i < num_sgs; i++) {
+ desc->sg[i].hw = &hws[i];
+ desc->sg[i].hw_phys = hw_phys + i * sizeof(*hws);
+
+ hws[i].id = AXI_DMAC_SG_UNUSED;
+ hws[i].flags = 0;
+
+ /* Link hardware descriptors */
+ hws[i].next_sg_addr = hw_phys + (i + 1) * sizeof(*hws);
+ }
+
+ /* The last hardware descriptor will trigger an interrupt */
+ desc->sg[num_sgs - 1].hw->flags = AXI_DMAC_HW_FLAG_LAST | AXI_DMAC_HW_FLAG_IRQ;
return desc;
}
+static void axi_dmac_free_desc(struct axi_dmac_desc *desc)
+{
+ struct axi_dmac *dmac = chan_to_axi_dmac(desc->chan);
+ struct device *dev = dmac->dma_dev.dev;
+ struct axi_dmac_hw_desc *hw = desc->sg[0].hw;
+ dma_addr_t hw_phys = desc->sg[0].hw_phys;
+
+ dma_free_coherent(dev, PAGE_ALIGN(desc->num_sgs * sizeof(*hw)),
+ hw, hw_phys);
+ kfree(desc);
+}
+
static struct axi_dmac_sg *axi_dmac_fill_linear_sg(struct axi_dmac_chan *chan,
enum dma_transfer_direction direction, dma_addr_t addr,
unsigned int num_periods, unsigned int period_len,
@@ -508,26 +595,24 @@ static struct axi_dmac_sg *axi_dmac_fill_linear_sg(struct axi_dmac_chan *chan,
segment_size = ((segment_size - 1) | chan->length_align_mask) + 1;
for (i = 0; i < num_periods; i++) {
- len = period_len;
-
- while (len > segment_size) {
+ for (len = period_len; len > segment_size; sg++) {
if (direction == DMA_DEV_TO_MEM)
- sg->dest_addr = addr;
+ sg->hw->dest_addr = addr;
else
- sg->src_addr = addr;
- sg->x_len = segment_size;
- sg->y_len = 1;
- sg++;
+ sg->hw->src_addr = addr;
+ sg->hw->x_len = segment_size - 1;
+ sg->hw->y_len = 0;
+ sg->hw->flags = 0;
addr += segment_size;
len -= segment_size;
}
if (direction == DMA_DEV_TO_MEM)
- sg->dest_addr = addr;
+ sg->hw->dest_addr = addr;
else
- sg->src_addr = addr;
- sg->x_len = len;
- sg->y_len = 1;
+ sg->hw->src_addr = addr;
+ sg->hw->x_len = len - 1;
+ sg->hw->y_len = 0;
sg++;
addr += len;
}
@@ -554,7 +639,7 @@ static struct dma_async_tx_descriptor *axi_dmac_prep_slave_sg(
for_each_sg(sgl, sg, sg_len, i)
num_sgs += DIV_ROUND_UP(sg_dma_len(sg), chan->max_length);
- desc = axi_dmac_alloc_desc(num_sgs);
+ desc = axi_dmac_alloc_desc(chan, num_sgs);
if (!desc)
return NULL;
@@ -563,7 +648,7 @@ static struct dma_async_tx_descriptor *axi_dmac_prep_slave_sg(
for_each_sg(sgl, sg, sg_len, i) {
if (!axi_dmac_check_addr(chan, sg_dma_address(sg)) ||
!axi_dmac_check_len(chan, sg_dma_len(sg))) {
- kfree(desc);
+ axi_dmac_free_desc(desc);
return NULL;
}
@@ -583,7 +668,7 @@ static struct dma_async_tx_descriptor *axi_dmac_prep_dma_cyclic(
{
struct axi_dmac_chan *chan = to_axi_dmac_chan(c);
struct axi_dmac_desc *desc;
- unsigned int num_periods, num_segments;
+ unsigned int num_periods, num_segments, num_sgs;
if (direction != chan->direction)
return NULL;
@@ -597,11 +682,16 @@ static struct dma_async_tx_descriptor *axi_dmac_prep_dma_cyclic(
num_periods = buf_len / period_len;
num_segments = DIV_ROUND_UP(period_len, chan->max_length);
+ num_sgs = num_periods * num_segments;
- desc = axi_dmac_alloc_desc(num_periods * num_segments);
+ desc = axi_dmac_alloc_desc(chan, num_sgs);
if (!desc)
return NULL;
+ /* Chain the last descriptor to the first, and remove its "last" flag */
+ desc->sg[num_sgs - 1].hw->next_sg_addr = desc->sg[0].hw_phys;
+ desc->sg[num_sgs - 1].hw->flags &= ~AXI_DMAC_HW_FLAG_LAST;
+
axi_dmac_fill_linear_sg(chan, direction, buf_addr, num_periods,
period_len, desc->sg);
@@ -653,26 +743,26 @@ static struct dma_async_tx_descriptor *axi_dmac_prep_interleaved(
return NULL;
}
- desc = axi_dmac_alloc_desc(1);
+ desc = axi_dmac_alloc_desc(chan, 1);
if (!desc)
return NULL;
if (axi_dmac_src_is_mem(chan)) {
- desc->sg[0].src_addr = xt->src_start;
- desc->sg[0].src_stride = xt->sgl[0].size + src_icg;
+ desc->sg[0].hw->src_addr = xt->src_start;
+ desc->sg[0].hw->src_stride = xt->sgl[0].size + src_icg;
}
if (axi_dmac_dest_is_mem(chan)) {
- desc->sg[0].dest_addr = xt->dst_start;
- desc->sg[0].dest_stride = xt->sgl[0].size + dst_icg;
+ desc->sg[0].hw->dest_addr = xt->dst_start;
+ desc->sg[0].hw->dst_stride = xt->sgl[0].size + dst_icg;
}
if (chan->hw_2d) {
- desc->sg[0].x_len = xt->sgl[0].size;
- desc->sg[0].y_len = xt->numf;
+ desc->sg[0].hw->x_len = xt->sgl[0].size - 1;
+ desc->sg[0].hw->y_len = xt->numf - 1;
} else {
- desc->sg[0].x_len = xt->sgl[0].size * xt->numf;
- desc->sg[0].y_len = 1;
+ desc->sg[0].hw->x_len = xt->sgl[0].size * xt->numf - 1;
+ desc->sg[0].hw->y_len = 0;
}
if (flags & DMA_CYCLIC)
@@ -688,7 +778,7 @@ static void axi_dmac_free_chan_resources(struct dma_chan *c)
static void axi_dmac_desc_free(struct virt_dma_desc *vdesc)
{
- kfree(container_of(vdesc, struct axi_dmac_desc, vdesc));
+ axi_dmac_free_desc(to_axi_dmac_desc(vdesc));
}
static bool axi_dmac_regmap_rdwr(struct device *dev, unsigned int reg)
@@ -714,6 +804,9 @@ static bool axi_dmac_regmap_rdwr(struct device *dev, unsigned int reg)
case AXI_DMAC_REG_CURRENT_DEST_ADDR:
case AXI_DMAC_REG_PARTIAL_XFER_LEN:
case AXI_DMAC_REG_PARTIAL_XFER_ID:
+ case AXI_DMAC_REG_CURRENT_SG_ID:
+ case AXI_DMAC_REG_SG_ADDRESS:
+ case AXI_DMAC_REG_SG_ADDRESS_HIGH:
return true;
default:
return false;
@@ -866,6 +959,10 @@ static int axi_dmac_detect_caps(struct axi_dmac *dmac, unsigned int version)
if (axi_dmac_read(dmac, AXI_DMAC_REG_FLAGS) == AXI_DMAC_FLAG_CYCLIC)
chan->hw_cyclic = true;
+ axi_dmac_write(dmac, AXI_DMAC_REG_SG_ADDRESS, 0xffffffff);
+ if (axi_dmac_read(dmac, AXI_DMAC_REG_SG_ADDRESS))
+ chan->hw_sg = true;
+
axi_dmac_write(dmac, AXI_DMAC_REG_Y_LENGTH, 1);
if (axi_dmac_read(dmac, AXI_DMAC_REG_Y_LENGTH) == 1)
chan->hw_2d = true;
@@ -911,6 +1008,7 @@ static int axi_dmac_probe(struct platform_device *pdev)
struct axi_dmac *dmac;
struct regmap *regmap;
unsigned int version;
+ u32 irq_mask = 0;
int ret;
dmac = devm_kzalloc(&pdev->dev, sizeof(*dmac), GFP_KERNEL);
@@ -966,6 +1064,7 @@ static int axi_dmac_probe(struct platform_device *pdev)
dma_dev->dst_addr_widths = BIT(dmac->chan.dest_width);
dma_dev->directions = BIT(dmac->chan.direction);
dma_dev->residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR;
+ dma_dev->max_sg_burst = 31; /* 31 SGs maximum in one burst */
INIT_LIST_HEAD(&dma_dev->channels);
dmac->chan.vchan.desc_free = axi_dmac_desc_free;
@@ -977,7 +1076,10 @@ static int axi_dmac_probe(struct platform_device *pdev)
dma_dev->copy_align = (dmac->chan.address_align_mask + 1);
- axi_dmac_write(dmac, AXI_DMAC_REG_IRQ_MASK, 0x00);
+ if (dmac->chan.hw_sg)
+ irq_mask |= AXI_DMAC_IRQ_SOT;
+
+ axi_dmac_write(dmac, AXI_DMAC_REG_IRQ_MASK, irq_mask);
if (of_dma_is_coherent(pdev->dev.of_node)) {
ret = axi_dmac_read(dmac, AXI_DMAC_REG_COHERENCY_DESC);
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index b7388ae62d7f1fde1b24118a38c1d454974b2bd9..491b222402216a4a7bee1627b3e559321af33f36 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -1103,6 +1103,9 @@ EXPORT_SYMBOL_GPL(dma_async_device_channel_register);
static void __dma_async_device_channel_unregister(struct dma_device *device,
struct dma_chan *chan)
{
+ if (chan->local == NULL)
+ return;
+
WARN_ONCE(!device->device_release && chan->client_count,
"%s called while %d clients hold a reference\n",
__func__, chan->client_count);
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index ffe621695e472b6b6d96e2a06a85ff514ee65651..a4f6088378492d0338fe65edc86ec51c4a9c0a10 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -21,6 +21,10 @@
#include
#include
+static bool nobounce;
+module_param(nobounce, bool, 0644);
+MODULE_PARM_DESC(nobounce, "Prevent using swiotlb buffer (default: use swiotlb buffer)");
+
static unsigned int test_buf_size = 16384;
module_param(test_buf_size, uint, 0644);
MODULE_PARM_DESC(test_buf_size, "Size of the memcpy test buffer");
@@ -90,6 +94,7 @@ MODULE_PARM_DESC(polled, "Use polling for completion instead of interrupts");
/**
* struct dmatest_params - test parameters.
+ * @nobounce: prevent using swiotlb buffer
* @buf_size: size of the memcpy test buffer
* @channel: bus ID of the channel to test
* @device: bus ID of the DMA Engine to test
@@ -106,6 +111,7 @@ MODULE_PARM_DESC(polled, "Use polling for completion instead of interrupts");
* @polled: use polling for completion instead of interrupts
*/
struct dmatest_params {
+ bool nobounce;
unsigned int buf_size;
char channel[20];
char device[32];
@@ -215,6 +221,7 @@ struct dmatest_done {
struct dmatest_data {
u8 **raw;
u8 **aligned;
+ gfp_t gfp_flags;
unsigned int cnt;
unsigned int off;
};
@@ -533,7 +540,7 @@ static int dmatest_alloc_test_data(struct dmatest_data *d,
goto err;
for (i = 0; i < d->cnt; i++) {
- d->raw[i] = kmalloc(buf_size + align, GFP_KERNEL);
+ d->raw[i] = kmalloc(buf_size + align, d->gfp_flags);
if (!d->raw[i])
goto err;
@@ -655,6 +662,13 @@ static int dmatest_func(void *data)
goto err_free_coefs;
}
+ src->gfp_flags = GFP_KERNEL;
+ dst->gfp_flags = GFP_KERNEL;
+ if (params->nobounce) {
+ src->gfp_flags = GFP_DMA;
+ dst->gfp_flags = GFP_DMA;
+ }
+
if (dmatest_alloc_test_data(src, buf_size, align) < 0)
goto err_free_coefs;
@@ -1093,6 +1107,7 @@ static void add_threaded_test(struct dmatest_info *info)
struct dmatest_params *params = &info->params;
/* Copy test parameters */
+ params->nobounce = nobounce;
params->buf_size = test_buf_size;
strscpy(params->channel, strim(test_channel), sizeof(params->channel));
strscpy(params->device, strim(test_device), sizeof(params->device));
diff --git a/drivers/dma/dw-edma/dw-edma-v0-debugfs.c b/drivers/dma/dw-edma/dw-edma-v0-debugfs.c
index 0745d9e7d259b1294e519744ced86dcdecbd7d7d..406f169b09a75a52197c6615c675b1eb61022169 100644
--- a/drivers/dma/dw-edma/dw-edma-v0-debugfs.c
+++ b/drivers/dma/dw-edma/dw-edma-v0-debugfs.c
@@ -176,7 +176,7 @@ dw_edma_debugfs_regs_wr(struct dw_edma *dw, struct dentry *dent)
};
struct dentry *regs_dent, *ch_dent;
int nr_entries, i;
- char name[16];
+ char name[32];
regs_dent = debugfs_create_dir(WRITE_STR, dent);
@@ -239,7 +239,7 @@ static noinline_for_stack void dw_edma_debugfs_regs_rd(struct dw_edma *dw,
};
struct dentry *regs_dent, *ch_dent;
int nr_entries, i;
- char name[16];
+ char name[32];
regs_dent = debugfs_create_dir(READ_STR, dent);
diff --git a/drivers/dma/dw-edma/dw-hdma-v0-debugfs.c b/drivers/dma/dw-edma/dw-hdma-v0-debugfs.c
index 520c81978b085fb244311d041faf1786ec7b5750..dcdc57fe976c134f7825425627e782f3ad5b96de 100644
--- a/drivers/dma/dw-edma/dw-hdma-v0-debugfs.c
+++ b/drivers/dma/dw-edma/dw-hdma-v0-debugfs.c
@@ -116,7 +116,7 @@ static void dw_hdma_debugfs_regs_ch(struct dw_edma *dw, enum dw_edma_dir dir,
static void dw_hdma_debugfs_regs_wr(struct dw_edma *dw, struct dentry *dent)
{
struct dentry *regs_dent, *ch_dent;
- char name[16];
+ char name[32];
int i;
regs_dent = debugfs_create_dir(WRITE_STR, dent);
@@ -133,7 +133,7 @@ static void dw_hdma_debugfs_regs_wr(struct dw_edma *dw, struct dentry *dent)
static void dw_hdma_debugfs_regs_rd(struct dw_edma *dw, struct dentry *dent)
{
struct dentry *regs_dent, *ch_dent;
- char name[16];
+ char name[32];
int i;
regs_dent = debugfs_create_dir(READ_STR, dent);
diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c
index 238a69bd0d6f5d3ba6d8329543c49d3a750dba21..45cc419b1b4acbe87c12c3daaccafce73f8de1ba 100644
--- a/drivers/dma/fsl-edma-main.c
+++ b/drivers/dma/fsl-edma-main.c
@@ -9,6 +9,7 @@
* Vybrid and Layerscape SoCs.
*/
+#include
#include
#include
#include
@@ -21,10 +22,6 @@
#include "fsl-edma-common.h"
-#define ARGS_RX BIT(0)
-#define ARGS_REMOTE BIT(1)
-#define ARGS_MULTI_FIFO BIT(2)
-
static void fsl_edma_synchronize(struct dma_chan *chan)
{
struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
@@ -153,9 +150,15 @@ static struct dma_chan *fsl_edma3_xlate(struct of_phandle_args *dma_spec,
i = fsl_chan - fsl_edma->chans;
fsl_chan->priority = dma_spec->args[1];
- fsl_chan->is_rxchan = dma_spec->args[2] & ARGS_RX;
- fsl_chan->is_remote = dma_spec->args[2] & ARGS_REMOTE;
- fsl_chan->is_multi_fifo = dma_spec->args[2] & ARGS_MULTI_FIFO;
+ fsl_chan->is_rxchan = dma_spec->args[2] & FSL_EDMA_RX;
+ fsl_chan->is_remote = dma_spec->args[2] & FSL_EDMA_REMOTE;
+ fsl_chan->is_multi_fifo = dma_spec->args[2] & FSL_EDMA_MULTI_FIFO;
+
+ if ((dma_spec->args[2] & FSL_EDMA_EVEN_CH) && (i & 0x1))
+ continue;
+
+ if ((dma_spec->args[2] & FSL_EDMA_ODD_CH) && !(i & 0x1))
+ continue;
if (!b_chmux && i == dma_spec->args[0]) {
chan = dma_get_slave_channel(chan);
diff --git a/drivers/dma/fsl-qdma.c b/drivers/dma/fsl-qdma.c
index 47cb284680494cc842141c3c680a617a424d5669..a1d0aa63142a981bb59fcde5663e53ee7355947c 100644
--- a/drivers/dma/fsl-qdma.c
+++ b/drivers/dma/fsl-qdma.c
@@ -805,7 +805,7 @@ fsl_qdma_irq_init(struct platform_device *pdev,
int i;
int cpu;
int ret;
- char irq_name[20];
+ char irq_name[32];
fsl_qdma->error_irq =
platform_get_irq_byname(pdev, "qdma-error");
diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c
index 1d918d45d9f6d67453f8f662e08b6f430161f126..77f8885cf4075acfd3ff535b7e09519a8df41c70 100644
--- a/drivers/dma/idxd/cdev.c
+++ b/drivers/dma/idxd/cdev.c
@@ -165,7 +165,7 @@ static void idxd_cdev_dev_release(struct device *dev)
struct idxd_wq *wq = idxd_cdev->wq;
cdev_ctx = &ictx[wq->idxd->data->type];
- ida_simple_remove(&cdev_ctx->minor_ida, idxd_cdev->minor);
+ ida_free(&cdev_ctx->minor_ida, idxd_cdev->minor);
kfree(idxd_cdev);
}
@@ -463,7 +463,7 @@ int idxd_wq_add_cdev(struct idxd_wq *wq)
cdev = &idxd_cdev->cdev;
dev = cdev_dev(idxd_cdev);
cdev_ctx = &ictx[wq->idxd->data->type];
- minor = ida_simple_get(&cdev_ctx->minor_ida, 0, MINORMASK, GFP_KERNEL);
+ minor = ida_alloc_max(&cdev_ctx->minor_ida, MINORMASK, GFP_KERNEL);
if (minor < 0) {
kfree(idxd_cdev);
return minor;
diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index f43d81128b96b3672fab2ce2de0f54fea1660f2e..ecfdf4a8f1f838ea49f1dbe3f60b15574aa8be11 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -807,6 +807,9 @@ static int idxd_device_evl_setup(struct idxd_device *idxd)
static void idxd_device_evl_free(struct idxd_device *idxd)
{
+ void *evl_log;
+ unsigned int evl_log_size;
+ dma_addr_t evl_dma;
union gencfg_reg gencfg;
union genctrl_reg genctrl;
struct device *dev = &idxd->pdev->dev;
@@ -827,11 +830,15 @@ static void idxd_device_evl_free(struct idxd_device *idxd)
iowrite64(0, idxd->reg_base + IDXD_EVLCFG_OFFSET);
iowrite64(0, idxd->reg_base + IDXD_EVLCFG_OFFSET + 8);
- dma_free_coherent(dev, evl->log_size, evl->log, evl->dma);
bitmap_free(evl->bmap);
+ evl_log = evl->log;
+ evl_log_size = evl->log_size;
+ evl_dma = evl->dma;
evl->log = NULL;
evl->size = IDXD_EVL_SIZE_MIN;
spin_unlock(&evl->lock);
+
+ dma_free_coherent(dev, evl_log_size, evl_log, evl_dma);
}
static void idxd_group_config_write(struct idxd_group *group)
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index f81ecf5863e86ec00190f986e64f129cc8a3dac7..9b42f5e96b1e0a2b7d001fa406a7d98cd040a577 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -421,9 +421,7 @@ struct sdma_desc {
* @shp_addr: value for gReg[6]
* @per_addr: value for gReg[2]
* @status: status of dma channel
- * @context_loaded: ensure context is only loaded once
* @data: specific sdma interface structure
- * @bd_pool: dma_pool for bd
* @terminate_worker: used to call back into terminate work function
* @terminated: terminated list
* @is_ram_script: flag for script in ram
@@ -486,8 +484,6 @@ struct sdma_channel {
* @num_script_addrs: Number of script addresses in this image
* @ram_code_start: offset of SDMA ram image in this firmware image
* @ram_code_size: size of SDMA ram image
- * @script_addrs: Stores the start address of the SDMA scripts
- * (in SDMA memory space)
*/
struct sdma_firmware_header {
u32 magic;
diff --git a/drivers/dma/ls2x-apb-dma.c b/drivers/dma/ls2x-apb-dma.c
new file mode 100644
index 0000000000000000000000000000000000000000..a49913f3ed3f7c0b36de34533f75e7806eb2a8c0
--- /dev/null
+++ b/drivers/dma/ls2x-apb-dma.c
@@ -0,0 +1,705 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Driver for the Loongson LS2X APB DMA Controller
+ *
+ * Copyright (C) 2017-2023 Loongson Corporation
+ */
+
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+
+#include "dmaengine.h"
+#include "virt-dma.h"
+
+/* Global Configuration Register */
+#define LDMA_ORDER_ERG 0x0
+
+/* Bitfield definitions */
+
+/* Bitfields in Global Configuration Register */
+#define LDMA_64BIT_EN BIT(0) /* 1: 64 bit support */
+#define LDMA_UNCOHERENT_EN BIT(1) /* 0: cache, 1: uncache */
+#define LDMA_ASK_VALID BIT(2)
+#define LDMA_START BIT(3) /* DMA start operation */
+#define LDMA_STOP BIT(4) /* DMA stop operation */
+#define LDMA_CONFIG_MASK GENMASK(4, 0) /* DMA controller config bits mask */
+
+/* Bitfields in ndesc_addr field of HW decriptor */
+#define LDMA_DESC_EN BIT(0) /*1: The next descriptor is valid */
+#define LDMA_DESC_ADDR_LOW GENMASK(31, 1)
+
+/* Bitfields in cmd field of HW decriptor */
+#define LDMA_INT BIT(1) /* Enable DMA interrupts */
+#define LDMA_DATA_DIRECTION BIT(12) /* 1: write to device, 0: read from device */
+
+#define LDMA_SLAVE_BUSWIDTHS (BIT(DMA_SLAVE_BUSWIDTH_4_BYTES) | \
+ BIT(DMA_SLAVE_BUSWIDTH_8_BYTES))
+
+#define LDMA_MAX_TRANS_LEN U32_MAX
+
+/*-- descriptors -----------------------------------------------------*/
+
+/*
+ * struct ls2x_dma_hw_desc - DMA HW descriptor
+ * @ndesc_addr: the next descriptor low address.
+ * @mem_addr: memory low address.
+ * @apb_addr: device buffer address.
+ * @len: length of a piece of carried content, in words.
+ * @step_len: length between two moved memory data blocks.
+ * @step_times: number of blocks to be carried in a single DMA operation.
+ * @cmd: descriptor command or state.
+ * @stats: DMA status.
+ * @high_ndesc_addr: the next descriptor high address.
+ * @high_mem_addr: memory high address.
+ * @reserved: reserved
+ */
+struct ls2x_dma_hw_desc {
+ u32 ndesc_addr;
+ u32 mem_addr;
+ u32 apb_addr;
+ u32 len;
+ u32 step_len;
+ u32 step_times;
+ u32 cmd;
+ u32 stats;
+ u32 high_ndesc_addr;
+ u32 high_mem_addr;
+ u32 reserved[2];
+} __packed;
+
+/*
+ * struct ls2x_dma_sg - ls2x dma scatter gather entry
+ * @hw: the pointer to DMA HW descriptor.
+ * @llp: physical address of the DMA HW descriptor.
+ * @phys: destination or source address(mem).
+ * @len: number of Bytes to read.
+ */
+struct ls2x_dma_sg {
+ struct ls2x_dma_hw_desc *hw;
+ dma_addr_t llp;
+ dma_addr_t phys;
+ u32 len;
+};
+
+/*
+ * struct ls2x_dma_desc - software descriptor
+ * @vdesc: pointer to the virtual dma descriptor.
+ * @cyclic: flag to dma cyclic
+ * @burst_size: burst size of transaction, in words.
+ * @desc_num: number of sg entries.
+ * @direction: transfer direction, to or from device.
+ * @status: dma controller status.
+ * @sg: array of sgs.
+ */
+struct ls2x_dma_desc {
+ struct virt_dma_desc vdesc;
+ bool cyclic;
+ size_t burst_size;
+ u32 desc_num;
+ enum dma_transfer_direction direction;
+ enum dma_status status;
+ struct ls2x_dma_sg sg[] __counted_by(desc_num);
+};
+
+/*-- Channels --------------------------------------------------------*/
+
+/*
+ * struct ls2x_dma_chan - internal representation of an LS2X APB DMA channel
+ * @vchan: virtual dma channel entry.
+ * @desc: pointer to the ls2x sw dma descriptor.
+ * @pool: hw desc table
+ * @irq: irq line
+ * @sconfig: configuration for slave transfers, passed via .device_config
+ */
+struct ls2x_dma_chan {
+ struct virt_dma_chan vchan;
+ struct ls2x_dma_desc *desc;
+ void *pool;
+ int irq;
+ struct dma_slave_config sconfig;
+};
+
+/*-- Controller ------------------------------------------------------*/
+
+/*
+ * struct ls2x_dma_priv - LS2X APB DMAC specific information
+ * @ddev: dmaengine dma_device object members
+ * @dma_clk: DMAC clock source
+ * @regs: memory mapped register base
+ * @lchan: channel to store ls2x_dma_chan structures
+ */
+struct ls2x_dma_priv {
+ struct dma_device ddev;
+ struct clk *dma_clk;
+ void __iomem *regs;
+ struct ls2x_dma_chan lchan;
+};
+
+/*-- Helper functions ------------------------------------------------*/
+
+static inline struct ls2x_dma_desc *to_ldma_desc(struct virt_dma_desc *vdesc)
+{
+ return container_of(vdesc, struct ls2x_dma_desc, vdesc);
+}
+
+static inline struct ls2x_dma_chan *to_ldma_chan(struct dma_chan *chan)
+{
+ return container_of(chan, struct ls2x_dma_chan, vchan.chan);
+}
+
+static inline struct ls2x_dma_priv *to_ldma_priv(struct dma_device *ddev)
+{
+ return container_of(ddev, struct ls2x_dma_priv, ddev);
+}
+
+static struct device *chan2dev(struct dma_chan *chan)
+{
+ return &chan->dev->device;
+}
+
+static void ls2x_dma_desc_free(struct virt_dma_desc *vdesc)
+{
+ struct ls2x_dma_chan *lchan = to_ldma_chan(vdesc->tx.chan);
+ struct ls2x_dma_desc *desc = to_ldma_desc(vdesc);
+ int i;
+
+ for (i = 0; i < desc->desc_num; i++) {
+ if (desc->sg[i].hw)
+ dma_pool_free(lchan->pool, desc->sg[i].hw,
+ desc->sg[i].llp);
+ }
+
+ kfree(desc);
+}
+
+static void ls2x_dma_write_cmd(struct ls2x_dma_chan *lchan, bool cmd)
+{
+ struct ls2x_dma_priv *priv = to_ldma_priv(lchan->vchan.chan.device);
+ u64 val;
+
+ val = lo_hi_readq(priv->regs + LDMA_ORDER_ERG) & ~LDMA_CONFIG_MASK;
+ val |= LDMA_64BIT_EN | cmd;
+ lo_hi_writeq(val, priv->regs + LDMA_ORDER_ERG);
+}
+
+static void ls2x_dma_start_transfer(struct ls2x_dma_chan *lchan)
+{
+ struct ls2x_dma_priv *priv = to_ldma_priv(lchan->vchan.chan.device);
+ struct ls2x_dma_sg *ldma_sg;
+ struct virt_dma_desc *vdesc;
+ u64 val;
+
+ /* Get the next descriptor */
+ vdesc = vchan_next_desc(&lchan->vchan);
+ if (!vdesc) {
+ lchan->desc = NULL;
+ return;
+ }
+
+ list_del(&vdesc->node);
+ lchan->desc = to_ldma_desc(vdesc);
+ ldma_sg = &lchan->desc->sg[0];
+
+ /* Start DMA */
+ lo_hi_writeq(0, priv->regs + LDMA_ORDER_ERG);
+ val = (ldma_sg->llp & ~LDMA_CONFIG_MASK) | LDMA_64BIT_EN | LDMA_START;
+ lo_hi_writeq(val, priv->regs + LDMA_ORDER_ERG);
+}
+
+static size_t ls2x_dmac_detect_burst(struct ls2x_dma_chan *lchan)
+{
+ u32 maxburst, buswidth;
+
+ /* Reject definitely invalid configurations */
+ if ((lchan->sconfig.src_addr_width & LDMA_SLAVE_BUSWIDTHS) &&
+ (lchan->sconfig.dst_addr_width & LDMA_SLAVE_BUSWIDTHS))
+ return 0;
+
+ if (lchan->sconfig.direction == DMA_MEM_TO_DEV) {
+ maxburst = lchan->sconfig.dst_maxburst;
+ buswidth = lchan->sconfig.dst_addr_width;
+ } else {
+ maxburst = lchan->sconfig.src_maxburst;
+ buswidth = lchan->sconfig.src_addr_width;
+ }
+
+ /* If maxburst is zero, fallback to LDMA_MAX_TRANS_LEN */
+ return maxburst ? (maxburst * buswidth) >> 2 : LDMA_MAX_TRANS_LEN;
+}
+
+static void ls2x_dma_fill_desc(struct ls2x_dma_chan *lchan, u32 sg_index,
+ struct ls2x_dma_desc *desc)
+{
+ struct ls2x_dma_sg *ldma_sg = &desc->sg[sg_index];
+ u32 num_segments, segment_size;
+
+ if (desc->direction == DMA_MEM_TO_DEV) {
+ ldma_sg->hw->cmd = LDMA_INT | LDMA_DATA_DIRECTION;
+ ldma_sg->hw->apb_addr = lchan->sconfig.dst_addr;
+ } else {
+ ldma_sg->hw->cmd = LDMA_INT;
+ ldma_sg->hw->apb_addr = lchan->sconfig.src_addr;
+ }
+
+ ldma_sg->hw->mem_addr = lower_32_bits(ldma_sg->phys);
+ ldma_sg->hw->high_mem_addr = upper_32_bits(ldma_sg->phys);
+
+ /* Split into multiple equally sized segments if necessary */
+ num_segments = DIV_ROUND_UP((ldma_sg->len + 3) >> 2, desc->burst_size);
+ segment_size = DIV_ROUND_UP((ldma_sg->len + 3) >> 2, num_segments);
+
+ /* Word count register takes input in words */
+ ldma_sg->hw->len = segment_size;
+ ldma_sg->hw->step_times = num_segments;
+ ldma_sg->hw->step_len = 0;
+
+ /* lets make a link list */
+ if (sg_index) {
+ desc->sg[sg_index - 1].hw->ndesc_addr = ldma_sg->llp | LDMA_DESC_EN;
+ desc->sg[sg_index - 1].hw->high_ndesc_addr = upper_32_bits(ldma_sg->llp);
+ }
+}
+
+/*-- DMA Engine API --------------------------------------------------*/
+
+/*
+ * ls2x_dma_alloc_chan_resources - allocate resources for DMA channel
+ * @chan: allocate descriptor resources for this channel
+ *
+ * return - the number of allocated descriptors
+ */
+static int ls2x_dma_alloc_chan_resources(struct dma_chan *chan)
+{
+ struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+
+ /* Create a pool of consistent memory blocks for hardware descriptors */
+ lchan->pool = dma_pool_create(dev_name(chan2dev(chan)),
+ chan->device->dev, PAGE_SIZE,
+ __alignof__(struct ls2x_dma_hw_desc), 0);
+ if (!lchan->pool) {
+ dev_err(chan2dev(chan), "No memory for descriptors\n");
+ return -ENOMEM;
+ }
+
+ return 1;
+}
+
+/*
+ * ls2x_dma_free_chan_resources - free all channel resources
+ * @chan: DMA channel
+ */
+static void ls2x_dma_free_chan_resources(struct dma_chan *chan)
+{
+ struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+
+ vchan_free_chan_resources(to_virt_chan(chan));
+ dma_pool_destroy(lchan->pool);
+ lchan->pool = NULL;
+}
+
+/*
+ * ls2x_dma_prep_slave_sg - prepare descriptors for a DMA_SLAVE transaction
+ * @chan: DMA channel
+ * @sgl: scatterlist to transfer to/from
+ * @sg_len: number of entries in @scatterlist
+ * @direction: DMA direction
+ * @flags: tx descriptor status flags
+ * @context: transaction context (ignored)
+ *
+ * Return: Async transaction descriptor on success and NULL on failure
+ */
+static struct dma_async_tx_descriptor *
+ls2x_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
+ u32 sg_len, enum dma_transfer_direction direction,
+ unsigned long flags, void *context)
+{
+ struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+ struct ls2x_dma_desc *desc;
+ struct scatterlist *sg;
+ size_t burst_size;
+ int i;
+
+ if (unlikely(!sg_len || !is_slave_direction(direction)))
+ return NULL;
+
+ burst_size = ls2x_dmac_detect_burst(lchan);
+ if (!burst_size)
+ return NULL;
+
+ desc = kzalloc(struct_size(desc, sg, sg_len), GFP_NOWAIT);
+ if (!desc)
+ return NULL;
+
+ desc->desc_num = sg_len;
+ desc->direction = direction;
+ desc->burst_size = burst_size;
+
+ for_each_sg(sgl, sg, sg_len, i) {
+ struct ls2x_dma_sg *ldma_sg = &desc->sg[i];
+
+ /* Allocate DMA capable memory for hardware descriptor */
+ ldma_sg->hw = dma_pool_alloc(lchan->pool, GFP_NOWAIT, &ldma_sg->llp);
+ if (!ldma_sg->hw) {
+ desc->desc_num = i;
+ ls2x_dma_desc_free(&desc->vdesc);
+ return NULL;
+ }
+
+ ldma_sg->phys = sg_dma_address(sg);
+ ldma_sg->len = sg_dma_len(sg);
+
+ ls2x_dma_fill_desc(lchan, i, desc);
+ }
+
+ /* Setting the last descriptor enable bit */
+ desc->sg[sg_len - 1].hw->ndesc_addr &= ~LDMA_DESC_EN;
+ desc->status = DMA_IN_PROGRESS;
+
+ return vchan_tx_prep(&lchan->vchan, &desc->vdesc, flags);
+}
+
+/*
+ * ls2x_dma_prep_dma_cyclic - prepare the cyclic DMA transfer
+ * @chan: the DMA channel to prepare
+ * @buf_addr: physical DMA address where the buffer starts
+ * @buf_len: total number of bytes for the entire buffer
+ * @period_len: number of bytes for each period
+ * @direction: transfer direction, to or from device
+ * @flags: tx descriptor status flags
+ *
+ * Return: Async transaction descriptor on success and NULL on failure
+ */
+static struct dma_async_tx_descriptor *
+ls2x_dma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
+ size_t period_len, enum dma_transfer_direction direction,
+ unsigned long flags)
+{
+ struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+ struct ls2x_dma_desc *desc;
+ size_t burst_size;
+ u32 num_periods;
+ int i;
+
+ if (unlikely(!buf_len || !period_len))
+ return NULL;
+
+ if (unlikely(!is_slave_direction(direction)))
+ return NULL;
+
+ burst_size = ls2x_dmac_detect_burst(lchan);
+ if (!burst_size)
+ return NULL;
+
+ num_periods = buf_len / period_len;
+ desc = kzalloc(struct_size(desc, sg, num_periods), GFP_NOWAIT);
+ if (!desc)
+ return NULL;
+
+ desc->desc_num = num_periods;
+ desc->direction = direction;
+ desc->burst_size = burst_size;
+
+ /* Build cyclic linked list */
+ for (i = 0; i < num_periods; i++) {
+ struct ls2x_dma_sg *ldma_sg = &desc->sg[i];
+
+ /* Allocate DMA capable memory for hardware descriptor */
+ ldma_sg->hw = dma_pool_alloc(lchan->pool, GFP_NOWAIT, &ldma_sg->llp);
+ if (!ldma_sg->hw) {
+ desc->desc_num = i;
+ ls2x_dma_desc_free(&desc->vdesc);
+ return NULL;
+ }
+
+ ldma_sg->phys = buf_addr + period_len * i;
+ ldma_sg->len = period_len;
+
+ ls2x_dma_fill_desc(lchan, i, desc);
+ }
+
+ /* Lets make a cyclic list */
+ desc->sg[num_periods - 1].hw->ndesc_addr = desc->sg[0].llp | LDMA_DESC_EN;
+ desc->sg[num_periods - 1].hw->high_ndesc_addr = upper_32_bits(desc->sg[0].llp);
+ desc->cyclic = true;
+ desc->status = DMA_IN_PROGRESS;
+
+ return vchan_tx_prep(&lchan->vchan, &desc->vdesc, flags);
+}
+
+/*
+ * ls2x_slave_config - set slave configuration for channel
+ * @chan: dma channel
+ * @cfg: slave configuration
+ *
+ * Sets slave configuration for channel
+ */
+static int ls2x_dma_slave_config(struct dma_chan *chan,
+ struct dma_slave_config *config)
+{
+ struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+
+ memcpy(&lchan->sconfig, config, sizeof(*config));
+ return 0;
+}
+
+/*
+ * ls2x_dma_issue_pending - push pending transactions to the hardware
+ * @chan: channel
+ *
+ * When this function is called, all pending transactions are pushed to the
+ * hardware and executed.
+ */
+static void ls2x_dma_issue_pending(struct dma_chan *chan)
+{
+ struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+ unsigned long flags;
+
+ spin_lock_irqsave(&lchan->vchan.lock, flags);
+ if (vchan_issue_pending(&lchan->vchan) && !lchan->desc)
+ ls2x_dma_start_transfer(lchan);
+ spin_unlock_irqrestore(&lchan->vchan.lock, flags);
+}
+
+/*
+ * ls2x_dma_terminate_all - terminate all transactions
+ * @chan: channel
+ *
+ * Stops all DMA transactions.
+ */
+static int ls2x_dma_terminate_all(struct dma_chan *chan)
+{
+ struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+ unsigned long flags;
+ LIST_HEAD(head);
+
+ spin_lock_irqsave(&lchan->vchan.lock, flags);
+ /* Setting stop cmd */
+ ls2x_dma_write_cmd(lchan, LDMA_STOP);
+ if (lchan->desc) {
+ vchan_terminate_vdesc(&lchan->desc->vdesc);
+ lchan->desc = NULL;
+ }
+
+ vchan_get_all_descriptors(&lchan->vchan, &head);
+ spin_unlock_irqrestore(&lchan->vchan.lock, flags);
+
+ vchan_dma_desc_free_list(&lchan->vchan, &head);
+ return 0;
+}
+
+/*
+ * ls2x_dma_synchronize - Synchronizes the termination of transfers to the
+ * current context.
+ * @chan: channel
+ */
+static void ls2x_dma_synchronize(struct dma_chan *chan)
+{
+ struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+
+ vchan_synchronize(&lchan->vchan);
+}
+
+static int ls2x_dma_pause(struct dma_chan *chan)
+{
+ struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+ unsigned long flags;
+
+ spin_lock_irqsave(&lchan->vchan.lock, flags);
+ if (lchan->desc && lchan->desc->status == DMA_IN_PROGRESS) {
+ ls2x_dma_write_cmd(lchan, LDMA_STOP);
+ lchan->desc->status = DMA_PAUSED;
+ }
+ spin_unlock_irqrestore(&lchan->vchan.lock, flags);
+
+ return 0;
+}
+
+static int ls2x_dma_resume(struct dma_chan *chan)
+{
+ struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+ unsigned long flags;
+
+ spin_lock_irqsave(&lchan->vchan.lock, flags);
+ if (lchan->desc && lchan->desc->status == DMA_PAUSED) {
+ lchan->desc->status = DMA_IN_PROGRESS;
+ ls2x_dma_write_cmd(lchan, LDMA_START);
+ }
+ spin_unlock_irqrestore(&lchan->vchan.lock, flags);
+
+ return 0;
+}
+
+/*
+ * ls2x_dma_isr - LS2X DMA Interrupt handler
+ * @irq: IRQ number
+ * @dev_id: Pointer to ls2x_dma_chan
+ *
+ * Return: IRQ_HANDLED/IRQ_NONE
+ */
+static irqreturn_t ls2x_dma_isr(int irq, void *dev_id)
+{
+ struct ls2x_dma_chan *lchan = dev_id;
+ struct ls2x_dma_desc *desc;
+
+ spin_lock(&lchan->vchan.lock);
+ desc = lchan->desc;
+ if (desc) {
+ if (desc->cyclic) {
+ vchan_cyclic_callback(&desc->vdesc);
+ } else {
+ desc->status = DMA_COMPLETE;
+ vchan_cookie_complete(&desc->vdesc);
+ ls2x_dma_start_transfer(lchan);
+ }
+
+ /* ls2x_dma_start_transfer() updates lchan->desc */
+ if (!lchan->desc)
+ ls2x_dma_write_cmd(lchan, LDMA_STOP);
+ }
+ spin_unlock(&lchan->vchan.lock);
+
+ return IRQ_HANDLED;
+}
+
+static int ls2x_dma_chan_init(struct platform_device *pdev,
+ struct ls2x_dma_priv *priv)
+{
+ struct ls2x_dma_chan *lchan = &priv->lchan;
+ struct device *dev = &pdev->dev;
+ int ret;
+
+ lchan->irq = platform_get_irq(pdev, 0);
+ if (lchan->irq < 0)
+ return lchan->irq;
+
+ ret = devm_request_irq(dev, lchan->irq, ls2x_dma_isr, IRQF_TRIGGER_RISING,
+ dev_name(&pdev->dev), lchan);
+ if (ret)
+ return ret;
+
+ /* Initialize channels related values */
+ INIT_LIST_HEAD(&priv->ddev.channels);
+ lchan->vchan.desc_free = ls2x_dma_desc_free;
+ vchan_init(&lchan->vchan, &priv->ddev);
+
+ return 0;
+}
+
+/*
+ * ls2x_dma_probe - Driver probe function
+ * @pdev: Pointer to the platform_device structure
+ *
+ * Return: '0' on success and failure value on error
+ */
+static int ls2x_dma_probe(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ struct ls2x_dma_priv *priv;
+ struct dma_device *ddev;
+ int ret;
+
+ priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+ if (!priv)
+ return -ENOMEM;
+
+ priv->regs = devm_platform_ioremap_resource(pdev, 0);
+ if (IS_ERR(priv->regs))
+ return dev_err_probe(dev, PTR_ERR(priv->regs),
+ "devm_platform_ioremap_resource failed.\n");
+
+ priv->dma_clk = devm_clk_get(&pdev->dev, NULL);
+ if (IS_ERR(priv->dma_clk))
+ return dev_err_probe(dev, PTR_ERR(priv->dma_clk), "devm_clk_get failed.\n");
+
+ ret = clk_prepare_enable(priv->dma_clk);
+ if (ret)
+ return dev_err_probe(dev, ret, "clk_prepare_enable failed.\n");
+
+ ret = ls2x_dma_chan_init(pdev, priv);
+ if (ret)
+ goto disable_clk;
+
+ ddev = &priv->ddev;
+ ddev->dev = dev;
+ dma_cap_zero(ddev->cap_mask);
+ dma_cap_set(DMA_SLAVE, ddev->cap_mask);
+ dma_cap_set(DMA_CYCLIC, ddev->cap_mask);
+
+ ddev->device_alloc_chan_resources = ls2x_dma_alloc_chan_resources;
+ ddev->device_free_chan_resources = ls2x_dma_free_chan_resources;
+ ddev->device_tx_status = dma_cookie_status;
+ ddev->device_issue_pending = ls2x_dma_issue_pending;
+ ddev->device_prep_slave_sg = ls2x_dma_prep_slave_sg;
+ ddev->device_prep_dma_cyclic = ls2x_dma_prep_dma_cyclic;
+ ddev->device_config = ls2x_dma_slave_config;
+ ddev->device_terminate_all = ls2x_dma_terminate_all;
+ ddev->device_synchronize = ls2x_dma_synchronize;
+ ddev->device_pause = ls2x_dma_pause;
+ ddev->device_resume = ls2x_dma_resume;
+
+ ddev->src_addr_widths = LDMA_SLAVE_BUSWIDTHS;
+ ddev->dst_addr_widths = LDMA_SLAVE_BUSWIDTHS;
+ ddev->directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
+
+ ret = dma_async_device_register(&priv->ddev);
+ if (ret < 0)
+ goto disable_clk;
+
+ ret = of_dma_controller_register(dev->of_node, of_dma_xlate_by_chan_id, priv);
+ if (ret < 0)
+ goto unregister_dmac;
+
+ platform_set_drvdata(pdev, priv);
+
+ dev_info(dev, "Loongson LS2X APB DMA driver registered successfully.\n");
+ return 0;
+
+unregister_dmac:
+ dma_async_device_unregister(&priv->ddev);
+disable_clk:
+ clk_disable_unprepare(priv->dma_clk);
+
+ return ret;
+}
+
+/*
+ * ls2x_dma_remove - Driver remove function
+ * @pdev: Pointer to the platform_device structure
+ */
+static void ls2x_dma_remove(struct platform_device *pdev)
+{
+ struct ls2x_dma_priv *priv = platform_get_drvdata(pdev);
+
+ of_dma_controller_free(pdev->dev.of_node);
+ dma_async_device_unregister(&priv->ddev);
+ clk_disable_unprepare(priv->dma_clk);
+}
+
+static const struct of_device_id ls2x_dma_of_match_table[] = {
+ { .compatible = "loongson,ls2k1000-apbdma" },
+ { /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, ls2x_dma_of_match_table);
+
+static struct platform_driver ls2x_dmac_driver = {
+ .probe = ls2x_dma_probe,
+ .remove_new = ls2x_dma_remove,
+ .driver = {
+ .name = "ls2x-apbdma",
+ .of_match_table = ls2x_dma_of_match_table,
+ },
+};
+module_platform_driver(ls2x_dmac_driver);
+
+MODULE_DESCRIPTION("Loongson LS2X APB DMA Controller driver");
+MODULE_AUTHOR("Loongson Technology Corporation Limited");
+MODULE_LICENSE("GPL");
diff --git a/drivers/dma/milbeaut-hdmac.c b/drivers/dma/milbeaut-hdmac.c
index 1b0a95892627d6dc31439b9112f1c76d9b86071d..7b41c670970a655267f470a945178c53c04602e9 100644
--- a/drivers/dma/milbeaut-hdmac.c
+++ b/drivers/dma/milbeaut-hdmac.c
@@ -531,7 +531,7 @@ static int milbeaut_hdmac_probe(struct platform_device *pdev)
return ret;
}
-static int milbeaut_hdmac_remove(struct platform_device *pdev)
+static void milbeaut_hdmac_remove(struct platform_device *pdev)
{
struct milbeaut_hdmac_device *mdev = platform_get_drvdata(pdev);
struct dma_chan *chan;
@@ -546,16 +546,21 @@ static int milbeaut_hdmac_remove(struct platform_device *pdev)
*/
list_for_each_entry(chan, &mdev->ddev.channels, device_node) {
ret = dmaengine_terminate_sync(chan);
- if (ret)
- return ret;
+ if (ret) {
+ /*
+ * This results in resource leakage and maybe also
+ * use-after-free errors as e.g. *mdev is kfreed.
+ */
+ dev_alert(&pdev->dev, "Failed to terminate channel %d (%pe)\n",
+ chan->chan_id, ERR_PTR(ret));
+ return;
+ }
milbeaut_hdmac_free_chan_resources(chan);
}
of_dma_controller_free(pdev->dev.of_node);
dma_async_device_unregister(&mdev->ddev);
clk_disable_unprepare(mdev->clk);
-
- return 0;
}
static const struct of_device_id milbeaut_hdmac_match[] = {
@@ -566,7 +571,7 @@ MODULE_DEVICE_TABLE(of, milbeaut_hdmac_match);
static struct platform_driver milbeaut_hdmac_driver = {
.probe = milbeaut_hdmac_probe,
- .remove = milbeaut_hdmac_remove,
+ .remove_new = milbeaut_hdmac_remove,
.driver = {
.name = "milbeaut-m10v-hdmac",
.of_match_table = milbeaut_hdmac_match,
diff --git a/drivers/dma/milbeaut-xdmac.c b/drivers/dma/milbeaut-xdmac.c
index d29d01e730aa09171eecc60cfd298943b9783c9a..2cce529b448eb732f90dbeee236ac92a8d599ced 100644
--- a/drivers/dma/milbeaut-xdmac.c
+++ b/drivers/dma/milbeaut-xdmac.c
@@ -368,7 +368,7 @@ static int milbeaut_xdmac_probe(struct platform_device *pdev)
return ret;
}
-static int milbeaut_xdmac_remove(struct platform_device *pdev)
+static void milbeaut_xdmac_remove(struct platform_device *pdev)
{
struct milbeaut_xdmac_device *mdev = platform_get_drvdata(pdev);
struct dma_chan *chan;
@@ -383,8 +383,15 @@ static int milbeaut_xdmac_remove(struct platform_device *pdev)
*/
list_for_each_entry(chan, &mdev->ddev.channels, device_node) {
ret = dmaengine_terminate_sync(chan);
- if (ret)
- return ret;
+ if (ret) {
+ /*
+ * This results in resource leakage and maybe also
+ * use-after-free errors as e.g. *mdev is kfreed.
+ */
+ dev_alert(&pdev->dev, "Failed to terminate channel %d (%pe)\n",
+ chan->chan_id, ERR_PTR(ret));
+ return;
+ }
milbeaut_xdmac_free_chan_resources(chan);
}
@@ -392,8 +399,6 @@ static int milbeaut_xdmac_remove(struct platform_device *pdev)
dma_async_device_unregister(&mdev->ddev);
disable_xdmac(mdev);
-
- return 0;
}
static const struct of_device_id milbeaut_xdmac_match[] = {
@@ -404,7 +409,7 @@ MODULE_DEVICE_TABLE(of, milbeaut_xdmac_match);
static struct platform_driver milbeaut_xdmac_driver = {
.probe = milbeaut_xdmac_probe,
- .remove = milbeaut_xdmac_remove,
+ .remove_new = milbeaut_xdmac_remove,
.driver = {
.name = "milbeaut-m10v-xdmac",
.of_match_table = milbeaut_xdmac_match,
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index 3cf0b38387ae5604adf7fbf07574444171c21043..c29744bfdf2c2afc4ae6a7b6fdcd963a19db2977 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -1053,6 +1053,9 @@ static bool _trigger(struct pl330_thread *thrd)
thrd->req_running = idx;
+ if (desc->rqtype == DMA_MEM_TO_DEV || desc->rqtype == DMA_DEV_TO_MEM)
+ UNTIL(thrd, PL330_STATE_WFP);
+
return true;
}
diff --git a/drivers/dma/sf-pdma/sf-pdma.c b/drivers/dma/sf-pdma/sf-pdma.c
index 3125a2f162b4788d3ffbf182265bff18532ba19c..428473611115d1007755f244a51ab52eeefe46a5 100644
--- a/drivers/dma/sf-pdma/sf-pdma.c
+++ b/drivers/dma/sf-pdma/sf-pdma.c
@@ -20,10 +20,13 @@
#include
#include
#include
+#include
#include
#include "sf-pdma.h"
+#define PDMA_QUIRK_NO_STRICT_ORDERING BIT(0)
+
#ifndef readq
static inline unsigned long long readq(void __iomem *addr)
{
@@ -65,7 +68,7 @@ static struct sf_pdma_desc *sf_pdma_alloc_desc(struct sf_pdma_chan *chan)
static void sf_pdma_fill_desc(struct sf_pdma_desc *desc,
u64 dst, u64 src, u64 size)
{
- desc->xfer_type = PDMA_FULL_SPEED;
+ desc->xfer_type = desc->chan->pdma->transfer_type;
desc->xfer_size = size;
desc->dst_addr = dst;
desc->src_addr = src;
@@ -492,6 +495,7 @@ static void sf_pdma_setup_chans(struct sf_pdma *pdma)
static int sf_pdma_probe(struct platform_device *pdev)
{
+ const struct sf_pdma_driver_platdata *ddata;
struct sf_pdma *pdma;
int ret, n_chans;
const enum dma_slave_buswidth widths =
@@ -517,6 +521,14 @@ static int sf_pdma_probe(struct platform_device *pdev)
pdma->n_chans = n_chans;
+ pdma->transfer_type = PDMA_FULL_SPEED | PDMA_STRICT_ORDERING;
+
+ ddata = device_get_match_data(&pdev->dev);
+ if (ddata) {
+ if (ddata->quirks & PDMA_QUIRK_NO_STRICT_ORDERING)
+ pdma->transfer_type &= ~PDMA_STRICT_ORDERING;
+ }
+
pdma->membase = devm_platform_ioremap_resource(pdev, 0);
if (IS_ERR(pdma->membase))
return PTR_ERR(pdma->membase);
@@ -563,7 +575,20 @@ static int sf_pdma_probe(struct platform_device *pdev)
return ret;
}
+ ret = of_dma_controller_register(pdev->dev.of_node,
+ of_dma_xlate_by_chan_id, pdma);
+ if (ret < 0) {
+ dev_err(&pdev->dev,
+ "Can't register SiFive Platform OF_DMA. (%d)\n", ret);
+ goto err_unregister;
+ }
+
return 0;
+
+err_unregister:
+ dma_async_device_unregister(&pdma->dma_dev);
+
+ return ret;
}
static void sf_pdma_remove(struct platform_device *pdev)
@@ -583,12 +608,25 @@ static void sf_pdma_remove(struct platform_device *pdev)
tasklet_kill(&ch->err_tasklet);
}
+ if (pdev->dev.of_node)
+ of_dma_controller_free(pdev->dev.of_node);
+
dma_async_device_unregister(&pdma->dma_dev);
}
+static const struct sf_pdma_driver_platdata mpfs_pdma = {
+ .quirks = PDMA_QUIRK_NO_STRICT_ORDERING,
+};
+
static const struct of_device_id sf_pdma_dt_ids[] = {
- { .compatible = "sifive,fu540-c000-pdma" },
- { .compatible = "sifive,pdma0" },
+ {
+ .compatible = "sifive,fu540-c000-pdma",
+ }, {
+ .compatible = "sifive,pdma0",
+ }, {
+ .compatible = "microchip,mpfs-pdma",
+ .data = &mpfs_pdma,
+ },
{},
};
MODULE_DEVICE_TABLE(of, sf_pdma_dt_ids);
diff --git a/drivers/dma/sf-pdma/sf-pdma.h b/drivers/dma/sf-pdma/sf-pdma.h
index d05772b5d8d3fd3e0bee8d984eb41916c80e5214..215e07183d7e26b71f4238ab70e14c50bf72b5a2 100644
--- a/drivers/dma/sf-pdma/sf-pdma.h
+++ b/drivers/dma/sf-pdma/sf-pdma.h
@@ -48,7 +48,8 @@
#define PDMA_ERR_STATUS_MASK GENMASK(31, 31)
/* Transfer Type */
-#define PDMA_FULL_SPEED 0xFF000008
+#define PDMA_FULL_SPEED 0xFF000000
+#define PDMA_STRICT_ORDERING BIT(3)
/* Error Recovery */
#define MAX_RETRY 1
@@ -112,8 +113,13 @@ struct sf_pdma {
struct dma_device dma_dev;
void __iomem *membase;
void __iomem *mappedbase;
+ u32 transfer_type;
u32 n_chans;
struct sf_pdma_chan chans[] __counted_by(n_chans);
};
+struct sf_pdma_driver_platdata {
+ u32 quirks;
+};
+
#endif /* _SF_PDMA_H */
diff --git a/drivers/dma/sh/rz-dmac.c b/drivers/dma/sh/rz-dmac.c
index fea5bda34bc20f679b987e0a2d4ffde4f28e1f7c..1f1e86ba5c66aa8c33556eabb34a94ba431e4cc8 100644
--- a/drivers/dma/sh/rz-dmac.c
+++ b/drivers/dma/sh/rz-dmac.c
@@ -755,11 +755,11 @@ static struct dma_chan *rz_dmac_of_xlate(struct of_phandle_args *dma_spec,
static int rz_dmac_chan_probe(struct rz_dmac *dmac,
struct rz_dmac_chan *channel,
- unsigned int index)
+ u8 index)
{
struct platform_device *pdev = to_platform_device(dmac->dev);
struct rz_lmdesc *lmdesc;
- char pdev_irqname[5];
+ char pdev_irqname[6];
char *irqname;
int ret;
@@ -767,7 +767,7 @@ static int rz_dmac_chan_probe(struct rz_dmac *dmac,
channel->mid_rid = -EINVAL;
/* Request the channel interrupt. */
- sprintf(pdev_irqname, "ch%u", index);
+ scnprintf(pdev_irqname, sizeof(pdev_irqname), "ch%u", index);
channel->irq = platform_get_irq_byname(pdev, pdev_irqname);
if (channel->irq < 0)
return channel->irq;
@@ -845,9 +845,9 @@ static int rz_dmac_probe(struct platform_device *pdev)
struct dma_device *engine;
struct rz_dmac *dmac;
int channel_num;
- unsigned int i;
int ret;
int irq;
+ u8 i;
dmac = devm_kzalloc(&pdev->dev, sizeof(*dmac), GFP_KERNEL);
if (!dmac)
diff --git a/drivers/dma/sh/shdma.h b/drivers/dma/sh/shdma.h
index 9c121a4b33ad829c77ae88c094fc80d942b9d709..f97d80343aea42fd399e93da3492e07a8fa86b35 100644
--- a/drivers/dma/sh/shdma.h
+++ b/drivers/dma/sh/shdma.h
@@ -25,7 +25,7 @@ struct sh_dmae_chan {
const struct sh_dmae_slave_config *config; /* Slave DMA configuration */
int xmit_shift; /* log_2(bytes_per_xfer) */
void __iomem *base;
- char dev_id[16]; /* unique name per DMAC of channel */
+ char dev_id[32]; /* unique name per DMAC of channel */
int pm_error;
dma_addr_t slave_addr;
};
diff --git a/drivers/dma/sh/usb-dmac.c b/drivers/dma/sh/usb-dmac.c
index a9b4302f6050144f2359927c4cd4cf41dc38e80f..f7cd0cad056c16ced372483d64b5d1032696dea4 100644
--- a/drivers/dma/sh/usb-dmac.c
+++ b/drivers/dma/sh/usb-dmac.c
@@ -706,10 +706,10 @@ static const struct dev_pm_ops usb_dmac_pm = {
static int usb_dmac_chan_probe(struct usb_dmac *dmac,
struct usb_dmac_chan *uchan,
- unsigned int index)
+ u8 index)
{
struct platform_device *pdev = to_platform_device(dmac->dev);
- char pdev_irqname[5];
+ char pdev_irqname[6];
char *irqname;
int ret;
@@ -717,7 +717,7 @@ static int usb_dmac_chan_probe(struct usb_dmac *dmac,
uchan->iomem = dmac->iomem + USB_DMAC_CHAN_OFFSET(index);
/* Request the channel interrupt. */
- sprintf(pdev_irqname, "ch%u", index);
+ scnprintf(pdev_irqname, sizeof(pdev_irqname), "ch%u", index);
uchan->irq = platform_get_irq_byname(pdev, pdev_irqname);
if (uchan->irq < 0)
return -ENODEV;
@@ -768,8 +768,8 @@ static int usb_dmac_probe(struct platform_device *pdev)
const enum dma_slave_buswidth widths = USB_DMAC_SLAVE_BUSWIDTH;
struct dma_device *engine;
struct usb_dmac *dmac;
- unsigned int i;
int ret;
+ u8 i;
dmac = devm_kzalloc(&pdev->dev, sizeof(*dmac), GFP_KERNEL);
if (!dmac)
@@ -869,7 +869,7 @@ static void usb_dmac_chan_remove(struct usb_dmac *dmac,
static void usb_dmac_remove(struct platform_device *pdev)
{
struct usb_dmac *dmac = platform_get_drvdata(pdev);
- int i;
+ u8 i;
for (i = 0; i < dmac->n_channels; ++i)
usb_dmac_chan_remove(dmac, &dmac->channels[i]);
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index 002833fb1fa04cabddb058fa6c575d7ffc42247e..2c489299148eeea268e83e1a74824c434d86cdee 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -31,13 +31,11 @@
/**
* struct stedma40_platform_data - Configuration struct for the dma device.
*
- * @dev_tx: mapping between destination event line and io address
- * @dev_rx: mapping between source event line and io address
* @disabled_channels: A vector, ending with -1, that marks physical channels
* that are for different reasons not available for the driver.
* @soft_lli_chans: A vector, that marks physical channels will use LLI by SW
* which avoids HW bug that exists in some versions of the controller.
- * SoftLLI introduces relink overhead that could impact performace for
+ * SoftLLI introduces relink overhead that could impact performance for
* certain use cases.
* @num_of_soft_lli_chans: The number of channels that needs to be configured
* to use SoftLLI.
@@ -184,7 +182,7 @@ static __maybe_unused u32 d40_backup_regs[] = {
/*
* since 9540 and 8540 has the same HW revision
- * use v4a for 9540 or ealier
+ * use v4a for 9540 or earlier
* use v4b for 8540 or later
* HW revision:
* DB8500ed has revision 0
@@ -411,7 +409,7 @@ struct d40_desc {
*
* @base: The virtual address of LCLA. 18 bit aligned.
* @dma_addr: DMA address, if mapped
- * @base_unaligned: The orignal kmalloc pointer, if kmalloc is used.
+ * @base_unaligned: The original kmalloc pointer, if kmalloc is used.
* This pointer is only there for clean-up on error.
* @pages: The number of pages needed for all physical channels.
* Only used later for clean-up on error
@@ -1655,7 +1653,7 @@ static void dma_tasklet(struct tasklet_struct *t)
return;
check_pending_tx:
- /* Rescue manouver if receiving double interrupts */
+ /* Rescue maneuver if receiving double interrupts */
if (d40c->pending_tx > 0)
d40c->pending_tx--;
spin_unlock_irqrestore(&d40c->lock, flags);
@@ -3412,7 +3410,7 @@ static int __init d40_lcla_allocate(struct d40_base *base)
base->lcla_pool.base = (void *)page_list[i];
} else {
/*
- * After many attempts and no succees with finding the correct
+ * After many attempts and no success with finding the correct
* alignment, try with allocating a big buffer.
*/
dev_warn(base->dev,
diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c
index 7a0586633bf32624b442cf5569bacf9361408b78..24ad7077c53ba8f87b7dfb53b1d922a4bec411d2 100644
--- a/drivers/dma/tegra210-adma.c
+++ b/drivers/dma/tegra210-adma.c
@@ -153,6 +153,7 @@ struct tegra_adma {
void __iomem *base_addr;
struct clk *ahub_clk;
unsigned int nr_channels;
+ unsigned long *dma_chan_mask;
unsigned long rx_requests_reserved;
unsigned long tx_requests_reserved;
@@ -741,6 +742,10 @@ static int __maybe_unused tegra_adma_runtime_suspend(struct device *dev)
for (i = 0; i < tdma->nr_channels; i++) {
tdc = &tdma->channels[i];
+ /* skip for reserved channels */
+ if (!tdc->tdma)
+ continue;
+
ch_reg = &tdc->ch_regs;
ch_reg->cmd = tdma_ch_read(tdc, ADMA_CH_CMD);
/* skip if channel is not active */
@@ -779,6 +784,9 @@ static int __maybe_unused tegra_adma_runtime_resume(struct device *dev)
for (i = 0; i < tdma->nr_channels; i++) {
tdc = &tdma->channels[i];
+ /* skip for reserved channels */
+ if (!tdc->tdma)
+ continue;
ch_reg = &tdc->ch_regs;
/* skip if channel was not active earlier */
if (!ch_reg->cmd)
@@ -867,10 +875,31 @@ static int tegra_adma_probe(struct platform_device *pdev)
return PTR_ERR(tdma->ahub_clk);
}
+ tdma->dma_chan_mask = devm_kzalloc(&pdev->dev,
+ BITS_TO_LONGS(tdma->nr_channels) * sizeof(unsigned long),
+ GFP_KERNEL);
+ if (!tdma->dma_chan_mask)
+ return -ENOMEM;
+
+ /* Enable all channels by default */
+ bitmap_fill(tdma->dma_chan_mask, tdma->nr_channels);
+
+ ret = of_property_read_u32_array(pdev->dev.of_node, "dma-channel-mask",
+ (u32 *)tdma->dma_chan_mask,
+ BITS_TO_U32(tdma->nr_channels));
+ if (ret < 0 && (ret != -EINVAL)) {
+ dev_err(&pdev->dev, "dma-channel-mask is not complete.\n");
+ return ret;
+ }
+
INIT_LIST_HEAD(&tdma->dma_dev.channels);
for (i = 0; i < tdma->nr_channels; i++) {
struct tegra_adma_chan *tdc = &tdma->channels[i];
+ /* skip for reserved channels */
+ if (!test_bit(i, tdma->dma_chan_mask))
+ continue;
+
tdc->chan_addr = tdma->base_addr + cdata->ch_base_offset
+ (cdata->ch_reg_size * i);
@@ -957,8 +986,10 @@ static void tegra_adma_remove(struct platform_device *pdev)
of_dma_controller_free(pdev->dev.of_node);
dma_async_device_unregister(&tdma->dma_dev);
- for (i = 0; i < tdma->nr_channels; ++i)
- irq_dispose_mapping(tdma->channels[i].irq);
+ for (i = 0; i < tdma->nr_channels; ++i) {
+ if (tdma->channels[i].irq)
+ irq_dispose_mapping(tdma->channels[i].irq);
+ }
pm_runtime_disable(&pdev->dev);
}
diff --git a/drivers/dma/ti/Makefile b/drivers/dma/ti/Makefile
index acc950bf609c36de7c6382851631ed441abc3af3..d376c117cecf60d0d314cde97f73cb5d3532a013 100644
--- a/drivers/dma/ti/Makefile
+++ b/drivers/dma/ti/Makefile
@@ -12,6 +12,7 @@ k3-psil-lib-objs := k3-psil.o \
k3-psil-j721s2.o \
k3-psil-am62.o \
k3-psil-am62a.o \
- k3-psil-j784s4.o
+ k3-psil-j784s4.o \
+ k3-psil-am62p.o
obj-$(CONFIG_TI_K3_PSIL) += k3-psil-lib.o
obj-$(CONFIG_TI_DMA_CROSSBAR) += dma-crossbar.o
diff --git a/drivers/dma/ti/k3-psil-am62p.c b/drivers/dma/ti/k3-psil-am62p.c
new file mode 100644
index 0000000000000000000000000000000000000000..0f338e16d9710f25998a3919f8b65bc57d12a824
--- /dev/null
+++ b/drivers/dma/ti/k3-psil-am62p.c
@@ -0,0 +1,325 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 Texas Instruments Incorporated - https://www.ti.com
+ */
+
+#include
+
+#include "k3-psil-priv.h"
+
+#define PSIL_PDMA_XY_TR(x) \
+ { \
+ .thread_id = x, \
+ .ep_config = { \
+ .ep_type = PSIL_EP_PDMA_XY, \
+ .mapped_channel_id = -1, \
+ .default_flow_id = -1, \
+ }, \
+ }
+
+#define PSIL_PDMA_XY_PKT(x) \
+ { \
+ .thread_id = x, \
+ .ep_config = { \
+ .ep_type = PSIL_EP_PDMA_XY, \
+ .mapped_channel_id = -1, \
+ .default_flow_id = -1, \
+ .pkt_mode = 1, \
+ }, \
+ }
+
+#define PSIL_ETHERNET(x, ch, flow_base, flow_cnt) \
+ { \
+ .thread_id = x, \
+ .ep_config = { \
+ .ep_type = PSIL_EP_NATIVE, \
+ .pkt_mode = 1, \
+ .needs_epib = 1, \
+ .psd_size = 16, \
+ .mapped_channel_id = ch, \
+ .flow_start = flow_base, \
+ .flow_num = flow_cnt, \
+ .default_flow_id = flow_base, \
+ }, \
+ }
+
+#define PSIL_SAUL(x, ch, flow_base, flow_cnt, default_flow, tx) \
+ { \
+ .thread_id = x, \
+ .ep_config = { \
+ .ep_type = PSIL_EP_NATIVE, \
+ .pkt_mode = 1, \
+ .needs_epib = 1, \
+ .psd_size = 64, \
+ .mapped_channel_id = ch, \
+ .flow_start = flow_base, \
+ .flow_num = flow_cnt, \
+ .default_flow_id = default_flow, \
+ .notdpkt = tx, \
+ }, \
+ }
+
+#define PSIL_PDMA_MCASP(x) \
+ { \
+ .thread_id = x, \
+ .ep_config = { \
+ .ep_type = PSIL_EP_PDMA_XY, \
+ .pdma_acc32 = 1, \
+ .pdma_burst = 1, \
+ }, \
+ }
+
+#define PSIL_CSI2RX(x) \
+ { \
+ .thread_id = x, \
+ .ep_config = { \
+ .ep_type = PSIL_EP_NATIVE, \
+ }, \
+ }
+
+/* PSI-L source thread IDs, used for RX (DMA_DEV_TO_MEM) */
+static struct psil_ep am62p_src_ep_map[] = {
+ /* SAUL */
+ PSIL_SAUL(0x7504, 20, 35, 8, 35, 0),
+ PSIL_SAUL(0x7505, 21, 35, 8, 36, 0),
+ PSIL_SAUL(0x7506, 22, 43, 8, 43, 0),
+ PSIL_SAUL(0x7507, 23, 43, 8, 44, 0),
+ /* PDMA_MAIN0 - SPI0-2 */
+ PSIL_PDMA_XY_PKT(0x4300),
+ PSIL_PDMA_XY_PKT(0x4301),
+ PSIL_PDMA_XY_PKT(0x4302),
+ PSIL_PDMA_XY_PKT(0x4303),
+ PSIL_PDMA_XY_PKT(0x4304),
+ PSIL_PDMA_XY_PKT(0x4305),
+ PSIL_PDMA_XY_PKT(0x4306),
+ PSIL_PDMA_XY_PKT(0x4307),
+ PSIL_PDMA_XY_PKT(0x4308),
+ PSIL_PDMA_XY_PKT(0x4309),
+ PSIL_PDMA_XY_PKT(0x430a),
+ PSIL_PDMA_XY_PKT(0x430b),
+ /* PDMA_MAIN1 - UART0-6 */
+ PSIL_PDMA_XY_PKT(0x4400),
+ PSIL_PDMA_XY_PKT(0x4401),
+ PSIL_PDMA_XY_PKT(0x4402),
+ PSIL_PDMA_XY_PKT(0x4403),
+ PSIL_PDMA_XY_PKT(0x4404),
+ PSIL_PDMA_XY_PKT(0x4405),
+ PSIL_PDMA_XY_PKT(0x4406),
+ /* PDMA_MAIN2 - MCASP0-2 */
+ PSIL_PDMA_MCASP(0x4500),
+ PSIL_PDMA_MCASP(0x4501),
+ PSIL_PDMA_MCASP(0x4502),
+ /* CPSW3G */
+ PSIL_ETHERNET(0x4600, 19, 19, 16),
+ /* CSI2RX */
+ PSIL_CSI2RX(0x5000),
+ PSIL_CSI2RX(0x5001),
+ PSIL_CSI2RX(0x5002),
+ PSIL_CSI2RX(0x5003),
+ PSIL_CSI2RX(0x5004),
+ PSIL_CSI2RX(0x5005),
+ PSIL_CSI2RX(0x5006),
+ PSIL_CSI2RX(0x5007),
+ PSIL_CSI2RX(0x5008),
+ PSIL_CSI2RX(0x5009),
+ PSIL_CSI2RX(0x500a),
+ PSIL_CSI2RX(0x500b),
+ PSIL_CSI2RX(0x500c),
+ PSIL_CSI2RX(0x500d),
+ PSIL_CSI2RX(0x500e),
+ PSIL_CSI2RX(0x500f),
+ PSIL_CSI2RX(0x5010),
+ PSIL_CSI2RX(0x5011),
+ PSIL_CSI2RX(0x5012),
+ PSIL_CSI2RX(0x5013),
+ PSIL_CSI2RX(0x5014),
+ PSIL_CSI2RX(0x5015),
+ PSIL_CSI2RX(0x5016),
+ PSIL_CSI2RX(0x5017),
+ PSIL_CSI2RX(0x5018),
+ PSIL_CSI2RX(0x5019),
+ PSIL_CSI2RX(0x501a),
+ PSIL_CSI2RX(0x501b),
+ PSIL_CSI2RX(0x501c),
+ PSIL_CSI2RX(0x501d),
+ PSIL_CSI2RX(0x501e),
+ PSIL_CSI2RX(0x501f),
+ PSIL_CSI2RX(0x5000),
+ PSIL_CSI2RX(0x5001),
+ PSIL_CSI2RX(0x5002),
+ PSIL_CSI2RX(0x5003),
+ PSIL_CSI2RX(0x5004),
+ PSIL_CSI2RX(0x5005),
+ PSIL_CSI2RX(0x5006),
+ PSIL_CSI2RX(0x5007),
+ PSIL_CSI2RX(0x5008),
+ PSIL_CSI2RX(0x5009),
+ PSIL_CSI2RX(0x500a),
+ PSIL_CSI2RX(0x500b),
+ PSIL_CSI2RX(0x500c),
+ PSIL_CSI2RX(0x500d),
+ PSIL_CSI2RX(0x500e),
+ PSIL_CSI2RX(0x500f),
+ PSIL_CSI2RX(0x5010),
+ PSIL_CSI2RX(0x5011),
+ PSIL_CSI2RX(0x5012),
+ PSIL_CSI2RX(0x5013),
+ PSIL_CSI2RX(0x5014),
+ PSIL_CSI2RX(0x5015),
+ PSIL_CSI2RX(0x5016),
+ PSIL_CSI2RX(0x5017),
+ PSIL_CSI2RX(0x5018),
+ PSIL_CSI2RX(0x5019),
+ PSIL_CSI2RX(0x501a),
+ PSIL_CSI2RX(0x501b),
+ PSIL_CSI2RX(0x501c),
+ PSIL_CSI2RX(0x501d),
+ PSIL_CSI2RX(0x501e),
+ PSIL_CSI2RX(0x501f),
+ /* CSIRX 1-3 (only for J722S) */
+ PSIL_CSI2RX(0x5100),
+ PSIL_CSI2RX(0x5101),
+ PSIL_CSI2RX(0x5102),
+ PSIL_CSI2RX(0x5103),
+ PSIL_CSI2RX(0x5104),
+ PSIL_CSI2RX(0x5105),
+ PSIL_CSI2RX(0x5106),
+ PSIL_CSI2RX(0x5107),
+ PSIL_CSI2RX(0x5108),
+ PSIL_CSI2RX(0x5109),
+ PSIL_CSI2RX(0x510a),
+ PSIL_CSI2RX(0x510b),
+ PSIL_CSI2RX(0x510c),
+ PSIL_CSI2RX(0x510d),
+ PSIL_CSI2RX(0x510e),
+ PSIL_CSI2RX(0x510f),
+ PSIL_CSI2RX(0x5110),
+ PSIL_CSI2RX(0x5111),
+ PSIL_CSI2RX(0x5112),
+ PSIL_CSI2RX(0x5113),
+ PSIL_CSI2RX(0x5114),
+ PSIL_CSI2RX(0x5115),
+ PSIL_CSI2RX(0x5116),
+ PSIL_CSI2RX(0x5117),
+ PSIL_CSI2RX(0x5118),
+ PSIL_CSI2RX(0x5119),
+ PSIL_CSI2RX(0x511a),
+ PSIL_CSI2RX(0x511b),
+ PSIL_CSI2RX(0x511c),
+ PSIL_CSI2RX(0x511d),
+ PSIL_CSI2RX(0x511e),
+ PSIL_CSI2RX(0x511f),
+ PSIL_CSI2RX(0x5200),
+ PSIL_CSI2RX(0x5201),
+ PSIL_CSI2RX(0x5202),
+ PSIL_CSI2RX(0x5203),
+ PSIL_CSI2RX(0x5204),
+ PSIL_CSI2RX(0x5205),
+ PSIL_CSI2RX(0x5206),
+ PSIL_CSI2RX(0x5207),
+ PSIL_CSI2RX(0x5208),
+ PSIL_CSI2RX(0x5209),
+ PSIL_CSI2RX(0x520a),
+ PSIL_CSI2RX(0x520b),
+ PSIL_CSI2RX(0x520c),
+ PSIL_CSI2RX(0x520d),
+ PSIL_CSI2RX(0x520e),
+ PSIL_CSI2RX(0x520f),
+ PSIL_CSI2RX(0x5210),
+ PSIL_CSI2RX(0x5211),
+ PSIL_CSI2RX(0x5212),
+ PSIL_CSI2RX(0x5213),
+ PSIL_CSI2RX(0x5214),
+ PSIL_CSI2RX(0x5215),
+ PSIL_CSI2RX(0x5216),
+ PSIL_CSI2RX(0x5217),
+ PSIL_CSI2RX(0x5218),
+ PSIL_CSI2RX(0x5219),
+ PSIL_CSI2RX(0x521a),
+ PSIL_CSI2RX(0x521b),
+ PSIL_CSI2RX(0x521c),
+ PSIL_CSI2RX(0x521d),
+ PSIL_CSI2RX(0x521e),
+ PSIL_CSI2RX(0x521f),
+ PSIL_CSI2RX(0x5300),
+ PSIL_CSI2RX(0x5301),
+ PSIL_CSI2RX(0x5302),
+ PSIL_CSI2RX(0x5303),
+ PSIL_CSI2RX(0x5304),
+ PSIL_CSI2RX(0x5305),
+ PSIL_CSI2RX(0x5306),
+ PSIL_CSI2RX(0x5307),
+ PSIL_CSI2RX(0x5308),
+ PSIL_CSI2RX(0x5309),
+ PSIL_CSI2RX(0x530a),
+ PSIL_CSI2RX(0x530b),
+ PSIL_CSI2RX(0x530c),
+ PSIL_CSI2RX(0x530d),
+ PSIL_CSI2RX(0x530e),
+ PSIL_CSI2RX(0x530f),
+ PSIL_CSI2RX(0x5310),
+ PSIL_CSI2RX(0x5311),
+ PSIL_CSI2RX(0x5312),
+ PSIL_CSI2RX(0x5313),
+ PSIL_CSI2RX(0x5314),
+ PSIL_CSI2RX(0x5315),
+ PSIL_CSI2RX(0x5316),
+ PSIL_CSI2RX(0x5317),
+ PSIL_CSI2RX(0x5318),
+ PSIL_CSI2RX(0x5319),
+ PSIL_CSI2RX(0x531a),
+ PSIL_CSI2RX(0x531b),
+ PSIL_CSI2RX(0x531c),
+ PSIL_CSI2RX(0x531d),
+ PSIL_CSI2RX(0x531e),
+ PSIL_CSI2RX(0x531f),
+};
+
+/* PSI-L destination thread IDs, used for TX (DMA_MEM_TO_DEV) */
+static struct psil_ep am62p_dst_ep_map[] = {
+ /* SAUL */
+ PSIL_SAUL(0xf500, 27, 83, 8, 83, 1),
+ PSIL_SAUL(0xf501, 28, 91, 8, 91, 1),
+ /* PDMA_MAIN0 - SPI0-2 */
+ PSIL_PDMA_XY_PKT(0xc300),
+ PSIL_PDMA_XY_PKT(0xc301),
+ PSIL_PDMA_XY_PKT(0xc302),
+ PSIL_PDMA_XY_PKT(0xc303),
+ PSIL_PDMA_XY_PKT(0xc304),
+ PSIL_PDMA_XY_PKT(0xc305),
+ PSIL_PDMA_XY_PKT(0xc306),
+ PSIL_PDMA_XY_PKT(0xc307),
+ PSIL_PDMA_XY_PKT(0xc308),
+ PSIL_PDMA_XY_PKT(0xc309),
+ PSIL_PDMA_XY_PKT(0xc30a),
+ PSIL_PDMA_XY_PKT(0xc30b),
+ /* PDMA_MAIN1 - UART0-6 */
+ PSIL_PDMA_XY_PKT(0xc400),
+ PSIL_PDMA_XY_PKT(0xc401),
+ PSIL_PDMA_XY_PKT(0xc402),
+ PSIL_PDMA_XY_PKT(0xc403),
+ PSIL_PDMA_XY_PKT(0xc404),
+ PSIL_PDMA_XY_PKT(0xc405),
+ PSIL_PDMA_XY_PKT(0xc406),
+ /* PDMA_MAIN2 - MCASP0-2 */
+ PSIL_PDMA_MCASP(0xc500),
+ PSIL_PDMA_MCASP(0xc501),
+ PSIL_PDMA_MCASP(0xc502),
+ /* CPSW3G */
+ PSIL_ETHERNET(0xc600, 19, 19, 8),
+ PSIL_ETHERNET(0xc601, 20, 27, 8),
+ PSIL_ETHERNET(0xc602, 21, 35, 8),
+ PSIL_ETHERNET(0xc603, 22, 43, 8),
+ PSIL_ETHERNET(0xc604, 23, 51, 8),
+ PSIL_ETHERNET(0xc605, 24, 59, 8),
+ PSIL_ETHERNET(0xc606, 25, 67, 8),
+ PSIL_ETHERNET(0xc607, 26, 75, 8),
+};
+
+struct psil_ep_map am62p_ep_map = {
+ .name = "am62p",
+ .src = am62p_src_ep_map,
+ .src_count = ARRAY_SIZE(am62p_src_ep_map),
+ .dst = am62p_dst_ep_map,
+ .dst_count = ARRAY_SIZE(am62p_dst_ep_map),
+};
diff --git a/drivers/dma/ti/k3-psil-priv.h b/drivers/dma/ti/k3-psil-priv.h
index c383723d1c8f662b9c0981d1b7b76e0ccf12196f..a577be97e3447148cfc941ca4afe6c6c17fc7697 100644
--- a/drivers/dma/ti/k3-psil-priv.h
+++ b/drivers/dma/ti/k3-psil-priv.h
@@ -45,5 +45,6 @@ extern struct psil_ep_map j721s2_ep_map;
extern struct psil_ep_map am62_ep_map;
extern struct psil_ep_map am62a_ep_map;
extern struct psil_ep_map j784s4_ep_map;
+extern struct psil_ep_map am62p_ep_map;
#endif /* K3_PSIL_PRIV_H_ */
diff --git a/drivers/dma/ti/k3-psil.c b/drivers/dma/ti/k3-psil.c
index c11389d67a3f0f2ff75f300c8f2dc914d27a1570..25148d9524720372ca8098f6cfe68cc59641d29a 100644
--- a/drivers/dma/ti/k3-psil.c
+++ b/drivers/dma/ti/k3-psil.c
@@ -26,6 +26,8 @@ static const struct soc_device_attribute k3_soc_devices[] = {
{ .family = "AM62X", .data = &am62_ep_map },
{ .family = "AM62AX", .data = &am62a_ep_map },
{ .family = "J784S4", .data = &j784s4_ep_map },
+ { .family = "AM62PX", .data = &am62p_ep_map },
+ { .family = "J722S", .data = &am62p_ep_map },
{ /* sentinel */ }
};
diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c
index 30fd2f386f36a1ada7fc5cbe6a4359eb7019a559..2841a539c264891cde8b8166d51d5bbf885a5d85 100644
--- a/drivers/dma/ti/k3-udma.c
+++ b/drivers/dma/ti/k3-udma.c
@@ -4441,6 +4441,8 @@ static const struct soc_device_attribute k3_soc_devices[] = {
{ .family = "AM62X", .data = &am64_soc_data },
{ .family = "AM62AX", .data = &am64_soc_data },
{ .family = "J784S4", .data = &j721e_soc_data },
+ { .family = "AM62PX", .data = &am64_soc_data },
+ { .family = "J722S", .data = &am64_soc_data },
{ /* sentinel */ }
};
diff --git a/drivers/dma/uniphier-mdmac.c b/drivers/dma/uniphier-mdmac.c
index 618839df074866c4d9a2feca56a9f4183baea3cb..ad7125f6e2ca8e4452195e3ad4cedf4ee154a5b3 100644
--- a/drivers/dma/uniphier-mdmac.c
+++ b/drivers/dma/uniphier-mdmac.c
@@ -453,7 +453,7 @@ static int uniphier_mdmac_probe(struct platform_device *pdev)
return ret;
}
-static int uniphier_mdmac_remove(struct platform_device *pdev)
+static void uniphier_mdmac_remove(struct platform_device *pdev)
{
struct uniphier_mdmac_device *mdev = platform_get_drvdata(pdev);
struct dma_chan *chan;
@@ -468,16 +468,21 @@ static int uniphier_mdmac_remove(struct platform_device *pdev)
*/
list_for_each_entry(chan, &mdev->ddev.channels, device_node) {
ret = dmaengine_terminate_sync(chan);
- if (ret)
- return ret;
+ if (ret) {
+ /*
+ * This results in resource leakage and maybe also
+ * use-after-free errors as e.g. *mdev is kfreed.
+ */
+ dev_alert(&pdev->dev, "Failed to terminate channel %d (%pe)\n",
+ chan->chan_id, ERR_PTR(ret));
+ return;
+ }
uniphier_mdmac_free_chan_resources(chan);
}
of_dma_controller_free(pdev->dev.of_node);
dma_async_device_unregister(&mdev->ddev);
clk_disable_unprepare(mdev->clk);
-
- return 0;
}
static const struct of_device_id uniphier_mdmac_match[] = {
@@ -488,7 +493,7 @@ MODULE_DEVICE_TABLE(of, uniphier_mdmac_match);
static struct platform_driver uniphier_mdmac_driver = {
.probe = uniphier_mdmac_probe,
- .remove = uniphier_mdmac_remove,
+ .remove_new = uniphier_mdmac_remove,
.driver = {
.name = "uniphier-mio-dmac",
.of_match_table = uniphier_mdmac_match,
diff --git a/drivers/dma/uniphier-xdmac.c b/drivers/dma/uniphier-xdmac.c
index 3a8ee2b173b52e83b775bbe27d5f715a205aef87..3ce2dc2ad9de4290887e6c5344206d0e747b0c7f 100644
--- a/drivers/dma/uniphier-xdmac.c
+++ b/drivers/dma/uniphier-xdmac.c
@@ -563,7 +563,7 @@ static int uniphier_xdmac_probe(struct platform_device *pdev)
return ret;
}
-static int uniphier_xdmac_remove(struct platform_device *pdev)
+static void uniphier_xdmac_remove(struct platform_device *pdev)
{
struct uniphier_xdmac_device *xdev = platform_get_drvdata(pdev);
struct dma_device *ddev = &xdev->ddev;
@@ -579,15 +579,20 @@ static int uniphier_xdmac_remove(struct platform_device *pdev)
*/
list_for_each_entry(chan, &ddev->channels, device_node) {
ret = dmaengine_terminate_sync(chan);
- if (ret)
- return ret;
+ if (ret) {
+ /*
+ * This results in resource leakage and maybe also
+ * use-after-free errors as e.g. *xdev is kfreed.
+ */
+ dev_alert(&pdev->dev, "Failed to terminate channel %d (%pe)\n",
+ chan->chan_id, ERR_PTR(ret));
+ return;
+ }
uniphier_xdmac_free_chan_resources(chan);
}
of_dma_controller_free(pdev->dev.of_node);
dma_async_device_unregister(ddev);
-
- return 0;
}
static const struct of_device_id uniphier_xdmac_match[] = {
@@ -598,7 +603,7 @@ MODULE_DEVICE_TABLE(of, uniphier_xdmac_match);
static struct platform_driver uniphier_xdmac_driver = {
.probe = uniphier_xdmac_probe,
- .remove = uniphier_xdmac_remove,
+ .remove_new = uniphier_xdmac_remove,
.driver = {
.name = "uniphier-xdmac",
.of_match_table = uniphier_xdmac_match,
diff --git a/drivers/dma/xilinx/xdma-regs.h b/drivers/dma/xilinx/xdma-regs.h
index e641a5083e14b081a7871b3a19bda0c57601d6b5..98f5f6fb9ff9c771270c64c364265f72fd7b216d 100644
--- a/drivers/dma/xilinx/xdma-regs.h
+++ b/drivers/dma/xilinx/xdma-regs.h
@@ -64,9 +64,10 @@ struct xdma_hw_desc {
__le64 next_desc;
};
-#define XDMA_DESC_SIZE sizeof(struct xdma_hw_desc)
-#define XDMA_DESC_BLOCK_SIZE (XDMA_DESC_SIZE * XDMA_DESC_ADJACENT)
-#define XDMA_DESC_BLOCK_ALIGN 4096
+#define XDMA_DESC_SIZE sizeof(struct xdma_hw_desc)
+#define XDMA_DESC_BLOCK_SIZE (XDMA_DESC_SIZE * XDMA_DESC_ADJACENT)
+#define XDMA_DESC_BLOCK_ALIGN 32
+#define XDMA_DESC_BLOCK_BOUNDARY 4096
/*
* Channel registers
@@ -76,6 +77,7 @@ struct xdma_hw_desc {
#define XDMA_CHAN_CONTROL_W1S 0x8
#define XDMA_CHAN_CONTROL_W1C 0xc
#define XDMA_CHAN_STATUS 0x40
+#define XDMA_CHAN_STATUS_RC 0x44
#define XDMA_CHAN_COMPLETED_DESC 0x48
#define XDMA_CHAN_ALIGNMENTS 0x4c
#define XDMA_CHAN_INTR_ENABLE 0x90
@@ -101,6 +103,7 @@ struct xdma_hw_desc {
#define CHAN_CTRL_IE_MAGIC_STOPPED BIT(4)
#define CHAN_CTRL_IE_IDLE_STOPPED BIT(6)
#define CHAN_CTRL_IE_READ_ERROR GENMASK(13, 9)
+#define CHAN_CTRL_IE_WRITE_ERROR GENMASK(18, 14)
#define CHAN_CTRL_IE_DESC_ERROR GENMASK(23, 19)
#define CHAN_CTRL_NON_INCR_ADDR BIT(25)
#define CHAN_CTRL_POLL_MODE_WB BIT(26)
@@ -111,8 +114,17 @@ struct xdma_hw_desc {
CHAN_CTRL_IE_DESC_ALIGN_MISMATCH | \
CHAN_CTRL_IE_MAGIC_STOPPED | \
CHAN_CTRL_IE_READ_ERROR | \
+ CHAN_CTRL_IE_WRITE_ERROR | \
CHAN_CTRL_IE_DESC_ERROR)
+#define XDMA_CHAN_STATUS_MASK CHAN_CTRL_START
+
+#define XDMA_CHAN_ERROR_MASK (CHAN_CTRL_IE_DESC_ALIGN_MISMATCH | \
+ CHAN_CTRL_IE_MAGIC_STOPPED | \
+ CHAN_CTRL_IE_READ_ERROR | \
+ CHAN_CTRL_IE_WRITE_ERROR | \
+ CHAN_CTRL_IE_DESC_ERROR)
+
/* bits of the channel interrupt enable mask */
#define CHAN_IM_DESC_ERROR BIT(19)
#define CHAN_IM_READ_ERROR BIT(9)
@@ -134,18 +146,6 @@ struct xdma_hw_desc {
#define XDMA_SGDMA_DESC_ADJ 0x4088
#define XDMA_SGDMA_DESC_CREDIT 0x408c
-/* bits of the SG DMA control register */
-#define XDMA_CTRL_RUN_STOP BIT(0)
-#define XDMA_CTRL_IE_DESC_STOPPED BIT(1)
-#define XDMA_CTRL_IE_DESC_COMPLETED BIT(2)
-#define XDMA_CTRL_IE_DESC_ALIGN_MISMATCH BIT(3)
-#define XDMA_CTRL_IE_MAGIC_STOPPED BIT(4)
-#define XDMA_CTRL_IE_IDLE_STOPPED BIT(6)
-#define XDMA_CTRL_IE_READ_ERROR GENMASK(13, 9)
-#define XDMA_CTRL_IE_DESC_ERROR GENMASK(23, 19)
-#define XDMA_CTRL_NON_INCR_ADDR BIT(25)
-#define XDMA_CTRL_POLL_MODE_WB BIT(26)
-
/*
* interrupt registers
*/
diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c
index 84a88029226fdc16e423d8162408eea40cc22d00..170017ff2aad6e58c8d0ee4ea6e7d42c15c8202c 100644
--- a/drivers/dma/xilinx/xdma.c
+++ b/drivers/dma/xilinx/xdma.c
@@ -78,27 +78,31 @@ struct xdma_chan {
* @vdesc: Virtual DMA descriptor
* @chan: DMA channel pointer
* @dir: Transferring direction of the request
- * @dev_addr: Physical address on DMA device side
* @desc_blocks: Hardware descriptor blocks
* @dblk_num: Number of hardware descriptor blocks
* @desc_num: Number of hardware descriptors
* @completed_desc_num: Completed hardware descriptors
* @cyclic: Cyclic transfer vs. scatter-gather
+ * @interleaved_dma: Interleaved DMA transfer
* @periods: Number of periods in the cyclic transfer
* @period_size: Size of a period in bytes in cyclic transfers
+ * @frames_left: Number of frames left in interleaved DMA transfer
+ * @error: tx error flag
*/
struct xdma_desc {
struct virt_dma_desc vdesc;
struct xdma_chan *chan;
enum dma_transfer_direction dir;
- u64 dev_addr;
struct xdma_desc_block *desc_blocks;
u32 dblk_num;
u32 desc_num;
u32 completed_desc_num;
bool cyclic;
+ bool interleaved_dma;
u32 periods;
u32 period_size;
+ u32 frames_left;
+ bool error;
};
#define XDMA_DEV_STATUS_REG_DMA BIT(0)
@@ -276,6 +280,7 @@ xdma_alloc_desc(struct xdma_chan *chan, u32 desc_num, bool cyclic)
sw_desc->chan = chan;
sw_desc->desc_num = desc_num;
sw_desc->cyclic = cyclic;
+ sw_desc->error = false;
dblk_num = DIV_ROUND_UP(desc_num, XDMA_DESC_ADJACENT);
sw_desc->desc_blocks = kcalloc(dblk_num, sizeof(*sw_desc->desc_blocks),
GFP_NOWAIT);
@@ -371,6 +376,31 @@ static int xdma_xfer_start(struct xdma_chan *xchan)
return ret;
xchan->busy = true;
+
+ return 0;
+}
+
+/**
+ * xdma_xfer_stop - Stop DMA transfer
+ * @xchan: DMA channel pointer
+ */
+static int xdma_xfer_stop(struct xdma_chan *xchan)
+{
+ int ret;
+ u32 val;
+ struct xdma_device *xdev = xchan->xdev_hdl;
+
+ /* clear run stop bit to prevent any further auto-triggering */
+ ret = regmap_write(xdev->rmap, xchan->base + XDMA_CHAN_CONTROL_W1C,
+ CHAN_CTRL_RUN_STOP);
+ if (ret)
+ return ret;
+
+ /* Clear the channel status register */
+ ret = regmap_read(xdev->rmap, xchan->base + XDMA_CHAN_STATUS_RC, &val);
+ if (ret)
+ return ret;
+
return 0;
}
@@ -475,6 +505,84 @@ static void xdma_issue_pending(struct dma_chan *chan)
spin_unlock_irqrestore(&xdma_chan->vchan.lock, flags);
}
+/**
+ * xdma_terminate_all - Terminate all transactions
+ * @chan: DMA channel pointer
+ */
+static int xdma_terminate_all(struct dma_chan *chan)
+{
+ struct xdma_chan *xdma_chan = to_xdma_chan(chan);
+ struct virt_dma_desc *vd;
+ unsigned long flags;
+ LIST_HEAD(head);
+
+ xdma_xfer_stop(xdma_chan);
+
+ spin_lock_irqsave(&xdma_chan->vchan.lock, flags);
+
+ xdma_chan->busy = false;
+ vd = vchan_next_desc(&xdma_chan->vchan);
+ if (vd) {
+ list_del(&vd->node);
+ dma_cookie_complete(&vd->tx);
+ vchan_terminate_vdesc(vd);
+ }
+ vchan_get_all_descriptors(&xdma_chan->vchan, &head);
+ list_splice_tail(&head, &xdma_chan->vchan.desc_terminated);
+
+ spin_unlock_irqrestore(&xdma_chan->vchan.lock, flags);
+
+ return 0;
+}
+
+/**
+ * xdma_synchronize - Synchronize terminated transactions
+ * @chan: DMA channel pointer
+ */
+static void xdma_synchronize(struct dma_chan *chan)
+{
+ struct xdma_chan *xdma_chan = to_xdma_chan(chan);
+
+ vchan_synchronize(&xdma_chan->vchan);
+}
+
+/**
+ * xdma_fill_descs - Fill hardware descriptors with contiguous memory block addresses
+ * @sw_desc: tx descriptor state container
+ * @src_addr: Value for a ->src_addr field of a first descriptor
+ * @dst_addr: Value for a ->dst_addr field of a first descriptor
+ * @size: Total size of a contiguous memory block
+ * @filled_descs_num: Number of filled hardware descriptors for corresponding sw_desc
+ */
+static inline u32 xdma_fill_descs(struct xdma_desc *sw_desc, u64 src_addr,
+ u64 dst_addr, u32 size, u32 filled_descs_num)
+{
+ u32 left = size, len, desc_num = filled_descs_num;
+ struct xdma_desc_block *dblk;
+ struct xdma_hw_desc *desc;
+
+ dblk = sw_desc->desc_blocks + (desc_num / XDMA_DESC_ADJACENT);
+ desc = dblk->virt_addr;
+ desc += desc_num & XDMA_DESC_ADJACENT_MASK;
+ do {
+ len = min_t(u32, left, XDMA_DESC_BLEN_MAX);
+ /* set hardware descriptor */
+ desc->bytes = cpu_to_le32(len);
+ desc->src_addr = cpu_to_le64(src_addr);
+ desc->dst_addr = cpu_to_le64(dst_addr);
+ if (!(++desc_num & XDMA_DESC_ADJACENT_MASK))
+ desc = (++dblk)->virt_addr;
+ else
+ desc++;
+
+ src_addr += len;
+ dst_addr += len;
+ left -= len;
+ } while (left);
+
+ return desc_num - filled_descs_num;
+}
+
/**
* xdma_prep_device_sg - prepare a descriptor for a DMA transaction
* @chan: DMA channel pointer
@@ -491,13 +599,10 @@ xdma_prep_device_sg(struct dma_chan *chan, struct scatterlist *sgl,
{
struct xdma_chan *xdma_chan = to_xdma_chan(chan);
struct dma_async_tx_descriptor *tx_desc;
- u32 desc_num = 0, i, len, rest;
- struct xdma_desc_block *dblk;
- struct xdma_hw_desc *desc;
struct xdma_desc *sw_desc;
- u64 dev_addr, *src, *dst;
+ u32 desc_num = 0, i;
+ u64 addr, dev_addr, *src, *dst;
struct scatterlist *sg;
- u64 addr;
for_each_sg(sgl, sg, sg_len, i)
desc_num += DIV_ROUND_UP(sg_dma_len(sg), XDMA_DESC_BLEN_MAX);
@@ -506,6 +611,8 @@ xdma_prep_device_sg(struct dma_chan *chan, struct scatterlist *sgl,
if (!sw_desc)
return NULL;
sw_desc->dir = dir;
+ sw_desc->cyclic = false;
+ sw_desc->interleaved_dma = false;
if (dir == DMA_MEM_TO_DEV) {
dev_addr = xdma_chan->cfg.dst_addr;
@@ -517,32 +624,11 @@ xdma_prep_device_sg(struct dma_chan *chan, struct scatterlist *sgl,
dst = &addr;
}
- dblk = sw_desc->desc_blocks;
- desc = dblk->virt_addr;
- desc_num = 1;
+ desc_num = 0;
for_each_sg(sgl, sg, sg_len, i) {
addr = sg_dma_address(sg);
- rest = sg_dma_len(sg);
-
- do {
- len = min_t(u32, rest, XDMA_DESC_BLEN_MAX);
- /* set hardware descriptor */
- desc->bytes = cpu_to_le32(len);
- desc->src_addr = cpu_to_le64(*src);
- desc->dst_addr = cpu_to_le64(*dst);
-
- if (!(desc_num & XDMA_DESC_ADJACENT_MASK)) {
- dblk++;
- desc = dblk->virt_addr;
- } else {
- desc++;
- }
-
- desc_num++;
- dev_addr += len;
- addr += len;
- rest -= len;
- } while (rest);
+ desc_num += xdma_fill_descs(sw_desc, *src, *dst, sg_dma_len(sg), desc_num);
+ dev_addr += sg_dma_len(sg);
}
tx_desc = vchan_tx_prep(&xdma_chan->vchan, &sw_desc->vdesc, flags);
@@ -576,9 +662,9 @@ xdma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t address,
struct xdma_device *xdev = xdma_chan->xdev_hdl;
unsigned int periods = size / period_size;
struct dma_async_tx_descriptor *tx_desc;
- struct xdma_desc_block *dblk;
- struct xdma_hw_desc *desc;
struct xdma_desc *sw_desc;
+ u64 addr, dev_addr, *src, *dst;
+ u32 desc_num;
unsigned int i;
/*
@@ -602,22 +688,23 @@ xdma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t address,
sw_desc->periods = periods;
sw_desc->period_size = period_size;
sw_desc->dir = dir;
+ sw_desc->interleaved_dma = false;
- dblk = sw_desc->desc_blocks;
- desc = dblk->virt_addr;
+ addr = address;
+ if (dir == DMA_MEM_TO_DEV) {
+ dev_addr = xdma_chan->cfg.dst_addr;
+ src = &addr;
+ dst = &dev_addr;
+ } else {
+ dev_addr = xdma_chan->cfg.src_addr;
+ src = &dev_addr;
+ dst = &addr;
+ }
- /* fill hardware descriptor */
+ desc_num = 0;
for (i = 0; i < periods; i++) {
- desc->bytes = cpu_to_le32(period_size);
- if (dir == DMA_MEM_TO_DEV) {
- desc->src_addr = cpu_to_le64(address + i * period_size);
- desc->dst_addr = cpu_to_le64(xdma_chan->cfg.dst_addr);
- } else {
- desc->src_addr = cpu_to_le64(xdma_chan->cfg.src_addr);
- desc->dst_addr = cpu_to_le64(address + i * period_size);
- }
-
- desc++;
+ desc_num += xdma_fill_descs(sw_desc, *src, *dst, period_size, desc_num);
+ addr += i * period_size;
}
tx_desc = vchan_tx_prep(&xdma_chan->vchan, &sw_desc->vdesc, flags);
@@ -632,6 +719,57 @@ xdma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t address,
return NULL;
}
+/**
+ * xdma_prep_interleaved_dma - Prepare virtual descriptor for interleaved DMA transfers
+ * @chan: DMA channel
+ * @xt: DMA transfer template
+ * @flags: tx flags
+ */
+static struct dma_async_tx_descriptor *
+xdma_prep_interleaved_dma(struct dma_chan *chan,
+ struct dma_interleaved_template *xt,
+ unsigned long flags)
+{
+ int i;
+ u32 desc_num = 0, period_size = 0;
+ struct dma_async_tx_descriptor *tx_desc;
+ struct xdma_chan *xchan = to_xdma_chan(chan);
+ struct xdma_desc *sw_desc;
+ u64 src_addr, dst_addr;
+
+ for (i = 0; i < xt->frame_size; ++i)
+ desc_num += DIV_ROUND_UP(xt->sgl[i].size, XDMA_DESC_BLEN_MAX);
+
+ sw_desc = xdma_alloc_desc(xchan, desc_num, false);
+ if (!sw_desc)
+ return NULL;
+ sw_desc->dir = xt->dir;
+ sw_desc->interleaved_dma = true;
+ sw_desc->cyclic = flags & DMA_PREP_REPEAT;
+ sw_desc->frames_left = xt->numf;
+ sw_desc->periods = xt->numf;
+
+ desc_num = 0;
+ src_addr = xt->src_start;
+ dst_addr = xt->dst_start;
+ for (i = 0; i < xt->frame_size; ++i) {
+ desc_num += xdma_fill_descs(sw_desc, src_addr, dst_addr, xt->sgl[i].size, desc_num);
+ src_addr += dmaengine_get_src_icg(xt, &xt->sgl[i]) + (xt->src_inc ?
+ xt->sgl[i].size : 0);
+ dst_addr += dmaengine_get_dst_icg(xt, &xt->sgl[i]) + (xt->dst_inc ?
+ xt->sgl[i].size : 0);
+ period_size += xt->sgl[i].size;
+ }
+ sw_desc->period_size = period_size;
+
+ tx_desc = vchan_tx_prep(&xchan->vchan, &sw_desc->vdesc, flags);
+ if (tx_desc)
+ return tx_desc;
+
+ xdma_free_desc(&sw_desc->vdesc);
+ return NULL;
+}
+
/**
* xdma_device_config - Configure the DMA channel
* @chan: DMA channel
@@ -677,9 +815,8 @@ static int xdma_alloc_chan_resources(struct dma_chan *chan)
return -EINVAL;
}
- xdma_chan->desc_pool = dma_pool_create(dma_chan_name(chan),
- dev, XDMA_DESC_BLOCK_SIZE,
- XDMA_DESC_BLOCK_ALIGN, 0);
+ xdma_chan->desc_pool = dma_pool_create(dma_chan_name(chan), dev, XDMA_DESC_BLOCK_SIZE,
+ XDMA_DESC_BLOCK_ALIGN, XDMA_DESC_BLOCK_BOUNDARY);
if (!xdma_chan->desc_pool) {
xdma_err(xdev, "unable to allocate descriptor pool");
return -ENOMEM;
@@ -706,20 +843,20 @@ static enum dma_status xdma_tx_status(struct dma_chan *chan, dma_cookie_t cookie
spin_lock_irqsave(&xdma_chan->vchan.lock, flags);
vd = vchan_find_desc(&xdma_chan->vchan, cookie);
- if (vd)
- desc = to_xdma_desc(vd);
- if (!desc || !desc->cyclic) {
- spin_unlock_irqrestore(&xdma_chan->vchan.lock, flags);
- return ret;
- }
-
- period_idx = desc->completed_desc_num % desc->periods;
- residue = (desc->periods - period_idx) * desc->period_size;
+ if (!vd)
+ goto out;
+ desc = to_xdma_desc(vd);
+ if (desc->error) {
+ ret = DMA_ERROR;
+ } else if (desc->cyclic) {
+ period_idx = desc->completed_desc_num % desc->periods;
+ residue = (desc->periods - period_idx) * desc->period_size;
+ dma_set_residue(state, residue);
+ }
+out:
spin_unlock_irqrestore(&xdma_chan->vchan.lock, flags);
- dma_set_residue(state, residue);
-
return ret;
}
@@ -732,11 +869,12 @@ static irqreturn_t xdma_channel_isr(int irq, void *dev_id)
{
struct xdma_chan *xchan = dev_id;
u32 complete_desc_num = 0;
- struct xdma_device *xdev;
- struct virt_dma_desc *vd;
+ struct xdma_device *xdev = xchan->xdev_hdl;
+ struct virt_dma_desc *vd, *next_vd;
struct xdma_desc *desc;
int ret;
u32 st;
+ bool repeat_tx;
spin_lock(&xchan->vchan.lock);
@@ -745,45 +883,76 @@ static irqreturn_t xdma_channel_isr(int irq, void *dev_id)
if (!vd)
goto out;
- xchan->busy = false;
+ /* Clear-on-read the status register */
+ ret = regmap_read(xdev->rmap, xchan->base + XDMA_CHAN_STATUS_RC, &st);
+ if (ret)
+ goto out;
+
desc = to_xdma_desc(vd);
- xdev = xchan->xdev_hdl;
+
+ st &= XDMA_CHAN_STATUS_MASK;
+ if ((st & XDMA_CHAN_ERROR_MASK) ||
+ !(st & (CHAN_CTRL_IE_DESC_COMPLETED | CHAN_CTRL_IE_DESC_STOPPED))) {
+ desc->error = true;
+ xdma_err(xdev, "channel error, status register value: 0x%x", st);
+ goto out;
+ }
ret = regmap_read(xdev->rmap, xchan->base + XDMA_CHAN_COMPLETED_DESC,
&complete_desc_num);
if (ret)
goto out;
- desc->completed_desc_num += complete_desc_num;
+ if (desc->interleaved_dma) {
+ xchan->busy = false;
+ desc->completed_desc_num += complete_desc_num;
+ if (complete_desc_num == XDMA_DESC_BLOCK_NUM * XDMA_DESC_ADJACENT) {
+ xdma_xfer_start(xchan);
+ goto out;
+ }
- if (desc->cyclic) {
- ret = regmap_read(xdev->rmap, xchan->base + XDMA_CHAN_STATUS,
- &st);
- if (ret)
+ /* last desc of any frame */
+ desc->frames_left--;
+ if (desc->frames_left)
+ goto out;
+
+ /* last desc of the last frame */
+ repeat_tx = vd->tx.flags & DMA_PREP_REPEAT;
+ next_vd = list_first_entry_or_null(&vd->node, struct virt_dma_desc, node);
+ if (next_vd)
+ repeat_tx = repeat_tx && !(next_vd->tx.flags & DMA_PREP_LOAD_EOT);
+ if (repeat_tx) {
+ desc->frames_left = desc->periods;
+ desc->completed_desc_num = 0;
+ vchan_cyclic_callback(vd);
+ } else {
+ list_del(&vd->node);
+ vchan_cookie_complete(vd);
+ }
+ /* start (or continue) the tx of a first desc on the vc.desc_issued list, if any */
+ xdma_xfer_start(xchan);
+ } else if (!desc->cyclic) {
+ xchan->busy = false;
+ desc->completed_desc_num += complete_desc_num;
+
+ /* if all data blocks are transferred, remove and complete the request */
+ if (desc->completed_desc_num == desc->desc_num) {
+ list_del(&vd->node);
+ vchan_cookie_complete(vd);
goto out;
+ }
- regmap_write(xdev->rmap, xchan->base + XDMA_CHAN_STATUS, st);
+ if (desc->completed_desc_num > desc->desc_num ||
+ complete_desc_num != XDMA_DESC_BLOCK_NUM * XDMA_DESC_ADJACENT)
+ goto out;
+ /* transfer the rest of data */
+ xdma_xfer_start(xchan);
+ } else {
+ desc->completed_desc_num = complete_desc_num;
vchan_cyclic_callback(vd);
- goto out;
- }
-
- /*
- * if all data blocks are transferred, remove and complete the request
- */
- if (desc->completed_desc_num == desc->desc_num) {
- list_del(&vd->node);
- vchan_cookie_complete(vd);
- goto out;
}
- if (desc->completed_desc_num > desc->desc_num ||
- complete_desc_num != XDMA_DESC_BLOCK_NUM * XDMA_DESC_ADJACENT)
- goto out;
-
- /* transfer the rest of data (SG only) */
- xdma_xfer_start(xchan);
-
out:
spin_unlock(&xchan->vchan.lock);
return IRQ_HANDLED;
@@ -1080,6 +1249,9 @@ static int xdma_probe(struct platform_device *pdev)
dma_cap_set(DMA_SLAVE, xdev->dma_dev.cap_mask);
dma_cap_set(DMA_PRIVATE, xdev->dma_dev.cap_mask);
dma_cap_set(DMA_CYCLIC, xdev->dma_dev.cap_mask);
+ dma_cap_set(DMA_INTERLEAVE, xdev->dma_dev.cap_mask);
+ dma_cap_set(DMA_REPEAT, xdev->dma_dev.cap_mask);
+ dma_cap_set(DMA_LOAD_EOT, xdev->dma_dev.cap_mask);
xdev->dma_dev.dev = &pdev->dev;
xdev->dma_dev.residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT;
@@ -1089,10 +1261,13 @@ static int xdma_probe(struct platform_device *pdev)
xdev->dma_dev.device_prep_slave_sg = xdma_prep_device_sg;
xdev->dma_dev.device_config = xdma_device_config;
xdev->dma_dev.device_issue_pending = xdma_issue_pending;
+ xdev->dma_dev.device_terminate_all = xdma_terminate_all;
+ xdev->dma_dev.device_synchronize = xdma_synchronize;
xdev->dma_dev.filter.map = pdata->device_map;
xdev->dma_dev.filter.mapcnt = pdata->device_map_cnt;
xdev->dma_dev.filter.fn = xdma_filter_fn;
xdev->dma_dev.device_prep_dma_cyclic = xdma_prep_dma_cyclic;
+ xdev->dma_dev.device_prep_interleaved_dma = xdma_prep_interleaved_dma;
ret = dma_async_device_register(&xdev->dma_dev);
if (ret) {
diff --git a/drivers/dma/xilinx/xilinx_dpdma.c b/drivers/dma/xilinx/xilinx_dpdma.c
index 69587d85a7cd20417b83be157aa4134784eae389..b82815e64d24e8352ac025bc1bd52de497530d66 100644
--- a/drivers/dma/xilinx/xilinx_dpdma.c
+++ b/drivers/dma/xilinx/xilinx_dpdma.c
@@ -309,7 +309,7 @@ static ssize_t xilinx_dpdma_debugfs_desc_done_irq_read(char *buf)
out_str_len = strlen(XILINX_DPDMA_DEBUGFS_UINT16_MAX_STR);
out_str_len = min_t(size_t, XILINX_DPDMA_DEBUGFS_READ_MAX_SIZE,
- out_str_len);
+ out_str_len + 1);
snprintf(buf, out_str_len, "%d",
dpdma_debugfs.xilinx_dpdma_irq_done_count);
diff --git a/drivers/dpll/dpll_core.c b/drivers/dpll/dpll_core.c
index 1eca8cc271f841e7b15967b2c33394169065b4ab..5152bd1b0daf599869195e81805fbb2709dbe6b4 100644
--- a/drivers/dpll/dpll_core.c
+++ b/drivers/dpll/dpll_core.c
@@ -29,8 +29,6 @@ static u32 dpll_pin_xa_id;
WARN_ON_ONCE(!xa_get_mark(&dpll_device_xa, (d)->id, DPLL_REGISTERED))
#define ASSERT_DPLL_NOT_REGISTERED(d) \
WARN_ON_ONCE(xa_get_mark(&dpll_device_xa, (d)->id, DPLL_REGISTERED))
-#define ASSERT_PIN_REGISTERED(p) \
- WARN_ON_ONCE(!xa_get_mark(&dpll_pin_xa, (p)->id, DPLL_REGISTERED))
struct dpll_device_registration {
struct list_head list;
@@ -425,6 +423,53 @@ void dpll_device_unregister(struct dpll_device *dpll,
}
EXPORT_SYMBOL_GPL(dpll_device_unregister);
+static void dpll_pin_prop_free(struct dpll_pin_properties *prop)
+{
+ kfree(prop->package_label);
+ kfree(prop->panel_label);
+ kfree(prop->board_label);
+ kfree(prop->freq_supported);
+}
+
+static int dpll_pin_prop_dup(const struct dpll_pin_properties *src,
+ struct dpll_pin_properties *dst)
+{
+ memcpy(dst, src, sizeof(*dst));
+ if (src->freq_supported && src->freq_supported_num) {
+ size_t freq_size = src->freq_supported_num *
+ sizeof(*src->freq_supported);
+ dst->freq_supported = kmemdup(src->freq_supported,
+ freq_size, GFP_KERNEL);
+ if (!src->freq_supported)
+ return -ENOMEM;
+ }
+ if (src->board_label) {
+ dst->board_label = kstrdup(src->board_label, GFP_KERNEL);
+ if (!dst->board_label)
+ goto err_board_label;
+ }
+ if (src->panel_label) {
+ dst->panel_label = kstrdup(src->panel_label, GFP_KERNEL);
+ if (!dst->panel_label)
+ goto err_panel_label;
+ }
+ if (src->package_label) {
+ dst->package_label = kstrdup(src->package_label, GFP_KERNEL);
+ if (!dst->package_label)
+ goto err_package_label;
+ }
+
+ return 0;
+
+err_package_label:
+ kfree(dst->panel_label);
+err_panel_label:
+ kfree(dst->board_label);
+err_board_label:
+ kfree(dst->freq_supported);
+ return -ENOMEM;
+}
+
static struct dpll_pin *
dpll_pin_alloc(u64 clock_id, u32 pin_idx, struct module *module,
const struct dpll_pin_properties *prop)
@@ -441,20 +486,24 @@ dpll_pin_alloc(u64 clock_id, u32 pin_idx, struct module *module,
if (WARN_ON(prop->type < DPLL_PIN_TYPE_MUX ||
prop->type > DPLL_PIN_TYPE_MAX)) {
ret = -EINVAL;
- goto err;
+ goto err_pin_prop;
}
- pin->prop = prop;
+ ret = dpll_pin_prop_dup(prop, &pin->prop);
+ if (ret)
+ goto err_pin_prop;
refcount_set(&pin->refcount, 1);
xa_init_flags(&pin->dpll_refs, XA_FLAGS_ALLOC);
xa_init_flags(&pin->parent_refs, XA_FLAGS_ALLOC);
ret = xa_alloc_cyclic(&dpll_pin_xa, &pin->id, pin, xa_limit_32b,
&dpll_pin_xa_id, GFP_KERNEL);
if (ret)
- goto err;
+ goto err_xa_alloc;
return pin;
-err:
+err_xa_alloc:
xa_destroy(&pin->dpll_refs);
xa_destroy(&pin->parent_refs);
+ dpll_pin_prop_free(&pin->prop);
+err_pin_prop:
kfree(pin);
return ERR_PTR(ret);
}
@@ -514,6 +563,7 @@ void dpll_pin_put(struct dpll_pin *pin)
xa_destroy(&pin->dpll_refs);
xa_destroy(&pin->parent_refs);
xa_erase(&dpll_pin_xa, pin->id);
+ dpll_pin_prop_free(&pin->prop);
kfree(pin);
}
mutex_unlock(&dpll_lock);
@@ -564,8 +614,6 @@ dpll_pin_register(struct dpll_device *dpll, struct dpll_pin *pin,
WARN_ON(!ops->state_on_dpll_get) ||
WARN_ON(!ops->direction_get))
return -EINVAL;
- if (ASSERT_DPLL_REGISTERED(dpll))
- return -EINVAL;
mutex_lock(&dpll_lock);
if (WARN_ON(!(dpll->module == pin->module &&
@@ -636,15 +684,13 @@ int dpll_pin_on_pin_register(struct dpll_pin *parent, struct dpll_pin *pin,
unsigned long i, stop;
int ret;
- if (WARN_ON(parent->prop->type != DPLL_PIN_TYPE_MUX))
+ if (WARN_ON(parent->prop.type != DPLL_PIN_TYPE_MUX))
return -EINVAL;
if (WARN_ON(!ops) ||
WARN_ON(!ops->state_on_pin_get) ||
WARN_ON(!ops->direction_get))
return -EINVAL;
- if (ASSERT_PIN_REGISTERED(parent))
- return -EINVAL;
mutex_lock(&dpll_lock);
ret = dpll_xa_ref_pin_add(&pin->parent_refs, parent, ops, priv);
diff --git a/drivers/dpll/dpll_core.h b/drivers/dpll/dpll_core.h
index 5585873c5c1b020e5618896aaa43ff1656ff53dd..717f715015c742238d5585fddc5cd267fbb0db9f 100644
--- a/drivers/dpll/dpll_core.h
+++ b/drivers/dpll/dpll_core.h
@@ -44,7 +44,7 @@ struct dpll_device {
* @module: module of creator
* @dpll_refs: hold referencees to dplls pin was registered with
* @parent_refs: hold references to parent pins pin was registered with
- * @prop: pointer to pin properties given by registerer
+ * @prop: pin properties copied from the registerer
* @rclk_dev_name: holds name of device when pin can recover clock from it
* @refcount: refcount
**/
@@ -55,7 +55,7 @@ struct dpll_pin {
struct module *module;
struct xarray dpll_refs;
struct xarray parent_refs;
- const struct dpll_pin_properties *prop;
+ struct dpll_pin_properties prop;
refcount_t refcount;
};
diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c
index 3370dbddb86bdeb6b627fdf741357eeb15ee3676..314bb377546519ef25987b2e6f77827f590fe5fe 100644
--- a/drivers/dpll/dpll_netlink.c
+++ b/drivers/dpll/dpll_netlink.c
@@ -303,17 +303,17 @@ dpll_msg_add_pin_freq(struct sk_buff *msg, struct dpll_pin *pin,
if (nla_put_64bit(msg, DPLL_A_PIN_FREQUENCY, sizeof(freq), &freq,
DPLL_A_PIN_PAD))
return -EMSGSIZE;
- for (fs = 0; fs < pin->prop->freq_supported_num; fs++) {
+ for (fs = 0; fs < pin->prop.freq_supported_num; fs++) {
nest = nla_nest_start(msg, DPLL_A_PIN_FREQUENCY_SUPPORTED);
if (!nest)
return -EMSGSIZE;
- freq = pin->prop->freq_supported[fs].min;
+ freq = pin->prop.freq_supported[fs].min;
if (nla_put_64bit(msg, DPLL_A_PIN_FREQUENCY_MIN, sizeof(freq),
&freq, DPLL_A_PIN_PAD)) {
nla_nest_cancel(msg, nest);
return -EMSGSIZE;
}
- freq = pin->prop->freq_supported[fs].max;
+ freq = pin->prop.freq_supported[fs].max;
if (nla_put_64bit(msg, DPLL_A_PIN_FREQUENCY_MAX, sizeof(freq),
&freq, DPLL_A_PIN_PAD)) {
nla_nest_cancel(msg, nest);
@@ -329,9 +329,9 @@ static bool dpll_pin_is_freq_supported(struct dpll_pin *pin, u32 freq)
{
int fs;
- for (fs = 0; fs < pin->prop->freq_supported_num; fs++)
- if (freq >= pin->prop->freq_supported[fs].min &&
- freq <= pin->prop->freq_supported[fs].max)
+ for (fs = 0; fs < pin->prop.freq_supported_num; fs++)
+ if (freq >= pin->prop.freq_supported[fs].min &&
+ freq <= pin->prop.freq_supported[fs].max)
return true;
return false;
}
@@ -421,7 +421,7 @@ static int
dpll_cmd_pin_get_one(struct sk_buff *msg, struct dpll_pin *pin,
struct netlink_ext_ack *extack)
{
- const struct dpll_pin_properties *prop = pin->prop;
+ const struct dpll_pin_properties *prop = &pin->prop;
struct dpll_pin_ref *ref;
int ret;
@@ -553,6 +553,24 @@ __dpll_device_change_ntf(struct dpll_device *dpll)
return dpll_device_event_send(DPLL_CMD_DEVICE_CHANGE_NTF, dpll);
}
+static bool dpll_pin_available(struct dpll_pin *pin)
+{
+ struct dpll_pin_ref *par_ref;
+ unsigned long i;
+
+ if (!xa_get_mark(&dpll_pin_xa, pin->id, DPLL_REGISTERED))
+ return false;
+ xa_for_each(&pin->parent_refs, i, par_ref)
+ if (xa_get_mark(&dpll_pin_xa, par_ref->pin->id,
+ DPLL_REGISTERED))
+ return true;
+ xa_for_each(&pin->dpll_refs, i, par_ref)
+ if (xa_get_mark(&dpll_device_xa, par_ref->dpll->id,
+ DPLL_REGISTERED))
+ return true;
+ return false;
+}
+
/**
* dpll_device_change_ntf - notify that the dpll device has been changed
* @dpll: registered dpll pointer
@@ -579,7 +597,7 @@ dpll_pin_event_send(enum dpll_cmd event, struct dpll_pin *pin)
int ret = -ENOMEM;
void *hdr;
- if (WARN_ON(!xa_get_mark(&dpll_pin_xa, pin->id, DPLL_REGISTERED)))
+ if (!dpll_pin_available(pin))
return -ENODEV;
msg = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
@@ -717,7 +735,7 @@ dpll_pin_on_pin_state_set(struct dpll_pin *pin, u32 parent_idx,
int ret;
if (!(DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE &
- pin->prop->capabilities)) {
+ pin->prop.capabilities)) {
NL_SET_ERR_MSG(extack, "state changing is not allowed");
return -EOPNOTSUPP;
}
@@ -753,7 +771,7 @@ dpll_pin_state_set(struct dpll_device *dpll, struct dpll_pin *pin,
int ret;
if (!(DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE &
- pin->prop->capabilities)) {
+ pin->prop.capabilities)) {
NL_SET_ERR_MSG(extack, "state changing is not allowed");
return -EOPNOTSUPP;
}
@@ -780,7 +798,7 @@ dpll_pin_prio_set(struct dpll_device *dpll, struct dpll_pin *pin,
int ret;
if (!(DPLL_PIN_CAPABILITIES_PRIORITY_CAN_CHANGE &
- pin->prop->capabilities)) {
+ pin->prop.capabilities)) {
NL_SET_ERR_MSG(extack, "prio changing is not allowed");
return -EOPNOTSUPP;
}
@@ -808,7 +826,7 @@ dpll_pin_direction_set(struct dpll_pin *pin, struct dpll_device *dpll,
int ret;
if (!(DPLL_PIN_CAPABILITIES_DIRECTION_CAN_CHANGE &
- pin->prop->capabilities)) {
+ pin->prop.capabilities)) {
NL_SET_ERR_MSG(extack, "direction changing is not allowed");
return -EOPNOTSUPP;
}
@@ -838,8 +856,8 @@ dpll_pin_phase_adj_set(struct dpll_pin *pin, struct nlattr *phase_adj_attr,
int ret;
phase_adj = nla_get_s32(phase_adj_attr);
- if (phase_adj > pin->prop->phase_range.max ||
- phase_adj < pin->prop->phase_range.min) {
+ if (phase_adj > pin->prop.phase_range.max ||
+ phase_adj < pin->prop.phase_range.min) {
NL_SET_ERR_MSG_ATTR(extack, phase_adj_attr,
"phase adjust value not supported");
return -EINVAL;
@@ -1023,7 +1041,7 @@ dpll_pin_find(u64 clock_id, struct nlattr *mod_name_attr,
unsigned long i;
xa_for_each_marked(&dpll_pin_xa, i, pin, DPLL_REGISTERED) {
- prop = pin->prop;
+ prop = &pin->prop;
cid_match = clock_id ? pin->clock_id == clock_id : true;
mod_match = mod_name_attr && module_name(pin->module) ?
!nla_strcmp(mod_name_attr,
@@ -1130,6 +1148,10 @@ int dpll_nl_pin_id_get_doit(struct sk_buff *skb, struct genl_info *info)
}
pin = dpll_pin_find_from_nlattr(info);
if (!IS_ERR(pin)) {
+ if (!dpll_pin_available(pin)) {
+ nlmsg_free(msg);
+ return -ENODEV;
+ }
ret = dpll_msg_add_pin_handle(msg, pin);
if (ret) {
nlmsg_free(msg);
@@ -1179,6 +1201,8 @@ int dpll_nl_pin_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
xa_for_each_marked_start(&dpll_pin_xa, i, pin, DPLL_REGISTERED,
ctx->idx) {
+ if (!dpll_pin_available(pin))
+ continue;
hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
&dpll_nl_family, NLM_F_MULTI,
@@ -1441,7 +1465,8 @@ int dpll_pin_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
}
info->user_ptr[0] = xa_load(&dpll_pin_xa,
nla_get_u32(info->attrs[DPLL_A_PIN_ID]));
- if (!info->user_ptr[0]) {
+ if (!info->user_ptr[0] ||
+ !dpll_pin_available(info->user_ptr[0])) {
NL_SET_ERR_MSG(info->extack, "pin not found");
ret = -ENODEV;
goto unlock_dev;
diff --git a/drivers/firmware/sysfb.c b/drivers/firmware/sysfb.c
index 19706bd2642adbec408cbba3bf8cf8bda4b51a6f..82fcfd29bc4d29116b051c946edb9b6535fd78ac 100644
--- a/drivers/firmware/sysfb.c
+++ b/drivers/firmware/sysfb.c
@@ -71,7 +71,7 @@ EXPORT_SYMBOL_GPL(sysfb_disable);
static __init int sysfb_init(void)
{
- const struct screen_info *si = &screen_info;
+ struct screen_info *si = &screen_info;
struct simplefb_platform_data mode;
const char *name;
bool compatible;
@@ -119,18 +119,6 @@ static __init int sysfb_init(void)
if (ret)
goto err;
- /*
- * The firmware framebuffer is now maintained by the created
- * device. Disable screen_info after we've consumed it. Prevents
- * invalid access during kexec reboots.
- *
- * TODO: Vgacon still relies on the global screen_info. Make
- * vgacon work with the platform device, so we can clear
- * the screen_info unconditionally.
- */
- if (strcmp(name, "platform-framebuffer"))
- screen_info.orig_video_isVGA = 0;
-
goto unlock_mutex;
err:
platform_device_put(pd);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 9da14436a3738f8b950db3aa44a71b47c6e4952c..3d8a48f46b015613dc44517ebd20d5250df5a3b1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -254,8 +254,6 @@ extern int amdgpu_agp;
extern int amdgpu_wbrf;
-extern int fw_bo_location;
-
#define AMDGPU_VM_MAX_NUM_CTX 4096
#define AMDGPU_SG_THRESHOLD (256*1024*1024)
#define AMDGPU_WAIT_IDLE_TIMEOUT_IN_MS 3000
@@ -1146,6 +1144,7 @@ struct amdgpu_device {
bool debug_vm;
bool debug_largebar;
bool debug_disable_soft_recovery;
+ bool debug_use_vram_fw_buf;
};
static inline uint32_t amdgpu_ip_version(const struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 067690ba7bffd4192817fe3acf9d46a19f1f274c..77e2636602887034c188ec695591d20e5b087b60 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -138,6 +138,9 @@ static void amdgpu_amdkfd_reset_work(struct work_struct *work)
amdgpu_device_gpu_recover(adev, NULL, &reset_context);
}
+static const struct drm_client_funcs kfd_client_funcs = {
+ .unregister = drm_client_release,
+};
void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
{
int i;
@@ -161,7 +164,7 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
.enable_mes = adev->enable_mes,
};
- ret = drm_client_init(&adev->ddev, &adev->kfd.client, "kfd", NULL);
+ ret = drm_client_init(&adev->ddev, &adev->kfd.client, "kfd", &kfd_client_funcs);
if (ret) {
dev_err(adev->dev, "Failed to init DRM client: %d\n", ret);
return;
@@ -695,10 +698,8 @@ int amdgpu_amdkfd_submit_ib(struct amdgpu_device *adev,
void amdgpu_amdkfd_set_compute_idle(struct amdgpu_device *adev, bool idle)
{
enum amd_powergating_state state = idle ? AMD_PG_STATE_GATE : AMD_PG_STATE_UNGATE;
- /* Temporary workaround to fix issues observed in some
- * compute applications when GFXOFF is enabled on GFX11.
- */
- if (IP_VERSION_MAJ(amdgpu_ip_version(adev, GC_HWIP, 0)) == 11) {
+ if (IP_VERSION_MAJ(amdgpu_ip_version(adev, GC_HWIP, 0)) == 11 &&
+ ((adev->mes.kiq_version & AMDGPU_MES_VERSION_MASK) <= 64)) {
pr_debug("GFXOFF is %s\n", idle ? "enabled" : "disabled");
amdgpu_gfx_off_ctrl(adev, idle);
} else if ((IP_VERSION_MAJ(amdgpu_ip_version(adev, GC_HWIP, 0)) == 9) &&
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index cf6ed5fce291f946854d329fa91e0fb6eedbc61a..f262b9d89541a8a971a394b5f0da0f6a1368ba65 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -311,7 +311,7 @@ void amdgpu_amdkfd_gpuvm_unmap_gtt_bo_from_kernel(struct kgd_mem *mem);
int amdgpu_amdkfd_map_gtt_bo_to_gart(struct amdgpu_device *adev, struct amdgpu_bo *bo);
int amdgpu_amdkfd_gpuvm_restore_process_bos(void *process_info,
- struct dma_fence **ef);
+ struct dma_fence __rcu **ef);
int amdgpu_amdkfd_gpuvm_get_vm_fault_info(struct amdgpu_device *adev,
struct kfd_vm_fault_info *info);
int amdgpu_amdkfd_gpuvm_import_dmabuf_fd(struct amdgpu_device *adev, int fd,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index d17b2452cb1f69df276dd95518cf0ca340539237..f183d7faeeece16cfc7c211f5a6a0232dce37c36 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -2802,7 +2802,7 @@ static void amdgpu_amdkfd_restore_userptr_worker(struct work_struct *work)
put_task_struct(usertask);
}
-static void replace_eviction_fence(struct dma_fence **ef,
+static void replace_eviction_fence(struct dma_fence __rcu **ef,
struct dma_fence *new_ef)
{
struct dma_fence *old_ef = rcu_replace_pointer(*ef, new_ef, true
@@ -2837,7 +2837,7 @@ static void replace_eviction_fence(struct dma_fence **ef,
* 7. Add fence to all PD and PT BOs.
* 8. Unreserve all BOs
*/
-int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef)
+int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu **ef)
{
struct amdkfd_process_info *process_info = info;
struct amdgpu_vm *peer_vm;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 5bb444bb36cece19b00fe27f0923c42b1bc1c83f..b158d27d0a71cbbafb55f0d58657c1ec178fa6c2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1544,6 +1544,7 @@ bool amdgpu_device_need_post(struct amdgpu_device *adev)
return true;
fw_ver = *((uint32_t *)adev->pm.fw->data + 69);
+ release_firmware(adev->pm.fw);
if (fw_ver < 0x00160e00)
return true;
}
@@ -5245,7 +5246,6 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle,
struct amdgpu_device *tmp_adev = NULL;
bool need_full_reset, skip_hw_reset, vram_lost = false;
int r = 0;
- bool gpu_reset_for_dev_remove = 0;
/* Try reset handler method first */
tmp_adev = list_first_entry(device_list_handle, struct amdgpu_device,
@@ -5265,10 +5265,6 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle,
test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags);
skip_hw_reset = test_bit(AMDGPU_SKIP_HW_RESET, &reset_context->flags);
- gpu_reset_for_dev_remove =
- test_bit(AMDGPU_RESET_FOR_DEVICE_REMOVE, &reset_context->flags) &&
- test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags);
-
/*
* ASIC reset has to be done on all XGMI hive nodes ASAP
* to allow proper links negotiation in FW (within 1 sec)
@@ -5311,18 +5307,6 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle,
amdgpu_ras_intr_cleared();
}
- /* Since the mode1 reset affects base ip blocks, the
- * phase1 ip blocks need to be resumed. Otherwise there
- * will be a BIOS signature error and the psp bootloader
- * can't load kdb on the next amdgpu install.
- */
- if (gpu_reset_for_dev_remove) {
- list_for_each_entry(tmp_adev, device_list_handle, reset_list)
- amdgpu_device_ip_resume_phase1(tmp_adev);
-
- goto end;
- }
-
list_for_each_entry(tmp_adev, device_list_handle, reset_list) {
if (need_full_reset) {
/* post card */
@@ -5559,11 +5543,6 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
int i, r = 0;
bool need_emergency_restart = false;
bool audio_suspended = false;
- bool gpu_reset_for_dev_remove = false;
-
- gpu_reset_for_dev_remove =
- test_bit(AMDGPU_RESET_FOR_DEVICE_REMOVE, &reset_context->flags) &&
- test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags);
/*
* Special case: RAS triggered and full reset isn't supported
@@ -5601,7 +5580,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
if (!amdgpu_sriov_vf(adev) && (adev->gmc.xgmi.num_physical_nodes > 1)) {
list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) {
list_add_tail(&tmp_adev->reset_list, &device_list);
- if (gpu_reset_for_dev_remove && adev->shutdown)
+ if (adev->shutdown)
tmp_adev->shutdown = true;
}
if (!list_is_first(&adev->reset_list, &device_list))
@@ -5686,10 +5665,6 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
retry: /* Rest of adevs pre asic reset from XGMI hive. */
list_for_each_entry(tmp_adev, device_list_handle, reset_list) {
- if (gpu_reset_for_dev_remove) {
- /* Workaroud for ASICs need to disable SMC first */
- amdgpu_device_smu_fini_early(tmp_adev);
- }
r = amdgpu_device_pre_asic_reset(tmp_adev, reset_context);
/*TODO Should we stop ?*/
if (r) {
@@ -5721,9 +5696,6 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
r = amdgpu_do_asic_reset(device_list_handle, reset_context);
if (r && r == -EAGAIN)
goto retry;
-
- if (!r && gpu_reset_for_dev_remove)
- goto recover_end;
}
skip_hw_reset:
@@ -5779,7 +5751,6 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
amdgpu_ras_set_error_query_ready(tmp_adev, true);
}
-recover_end:
tmp_adev = list_first_entry(device_list_handle, struct amdgpu_device,
reset_list);
amdgpu_device_unlock_reset_domain(tmp_adev->reset_domain);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index 0431eafa86b5324f4d63cc6060cea30baa03088b..c7d60dd0fb975d47d749300c79f976da15892736 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -1963,8 +1963,6 @@ static int amdgpu_discovery_set_gc_ip_blocks(struct amdgpu_device *adev)
amdgpu_device_ip_block_add(adev, &gfx_v9_0_ip_block);
break;
case IP_VERSION(9, 4, 3):
- if (!amdgpu_exp_hw_support)
- return -EINVAL;
amdgpu_device_ip_block_add(adev, &gfx_v9_4_3_ip_block);
break;
case IP_VERSION(10, 1, 10):
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 852cec98ff262359fb823ccb26f1b9977da8dec9..cc69005f5b46e7b9f06d65db13287a617cc384e2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -128,6 +128,7 @@ enum AMDGPU_DEBUG_MASK {
AMDGPU_DEBUG_VM = BIT(0),
AMDGPU_DEBUG_LARGEBAR = BIT(1),
AMDGPU_DEBUG_DISABLE_GPU_SOFT_RECOVERY = BIT(2),
+ AMDGPU_DEBUG_USE_VRAM_FW_BUF = BIT(3),
};
unsigned int amdgpu_vram_limit = UINT_MAX;
@@ -210,7 +211,6 @@ int amdgpu_seamless = -1; /* auto */
uint amdgpu_debug_mask;
int amdgpu_agp = -1; /* auto */
int amdgpu_wbrf = -1;
-int fw_bo_location = -1;
static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work);
@@ -990,10 +990,6 @@ MODULE_PARM_DESC(wbrf,
"Enable Wifi RFI interference mitigation (0 = disabled, 1 = enabled, -1 = auto(default)");
module_param_named(wbrf, amdgpu_wbrf, int, 0444);
-MODULE_PARM_DESC(fw_bo_location,
- "location to put firmware bo for frontdoor loading (-1 = auto (default), 0 = on ram, 1 = on vram");
-module_param(fw_bo_location, int, 0644);
-
/* These devices are not supported by amdgpu.
* They are supported by the mach64, r128, radeon drivers
*/
@@ -2122,6 +2118,11 @@ static void amdgpu_init_debug_options(struct amdgpu_device *adev)
pr_info("debug: soft reset for GPU recovery disabled\n");
adev->debug_disable_soft_recovery = true;
}
+
+ if (amdgpu_debug_mask & AMDGPU_DEBUG_USE_VRAM_FW_BUF) {
+ pr_info("debug: place fw in vram for frontdoor loading\n");
+ adev->debug_use_vram_fw_buf = true;
+ }
}
static unsigned long amdgpu_fix_asic_type(struct pci_dev *pdev, unsigned long flags)
@@ -2233,6 +2234,8 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
pci_set_drvdata(pdev, ddev);
+ amdgpu_init_debug_options(adev);
+
ret = amdgpu_driver_load_kms(adev, flags);
if (ret)
goto err_pci;
@@ -2313,8 +2316,6 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
amdgpu_get_secondary_funcs(adev);
}
- amdgpu_init_debug_options(adev);
-
return 0;
err_pci:
@@ -2336,38 +2337,6 @@ amdgpu_pci_remove(struct pci_dev *pdev)
pm_runtime_forbid(dev->dev);
}
- if (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 2) &&
- !amdgpu_sriov_vf(adev)) {
- bool need_to_reset_gpu = false;
-
- if (adev->gmc.xgmi.num_physical_nodes > 1) {
- struct amdgpu_hive_info *hive;
-
- hive = amdgpu_get_xgmi_hive(adev);
- if (hive->device_remove_count == 0)
- need_to_reset_gpu = true;
- hive->device_remove_count++;
- amdgpu_put_xgmi_hive(hive);
- } else {
- need_to_reset_gpu = true;
- }
-
- /* Workaround for ASICs need to reset SMU.
- * Called only when the first device is removed.
- */
- if (need_to_reset_gpu) {
- struct amdgpu_reset_context reset_context;
-
- adev->shutdown = true;
- memset(&reset_context, 0, sizeof(reset_context));
- reset_context.method = AMD_RESET_METHOD_NONE;
- reset_context.reset_req_dev = adev;
- set_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
- set_bit(AMDGPU_RESET_FOR_DEVICE_REMOVE, &reset_context.flags);
- amdgpu_device_gpu_recover(adev, NULL, &reset_context);
- }
- }
-
amdgpu_driver_unload_kms(dev);
/*
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index d2f273d77e59557ba5185cbfa36e243788d3d86e..55784a9f26c4c83b17008a766130c234df8ecbaf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -1045,21 +1045,28 @@ int amdgpu_gmc_vram_checking(struct amdgpu_device *adev)
* seconds, so here, we just pick up three parts for emulation.
*/
ret = memcmp(vram_ptr, cptr, 10);
- if (ret)
- return ret;
+ if (ret) {
+ ret = -EIO;
+ goto release_buffer;
+ }
ret = memcmp(vram_ptr + (size / 2), cptr, 10);
- if (ret)
- return ret;
+ if (ret) {
+ ret = -EIO;
+ goto release_buffer;
+ }
ret = memcmp(vram_ptr + size - 10, cptr, 10);
- if (ret)
- return ret;
+ if (ret) {
+ ret = -EIO;
+ goto release_buffer;
+ }
+release_buffer:
amdgpu_bo_free_kernel(&vram_bo, &vram_gpu,
&vram_ptr);
- return 0;
+ return ret;
}
static ssize_t current_memory_partition_show(
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index b5ebafd4a3adf82e37b29f9df84cbf6541955441..bf4f48fe438d1b5936852145c8b4c1059446381c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -1105,7 +1105,12 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
if (amdgpu_dpm_read_sensor(adev,
AMDGPU_PP_SENSOR_GPU_AVG_POWER,
(void *)&ui32, &ui32_size)) {
- return -EINVAL;
+ /* fall back to input power for backwards compat */
+ if (amdgpu_dpm_read_sensor(adev,
+ AMDGPU_PP_SENSOR_GPU_INPUT_POWER,
+ (void *)&ui32, &ui32_size)) {
+ return -EINVAL;
+ }
}
ui32 >>= 8;
break;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 2addbdf88394b8287b0ea9fb87297b3435e826fb..0328616473f80af861cd4a1176afc0221eee7db9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -466,7 +466,7 @@ static int psp_sw_init(void *handle)
}
ret = amdgpu_bo_create_kernel(adev, PSP_1_MEG, PSP_1_MEG,
- (amdgpu_sriov_vf(adev) || fw_bo_location == 1) ?
+ (amdgpu_sriov_vf(adev) || adev->debug_use_vram_fw_buf) ?
AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT,
&psp->fw_pri_bo,
&psp->fw_pri_mc_addr,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index fc42fb6ee1914b82e0bec3897cf92594f587423f..31823a30dea217b5af3a8a36624a01fab70b48a5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -305,11 +305,13 @@ static int amdgpu_ras_debugfs_ctrl_parse_data(struct file *f,
return -EINVAL;
data->head.block = block_id;
- /* only ue and ce errors are supported */
+ /* only ue, ce and poison errors are supported */
if (!memcmp("ue", err, 2))
data->head.type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
else if (!memcmp("ce", err, 2))
data->head.type = AMDGPU_RAS_ERROR__SINGLE_CORRECTABLE;
+ else if (!memcmp("poison", err, 6))
+ data->head.type = AMDGPU_RAS_ERROR__POISON;
else
return -EINVAL;
@@ -431,9 +433,10 @@ static void amdgpu_ras_instance_mask_check(struct amdgpu_device *adev,
* The block is one of: umc, sdma, gfx, etc.
* see ras_block_string[] for details
*
- * The error type is one of: ue, ce, where,
+ * The error type is one of: ue, ce and poison where,
* ue is multi-uncorrectable
* ce is single-correctable
+ * poison is poison
*
* The sub-block is a the sub-block index, pass 0 if there is no sub-block.
* The address and value are hexadecimal numbers, leading 0x is optional.
@@ -1067,8 +1070,7 @@ static void amdgpu_ras_error_print_error_data(struct amdgpu_device *adev,
mcm_info = &err_info->mcm_info;
if (err_info->ce_count) {
dev_info(adev->dev, "socket: %d, die: %d, "
- "%lld new correctable hardware errors detected in %s block, "
- "no user action is needed\n",
+ "%lld new correctable hardware errors detected in %s block\n",
mcm_info->socket_id,
mcm_info->die_id,
err_info->ce_count,
@@ -1080,8 +1082,7 @@ static void amdgpu_ras_error_print_error_data(struct amdgpu_device *adev,
err_info = &err_node->err_info;
mcm_info = &err_info->mcm_info;
dev_info(adev->dev, "socket: %d, die: %d, "
- "%lld correctable hardware errors detected in total in %s block, "
- "no user action is needed\n",
+ "%lld correctable hardware errors detected in total in %s block\n",
mcm_info->socket_id, mcm_info->die_id, err_info->ce_count, blk_name);
}
}
@@ -1108,16 +1109,14 @@ static void amdgpu_ras_error_generate_report(struct amdgpu_device *adev,
adev->smuio.funcs->get_die_id) {
dev_info(adev->dev, "socket: %d, die: %d "
"%ld correctable hardware errors "
- "detected in %s block, no user "
- "action is needed.\n",
+ "detected in %s block\n",
adev->smuio.funcs->get_socket_id(adev),
adev->smuio.funcs->get_die_id(adev),
ras_mgr->err_data.ce_count,
blk_name);
} else {
dev_info(adev->dev, "%ld correctable hardware errors "
- "detected in %s block, no user "
- "action is needed.\n",
+ "detected in %s block\n",
ras_mgr->err_data.ce_count,
blk_name);
}
@@ -1920,7 +1919,7 @@ static void amdgpu_ras_interrupt_poison_creation_handler(struct ras_manager *obj
struct amdgpu_iv_entry *entry)
{
dev_info(obj->adev->dev,
- "Poison is created, no user action is needed.\n");
+ "Poison is created\n");
}
static void amdgpu_ras_interrupt_umc_handler(struct ras_manager *obj,
@@ -2920,6 +2919,11 @@ int amdgpu_ras_init(struct amdgpu_device *adev)
amdgpu_ras_query_poison_mode(adev);
+ /* Packed socket_id to ras feature mask bits[31:29] */
+ if (adev->smuio.funcs &&
+ adev->smuio.funcs->get_socket_id)
+ con->features |= ((adev->smuio.funcs->get_socket_id(adev)) << 29);
+
/* Get RAS schema for particular SOC */
con->schema = amdgpu_get_ras_schema(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
index b0335a1c5e90cb8f000fe1989bfb20dfbbd53c58..19899f6b9b2b419a0fdf2ed84c71f0278963f511 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
@@ -32,7 +32,6 @@ enum AMDGPU_RESET_FLAGS {
AMDGPU_NEED_FULL_RESET = 0,
AMDGPU_SKIP_HW_RESET = 1,
- AMDGPU_RESET_FOR_DEVICE_REMOVE = 2,
};
struct amdgpu_reset_context {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
index d334e42fe0ebe648e3efafb3970f650b615f716d..3e12763e477aa45724d0c16a1b514a5a299a76a9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
@@ -1062,7 +1062,7 @@ int amdgpu_ucode_create_bo(struct amdgpu_device *adev)
{
if (adev->firmware.load_type != AMDGPU_FW_LOAD_DIRECT) {
amdgpu_bo_create_kernel(adev, adev->firmware.fw_size, PAGE_SIZE,
- (amdgpu_sriov_vf(adev) || fw_bo_location == 1) ?
+ (amdgpu_sriov_vf(adev) || adev->debug_use_vram_fw_buf) ?
AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT,
&adev->firmware.fw_buf,
&adev->firmware.fw_buf_mc,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index b6cd565562ad8d9a99270757fc2b37352600d2f3..4740dd65b99d6ccc107e5d63aba0f0d67d02d718 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -116,7 +116,7 @@ struct amdgpu_mem_stats;
#define AMDGPU_VM_FAULT_STOP_FIRST 1
#define AMDGPU_VM_FAULT_STOP_ALWAYS 2
-/* Reserve 4MB VRAM for page tables */
+/* How much VRAM be reserved for page tables */
#define AMDGPU_VM_RESERVED_VRAM (8ULL << 20)
/*
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
index 6f149b54d4d3970c5fe0a8255f8f7a080433381a..b9a15d51eb5c30e554d4e4f7c1397e3ce51996d9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
@@ -59,11 +59,8 @@ static inline uint16_t complete_integer_division_u16(
static uint16_t vpe_u1_8_from_fraction(uint16_t numerator, uint16_t denominator)
{
- bool arg1_negative = numerator < 0;
- bool arg2_negative = denominator < 0;
-
- uint16_t arg1_value = (uint16_t)(arg1_negative ? -numerator : numerator);
- uint16_t arg2_value = (uint16_t)(arg2_negative ? -denominator : denominator);
+ u16 arg1_value = numerator;
+ u16 arg2_value = denominator;
uint16_t remainder;
@@ -100,9 +97,6 @@ static uint16_t vpe_u1_8_from_fraction(uint16_t numerator, uint16_t denominator)
res_value += summand;
}
- if (arg1_negative ^ arg2_negative)
- res_value = -res_value;
-
return res_value;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
index 6cab882e8061e80f33bca5eb1a7b59d8cf0a687f..1592c63b3099b982d0b9bdda596919da8ec14f5f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
@@ -43,7 +43,6 @@ struct amdgpu_hive_info {
} pstate;
struct amdgpu_reset_domain *reset_domain;
- uint32_t device_remove_count;
atomic_t ras_recovery;
};
diff --git a/drivers/gpu/drm/amd/amdgpu/athub_v3_0.c b/drivers/gpu/drm/amd/amdgpu/athub_v3_0.c
index f0737fb3a999e03a44eb3c08f6e0099e3326c929..d1bba9c64e16d808fbaafd4e01d8764cb77b1a86 100644
--- a/drivers/gpu/drm/amd/amdgpu/athub_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/athub_v3_0.c
@@ -30,6 +30,8 @@
#define regATHUB_MISC_CNTL_V3_0_1 0x00d7
#define regATHUB_MISC_CNTL_V3_0_1_BASE_IDX 0
+#define regATHUB_MISC_CNTL_V3_3_0 0x00d8
+#define regATHUB_MISC_CNTL_V3_3_0_BASE_IDX 0
static uint32_t athub_v3_0_get_cg_cntl(struct amdgpu_device *adev)
@@ -40,6 +42,9 @@ static uint32_t athub_v3_0_get_cg_cntl(struct amdgpu_device *adev)
case IP_VERSION(3, 0, 1):
data = RREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL_V3_0_1);
break;
+ case IP_VERSION(3, 3, 0):
+ data = RREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL_V3_3_0);
+ break;
default:
data = RREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL);
break;
@@ -53,6 +58,9 @@ static void athub_v3_0_set_cg_cntl(struct amdgpu_device *adev, uint32_t data)
case IP_VERSION(3, 0, 1):
WREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL_V3_0_1, data);
break;
+ case IP_VERSION(3, 3, 0):
+ WREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL_V3_3_0, data);
+ break;
default:
WREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL, data);
break;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 73f6d7e72c737537f17264746b061a936b4960e5..d63cab294883b8b44caa908d5bafaeaf19750ef6 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -3996,16 +3996,13 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
if (!amdgpu_sriov_vf(adev)) {
snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", ucode_prefix);
- err = amdgpu_ucode_request(adev, &adev->gfx.rlc_fw, fw_name);
- /* don't check this. There are apparently firmwares in the wild with
- * incorrect size in the header
- */
- if (err == -ENODEV)
- goto out;
+ err = request_firmware(&adev->gfx.rlc_fw, fw_name, adev->dev);
if (err)
- dev_dbg(adev->dev,
- "gfx10: amdgpu_ucode_request() failed \"%s\"\n",
- fw_name);
+ goto out;
+
+ /* don't validate this firmware. There are apparently firmwares
+ * in the wild with incorrect size in the header
+ */
rlc_hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data;
version_major = le16_to_cpu(rlc_hdr->header.header_version_major);
version_minor = le16_to_cpu(rlc_hdr->header.header_version_minor);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 2fbcd9765980d01a79b9b295fc28d82a909c69a9..0ea0866c261f84e24e8494755387b3d22482a0a2 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -115,7 +115,7 @@ static const struct soc15_reg_golden golden_settings_gc_11_5_0[] = {
SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_ADDR_MATCH_MASK, 0xffffffff, 0xfffffff3),
SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_CTRL, 0xffffffff, 0xf37fff3f),
SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_CTRL3, 0xfffffffb, 0x00f40188),
- SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_CTRL4, 0xf0ffffff, 0x8000b007),
+ SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_CTRL4, 0xf0ffffff, 0x80009007),
SOC15_REG_GOLDEN_VALUE(GC, 0, regPA_CL_ENHANCE, 0xf1ffffff, 0x00880007),
SOC15_REG_GOLDEN_VALUE(GC, 0, regPC_CONFIG_CNTL_1, 0xffffffff, 0x00010000),
SOC15_REG_GOLDEN_VALUE(GC, 0, regTA_CNTL_AUX, 0xf7f7ffff, 0x01030000),
@@ -6383,6 +6383,9 @@ static int gfx_v11_0_get_cu_info(struct amdgpu_device *adev,
mutex_lock(&adev->grbm_idx_mutex);
for (i = 0; i < adev->gfx.config.max_shader_engines; i++) {
for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) {
+ bitmap = i * adev->gfx.config.max_sh_per_se + j;
+ if (!((gfx_v11_0_get_sa_active_bitmap(adev) >> bitmap) & 1))
+ continue;
mask = 1;
counter = 0;
gfx_v11_0_select_se_sh(adev, i, j, 0xffffffff, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c
index 95d06da544e2a54ebe6fb10ad1309a0c8074814f..49aecdcee006959491e4dba90058faf35e205fdb 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c
@@ -456,10 +456,12 @@ static void gfxhub_v1_2_xcc_gart_disable(struct amdgpu_device *adev,
WREG32_SOC15_RLC(GC, GET_INST(GC, j), regMC_VM_MX_L1_TLB_CNTL, tmp);
/* Setup L2 cache */
- tmp = RREG32_SOC15(GC, GET_INST(GC, j), regVM_L2_CNTL);
- tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, ENABLE_L2_CACHE, 0);
- WREG32_SOC15(GC, GET_INST(GC, j), regVM_L2_CNTL, tmp);
- WREG32_SOC15(GC, GET_INST(GC, j), regVM_L2_CNTL3, 0);
+ if (!amdgpu_sriov_vf(adev)) {
+ tmp = RREG32_SOC15(GC, GET_INST(GC, j), regVM_L2_CNTL);
+ tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, ENABLE_L2_CACHE, 0);
+ WREG32_SOC15(GC, GET_INST(GC, j), regVM_L2_CNTL, tmp);
+ WREG32_SOC15(GC, GET_INST(GC, j), regVM_L2_CNTL3, 0);
+ }
}
}
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
index 6d24c84924cb5dd646ddaa69bb91a3193493b5f4..19986ff6a48d7e773dcc892b9dccd585fe69c306 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
@@ -401,8 +401,7 @@ static void nbio_v7_4_handle_ras_controller_intr_no_bifring(struct amdgpu_device
if (err_data.ce_count)
dev_info(adev->dev, "%ld correctable hardware "
- "errors detected in %s block, "
- "no user action is needed.\n",
+ "errors detected in %s block\n",
obj->err_data.ce_count,
get_ras_block_str(adev->nbio.ras_if));
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
index 25a3da83e0fb97e5949221d17e3fcd63062dd29c..e90f33780803458c32843f2599c07e4f598ca659 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
@@ -597,8 +597,7 @@ static void nbio_v7_9_handle_ras_controller_intr_no_bifring(struct amdgpu_device
if (err_data.ce_count)
dev_info(adev->dev, "%ld correctable hardware "
- "errors detected in %s block, "
- "no user action is needed.\n",
+ "errors detected in %s block\n",
obj->err_data.ce_count,
get_ras_block_str(adev->nbio.ras_if));
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c
index 530549314ce46c541a192305d1a7e1db17f11ebf..a3ee3c4c650febb4ca6fa61c9b7b5b51f16ce60c 100644
--- a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c
@@ -64,7 +64,7 @@ static void umc_v6_7_query_error_status_helper(struct amdgpu_device *adev,
uint64_t reg_value;
if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Deferred) == 1)
- dev_info(adev->dev, "Deferred error, no user action is needed.\n");
+ dev_info(adev->dev, "Deferred error\n");
if (mc_umc_status)
dev_info(adev->dev, "MCA STATUS 0x%llx, umc_reg_offset 0x%x\n", mc_umc_status, umc_reg_offset);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index d630100b9e91b8588dc2e9611e279fba909e54c5..f856901055d34e605cd4ec51fbdfc3be18e2abeb 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -1026,7 +1026,7 @@ int kgd2kfd_init_zone_device(struct amdgpu_device *adev)
} else {
res = devm_request_free_mem_region(adev->dev, &iomem_resource, size);
if (IS_ERR(res))
- return -ENOMEM;
+ return PTR_ERR(res);
pgmap->range.start = res->start;
pgmap->range.end = res->end;
pgmap->type = MEMORY_DEVICE_PRIVATE;
@@ -1042,10 +1042,10 @@ int kgd2kfd_init_zone_device(struct amdgpu_device *adev)
r = devm_memremap_pages(adev->dev, pgmap);
if (IS_ERR(r)) {
pr_err("failed to register HMM device memory\n");
- /* Disable SVM support capability */
- pgmap->type = 0;
if (pgmap->type == MEMORY_DEVICE_PRIVATE)
devm_release_mem_region(adev->dev, res->start, resource_size(res));
+ /* Disable SVM support capability */
+ pgmap->type = 0;
return PTR_ERR(r);
}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 745024b313401261a73900360c3d50f62d8440d8..17fbedbf3651388edfcd0109a22d0fe9dfcd331f 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -917,7 +917,7 @@ struct kfd_process {
* fence will be triggered during eviction and new one will be created
* during restore
*/
- struct dma_fence *ef;
+ struct dma_fence __rcu *ef;
/* Work items for evicting and restoring BOs */
struct delayed_work eviction_work;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 71df51fcc1b0d80f42899a0e15ae454b3f03f2bc..717a60d7a4ea953b8dfc369b09d855ad74b49659 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -1110,6 +1110,7 @@ static void kfd_process_wq_release(struct work_struct *work)
{
struct kfd_process *p = container_of(work, struct kfd_process,
release_work);
+ struct dma_fence *ef;
kfd_process_dequeue_from_all_devices(p);
pqm_uninit(&p->pqm);
@@ -1118,7 +1119,9 @@ static void kfd_process_wq_release(struct work_struct *work)
* destroyed. This allows any BOs to be freed without
* triggering pointless evictions or waiting for fences.
*/
- dma_fence_signal(p->ef);
+ synchronize_rcu();
+ ef = rcu_access_pointer(p->ef);
+ dma_fence_signal(ef);
kfd_process_remove_sysfs(p);
@@ -1127,7 +1130,7 @@ static void kfd_process_wq_release(struct work_struct *work)
svm_range_list_fini(p);
kfd_process_destroy_pdds(p);
- dma_fence_put(p->ef);
+ dma_fence_put(ef);
kfd_event_free_process(p);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index ac84c4a2ca072a7629f1f933214bd2d17a230ac7..c50a0dc9c9c072f5692d003bce90aaaf13615c5d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -404,14 +404,9 @@ static void svm_range_bo_release(struct kref *kref)
spin_lock(&svm_bo->list_lock);
}
spin_unlock(&svm_bo->list_lock);
- if (!dma_fence_is_signaled(&svm_bo->eviction_fence->base)) {
- /* We're not in the eviction worker.
- * Signal the fence and synchronize with any
- * pending eviction work.
- */
+ if (!dma_fence_is_signaled(&svm_bo->eviction_fence->base))
+ /* We're not in the eviction worker. Signal the fence. */
dma_fence_signal(&svm_bo->eviction_fence->base);
- cancel_work_sync(&svm_bo->eviction_work);
- }
dma_fence_put(&svm_bo->eviction_fence->base);
amdgpu_bo_unref(&svm_bo->bo);
kfree(svm_bo);
@@ -2345,8 +2340,10 @@ static void svm_range_deferred_list_work(struct work_struct *work)
mutex_unlock(&svms->lock);
mmap_write_unlock(mm);
- /* Pairs with mmget in svm_range_add_list_work */
- mmput(mm);
+ /* Pairs with mmget in svm_range_add_list_work. If dropping the
+ * last mm refcount, schedule release work to avoid circular locking
+ */
+ mmput_async(mm);
spin_lock(&svms->deferred_list_lock);
}
@@ -2657,6 +2654,7 @@ svm_range_get_range_boundaries(struct kfd_process *p, int64_t addr,
{
struct vm_area_struct *vma;
struct interval_tree_node *node;
+ struct rb_node *rb_node;
unsigned long start_limit, end_limit;
vma = vma_lookup(p->mm, addr << PAGE_SHIFT);
@@ -2676,16 +2674,15 @@ svm_range_get_range_boundaries(struct kfd_process *p, int64_t addr,
if (node) {
end_limit = min(end_limit, node->start);
/* Last range that ends before the fault address */
- node = container_of(rb_prev(&node->rb),
- struct interval_tree_node, rb);
+ rb_node = rb_prev(&node->rb);
} else {
/* Last range must end before addr because
* there was no range after addr
*/
- node = container_of(rb_last(&p->svms.objects.rb_root),
- struct interval_tree_node, rb);
+ rb_node = rb_last(&p->svms.objects.rb_root);
}
- if (node) {
+ if (rb_node) {
+ node = container_of(rb_node, struct interval_tree_node, rb);
if (node->last >= addr) {
WARN(1, "Overlap with prev node and page fault addr\n");
return -EFAULT;
@@ -3432,13 +3429,14 @@ svm_range_trigger_migration(struct mm_struct *mm, struct svm_range *prange,
int svm_range_schedule_evict_svm_bo(struct amdgpu_amdkfd_fence *fence)
{
- if (!fence)
- return -EINVAL;
-
- if (dma_fence_is_signaled(&fence->base))
- return 0;
-
- if (fence->svm_bo) {
+ /* Dereferencing fence->svm_bo is safe here because the fence hasn't
+ * signaled yet and we're under the protection of the fence->lock.
+ * After the fence is signaled in svm_range_bo_release, we cannot get
+ * here any more.
+ *
+ * Reference is dropped in svm_range_evict_svm_bo_worker.
+ */
+ if (svm_bo_ref_unless_zero(fence->svm_bo)) {
WRITE_ONCE(fence->svm_bo->evicting, 1);
schedule_work(&fence->svm_bo->eviction_work);
}
@@ -3453,8 +3451,6 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work)
int r = 0;
svm_bo = container_of(work, struct svm_range_bo, eviction_work);
- if (!svm_bo_ref_unless_zero(svm_bo))
- return; /* svm_bo was freed while eviction was pending */
if (mmget_not_zero(svm_bo->eviction_fence->mm)) {
mm = svm_bo->eviction_fence->mm;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index b569b6eda4e3c9f0a978b2d9c65fd868e22a35d8..d4f525b66a09055909e163b815beee357f28d19d 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -9292,10 +9292,10 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
if (!new_con_state->writeback_job)
continue;
- new_crtc_state = NULL;
+ new_crtc_state = drm_atomic_get_new_crtc_state(state, &acrtc->base);
- if (acrtc)
- new_crtc_state = drm_atomic_get_new_crtc_state(state, &acrtc->base);
+ if (!new_crtc_state)
+ continue;
if (acrtc->wb_enabled)
continue;
@@ -10752,7 +10752,7 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
DRM_DEBUG_DRIVER("drm_dp_mst_atomic_check() failed\n");
goto fail;
}
- status = dc_validate_global_state(dc, dm_state->context, false);
+ status = dc_validate_global_state(dc, dm_state->context, true);
if (status != DC_OK) {
DRM_DEBUG_DRIVER("DC global validation failure: %s (%d)",
dc_status_to_str(status), status);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
index 9b527bffe11a1f55e1a63d94c937c829e0d6f820..c87b64e464ed5c8e13c6fb823b8bf9ca0bcfe0fc 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
@@ -1239,7 +1239,7 @@ int amdgpu_dm_update_plane_color_mgmt(struct dm_crtc_state *crtc,
if (has_crtc_cm_degamma && ret != -EINVAL) {
drm_dbg_kms(crtc->base.crtc->dev,
"doesn't support plane and CRTC degamma at the same time\n");
- return -EINVAL;
+ return -EINVAL;
}
/* If we are here, it means we don't have plane degamma settings, check
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
index eaf8d9f482446d5ea9728ec17657189e25917ae8..85b7f58a7f35a478f551ec097b1613b504ced535 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
@@ -979,6 +979,11 @@ int dm_helper_dmub_aux_transfer_sync(
struct aux_payload *payload,
enum aux_return_code_type *operation_result)
{
+ if (!link->hpd_status) {
+ *operation_result = AUX_RET_ERROR_HPD_DISCON;
+ return -1;
+ }
+
return amdgpu_dm_process_dmub_aux_transfer_sync(ctx, link->link_index, payload,
operation_result);
}
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
index 7575282563267c6cd33872debc3f59b7819d35f5..a84f1e376dee45f7fbefea37053c0df57074789a 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
@@ -87,6 +87,20 @@ static const struct IP_BASE CLK_BASE = { { { { 0x00016C00, 0x02401800, 0, 0, 0,
#define CLK1_CLK_PLL_REQ__PllSpineDiv_MASK 0x0000F000L
#define CLK1_CLK_PLL_REQ__FbMult_frac_MASK 0xFFFF0000L
+#define regCLK1_CLK2_BYPASS_CNTL 0x029c
+#define regCLK1_CLK2_BYPASS_CNTL_BASE_IDX 0
+
+#define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_SEL__SHIFT 0x0
+#define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_DIV__SHIFT 0x10
+#define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_SEL_MASK 0x00000007L
+#define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_DIV_MASK 0x000F0000L
+
+#define regCLK6_0_CLK6_spll_field_8 0x464b
+#define regCLK6_0_CLK6_spll_field_8_BASE_IDX 0
+
+#define CLK6_0_CLK6_spll_field_8__spll_ssc_en__SHIFT 0xd
+#define CLK6_0_CLK6_spll_field_8__spll_ssc_en_MASK 0x00002000L
+
#define REG(reg_name) \
(CLK_BASE.instance[0].segment[reg ## reg_name ## _BASE_IDX] + reg ## reg_name)
@@ -131,35 +145,63 @@ static int dcn314_get_active_display_cnt_wa(
return display_count;
}
-static void dcn314_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, bool disable)
+static void dcn314_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context,
+ bool safe_to_lower, bool disable)
{
struct dc *dc = clk_mgr_base->ctx->dc;
int i;
for (i = 0; i < dc->res_pool->pipe_count; ++i) {
- struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i];
+ struct pipe_ctx *pipe = safe_to_lower
+ ? &context->res_ctx.pipe_ctx[i]
+ : &dc->current_state->res_ctx.pipe_ctx[i];
if (pipe->top_pipe || pipe->prev_odm_pipe)
continue;
if (pipe->stream && (pipe->stream->dpms_off || dc_is_virtual_signal(pipe->stream->signal))) {
- struct stream_encoder *stream_enc = pipe->stream_res.stream_enc;
-
if (disable) {
- if (stream_enc && stream_enc->funcs->disable_fifo)
- pipe->stream_res.stream_enc->funcs->disable_fifo(stream_enc);
+ if (pipe->stream_res.tg && pipe->stream_res.tg->funcs->immediate_disable_crtc)
+ pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg);
- pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg);
reset_sync_context_for_pipe(dc, context, i);
} else {
pipe->stream_res.tg->funcs->enable_crtc(pipe->stream_res.tg);
-
- if (stream_enc && stream_enc->funcs->enable_fifo)
- pipe->stream_res.stream_enc->funcs->enable_fifo(stream_enc);
}
}
}
}
+bool dcn314_is_spll_ssc_enabled(struct clk_mgr *clk_mgr_base)
+{
+ struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base);
+ uint32_t ssc_enable;
+
+ REG_GET(CLK6_0_CLK6_spll_field_8, spll_ssc_en, &ssc_enable);
+
+ return ssc_enable == 1;
+}
+
+void dcn314_init_clocks(struct clk_mgr *clk_mgr)
+{
+ struct clk_mgr_internal *clk_mgr_int = TO_CLK_MGR_INTERNAL(clk_mgr);
+ uint32_t ref_dtbclk = clk_mgr->clks.ref_dtbclk_khz;
+
+ memset(&(clk_mgr->clks), 0, sizeof(struct dc_clocks));
+ // Assumption is that boot state always supports pstate
+ clk_mgr->clks.ref_dtbclk_khz = ref_dtbclk; // restore ref_dtbclk
+ clk_mgr->clks.p_state_change_support = true;
+ clk_mgr->clks.prev_p_state_change_support = true;
+ clk_mgr->clks.pwr_state = DCN_PWR_STATE_UNKNOWN;
+ clk_mgr->clks.zstate_support = DCN_ZSTATE_SUPPORT_UNKNOWN;
+
+ // to adjust dp_dto reference clock if ssc is enable otherwise to apply dprefclk
+ if (dcn314_is_spll_ssc_enabled(clk_mgr))
+ clk_mgr->dp_dto_source_clock_in_khz =
+ dce_adjust_dp_ref_freq_for_ss(clk_mgr_int, clk_mgr->dprefclk_khz);
+ else
+ clk_mgr->dp_dto_source_clock_in_khz = clk_mgr->dprefclk_khz;
+}
+
void dcn314_update_clocks(struct clk_mgr *clk_mgr_base,
struct dc_state *context,
bool safe_to_lower)
@@ -252,11 +294,11 @@ void dcn314_update_clocks(struct clk_mgr *clk_mgr_base,
}
if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) {
- dcn314_disable_otg_wa(clk_mgr_base, context, true);
+ dcn314_disable_otg_wa(clk_mgr_base, context, safe_to_lower, true);
clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz;
dcn314_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz);
- dcn314_disable_otg_wa(clk_mgr_base, context, false);
+ dcn314_disable_otg_wa(clk_mgr_base, context, safe_to_lower, false);
update_dispclk = true;
}
@@ -436,6 +478,11 @@ static DpmClocks314_t dummy_clocks;
static struct dcn314_watermarks dummy_wms = { 0 };
+static struct dcn314_ss_info_table ss_info_table = {
+ .ss_divider = 1000,
+ .ss_percentage = {0, 0, 375, 375, 375}
+};
+
static void dcn314_build_watermark_ranges(struct clk_bw_params *bw_params, struct dcn314_watermarks *table)
{
int i, num_valid_sets;
@@ -708,13 +755,31 @@ static struct clk_mgr_funcs dcn314_funcs = {
.get_dp_ref_clk_frequency = dce12_get_dp_ref_freq_khz,
.get_dtb_ref_clk_frequency = dcn31_get_dtb_ref_freq_khz,
.update_clocks = dcn314_update_clocks,
- .init_clocks = dcn31_init_clocks,
+ .init_clocks = dcn314_init_clocks,
.enable_pme_wa = dcn314_enable_pme_wa,
.are_clock_states_equal = dcn314_are_clock_states_equal,
.notify_wm_ranges = dcn314_notify_wm_ranges
};
extern struct clk_mgr_funcs dcn3_fpga_funcs;
+static void dcn314_read_ss_info_from_lut(struct clk_mgr_internal *clk_mgr)
+{
+ uint32_t clock_source;
+ //uint32_t ssc_enable;
+
+ REG_GET(CLK1_CLK2_BYPASS_CNTL, CLK2_BYPASS_SEL, &clock_source);
+ //REG_GET(CLK6_0_CLK6_spll_field_8, spll_ssc_en, &ssc_enable);
+
+ if (dcn314_is_spll_ssc_enabled(&clk_mgr->base) && (clock_source < ARRAY_SIZE(ss_info_table.ss_percentage))) {
+ clk_mgr->dprefclk_ss_percentage = ss_info_table.ss_percentage[clock_source];
+
+ if (clk_mgr->dprefclk_ss_percentage != 0) {
+ clk_mgr->ss_on_dprefclk = true;
+ clk_mgr->dprefclk_ss_divider = ss_info_table.ss_divider;
+ }
+ }
+}
+
void dcn314_clk_mgr_construct(
struct dc_context *ctx,
struct clk_mgr_dcn314 *clk_mgr,
@@ -782,6 +847,7 @@ void dcn314_clk_mgr_construct(
clk_mgr->base.base.dprefclk_khz = 600000;
clk_mgr->base.base.clks.ref_dtbclk_khz = 600000;
dce_clock_read_ss_info(&clk_mgr->base);
+ dcn314_read_ss_info_from_lut(&clk_mgr->base);
/*if bios enabled SS, driver needs to adjust dtb clock, only enable with correct bios*/
clk_mgr->base.base.bw_params = &dcn314_bw_params;
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h
index 171f84340eb2fb1d532776ac348cc1fbfad858f5..002c28e807208e584396fdc99dc1822072e8ffa5 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h
@@ -28,6 +28,8 @@
#define __DCN314_CLK_MGR_H__
#include "clk_mgr_internal.h"
+#define DCN314_NUM_CLOCK_SOURCES 5
+
struct dcn314_watermarks;
struct dcn314_smu_watermark_set {
@@ -40,9 +42,18 @@ struct clk_mgr_dcn314 {
struct dcn314_smu_watermark_set smu_wm_set;
};
+struct dcn314_ss_info_table {
+ uint32_t ss_divider;
+ uint32_t ss_percentage[DCN314_NUM_CLOCK_SOURCES];
+};
+
bool dcn314_are_clock_states_equal(struct dc_clocks *a,
struct dc_clocks *b);
+bool dcn314_is_spll_ssc_enabled(struct clk_mgr *clk_mgr_base);
+
+void dcn314_init_clocks(struct clk_mgr *clk_mgr);
+
void dcn314_update_clocks(struct clk_mgr *clk_mgr_base,
struct dc_state *context,
bool safe_to_lower);
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 2d7205058c64abfece9cd154a4aebea8958e0168..aa7c02ba948e9ce63aa84eb7518f9c73c80d107a 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -411,12 +411,9 @@ bool dc_stream_adjust_vmin_vmax(struct dc *dc,
* avoid conflicting with firmware updates.
*/
if (dc->ctx->dce_version > DCE_VERSION_MAX)
- if (dc->optimized_required)
+ if (dc->optimized_required || dc->wm_optimized_required)
return false;
- if (!memcmp(&stream->adjust, adjust, sizeof(*adjust)))
- return true;
-
stream->adjust.v_total_max = adjust->v_total_max;
stream->adjust.v_total_mid = adjust->v_total_mid;
stream->adjust.v_total_mid_frame_num = adjust->v_total_mid_frame_num;
@@ -2230,6 +2227,7 @@ void dc_post_update_surfaces_to_stream(struct dc *dc)
}
dc->optimized_required = false;
+ dc->wm_optimized_required = false;
}
bool dc_set_generic_gpio_for_stereo(bool enable,
@@ -2652,6 +2650,8 @@ enum surface_update_type dc_check_update_surfaces_for_stream(
} else if (memcmp(&dc->current_state->bw_ctx.bw.dcn.clk, &dc->clk_mgr->clks, offsetof(struct dc_clocks, prev_p_state_change_support)) != 0) {
dc->optimized_required = true;
}
+
+ dc->optimized_required |= dc->wm_optimized_required;
}
return type;
@@ -2859,6 +2859,9 @@ static void copy_stream_update_to_stream(struct dc *dc,
if (update->vrr_active_fixed)
stream->vrr_active_fixed = *update->vrr_active_fixed;
+ if (update->crtc_timing_adjust)
+ stream->adjust = *update->crtc_timing_adjust;
+
if (update->dpms_off)
stream->dpms_off = *update->dpms_off;
@@ -3519,7 +3522,7 @@ static void commit_planes_for_stream(struct dc *dc,
top_pipe_to_program = resource_get_otg_master_for_stream(
&context->res_ctx,
stream);
-
+ ASSERT(top_pipe_to_program != NULL);
for (i = 0; i < dc->res_pool->pipe_count; i++) {
struct pipe_ctx *old_pipe = &dc->current_state->res_ctx.pipe_ctx[i];
@@ -4288,7 +4291,8 @@ static bool full_update_required(struct dc *dc,
stream_update->mst_bw_update ||
stream_update->func_shaper ||
stream_update->lut3d_func ||
- stream_update->pending_test_pattern))
+ stream_update->pending_test_pattern ||
+ stream_update->crtc_timing_adjust))
return true;
if (stream) {
@@ -4341,6 +4345,8 @@ static bool should_commit_minimal_transition_for_windowed_mpo_odm(struct dc *dc,
cur_pipe = resource_get_otg_master_for_stream(&dc->current_state->res_ctx, stream);
new_pipe = resource_get_otg_master_for_stream(&context->res_ctx, stream);
+ if (!cur_pipe || !new_pipe)
+ return false;
cur_is_odm_in_use = resource_get_odm_slice_count(cur_pipe) > 1;
new_is_odm_in_use = resource_get_odm_slice_count(new_pipe) > 1;
if (cur_is_odm_in_use == new_is_odm_in_use)
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index 57f0ddd1592399821222c4c5abd3708dbd2bd6b0..9fbdb09697fd5ea16abe86e4f970e80fb764ff7f 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -2194,6 +2194,10 @@ void resource_log_pipe_topology_update(struct dc *dc, struct dc_state *state)
for (stream_idx = 0; stream_idx < state->stream_count; stream_idx++) {
otg_master = resource_get_otg_master_for_stream(
&state->res_ctx, state->streams[stream_idx]);
+ if (!otg_master || otg_master->stream_res.tg == NULL) {
+ DC_LOG_DC("topology update: otg_master NULL stream_idx %d!\n", stream_idx);
+ return;
+ }
slice_count = resource_get_opp_heads_for_otg_master(otg_master,
&state->res_ctx, opp_heads);
for (slice_idx = 0; slice_idx < slice_count; slice_idx++) {
@@ -4986,20 +4990,6 @@ enum dc_status update_dp_encoder_resources_for_test_harness(const struct dc *dc,
return DC_OK;
}
-bool resource_subvp_in_use(struct dc *dc,
- struct dc_state *context)
-{
- uint32_t i;
-
- for (i = 0; i < dc->res_pool->pipe_count; i++) {
- struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
-
- if (dc_state_get_pipe_subvp_type(context, pipe) != SUBVP_NONE)
- return true;
- }
- return false;
-}
-
bool check_subvp_sw_cursor_fallback_req(const struct dc *dc, struct dc_stream_state *stream)
{
if (!dc->debug.disable_subvp_high_refresh && is_subvp_high_refresh_candidate(stream))
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_state.c b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
index 460a8010c79fef0496755ce435f4691e20c3a08e..88c6436b28b69ca7f4791bdc47404cd5f73a5f83 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_state.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
@@ -267,7 +267,8 @@ void dc_state_construct(struct dc *dc, struct dc_state *state)
state->clk_mgr = dc->clk_mgr;
/* Initialise DIG link encoder resource tracking variables. */
- link_enc_cfg_init(dc, state);
+ if (dc->res_pool)
+ link_enc_cfg_init(dc, state);
}
void dc_state_destruct(struct dc_state *state)
@@ -433,8 +434,9 @@ bool dc_state_add_plane(
otg_master_pipe = resource_get_otg_master_for_stream(
&state->res_ctx, stream);
- added = resource_append_dpp_pipes_for_plane_composition(state,
- dc->current_state, pool, otg_master_pipe, plane_state);
+ if (otg_master_pipe)
+ added = resource_append_dpp_pipes_for_plane_composition(state,
+ dc->current_state, pool, otg_master_pipe, plane_state);
if (added) {
stream_status->plane_states[stream_status->plane_count] =
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index f30a341bc09014b156dbe4463b41f84b0f16e083..5d7aa882416b3435a5dcfbaf502a9f326981bc81 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -51,7 +51,7 @@ struct aux_payload;
struct set_config_cmd_payload;
struct dmub_notification;
-#define DC_VER "3.2.265"
+#define DC_VER "3.2.266"
#define MAX_SURFACES 3
#define MAX_PLANES 6
@@ -1036,6 +1036,7 @@ struct dc {
/* Require to optimize clocks and bandwidth for added/removed planes */
bool optimized_required;
+ bool wm_optimized_required;
bool idle_optimizations_allowed;
bool enable_c20_dtm_b0;
diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h
index a23eebd9933b72ea5c1c2a951a560232250bf34c..ee10941caa5980999044407184e7a41b8548e6b0 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_stream.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h
@@ -139,6 +139,7 @@ union stream_update_flags {
uint32_t wb_update:1;
uint32_t dsc_changed : 1;
uint32_t mst_bw : 1;
+ uint32_t crtc_timing_adjust : 1;
uint32_t fams_changed : 1;
} bits;
@@ -325,6 +326,7 @@ struct dc_stream_update {
struct dc_3dlut *lut3d_func;
struct test_pattern *pending_test_pattern;
+ struct dc_crtc_timing_adjust *crtc_timing_adjust;
};
bool dc_is_stream_unchanged(
diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index 4f276169e05a91098662edc07fd50d0bc1ed327b..b08ccb8c68bc366386e82a566c452459da0aabdc 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -1140,23 +1140,25 @@ struct dc_panel_config {
} ilr;
};
+#define MAX_SINKS_PER_LINK 4
+
/*
* USB4 DPIA BW ALLOCATION STRUCTS
*/
struct dc_dpia_bw_alloc {
- int sink_verified_bw; // The Verified BW that sink can allocated and use that has been verified already
- int sink_allocated_bw; // The Actual Allocated BW that sink currently allocated
- int sink_max_bw; // The Max BW that sink can require/support
+ int remote_sink_req_bw[MAX_SINKS_PER_LINK]; // BW requested by remote sinks
+ int link_verified_bw; // The Verified BW that link can allocated and use that has been verified already
+ int link_max_bw; // The Max BW that link can require/support
+ int allocated_bw; // The Actual Allocated BW for this DPIA
int estimated_bw; // The estimated available BW for this DPIA
int bw_granularity; // BW Granularity
+ int dp_overhead; // DP overhead in dp tunneling
bool bw_alloc_enabled; // The BW Alloc Mode Support is turned ON for all 3: DP-Tx & Dpia & CM
bool response_ready; // Response ready from the CM side
uint8_t nrd_max_lane_count; // Non-reduced max lane count
uint8_t nrd_max_link_rate; // Non-reduced max link rate
};
-#define MAX_SINKS_PER_LINK 4
-
enum dc_hpd_enable_select {
HPD_EN_FOR_ALL_EDP = 0,
HPD_EN_FOR_PRIMARY_EDP_ONLY,
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c b/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c
index 140598f18bbdd4cb4758ec7e9ec17c91286d0ecc..f0458b8f00af842b87ab91feadd71eef4c680e27 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c
@@ -782,7 +782,7 @@ static void get_azalia_clock_info_dp(
/*audio_dto_module = dpDtoSourceClockInkhz * 10,000;
* [khz] ->[100Hz] */
azalia_clock_info->audio_dto_module =
- pll_info->dp_dto_source_clock_in_khz * 10;
+ pll_info->audio_dto_source_clock_in_khz * 10;
}
void dce_aud_wall_dto_setup(
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
index 5d3f6fa1011e8e33f5e7772bee445cb6602e278d..970644b695cd4f1d96f166cc1786987b460cdafd 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
@@ -975,6 +975,9 @@ static bool dcn31_program_pix_clk(
look_up_in_video_optimized_rate_tlb(pix_clk_params->requested_pix_clk_100hz / 10);
struct bp_pixel_clock_parameters bp_pc_params = {0};
enum transmitter_color_depth bp_pc_colour_depth = TRANSMITTER_COLOR_DEPTH_24;
+
+ if (clock_source->ctx->dc->clk_mgr->dp_dto_source_clock_in_khz != 0)
+ dp_dto_ref_khz = clock_source->ctx->dc->clk_mgr->dp_dto_source_clock_in_khz;
// For these signal types Driver to program DP_DTO without calling VBIOS Command table
if (dc_is_dp_signal(pix_clk_params->signal_type) || dc_is_virtual_signal(pix_clk_params->signal_type)) {
if (e) {
@@ -1088,6 +1091,10 @@ static bool get_pixel_clk_frequency_100hz(
struct dce110_clk_src *clk_src = TO_DCE110_CLK_SRC(clock_source);
unsigned int clock_hz = 0;
unsigned int modulo_hz = 0;
+ unsigned int dp_dto_ref_khz = clock_source->ctx->dc->clk_mgr->dprefclk_khz;
+
+ if (clock_source->ctx->dc->clk_mgr->dp_dto_source_clock_in_khz != 0)
+ dp_dto_ref_khz = clock_source->ctx->dc->clk_mgr->dp_dto_source_clock_in_khz;
if (clock_source->id == CLOCK_SOURCE_ID_DP_DTO) {
clock_hz = REG_READ(PHASE[inst]);
@@ -1100,7 +1107,7 @@ static bool get_pixel_clk_frequency_100hz(
modulo_hz = REG_READ(MODULO[inst]);
if (modulo_hz)
*pixel_clk_khz = div_u64((uint64_t)clock_hz*
- clock_source->ctx->dc->clk_mgr->dprefclk_khz*10,
+ dp_dto_ref_khz*10,
modulo_hz);
else
*pixel_clk_khz = 0;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
index e4a328b45c8a5153c6468486dff940a6eb9435a3..87760600e154dad46e911e28f0b2937e6e012602 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
@@ -183,6 +183,20 @@ bool dcn32_all_pipes_have_stream_and_plane(struct dc *dc,
return true;
}
+bool dcn32_subvp_in_use(struct dc *dc,
+ struct dc_state *context)
+{
+ uint32_t i;
+
+ for (i = 0; i < dc->res_pool->pipe_count; i++) {
+ struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
+
+ if (dc_state_get_pipe_subvp_type(context, pipe) != SUBVP_NONE)
+ return true;
+ }
+ return false;
+}
+
bool dcn32_mpo_in_use(struct dc_state *context)
{
uint32_t i;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
index aa68d010cbfd247057da5a210b5209ad7a62ded3..9f37f717a1f86f88c5fa41bc30f477406d70f3b8 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
@@ -33,7 +33,6 @@
#include "dcn30/dcn30_resource.h"
#include "link.h"
#include "dc_state_priv.h"
-#include "resource.h"
#define DC_LOGGER_INIT(logger)
@@ -292,7 +291,7 @@ int dcn32_find_dummy_latency_index_for_fw_based_mclk_switch(struct dc *dc,
/* for subvp + DRR case, if subvp pipes are still present we support pstate */
if (vba->DRAMClockChangeSupport[vlevel][vba->maxMpcComb] == dm_dram_clock_change_unsupported &&
- resource_subvp_in_use(dc, context))
+ dcn32_subvp_in_use(dc, context))
vba->DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] = temp_clock_change_support;
if (vlevel < context->bw_ctx.dml.vba.soc.num_states &&
@@ -2273,7 +2272,7 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context,
unsigned int dummy_latency_index = 0;
int maxMpcComb = context->bw_ctx.dml.vba.maxMpcComb;
unsigned int min_dram_speed_mts = context->bw_ctx.dml.vba.DRAMSpeed;
- bool subvp_active = resource_subvp_in_use(dc, context);
+ bool subvp_in_use = dcn32_subvp_in_use(dc, context);
unsigned int min_dram_speed_mts_margin;
bool need_fclk_lat_as_dummy = false;
bool is_subvp_p_drr = false;
@@ -2282,7 +2281,7 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context,
dc_assert_fp_enabled();
/* need to find dummy latency index for subvp */
- if (subvp_active) {
+ if (subvp_in_use) {
/* Override DRAMClockChangeSupport for SubVP + DRR case where the DRR cannot switch without stretching it's VBLANK */
if (!pstate_en) {
context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][maxMpcComb] = dm_dram_clock_change_vblank_w_mall_sub_vp;
@@ -2468,7 +2467,7 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context,
dc->clk_mgr->bw_params->clk_table.entries[min_dram_speed_mts_offset].memclk_mhz * 16;
}
- if (!context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching && !subvp_active) {
+ if (!context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching && !subvp_in_use) {
/* find largest table entry that is lower than dram speed,
* but lower than DPM0 still uses DPM0
*/
@@ -3528,7 +3527,7 @@ void dcn32_set_clock_limits(const struct _vcs_dpi_soc_bounding_box_st *soc_bb)
void dcn32_override_min_req_memclk(struct dc *dc, struct dc_state *context)
{
// WA: restrict FPO and SubVP to use first non-strobe mode (DCN32 BW issue)
- if ((context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching || resource_subvp_in_use(dc, context)) &&
+ if ((context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching || dcn32_subvp_in_use(dc, context)) &&
dc->dml.soc.num_chans <= 8) {
int num_mclk_levels = dc->clk_mgr->bw_params->clk_table.num_entries_per_clk.num_memclk_levels;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
index 3d12dabd39e47d0d2a3fc918dd1d07dbc3902e5d..475c4ec43c013f481a71ad5668a8aef82ac7ba0a 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
@@ -166,9 +166,9 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = {
.num_states = 5,
.sr_exit_time_us = 14.0,
.sr_enter_plus_exit_time_us = 16.0,
- .sr_exit_z8_time_us = 525.0,
- .sr_enter_plus_exit_z8_time_us = 715.0,
- .fclk_change_latency_us = 20.0,
+ .sr_exit_z8_time_us = 210.0,
+ .sr_enter_plus_exit_z8_time_us = 320.0,
+ .fclk_change_latency_us = 24.0,
.usr_retraining_latency_us = 2,
.writeback_latency_us = 12.0,
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c
index b95bf27f2fe2fe9a943cda43ce121c07c548f5dc..9be5ebf3a8c0ba7805b793b108923e057f2fdfe0 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c
@@ -6229,7 +6229,7 @@ static void set_calculate_prefetch_schedule_params(struct display_mode_lib_st *m
CalculatePrefetchSchedule_params->GPUVMEnable = mode_lib->ms.cache_display_cfg.plane.GPUVMEnable;
CalculatePrefetchSchedule_params->HostVMEnable = mode_lib->ms.cache_display_cfg.plane.HostVMEnable;
CalculatePrefetchSchedule_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels;
- CalculatePrefetchSchedule_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes;
+ CalculatePrefetchSchedule_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024;
CalculatePrefetchSchedule_params->DynamicMetadataEnable = mode_lib->ms.cache_display_cfg.plane.DynamicMetadataEnable[k];
CalculatePrefetchSchedule_params->DynamicMetadataVMEnabled = mode_lib->ms.ip.dynamic_metadata_vm_enabled;
CalculatePrefetchSchedule_params->DynamicMetadataLinesBeforeActiveRequired = mode_lib->ms.cache_display_cfg.plane.DynamicMetadataLinesBeforeActiveRequired[k];
@@ -6329,7 +6329,7 @@ static void dml_prefetch_check(struct display_mode_lib_st *mode_lib)
mode_lib->ms.NoOfDPPThisState,
mode_lib->ms.dpte_group_bytes,
s->HostVMInefficiencyFactor,
- mode_lib->ms.soc.hostvm_min_page_size_kbytes,
+ mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024,
mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels);
s->NextMaxVStartup = s->MaxVStartupAllPlanes[j];
@@ -6542,7 +6542,7 @@ static void dml_prefetch_check(struct display_mode_lib_st *mode_lib)
mode_lib->ms.cache_display_cfg.plane.HostVMEnable,
mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels,
mode_lib->ms.cache_display_cfg.plane.GPUVMEnable,
- mode_lib->ms.soc.hostvm_min_page_size_kbytes,
+ mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024,
mode_lib->ms.PDEAndMetaPTEBytesPerFrame[j][k],
mode_lib->ms.MetaRowBytes[j][k],
mode_lib->ms.DPTEBytesPerRow[j][k],
@@ -7687,7 +7687,7 @@ dml_bool_t dml_core_mode_support(struct display_mode_lib_st *mode_lib)
CalculateVMRowAndSwath_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels;
CalculateVMRowAndSwath_params->GPUVMMaxPageTableLevels = mode_lib->ms.cache_display_cfg.plane.GPUVMMaxPageTableLevels;
CalculateVMRowAndSwath_params->GPUVMMinPageSizeKBytes = mode_lib->ms.cache_display_cfg.plane.GPUVMMinPageSizeKBytes;
- CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes;
+ CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024;
CalculateVMRowAndSwath_params->PTEBufferModeOverrideEn = mode_lib->ms.cache_display_cfg.plane.PTEBufferModeOverrideEn;
CalculateVMRowAndSwath_params->PTEBufferModeOverrideVal = mode_lib->ms.cache_display_cfg.plane.PTEBufferMode;
CalculateVMRowAndSwath_params->PTEBufferSizeNotExceeded = mode_lib->ms.PTEBufferSizeNotExceededPerState;
@@ -7957,7 +7957,7 @@ dml_bool_t dml_core_mode_support(struct display_mode_lib_st *mode_lib)
UseMinimumDCFCLK_params->GPUVMMaxPageTableLevels = mode_lib->ms.cache_display_cfg.plane.GPUVMMaxPageTableLevels;
UseMinimumDCFCLK_params->HostVMEnable = mode_lib->ms.cache_display_cfg.plane.HostVMEnable;
UseMinimumDCFCLK_params->NumberOfActiveSurfaces = mode_lib->ms.num_active_planes;
- UseMinimumDCFCLK_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes;
+ UseMinimumDCFCLK_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024;
UseMinimumDCFCLK_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels;
UseMinimumDCFCLK_params->DynamicMetadataVMEnabled = mode_lib->ms.ip.dynamic_metadata_vm_enabled;
UseMinimumDCFCLK_params->ImmediateFlipRequirement = s->ImmediateFlipRequiredFinal;
@@ -8699,7 +8699,7 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc
CalculateVMRowAndSwath_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels;
CalculateVMRowAndSwath_params->GPUVMMaxPageTableLevels = mode_lib->ms.cache_display_cfg.plane.GPUVMMaxPageTableLevels;
CalculateVMRowAndSwath_params->GPUVMMinPageSizeKBytes = mode_lib->ms.cache_display_cfg.plane.GPUVMMinPageSizeKBytes;
- CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes;
+ CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024;
CalculateVMRowAndSwath_params->PTEBufferModeOverrideEn = mode_lib->ms.cache_display_cfg.plane.PTEBufferModeOverrideEn;
CalculateVMRowAndSwath_params->PTEBufferModeOverrideVal = mode_lib->ms.cache_display_cfg.plane.PTEBufferMode;
CalculateVMRowAndSwath_params->PTEBufferSizeNotExceeded = s->dummy_boolean_array[0];
@@ -8805,7 +8805,7 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc
mode_lib->ms.cache_display_cfg.hw.DPPPerSurface,
locals->dpte_group_bytes,
s->HostVMInefficiencyFactor,
- mode_lib->ms.soc.hostvm_min_page_size_kbytes,
+ mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024,
mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels);
locals->TCalc = 24.0 / locals->DCFCLKDeepSleep;
@@ -8995,7 +8995,7 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc
CalculatePrefetchSchedule_params->GPUVMEnable = mode_lib->ms.cache_display_cfg.plane.GPUVMEnable;
CalculatePrefetchSchedule_params->HostVMEnable = mode_lib->ms.cache_display_cfg.plane.HostVMEnable;
CalculatePrefetchSchedule_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels;
- CalculatePrefetchSchedule_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes;
+ CalculatePrefetchSchedule_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024;
CalculatePrefetchSchedule_params->DynamicMetadataEnable = mode_lib->ms.cache_display_cfg.plane.DynamicMetadataEnable[k];
CalculatePrefetchSchedule_params->DynamicMetadataVMEnabled = mode_lib->ms.ip.dynamic_metadata_vm_enabled;
CalculatePrefetchSchedule_params->DynamicMetadataLinesBeforeActiveRequired = mode_lib->ms.cache_display_cfg.plane.DynamicMetadataLinesBeforeActiveRequired[k];
@@ -9240,7 +9240,7 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc
mode_lib->ms.cache_display_cfg.plane.HostVMEnable,
mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels,
mode_lib->ms.cache_display_cfg.plane.GPUVMEnable,
- mode_lib->ms.soc.hostvm_min_page_size_kbytes,
+ mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024,
locals->PDEAndMetaPTEBytesFrame[k],
locals->MetaRowByte[k],
locals->PixelPTEBytesPerRow[k],
@@ -9446,13 +9446,13 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc
CalculateWatermarks_params->CompressedBufferSizeInkByte = locals->CompressedBufferSizeInkByte;
// Output
- CalculateWatermarks_params->Watermark = &s->dummy_watermark; // Watermarks *Watermark
- CalculateWatermarks_params->DRAMClockChangeSupport = &mode_lib->ms.support.DRAMClockChangeSupport[0];
- CalculateWatermarks_params->MaxActiveDRAMClockChangeLatencySupported = &s->dummy_single_array[0][0]; // dml_float_t *MaxActiveDRAMClockChangeLatencySupported[]
- CalculateWatermarks_params->SubViewportLinesNeededInMALL = &mode_lib->ms.SubViewportLinesNeededInMALL[j]; // dml_uint_t SubViewportLinesNeededInMALL[]
- CalculateWatermarks_params->FCLKChangeSupport = &mode_lib->ms.support.FCLKChangeSupport[0];
- CalculateWatermarks_params->MaxActiveFCLKChangeLatencySupported = &s->dummy_single[0]; // dml_float_t *MaxActiveFCLKChangeLatencySupported
- CalculateWatermarks_params->USRRetrainingSupport = &mode_lib->ms.support.USRRetrainingSupport[0];
+ CalculateWatermarks_params->Watermark = &locals->Watermark; // Watermarks *Watermark
+ CalculateWatermarks_params->DRAMClockChangeSupport = &locals->DRAMClockChangeSupport;
+ CalculateWatermarks_params->MaxActiveDRAMClockChangeLatencySupported = locals->MaxActiveDRAMClockChangeLatencySupported; // dml_float_t *MaxActiveDRAMClockChangeLatencySupported[]
+ CalculateWatermarks_params->SubViewportLinesNeededInMALL = locals->SubViewportLinesNeededInMALL; // dml_uint_t SubViewportLinesNeededInMALL[]
+ CalculateWatermarks_params->FCLKChangeSupport = &locals->FCLKChangeSupport;
+ CalculateWatermarks_params->MaxActiveFCLKChangeLatencySupported = &locals->MaxActiveFCLKChangeLatencySupported; // dml_float_t *MaxActiveFCLKChangeLatencySupported
+ CalculateWatermarks_params->USRRetrainingSupport = &locals->USRRetrainingSupport;
CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport(
&mode_lib->scratch,
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
index fa6a93dd9629558120304beae4da239a60268c0d..64d01a9cd68c859db9bcffbc478ef09090b07fbf 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
@@ -626,8 +626,8 @@ static void populate_dml_output_cfg_from_stream_state(struct dml_output_cfg_st *
if (is_dp2p0_output_encoder(pipe))
out->OutputEncoder[location] = dml_dp2p0;
break;
- out->OutputEncoder[location] = dml_edp;
case SIGNAL_TYPE_EDP:
+ out->OutputEncoder[location] = dml_edp;
break;
case SIGNAL_TYPE_HDMI_TYPE_A:
case SIGNAL_TYPE_DVI_SINGLE_LINK:
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
index fb328cd06cea2c8a00f7450c8ade7408fb4716a9..5660f15da291e9de58637c115e315b07f1cee7a3 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
@@ -1354,7 +1354,7 @@ static void build_audio_output(
if (state->clk_mgr &&
(pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT ||
pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST)) {
- audio_output->pll_info.dp_dto_source_clock_in_khz =
+ audio_output->pll_info.audio_dto_source_clock_in_khz =
state->clk_mgr->funcs->get_dp_ref_clk_frequency(
state->clk_mgr);
}
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
index 51dd2ae09b2a6235f822c7eb6c72335f38fafe24..6dd479e8a348502c9b285a38f16650fb7cb4f95e 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
@@ -3076,7 +3076,7 @@ void dcn10_prepare_bandwidth(
context,
false);
- dc->optimized_required |= hubbub->funcs->program_watermarks(hubbub,
+ dc->wm_optimized_required = hubbub->funcs->program_watermarks(hubbub,
&context->bw_ctx.bw.dcn.watermarks,
dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000,
true);
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
index bc71a9b058fedd2c211cf38088758ca6a71480b9..e931342fcf4cf1d4f4b0cf41628cd9f855fa6dac 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
@@ -1882,42 +1882,6 @@ static void dcn20_program_pipe(
}
}
-static void update_vmin_vmax_fams(struct dc *dc,
- struct dc_state *context)
-{
- uint32_t i;
- struct drr_params params = {0};
- bool subvp_in_use = resource_subvp_in_use(dc, context);
-
- for (i = 0; i < dc->res_pool->pipe_count; i++) {
- struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
-
- if (resource_is_pipe_type(pipe, OTG_MASTER) &&
- ((subvp_in_use && dc_state_get_pipe_subvp_type(context, pipe) != SUBVP_PHANTOM &&
- pipe->stream->allow_freesync) || (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching && pipe->stream->fpo_in_use))) {
- if (!pipe->stream->vrr_active_variable && !pipe->stream->vrr_active_fixed) {
- struct timing_generator *tg = context->res_ctx.pipe_ctx[i].stream_res.tg;
-
- /* DRR should be configured already if we're in active variable
- * or active fixed, so only program if we're not in this state
- */
- params.vertical_total_min = pipe->stream->timing.v_total;
- params.vertical_total_max = pipe->stream->timing.v_total;
- tg->funcs->set_drr(tg, ¶ms);
- }
- } else {
- if (resource_is_pipe_type(pipe, OTG_MASTER) &&
- !pipe->stream->vrr_active_variable &&
- !pipe->stream->vrr_active_fixed) {
- struct timing_generator *tg = context->res_ctx.pipe_ctx[i].stream_res.tg;
- params.vertical_total_min = 0;
- params.vertical_total_max = 0;
- tg->funcs->set_drr(tg, ¶ms);
- }
- }
- }
-}
-
void dcn20_program_front_end_for_ctx(
struct dc *dc,
struct dc_state *context)
@@ -1994,7 +1958,6 @@ void dcn20_program_front_end_for_ctx(
&& context->res_ctx.pipe_ctx[i].stream)
hws->funcs.blank_pixel_data(dc, &context->res_ctx.pipe_ctx[i], true);
- update_vmin_vmax_fams(dc, context);
/* Disconnect mpcc */
for (i = 0; i < dc->res_pool->pipe_count; i++)
@@ -2196,10 +2159,10 @@ void dcn20_prepare_bandwidth(
}
/* program dchubbub watermarks:
- * For assigning optimized_required, use |= operator since we don't want
+ * For assigning wm_optimized_required, use |= operator since we don't want
* to clear the value if the optimize has not happened yet
*/
- dc->optimized_required |= hubbub->funcs->program_watermarks(hubbub,
+ dc->wm_optimized_required |= hubbub->funcs->program_watermarks(hubbub,
&context->bw_ctx.bw.dcn.watermarks,
dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000,
false);
@@ -2212,10 +2175,10 @@ void dcn20_prepare_bandwidth(
if (hubbub->funcs->program_compbuf_size) {
if (context->bw_ctx.dml.ip.min_comp_buffer_size_kbytes) {
compbuf_size_kb = context->bw_ctx.dml.ip.min_comp_buffer_size_kbytes;
- dc->optimized_required |= (compbuf_size_kb != dc->current_state->bw_ctx.dml.ip.min_comp_buffer_size_kbytes);
+ dc->wm_optimized_required |= (compbuf_size_kb != dc->current_state->bw_ctx.dml.ip.min_comp_buffer_size_kbytes);
} else {
compbuf_size_kb = context->bw_ctx.bw.dcn.compbuf_size_kb;
- dc->optimized_required |= (compbuf_size_kb != dc->current_state->bw_ctx.bw.dcn.compbuf_size_kb);
+ dc->wm_optimized_required |= (compbuf_size_kb != dc->current_state->bw_ctx.bw.dcn.compbuf_size_kb);
}
hubbub->funcs->program_compbuf_size(hubbub, compbuf_size_kb, false);
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
index cbba39d251e5335d6e11604fc327b8ad31284aea..17e014d3bdc8401893847a4f0fd9670d664f65c5 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
@@ -333,6 +333,7 @@ struct clk_mgr {
bool force_smu_not_present;
bool dc_mode_softmax_enabled;
int dprefclk_khz; // Used by program pixel clock in clock source funcs, need to figureout where this goes
+ int dp_dto_source_clock_in_khz; // Used to program DP DTO with ss adjustment on DCN314
int dentist_vco_freq_khz;
struct clk_state_registers_and_bypass boot_snapshot;
struct clk_bw_params *bw_params;
diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h
index 1d51fed12e20037b3baf40ed7f3b89095437457e..c958ef37b78a667b1bb9bfb26827ae3e45053715 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/resource.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h
@@ -609,9 +609,6 @@ bool dc_resource_acquire_secondary_pipe_for_mpc_odm_legacy(
struct pipe_ctx *sec_pipe,
bool odm);
-bool resource_subvp_in_use(struct dc *dc,
- struct dc_state *context);
-
/* A test harness interface that modifies dp encoder resources in the given dc
* state and bypasses the need to revalidate. The interface assumes that the
* test harness interface is called with pre-validated link config stored in the
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
index 5fe8b4871c77614eb0fd46421db49fb79197e6f7..3cbfbf8d107e9b62c639ef1618041b8fc09dd9b5 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
@@ -900,11 +900,15 @@ bool link_set_dsc_pps_packet(struct pipe_ctx *pipe_ctx, bool enable, bool immedi
{
struct display_stream_compressor *dsc = pipe_ctx->stream_res.dsc;
struct dc_stream_state *stream = pipe_ctx->stream;
- DC_LOGGER_INIT(dsc->ctx->logger);
- if (!pipe_ctx->stream->timing.flags.DSC || !dsc)
+ if (!pipe_ctx->stream->timing.flags.DSC)
return false;
+ if (!dsc)
+ return false;
+
+ DC_LOGGER_INIT(dsc->ctx->logger);
+
if (enable) {
struct dsc_config dsc_cfg;
uint8_t dsc_packed_pps[128];
@@ -2005,17 +2009,11 @@ static enum dc_status enable_link_dp(struct dc_state *state,
}
}
- /*
- * If the link is DP-over-USB4 do the following:
- * - Train with fallback when enabling DPIA link. Conventional links are
+ /* Train with fallback when enabling DPIA link. Conventional links are
* trained with fallback during sink detection.
- * - Allocate only what the stream needs for bw in Gbps. Inform the CM
- * in case stream needs more or less bw from what has been allocated
- * earlier at plug time.
*/
- if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) {
+ if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA)
do_fallback = true;
- }
/*
* Temporary w/a to get DP2.0 link rates to work with SST.
@@ -2197,6 +2195,32 @@ static enum dc_status enable_link(
return status;
}
+static bool allocate_usb4_bandwidth_for_stream(struct dc_stream_state *stream, int bw)
+{
+ return true;
+}
+
+static bool allocate_usb4_bandwidth(struct dc_stream_state *stream)
+{
+ bool ret;
+
+ int bw = dc_bandwidth_in_kbps_from_timing(&stream->timing,
+ dc_link_get_highest_encoding_format(stream->sink->link));
+
+ ret = allocate_usb4_bandwidth_for_stream(stream, bw);
+
+ return ret;
+}
+
+static bool deallocate_usb4_bandwidth(struct dc_stream_state *stream)
+{
+ bool ret;
+
+ ret = allocate_usb4_bandwidth_for_stream(stream, 0);
+
+ return ret;
+}
+
void link_set_dpms_off(struct pipe_ctx *pipe_ctx)
{
struct dc *dc = pipe_ctx->stream->ctx->dc;
@@ -2232,6 +2256,9 @@ void link_set_dpms_off(struct pipe_ctx *pipe_ctx)
update_psp_stream_config(pipe_ctx, true);
dc->hwss.blank_stream(pipe_ctx);
+ if (pipe_ctx->stream->link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA)
+ deallocate_usb4_bandwidth(pipe_ctx->stream);
+
if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST)
deallocate_mst_payload(pipe_ctx);
else if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT &&
@@ -2474,6 +2501,9 @@ void link_set_dpms_on(
}
}
+ if (pipe_ctx->stream->link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA)
+ allocate_usb4_bandwidth(pipe_ctx->stream);
+
if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST)
allocate_mst_payload(pipe_ctx);
else if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT &&
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_validation.c b/drivers/gpu/drm/amd/display/dc/link/link_validation.c
index b45fda96eaf649bf16f291df2294d787680e0287..8fe66c3678508d9aee6779fa25cd6128e1f30832 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_validation.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_validation.c
@@ -346,23 +346,61 @@ enum dc_status link_validate_mode_timing(
return DC_OK;
}
+/*
+ * This function calculates the bandwidth required for the stream timing
+ * and aggregates the stream bandwidth for the respective dpia link
+ *
+ * @stream: pointer to the dc_stream_state struct instance
+ * @num_streams: number of streams to be validated
+ *
+ * return: true if validation is succeeded
+ */
bool link_validate_dpia_bandwidth(const struct dc_stream_state *stream, const unsigned int num_streams)
{
- bool ret = true;
- int bw_needed[MAX_DPIA_NUM];
- struct dc_link *link[MAX_DPIA_NUM];
-
- if (!num_streams || num_streams > MAX_DPIA_NUM)
- return ret;
+ int bw_needed[MAX_DPIA_NUM] = {0};
+ struct dc_link *dpia_link[MAX_DPIA_NUM] = {0};
+ int num_dpias = 0;
for (uint8_t i = 0; i < num_streams; ++i) {
+ if (stream[i].signal == SIGNAL_TYPE_DISPLAY_PORT) {
+ /* new dpia sst stream, check whether it exceeds max dpia */
+ if (num_dpias >= MAX_DPIA_NUM)
+ return false;
- link[i] = stream[i].link;
- bw_needed[i] = dc_bandwidth_in_kbps_from_timing(&stream[i].timing,
- dc_link_get_highest_encoding_format(link[i]));
+ dpia_link[num_dpias] = stream[i].link;
+ bw_needed[num_dpias] = dc_bandwidth_in_kbps_from_timing(&stream[i].timing,
+ dc_link_get_highest_encoding_format(dpia_link[num_dpias]));
+ num_dpias++;
+ } else if (stream[i].signal == SIGNAL_TYPE_DISPLAY_PORT_MST) {
+ uint8_t j = 0;
+ /* check whether its a known dpia link */
+ for (; j < num_dpias; ++j) {
+ if (dpia_link[j] == stream[i].link)
+ break;
+ }
+
+ if (j == num_dpias) {
+ /* new dpia mst stream, check whether it exceeds max dpia */
+ if (num_dpias >= MAX_DPIA_NUM)
+ return false;
+ else {
+ dpia_link[j] = stream[i].link;
+ num_dpias++;
+ }
+ }
+
+ bw_needed[j] += dc_bandwidth_in_kbps_from_timing(&stream[i].timing,
+ dc_link_get_highest_encoding_format(dpia_link[j]));
+ }
}
- ret = dpia_validate_usb4_bw(link, bw_needed, num_streams);
+ /* Include dp overheads */
+ for (uint8_t i = 0; i < num_dpias; ++i) {
+ int dp_overhead = 0;
+
+ dp_overhead = link_dp_dpia_get_dp_overhead_in_dp_tunneling(dpia_link[i]);
+ bw_needed[i] += dp_overhead;
+ }
- return ret;
+ return dpia_validate_usb4_bw(dpia_link, bw_needed, num_dpias);
}
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia.c
index 982eda3c46f5680af8c60042e4cc7fc8909f68d3..6af42ba9885c054ead528e11d14007622af098a8 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia.c
@@ -82,25 +82,33 @@ bool dpia_query_hpd_status(struct dc_link *link)
{
union dmub_rb_cmd cmd = {0};
struct dc_dmub_srv *dmub_srv = link->ctx->dmub_srv;
- bool is_hpd_high = false;
/* prepare QUERY_HPD command */
cmd.query_hpd.header.type = DMUB_CMD__QUERY_HPD_STATE;
cmd.query_hpd.data.instance = link->link_id.enum_id - ENUM_ID_1;
cmd.query_hpd.data.ch_type = AUX_CHANNEL_DPIA;
- /* Return HPD status reported by DMUB if query successfully executed. */
- if (dc_wake_and_execute_dmub_cmd(dmub_srv->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY) &&
- cmd.query_hpd.data.status == AUX_RET_SUCCESS)
- is_hpd_high = cmd.query_hpd.data.result;
-
- DC_LOG_DEBUG("%s: link(%d) dpia(%d) cmd_status(%d) result(%d)\n",
- __func__,
- link->link_index,
- link->link_id.enum_id - ENUM_ID_1,
- cmd.query_hpd.data.status,
- cmd.query_hpd.data.result);
-
- return is_hpd_high;
+ /* Query dpia hpd status from dmub */
+ if (dc_wake_and_execute_dmub_cmd(dmub_srv->ctx, &cmd,
+ DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY) &&
+ cmd.query_hpd.data.status == AUX_RET_SUCCESS) {
+ DC_LOG_DEBUG("%s: for link(%d) dpia(%d) success, current_hpd_status(%d) new_hpd_status(%d)\n",
+ __func__,
+ link->link_index,
+ link->link_id.enum_id - ENUM_ID_1,
+ link->hpd_status,
+ cmd.query_hpd.data.result);
+ link->hpd_status = cmd.query_hpd.data.result;
+ } else {
+ DC_LOG_ERROR("%s: for link(%d) dpia(%d) failed with status(%d), current_hpd_status(%d) new_hpd_status(0)\n",
+ __func__,
+ link->link_index,
+ link->link_id.enum_id - ENUM_ID_1,
+ cmd.query_hpd.data.status,
+ link->hpd_status);
+ link->hpd_status = false;
+ }
+
+ return link->hpd_status;
}
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
index a7aa8c9da868fcf81a335b3d1384aeb8e37a1f42..dd0d2b206462c927c5f68b355498e71250c154b9 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
@@ -54,12 +54,18 @@ static bool get_bw_alloc_proceed_flag(struct dc_link *tmp)
static void reset_bw_alloc_struct(struct dc_link *link)
{
link->dpia_bw_alloc_config.bw_alloc_enabled = false;
- link->dpia_bw_alloc_config.sink_verified_bw = 0;
- link->dpia_bw_alloc_config.sink_max_bw = 0;
+ link->dpia_bw_alloc_config.link_verified_bw = 0;
+ link->dpia_bw_alloc_config.link_max_bw = 0;
+ link->dpia_bw_alloc_config.allocated_bw = 0;
link->dpia_bw_alloc_config.estimated_bw = 0;
link->dpia_bw_alloc_config.bw_granularity = 0;
+ link->dpia_bw_alloc_config.dp_overhead = 0;
link->dpia_bw_alloc_config.response_ready = false;
- link->dpia_bw_alloc_config.sink_allocated_bw = 0;
+ link->dpia_bw_alloc_config.nrd_max_lane_count = 0;
+ link->dpia_bw_alloc_config.nrd_max_link_rate = 0;
+ for (int i = 0; i < MAX_SINKS_PER_LINK; i++)
+ link->dpia_bw_alloc_config.remote_sink_req_bw[i] = 0;
+ DC_LOG_DEBUG("reset usb4 bw alloc of link(%d)\n", link->link_index);
}
#define BW_GRANULARITY_0 4 // 0.25 Gbps
@@ -210,8 +216,8 @@ static int get_host_router_total_dp_tunnel_bw(const struct dc *dc, uint8_t hr_in
link_dpia_primary->dpia_bw_alloc_config.bw_alloc_enabled) &&
(link_dpia_secondary->hpd_status &&
link_dpia_secondary->dpia_bw_alloc_config.bw_alloc_enabled)) {
- total_bw += link_dpia_primary->dpia_bw_alloc_config.estimated_bw +
- link_dpia_secondary->dpia_bw_alloc_config.sink_allocated_bw;
+ total_bw += link_dpia_primary->dpia_bw_alloc_config.estimated_bw +
+ link_dpia_secondary->dpia_bw_alloc_config.allocated_bw;
} else if (link_dpia_primary->hpd_status &&
link_dpia_primary->dpia_bw_alloc_config.bw_alloc_enabled) {
total_bw = link_dpia_primary->dpia_bw_alloc_config.estimated_bw;
@@ -264,7 +270,7 @@ static void set_usb4_req_bw_req(struct dc_link *link, int req_bw)
/* Error check whether requested and allocated are equal */
req_bw = requested_bw * (Kbps_TO_Gbps / link->dpia_bw_alloc_config.bw_granularity);
- if (req_bw == link->dpia_bw_alloc_config.sink_allocated_bw) {
+ if (req_bw == link->dpia_bw_alloc_config.allocated_bw) {
DC_LOG_ERROR("%s: Request bw equals to allocated bw for link(%d)\n",
__func__, link->link_index);
}
@@ -387,9 +393,9 @@ void dpia_handle_bw_alloc_response(struct dc_link *link, uint8_t bw, uint8_t res
DC_LOG_DEBUG("%s: BW REQ SUCCESS for DP-TX Request for link(%d)\n",
__func__, link->link_index);
DC_LOG_DEBUG("%s: current allocated_bw(%d), new allocated_bw(%d)\n",
- __func__, link->dpia_bw_alloc_config.sink_allocated_bw, bw_needed);
+ __func__, link->dpia_bw_alloc_config.allocated_bw, bw_needed);
- link->dpia_bw_alloc_config.sink_allocated_bw = bw_needed;
+ link->dpia_bw_alloc_config.allocated_bw = bw_needed;
link->dpia_bw_alloc_config.response_ready = true;
break;
@@ -427,8 +433,8 @@ int dpia_handle_usb4_bandwidth_allocation_for_link(struct dc_link *link, int pea
if (link->hpd_status && peak_bw > 0) {
// If DP over USB4 then we need to check BW allocation
- link->dpia_bw_alloc_config.sink_max_bw = peak_bw;
- set_usb4_req_bw_req(link, link->dpia_bw_alloc_config.sink_max_bw);
+ link->dpia_bw_alloc_config.link_max_bw = peak_bw;
+ set_usb4_req_bw_req(link, link->dpia_bw_alloc_config.link_max_bw);
do {
if (timeout > 0)
@@ -440,8 +446,8 @@ int dpia_handle_usb4_bandwidth_allocation_for_link(struct dc_link *link, int pea
if (!timeout)
ret = 0;// ERROR TIMEOUT waiting for response for allocating bw
- else if (link->dpia_bw_alloc_config.sink_allocated_bw > 0)
- ret = link->dpia_bw_alloc_config.sink_allocated_bw;
+ else if (link->dpia_bw_alloc_config.allocated_bw > 0)
+ ret = link->dpia_bw_alloc_config.allocated_bw;
}
//2. Cold Unplug
else if (!link->hpd_status)
@@ -450,7 +456,6 @@ int dpia_handle_usb4_bandwidth_allocation_for_link(struct dc_link *link, int pea
out:
return ret;
}
-
bool link_dp_dpia_allocate_usb4_bandwidth_for_stream(struct dc_link *link, int req_bw)
{
bool ret = false;
@@ -458,7 +463,7 @@ bool link_dp_dpia_allocate_usb4_bandwidth_for_stream(struct dc_link *link, int r
DC_LOG_DEBUG("%s: ENTER: link(%d), hpd_status(%d), current allocated_bw(%d), req_bw(%d)\n",
__func__, link->link_index, link->hpd_status,
- link->dpia_bw_alloc_config.sink_allocated_bw, req_bw);
+ link->dpia_bw_alloc_config.allocated_bw, req_bw);
if (!get_bw_alloc_proceed_flag(link))
goto out;
@@ -523,3 +528,30 @@ bool dpia_validate_usb4_bw(struct dc_link **link, int *bw_needed_per_dpia, const
return ret;
}
+
+int link_dp_dpia_get_dp_overhead_in_dp_tunneling(struct dc_link *link)
+{
+ int dp_overhead = 0, link_mst_overhead = 0;
+
+ if (!get_bw_alloc_proceed_flag((link)))
+ return dp_overhead;
+
+ /* if its mst link, add MTPH overhead */
+ if ((link->type == dc_connection_mst_branch) &&
+ !link->dpcd_caps.channel_coding_cap.bits.DP_128b_132b_SUPPORTED) {
+ /* For 8b/10b encoding: MTP is 64 time slots long, slot 0 is used for MTPH
+ * MST overhead is 1/64 of link bandwidth (excluding any overhead)
+ */
+ const struct dc_link_settings *link_cap =
+ dc_link_get_link_cap(link);
+ uint32_t link_bw_in_kbps = (uint32_t)link_cap->link_rate *
+ (uint32_t)link_cap->lane_count *
+ LINK_RATE_REF_FREQ_IN_KHZ * 8;
+ link_mst_overhead = (link_bw_in_kbps / 64) + ((link_bw_in_kbps % 64) ? 1 : 0);
+ }
+
+ /* add all the overheads */
+ dp_overhead = link_mst_overhead;
+
+ return dp_overhead;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h
index 981bc4eb6120e76ad959435be7ad716cdc498926..3b6d8494f9d5da4ceb05711c9596007ac73f08a2 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h
@@ -99,4 +99,13 @@ void dpia_handle_bw_alloc_response(struct dc_link *link, uint8_t bw, uint8_t res
*/
bool dpia_validate_usb4_bw(struct dc_link **link, int *bw_needed, const unsigned int num_dpias);
+/*
+ * Obtain all the DP overheads in dp tunneling for the dpia link
+ *
+ * @link: pointer to the dc_link struct instance
+ *
+ * return: DP overheads in DP tunneling
+ */
+int link_dp_dpia_get_dp_overhead_in_dp_tunneling(struct dc_link *link);
+
#endif /* DC_INC_LINK_DP_DPIA_BW_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
index 7f1196528218692c98f1f15375f153dfe56fe514..046d3e205415311cd63a98aa3c0e59c8aaea2e89 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
@@ -930,8 +930,8 @@ bool edp_get_replay_state(const struct dc_link *link, uint64_t *state)
bool edp_setup_replay(struct dc_link *link, const struct dc_stream_state *stream)
{
/* To-do: Setup Replay */
- struct dc *dc = link->ctx->dc;
- struct dmub_replay *replay = dc->res_pool->replay;
+ struct dc *dc;
+ struct dmub_replay *replay;
int i;
unsigned int panel_inst;
struct replay_context replay_context = { 0 };
@@ -947,6 +947,10 @@ bool edp_setup_replay(struct dc_link *link, const struct dc_stream_state *stream
if (!link)
return false;
+ dc = link->ctx->dc;
+
+ replay = dc->res_pool->replay;
+
if (!replay)
return false;
@@ -975,8 +979,7 @@ bool edp_setup_replay(struct dc_link *link, const struct dc_stream_state *stream
replay_context.line_time_in_ns = lineTimeInNs;
- if (replay)
- link->replay_settings.replay_feature_enabled =
+ link->replay_settings.replay_feature_enabled =
replay->funcs->replay_copy_settings(replay, link, &replay_context, panel_inst);
if (link->replay_settings.replay_feature_enabled) {
diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c b/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c
index 91ea0d4da06a9443bb199759fde0c75ae44fc8f3..82349354332548e160494c23bee15acaa18b7630 100644
--- a/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c
@@ -166,12 +166,6 @@ static bool optc32_disable_crtc(struct timing_generator *optc)
{
struct optc *optc1 = DCN10TG_FROM_TG(optc);
- /* disable otg request until end of the first line
- * in the vertical blank region
- */
- REG_UPDATE(OTG_CONTROL,
- OTG_MASTER_EN, 0);
-
REG_UPDATE_5(OPTC_DATA_SOURCE_SELECT,
OPTC_SEG0_SRC_SEL, 0xf,
OPTC_SEG1_SRC_SEL, 0xf,
@@ -179,6 +173,15 @@ static bool optc32_disable_crtc(struct timing_generator *optc)
OPTC_SEG3_SRC_SEL, 0xf,
OPTC_NUM_OF_INPUT_SEGMENT, 0);
+ REG_UPDATE(OPTC_MEMORY_CONFIG,
+ OPTC_MEM_SEL, 0);
+
+ /* disable otg request until end of the first line
+ * in the vertical blank region
+ */
+ REG_UPDATE(OTG_CONTROL,
+ OTG_MASTER_EN, 0);
+
REG_UPDATE(CONTROL,
VTG0_ENABLE, 0);
@@ -205,6 +208,13 @@ static void optc32_disable_phantom_otg(struct timing_generator *optc)
{
struct optc *optc1 = DCN10TG_FROM_TG(optc);
+ REG_UPDATE_5(OPTC_DATA_SOURCE_SELECT,
+ OPTC_SEG0_SRC_SEL, 0xf,
+ OPTC_SEG1_SRC_SEL, 0xf,
+ OPTC_SEG2_SRC_SEL, 0xf,
+ OPTC_SEG3_SRC_SEL, 0xf,
+ OPTC_NUM_OF_INPUT_SEGMENT, 0);
+
REG_UPDATE(OTG_CONTROL, OTG_MASTER_EN, 0);
}
diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn35/dcn35_optc.c b/drivers/gpu/drm/amd/display/dc/optc/dcn35/dcn35_optc.c
index 08a59cf449cae5c27fe7dbe8fc1b2f847f462f9f..5b154750885030e171a483d30e014aa8f4bff8a1 100644
--- a/drivers/gpu/drm/amd/display/dc/optc/dcn35/dcn35_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/optc/dcn35/dcn35_optc.c
@@ -138,12 +138,6 @@ static bool optc35_disable_crtc(struct timing_generator *optc)
{
struct optc *optc1 = DCN10TG_FROM_TG(optc);
- /* disable otg request until end of the first line
- * in the vertical blank region
- */
- REG_UPDATE(OTG_CONTROL,
- OTG_MASTER_EN, 0);
-
REG_UPDATE_5(OPTC_DATA_SOURCE_SELECT,
OPTC_SEG0_SRC_SEL, 0xf,
OPTC_SEG1_SRC_SEL, 0xf,
@@ -151,6 +145,15 @@ static bool optc35_disable_crtc(struct timing_generator *optc)
OPTC_SEG3_SRC_SEL, 0xf,
OPTC_NUM_OF_INPUT_SEGMENT, 0);
+ REG_UPDATE(OPTC_MEMORY_CONFIG,
+ OPTC_MEM_SEL, 0);
+
+ /* disable otg request until end of the first line
+ * in the vertical blank region
+ */
+ REG_UPDATE(OTG_CONTROL,
+ OTG_MASTER_EN, 0);
+
REG_UPDATE(CONTROL,
VTG0_ENABLE, 0);
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
index ac04a9c9a3d86808000942fd4eae12d5f9fdea66..c4d71e7f18af47ba47dbc89e1a9098a0a4eade04 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
@@ -1899,7 +1899,7 @@ int dcn32_populate_dml_pipes_from_context(
static struct dc_cap_funcs cap_funcs = {
.get_dcc_compression_cap = dcn20_get_dcc_compression_cap,
- .get_subvp_en = resource_subvp_in_use,
+ .get_subvp_en = dcn32_subvp_in_use,
};
void dcn32_calculate_wm_and_dlg(struct dc *dc, struct dc_state *context,
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h
index 62611acd4bcb522c78fafdaa8d811101b65b5f42..0c87b0fabba7d96ff38180900e41f1438419912c 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h
@@ -131,6 +131,9 @@ void dcn32_merge_pipes_for_subvp(struct dc *dc,
bool dcn32_all_pipes_have_stream_and_plane(struct dc *dc,
struct dc_state *context);
+bool dcn32_subvp_in_use(struct dc *dc,
+ struct dc_state *context);
+
bool dcn32_mpo_in_use(struct dc_state *context);
bool dcn32_any_surfaces_rotated(struct dc *dc, struct dc_state *context);
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c
index e1ab207c46f15b1c6dd6e13ec35f6049674c0444..74412e5f03fefbaa9350982ac92bc528cc8e80e8 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c
@@ -1574,7 +1574,7 @@ static void dcn321_destroy_resource_pool(struct resource_pool **pool)
static struct dc_cap_funcs cap_funcs = {
.get_dcc_compression_cap = dcn20_get_dcc_compression_cap,
- .get_subvp_en = resource_subvp_in_use,
+ .get_subvp_en = dcn32_subvp_in_use,
};
static void dcn321_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params)
diff --git a/drivers/gpu/drm/amd/display/include/audio_types.h b/drivers/gpu/drm/amd/display/include/audio_types.h
index 66a54da0641ce11feb10e1d777395f9bcd85f658..915a031a43cb286fdb03f2fb2788d0fa9e539b59 100644
--- a/drivers/gpu/drm/amd/display/include/audio_types.h
+++ b/drivers/gpu/drm/amd/display/include/audio_types.h
@@ -64,7 +64,7 @@ enum audio_dto_source {
/* PLL information required for AZALIA DTO calculation */
struct audio_pll_info {
- uint32_t dp_dto_source_clock_in_khz;
+ uint32_t audio_dto_source_clock_in_khz;
uint32_t feed_back_divider;
enum audio_dto_source dto_source;
bool ss_enabled;
diff --git a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h
index 7ee3d291120d5429d879745c2e63af38cd79f371..6f80bfa7e41ac9c1bdd2faaba4c298cc3f4f9d34 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h
@@ -8707,10 +8707,10 @@
#define regBIF_BX1_MM_CFGREGS_CNTL_BASE_IDX 2
#define regBIF_BX1_BX_RESET_CNTL 0x00f0
#define regBIF_BX1_BX_RESET_CNTL_BASE_IDX 2
-#define regBIF_BX1_INTERRUPT_CNTL 0x8e11
-#define regBIF_BX1_INTERRUPT_CNTL_BASE_IDX 5
-#define regBIF_BX1_INTERRUPT_CNTL2 0x8e12
-#define regBIF_BX1_INTERRUPT_CNTL2_BASE_IDX 5
+#define regBIF_BX1_INTERRUPT_CNTL 0x00f1
+#define regBIF_BX1_INTERRUPT_CNTL_BASE_IDX 2
+#define regBIF_BX1_INTERRUPT_CNTL2 0x00f2
+#define regBIF_BX1_INTERRUPT_CNTL2_BASE_IDX 2
#define regBIF_BX1_CLKREQB_PAD_CNTL 0x00f8
#define regBIF_BX1_CLKREQB_PAD_CNTL_BASE_IDX 2
#define regBIF_BX1_BIF_FEATURES_CONTROL_MISC 0x00fb
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index f3cb490fe79b16baa5a917c8304b6fbfcfeb8729..087d57850304c45193a7f5de336953c1dec9cbba 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -4349,11 +4349,19 @@ static int amdgpu_debugfs_pm_info_pp(struct seq_file *m, struct amdgpu_device *a
if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VDDNB, (void *)&value, &size))
seq_printf(m, "\t%u mV (VDDNB)\n", value);
size = sizeof(uint32_t);
- if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_AVG_POWER, (void *)&query, &size))
- seq_printf(m, "\t%u.%02u W (average GPU)\n", query >> 8, query & 0xff);
+ if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_AVG_POWER, (void *)&query, &size)) {
+ if (adev->flags & AMD_IS_APU)
+ seq_printf(m, "\t%u.%02u W (average SoC including CPU)\n", query >> 8, query & 0xff);
+ else
+ seq_printf(m, "\t%u.%02u W (average SoC)\n", query >> 8, query & 0xff);
+ }
size = sizeof(uint32_t);
- if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_INPUT_POWER, (void *)&query, &size))
- seq_printf(m, "\t%u.%02u W (current GPU)\n", query >> 8, query & 0xff);
+ if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_INPUT_POWER, (void *)&query, &size)) {
+ if (adev->flags & AMD_IS_APU)
+ seq_printf(m, "\t%u.%02u W (current SoC including CPU)\n", query >> 8, query & 0xff);
+ else
+ seq_printf(m, "\t%u.%02u W (current SoC)\n", query >> 8, query & 0xff);
+ }
size = sizeof(value);
seq_printf(m, "\n");
@@ -4379,9 +4387,9 @@ static int amdgpu_debugfs_pm_info_pp(struct seq_file *m, struct amdgpu_device *a
/* VCN clocks */
if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VCN_POWER_STATE, (void *)&value, &size)) {
if (!value) {
- seq_printf(m, "VCN: Disabled\n");
+ seq_printf(m, "VCN: Powered down\n");
} else {
- seq_printf(m, "VCN: Enabled\n");
+ seq_printf(m, "VCN: Powered up\n");
if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_DCLK, (void *)&value, &size))
seq_printf(m, "\t%u MHz (DCLK)\n", value/100);
if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_VCLK, (void *)&value, &size))
@@ -4393,9 +4401,9 @@ static int amdgpu_debugfs_pm_info_pp(struct seq_file *m, struct amdgpu_device *a
/* UVD clocks */
if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_POWER, (void *)&value, &size)) {
if (!value) {
- seq_printf(m, "UVD: Disabled\n");
+ seq_printf(m, "UVD: Powered down\n");
} else {
- seq_printf(m, "UVD: Enabled\n");
+ seq_printf(m, "UVD: Powered up\n");
if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_DCLK, (void *)&value, &size))
seq_printf(m, "\t%u MHz (DCLK)\n", value/100);
if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_VCLK, (void *)&value, &size))
@@ -4407,9 +4415,9 @@ static int amdgpu_debugfs_pm_info_pp(struct seq_file *m, struct amdgpu_device *a
/* VCE clocks */
if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VCE_POWER, (void *)&value, &size)) {
if (!value) {
- seq_printf(m, "VCE: Disabled\n");
+ seq_printf(m, "VCE: Powered down\n");
} else {
- seq_printf(m, "VCE: Enabled\n");
+ seq_printf(m, "VCE: Powered up\n");
if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VCE_ECCLK, (void *)&value, &size))
seq_printf(m, "\t%u MHz (ECCLK)\n", value/100);
}
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c
index f2a55c1413f597a4d643d1a2c99367517bdff17e..17882f8dfdd34f92d5d37a9b0ee37f4a7d1bb406 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c
@@ -200,7 +200,7 @@ static int get_platform_power_management_table(
struct pp_hwmgr *hwmgr,
ATOM_Tonga_PPM_Table *atom_ppm_table)
{
- struct phm_ppm_table *ptr = kzalloc(sizeof(ATOM_Tonga_PPM_Table), GFP_KERNEL);
+ struct phm_ppm_table *ptr = kzalloc(sizeof(*ptr), GFP_KERNEL);
struct phm_ppt_v1_information *pp_table_information =
(struct phm_ppt_v1_information *)(hwmgr->pptable);
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
index b1a8799e2dee320390d239c6242600d4d30cdc39..aa91730e4eaffdf7760c844a7722aa1dedcb42d9 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
@@ -3999,6 +3999,7 @@ static int smu7_read_sensor(struct pp_hwmgr *hwmgr, int idx,
uint32_t sclk, mclk, activity_percent;
uint32_t offset, val_vid;
struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
+ struct amdgpu_device *adev = hwmgr->adev;
/* size must be at least 4 bytes for all sensors */
if (*size < 4)
@@ -4042,7 +4043,21 @@ static int smu7_read_sensor(struct pp_hwmgr *hwmgr, int idx,
*size = 4;
return 0;
case AMDGPU_PP_SENSOR_GPU_INPUT_POWER:
- return smu7_get_gpu_power(hwmgr, (uint32_t *)value);
+ if ((adev->asic_type != CHIP_HAWAII) &&
+ (adev->asic_type != CHIP_BONAIRE) &&
+ (adev->asic_type != CHIP_FIJI) &&
+ (adev->asic_type != CHIP_TONGA))
+ return smu7_get_gpu_power(hwmgr, (uint32_t *)value);
+ else
+ return -EOPNOTSUPP;
+ case AMDGPU_PP_SENSOR_GPU_AVG_POWER:
+ if ((adev->asic_type != CHIP_HAWAII) &&
+ (adev->asic_type != CHIP_BONAIRE) &&
+ (adev->asic_type != CHIP_FIJI) &&
+ (adev->asic_type != CHIP_TONGA))
+ return -EOPNOTSUPP;
+ else
+ return smu7_get_gpu_power(hwmgr, (uint32_t *)value);
case AMDGPU_PP_SENSOR_VDDGFX:
if ((data->vr_config & VRCONF_VDDGFX_MASK) ==
(VR_SVI2_PLANE_2 << VRCONF_VDDGFX_SHIFT))
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index cc2a02ceea85955bdb8f3904aebe9ba4fa7ac816..3c98a8a0386a2612d0470dd6dbd767a6ecc308b0 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -970,7 +970,9 @@ static int smu_v13_0_6_print_clks(struct smu_context *smu, char *buf, int size,
if (i < (clocks.num_levels - 1))
clk2 = clocks.data[i + 1].clocks_in_khz / 1000;
- if (curr_clk >= clk1 && curr_clk < clk2) {
+ if (curr_clk == clk1) {
+ level = i;
+ } else if (curr_clk >= clk1 && curr_clk < clk2) {
level = (curr_clk - clk1) <= (clk2 - curr_clk) ?
i :
i + 1;
@@ -2234,17 +2236,18 @@ static int smu_v13_0_6_mode2_reset(struct smu_context *smu)
continue;
}
- if (ret) {
- dev_err(adev->dev,
- "failed to send mode2 message \tparam: 0x%08x error code %d\n",
- SMU_RESET_MODE_2, ret);
+ if (ret)
goto out;
- }
+
} while (ret == -ETIME && timeout);
out:
mutex_unlock(&smu->message_lock);
+ if (ret)
+ dev_err(adev->dev, "failed to send mode2 reset, error code %d",
+ ret);
+
return ret;
}
diff --git a/drivers/gpu/drm/nouveau/nouveau_vmm.c b/drivers/gpu/drm/nouveau/nouveau_vmm.c
index a6602c0126715635d6328c2fb295d4195b7dd873..3dda885df5b223dc2b637592e50cc7e958b5cbb7 100644
--- a/drivers/gpu/drm/nouveau/nouveau_vmm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_vmm.c
@@ -108,6 +108,9 @@ nouveau_vma_new(struct nouveau_bo *nvbo, struct nouveau_vmm *vmm,
} else {
ret = nvif_vmm_get(&vmm->vmm, PTES, false, mem->mem.page, 0,
mem->mem.size, &tmp);
+ if (ret)
+ goto done;
+
vma->addr = tmp.addr;
}
diff --git a/drivers/gpu/drm/ttm/ttm_device.c b/drivers/gpu/drm/ttm/ttm_device.c
index f5187b384ae9ac8eedede8e6a0d4d56eb8af1670..4130945052ed2a523d50e1d39d028ca3741c6605 100644
--- a/drivers/gpu/drm/ttm/ttm_device.c
+++ b/drivers/gpu/drm/ttm/ttm_device.c
@@ -195,7 +195,7 @@ int ttm_device_init(struct ttm_device *bdev, const struct ttm_device_funcs *func
bool use_dma_alloc, bool use_dma32)
{
struct ttm_global *glob = &ttm_glob;
- int ret;
+ int ret, nid;
if (WARN_ON(vma_manager == NULL))
return -EINVAL;
@@ -215,7 +215,12 @@ int ttm_device_init(struct ttm_device *bdev, const struct ttm_device_funcs *func
ttm_sys_man_init(bdev);
- ttm_pool_init(&bdev->pool, dev, dev_to_node(dev), use_dma_alloc, use_dma32);
+ if (dev)
+ nid = dev_to_node(dev);
+ else
+ nid = NUMA_NO_NODE;
+
+ ttm_pool_init(&bdev->pool, dev, nid, use_dma_alloc, use_dma32);
bdev->vma_manager = vma_manager;
spin_lock_init(&bdev->lru_lock);
diff --git a/drivers/gpu/drm/xe/Kconfig b/drivers/gpu/drm/xe/Kconfig
index 1cced50d8d8c9dadcb40f7ebe75cf7474170772b..e36ae1f0d8859fc82f2e0a9ed06f8e7ee6387372 100644
--- a/drivers/gpu/drm/xe/Kconfig
+++ b/drivers/gpu/drm/xe/Kconfig
@@ -47,7 +47,7 @@ config DRM_XE
config DRM_XE_DISPLAY
bool "Enable display support"
- depends on DRM_XE && EXPERT && DRM_XE=m
+ depends on DRM_XE && DRM_XE=m
select FB_IOMEM_HELPERS
select I2C
select I2C_ALGOBIT
diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile
index 53bd2a8ba1ae5cea2535c59047d028f18bec8e65..efcf0ab7a1a69d35271b5655c5a746e992459b02 100644
--- a/drivers/gpu/drm/xe/Makefile
+++ b/drivers/gpu/drm/xe/Makefile
@@ -17,7 +17,6 @@ subdir-ccflags-y += $(call cc-option, -Wunused-const-variable)
subdir-ccflags-y += $(call cc-option, -Wpacked-not-aligned)
subdir-ccflags-y += $(call cc-option, -Wformat-overflow)
subdir-ccflags-y += $(call cc-option, -Wformat-truncation)
-subdir-ccflags-y += $(call cc-option, -Wstringop-overflow)
subdir-ccflags-y += $(call cc-option, -Wstringop-truncation)
# The following turn off the warnings enabled by -Wextra
ifeq ($(findstring 2, $(KBUILD_EXTRA_WARN)),)
diff --git a/drivers/gpu/drm/xe/tests/xe_bo.c b/drivers/gpu/drm/xe/tests/xe_bo.c
index 412b2e7ce40cb3ea38b6f5c76fb293009c10c3a2..3436fd9cf2b2738446608990a5f5be1a4f33fb2e 100644
--- a/drivers/gpu/drm/xe/tests/xe_bo.c
+++ b/drivers/gpu/drm/xe/tests/xe_bo.c
@@ -125,14 +125,13 @@ static void ccs_test_run_tile(struct xe_device *xe, struct xe_tile *tile,
bo = xe_bo_create_user(xe, NULL, NULL, SZ_1M, DRM_XE_GEM_CPU_CACHING_WC,
ttm_bo_type_device, bo_flags);
-
- xe_bo_lock(bo, false);
-
if (IS_ERR(bo)) {
KUNIT_FAIL(test, "Failed to create bo.\n");
return;
}
+ xe_bo_lock(bo, false);
+
kunit_info(test, "Verifying that CCS data is cleared on creation.\n");
ret = ccs_test_migrate(tile, bo, false, 0ULL, 0xdeadbeefdeadbeefULL,
test);
diff --git a/drivers/gpu/drm/xe/tests/xe_migrate.c b/drivers/gpu/drm/xe/tests/xe_migrate.c
index 7a32faa2f68880dcd4cb5b217ff9986153b990cb..a6523df0f1d39fbe7f0354d404f95886a3d56424 100644
--- a/drivers/gpu/drm/xe/tests/xe_migrate.c
+++ b/drivers/gpu/drm/xe/tests/xe_migrate.c
@@ -331,7 +331,7 @@ static void xe_migrate_sanity_test(struct xe_migrate *m, struct kunit *test)
xe_res_first_sg(xe_bo_sg(pt), 0, pt->size, &src_it);
emit_pte(m, bb, NUM_KERNEL_PDE - 1, xe_bo_is_vram(pt), false,
- &src_it, XE_PAGE_SIZE, pt);
+ &src_it, XE_PAGE_SIZE, pt->ttm.resource);
run_sanity_job(m, xe, bb, bb->len, "Writing PTE for our fake PT", test);
diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 8e4a3b1f6b938e5a76b8fc6640058ca63a30c709..0b0e262e2166d69da1063915fa4c6eeedfd38bd6 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -125,9 +125,9 @@ static struct xe_mem_region *res_to_mem_region(struct ttm_resource *res)
static void try_add_system(struct xe_device *xe, struct xe_bo *bo,
u32 bo_flags, u32 *c)
{
- xe_assert(xe, *c < ARRAY_SIZE(bo->placements));
-
if (bo_flags & XE_BO_CREATE_SYSTEM_BIT) {
+ xe_assert(xe, *c < ARRAY_SIZE(bo->placements));
+
bo->placements[*c] = (struct ttm_place) {
.mem_type = XE_PL_TT,
};
@@ -145,6 +145,8 @@ static void add_vram(struct xe_device *xe, struct xe_bo *bo,
struct xe_mem_region *vram;
u64 io_size;
+ xe_assert(xe, *c < ARRAY_SIZE(bo->placements));
+
vram = to_xe_ttm_vram_mgr(ttm_manager_type(&xe->ttm, mem_type))->vram;
xe_assert(xe, vram && vram->usable_size);
io_size = vram->io_size;
@@ -175,8 +177,6 @@ static void add_vram(struct xe_device *xe, struct xe_bo *bo,
static void try_add_vram(struct xe_device *xe, struct xe_bo *bo,
u32 bo_flags, u32 *c)
{
- xe_assert(xe, *c < ARRAY_SIZE(bo->placements));
-
if (bo->props.preferred_gt == XE_GT1) {
if (bo_flags & XE_BO_CREATE_VRAM1_BIT)
add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM1, c);
@@ -193,9 +193,9 @@ static void try_add_vram(struct xe_device *xe, struct xe_bo *bo,
static void try_add_stolen(struct xe_device *xe, struct xe_bo *bo,
u32 bo_flags, u32 *c)
{
- xe_assert(xe, *c < ARRAY_SIZE(bo->placements));
-
if (bo_flags & XE_BO_CREATE_STOLEN_BIT) {
+ xe_assert(xe, *c < ARRAY_SIZE(bo->placements));
+
bo->placements[*c] = (struct ttm_place) {
.mem_type = XE_PL_STOLEN,
.flags = bo_flags & (XE_BO_CREATE_PINNED_BIT |
@@ -442,7 +442,7 @@ static int xe_ttm_io_mem_reserve(struct ttm_device *bdev,
if (vram->mapping &&
mem->placement & TTM_PL_FLAG_CONTIGUOUS)
- mem->bus.addr = (u8 *)vram->mapping +
+ mem->bus.addr = (u8 __force *)vram->mapping +
mem->bus.offset;
mem->bus.offset += vram->io_start;
@@ -734,7 +734,7 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict,
/* Create a new VMAP once kernel BO back in VRAM */
if (!ret && resource_is_vram(new_mem)) {
struct xe_mem_region *vram = res_to_mem_region(new_mem);
- void *new_addr = vram->mapping +
+ void __iomem *new_addr = vram->mapping +
(new_mem->start << PAGE_SHIFT);
if (XE_WARN_ON(new_mem->start == XE_BO_INVALID_OFFSET)) {
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index d9ae77fe7382ddf9997858995fe255108f7c5944..b8d8da5466708c6903ccb3ade3852a7ac9911235 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -484,7 +484,7 @@ int xe_device_probe(struct xe_device *xe)
err = xe_device_set_has_flat_ccs(xe);
if (err)
- return err;
+ goto err_irq_shutdown;
err = xe_mmio_probe_vram(xe);
if (err)
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index c45ef17b347323801d397a964e53aa3fc5b060f4..5dc9127a20293e1ebb56c3684e2fdb7e6f425b43 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -97,7 +97,7 @@ struct xe_mem_region {
*/
resource_size_t actual_physical_size;
/** @mapping: pointer to VRAM mappable space */
- void *__iomem mapping;
+ void __iomem *mapping;
};
/**
@@ -146,7 +146,7 @@ struct xe_tile {
size_t size;
/** @regs: pointer to tile's MMIO space (starting with registers) */
- void *regs;
+ void __iomem *regs;
} mmio;
/**
@@ -159,7 +159,7 @@ struct xe_tile {
size_t size;
/** @regs: pointer to tile's additional MMIO-extension space */
- void *regs;
+ void __iomem *regs;
} mmio_ext;
/** @mem: memory management info for tile */
@@ -301,7 +301,7 @@ struct xe_device {
/** @size: size of MMIO space for device */
size_t size;
/** @regs: pointer to MMIO space for device */
- void *regs;
+ void __iomem *regs;
} mmio;
/** @mem: memory info for device */
diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
index d30c0d0689bcc7d4ae55cdd7fc93b116826160e6..b853feed9ccc15eefab7f0ccdf070096521e6015 100644
--- a/drivers/gpu/drm/xe/xe_exec.c
+++ b/drivers/gpu/drm/xe/xe_exec.c
@@ -115,7 +115,7 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
struct xe_sched_job *job;
struct dma_fence *rebind_fence;
struct xe_vm *vm;
- bool write_locked;
+ bool write_locked, skip_retry = false;
ktime_t end = 0;
int err = 0;
@@ -227,7 +227,8 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
}
if (xe_exec_queue_is_lr(q) && xe_exec_queue_ring_full(q)) {
- err = -EWOULDBLOCK;
+ err = -EWOULDBLOCK; /* Aliased to -EAGAIN */
+ skip_retry = true;
goto err_exec;
}
@@ -337,7 +338,7 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
up_write(&vm->lock);
else
up_read(&vm->lock);
- if (err == -EAGAIN)
+ if (err == -EAGAIN && !skip_retry)
goto retry;
err_syncs:
for (i = 0; i < num_syncs; i++)
diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 44fe8097b7cdac8d5c89a3bf00168cf3b8343ca7..bcfc4127c7c59f0fffc8e40df70a5b1c8222495f 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -67,6 +67,11 @@ static struct xe_exec_queue *__xe_exec_queue_create(struct xe_device *xe,
q->sched_props.timeslice_us = hwe->eclass->sched_props.timeslice_us;
q->sched_props.preempt_timeout_us =
hwe->eclass->sched_props.preempt_timeout_us;
+ if (q->flags & EXEC_QUEUE_FLAG_KERNEL &&
+ q->flags & EXEC_QUEUE_FLAG_HIGH_PRIORITY)
+ q->sched_props.priority = XE_EXEC_QUEUE_PRIORITY_KERNEL;
+ else
+ q->sched_props.priority = XE_EXEC_QUEUE_PRIORITY_NORMAL;
if (xe_exec_queue_is_parallel(q)) {
q->parallel.composite_fence_ctx = dma_fence_context_alloc(1);
diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h
index 3d7e704ec3d9f33b9c0e47867bb58135ea01df91..8d4b7feb8c306b8a406a46f74c5cad2a430bdef3 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue_types.h
+++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h
@@ -52,8 +52,6 @@ struct xe_exec_queue {
struct xe_vm *vm;
/** @class: class of this exec queue */
enum xe_engine_class class;
- /** @priority: priority of this exec queue */
- enum xe_exec_queue_priority priority;
/**
* @logical_mask: logical mask of where job submitted to exec queue can run
*/
@@ -84,6 +82,8 @@ struct xe_exec_queue {
#define EXEC_QUEUE_FLAG_VM BIT(4)
/* child of VM queue for multi-tile VM jobs */
#define EXEC_QUEUE_FLAG_BIND_ENGINE_CHILD BIT(5)
+/* kernel exec_queue only, set priority to highest level */
+#define EXEC_QUEUE_FLAG_HIGH_PRIORITY BIT(6)
/**
* @flags: flags for this exec queue, should statically setup aside from ban
@@ -142,6 +142,8 @@ struct xe_exec_queue {
u32 timeslice_us;
/** @preempt_timeout_us: preemption timeout in micro-seconds */
u32 preempt_timeout_us;
+ /** @priority: priority of this exec queue */
+ enum xe_exec_queue_priority priority;
} sched_props;
/** @compute: compute exec queue state */
diff --git a/drivers/gpu/drm/xe/xe_gt_freq.c b/drivers/gpu/drm/xe/xe_gt_freq.c
index 3adfa6686e7cf9eb2763bccc28b7a0a382dd4834..e5b0f4ecdbe8261ee5c3fa9530a30dc2fd46c14b 100644
--- a/drivers/gpu/drm/xe/xe_gt_freq.c
+++ b/drivers/gpu/drm/xe/xe_gt_freq.c
@@ -196,6 +196,9 @@ void xe_gt_freq_init(struct xe_gt *gt)
struct xe_device *xe = gt_to_xe(gt);
int err;
+ if (xe->info.skip_guc_pc)
+ return;
+
gt->freq = kobject_create_and_add("freq0", gt->sysfs);
if (!gt->freq) {
drm_warn(&xe->drm, "failed to add freq0 directory to %s\n",
diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c
index 482cb0df9f15bc28d9f5c2a0ea194319f1b2a21a..0a61390c64a7b7100113641f2e073f4ce58d358e 100644
--- a/drivers/gpu/drm/xe/xe_guc.c
+++ b/drivers/gpu/drm/xe/xe_guc.c
@@ -60,7 +60,12 @@ static u32 guc_ctl_debug_flags(struct xe_guc *guc)
static u32 guc_ctl_feature_flags(struct xe_guc *guc)
{
- return GUC_CTL_ENABLE_SLPC;
+ u32 flags = 0;
+
+ if (!guc_to_xe(guc)->info.skip_guc_pc)
+ flags |= GUC_CTL_ENABLE_SLPC;
+
+ return flags;
}
static u32 guc_ctl_log_params_flags(struct xe_guc *guc)
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 21ac68e3246f86f1e16d05880da8aa9315769ecb..54ffcfcdd41f9ce3c590f5814fcbe3d3535946ac 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -421,7 +421,7 @@ static void init_policies(struct xe_guc *guc, struct xe_exec_queue *q)
{
struct exec_queue_policy policy;
struct xe_device *xe = guc_to_xe(guc);
- enum xe_exec_queue_priority prio = q->priority;
+ enum xe_exec_queue_priority prio = q->sched_props.priority;
u32 timeslice_us = q->sched_props.timeslice_us;
u32 preempt_timeout_us = q->sched_props.preempt_timeout_us;
@@ -1231,7 +1231,6 @@ static int guc_exec_queue_init(struct xe_exec_queue *q)
err = xe_sched_entity_init(&ge->entity, sched);
if (err)
goto err_sched;
- q->priority = XE_EXEC_QUEUE_PRIORITY_NORMAL;
if (xe_exec_queue_is_lr(q))
INIT_WORK(&q->guc->lr_tdr, xe_guc_exec_queue_lr_cleanup);
@@ -1301,15 +1300,15 @@ static int guc_exec_queue_set_priority(struct xe_exec_queue *q,
{
struct xe_sched_msg *msg;
- if (q->priority == priority || exec_queue_killed_or_banned(q))
+ if (q->sched_props.priority == priority || exec_queue_killed_or_banned(q))
return 0;
msg = kmalloc(sizeof(*msg), GFP_KERNEL);
if (!msg)
return -ENOMEM;
+ q->sched_props.priority = priority;
guc_exec_queue_add_msg(q, msg, SET_SCHED_PROPS);
- q->priority = priority;
return 0;
}
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index adf1dab5eba253297fb8b4ae4c2c5b5f15b2ec7a..e05e9e7282b68abdcab839a9134efd09e60750f2 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -62,6 +62,8 @@ struct xe_migrate {
* out of the pt_bo.
*/
struct drm_suballoc_manager vm_update_sa;
+ /** @min_chunk_size: For dgfx, Minimum chunk size */
+ u64 min_chunk_size;
};
#define MAX_PREEMPTDISABLE_TRANSFER SZ_8M /* Around 1ms. */
@@ -344,7 +346,8 @@ struct xe_migrate *xe_migrate_init(struct xe_tile *tile)
m->q = xe_exec_queue_create(xe, vm, logical_mask, 1, hwe,
EXEC_QUEUE_FLAG_KERNEL |
- EXEC_QUEUE_FLAG_PERMANENT);
+ EXEC_QUEUE_FLAG_PERMANENT |
+ EXEC_QUEUE_FLAG_HIGH_PRIORITY);
} else {
m->q = xe_exec_queue_create_class(xe, primary_gt, vm,
XE_ENGINE_CLASS_COPY,
@@ -355,8 +358,6 @@ struct xe_migrate *xe_migrate_init(struct xe_tile *tile)
xe_vm_close_and_put(vm);
return ERR_CAST(m->q);
}
- if (xe->info.has_usm)
- m->q->priority = XE_EXEC_QUEUE_PRIORITY_KERNEL;
mutex_init(&m->job_mutex);
@@ -364,6 +365,19 @@ struct xe_migrate *xe_migrate_init(struct xe_tile *tile)
if (err)
return ERR_PTR(err);
+ if (IS_DGFX(xe)) {
+ if (xe_device_has_flat_ccs(xe))
+ /* min chunk size corresponds to 4K of CCS Metadata */
+ m->min_chunk_size = SZ_4K * SZ_64K /
+ xe_device_ccs_bytes(xe, SZ_64K);
+ else
+ /* Somewhat arbitrary to avoid a huge amount of blits */
+ m->min_chunk_size = SZ_64K;
+ m->min_chunk_size = roundup_pow_of_two(m->min_chunk_size);
+ drm_dbg(&xe->drm, "Migrate min chunk size is 0x%08llx\n",
+ (unsigned long long)m->min_chunk_size);
+ }
+
return m;
}
@@ -375,16 +389,35 @@ static u64 max_mem_transfer_per_pass(struct xe_device *xe)
return MAX_PREEMPTDISABLE_TRANSFER;
}
-static u64 xe_migrate_res_sizes(struct xe_device *xe, struct xe_res_cursor *cur)
+static u64 xe_migrate_res_sizes(struct xe_migrate *m, struct xe_res_cursor *cur)
{
- /*
- * For VRAM we use identity mapped pages so we are limited to current
- * cursor size. For system we program the pages ourselves so we have no
- * such limitation.
- */
- return min_t(u64, max_mem_transfer_per_pass(xe),
- mem_type_is_vram(cur->mem_type) ? cur->size :
- cur->remaining);
+ struct xe_device *xe = tile_to_xe(m->tile);
+ u64 size = min_t(u64, max_mem_transfer_per_pass(xe), cur->remaining);
+
+ if (mem_type_is_vram(cur->mem_type)) {
+ /*
+ * VRAM we want to blit in chunks with sizes aligned to
+ * min_chunk_size in order for the offset to CCS metadata to be
+ * page-aligned. If it's the last chunk it may be smaller.
+ *
+ * Another constraint is that we need to limit the blit to
+ * the VRAM block size, unless size is smaller than
+ * min_chunk_size.
+ */
+ u64 chunk = max_t(u64, cur->size, m->min_chunk_size);
+
+ size = min_t(u64, size, chunk);
+ if (size > m->min_chunk_size)
+ size = round_down(size, m->min_chunk_size);
+ }
+
+ return size;
+}
+
+static bool xe_migrate_allow_identity(u64 size, const struct xe_res_cursor *cur)
+{
+ /* If the chunk is not fragmented, allow identity map. */
+ return cur->size >= size;
}
static u32 pte_update_size(struct xe_migrate *m,
@@ -397,7 +430,12 @@ static u32 pte_update_size(struct xe_migrate *m,
u32 cmds = 0;
*L0_pt = pt_ofs;
- if (!is_vram) {
+ if (is_vram && xe_migrate_allow_identity(*L0, cur)) {
+ /* Offset into identity map. */
+ *L0_ofs = xe_migrate_vram_ofs(tile_to_xe(m->tile),
+ cur->start + vram_region_gpu_offset(res));
+ cmds += cmd_size;
+ } else {
/* Clip L0 to available size */
u64 size = min(*L0, (u64)avail_pts * SZ_2M);
u64 num_4k_pages = DIV_ROUND_UP(size, XE_PAGE_SIZE);
@@ -413,11 +451,6 @@ static u32 pte_update_size(struct xe_migrate *m,
/* Each chunk has a single blit command */
cmds += cmd_size;
- } else {
- /* Offset into identity map. */
- *L0_ofs = xe_migrate_vram_ofs(tile_to_xe(m->tile),
- cur->start + vram_region_gpu_offset(res));
- cmds += cmd_size;
}
return cmds;
@@ -427,10 +460,10 @@ static void emit_pte(struct xe_migrate *m,
struct xe_bb *bb, u32 at_pt,
bool is_vram, bool is_comp_pte,
struct xe_res_cursor *cur,
- u32 size, struct xe_bo *bo)
+ u32 size, struct ttm_resource *res)
{
struct xe_device *xe = tile_to_xe(m->tile);
-
+ struct xe_vm *vm = m->q->vm;
u16 pat_index;
u32 ptes;
u64 ofs = at_pt * XE_PAGE_SIZE;
@@ -443,13 +476,6 @@ static void emit_pte(struct xe_migrate *m,
else
pat_index = xe->pat.idx[XE_CACHE_WB];
- /*
- * FIXME: Emitting VRAM PTEs to L0 PTs is forbidden. Currently
- * we're only emitting VRAM PTEs during sanity tests, so when
- * that's moved to a Kunit test, we should condition VRAM PTEs
- * on running tests.
- */
-
ptes = DIV_ROUND_UP(size, XE_PAGE_SIZE);
while (ptes) {
@@ -469,20 +495,22 @@ static void emit_pte(struct xe_migrate *m,
addr = xe_res_dma(cur) & PAGE_MASK;
if (is_vram) {
- /* Is this a 64K PTE entry? */
- if ((m->q->vm->flags & XE_VM_FLAG_64K) &&
- !(cur_ofs & (16 * 8 - 1))) {
- xe_tile_assert(m->tile, IS_ALIGNED(addr, SZ_64K));
+ if (vm->flags & XE_VM_FLAG_64K) {
+ u64 va = cur_ofs * XE_PAGE_SIZE / 8;
+
+ xe_assert(xe, (va & (SZ_64K - 1)) ==
+ (addr & (SZ_64K - 1)));
+
flags |= XE_PTE_PS64;
}
- addr += vram_region_gpu_offset(bo->ttm.resource);
+ addr += vram_region_gpu_offset(res);
devmem = true;
}
- addr = m->q->vm->pt_ops->pte_encode_addr(m->tile->xe,
- addr, pat_index,
- 0, devmem, flags);
+ addr = vm->pt_ops->pte_encode_addr(m->tile->xe,
+ addr, pat_index,
+ 0, devmem, flags);
bb->cs[bb->len++] = lower_32_bits(addr);
bb->cs[bb->len++] = upper_32_bits(addr);
@@ -694,8 +722,8 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m,
bool usm = xe->info.has_usm;
u32 avail_pts = max_mem_transfer_per_pass(xe) / LEVEL0_PAGE_TABLE_ENCODE_SIZE;
- src_L0 = xe_migrate_res_sizes(xe, &src_it);
- dst_L0 = xe_migrate_res_sizes(xe, &dst_it);
+ src_L0 = xe_migrate_res_sizes(m, &src_it);
+ dst_L0 = xe_migrate_res_sizes(m, &dst_it);
drm_dbg(&xe->drm, "Pass %u, sizes: %llu & %llu\n",
pass++, src_L0, dst_L0);
@@ -716,6 +744,7 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m,
&ccs_ofs, &ccs_pt, 0,
2 * avail_pts,
avail_pts);
+ xe_assert(xe, IS_ALIGNED(ccs_it.start, PAGE_SIZE));
}
/* Add copy commands size here */
@@ -728,20 +757,20 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m,
goto err_sync;
}
- if (!src_is_vram)
- emit_pte(m, bb, src_L0_pt, src_is_vram, true, &src_it, src_L0,
- src_bo);
- else
+ if (src_is_vram && xe_migrate_allow_identity(src_L0, &src_it))
xe_res_next(&src_it, src_L0);
-
- if (!dst_is_vram)
- emit_pte(m, bb, dst_L0_pt, dst_is_vram, true, &dst_it, src_L0,
- dst_bo);
else
+ emit_pte(m, bb, src_L0_pt, src_is_vram, true, &src_it, src_L0,
+ src);
+
+ if (dst_is_vram && xe_migrate_allow_identity(src_L0, &dst_it))
xe_res_next(&dst_it, src_L0);
+ else
+ emit_pte(m, bb, dst_L0_pt, dst_is_vram, true, &dst_it, src_L0,
+ dst);
if (copy_system_ccs)
- emit_pte(m, bb, ccs_pt, false, false, &ccs_it, ccs_size, src_bo);
+ emit_pte(m, bb, ccs_pt, false, false, &ccs_it, ccs_size, src);
bb->cs[bb->len++] = MI_BATCH_BUFFER_END;
update_idx = bb->len;
@@ -950,7 +979,7 @@ struct dma_fence *xe_migrate_clear(struct xe_migrate *m,
bool usm = xe->info.has_usm;
u32 avail_pts = max_mem_transfer_per_pass(xe) / LEVEL0_PAGE_TABLE_ENCODE_SIZE;
- clear_L0 = xe_migrate_res_sizes(xe, &src_it);
+ clear_L0 = xe_migrate_res_sizes(m, &src_it);
drm_dbg(&xe->drm, "Pass %u, size: %llu\n", pass++, clear_L0);
@@ -977,12 +1006,12 @@ struct dma_fence *xe_migrate_clear(struct xe_migrate *m,
size -= clear_L0;
/* Preemption is enabled again by the ring ops. */
- if (!clear_vram) {
- emit_pte(m, bb, clear_L0_pt, clear_vram, true, &src_it, clear_L0,
- bo);
- } else {
+ if (clear_vram && xe_migrate_allow_identity(clear_L0, &src_it))
xe_res_next(&src_it, clear_L0);
- }
+ else
+ emit_pte(m, bb, clear_L0_pt, clear_vram, true, &src_it, clear_L0,
+ dst);
+
bb->cs[bb->len++] = MI_BATCH_BUFFER_END;
update_idx = bb->len;
diff --git a/drivers/gpu/drm/xe/xe_mmio.c b/drivers/gpu/drm/xe/xe_mmio.c
index f660cfb79f504e264f9a3ced4a5f5544fada74e0..c8c5d74b6e9041ec53c38ba81d184b83037427ab 100644
--- a/drivers/gpu/drm/xe/xe_mmio.c
+++ b/drivers/gpu/drm/xe/xe_mmio.c
@@ -303,7 +303,7 @@ void xe_mmio_probe_tiles(struct xe_device *xe)
u8 id, tile_count = xe->info.tile_count;
struct xe_gt *gt = xe_root_mmio_gt(xe);
struct xe_tile *tile;
- void *regs;
+ void __iomem *regs;
u32 mtcfg;
if (tile_count == 1)
diff --git a/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c b/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c
index d2b00d0bf1e203c8b9c9322bcf8a489b1409821b..e5d7d5e2bec129937317f14f6b0063308a19bf58 100644
--- a/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c
+++ b/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c
@@ -31,7 +31,7 @@ struct xe_ttm_stolen_mgr {
/* GPU base offset */
resource_size_t stolen_base;
- void *__iomem mapping;
+ void __iomem *mapping;
};
static inline struct xe_ttm_stolen_mgr *
@@ -275,7 +275,7 @@ static int __xe_ttm_stolen_io_mem_reserve_bar2(struct xe_device *xe,
drm_WARN_ON(&xe->drm, !(mem->placement & TTM_PL_FLAG_CONTIGUOUS));
if (mem->placement & TTM_PL_FLAG_CONTIGUOUS && mgr->mapping)
- mem->bus.addr = (u8 *)mgr->mapping + mem->bus.offset;
+ mem->bus.addr = (u8 __force *)mgr->mapping + mem->bus.offset;
mem->bus.offset += mgr->io_base;
mem->bus.is_iomem = true;
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 0cfe7289b97efddd3d3b1177b6e91ebafd22fdc9..10b6995fbf294690a36234dc3c36bf741245b7a9 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -335,13 +335,13 @@ int xe_vm_add_compute_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q)
down_write(&vm->lock);
err = drm_gpuvm_exec_lock(&vm_exec);
if (err)
- return err;
+ goto out_up_write;
pfence = xe_preempt_fence_create(q, q->compute.context,
++q->compute.seqno);
if (!pfence) {
err = -ENOMEM;
- goto out_unlock;
+ goto out_fini;
}
list_add(&q->compute.link, &vm->preempt.exec_queues);
@@ -364,8 +364,9 @@ int xe_vm_add_compute_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q)
up_read(&vm->userptr.notifier_lock);
-out_unlock:
+out_fini:
drm_exec_fini(exec);
+out_up_write:
up_write(&vm->lock);
return err;
@@ -2063,9 +2064,11 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo,
if (err)
return ERR_PTR(err);
- vm_bo = drm_gpuvm_bo_find(&vm->gpuvm, obj);
- if (!vm_bo)
- break;
+ vm_bo = drm_gpuvm_bo_obtain(&vm->gpuvm, obj);
+ if (IS_ERR(vm_bo)) {
+ xe_bo_unlock(bo);
+ return ERR_CAST(vm_bo);
+ }
ops = drm_gpuvm_bo_unmap_ops_create(vm_bo);
drm_gpuvm_bo_put(vm_bo);
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 0a2bd72a6d76754ed4526b6a098b095476e1772b..2266358d807466f95d02b431d09ee39805dff5e8 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -8132,6 +8132,19 @@ static void status_unused(struct seq_file *seq)
seq_printf(seq, "\n");
}
+static void status_personalities(struct seq_file *seq)
+{
+ struct md_personality *pers;
+
+ seq_puts(seq, "Personalities : ");
+ spin_lock(&pers_lock);
+ list_for_each_entry(pers, &pers_list, list)
+ seq_printf(seq, "[%s] ", pers->name);
+
+ spin_unlock(&pers_lock);
+ seq_puts(seq, "\n");
+}
+
static int status_resync(struct seq_file *seq, struct mddev *mddev)
{
sector_t max_sectors, resync, res;
@@ -8273,20 +8286,10 @@ static int status_resync(struct seq_file *seq, struct mddev *mddev)
static void *md_seq_start(struct seq_file *seq, loff_t *pos)
__acquires(&all_mddevs_lock)
{
- struct md_personality *pers;
-
- seq_puts(seq, "Personalities : ");
- spin_lock(&pers_lock);
- list_for_each_entry(pers, &pers_list, list)
- seq_printf(seq, "[%s] ", pers->name);
-
- spin_unlock(&pers_lock);
- seq_puts(seq, "\n");
seq->poll_event = atomic_read(&md_event_count);
-
spin_lock(&all_mddevs_lock);
- return seq_list_start(&all_mddevs, *pos);
+ return seq_list_start_head(&all_mddevs, *pos);
}
static void *md_seq_next(struct seq_file *seq, void *v, loff_t *pos)
@@ -8297,16 +8300,23 @@ static void *md_seq_next(struct seq_file *seq, void *v, loff_t *pos)
static void md_seq_stop(struct seq_file *seq, void *v)
__releases(&all_mddevs_lock)
{
- status_unused(seq);
spin_unlock(&all_mddevs_lock);
}
static int md_seq_show(struct seq_file *seq, void *v)
{
- struct mddev *mddev = list_entry(v, struct mddev, all_mddevs);
+ struct mddev *mddev;
sector_t sectors;
struct md_rdev *rdev;
+ if (v == &all_mddevs) {
+ status_personalities(seq);
+ if (list_empty(&all_mddevs))
+ status_unused(seq);
+ return 0;
+ }
+
+ mddev = list_entry(v, struct mddev, all_mddevs);
if (!mddev_get(mddev))
return 0;
@@ -8382,6 +8392,10 @@ static int md_seq_show(struct seq_file *seq, void *v)
}
spin_unlock(&mddev->lock);
spin_lock(&all_mddevs_lock);
+
+ if (mddev == list_last_entry(&all_mddevs, struct mddev, all_mddevs))
+ status_unused(seq);
+
if (atomic_dec_and_test(&mddev->active))
__mddev_put(mddev);
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index aaa434f0c17515f31519199e94468f92ff96b57d..24f0d799fd98ed318f2f1d2fc7b682d5ebf77e4c 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1968,12 +1968,12 @@ static void end_sync_write(struct bio *bio)
}
static int r1_sync_page_io(struct md_rdev *rdev, sector_t sector,
- int sectors, struct page *page, int rw)
+ int sectors, struct page *page, blk_opf_t rw)
{
if (sync_page_io(rdev, sector, sectors << 9, page, rw, false))
/* success */
return 1;
- if (rw == WRITE) {
+ if (rw == REQ_OP_WRITE) {
set_bit(WriteErrorSeen, &rdev->flags);
if (!test_and_set_bit(WantReplacement,
&rdev->flags))
@@ -2090,7 +2090,7 @@ static int fix_sync_read_error(struct r1bio *r1_bio)
rdev = conf->mirrors[d].rdev;
if (r1_sync_page_io(rdev, sect, s,
pages[idx],
- WRITE) == 0) {
+ REQ_OP_WRITE) == 0) {
r1_bio->bios[d]->bi_end_io = NULL;
rdev_dec_pending(rdev, mddev);
}
@@ -2105,7 +2105,7 @@ static int fix_sync_read_error(struct r1bio *r1_bio)
rdev = conf->mirrors[d].rdev;
if (r1_sync_page_io(rdev, sect, s,
pages[idx],
- READ) != 0)
+ REQ_OP_READ) != 0)
atomic_add(s, &rdev->corrected_errors);
}
sectors -= s;
@@ -2321,7 +2321,7 @@ static void fix_read_error(struct r1conf *conf, struct r1bio *r1_bio)
!test_bit(Faulty, &rdev->flags)) {
atomic_inc(&rdev->nr_pending);
r1_sync_page_io(rdev, sect, s,
- conf->tmppage, WRITE);
+ conf->tmppage, REQ_OP_WRITE);
rdev_dec_pending(rdev, mddev);
}
}
@@ -2335,7 +2335,7 @@ static void fix_read_error(struct r1conf *conf, struct r1bio *r1_bio)
!test_bit(Faulty, &rdev->flags)) {
atomic_inc(&rdev->nr_pending);
if (r1_sync_page_io(rdev, sect, s,
- conf->tmppage, READ)) {
+ conf->tmppage, REQ_OP_READ)) {
atomic_add(s, &rdev->corrected_errors);
pr_info("md/raid1:%s: read error corrected (%d sectors at %llu on %pg)\n",
mdname(mddev), s,
diff --git a/drivers/media/pci/solo6x10/solo6x10-offsets.h b/drivers/media/pci/solo6x10/solo6x10-offsets.h
index f414ee1316f29ca3feecbd0253c585c2adce8cb3..fdbb817e63601c032b312ab83a6a810cfbf71c6c 100644
--- a/drivers/media/pci/solo6x10/solo6x10-offsets.h
+++ b/drivers/media/pci/solo6x10/solo6x10-offsets.h
@@ -57,16 +57,16 @@
#define SOLO_MP4E_EXT_ADDR(__solo) \
(SOLO_EREF_EXT_ADDR(__solo) + SOLO_EREF_EXT_AREA(__solo))
#define SOLO_MP4E_EXT_SIZE(__solo) \
- max((__solo->nr_chans * 0x00080000), \
- min(((__solo->sdram_size - SOLO_MP4E_EXT_ADDR(__solo)) - \
- __SOLO_JPEG_MIN_SIZE(__solo)), 0x00ff0000))
+ clamp(__solo->sdram_size - SOLO_MP4E_EXT_ADDR(__solo) - \
+ __SOLO_JPEG_MIN_SIZE(__solo), \
+ __solo->nr_chans * 0x00080000, 0x00ff0000)
#define __SOLO_JPEG_MIN_SIZE(__solo) (__solo->nr_chans * 0x00080000)
#define SOLO_JPEG_EXT_ADDR(__solo) \
(SOLO_MP4E_EXT_ADDR(__solo) + SOLO_MP4E_EXT_SIZE(__solo))
#define SOLO_JPEG_EXT_SIZE(__solo) \
- max(__SOLO_JPEG_MIN_SIZE(__solo), \
- min((__solo->sdram_size - SOLO_JPEG_EXT_ADDR(__solo)), 0x00ff0000))
+ clamp(__solo->sdram_size - SOLO_JPEG_EXT_ADDR(__solo), \
+ __SOLO_JPEG_MIN_SIZE(__solo), 0x00ff0000)
#define SOLO_SDRAM_END(__solo) \
(SOLO_JPEG_EXT_ADDR(__solo) + SOLO_JPEG_EXT_SIZE(__solo))
diff --git a/drivers/net/can/c_can/c_can_platform.c b/drivers/net/can/c_can/c_can_platform.c
index f44ba2600415f639b0d80958414201cf16ed9a38..e2ec69aa46e53154217d75e09d5fc07c212ee73f 100644
--- a/drivers/net/can/c_can/c_can_platform.c
+++ b/drivers/net/can/c_can/c_can_platform.c
@@ -30,9 +30,9 @@
#include
#include
#include
+#include
#include
#include
-#include
#include
#include
@@ -259,22 +259,13 @@ static int c_can_plat_probe(struct platform_device *pdev)
void __iomem *addr;
struct net_device *dev;
struct c_can_priv *priv;
- const struct of_device_id *match;
struct resource *mem;
int irq;
struct clk *clk;
const struct c_can_driver_data *drvdata;
struct device_node *np = pdev->dev.of_node;
- match = of_match_device(c_can_of_table, &pdev->dev);
- if (match) {
- drvdata = match->data;
- } else if (pdev->id_entry->driver_data) {
- drvdata = (struct c_can_driver_data *)
- platform_get_device_id(pdev)->driver_data;
- } else {
- return -ENODEV;
- }
+ drvdata = device_get_match_data(&pdev->dev);
/* get the appropriate clk */
clk = devm_clk_get(&pdev->dev, NULL);
diff --git a/drivers/net/can/flexcan/flexcan-core.c b/drivers/net/can/flexcan/flexcan-core.c
index d15f85a40c1e5be5b703fbe9d27c104564f54f58..8ea7f2795551bb4867869a11858cfd50f3f73f67 100644
--- a/drivers/net/can/flexcan/flexcan-core.c
+++ b/drivers/net/can/flexcan/flexcan-core.c
@@ -23,11 +23,11 @@
#include
#include
#include
-#include
#include
#include
#include
#include
+#include
#include
#include
@@ -2034,7 +2034,6 @@ MODULE_DEVICE_TABLE(platform, flexcan_id_table);
static int flexcan_probe(struct platform_device *pdev)
{
- const struct of_device_id *of_id;
const struct flexcan_devtype_data *devtype_data;
struct net_device *dev;
struct flexcan_priv *priv;
@@ -2090,14 +2089,7 @@ static int flexcan_probe(struct platform_device *pdev)
if (IS_ERR(regs))
return PTR_ERR(regs);
- of_id = of_match_device(flexcan_of_match, &pdev->dev);
- if (of_id)
- devtype_data = of_id->data;
- else if (platform_get_device_id(pdev)->driver_data)
- devtype_data = (struct flexcan_devtype_data *)
- platform_get_device_id(pdev)->driver_data;
- else
- return -ENODEV;
+ devtype_data = device_get_match_data(&pdev->dev);
if ((devtype_data->quirks & FLEXCAN_QUIRK_SUPPORT_FD) &&
!((devtype_data->quirks &
diff --git a/drivers/net/can/mscan/mpc5xxx_can.c b/drivers/net/can/mscan/mpc5xxx_can.c
index 4837df6efa92685fbb632986dbb51bab67590de5..5b3d69c3b6b66fe1f4cb10a42db9120ebecdea6f 100644
--- a/drivers/net/can/mscan/mpc5xxx_can.c
+++ b/drivers/net/can/mscan/mpc5xxx_can.c
@@ -12,8 +12,10 @@
#include
#include
#include
+#include
#include
#include
+#include
#include
#include
#include
@@ -290,7 +292,7 @@ static int mpc5xxx_can_probe(struct platform_device *ofdev)
int irq, mscan_clksrc = 0;
int err = -ENOMEM;
- data = of_device_get_match_data(&ofdev->dev);
+ data = device_get_match_data(&ofdev->dev);
if (!data)
return -EINVAL;
@@ -351,13 +353,11 @@ static int mpc5xxx_can_probe(struct platform_device *ofdev)
static void mpc5xxx_can_remove(struct platform_device *ofdev)
{
- const struct of_device_id *match;
const struct mpc5xxx_can_data *data;
struct net_device *dev = platform_get_drvdata(ofdev);
struct mscan_priv *priv = netdev_priv(dev);
- match = of_match_device(mpc5xxx_can_table, &ofdev->dev);
- data = match ? match->data : NULL;
+ data = device_get_match_data(&ofdev->dev);
unregister_mscandev(dev);
if (data && data->put_clock)
diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index abe58f103043360d268d48c4fa4cbd880e1b44b2..3722eaa84234ec90d8decaad66015b8fcc40dfe3 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -20,8 +20,8 @@
#include
#include
#include
-#include
#include
+#include
#include
#include
#include
@@ -1726,8 +1726,7 @@ static int xcan_probe(struct platform_device *pdev)
struct net_device *ndev;
struct xcan_priv *priv;
struct phy *transceiver;
- const struct of_device_id *of_id;
- const struct xcan_devtype_data *devtype = &xcan_axi_data;
+ const struct xcan_devtype_data *devtype;
void __iomem *addr;
int ret;
int rx_max, tx_max;
@@ -1741,9 +1740,7 @@ static int xcan_probe(struct platform_device *pdev)
goto err;
}
- of_id = of_match_device(xcan_of_match, &pdev->dev);
- if (of_id && of_id->data)
- devtype = of_id->data;
+ devtype = device_get_match_data(&pdev->dev);
hw_tx_max_property = devtype->flags & XCAN_FLAG_TX_MAILBOXES ?
"tx-mailbox-count" : "tx-fifo-depth";
diff --git a/drivers/net/ethernet/8390/8390.c b/drivers/net/ethernet/8390/8390.c
index 0e0aa40168588fff69ff76fc9fa0b3b442319f58..c5636245f1cad225bbd1a638a0bea855db566235 100644
--- a/drivers/net/ethernet/8390/8390.c
+++ b/drivers/net/ethernet/8390/8390.c
@@ -100,4 +100,5 @@ static void __exit ns8390_module_exit(void)
module_init(ns8390_module_init);
module_exit(ns8390_module_exit);
#endif /* MODULE */
+MODULE_DESCRIPTION("National Semiconductor 8390 core driver");
MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/8390/8390p.c b/drivers/net/ethernet/8390/8390p.c
index 6834742057b3eb041065793057b86d31aba9d2c1..6d429b11e9c6aa5ce0a1ea3a6c3925a3672dd2bc 100644
--- a/drivers/net/ethernet/8390/8390p.c
+++ b/drivers/net/ethernet/8390/8390p.c
@@ -102,4 +102,5 @@ static void __exit NS8390p_cleanup_module(void)
module_init(NS8390p_init_module);
module_exit(NS8390p_cleanup_module);
+MODULE_DESCRIPTION("National Semiconductor 8390 core for ISA driver");
MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/8390/apne.c b/drivers/net/ethernet/8390/apne.c
index a09f383dd249f1e1782d20de475bdac76a90c54d..828edca8d30c59dec13c8a764fe0f2ed39ceb8ea 100644
--- a/drivers/net/ethernet/8390/apne.c
+++ b/drivers/net/ethernet/8390/apne.c
@@ -610,4 +610,5 @@ static int init_pcmcia(void)
return 1;
}
+MODULE_DESCRIPTION("National Semiconductor 8390 Amiga PCMCIA ethernet driver");
MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/8390/hydra.c b/drivers/net/ethernet/8390/hydra.c
index 24f49a8ff903ff3ae8496074c19df0235b7965cf..fd9dcdc356e681b4eba0698d7f61bbd0196fcb8f 100644
--- a/drivers/net/ethernet/8390/hydra.c
+++ b/drivers/net/ethernet/8390/hydra.c
@@ -270,4 +270,5 @@ static void __exit hydra_cleanup_module(void)
module_init(hydra_init_module);
module_exit(hydra_cleanup_module);
+MODULE_DESCRIPTION("Zorro-II Hydra 8390 ethernet driver");
MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/8390/stnic.c b/drivers/net/ethernet/8390/stnic.c
index 265976e3b64ab227c55924bd8e0581b24b506d42..6cc0e190aa79c129ca65becb4699a5c55e034340 100644
--- a/drivers/net/ethernet/8390/stnic.c
+++ b/drivers/net/ethernet/8390/stnic.c
@@ -296,4 +296,5 @@ static void __exit stnic_cleanup(void)
module_init(stnic_probe);
module_exit(stnic_cleanup);
+MODULE_DESCRIPTION("National Semiconductor DP83902AV ethernet driver");
MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/8390/zorro8390.c b/drivers/net/ethernet/8390/zorro8390.c
index d70390e9d03d9bfe421554ef9e50ce78123bddfe..c24dd4fe7a10666a25b53fc5246280c9891b10ac 100644
--- a/drivers/net/ethernet/8390/zorro8390.c
+++ b/drivers/net/ethernet/8390/zorro8390.c
@@ -443,4 +443,5 @@ static void __exit zorro8390_cleanup_module(void)
module_init(zorro8390_init_module);
module_exit(zorro8390_cleanup_module);
+MODULE_DESCRIPTION("Zorro NS8390-based ethernet driver");
MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/broadcom/bcm4908_enet.c b/drivers/net/ethernet/broadcom/bcm4908_enet.c
index 3e7c8671cd116485252414e3dc3235d80054495d..72df1bb101728872fb8ac4b4905657ce0a67096b 100644
--- a/drivers/net/ethernet/broadcom/bcm4908_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm4908_enet.c
@@ -793,5 +793,6 @@ static struct platform_driver bcm4908_enet_driver = {
};
module_platform_driver(bcm4908_enet_driver);
+MODULE_DESCRIPTION("Broadcom BCM4908 Gigabit Ethernet driver");
MODULE_LICENSE("GPL v2");
MODULE_DEVICE_TABLE(of, bcm4908_enet_of_match);
diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma-mdio.c b/drivers/net/ethernet/broadcom/bgmac-bcma-mdio.c
index 9b83d536169940ea7f2b861c44fe256faed305aa..50b8e97a811d205fb9ed57c37a74dad701607552 100644
--- a/drivers/net/ethernet/broadcom/bgmac-bcma-mdio.c
+++ b/drivers/net/ethernet/broadcom/bgmac-bcma-mdio.c
@@ -260,4 +260,5 @@ void bcma_mdio_mii_unregister(struct mii_bus *mii_bus)
EXPORT_SYMBOL_GPL(bcma_mdio_mii_unregister);
MODULE_AUTHOR("Rafał Miłecki");
+MODULE_DESCRIPTION("Broadcom iProc GBit BCMA MDIO helpers");
MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma.c b/drivers/net/ethernet/broadcom/bgmac-bcma.c
index 6e4f36aaf5db6a6f869141e3c87bac4891cc7e50..36f9bad28e6a90da7456a8ec3e40a38038351c84 100644
--- a/drivers/net/ethernet/broadcom/bgmac-bcma.c
+++ b/drivers/net/ethernet/broadcom/bgmac-bcma.c
@@ -362,4 +362,5 @@ module_init(bgmac_init)
module_exit(bgmac_exit)
MODULE_AUTHOR("Rafał Miłecki");
+MODULE_DESCRIPTION("Broadcom iProc GBit BCMA interface driver");
MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c
index 0b21fd5bd4575e7a76d52e704051d3e6d30c0f72..77425c7a32dbf882672c9e664b2b006d9bc1e5f9 100644
--- a/drivers/net/ethernet/broadcom/bgmac-platform.c
+++ b/drivers/net/ethernet/broadcom/bgmac-platform.c
@@ -298,4 +298,5 @@ static struct platform_driver bgmac_enet_driver = {
};
module_platform_driver(bgmac_enet_driver);
+MODULE_DESCRIPTION("Broadcom iProc GBit platform interface driver");
MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index 448a1b90de5ebcf6de79a6b749f5bf279875d0e3..6ffdc42294074f86b08e92accb705e7e58409967 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -1626,4 +1626,5 @@ int bgmac_enet_resume(struct bgmac *bgmac)
EXPORT_SYMBOL_GPL(bgmac_enet_resume);
MODULE_AUTHOR("Rafał Miłecki");
+MODULE_DESCRIPTION("Broadcom iProc GBit driver");
MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 0aacd3c6ed5c0bbf2e02f1ddddc5dc292ae84a07..39845d556bafc949cdf4e599007db26c11b414ac 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -3817,7 +3817,7 @@ static int bnxt_alloc_cp_rings(struct bnxt *bp)
{
bool sh = !!(bp->flags & BNXT_FLAG_SHARED_RINGS);
int i, j, rc, ulp_base_vec, ulp_msix;
- int tcs = netdev_get_num_tc(bp->dev);
+ int tcs = bp->num_tc;
if (!tcs)
tcs = 1;
@@ -5935,8 +5935,12 @@ static u16 bnxt_get_max_rss_ring(struct bnxt *bp)
int bnxt_get_nr_rss_ctxs(struct bnxt *bp, int rx_rings)
{
- if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
- return DIV_ROUND_UP(rx_rings, BNXT_RSS_TABLE_ENTRIES_P5);
+ if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
+ if (!rx_rings)
+ return 0;
+ return bnxt_calc_nr_ring_pages(rx_rings - 1,
+ BNXT_RSS_TABLE_ENTRIES_P5);
+ }
if (BNXT_CHIP_TYPE_NITRO_A0(bp))
return 2;
return 1;
@@ -6926,7 +6930,7 @@ static int bnxt_hwrm_get_rings(struct bnxt *bp)
if (cp < (rx + tx)) {
rc = __bnxt_trim_rings(bp, &rx, &tx, cp, false);
if (rc)
- return rc;
+ goto get_rings_exit;
if (bp->flags & BNXT_FLAG_AGG_RINGS)
rx <<= 1;
hw_resc->resv_rx_rings = rx;
@@ -6938,8 +6942,9 @@ static int bnxt_hwrm_get_rings(struct bnxt *bp)
hw_resc->resv_cp_rings = cp;
hw_resc->resv_stat_ctxs = stats;
}
+get_rings_exit:
hwrm_req_drop(bp, req);
- return 0;
+ return rc;
}
int __bnxt_hwrm_get_tx_rings(struct bnxt *bp, u16 fid, int *tx_rings)
@@ -7000,10 +7005,11 @@ __bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
req->num_rx_rings = cpu_to_le16(rx_rings);
if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
+ u16 rss_ctx = bnxt_get_nr_rss_ctxs(bp, ring_grps);
+
req->num_cmpl_rings = cpu_to_le16(tx_rings + ring_grps);
req->num_msix = cpu_to_le16(cp_rings);
- req->num_rsscos_ctxs =
- cpu_to_le16(DIV_ROUND_UP(ring_grps, 64));
+ req->num_rsscos_ctxs = cpu_to_le16(rss_ctx);
} else {
req->num_cmpl_rings = cpu_to_le16(cp_rings);
req->num_hw_ring_grps = cpu_to_le16(ring_grps);
@@ -7050,8 +7056,10 @@ __bnxt_hwrm_reserve_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
req->num_tx_rings = cpu_to_le16(tx_rings);
req->num_rx_rings = cpu_to_le16(rx_rings);
if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
+ u16 rss_ctx = bnxt_get_nr_rss_ctxs(bp, ring_grps);
+
req->num_cmpl_rings = cpu_to_le16(tx_rings + ring_grps);
- req->num_rsscos_ctxs = cpu_to_le16(DIV_ROUND_UP(ring_grps, 64));
+ req->num_rsscos_ctxs = cpu_to_le16(rss_ctx);
} else {
req->num_cmpl_rings = cpu_to_le16(cp_rings);
req->num_hw_ring_grps = cpu_to_le16(ring_grps);
@@ -9938,7 +9946,7 @@ static int __bnxt_num_tx_to_cp(struct bnxt *bp, int tx, int tx_sets, int tx_xdp)
int bnxt_num_tx_to_cp(struct bnxt *bp, int tx)
{
- int tcs = netdev_get_num_tc(bp->dev);
+ int tcs = bp->num_tc;
if (!tcs)
tcs = 1;
@@ -9947,7 +9955,7 @@ int bnxt_num_tx_to_cp(struct bnxt *bp, int tx)
static int bnxt_num_cp_to_tx(struct bnxt *bp, int tx_cp)
{
- int tcs = netdev_get_num_tc(bp->dev);
+ int tcs = bp->num_tc;
return (tx_cp - bp->tx_nr_rings_xdp) * tcs +
bp->tx_nr_rings_xdp;
@@ -9977,7 +9985,7 @@ static void bnxt_setup_msix(struct bnxt *bp)
struct net_device *dev = bp->dev;
int tcs, i;
- tcs = netdev_get_num_tc(dev);
+ tcs = bp->num_tc;
if (tcs) {
int i, off, count;
@@ -10009,8 +10017,10 @@ static void bnxt_setup_inta(struct bnxt *bp)
{
const int len = sizeof(bp->irq_tbl[0].name);
- if (netdev_get_num_tc(bp->dev))
+ if (bp->num_tc) {
netdev_reset_tc(bp->dev);
+ bp->num_tc = 0;
+ }
snprintf(bp->irq_tbl[0].name, len, "%s-%s-%d", bp->dev->name, "TxRx",
0);
@@ -10236,8 +10246,8 @@ static void bnxt_clear_int_mode(struct bnxt *bp)
int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init)
{
- int tcs = netdev_get_num_tc(bp->dev);
bool irq_cleared = false;
+ int tcs = bp->num_tc;
int rc;
if (!bnxt_need_reserve_rings(bp))
@@ -10263,6 +10273,7 @@ int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init)
bp->tx_nr_rings - bp->tx_nr_rings_xdp)) {
netdev_err(bp->dev, "tx ring reservation failure\n");
netdev_reset_tc(bp->dev);
+ bp->num_tc = 0;
if (bp->tx_nr_rings_xdp)
bp->tx_nr_rings_per_tc = bp->tx_nr_rings_xdp;
else
@@ -11564,10 +11575,12 @@ int bnxt_half_open_nic(struct bnxt *bp)
netdev_err(bp->dev, "bnxt_alloc_mem err: %x\n", rc);
goto half_open_err;
}
+ bnxt_init_napi(bp);
set_bit(BNXT_STATE_HALF_OPEN, &bp->state);
rc = bnxt_init_nic(bp, true);
if (rc) {
clear_bit(BNXT_STATE_HALF_OPEN, &bp->state);
+ bnxt_del_napi(bp);
netdev_err(bp->dev, "bnxt_init_nic err: %x\n", rc);
goto half_open_err;
}
@@ -11586,6 +11599,7 @@ int bnxt_half_open_nic(struct bnxt *bp)
void bnxt_half_close_nic(struct bnxt *bp)
{
bnxt_hwrm_resource_free(bp, false, true);
+ bnxt_del_napi(bp);
bnxt_free_skbs(bp);
bnxt_free_mem(bp, true);
clear_bit(BNXT_STATE_HALF_OPEN, &bp->state);
@@ -13232,6 +13246,11 @@ static int bnxt_fw_init_one_p1(struct bnxt *bp)
bp->fw_cap = 0;
rc = bnxt_hwrm_ver_get(bp);
+ /* FW may be unresponsive after FLR. FLR must complete within 100 msec
+ * so wait before continuing with recovery.
+ */
+ if (rc)
+ msleep(100);
bnxt_try_map_fw_health_reg(bp);
if (rc) {
rc = bnxt_try_recover_fw(bp);
@@ -13784,7 +13803,7 @@ int bnxt_setup_mq_tc(struct net_device *dev, u8 tc)
return -EINVAL;
}
- if (netdev_get_num_tc(dev) == tc)
+ if (bp->num_tc == tc)
return 0;
if (bp->flags & BNXT_FLAG_SHARED_RINGS)
@@ -13802,9 +13821,11 @@ int bnxt_setup_mq_tc(struct net_device *dev, u8 tc)
if (tc) {
bp->tx_nr_rings = bp->tx_nr_rings_per_tc * tc;
netdev_set_num_tc(dev, tc);
+ bp->num_tc = tc;
} else {
bp->tx_nr_rings = bp->tx_nr_rings_per_tc;
netdev_reset_tc(dev);
+ bp->num_tc = 0;
}
bp->tx_nr_rings += bp->tx_nr_rings_xdp;
tx_cp = bnxt_num_tx_to_cp(bp, bp->tx_nr_rings);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index b8ef1717cb65fb128b6a60d8148829f3c2b6af36..47338b48ca203d2ebea4c72b433690a0afde3c58 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -2225,6 +2225,7 @@ struct bnxt {
u8 tc_to_qidx[BNXT_MAX_QUEUE];
u8 q_ids[BNXT_MAX_QUEUE];
u8 max_q;
+ u8 num_tc;
unsigned int current_interval;
#define BNXT_TIMER_INTERVAL HZ
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
index 63e0670383852af5b6ab4a7c28c9d25e0ea64a1b..0dbb880a7aa0e721f98e42d17f845596a702abc4 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
@@ -228,7 +228,7 @@ static int bnxt_queue_remap(struct bnxt *bp, unsigned int lltc_mask)
}
}
if (bp->ieee_ets) {
- int tc = netdev_get_num_tc(bp->dev);
+ int tc = bp->num_tc;
if (!tc)
tc = 1;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 27b983c0a8a9cdfb3f928fdc026ce7480307ff31..dc4ca706b0e299d9df7da1b2edba240becd68878 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -884,7 +884,7 @@ static void bnxt_get_channels(struct net_device *dev,
if (max_tx_sch_inputs)
max_tx_rings = min_t(int, max_tx_rings, max_tx_sch_inputs);
- tcs = netdev_get_num_tc(dev);
+ tcs = bp->num_tc;
tx_grps = max(tcs, 1);
if (bp->tx_nr_rings_xdp)
tx_grps++;
@@ -944,7 +944,7 @@ static int bnxt_set_channels(struct net_device *dev,
if (channel->combined_count)
sh = true;
- tcs = netdev_get_num_tc(dev);
+ tcs = bp->num_tc;
req_tx_rings = sh ? channel->combined_count : channel->tx_count;
req_rx_rings = sh ? channel->combined_count : channel->rx_count;
@@ -1574,7 +1574,8 @@ u32 bnxt_get_rxfh_indir_size(struct net_device *dev)
struct bnxt *bp = netdev_priv(dev);
if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
- return ALIGN(bp->rx_nr_rings, BNXT_RSS_TABLE_ENTRIES_P5);
+ return bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings) *
+ BNXT_RSS_TABLE_ENTRIES_P5;
return HW_HASH_INDEX_SIZE;
}
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index c2b25fc623ecc08410e8fc45cb391d5a555cc1d9..4079538bc310eaaeee0ee568f6fcc3fbf2b4e758 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -407,7 +407,7 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog)
if (prog)
tx_xdp = bp->rx_nr_rings;
- tc = netdev_get_num_tc(dev);
+ tc = bp->num_tc;
if (!tc)
tc = 1;
rc = bnxt_check_rings(bp, bp->tx_nr_rings_per_tc, bp->rx_nr_rings,
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c
index 9cc6303c82ffb7f2680d3a01e4ca4c7fb227574c..f38d31bfab1bbcecafacaa4adf2e1ee67bd332b6 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_core.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c
@@ -27,6 +27,7 @@
#include "octeon_network.h"
MODULE_AUTHOR("Cavium Networks,