diff --git a/.clang-format b/.clang-format index 196ca317bd1f24ad57ad9ded549bc0b7994d8111..6ec5558b516bd909e2bb266208e08fdffee4364e 100644 --- a/.clang-format +++ b/.clang-format @@ -86,6 +86,8 @@ ForEachMacros: - 'bio_for_each_segment_all' - 'bio_list_for_each' - 'bip_for_each_vec' + - 'bitmap_for_each_clear_region' + - 'bitmap_for_each_set_region' - 'blkg_for_each_descendant_post' - 'blkg_for_each_descendant_pre' - 'blk_queue_for_each_rl' @@ -115,6 +117,7 @@ ForEachMacros: - 'drm_client_for_each_connector_iter' - 'drm_client_for_each_modeset' - 'drm_connector_for_each_possible_encoder' + - 'drm_for_each_bridge_in_chain' - 'drm_for_each_connector_iter' - 'drm_for_each_crtc' - 'drm_for_each_encoder' @@ -136,9 +139,10 @@ ForEachMacros: - 'for_each_bio' - 'for_each_board_func_rsrc' - 'for_each_bvec' + - 'for_each_card_auxs' + - 'for_each_card_auxs_safe' - 'for_each_card_components' - - 'for_each_card_links' - - 'for_each_card_links_safe' + - 'for_each_card_pre_auxs' - 'for_each_card_prelinks' - 'for_each_card_rtds' - 'for_each_card_rtds_safe' @@ -166,6 +170,7 @@ ForEachMacros: - 'for_each_dpcm_fe' - 'for_each_drhd_unit' - 'for_each_dss_dev' + - 'for_each_efi_handle' - 'for_each_efi_memory_desc' - 'for_each_efi_memory_desc_in_map' - 'for_each_element' @@ -190,6 +195,7 @@ ForEachMacros: - 'for_each_lru' - 'for_each_matching_node' - 'for_each_matching_node_and_match' + - 'for_each_member' - 'for_each_memblock' - 'for_each_memblock_type' - 'for_each_memcg_cache_index' @@ -200,9 +206,11 @@ ForEachMacros: - 'for_each_msi_entry' - 'for_each_msi_entry_safe' - 'for_each_net' + - 'for_each_net_continue_reverse' - 'for_each_netdev' - 'for_each_netdev_continue' - 'for_each_netdev_continue_rcu' + - 'for_each_netdev_continue_reverse' - 'for_each_netdev_feature' - 'for_each_netdev_in_bond_rcu' - 'for_each_netdev_rcu' @@ -254,10 +262,10 @@ ForEachMacros: - 'for_each_reserved_mem_region' - 'for_each_rtd_codec_dai' - 'for_each_rtd_codec_dai_rollback' - - 'for_each_rtdcom' - - 'for_each_rtdcom_safe' + - 'for_each_rtd_components' - 'for_each_set_bit' - 'for_each_set_bit_from' + - 'for_each_set_clump8' - 'for_each_sg' - 'for_each_sg_dma_page' - 'for_each_sg_page' @@ -267,6 +275,7 @@ ForEachMacros: - 'for_each_subelement_id' - '__for_each_thread' - 'for_each_thread' + - 'for_each_wakeup_source' - 'for_each_zone' - 'for_each_zone_zonelist' - 'for_each_zone_zonelist_nodemask' @@ -330,6 +339,7 @@ ForEachMacros: - 'list_for_each' - 'list_for_each_codec' - 'list_for_each_codec_safe' + - 'list_for_each_continue' - 'list_for_each_entry' - 'list_for_each_entry_continue' - 'list_for_each_entry_continue_rcu' @@ -351,6 +361,7 @@ ForEachMacros: - 'llist_for_each_entry' - 'llist_for_each_entry_safe' - 'llist_for_each_safe' + - 'mci_for_each_dimm' - 'media_device_for_each_entity' - 'media_device_for_each_intf' - 'media_device_for_each_link' @@ -444,10 +455,16 @@ ForEachMacros: - 'virtio_device_for_each_vq' - 'xa_for_each' - 'xa_for_each_marked' + - 'xa_for_each_range' - 'xa_for_each_start' - 'xas_for_each' - 'xas_for_each_conflict' - 'xas_for_each_marked' + - 'xbc_array_for_each_value' + - 'xbc_for_each_key_value' + - 'xbc_node_for_each_array_value' + - 'xbc_node_for_each_child' + - 'xbc_node_for_each_key_value' - 'zorro_for_each_dev' #IncludeBlocks: Preserve # Unknown to clang-format-5.0 diff --git a/COPYING b/COPYING index da4cb28febe66172a9fdf1a235525ae6c00cde1d..a635a38ef9405fdfcfe97f3a435393c1e9cae971 100644 --- a/COPYING +++ b/COPYING @@ -16,3 +16,5 @@ In addition, other licenses may also apply. Please see: Documentation/process/license-rules.rst for more details. + +All contributions to the Linux Kernel are subject to this COPYING file. diff --git a/CREDITS b/CREDITS index a97d3280a627b3665e68c94a574409f71cee1da6..032b5994f4760a13770d1629b8b057195d9266c2 100644 --- a/CREDITS +++ b/CREDITS @@ -567,6 +567,11 @@ D: Original author of Amiga FFS filesystem S: Orlando, Florida S: USA +N: Paul Burton +E: paulburton@kernel.org +W: https://pburton.com +D: MIPS maintainer 2018-2020 + N: Lennert Buytenhek E: kernel@wantstofly.org D: Original (2.4) rewrite of the ethernet bridging code diff --git a/Documentation/admin-guide/acpi/fan_performance_states.rst b/Documentation/admin-guide/acpi/fan_performance_states.rst index 21d233ca50d8b1009cb21bd033088af60d297c39..98fe5c3331214df8745ba8fab3e25875bdec7f8f 100644 --- a/Documentation/admin-guide/acpi/fan_performance_states.rst +++ b/Documentation/admin-guide/acpi/fan_performance_states.rst @@ -18,7 +18,7 @@ may look as follows:: $ ls -l /sys/bus/acpi/devices/INT3404:00/ total 0 -... + ... -r--r--r-- 1 root root 4096 Dec 13 20:38 state0 -r--r--r-- 1 root root 4096 Dec 13 20:38 state1 -r--r--r-- 1 root root 4096 Dec 13 20:38 state10 @@ -38,7 +38,7 @@ where each of the "state*" files represents one performance state of the fan and contains a colon-separated list of 5 integer numbers (fields) with the following interpretation:: -control_percent:trip_point_index:speed_rpm:noise_level_mdb:power_mw + control_percent:trip_point_index:speed_rpm:noise_level_mdb:power_mw * ``control_percent``: The percent value to be used to set the fan speed to a specific level using the _FSL object (0-100). diff --git a/Documentation/admin-guide/bootconfig.rst b/Documentation/admin-guide/bootconfig.rst index b342a679639277c41100b13d9cdf6b88d70040b8..cf2edcd09183bef328294cbe67b28983149d283f 100644 --- a/Documentation/admin-guide/bootconfig.rst +++ b/Documentation/admin-guide/bootconfig.rst @@ -62,6 +62,30 @@ Or more shorter, written as following:: In both styles, same key words are automatically merged when parsing it at boot time. So you can append similar trees or key-values. +Same-key Values +--------------- + +It is prohibited that two or more values or arrays share a same-key. +For example,:: + + foo = bar, baz + foo = qux # !ERROR! we can not re-define same key + +If you want to append the value to existing key as an array member, +you can use ``+=`` operator. For example:: + + foo = bar, baz + foo += qux + +In this case, the key ``foo`` has ``bar``, ``baz`` and ``qux``. + +However, a sub-key and a value can not co-exist under a parent key. +For example, following config is NOT allowed.:: + + foo = value1 + foo.bar = value2 # !ERROR! subkey "bar" and value "value1" can NOT co-exist + + Comments -------- @@ -102,9 +126,13 @@ Boot Kernel With a Boot Config ============================== Since the boot configuration file is loaded with initrd, it will be added -to the end of the initrd (initramfs) image file. The Linux kernel decodes -the last part of the initrd image in memory to get the boot configuration -data. +to the end of the initrd (initramfs) image file with size, checksum and +12-byte magic word as below. + +[initrd][bootconfig][size(u32)][checksum(u32)][#BOOTCONFIG\n] + +The Linux kernel decodes the last part of the initrd image in memory to +get the boot configuration data. Because of this "piggyback" method, there is no need to change or update the boot loader and the kernel image itself. diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index dbc22d68462751d2bb59ab35784c1c61c84bbb0a..c07815d230bcd4bde32a93c0615326f37a68824c 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -136,6 +136,10 @@ dynamic table installation which will install SSDT tables to /sys/firmware/acpi/tables/dynamic. + acpi_no_watchdog [HW,ACPI,WDT] + Ignore the ACPI-based watchdog interface (WDAT) and let + a native driver control the watchdog device instead. + acpi_rsdp= [ACPI,EFI,KEXEC] Pass the RSDP address to the kernel, mostly used on machines running EFI runtime service to boot the diff --git a/Documentation/arm64/memory.rst b/Documentation/arm64/memory.rst index 02e02175e6f56a75da568cd0112bf71769b8f938..cf03b3290800c25ea7c5d8cba093b0189e3d727a 100644 --- a/Documentation/arm64/memory.rst +++ b/Documentation/arm64/memory.rst @@ -129,7 +129,7 @@ this logic. As a single binary will need to support both 48-bit and 52-bit VA spaces, the VMEMMAP must be sized large enough for 52-bit VAs and -also must be sized large enought to accommodate a fixed PAGE_OFFSET. +also must be sized large enough to accommodate a fixed PAGE_OFFSET. Most code in the kernel should not need to consider the VA_BITS, for code that does need to know the VA size the variables are diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 9120e59578dcaaf24e5633cd0c1a2ec37b1ea278..2c08c628febdf3c7a17c2129047d9f53e246a779 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -110,6 +110,8 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | Cavium | ThunderX GICv3 | #23154 | CAVIUM_ERRATUM_23154 | +----------------+-----------------+-----------------+-----------------------------+ +| Cavium | ThunderX GICv3 | #38539 | N/A | ++----------------+-----------------+-----------------+-----------------------------+ | Cavium | ThunderX Core | #27456 | CAVIUM_ERRATUM_27456 | +----------------+-----------------+-----------------+-----------------------------+ | Cavium | ThunderX Core | #30115 | CAVIUM_ERRATUM_30115 | diff --git a/Documentation/arm64/tagged-address-abi.rst b/Documentation/arm64/tagged-address-abi.rst index d4a85d535bf99e09cfe5c3dc41652eaa3b64f21b..4a9d9c794ee5d889638d1a3af008dec06d11feaf 100644 --- a/Documentation/arm64/tagged-address-abi.rst +++ b/Documentation/arm64/tagged-address-abi.rst @@ -44,8 +44,15 @@ The AArch64 Tagged Address ABI has two stages of relaxation depending how the user addresses are used by the kernel: 1. User addresses not accessed by the kernel but used for address space - management (e.g. ``mmap()``, ``mprotect()``, ``madvise()``). The use - of valid tagged pointers in this context is always allowed. + management (e.g. ``mprotect()``, ``madvise()``). The use of valid + tagged pointers in this context is allowed with the exception of + ``brk()``, ``mmap()`` and the ``new_address`` argument to + ``mremap()`` as these have the potential to alias with existing + user addresses. + + NOTE: This behaviour changed in v5.6 and so some earlier kernels may + incorrectly accept valid tagged pointers for the ``brk()``, + ``mmap()`` and ``mremap()`` system calls. 2. User addresses accessed by the kernel (e.g. ``write()``). This ABI relaxation is disabled by default and the application thread needs to diff --git a/Documentation/dev-tools/kunit/usage.rst b/Documentation/dev-tools/kunit/usage.rst index 7cd56a1993b14ad75e5d21c5b3c23c29bee8f1cb..607758a66a99cc04b6abb71b3f3d610a3ccaf26c 100644 --- a/Documentation/dev-tools/kunit/usage.rst +++ b/Documentation/dev-tools/kunit/usage.rst @@ -551,6 +551,7 @@ options to your ``.config``: Once the kernel is built and installed, a simple .. code-block:: bash + modprobe example-test ...will run the tests. diff --git a/Documentation/devicetree/bindings/arm/arm,scmi.txt b/Documentation/devicetree/bindings/arm/arm,scmi.txt index f493d69e61946acf1d50476fad0429645e96114e..dc102c4e4a78b8cf6f79fae1fdf502f7dac924cb 100644 --- a/Documentation/devicetree/bindings/arm/arm,scmi.txt +++ b/Documentation/devicetree/bindings/arm/arm,scmi.txt @@ -102,7 +102,7 @@ Required sub-node properties: [1] Documentation/devicetree/bindings/clock/clock-bindings.txt [2] Documentation/devicetree/bindings/power/power-domain.yaml [3] Documentation/devicetree/bindings/thermal/thermal.txt -[4] Documentation/devicetree/bindings/sram/sram.txt +[4] Documentation/devicetree/bindings/sram/sram.yaml [5] Documentation/devicetree/bindings/reset/reset.txt Example: diff --git a/Documentation/devicetree/bindings/arm/arm,scpi.txt b/Documentation/devicetree/bindings/arm/arm,scpi.txt index 7b83ef43b41877ba783f47863d51f76d60813df9..dd04d9d9a1b8e0b06e43d16683feb440ebbff4d5 100644 --- a/Documentation/devicetree/bindings/arm/arm,scpi.txt +++ b/Documentation/devicetree/bindings/arm/arm,scpi.txt @@ -109,7 +109,7 @@ Required properties: [0] http://infocenter.arm.com/help/topic/com.arm.doc.dui0922b/index.html [1] Documentation/devicetree/bindings/clock/clock-bindings.txt [2] Documentation/devicetree/bindings/thermal/thermal.txt -[3] Documentation/devicetree/bindings/sram/sram.txt +[3] Documentation/devicetree/bindings/sram/sram.yaml [4] Documentation/devicetree/bindings/power/power-domain.yaml Example: diff --git a/Documentation/devicetree/bindings/arm/bcm/brcm,bcm63138.txt b/Documentation/devicetree/bindings/arm/bcm/brcm,bcm63138.txt index b82b6a0ae6f725cee5f6138657e05bdb92e138f7..8c7a4908a8492cf17a65a6eee99c457312982883 100644 --- a/Documentation/devicetree/bindings/arm/bcm/brcm,bcm63138.txt +++ b/Documentation/devicetree/bindings/arm/bcm/brcm,bcm63138.txt @@ -62,7 +62,7 @@ Timer node: Syscon reboot node: -See Documentation/devicetree/bindings/power/reset/syscon-reboot.txt for the +See Documentation/devicetree/bindings/power/reset/syscon-reboot.yaml for the detailed list of properties, the two values defined below are specific to the BCM6328-style timer: diff --git a/Documentation/devicetree/bindings/arm/cpus.yaml b/Documentation/devicetree/bindings/arm/cpus.yaml index 7a9c3ce2dbef991d87c2111609c0aff4db40ca57..0d5b61056b106db0a356f473b2e9fa448838f7ed 100644 --- a/Documentation/devicetree/bindings/arm/cpus.yaml +++ b/Documentation/devicetree/bindings/arm/cpus.yaml @@ -216,7 +216,7 @@ properties: $ref: '/schemas/types.yaml#/definitions/phandle-array' description: | List of phandles to idle state nodes supported - by this cpu (see ./idle-states.txt). + by this cpu (see ./idle-states.yaml). capacity-dmips-mhz: $ref: '/schemas/types.yaml#/definitions/uint32' diff --git a/Documentation/devicetree/bindings/arm/fsl.yaml b/Documentation/devicetree/bindings/arm/fsl.yaml index a8e0b4a813edcf4e6f21803f9afe2896cdab0d88..0e17e1f6fb807e233723c9b53c732269b1a60b06 100644 --- a/Documentation/devicetree/bindings/arm/fsl.yaml +++ b/Documentation/devicetree/bindings/arm/fsl.yaml @@ -160,7 +160,7 @@ properties: items: - enum: - armadeus,imx6dl-apf6 # APF6 (Solo) SoM - - armadeus,imx6dl-apf6dldev # APF6 (Solo) SoM on APF6Dev board + - armadeus,imx6dl-apf6dev # APF6 (Solo) SoM on APF6Dev board - eckelmann,imx6dl-ci4x10 - emtrion,emcon-mx6 # emCON-MX6S or emCON-MX6DL SoM - emtrion,emcon-mx6-avari # emCON-MX6S or emCON-MX6DL SoM on Avari Base diff --git a/Documentation/devicetree/bindings/arm/hisilicon/hi3519-sysctrl.txt b/Documentation/devicetree/bindings/arm/hisilicon/hi3519-sysctrl.txt index 115c5be0bd0b0a3db9d6fc8df048bfd33ec81622..8defacc44dd5b9e43a62f1db0fc5cea34a0edfd5 100644 --- a/Documentation/devicetree/bindings/arm/hisilicon/hi3519-sysctrl.txt +++ b/Documentation/devicetree/bindings/arm/hisilicon/hi3519-sysctrl.txt @@ -1,7 +1,7 @@ * Hisilicon Hi3519 System Controller Block This bindings use the following binding: -Documentation/devicetree/bindings/mfd/syscon.txt +Documentation/devicetree/bindings/mfd/syscon.yaml Required properties: - compatible: "hisilicon,hi3519-sysctrl". diff --git a/Documentation/devicetree/bindings/arm/msm/qcom,idle-state.txt b/Documentation/devicetree/bindings/arm/msm/qcom,idle-state.txt index 06df04cc827a5eaba364f86f6800d1c0a84773d5..6ce0b212ec6d6447f4ef037ec2588278d72d0ef4 100644 --- a/Documentation/devicetree/bindings/arm/msm/qcom,idle-state.txt +++ b/Documentation/devicetree/bindings/arm/msm/qcom,idle-state.txt @@ -81,4 +81,4 @@ Example: }; }; -[1]. Documentation/devicetree/bindings/arm/idle-states.txt +[1]. Documentation/devicetree/bindings/arm/idle-states.yaml diff --git a/Documentation/devicetree/bindings/arm/omap/mpu.txt b/Documentation/devicetree/bindings/arm/omap/mpu.txt index f301e636fd525b9dd9fd11bffe718332f38c0da9..e41490e6979c3df792a57d0d44246d331ec8d847 100644 --- a/Documentation/devicetree/bindings/arm/omap/mpu.txt +++ b/Documentation/devicetree/bindings/arm/omap/mpu.txt @@ -17,7 +17,7 @@ am335x and am437x only: - pm-sram: Phandles to ocmcram nodes to be used for power management. First should be type 'protect-exec' for the driver to use to copy and run PM functions, second should be regular pool to be used for - data region for code. See Documentation/devicetree/bindings/sram/sram.txt + data region for code. See Documentation/devicetree/bindings/sram/sram.yaml for more details. Examples: diff --git a/Documentation/devicetree/bindings/arm/psci.yaml b/Documentation/devicetree/bindings/arm/psci.yaml index 8ef85420b2ab1913786fc69dd5fbfda86c8c1f0b..5e66934455bbc986afb759e32be3ed2e4e80b8a5 100644 --- a/Documentation/devicetree/bindings/arm/psci.yaml +++ b/Documentation/devicetree/bindings/arm/psci.yaml @@ -100,13 +100,14 @@ properties: bindings in [1]) must specify this property. [1] Kernel documentation - ARM idle states bindings - Documentation/devicetree/bindings/arm/idle-states.txt - - "#power-domain-cells": - description: - The number of cells in a PM domain specifier as per binding in [3]. - Must be 0 as to represent a single PM domain. + Documentation/devicetree/bindings/arm/idle-states.yaml +patternProperties: + "^power-domain-": + allOf: + - $ref: "../power/power-domain.yaml#" + type: object + description: | ARM systems can have multiple cores, sometimes in an hierarchical arrangement. This often, but not always, maps directly to the processor power topology of the system. Individual nodes in a topology have their @@ -122,14 +123,8 @@ properties: helps to implement support for OSI mode and OS implementations may choose to mandate it. - [3] Documentation/devicetree/bindings/power/power_domain.txt - [4] Documentation/devicetree/bindings/power/domain-idle-state.txt - - power-domains: - $ref: '/schemas/types.yaml#/definitions/phandle-array' - description: - List of phandles and PM domain specifiers, as defined by bindings of the - PM domain provider. + [3] Documentation/devicetree/bindings/power/power-domain.yaml + [4] Documentation/devicetree/bindings/power/domain-idle-state.yaml required: - compatible @@ -199,7 +194,7 @@ examples: CPU0: cpu@0 { device_type = "cpu"; - compatible = "arm,cortex-a53", "arm,armv8"; + compatible = "arm,cortex-a53"; reg = <0x0>; enable-method = "psci"; power-domains = <&CPU_PD0>; @@ -208,7 +203,7 @@ examples: CPU1: cpu@1 { device_type = "cpu"; - compatible = "arm,cortex-a57", "arm,armv8"; + compatible = "arm,cortex-a53"; reg = <0x100>; enable-method = "psci"; power-domains = <&CPU_PD1>; @@ -224,6 +219,9 @@ examples: exit-latency-us = <10>; min-residency-us = <100>; }; + }; + + domain-idle-states { CLUSTER_RET: cluster-retention { compatible = "domain-idle-state"; @@ -247,19 +245,19 @@ examples: compatible = "arm,psci-1.0"; method = "smc"; - CPU_PD0: cpu-pd0 { + CPU_PD0: power-domain-cpu0 { #power-domain-cells = <0>; domain-idle-states = <&CPU_PWRDN>; power-domains = <&CLUSTER_PD>; }; - CPU_PD1: cpu-pd1 { + CPU_PD1: power-domain-cpu1 { #power-domain-cells = <0>; domain-idle-states = <&CPU_PWRDN>; power-domains = <&CLUSTER_PD>; }; - CLUSTER_PD: cluster-pd { + CLUSTER_PD: power-domain-cluster { #power-domain-cells = <0>; domain-idle-states = <&CLUSTER_RET>, <&CLUSTER_PWRDN>; }; diff --git a/Documentation/devicetree/bindings/arm/stm32/st,mlahb.yaml b/Documentation/devicetree/bindings/arm/stm32/st,mlahb.yaml index 68917bb7c7e8727a55ad52cb03dd7bbc649b3441..55f7938c48260149736fc0117cdc669c23011bd9 100644 --- a/Documentation/devicetree/bindings/arm/stm32/st,mlahb.yaml +++ b/Documentation/devicetree/bindings/arm/stm32/st,mlahb.yaml @@ -52,7 +52,7 @@ required: examples: - | - mlahb: ahb { + mlahb: ahb@38000000 { compatible = "st,mlahb", "simple-bus"; #address-cells = <1>; #size-cells = <1>; diff --git a/Documentation/devicetree/bindings/bus/allwinner,sun8i-a23-rsb.yaml b/Documentation/devicetree/bindings/bus/allwinner,sun8i-a23-rsb.yaml index 9fe11ceecdba004c5546f30711be002eaca64694..80973619342d9803bf43edf6a66f7b3bb10cd809 100644 --- a/Documentation/devicetree/bindings/bus/allwinner,sun8i-a23-rsb.yaml +++ b/Documentation/devicetree/bindings/bus/allwinner,sun8i-a23-rsb.yaml @@ -70,7 +70,6 @@ examples: #size-cells = <0>; pmic@3e3 { - compatible = "..."; reg = <0x3e3>; /* ... */ diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-osc-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-osc-clk.yaml index 69cfa4a3d562833aaaa7f0b11154c148dbb7c3ac..c604822cda073a3d97dc2a4625136aab9b2b40df 100644 --- a/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-osc-clk.yaml +++ b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-osc-clk.yaml @@ -40,7 +40,7 @@ additionalProperties: false examples: - | - osc24M: clk@01c20050 { + osc24M: clk@1c20050 { #clock-cells = <0>; compatible = "allwinner,sun4i-a10-osc-clk"; reg = <0x01c20050 0x4>; diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun9i-a80-gt-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun9i-a80-gt-clk.yaml index 07f38def7dc3b3ebc43a4f9929507c8cee9e1b76..43963c3062c81a650de3c4f553724a9b1eb0dacb 100644 --- a/Documentation/devicetree/bindings/clock/allwinner,sun9i-a80-gt-clk.yaml +++ b/Documentation/devicetree/bindings/clock/allwinner,sun9i-a80-gt-clk.yaml @@ -41,7 +41,7 @@ additionalProperties: false examples: - | - clk@0600005c { + clk@600005c { #clock-cells = <0>; compatible = "allwinner,sun9i-a80-gt-clk"; reg = <0x0600005c 0x4>; diff --git a/Documentation/devicetree/bindings/clock/qcom,gcc-apq8064.yaml b/Documentation/devicetree/bindings/clock/qcom,gcc-apq8064.yaml index 17f87178f6b8e91f7c21c0c97b41c673f70a2be5..3647007f82cad9c0dcf6f3511c815894061956af 100644 --- a/Documentation/devicetree/bindings/clock/qcom,gcc-apq8064.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,gcc-apq8064.yaml @@ -42,7 +42,7 @@ properties: be part of GCC and hence the TSENS properties can also be part of the GCC/clock-controller node. For more details on the TSENS properties please refer - Documentation/devicetree/bindings/thermal/qcom-tsens.txt + Documentation/devicetree/bindings/thermal/qcom-tsens.yaml nvmem-cell-names: minItems: 1 diff --git a/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tcon.yaml b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tcon.yaml index 86ad617d2327d459bd6c11c95705248f35b9df0d..5ff9cf26ca380b4886a8848ee308e3f8a9838f6a 100644 --- a/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tcon.yaml +++ b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tcon.yaml @@ -43,9 +43,13 @@ properties: - enum: - allwinner,sun8i-h3-tcon-tv - allwinner,sun50i-a64-tcon-tv - - allwinner,sun50i-h6-tcon-tv - const: allwinner,sun8i-a83t-tcon-tv + - items: + - enum: + - allwinner,sun50i-h6-tcon-tv + - const: allwinner,sun8i-r40-tcon-tv + reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tv-encoder.yaml b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tv-encoder.yaml index 5d5d396651190b72ede21c5d5acd9a40605f2940..6009324be967ef517a64b99c0efed92d7862f932 100644 --- a/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tv-encoder.yaml +++ b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tv-encoder.yaml @@ -49,11 +49,7 @@ examples: resets = <&tcon_ch0_clk 0>; port { - #address-cells = <1>; - #size-cells = <0>; - - tve0_in_tcon0: endpoint@0 { - reg = <0>; + tve0_in_tcon0: endpoint { remote-endpoint = <&tcon0_out_tve0>; }; }; diff --git a/Documentation/devicetree/bindings/display/bridge/anx6345.yaml b/Documentation/devicetree/bindings/display/bridge/anx6345.yaml index 6d72b3d11fbc4e9a31a9329cded32adea96285ff..c211038699233b943ad3e10e93215ef30be40434 100644 --- a/Documentation/devicetree/bindings/display/bridge/anx6345.yaml +++ b/Documentation/devicetree/bindings/display/bridge/anx6345.yaml @@ -79,21 +79,15 @@ examples: #size-cells = <0>; anx6345_in: port@0 { - #address-cells = <1>; - #size-cells = <0>; reg = <0>; - anx6345_in_tcon0: endpoint@0 { - reg = <0>; + anx6345_in_tcon0: endpoint { remote-endpoint = <&tcon0_out_anx6345>; }; }; anx6345_out: port@1 { - #address-cells = <1>; - #size-cells = <0>; reg = <1>; - anx6345_out_panel: endpoint@0 { - reg = <0>; + anx6345_out_panel: endpoint { remote-endpoint = <&panel_in_edp>; }; }; diff --git a/Documentation/devicetree/bindings/display/panel/leadtek,ltk500hd1829.yaml b/Documentation/devicetree/bindings/display/panel/leadtek,ltk500hd1829.yaml index 4ebcea7d0c6399335bee21b23217b30436709d8e..a614644c9849dfa96836caa6850f14618126f12e 100644 --- a/Documentation/devicetree/bindings/display/panel/leadtek,ltk500hd1829.yaml +++ b/Documentation/devicetree/bindings/display/panel/leadtek,ltk500hd1829.yaml @@ -37,6 +37,8 @@ examples: dsi@ff450000 { #address-cells = <1>; #size-cells = <0>; + reg = <0xff450000 0x1000>; + panel@0 { compatible = "leadtek,ltk500hd1829"; reg = <0>; diff --git a/Documentation/devicetree/bindings/display/panel/xinpeng,xpp055c272.yaml b/Documentation/devicetree/bindings/display/panel/xinpeng,xpp055c272.yaml index 186e5e1c8fa3b7c836eb35adb4c797413adada48..22c91beb054103d197f4c16e487b264ca5f7ddd5 100644 --- a/Documentation/devicetree/bindings/display/panel/xinpeng,xpp055c272.yaml +++ b/Documentation/devicetree/bindings/display/panel/xinpeng,xpp055c272.yaml @@ -37,6 +37,8 @@ examples: dsi@ff450000 { #address-cells = <1>; #size-cells = <0>; + reg = <0xff450000 0x1000>; + panel@0 { compatible = "xinpeng,xpp055c272"; reg = <0>; diff --git a/Documentation/devicetree/bindings/display/simple-framebuffer.yaml b/Documentation/devicetree/bindings/display/simple-framebuffer.yaml index 678776b6012a2b3effde9aa4b952fae5ea6b2027..1db608c9eef59a0ad754554aea36d692fbe15fed 100644 --- a/Documentation/devicetree/bindings/display/simple-framebuffer.yaml +++ b/Documentation/devicetree/bindings/display/simple-framebuffer.yaml @@ -174,10 +174,6 @@ examples: }; }; - soc@1c00000 { - lcdc0: lcdc@1c0c000 { - compatible = "allwinner,sun4i-a10-lcdc"; - }; - }; + lcdc0: lcdc { }; ... diff --git a/Documentation/devicetree/bindings/display/tilcdc/tilcdc.txt b/Documentation/devicetree/bindings/display/tilcdc/tilcdc.txt index 7bf1bb444812adc0a417e7d57e8be0ddbddc28d2..aac617acb64f5ff391be254d078d1b8bbe3aa895 100644 --- a/Documentation/devicetree/bindings/display/tilcdc/tilcdc.txt +++ b/Documentation/devicetree/bindings/display/tilcdc/tilcdc.txt @@ -37,7 +37,7 @@ Optional nodes: supports a single port with a single endpoint. - See also Documentation/devicetree/bindings/display/tilcdc/panel.txt and - Documentation/devicetree/bindings/display/tilcdc/tfp410.txt for connecting + Documentation/devicetree/bindings/display/bridge/ti,tfp410.txt for connecting tfp410 DVI encoder or lcd panel to lcdc [1] There is an errata about AM335x color wiring. For 16-bit color mode diff --git a/Documentation/devicetree/bindings/dma/ti/k3-udma.yaml b/Documentation/devicetree/bindings/dma/ti/k3-udma.yaml index 8b5c346f23f6c7da10bab6bd3978475bc221efc0..34780d7535b8a915a972febb669ec95170886e51 100644 --- a/Documentation/devicetree/bindings/dma/ti/k3-udma.yaml +++ b/Documentation/devicetree/bindings/dma/ti/k3-udma.yaml @@ -143,7 +143,7 @@ examples: #size-cells = <2>; dma-coherent; dma-ranges; - ranges; + ranges = <0x0 0x30800000 0x0 0x30800000 0x0 0x05000000>; ti,sci-dev-id = <118>; @@ -169,16 +169,4 @@ examples: ti,sci-rm-range-rflow = <0x6>; /* GP RFLOW */ }; }; - - mcasp0: mcasp@02B00000 { - dmas = <&main_udmap 0xc400>, <&main_udmap 0x4400>; - dma-names = "tx", "rx"; - }; - - crypto: crypto@4E00000 { - compatible = "ti,sa2ul-crypto"; - - dmas = <&main_udmap 0xc000>, <&main_udmap 0x4000>, <&main_udmap 0x4001>; - dma-names = "tx", "rx1", "rx2"; - }; }; diff --git a/Documentation/devicetree/bindings/gpu/arm,mali-bifrost.yaml b/Documentation/devicetree/bindings/gpu/arm,mali-bifrost.yaml index 4ea6a8789699709d898496353d5de4963507a1f7..e8b99adcb1bd2926c4ffe44faa2c6d6b1bd409d7 100644 --- a/Documentation/devicetree/bindings/gpu/arm,mali-bifrost.yaml +++ b/Documentation/devicetree/bindings/gpu/arm,mali-bifrost.yaml @@ -84,31 +84,31 @@ examples: gpu_opp_table: opp_table0 { compatible = "operating-points-v2"; - opp@533000000 { + opp-533000000 { opp-hz = /bits/ 64 <533000000>; opp-microvolt = <1250000>; }; - opp@450000000 { + opp-450000000 { opp-hz = /bits/ 64 <450000000>; opp-microvolt = <1150000>; }; - opp@400000000 { + opp-400000000 { opp-hz = /bits/ 64 <400000000>; opp-microvolt = <1125000>; }; - opp@350000000 { + opp-350000000 { opp-hz = /bits/ 64 <350000000>; opp-microvolt = <1075000>; }; - opp@266000000 { + opp-266000000 { opp-hz = /bits/ 64 <266000000>; opp-microvolt = <1025000>; }; - opp@160000000 { + opp-160000000 { opp-hz = /bits/ 64 <160000000>; opp-microvolt = <925000>; }; - opp@100000000 { + opp-100000000 { opp-hz = /bits/ 64 <100000000>; opp-microvolt = <912500>; }; diff --git a/Documentation/devicetree/bindings/gpu/arm,mali-midgard.yaml b/Documentation/devicetree/bindings/gpu/arm,mali-midgard.yaml index 36f59b3ade71dd6737e440e606ca08450de30eab..8d966f3ff3dbd6fdcb8ae446495e93172ffd1f80 100644 --- a/Documentation/devicetree/bindings/gpu/arm,mali-midgard.yaml +++ b/Documentation/devicetree/bindings/gpu/arm,mali-midgard.yaml @@ -138,31 +138,31 @@ examples: gpu_opp_table: opp_table0 { compatible = "operating-points-v2"; - opp@533000000 { + opp-533000000 { opp-hz = /bits/ 64 <533000000>; opp-microvolt = <1250000>; }; - opp@450000000 { + opp-450000000 { opp-hz = /bits/ 64 <450000000>; opp-microvolt = <1150000>; }; - opp@400000000 { + opp-400000000 { opp-hz = /bits/ 64 <400000000>; opp-microvolt = <1125000>; }; - opp@350000000 { + opp-350000000 { opp-hz = /bits/ 64 <350000000>; opp-microvolt = <1075000>; }; - opp@266000000 { + opp-266000000 { opp-hz = /bits/ 64 <266000000>; opp-microvolt = <1025000>; }; - opp@160000000 { + opp-160000000 { opp-hz = /bits/ 64 <160000000>; opp-microvolt = <925000>; }; - opp@100000000 { + opp-100000000 { opp-hz = /bits/ 64 <100000000>; opp-microvolt = <912500>; }; diff --git a/Documentation/devicetree/bindings/iio/adc/samsung,exynos-adc.yaml b/Documentation/devicetree/bindings/iio/adc/samsung,exynos-adc.yaml index f46de17c08788d185fa7f1dd1aba148178f99a14..cc3c8ea6a894807992ed47eeb1d52ecaca077c7c 100644 --- a/Documentation/devicetree/bindings/iio/adc/samsung,exynos-adc.yaml +++ b/Documentation/devicetree/bindings/iio/adc/samsung,exynos-adc.yaml @@ -123,7 +123,7 @@ examples: samsung,syscon-phandle = <&pmu_system_controller>; /* NTC thermistor is a hwmon device */ - ncp15wb473@0 { + ncp15wb473 { compatible = "murata,ncp15wb473"; pullup-uv = <1800000>; pullup-ohm = <47000>; diff --git a/Documentation/devicetree/bindings/input/ilitek,ili2xxx.txt b/Documentation/devicetree/bindings/input/ilitek,ili2xxx.txt index dc194b2c151ac710b64dcc0c36709656f7b103ae..cdcaa3f52d25367074161e4f80049f66402dc972 100644 --- a/Documentation/devicetree/bindings/input/ilitek,ili2xxx.txt +++ b/Documentation/devicetree/bindings/input/ilitek,ili2xxx.txt @@ -1,9 +1,10 @@ -Ilitek ILI210x/ILI2117/ILI251x touchscreen controller +Ilitek ILI210x/ILI2117/ILI2120/ILI251x touchscreen controller Required properties: - compatible: ilitek,ili210x for ILI210x ilitek,ili2117 for ILI2117 + ilitek,ili2120 for ILI2120 ilitek,ili251x for ILI251x - reg: The I2C address of the device diff --git a/Documentation/devicetree/bindings/input/touchscreen/goodix.yaml b/Documentation/devicetree/bindings/input/touchscreen/goodix.yaml index d7c3262b249450932fd1e25649e2299561450ae7..c99ed3934d7ee34aac7e416552db0c4bb29849ee 100644 --- a/Documentation/devicetree/bindings/input/touchscreen/goodix.yaml +++ b/Documentation/devicetree/bindings/input/touchscreen/goodix.yaml @@ -62,7 +62,7 @@ required: examples: - | - i2c@00000000 { + i2c { #address-cells = <1>; #size-cells = <0>; gt928@5d { diff --git a/Documentation/devicetree/bindings/input/twl4030-pwrbutton.txt b/Documentation/devicetree/bindings/input/twl4030-pwrbutton.txt index c864a46cddcf65ea573a0e7575ff30c7405b9476..f5021214edecb9b5bab54887e1e98cc6bd3ef090 100644 --- a/Documentation/devicetree/bindings/input/twl4030-pwrbutton.txt +++ b/Documentation/devicetree/bindings/input/twl4030-pwrbutton.txt @@ -1,7 +1,7 @@ Texas Instruments TWL family (twl4030) pwrbutton module This module is part of the TWL4030. For more details about the whole -chip see Documentation/devicetree/bindings/mfd/twl-familly.txt. +chip see Documentation/devicetree/bindings/mfd/twl-family.txt. This module provides a simple power button event via an Interrupt. diff --git a/Documentation/devicetree/bindings/leds/common.yaml b/Documentation/devicetree/bindings/leds/common.yaml index d97d099b87e5b96ff9d3cabc3f962bf94f432e63..c60b994fe116d8bf8f369ea2aaeb50ec28afdb2b 100644 --- a/Documentation/devicetree/bindings/leds/common.yaml +++ b/Documentation/devicetree/bindings/leds/common.yaml @@ -85,7 +85,7 @@ properties: # LED will act as a back-light, controlled by the framebuffer system - backlight # LED will turn on (but for leds-gpio see "default-state" property in - # Documentation/devicetree/bindings/leds/leds-gpio.txt) + # Documentation/devicetree/bindings/leds/leds-gpio.yaml) - default-on # LED "double" flashes at a load average based rate - heartbeat diff --git a/Documentation/devicetree/bindings/leds/register-bit-led.txt b/Documentation/devicetree/bindings/leds/register-bit-led.txt index cf1ea403ba7aa22f14542c8ceb295475b9f2a574..c7af6f70a97bf50acd57dcb332506b8486322dc9 100644 --- a/Documentation/devicetree/bindings/leds/register-bit-led.txt +++ b/Documentation/devicetree/bindings/leds/register-bit-led.txt @@ -5,7 +5,7 @@ where single bits in a certain register can turn on/off a single LED. The register bit LEDs appear as children to the syscon device, with the proper compatible string. For the syscon bindings see: -Documentation/devicetree/bindings/mfd/syscon.txt +Documentation/devicetree/bindings/mfd/syscon.yaml Each LED is represented as a sub-node of the syscon device. Each node's name represents the name of the corresponding LED. diff --git a/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-csi.yaml b/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-csi.yaml index 9af873b43acd8742ade8ed944e2cfea4ec045369..8453ee340b9fb0abffb19f48c95391bb0e93e9c9 100644 --- a/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-csi.yaml +++ b/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-csi.yaml @@ -33,24 +33,40 @@ properties: maxItems: 1 clocks: - minItems: 2 - maxItems: 3 - items: - - description: The CSI interface clock - - description: The CSI ISP clock - - description: The CSI DRAM clock + oneOf: + - items: + - description: The CSI interface clock + - description: The CSI DRAM clock + + - items: + - description: The CSI interface clock + - description: The CSI ISP clock + - description: The CSI DRAM clock clock-names: - minItems: 2 - maxItems: 3 - items: - - const: bus - - const: isp - - const: ram + oneOf: + - items: + - const: bus + - const: ram + + - items: + - const: bus + - const: isp + - const: ram resets: maxItems: 1 + # FIXME: This should be made required eventually once every SoC will + # have the MBUS declared. + interconnects: + maxItems: 1 + + # FIXME: This should be made required eventually once every SoC will + # have the MBUS declared. + interconnect-names: + const: dma-mem + # See ./video-interfaces.txt for details port: type: object diff --git a/Documentation/devicetree/bindings/media/ti,cal.yaml b/Documentation/devicetree/bindings/media/ti,cal.yaml index 1ea78417953649fad0700fc3b429f4e15f840309..5e066629287d4de310094b60d3104ee65e99f48a 100644 --- a/Documentation/devicetree/bindings/media/ti,cal.yaml +++ b/Documentation/devicetree/bindings/media/ti,cal.yaml @@ -177,7 +177,7 @@ examples: }; }; - i2c5: i2c@4807c000 { + i2c { clock-frequency = <400000>; #address-cells = <1>; #size-cells = <0>; diff --git a/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra124-emc.yaml b/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra124-emc.yaml index dd1843489ad15075fa2b31c48fa00e18d40ae032..3e0a8a92d6529ef6f2ed0901b9264e1496f7d3b8 100644 --- a/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra124-emc.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra124-emc.yaml @@ -347,6 +347,7 @@ examples: interrupts = ; #iommu-cells = <1>; + #reset-cells = <1>; }; external-memory-controller@7001b000 { @@ -363,20 +364,23 @@ examples: timing-0 { clock-frequency = <12750000>; - nvidia,emc-zcal-cnt-long = <0x00000042>; - nvidia,emc-auto-cal-interval = <0x001fffff>; - nvidia,emc-ctt-term-ctrl = <0x00000802>; - nvidia,emc-cfg = <0x73240000>; - nvidia,emc-cfg-2 = <0x000008c5>; - nvidia,emc-sel-dpd-ctrl = <0x00040128>; - nvidia,emc-bgbias-ctl0 = <0x00000008>; nvidia,emc-auto-cal-config = <0xa1430000>; nvidia,emc-auto-cal-config2 = <0x00000000>; nvidia,emc-auto-cal-config3 = <0x00000000>; - nvidia,emc-mode-reset = <0x80001221>; + nvidia,emc-auto-cal-interval = <0x001fffff>; + nvidia,emc-bgbias-ctl0 = <0x00000008>; + nvidia,emc-cfg = <0x73240000>; + nvidia,emc-cfg-2 = <0x000008c5>; + nvidia,emc-ctt-term-ctrl = <0x00000802>; nvidia,emc-mode-1 = <0x80100003>; nvidia,emc-mode-2 = <0x80200008>; nvidia,emc-mode-4 = <0x00000000>; + nvidia,emc-mode-reset = <0x80001221>; + nvidia,emc-mrs-wait-cnt = <0x000e000e>; + nvidia,emc-sel-dpd-ctrl = <0x00040128>; + nvidia,emc-xm2dqspadctrl2 = <0x0130b118>; + nvidia,emc-zcal-cnt-long = <0x00000042>; + nvidia,emc-zcal-interval = <0x00000000>; nvidia,emc-configuration = < 0x00000000 /* EMC_RC */ diff --git a/Documentation/devicetree/bindings/memory-controllers/ti/emif.txt b/Documentation/devicetree/bindings/memory-controllers/ti/emif.txt index 44d71469c9148001df7ed926d54096f09c109e9f..63f674ffeb4f432699f2a5c60c9dbbacf5c166ab 100644 --- a/Documentation/devicetree/bindings/memory-controllers/ti/emif.txt +++ b/Documentation/devicetree/bindings/memory-controllers/ti/emif.txt @@ -32,7 +32,7 @@ Required only for "ti,emif-am3352" and "ti,emif-am4372": - sram : Phandles for generic sram driver nodes, first should be type 'protect-exec' for the driver to use to copy and run PM functions, second should be regular pool to be used for - data region for code. See Documentation/devicetree/bindings/sram/sram.txt + data region for code. See Documentation/devicetree/bindings/sram/sram.yaml for more details. Optional properties: diff --git a/Documentation/devicetree/bindings/mfd/max77650.yaml b/Documentation/devicetree/bindings/mfd/max77650.yaml index 4a70f875a6eb9ff6163d1cbcc9ba7898eed0891d..4803857893942a420baaf525ed2e687a2dacc6ca 100644 --- a/Documentation/devicetree/bindings/mfd/max77650.yaml +++ b/Documentation/devicetree/bindings/mfd/max77650.yaml @@ -97,14 +97,14 @@ examples: regulators { compatible = "maxim,max77650-regulator"; - max77650_ldo: regulator@0 { + max77650_ldo: regulator-ldo { regulator-compatible = "ldo"; regulator-name = "max77650-ldo"; regulator-min-microvolt = <1350000>; regulator-max-microvolt = <2937500>; }; - max77650_sbb0: regulator@1 { + max77650_sbb0: regulator-sbb0 { regulator-compatible = "sbb0"; regulator-name = "max77650-sbb0"; regulator-min-microvolt = <800000>; diff --git a/Documentation/devicetree/bindings/mfd/tps65910.txt b/Documentation/devicetree/bindings/mfd/tps65910.txt index 4f62143afd240d7bd63010639f5635e6633cadc4..a5ced46bbde97e1d59080924fd0bc1aa43f102d7 100644 --- a/Documentation/devicetree/bindings/mfd/tps65910.txt +++ b/Documentation/devicetree/bindings/mfd/tps65910.txt @@ -26,8 +26,8 @@ Required properties: ldo6, ldo7, ldo8 - xxx-supply: Input voltage supply regulator. - These entries are require if regulators are enabled for a device. Missing of these - properties can cause the regulator registration fails. + These entries are required if regulators are enabled for a device. Missing these + properties can cause the regulator registration to fail. If some of input supply is powered through battery or always-on supply then also it is require to have these parameters with proper node handle of always on power supply. diff --git a/Documentation/devicetree/bindings/mfd/twl-familly.txt b/Documentation/devicetree/bindings/mfd/twl-family.txt similarity index 100% rename from Documentation/devicetree/bindings/mfd/twl-familly.txt rename to Documentation/devicetree/bindings/mfd/twl-family.txt diff --git a/Documentation/devicetree/bindings/mfd/zii,rave-sp.txt b/Documentation/devicetree/bindings/mfd/zii,rave-sp.txt index 088eff9ddb786cdbdf0a26ea3d9fed27f048b021..e0f901edc063563c28a26e70c3de1f3aebcd3847 100644 --- a/Documentation/devicetree/bindings/mfd/zii,rave-sp.txt +++ b/Documentation/devicetree/bindings/mfd/zii,rave-sp.txt @@ -20,7 +20,7 @@ RAVE SP consists of the following sub-devices: Device Description ------ ----------- rave-sp-wdt : Watchdog -rave-sp-nvmem : Interface to onborad EEPROM +rave-sp-nvmem : Interface to onboard EEPROM rave-sp-backlight : Display backlight rave-sp-hwmon : Interface to onboard hardware sensors rave-sp-leds : Interface to onboard LEDs diff --git a/Documentation/devicetree/bindings/misc/fsl,qoriq-mc.txt b/Documentation/devicetree/bindings/misc/fsl,qoriq-mc.txt index bb7e896cb644eb97831f234e19d19b6a82b6310e..9134e9bcca56690076f6d7eba1445cee486618ec 100644 --- a/Documentation/devicetree/bindings/misc/fsl,qoriq-mc.txt +++ b/Documentation/devicetree/bindings/misc/fsl,qoriq-mc.txt @@ -26,7 +26,7 @@ For generic IOMMU bindings, see Documentation/devicetree/bindings/iommu/iommu.txt. For arm-smmu binding, see: -Documentation/devicetree/bindings/iommu/arm,smmu.txt. +Documentation/devicetree/bindings/iommu/arm,smmu.yaml. Required properties: diff --git a/Documentation/devicetree/bindings/mmc/mmc-controller.yaml b/Documentation/devicetree/bindings/mmc/mmc-controller.yaml index 3c0df4016a127c393e1dda89676ab942b53aff54..8fded83c519adc57f7de2da1a48ec4be043a265f 100644 --- a/Documentation/devicetree/bindings/mmc/mmc-controller.yaml +++ b/Documentation/devicetree/bindings/mmc/mmc-controller.yaml @@ -370,6 +370,7 @@ examples: mmc3: mmc@1c12000 { #address-cells = <1>; #size-cells = <0>; + reg = <0x1c12000 0x200>; pinctrl-names = "default"; pinctrl-0 = <&mmc3_pins_a>; vmmc-supply = <®_vmmc3>; diff --git a/Documentation/devicetree/bindings/mmc/ti-omap-hsmmc.txt b/Documentation/devicetree/bindings/mmc/ti-omap-hsmmc.txt index 19f5508a75696b722624c550700ee74f72b2362f..4a9145ef15d6b4a4485649eb85757445aa0bffb6 100644 --- a/Documentation/devicetree/bindings/mmc/ti-omap-hsmmc.txt +++ b/Documentation/devicetree/bindings/mmc/ti-omap-hsmmc.txt @@ -124,7 +124,7 @@ not every application needs SDIO irq, e.g. MMC cards. pinctrl-1 = <&mmc1_idle>; pinctrl-2 = <&mmc1_sleep>; ... - interrupts-extended = <&intc 64 &gpio2 28 GPIO_ACTIVE_LOW>; + interrupts-extended = <&intc 64 &gpio2 28 IRQ_TYPE_LEVEL_LOW>; }; mmc1_idle : pinmux_cirq_pin { diff --git a/Documentation/devicetree/bindings/mtd/cadence-nand-controller.txt b/Documentation/devicetree/bindings/mtd/cadence-nand-controller.txt index f3893c4d3c6a96952deb602897c750c452e29ebd..d2eada5044b2410fe36bf231b8abfdebb56f13e2 100644 --- a/Documentation/devicetree/bindings/mtd/cadence-nand-controller.txt +++ b/Documentation/devicetree/bindings/mtd/cadence-nand-controller.txt @@ -27,7 +27,7 @@ Required properties of NAND chips: - reg: shall contain the native Chip Select ids from 0 to max supported by the cadence nand flash controller -See Documentation/devicetree/bindings/mtd/nand.txt for more details on +See Documentation/devicetree/bindings/mtd/nand-controller.yaml for more details on generic bindings. Example: diff --git a/Documentation/devicetree/bindings/net/brcm,bcm7445-switch-v4.0.txt b/Documentation/devicetree/bindings/net/brcm,bcm7445-switch-v4.0.txt index 48a7f916c5e4e21e9c1b154b7cc7697ad0e5b608..88b57b0ca1f49ecea05a528d6be881e700c0cd2c 100644 --- a/Documentation/devicetree/bindings/net/brcm,bcm7445-switch-v4.0.txt +++ b/Documentation/devicetree/bindings/net/brcm,bcm7445-switch-v4.0.txt @@ -45,7 +45,7 @@ Optional properties: switch queue - resets: a single phandle and reset identifier pair. See - Documentation/devicetree/binding/reset/reset.txt for details. + Documentation/devicetree/bindings/reset/reset.txt for details. - reset-names: If the "reset" property is specified, this property should have the value "switch" to denote the switch reset line. diff --git a/Documentation/devicetree/bindings/net/fsl-fman.txt b/Documentation/devicetree/bindings/net/fsl-fman.txt index 250f8d8cdce4bc17d0acc1bdb3ee2bb7ecf3fb34..c00fb0d22c7b2355f47482d1fa93a2c118bacee3 100644 --- a/Documentation/devicetree/bindings/net/fsl-fman.txt +++ b/Documentation/devicetree/bindings/net/fsl-fman.txt @@ -110,6 +110,13 @@ PROPERTIES Usage: required Definition: See soc/fsl/qman.txt and soc/fsl/bman.txt +- fsl,erratum-a050385 + Usage: optional + Value type: boolean + Definition: A boolean property. Indicates the presence of the + erratum A050385 which indicates that DMA transactions that are + split can result in a FMan lock. + ============================================================================= FMan MURAM Node diff --git a/Documentation/devicetree/bindings/net/mdio.yaml b/Documentation/devicetree/bindings/net/mdio.yaml index 5d08d2ffd4ebcc0af0d542fa2d00700f5382b555..50c3397a82bc4cea8efc364827c4fefb0e0838f8 100644 --- a/Documentation/devicetree/bindings/net/mdio.yaml +++ b/Documentation/devicetree/bindings/net/mdio.yaml @@ -56,7 +56,6 @@ patternProperties: examples: - | davinci_mdio: mdio@5c030000 { - compatible = "ti,davinci_mdio"; reg = <0x5c030000 0x1000>; #address-cells = <1>; #size-cells = <0>; diff --git a/Documentation/devicetree/bindings/nvmem/nvmem.yaml b/Documentation/devicetree/bindings/nvmem/nvmem.yaml index b43c6c65294edd6f51c336b2555d2d938bb80160..65980224d550e773db3baa8cb960ddb4325f11f7 100644 --- a/Documentation/devicetree/bindings/nvmem/nvmem.yaml +++ b/Documentation/devicetree/bindings/nvmem/nvmem.yaml @@ -76,6 +76,8 @@ examples: qfprom: eeprom@700000 { #address-cells = <1>; #size-cells = <1>; + reg = <0x00700000 0x100000>; + wp-gpios = <&gpio1 3 GPIO_ACTIVE_HIGH>; /* ... */ diff --git a/Documentation/devicetree/bindings/phy/allwinner,sun4i-a10-usb-phy.yaml b/Documentation/devicetree/bindings/phy/allwinner,sun4i-a10-usb-phy.yaml index 020ef9e4c41194e0a7d83cc4fc4bb0f546c12643..94ac23687b7eba99d846fdadc57acdd6c57cac6d 100644 --- a/Documentation/devicetree/bindings/phy/allwinner,sun4i-a10-usb-phy.yaml +++ b/Documentation/devicetree/bindings/phy/allwinner,sun4i-a10-usb-phy.yaml @@ -86,7 +86,7 @@ examples: #include #include - usbphy: phy@01c13400 { + usbphy: phy@1c13400 { #phy-cells = <1>; compatible = "allwinner,sun4i-a10-usb-phy"; reg = <0x01c13400 0x10>, <0x01c14800 0x4>, <0x01c1c800 0x4>; diff --git a/Documentation/devicetree/bindings/pinctrl/aspeed,ast2400-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/aspeed,ast2400-pinctrl.yaml index bb690e20c36800d16a722ba633c5e08d404ac543..135c7dfbc1800f378ad564e3f7e0d7c9744fe86e 100644 --- a/Documentation/devicetree/bindings/pinctrl/aspeed,ast2400-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/aspeed,ast2400-pinctrl.yaml @@ -17,7 +17,7 @@ description: |+ "aspeed,ast2400-scu", "syscon", "simple-mfd" Refer to the the bindings described in - Documentation/devicetree/bindings/mfd/syscon.txt + Documentation/devicetree/bindings/mfd/syscon.yaml properties: compatible: diff --git a/Documentation/devicetree/bindings/pinctrl/aspeed,ast2500-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/aspeed,ast2500-pinctrl.yaml index f7f5d57f2c9adc70d99056779f9070e8f7b2058b..824f7fd1d51bf735bd496c4736dde06617f38b34 100644 --- a/Documentation/devicetree/bindings/pinctrl/aspeed,ast2500-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/aspeed,ast2500-pinctrl.yaml @@ -18,7 +18,7 @@ description: |+ "aspeed,g5-scu", "syscon", "simple-mfd" Refer to the the bindings described in - Documentation/devicetree/bindings/mfd/syscon.txt + Documentation/devicetree/bindings/mfd/syscon.yaml properties: compatible: diff --git a/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml index 3749fa233e87f995dc639e950b1b4dfd01713564..ac8d1c30a8ed75fc8e85b67a934b037c225ba8d6 100644 --- a/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml @@ -17,7 +17,7 @@ description: |+ "aspeed,ast2600-scu", "syscon", "simple-mfd" Refer to the the bindings described in - Documentation/devicetree/bindings/mfd/syscon.txt + Documentation/devicetree/bindings/mfd/syscon.yaml properties: compatible: diff --git a/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.yaml index 754ea7ab040ab03f506ad96659031b552b925a4f..ef4de32cb17cca1ec9214a109a0cb9223ba67e06 100644 --- a/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.yaml @@ -248,7 +248,7 @@ examples: }; //Example 3 pin groups - pinctrl@60020000 { + pinctrl { usart1_pins_a: usart1-0 { pins1 { pinmux = ; diff --git a/Documentation/devicetree/bindings/power/amlogic,meson-ee-pwrc.yaml b/Documentation/devicetree/bindings/power/amlogic,meson-ee-pwrc.yaml index aab70e8b681e489bb5213747b607bc77ef3a30a6..d3098c924b25e308d1eeb7341dbaaf16340b4ae9 100644 --- a/Documentation/devicetree/bindings/power/amlogic,meson-ee-pwrc.yaml +++ b/Documentation/devicetree/bindings/power/amlogic,meson-ee-pwrc.yaml @@ -18,7 +18,7 @@ description: |+ "amlogic,meson-gx-hhi-sysctrl", "simple-mfd", "syscon" Refer to the the bindings described in - Documentation/devicetree/bindings/mfd/syscon.txt + Documentation/devicetree/bindings/mfd/syscon.yaml properties: compatible: diff --git a/Documentation/devicetree/bindings/power/domain-idle-state.txt b/Documentation/devicetree/bindings/power/domain-idle-state.txt deleted file mode 100644 index eefc7ed22ca269129b142a7bea78e568a73e9bdc..0000000000000000000000000000000000000000 --- a/Documentation/devicetree/bindings/power/domain-idle-state.txt +++ /dev/null @@ -1,33 +0,0 @@ -PM Domain Idle State Node: - -A domain idle state node represents the state parameters that will be used to -select the state when there are no active components in the domain. - -The state node has the following parameters - - -- compatible: - Usage: Required - Value type: - Definition: Must be "domain-idle-state". - -- entry-latency-us - Usage: Required - Value type: - Definition: u32 value representing worst case latency in - microseconds required to enter the idle state. - The exit-latency-us duration may be guaranteed - only after entry-latency-us has passed. - -- exit-latency-us - Usage: Required - Value type: - Definition: u32 value representing worst case latency - in microseconds required to exit the idle state. - -- min-residency-us - Usage: Required - Value type: - Definition: u32 value representing minimum residency duration - in microseconds after which the idle state will yield - power benefits after overcoming the overhead in entering -i the idle state. diff --git a/Documentation/devicetree/bindings/power/domain-idle-state.yaml b/Documentation/devicetree/bindings/power/domain-idle-state.yaml new file mode 100644 index 0000000000000000000000000000000000000000..dfba1af9abe55b3d963bdcc8fd786f634715f1bd --- /dev/null +++ b/Documentation/devicetree/bindings/power/domain-idle-state.yaml @@ -0,0 +1,64 @@ +# SPDX-License-Identifier: GPL-2.0 +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/power/domain-idle-state.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: PM Domain Idle States binding description + +maintainers: + - Ulf Hansson + +description: + A domain idle state node represents the state parameters that will be used to + select the state when there are no active components in the PM domain. + +properties: + $nodename: + const: domain-idle-states + +patternProperties: + "^(cpu|cluster|domain)-": + type: object + description: + Each state node represents a domain idle state description. + + properties: + compatible: + const: domain-idle-state + + entry-latency-us: + description: + The worst case latency in microseconds required to enter the idle + state. Note that, the exit-latency-us duration may be guaranteed only + after the entry-latency-us has passed. + + exit-latency-us: + description: + The worst case latency in microseconds required to exit the idle + state. + + min-residency-us: + description: + The minimum residency duration in microseconds after which the idle + state will yield power benefits, after overcoming the overhead while + entering the idle state. + + required: + - compatible + - entry-latency-us + - exit-latency-us + - min-residency-us + +examples: + - | + + domain-idle-states { + domain_retention: domain-retention { + compatible = "domain-idle-state"; + entry-latency-us = <20>; + exit-latency-us = <40>; + min-residency-us = <80>; + }; + }; +... diff --git a/Documentation/devicetree/bindings/power/power-domain.yaml b/Documentation/devicetree/bindings/power/power-domain.yaml index 455b573293aed46fadd0a3499eccdc9271e35630..6047aacd77667b16e1bba2a68f5d0ceb1236de08 100644 --- a/Documentation/devicetree/bindings/power/power-domain.yaml +++ b/Documentation/devicetree/bindings/power/power-domain.yaml @@ -25,22 +25,20 @@ description: |+ properties: $nodename: - pattern: "^(power-controller|power-domain)(@.*)?$" + pattern: "^(power-controller|power-domain)([@-].*)?$" domain-idle-states: $ref: /schemas/types.yaml#/definitions/phandle-array - description: - A phandle of an idle-state that shall be soaked into a generic domain - power state. The idle state definitions are compatible with - domain-idle-state specified in - Documentation/devicetree/bindings/power/domain-idle-state.txt - phandles that are not compatible with domain-idle-state will be ignored. - The domain-idle-state property reflects the idle state of this PM domain - and not the idle states of the devices or sub-domains in the PM domain. - Devices and sub-domains have their own idle-states independent - of the parent domain's idle states. In the absence of this property, - the domain would be considered as capable of being powered-on - or powered-off. + description: | + Phandles of idle states that defines the available states for the + power-domain provider. The idle state definitions are compatible with the + domain-idle-state bindings, specified in ./domain-idle-state.yaml. + + Note that, the domain-idle-state property reflects the idle states of this + PM domain and not the idle states of the devices or sub-domains in the PM + domain. Devices and sub-domains have their own idle states independent of + the parent domain's idle states. In the absence of this property, the + domain would be considered as capable of being powered-on or powered-off. operating-points-v2: $ref: /schemas/types.yaml#/definitions/phandle-array diff --git a/Documentation/devicetree/bindings/power/power_domain.txt b/Documentation/devicetree/bindings/power/power_domain.txt index 5b09b2deb4833069273823d4f0e4ccec81f2b72e..08497ef26c7aabf49787ee36f434ef46bf00e6cd 100644 --- a/Documentation/devicetree/bindings/power/power_domain.txt +++ b/Documentation/devicetree/bindings/power/power_domain.txt @@ -109,4 +109,4 @@ Example: required-opps = <&domain1_opp_1>; }; -[1]. Documentation/devicetree/bindings/power/domain-idle-state.txt +[1]. Documentation/devicetree/bindings/power/domain-idle-state.yaml diff --git a/Documentation/devicetree/bindings/regulator/qcom,spmi-regulator.txt b/Documentation/devicetree/bindings/regulator/qcom,spmi-regulator.txt index f5cdac8b284710055ef5ccf57ffec590e18baa8f..8b005192f6e89b9ba8847ffcf72a3851bf630444 100644 --- a/Documentation/devicetree/bindings/regulator/qcom,spmi-regulator.txt +++ b/Documentation/devicetree/bindings/regulator/qcom,spmi-regulator.txt @@ -161,7 +161,7 @@ The regulator node houses sub-nodes for each regulator within the device. Each sub-node is identified using the node's name, with valid values listed for each of the PMICs below. -pm8005: +pm8004: s2, s5 pm8005: diff --git a/Documentation/devicetree/bindings/regulator/regulator.yaml b/Documentation/devicetree/bindings/regulator/regulator.yaml index 92ff2e8ad572ba47517e6d38a2656aa4a7e50000..91a39a33000b17fa0a15d1484c5e21b1932d279a 100644 --- a/Documentation/devicetree/bindings/regulator/regulator.yaml +++ b/Documentation/devicetree/bindings/regulator/regulator.yaml @@ -191,7 +191,7 @@ patternProperties: examples: - | - xyzreg: regulator@0 { + xyzreg: regulator { regulator-min-microvolt = <1000000>; regulator-max-microvolt = <2500000>; regulator-always-on; diff --git a/Documentation/devicetree/bindings/reset/intel,rcu-gw.yaml b/Documentation/devicetree/bindings/reset/intel,rcu-gw.yaml index 246dea8a2ec95874f7d05c98806d2ccdc3c47e48..8ac4372826591e8a9d03664b839824b117382411 100644 --- a/Documentation/devicetree/bindings/reset/intel,rcu-gw.yaml +++ b/Documentation/devicetree/bindings/reset/intel,rcu-gw.yaml @@ -23,7 +23,11 @@ properties: description: Global reset register offset and bit offset. allOf: - $ref: /schemas/types.yaml#/definitions/uint32-array - - maxItems: 2 + items: + - description: Register offset + - description: Register bit offset + minimum: 0 + maximum: 31 "#reset-cells": minimum: 2 diff --git a/Documentation/devicetree/bindings/reset/st,stm32mp1-rcc.txt b/Documentation/devicetree/bindings/reset/st,stm32mp1-rcc.txt index b4edaf7c7ff3d77f11ecd4bb8645ab735a5bab6a..2880d5dda95e8326c561fb6347b3336d5d10c4b5 100644 --- a/Documentation/devicetree/bindings/reset/st,stm32mp1-rcc.txt +++ b/Documentation/devicetree/bindings/reset/st,stm32mp1-rcc.txt @@ -3,4 +3,4 @@ STMicroelectronics STM32MP1 Peripheral Reset Controller The RCC IP is both a reset and a clock controller. -Please see Documentation/devicetree/bindings/clock/st,stm32mp1-rcc.txt +Please see Documentation/devicetree/bindings/clock/st,stm32mp1-rcc.yaml diff --git a/Documentation/devicetree/bindings/sound/st,stm32-sai.txt b/Documentation/devicetree/bindings/sound/st,stm32-sai.txt index 944743dd9212550135242a6ad374edf0fbcff501..c42b91e525fa2d9105921fd0f93aa663ace9d39f 100644 --- a/Documentation/devicetree/bindings/sound/st,stm32-sai.txt +++ b/Documentation/devicetree/bindings/sound/st,stm32-sai.txt @@ -36,7 +36,7 @@ SAI subnodes required properties: - clock-names: Must contain "sai_ck". Must also contain "MCLK", if SAI shares a master clock, with a SAI set as MCLK clock provider. - - dmas: see Documentation/devicetree/bindings/dma/stm32-dma.txt + - dmas: see Documentation/devicetree/bindings/dma/st,stm32-dma.yaml - dma-names: identifier string for each DMA request line "tx": if sai sub-block is configured as playback DAI "rx": if sai sub-block is configured as capture DAI diff --git a/Documentation/devicetree/bindings/sound/st,stm32-spdifrx.txt b/Documentation/devicetree/bindings/sound/st,stm32-spdifrx.txt index 33826f2459fa80215753f918f732056b0fecf322..ca9101777c44b19a6d85e075e93691ab6e06b7ce 100644 --- a/Documentation/devicetree/bindings/sound/st,stm32-spdifrx.txt +++ b/Documentation/devicetree/bindings/sound/st,stm32-spdifrx.txt @@ -10,7 +10,7 @@ Required properties: - clock-names: must contain "kclk" - interrupts: cpu DAI interrupt line - dmas: DMA specifiers for audio data DMA and iec control flow DMA - See STM32 DMA bindings, Documentation/devicetree/bindings/dma/stm32-dma.txt + See STM32 DMA bindings, Documentation/devicetree/bindings/dma/st,stm32-dma.yaml - dma-names: two dmas have to be defined, "rx" and "rx-ctrl" Optional properties: diff --git a/Documentation/devicetree/bindings/spi/st,stm32-spi.yaml b/Documentation/devicetree/bindings/spi/st,stm32-spi.yaml index f0d979664f0763429d0feefe1ccbb7f84ff6bbb5..e49ecbf715ba0814948e240d92e5892bd9a891ad 100644 --- a/Documentation/devicetree/bindings/spi/st,stm32-spi.yaml +++ b/Documentation/devicetree/bindings/spi/st,stm32-spi.yaml @@ -49,7 +49,7 @@ properties: dmas: description: | DMA specifiers for tx and rx dma. DMA fifo mode must be used. See - the STM32 DMA bindings Documentation/devicetree/bindings/dma/stm32-dma.txt. + the STM32 DMA bindings Documentation/devicetree/bindings/dma/st,stm32-dma.yaml. items: - description: rx DMA channel - description: tx DMA channel diff --git a/Documentation/devicetree/bindings/sram/allwinner,sun4i-a10-system-control.yaml b/Documentation/devicetree/bindings/sram/allwinner,sun4i-a10-system-control.yaml index 80bac7a182d571c8d0d448a1a0dda1ea51571955..4b550943658879c66d3f087e5f3b41137d8683a9 100644 --- a/Documentation/devicetree/bindings/sram/allwinner,sun4i-a10-system-control.yaml +++ b/Documentation/devicetree/bindings/sram/allwinner,sun4i-a10-system-control.yaml @@ -125,7 +125,7 @@ examples: #size-cells = <1>; ranges; - sram_a: sram@00000000 { + sram_a: sram@0 { compatible = "mmio-sram"; reg = <0x00000000 0xc000>; #address-cells = <1>; diff --git a/Documentation/devicetree/bindings/thermal/brcm,avs-ro-thermal.yaml b/Documentation/devicetree/bindings/thermal/brcm,avs-ro-thermal.yaml index d9fdf4809a4971efd0dd550da7cdf2cf5b984ed7..f3e68ed03abf89d290fba1016363959140bf56fd 100644 --- a/Documentation/devicetree/bindings/thermal/brcm,avs-ro-thermal.yaml +++ b/Documentation/devicetree/bindings/thermal/brcm,avs-ro-thermal.yaml @@ -17,7 +17,7 @@ description: |+ "brcm,bcm2711-avs-monitor", "syscon", "simple-mfd" Refer to the the bindings described in - Documentation/devicetree/bindings/mfd/syscon.txt + Documentation/devicetree/bindings/mfd/syscon.yaml properties: compatible: diff --git a/Documentation/devicetree/bindings/timer/allwinner,sun4i-a10-timer.yaml b/Documentation/devicetree/bindings/timer/allwinner,sun4i-a10-timer.yaml index 23e989e0976630382d70ab5ddaeeb3b4c3542b61..d918cee100aced4e31c4a0dddf5ec176ade12460 100644 --- a/Documentation/devicetree/bindings/timer/allwinner,sun4i-a10-timer.yaml +++ b/Documentation/devicetree/bindings/timer/allwinner,sun4i-a10-timer.yaml @@ -87,7 +87,7 @@ additionalProperties: false examples: - | - timer { + timer@1c20c00 { compatible = "allwinner,sun4i-a10-timer"; reg = <0x01c20c00 0x400>; interrupts = <22>, diff --git a/Documentation/driver-api/dmaengine/client.rst b/Documentation/driver-api/dmaengine/client.rst index e5953e7e4bf429a20afd44234efa48df8e2c1003..2104830a99aeff529f54df726db45451075ea86c 100644 --- a/Documentation/driver-api/dmaengine/client.rst +++ b/Documentation/driver-api/dmaengine/client.rst @@ -151,8 +151,8 @@ The details of these operations are: Note that callbacks will always be invoked from the DMA engines tasklet, never from interrupt context. -Optional: per descriptor metadata ---------------------------------- + **Optional: per descriptor metadata** + DMAengine provides two ways for metadata support. DESC_METADATA_CLIENT @@ -199,12 +199,15 @@ Optional: per descriptor metadata DESC_METADATA_CLIENT - DMA_MEM_TO_DEV / DEV_MEM_TO_MEM: + 1. prepare the descriptor (dmaengine_prep_*) construct the metadata in the client's buffer 2. use dmaengine_desc_attach_metadata() to attach the buffer to the descriptor 3. submit the transfer + - DMA_DEV_TO_MEM: + 1. prepare the descriptor (dmaengine_prep_*) 2. use dmaengine_desc_attach_metadata() to attach the buffer to the descriptor @@ -215,6 +218,7 @@ Optional: per descriptor metadata DESC_METADATA_ENGINE - DMA_MEM_TO_DEV / DEV_MEM_TO_MEM: + 1. prepare the descriptor (dmaengine_prep_*) 2. use dmaengine_desc_get_metadata_ptr() to get the pointer to the engine's metadata area @@ -222,7 +226,9 @@ Optional: per descriptor metadata 4. use dmaengine_desc_set_metadata_len() to tell the DMA engine the amount of data the client has placed into the metadata buffer 5. submit the transfer + - DMA_DEV_TO_MEM: + 1. prepare the descriptor (dmaengine_prep_*) 2. submit the transfer 3. on transfer completion, use dmaengine_desc_get_metadata_ptr() to get @@ -278,8 +284,8 @@ Optional: per descriptor metadata void dma_async_issue_pending(struct dma_chan *chan); -Further APIs: -------------- +Further APIs +------------ 1. Terminate APIs diff --git a/Documentation/driver-api/ipmb.rst b/Documentation/driver-api/ipmb.rst index 3ec3baed84c4490a724e4aef92f098664e689913..209c49e051163f2c411e5cbe2fa135438333c56b 100644 --- a/Documentation/driver-api/ipmb.rst +++ b/Documentation/driver-api/ipmb.rst @@ -71,9 +71,13 @@ b) Example for device tree:: ipmb@10 { compatible = "ipmb-dev"; reg = <0x10>; + i2c-protocol; }; }; +If xmit of data to be done using raw i2c block vs smbus +then "i2c-protocol" needs to be defined as above. + 2) Manually from Linux:: modprobe ipmb-dev-int diff --git a/Documentation/filesystems/debugfs.txt b/Documentation/filesystems/debugfs.txt index dc497b96fa4ff54dc6b84cbf2951391a369473c0..55336a47a110c679dbcb26ec70f95e6be74a7d56 100644 --- a/Documentation/filesystems/debugfs.txt +++ b/Documentation/filesystems/debugfs.txt @@ -164,9 +164,9 @@ file. void __iomem *base; }; - struct dentry *debugfs_create_regset32(const char *name, umode_t mode, - struct dentry *parent, - struct debugfs_regset32 *regset); + debugfs_create_regset32(const char *name, umode_t mode, + struct dentry *parent, + struct debugfs_regset32 *regset); void debugfs_print_regs32(struct seq_file *s, struct debugfs_reg32 *regs, int nregs, void __iomem *base, char *prefix); diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst index f18506083ced831cf0ceef4870d964144152cd99..26c093969573639fc815803aa275d609057c7bfc 100644 --- a/Documentation/filesystems/porting.rst +++ b/Documentation/filesystems/porting.rst @@ -850,3 +850,11 @@ business doing so. d_alloc_pseudo() is internal-only; uses outside of alloc_file_pseudo() are very suspect (and won't work in modules). Such uses are very likely to be misspelled d_alloc_anon(). + +--- + +**mandatory** + +[should've been added in 2016] stale comment in finish_open() nonwithstanding, +failure exits in ->atomic_open() instances should *NOT* fput() the file, +no matter what. Everything is handled by the caller. diff --git a/Documentation/filesystems/zonefs.txt b/Documentation/filesystems/zonefs.txt index 935bf22031ca1ce8ea2df2cfc8cd6cb6a33d672b..d54fa98ac1582866ecb7abc4cf19d0790ea3673d 100644 --- a/Documentation/filesystems/zonefs.txt +++ b/Documentation/filesystems/zonefs.txt @@ -134,7 +134,7 @@ Sequential zone files can only be written sequentially, starting from the file end, that is, write operations can only be append writes. Zonefs makes no attempt at accepting random writes and will fail any write request that has a start offset not corresponding to the end of the file, or to the end of the last -write issued and still in-flight (for asynchrnous I/O operations). +write issued and still in-flight (for asynchronous I/O operations). Since dirty page writeback by the page cache does not guarantee a sequential write pattern, zonefs prevents buffered writes and writeable shared mappings @@ -142,7 +142,7 @@ on sequential files. Only direct I/O writes are accepted for these files. zonefs relies on the sequential delivery of write I/O requests to the device implemented by the block layer elevator. An elevator implementing the sequential write feature for zoned block device (ELEVATOR_F_ZBD_SEQ_WRITE elevator feature) -must be used. This type of elevator (e.g. mq-deadline) is the set by default +must be used. This type of elevator (e.g. mq-deadline) is set by default for zoned block devices on device initialization. There are no restrictions on the type of I/O used for read operations in @@ -196,7 +196,7 @@ additional conditions that result in I/O errors. may still happen in the case of a partial failure of a very large direct I/O operation split into multiple BIOs/requests or asynchronous I/O operations. If one of the write request within the set of sequential write requests - issued to the device fails, all write requests after queued after it will + issued to the device fails, all write requests queued after it will become unaligned and fail. * Delayed write errors: similarly to regular block devices, if the device side @@ -207,7 +207,7 @@ additional conditions that result in I/O errors. causing all data to be dropped after the sector that caused the error. All I/O errors detected by zonefs are notified to the user with an error code -return for the system call that trigered or detected the error. The recovery +return for the system call that triggered or detected the error. The recovery actions taken by zonefs in response to I/O errors depend on the I/O type (read vs write) and on the reason for the error (bad sector, unaligned writes or zone condition change). @@ -222,7 +222,7 @@ condition change). * A zone condition change to read-only or offline also always triggers zonefs I/O error recovery. -Zonefs minimal I/O error recovery may change a file size and a file access +Zonefs minimal I/O error recovery may change a file size and file access permissions. * File size changes: @@ -237,7 +237,7 @@ permissions. A file size may also be reduced to reflect a delayed write error detected on fsync(): in this case, the amount of data effectively written in the zone may be less than originally indicated by the file inode size. After such I/O - error, zonefs always fixes a file inode size to reflect the amount of data + error, zonefs always fixes the file inode size to reflect the amount of data persistently stored in the file zone. * Access permission changes: @@ -281,11 +281,11 @@ Further notes: permissions to read-only applies to all files. The file system is remounted read-only. * Access permission and file size changes due to the device transitioning zones - to the offline condition are permanent. Remounting or reformating the device + to the offline condition are permanent. Remounting or reformatting the device with mkfs.zonefs (mkzonefs) will not change back offline zone files to a good state. * File access permission changes to read-only due to the device transitioning - zones to the read-only condition are permanent. Remounting or reformating + zones to the read-only condition are permanent. Remounting or reformatting the device will not re-enable file write access. * File access permission changes implied by the remount-ro, zone-ro and zone-offline mount options are temporary for zones in a good condition. @@ -301,13 +301,13 @@ Mount options zonefs define the "errors=" mount option to allow the user to specify zonefs behavior in response to I/O errors, inode size inconsistencies or zone -condition chages. The defined behaviors are as follow: +condition changes. The defined behaviors are as follow: * remount-ro (default) * zone-ro * zone-offline * repair -The I/O error actions defined for each behavior is detailed in the previous +The I/O error actions defined for each behavior are detailed in the previous section. Zonefs User Space Tools diff --git a/Documentation/hwmon/adm1177.rst b/Documentation/hwmon/adm1177.rst index c81e0b4abd2875f53d5ec69e59c3b0098a94b2a3..471be1e98d6f6618989784e9508e2312fb66cb00 100644 --- a/Documentation/hwmon/adm1177.rst +++ b/Documentation/hwmon/adm1177.rst @@ -20,8 +20,7 @@ Usage Notes ----------- This driver does not auto-detect devices. You will have to instantiate the -devices explicitly. Please see Documentation/i2c/instantiating-devices for -details. +devices explicitly. Please see :doc:`/i2c/instantiating-devices` for details. Sysfs entries diff --git a/Documentation/hwmon/xdpe12284.rst b/Documentation/hwmon/xdpe12284.rst index 6b7ae98cc536f6382a947436f3ede87a3b112fdc..67d1f87808e57981a18c55c4877d6ab80659f5ce 100644 --- a/Documentation/hwmon/xdpe12284.rst +++ b/Documentation/hwmon/xdpe12284.rst @@ -24,6 +24,7 @@ This driver implements support for Infineon Multi-phase XDPE122 family dual loop voltage regulators. The family includes XDPE12284 and XDPE12254 devices. The devices from this family complaint with: + - Intel VR13 and VR13HC rev 1.3, IMVP8 rev 1.2 and IMPVP9 rev 1.3 DC-DC converter specification. - Intel SVID rev 1.9. protocol. diff --git a/Documentation/kbuild/kbuild.rst b/Documentation/kbuild/kbuild.rst index f1e5dce86af7cfe586cb2b751c8d4801cc810155..510f38d7e78a3480cb812761c9766415d2e84939 100644 --- a/Documentation/kbuild/kbuild.rst +++ b/Documentation/kbuild/kbuild.rst @@ -237,7 +237,7 @@ This is solely useful to speed up test compiles. KBUILD_EXTRA_SYMBOLS -------------------- For modules that use symbols from other modules. -See more details in modules.txt. +See more details in modules.rst. ALLSOURCE_ARCHS --------------- diff --git a/Documentation/kbuild/kconfig-macro-language.rst b/Documentation/kbuild/kconfig-macro-language.rst index 35b3263b7e4088618000bacbf8ced5f5277d69de..8b413ef9603dae16122706b62b340663814d8edf 100644 --- a/Documentation/kbuild/kconfig-macro-language.rst +++ b/Documentation/kbuild/kconfig-macro-language.rst @@ -44,7 +44,7 @@ intermediate:: def_bool y Then, Kconfig moves onto the evaluation stage to resolve inter-symbol -dependency as explained in kconfig-language.txt. +dependency as explained in kconfig-language.rst. Variables diff --git a/Documentation/kbuild/makefiles.rst b/Documentation/kbuild/makefiles.rst index 0e0eb2c8da7d541847ab2af34208f38c276898d5..04d5c01a2e998db16fa8ca7846a5d8e0034c41a0 100644 --- a/Documentation/kbuild/makefiles.rst +++ b/Documentation/kbuild/makefiles.rst @@ -765,7 +765,7 @@ is not sufficient this sometimes needs to be explicit. Example:: #arch/x86/boot/Makefile - subdir- := compressed/ + subdir- := compressed The above assignment instructs kbuild to descend down in the directory compressed/ when "make clean" is executed. @@ -924,7 +924,7 @@ When kbuild executes, the following steps are followed (roughly): $(KBUILD_AFLAGS_MODULE) is used to add arch-specific options that are used for assembler. - From commandline AFLAGS_MODULE shall be used (see kbuild.txt). + From commandline AFLAGS_MODULE shall be used (see kbuild.rst). KBUILD_CFLAGS_KERNEL $(CC) options specific for built-in @@ -937,7 +937,7 @@ When kbuild executes, the following steps are followed (roughly): $(KBUILD_CFLAGS_MODULE) is used to add arch-specific options that are used for $(CC). - From commandline CFLAGS_MODULE shall be used (see kbuild.txt). + From commandline CFLAGS_MODULE shall be used (see kbuild.rst). KBUILD_LDFLAGS_MODULE Options for $(LD) when linking modules @@ -945,7 +945,7 @@ When kbuild executes, the following steps are followed (roughly): $(KBUILD_LDFLAGS_MODULE) is used to add arch-specific options used when linking modules. This is often a linker script. - From commandline LDFLAGS_MODULE shall be used (see kbuild.txt). + From commandline LDFLAGS_MODULE shall be used (see kbuild.rst). KBUILD_LDS @@ -1379,9 +1379,6 @@ See subsequent chapter for the syntax of the Kbuild file. in arch/$(ARCH)/include/(uapi/)/asm, Kbuild will automatically generate a wrapper of the asm-generic one. - The convention is to list one subdir per line and - preferably in alphabetic order. - 8 Kbuild Variables ================== diff --git a/Documentation/kbuild/modules.rst b/Documentation/kbuild/modules.rst index 69fa48ee93d6ec5de3988e3a7450dda4652860c7..e0b45a257f2188e2cea5d7988480f5fb0819d7f8 100644 --- a/Documentation/kbuild/modules.rst +++ b/Documentation/kbuild/modules.rst @@ -470,9 +470,9 @@ build. The syntax of the Module.symvers file is:: - + - 0xe1cc2a05 usb_stor_suspend USB_STORAGE drivers/usb/storage/usb-storage EXPORT_SYMBOL_GPL + 0xe1cc2a05 usb_stor_suspend drivers/usb/storage/usb-storage EXPORT_SYMBOL_GPL USB_STORAGE The fields are separated by tabs and values may be empty (e.g. if no namespace is defined for an exported symbol). diff --git a/Documentation/networking/devlink/devlink-region.rst b/Documentation/networking/devlink/devlink-region.rst index 1a7683e7acb217d9782af60eb5bedd9b6e6631e5..8b46e8591fe0f7fbc9b43d1f5f3f9e0e25250728 100644 --- a/Documentation/networking/devlink/devlink-region.rst +++ b/Documentation/networking/devlink/devlink-region.rst @@ -40,9 +40,6 @@ example usage # Delete a snapshot using: $ devlink region del pci/0000:00:05.0/cr-space snapshot 1 - # Trigger (request) a snapshot be taken: - $ devlink region trigger pci/0000:00:05.0/cr-space - # Dump a snapshot: $ devlink region dump pci/0000:00:05.0/fw-health snapshot 1 0000000000000000 0014 95dc 0014 9514 0035 1670 0034 db30 diff --git a/Documentation/networking/net_failover.rst b/Documentation/networking/net_failover.rst index 06c97dcb57caee07743c55d7a500b2a42f1ff0a8..e143ab79a960d429a431993690a7db76d0e2afe9 100644 --- a/Documentation/networking/net_failover.rst +++ b/Documentation/networking/net_failover.rst @@ -8,9 +8,9 @@ Overview ======== The net_failover driver provides an automated failover mechanism via APIs -to create and destroy a failover master netdev and mananges a primary and +to create and destroy a failover master netdev and manages a primary and standby slave netdevs that get registered via the generic failover -infrastructrure. +infrastructure. The failover netdev acts a master device and controls 2 slave devices. The original paravirtual interface is registered as 'standby' slave netdev and @@ -29,7 +29,7 @@ virtio-net accelerated datapath: STANDBY mode ============================================= net_failover enables hypervisor controlled accelerated datapath to virtio-net -enabled VMs in a transparent manner with no/minimal guest userspace chanages. +enabled VMs in a transparent manner with no/minimal guest userspace changes. To support this, the hypervisor needs to enable VIRTIO_NET_F_STANDBY feature on the virtio-net interface and assign the same MAC address to both diff --git a/Documentation/networking/phy.rst b/Documentation/networking/phy.rst index 1e4735cc055351ff81bee0541dc221d974547bb1..256106054c8cb0b9d7fdc0a01f35100a388e6f08 100644 --- a/Documentation/networking/phy.rst +++ b/Documentation/networking/phy.rst @@ -487,8 +487,9 @@ phy_register_fixup_for_id():: The stubs set one of the two matching criteria, and set the other one to match anything. -When phy_register_fixup() or \*_for_uid()/\*_for_id() is called at module, -unregister fixup and free allocate memory are required. +When phy_register_fixup() or \*_for_uid()/\*_for_id() is called at module load +time, the module needs to unregister the fixup and free allocated memory when +it's unloaded. Call one of following function before unloading module:: diff --git a/Documentation/networking/rds.txt b/Documentation/networking/rds.txt index f2a0147c933d1b7be6f9b09de38de2e8994e6e2f..eec61694e894d2728f39c23eb5efe88558aa72c0 100644 --- a/Documentation/networking/rds.txt +++ b/Documentation/networking/rds.txt @@ -159,7 +159,7 @@ Socket Interface set SO_RDS_TRANSPORT on a socket for which the transport has been previously attached explicitly (by SO_RDS_TRANSPORT) or implicitly (via bind(2)) will return an error of EOPNOTSUPP. - An attempt to set SO_RDS_TRANSPPORT to RDS_TRANS_NONE will + An attempt to set SO_RDS_TRANSPORT to RDS_TRANS_NONE will always return EINVAL. RDMA for RDS diff --git a/Documentation/power/index.rst b/Documentation/power/index.rst index 002e42745263a6416de98bb93532786ab444b5cf..ced8a80074348ec744d7bedff3ce681a0162d94b 100644 --- a/Documentation/power/index.rst +++ b/Documentation/power/index.rst @@ -13,7 +13,6 @@ Power Management drivers-testing energy-model freezing-of-tasks - interface opp pci pm_qos_interface diff --git a/Documentation/process/embargoed-hardware-issues.rst b/Documentation/process/embargoed-hardware-issues.rst index 33edae6545994830942c317a1aa2f8ee8666f407..a19d084f9b2cdefd2fd90810bb9b900b64c0f68b 100644 --- a/Documentation/process/embargoed-hardware-issues.rst +++ b/Documentation/process/embargoed-hardware-issues.rst @@ -244,23 +244,23 @@ disclosure of a particular issue, unless requested by a response team or by an involved disclosed party. The current ambassadors list: ============= ======================================================== - ARM + ARM Grant Likely AMD Tom Lendacky IBM Intel Tony Luck Qualcomm Trilok Soni - Microsoft Sasha Levin + Microsoft James Morris VMware Xen Andrew Cooper - Canonical Tyler Hicks + Canonical John Johansen Debian Ben Hutchings Oracle Konrad Rzeszutek Wilk Red Hat Josh Poimboeuf SUSE Jiri Kosina - Amazon Peter Bowen + Amazon Google Kees Cook ============= ======================================================== diff --git a/Documentation/sphinx/parallel-wrapper.sh b/Documentation/sphinx/parallel-wrapper.sh index 7daf5133bdd3144df4f9ae7c624effabaa9e3c01..e54c44ce117d51835f7aeaba820ca48256681915 100644 --- a/Documentation/sphinx/parallel-wrapper.sh +++ b/Documentation/sphinx/parallel-wrapper.sh @@ -30,4 +30,4 @@ if [ -n "$parallel" ] ; then parallel="-j$parallel" fi -exec "$sphinx" "$parallel" "$@" +exec "$sphinx" $parallel "$@" diff --git a/Documentation/translations/zh_CN/process/embargoed-hardware-issues.rst b/Documentation/translations/zh_CN/process/embargoed-hardware-issues.rst index b93f1af6826131fe9f1996f8ea1e8fa35d785871..88273ebe7823d4512fdd59e1823876cbfba0a66c 100644 --- a/Documentation/translations/zh_CN/process/embargoed-hardware-issues.rst +++ b/Documentation/translations/zh_CN/process/embargoed-hardware-issues.rst @@ -183,7 +183,7 @@ CVE分配 VMware Xen Andrew Cooper - Canonical Tyler Hicks + Canonical John Johansen Debian Ben Hutchings Oracle Konrad Rzeszutek Wilk Red Hat Josh Poimboeuf diff --git a/Documentation/virtual/guest-halt-polling.txt b/Documentation/virt/guest-halt-polling.rst similarity index 91% rename from Documentation/virtual/guest-halt-polling.txt rename to Documentation/virt/guest-halt-polling.rst index b3a2a294532da0729a101b9ebb2751f6676ddf4b..b4e747942417ad3b94e83fdf5e264ffba71e98ba 100644 --- a/Documentation/virtual/guest-halt-polling.txt +++ b/Documentation/virt/guest-halt-polling.rst @@ -1,9 +1,11 @@ +================== Guest halt polling ================== The cpuidle_haltpoll driver, with the haltpoll governor, allows the guest vcpus to poll for a specified amount of time before halting. + This provides the following benefits to host side polling: 1) The POLL flag is set while polling is performed, which allows @@ -29,18 +31,21 @@ Module Parameters The haltpoll governor has 5 tunable module parameters: 1) guest_halt_poll_ns: + Maximum amount of time, in nanoseconds, that polling is performed before halting. Default: 200000 2) guest_halt_poll_shrink: + Division factor used to shrink per-cpu guest_halt_poll_ns when wakeup event occurs after the global guest_halt_poll_ns. Default: 2 3) guest_halt_poll_grow: + Multiplication factor used to grow per-cpu guest_halt_poll_ns when event occurs after per-cpu guest_halt_poll_ns but before global guest_halt_poll_ns. @@ -48,6 +53,7 @@ but before global guest_halt_poll_ns. Default: 2 4) guest_halt_poll_grow_start: + The per-cpu guest_halt_poll_ns eventually reaches zero in case of an idle system. This value sets the initial per-cpu guest_halt_poll_ns when growing. This can @@ -66,7 +72,7 @@ high once achieves global guest_halt_poll_ns value). Default: Y -The module parameters can be set from the debugfs files in: +The module parameters can be set from the debugfs files in:: /sys/module/haltpoll/parameters/ @@ -74,5 +80,5 @@ Further Notes ============= - Care should be taken when setting the guest_halt_poll_ns parameter as a -large value has the potential to drive the cpu usage to 100% on a machine which -would be almost entirely idle otherwise. + large value has the potential to drive the cpu usage to 100% on a machine + which would be almost entirely idle otherwise. diff --git a/Documentation/virt/index.rst b/Documentation/virt/index.rst index 062ffb5270438740f007479c33b022e5287580ce..de1ab81df95802b2a8a5b34e6b05ef98d422f6a0 100644 --- a/Documentation/virt/index.rst +++ b/Documentation/virt/index.rst @@ -8,7 +8,9 @@ Linux Virtualization Support :maxdepth: 2 kvm/index + uml/user_mode_linux paravirt_ops + guest-halt-polling .. only:: html and subproject diff --git a/Documentation/virt/kvm/api.txt b/Documentation/virt/kvm/api.rst similarity index 71% rename from Documentation/virt/kvm/api.txt rename to Documentation/virt/kvm/api.rst index c6e1ce5d40de992df7acd2c3782d619fd0838721..ebd383fba9399d02b7acea47b1ccbbf333949dad 100644 --- a/Documentation/virt/kvm/api.txt +++ b/Documentation/virt/kvm/api.rst @@ -1,8 +1,11 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=================================================================== The Definitive KVM (Kernel-based Virtual Machine) API Documentation =================================================================== 1. General description ----------------------- +====================== The kvm API is a set of ioctls that are issued to control various aspects of a virtual machine. The ioctls belong to the following classes: @@ -33,7 +36,7 @@ of a virtual machine. The ioctls belong to the following classes: was used to create the VM. 2. File descriptors -------------------- +=================== The kvm API is centered around file descriptors. An initial open("/dev/kvm") obtains a handle to the kvm subsystem; this handle @@ -70,7 +73,7 @@ the VM is shut down. 3. Extensions -------------- +============= As of Linux 2.6.22, the KVM ABI has been stabilized: no backward incompatible change are allowed. However, there is an extension @@ -84,13 +87,14 @@ set of ioctls is available for application use. 4. API description ------------------- +================== This section describes ioctls that can be used to control kvm guests. For each ioctl, the following information is provided along with a description: - Capability: which KVM extension provides this ioctl. Can be 'basic', + Capability: + which KVM extension provides this ioctl. Can be 'basic', which means that is will be provided by any kernel that supports API version 12 (see section 4.1), a KVM_CAP_xyz constant, which means availability needs to be checked with KVM_CHECK_EXTENSION @@ -99,24 +103,29 @@ description: availability: for kernels that don't support the ioctl, the ioctl returns -ENOTTY. - Architectures: which instruction set architectures provide this ioctl. + Architectures: + which instruction set architectures provide this ioctl. x86 includes both i386 and x86_64. - Type: system, vm, or vcpu. + Type: + system, vm, or vcpu. - Parameters: what parameters are accepted by the ioctl. + Parameters: + what parameters are accepted by the ioctl. - Returns: the return value. General error numbers (EBADF, ENOMEM, EINVAL) + Returns: + the return value. General error numbers (EBADF, ENOMEM, EINVAL) are not detailed, but errors with specific meanings are. 4.1 KVM_GET_API_VERSION +----------------------- -Capability: basic -Architectures: all -Type: system ioctl -Parameters: none -Returns: the constant KVM_API_VERSION (=12) +:Capability: basic +:Architectures: all +:Type: system ioctl +:Parameters: none +:Returns: the constant KVM_API_VERSION (=12) This identifies the API version as the stable kvm API. It is not expected that this number will change. However, Linux 2.6.20 and @@ -127,12 +136,13 @@ described as 'basic' will be available. 4.2 KVM_CREATE_VM +----------------- -Capability: basic -Architectures: all -Type: system ioctl -Parameters: machine type identifier (KVM_VM_*) -Returns: a VM fd that can be used to control the new virtual machine. +:Capability: basic +:Architectures: all +:Type: system ioctl +:Parameters: machine type identifier (KVM_VM_*) +:Returns: a VM fd that can be used to control the new virtual machine. The new VM has no virtual cpus and no memory. You probably want to use 0 as machine type. @@ -155,17 +165,17 @@ identifier, where IPA_Bits is the maximum width of any physical address used by the VM. The IPA_Bits is encoded in bits[7-0] of the machine type identifier. -e.g, to configure a guest to use 48bit physical address size : +e.g, to configure a guest to use 48bit physical address size:: vm_fd = ioctl(dev_fd, KVM_CREATE_VM, KVM_VM_TYPE_ARM_IPA_SIZE(48)); -The requested size (IPA_Bits) must be : - 0 - Implies default size, 40bits (for backward compatibility) +The requested size (IPA_Bits) must be: - or - - N - Implies N bits, where N is a positive integer such that, + == ========================================================= + 0 Implies default size, 40bits (for backward compatibility) + N Implies N bits, where N is a positive integer such that, 32 <= N <= Host_IPA_Limit + == ========================================================= Host_IPA_Limit is the maximum possible value for IPA_Bits on the host and is dependent on the CPU capability and the kernel configuration. The limit can @@ -179,21 +189,28 @@ host physical address translations). 4.3 KVM_GET_MSR_INDEX_LIST, KVM_GET_MSR_FEATURE_INDEX_LIST +---------------------------------------------------------- + +:Capability: basic, KVM_CAP_GET_MSR_FEATURES for KVM_GET_MSR_FEATURE_INDEX_LIST +:Architectures: x86 +:Type: system ioctl +:Parameters: struct kvm_msr_list (in/out) +:Returns: 0 on success; -1 on error -Capability: basic, KVM_CAP_GET_MSR_FEATURES for KVM_GET_MSR_FEATURE_INDEX_LIST -Architectures: x86 -Type: system ioctl -Parameters: struct kvm_msr_list (in/out) -Returns: 0 on success; -1 on error Errors: - EFAULT: the msr index list cannot be read from or written to - E2BIG: the msr index list is to be to fit in the array specified by + + ====== ============================================================ + EFAULT the msr index list cannot be read from or written to + E2BIG the msr index list is to be to fit in the array specified by the user. + ====== ============================================================ -struct kvm_msr_list { +:: + + struct kvm_msr_list { __u32 nmsrs; /* number of msrs in entries */ __u32 indices[0]; -}; + }; The user fills in the size of the indices array in nmsrs, and in return kvm adjusts nmsrs to reflect the actual number of msrs and fills in the @@ -214,12 +231,13 @@ otherwise. 4.4 KVM_CHECK_EXTENSION +----------------------- -Capability: basic, KVM_CAP_CHECK_EXTENSION_VM for vm ioctl -Architectures: all -Type: system ioctl, vm ioctl -Parameters: extension identifier (KVM_CAP_*) -Returns: 0 if unsupported; 1 (or some other positive integer) if supported +:Capability: basic, KVM_CAP_CHECK_EXTENSION_VM for vm ioctl +:Architectures: all +:Type: system ioctl, vm ioctl +:Parameters: extension identifier (KVM_CAP_*) +:Returns: 0 if unsupported; 1 (or some other positive integer) if supported The API allows the application to query about extensions to the core kvm API. Userspace passes an extension identifier (an integer) and @@ -232,12 +250,13 @@ It is thus encouraged to use the vm ioctl to query for capabilities (available with KVM_CAP_CHECK_EXTENSION_VM on the vm fd) 4.5 KVM_GET_VCPU_MMAP_SIZE +-------------------------- -Capability: basic -Architectures: all -Type: system ioctl -Parameters: none -Returns: size of vcpu mmap area, in bytes +:Capability: basic +:Architectures: all +:Type: system ioctl +:Parameters: none +:Returns: size of vcpu mmap area, in bytes The KVM_RUN ioctl (cf.) communicates with userspace via a shared memory region. This ioctl returns the size of that region. See the @@ -245,23 +264,25 @@ KVM_RUN documentation for details. 4.6 KVM_SET_MEMORY_REGION +------------------------- -Capability: basic -Architectures: all -Type: vm ioctl -Parameters: struct kvm_memory_region (in) -Returns: 0 on success, -1 on error +:Capability: basic +:Architectures: all +:Type: vm ioctl +:Parameters: struct kvm_memory_region (in) +:Returns: 0 on success, -1 on error This ioctl is obsolete and has been removed. 4.7 KVM_CREATE_VCPU +------------------- -Capability: basic -Architectures: all -Type: vm ioctl -Parameters: vcpu id (apic id on x86) -Returns: vcpu fd on success, -1 on error +:Capability: basic +:Architectures: all +:Type: vm ioctl +:Parameters: vcpu id (apic id on x86) +:Returns: vcpu fd on success, -1 on error This API adds a vcpu to a virtual machine. No more than max_vcpus may be added. The vcpu id is an integer in the range [0, max_vcpu_id). @@ -302,22 +323,25 @@ cpu's hardware control block. 4.8 KVM_GET_DIRTY_LOG (vm ioctl) +-------------------------------- -Capability: basic -Architectures: all -Type: vm ioctl -Parameters: struct kvm_dirty_log (in/out) -Returns: 0 on success, -1 on error +:Capability: basic +:Architectures: all +:Type: vm ioctl +:Parameters: struct kvm_dirty_log (in/out) +:Returns: 0 on success, -1 on error -/* for KVM_GET_DIRTY_LOG */ -struct kvm_dirty_log { +:: + + /* for KVM_GET_DIRTY_LOG */ + struct kvm_dirty_log { __u32 slot; __u32 padding; union { void __user *dirty_bitmap; /* one bit per page */ __u64 padding; }; -}; + }; Given a memory slot, return a bitmap containing any pages dirtied since the last call to this ioctl. Bit 0 is the first page in the @@ -334,25 +358,31 @@ KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 is enabled. For more information, see the description of the capability. 4.9 KVM_SET_MEMORY_ALIAS +------------------------ -Capability: basic -Architectures: x86 -Type: vm ioctl -Parameters: struct kvm_memory_alias (in) -Returns: 0 (success), -1 (error) +:Capability: basic +:Architectures: x86 +:Type: vm ioctl +:Parameters: struct kvm_memory_alias (in) +:Returns: 0 (success), -1 (error) This ioctl is obsolete and has been removed. 4.10 KVM_RUN +------------ + +:Capability: basic +:Architectures: all +:Type: vcpu ioctl +:Parameters: none +:Returns: 0 on success, -1 on error -Capability: basic -Architectures: all -Type: vcpu ioctl -Parameters: none -Returns: 0 on success, -1 on error Errors: - EINTR: an unmasked signal is pending + + ===== ============================= + EINTR an unmasked signal is pending + ===== ============================= This ioctl is used to run a guest virtual cpu. While there are no explicit parameters, there is an implicit parameter block that can be @@ -362,42 +392,46 @@ kvm_run' (see below). 4.11 KVM_GET_REGS +----------------- -Capability: basic -Architectures: all except ARM, arm64 -Type: vcpu ioctl -Parameters: struct kvm_regs (out) -Returns: 0 on success, -1 on error +:Capability: basic +:Architectures: all except ARM, arm64 +:Type: vcpu ioctl +:Parameters: struct kvm_regs (out) +:Returns: 0 on success, -1 on error Reads the general purpose registers from the vcpu. -/* x86 */ -struct kvm_regs { +:: + + /* x86 */ + struct kvm_regs { /* out (KVM_GET_REGS) / in (KVM_SET_REGS) */ __u64 rax, rbx, rcx, rdx; __u64 rsi, rdi, rsp, rbp; __u64 r8, r9, r10, r11; __u64 r12, r13, r14, r15; __u64 rip, rflags; -}; + }; -/* mips */ -struct kvm_regs { + /* mips */ + struct kvm_regs { /* out (KVM_GET_REGS) / in (KVM_SET_REGS) */ __u64 gpr[32]; __u64 hi; __u64 lo; __u64 pc; -}; + }; 4.12 KVM_SET_REGS +----------------- -Capability: basic -Architectures: all except ARM, arm64 -Type: vcpu ioctl -Parameters: struct kvm_regs (in) -Returns: 0 on success, -1 on error +:Capability: basic +:Architectures: all except ARM, arm64 +:Type: vcpu ioctl +:Parameters: struct kvm_regs (in) +:Returns: 0 on success, -1 on error Writes the general purpose registers into the vcpu. @@ -405,17 +439,20 @@ See KVM_GET_REGS for the data structure. 4.13 KVM_GET_SREGS +------------------ -Capability: basic -Architectures: x86, ppc -Type: vcpu ioctl -Parameters: struct kvm_sregs (out) -Returns: 0 on success, -1 on error +:Capability: basic +:Architectures: x86, ppc +:Type: vcpu ioctl +:Parameters: struct kvm_sregs (out) +:Returns: 0 on success, -1 on error Reads special registers from the vcpu. -/* x86 */ -struct kvm_sregs { +:: + + /* x86 */ + struct kvm_sregs { struct kvm_segment cs, ds, es, fs, gs, ss; struct kvm_segment tr, ldt; struct kvm_dtable gdt, idt; @@ -423,9 +460,9 @@ struct kvm_sregs { __u64 efer; __u64 apic_base; __u64 interrupt_bitmap[(KVM_NR_INTERRUPTS + 63) / 64]; -}; + }; -/* ppc -- see arch/powerpc/include/uapi/asm/kvm.h */ + /* ppc -- see arch/powerpc/include/uapi/asm/kvm.h */ interrupt_bitmap is a bitmap of pending external interrupts. At most one bit may be set. This interrupt has been acknowledged by the APIC @@ -433,29 +470,33 @@ but not yet injected into the cpu core. 4.14 KVM_SET_SREGS +------------------ -Capability: basic -Architectures: x86, ppc -Type: vcpu ioctl -Parameters: struct kvm_sregs (in) -Returns: 0 on success, -1 on error +:Capability: basic +:Architectures: x86, ppc +:Type: vcpu ioctl +:Parameters: struct kvm_sregs (in) +:Returns: 0 on success, -1 on error Writes special registers into the vcpu. See KVM_GET_SREGS for the data structures. 4.15 KVM_TRANSLATE +------------------ -Capability: basic -Architectures: x86 -Type: vcpu ioctl -Parameters: struct kvm_translation (in/out) -Returns: 0 on success, -1 on error +:Capability: basic +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_translation (in/out) +:Returns: 0 on success, -1 on error Translates a virtual address according to the vcpu's current address translation mode. -struct kvm_translation { +:: + + struct kvm_translation { /* in */ __u64 linear_address; @@ -465,59 +506,68 @@ struct kvm_translation { __u8 writeable; __u8 usermode; __u8 pad[5]; -}; + }; 4.16 KVM_INTERRUPT +------------------ -Capability: basic -Architectures: x86, ppc, mips -Type: vcpu ioctl -Parameters: struct kvm_interrupt (in) -Returns: 0 on success, negative on failure. +:Capability: basic +:Architectures: x86, ppc, mips +:Type: vcpu ioctl +:Parameters: struct kvm_interrupt (in) +:Returns: 0 on success, negative on failure. Queues a hardware interrupt vector to be injected. -/* for KVM_INTERRUPT */ -struct kvm_interrupt { +:: + + /* for KVM_INTERRUPT */ + struct kvm_interrupt { /* in */ __u32 irq; -}; + }; X86: +^^^^ + +:Returns: -Returns: 0 on success, - -EEXIST if an interrupt is already enqueued - -EINVAL the the irq number is invalid - -ENXIO if the PIC is in the kernel - -EFAULT if the pointer is invalid + ========= =================================== + 0 on success, + -EEXIST if an interrupt is already enqueued + -EINVAL the the irq number is invalid + -ENXIO if the PIC is in the kernel + -EFAULT if the pointer is invalid + ========= =================================== Note 'irq' is an interrupt vector, not an interrupt pin or line. This ioctl is useful if the in-kernel PIC is not used. PPC: +^^^^ Queues an external interrupt to be injected. This ioctl is overleaded with 3 different irq values: a) KVM_INTERRUPT_SET - This injects an edge type external interrupt into the guest once it's ready - to receive interrupts. When injected, the interrupt is done. + This injects an edge type external interrupt into the guest once it's ready + to receive interrupts. When injected, the interrupt is done. b) KVM_INTERRUPT_UNSET - This unsets any pending interrupt. + This unsets any pending interrupt. - Only available with KVM_CAP_PPC_UNSET_IRQ. + Only available with KVM_CAP_PPC_UNSET_IRQ. c) KVM_INTERRUPT_SET_LEVEL - This injects a level type external interrupt into the guest context. The - interrupt stays pending until a specific ioctl with KVM_INTERRUPT_UNSET - is triggered. + This injects a level type external interrupt into the guest context. The + interrupt stays pending until a specific ioctl with KVM_INTERRUPT_UNSET + is triggered. - Only available with KVM_CAP_PPC_IRQ_LEVEL. + Only available with KVM_CAP_PPC_IRQ_LEVEL. Note that any value for 'irq' other than the ones stated above is invalid and incurs unexpected behavior. @@ -525,6 +575,7 @@ and incurs unexpected behavior. This is an asynchronous vcpu ioctl and can be invoked from any thread. MIPS: +^^^^^ Queues an external interrupt to be injected into the virtual CPU. A negative interrupt number dequeues the interrupt. @@ -533,24 +584,26 @@ This is an asynchronous vcpu ioctl and can be invoked from any thread. 4.17 KVM_DEBUG_GUEST +-------------------- -Capability: basic -Architectures: none -Type: vcpu ioctl -Parameters: none) -Returns: -1 on error +:Capability: basic +:Architectures: none +:Type: vcpu ioctl +:Parameters: none) +:Returns: -1 on error Support for this has been removed. Use KVM_SET_GUEST_DEBUG instead. 4.18 KVM_GET_MSRS +----------------- -Capability: basic (vcpu), KVM_CAP_GET_MSR_FEATURES (system) -Architectures: x86 -Type: system ioctl, vcpu ioctl -Parameters: struct kvm_msrs (in/out) -Returns: number of msrs successfully returned; - -1 on error +:Capability: basic (vcpu), KVM_CAP_GET_MSR_FEATURES (system) +:Architectures: x86 +:Type: system ioctl, vcpu ioctl +:Parameters: struct kvm_msrs (in/out) +:Returns: number of msrs successfully returned; + -1 on error When used as a system ioctl: Reads the values of MSR-based features that are available for the VM. This @@ -562,18 +615,20 @@ When used as a vcpu ioctl: Reads model-specific registers from the vcpu. Supported msr indices can be obtained using KVM_GET_MSR_INDEX_LIST in a system ioctl. -struct kvm_msrs { +:: + + struct kvm_msrs { __u32 nmsrs; /* number of msrs in entries */ __u32 pad; struct kvm_msr_entry entries[0]; -}; + }; -struct kvm_msr_entry { + struct kvm_msr_entry { __u32 index; __u32 reserved; __u64 data; -}; + }; Application code should set the 'nmsrs' member (which indicates the size of the entries array) and the 'index' member of each array entry. @@ -581,12 +636,13 @@ kvm will fill in the 'data' member. 4.19 KVM_SET_MSRS +----------------- -Capability: basic -Architectures: x86 -Type: vcpu ioctl -Parameters: struct kvm_msrs (in) -Returns: number of msrs successfully set (see below), -1 on error +:Capability: basic +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_msrs (in) +:Returns: number of msrs successfully set (see below), -1 on error Writes model-specific registers to the vcpu. See KVM_GET_MSRS for the data structures. @@ -602,41 +658,44 @@ MSRs that have been set successfully. 4.20 KVM_SET_CPUID +------------------ -Capability: basic -Architectures: x86 -Type: vcpu ioctl -Parameters: struct kvm_cpuid (in) -Returns: 0 on success, -1 on error +:Capability: basic +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_cpuid (in) +:Returns: 0 on success, -1 on error Defines the vcpu responses to the cpuid instruction. Applications should use the KVM_SET_CPUID2 ioctl if available. +:: -struct kvm_cpuid_entry { + struct kvm_cpuid_entry { __u32 function; __u32 eax; __u32 ebx; __u32 ecx; __u32 edx; __u32 padding; -}; + }; -/* for KVM_SET_CPUID */ -struct kvm_cpuid { + /* for KVM_SET_CPUID */ + struct kvm_cpuid { __u32 nent; __u32 padding; struct kvm_cpuid_entry entries[0]; -}; + }; 4.21 KVM_SET_SIGNAL_MASK +------------------------ -Capability: basic -Architectures: all -Type: vcpu ioctl -Parameters: struct kvm_signal_mask (in) -Returns: 0 on success, -1 on error +:Capability: basic +:Architectures: all +:Type: vcpu ioctl +:Parameters: struct kvm_signal_mask (in) +:Returns: 0 on success, -1 on error Defines which signals are blocked during execution of KVM_RUN. This signal mask temporarily overrides the threads signal mask. Any @@ -646,25 +705,30 @@ their traditional behaviour) will cause KVM_RUN to return with -EINTR. Note the signal will only be delivered if not blocked by the original signal mask. -/* for KVM_SET_SIGNAL_MASK */ -struct kvm_signal_mask { +:: + + /* for KVM_SET_SIGNAL_MASK */ + struct kvm_signal_mask { __u32 len; __u8 sigset[0]; -}; + }; 4.22 KVM_GET_FPU +---------------- -Capability: basic -Architectures: x86 -Type: vcpu ioctl -Parameters: struct kvm_fpu (out) -Returns: 0 on success, -1 on error +:Capability: basic +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_fpu (out) +:Returns: 0 on success, -1 on error Reads the floating point state from the vcpu. -/* for KVM_GET_FPU and KVM_SET_FPU */ -struct kvm_fpu { +:: + + /* for KVM_GET_FPU and KVM_SET_FPU */ + struct kvm_fpu { __u8 fpr[8][16]; __u16 fcw; __u16 fsw; @@ -676,21 +740,24 @@ struct kvm_fpu { __u8 xmm[16][16]; __u32 mxcsr; __u32 pad2; -}; + }; 4.23 KVM_SET_FPU +---------------- -Capability: basic -Architectures: x86 -Type: vcpu ioctl -Parameters: struct kvm_fpu (in) -Returns: 0 on success, -1 on error +:Capability: basic +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_fpu (in) +:Returns: 0 on success, -1 on error Writes the floating point state to the vcpu. -/* for KVM_GET_FPU and KVM_SET_FPU */ -struct kvm_fpu { +:: + + /* for KVM_GET_FPU and KVM_SET_FPU */ + struct kvm_fpu { __u8 fpr[8][16]; __u16 fcw; __u16 fsw; @@ -702,16 +769,17 @@ struct kvm_fpu { __u8 xmm[16][16]; __u32 mxcsr; __u32 pad2; -}; + }; 4.24 KVM_CREATE_IRQCHIP +----------------------- -Capability: KVM_CAP_IRQCHIP, KVM_CAP_S390_IRQCHIP (s390) -Architectures: x86, ARM, arm64, s390 -Type: vm ioctl -Parameters: none -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_IRQCHIP, KVM_CAP_S390_IRQCHIP (s390) +:Architectures: x86, ARM, arm64, s390 +:Type: vm ioctl +:Parameters: none +:Returns: 0 on success, -1 on error Creates an interrupt controller model in the kernel. On x86, creates a virtual ioapic, a virtual PIC (two PICs, nested), and sets up @@ -727,12 +795,13 @@ before KVM_CREATE_IRQCHIP can be used. 4.25 KVM_IRQ_LINE +----------------- -Capability: KVM_CAP_IRQCHIP -Architectures: x86, arm, arm64 -Type: vm ioctl -Parameters: struct kvm_irq_level -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_IRQCHIP +:Architectures: x86, arm, arm64 +:Type: vm ioctl +:Parameters: struct kvm_irq_level +:Returns: 0 on success, -1 on error Sets the level of a GSI input to the interrupt controller model in the kernel. On some architectures it is required that an interrupt controller model has @@ -756,16 +825,20 @@ of course). ARM/arm64 can signal an interrupt either at the CPU level, or at the in-kernel irqchip (GIC), and for in-kernel irqchip can tell the GIC to use PPIs designated for specific cpus. The irq field is interpreted -like this: +like this::  bits: | 31 ... 28 | 27 ... 24 | 23 ... 16 | 15 ... 0 | field: | vcpu2_index | irq_type | vcpu_index | irq_id | The irq_type field has the following values: -- irq_type[0]: out-of-kernel GIC: irq_id 0 is IRQ, irq_id 1 is FIQ -- irq_type[1]: in-kernel GIC: SPI, irq_id between 32 and 1019 (incl.) + +- irq_type[0]: + out-of-kernel GIC: irq_id 0 is IRQ, irq_id 1 is FIQ +- irq_type[1]: + in-kernel GIC: SPI, irq_id between 32 and 1019 (incl.) (the vcpu_index field is ignored) -- irq_type[2]: in-kernel GIC: PPI, irq_id between 16 and 31 (incl.) +- irq_type[2]: + in-kernel GIC: PPI, irq_id between 16 and 31 (incl.) (The irq_id field thus corresponds nicely to the IRQ ID in the ARM GIC specs) @@ -779,27 +852,32 @@ Note that on arm/arm64, the KVM_CAP_IRQCHIP capability only conditions injection of interrupts for the in-kernel irqchip. KVM_IRQ_LINE can always be used for a userspace interrupt controller. -struct kvm_irq_level { +:: + + struct kvm_irq_level { union { __u32 irq; /* GSI */ __s32 status; /* not used for KVM_IRQ_LEVEL */ }; __u32 level; /* 0 or 1 */ -}; + }; 4.26 KVM_GET_IRQCHIP +-------------------- -Capability: KVM_CAP_IRQCHIP -Architectures: x86 -Type: vm ioctl -Parameters: struct kvm_irqchip (in/out) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_IRQCHIP +:Architectures: x86 +:Type: vm ioctl +:Parameters: struct kvm_irqchip (in/out) +:Returns: 0 on success, -1 on error Reads the state of a kernel interrupt controller created with KVM_CREATE_IRQCHIP into a buffer provided by the caller. -struct kvm_irqchip { +:: + + struct kvm_irqchip { __u32 chip_id; /* 0 = PIC1, 1 = PIC2, 2 = IOAPIC */ __u32 pad; union { @@ -807,21 +885,24 @@ struct kvm_irqchip { struct kvm_pic_state pic; struct kvm_ioapic_state ioapic; } chip; -}; + }; 4.27 KVM_SET_IRQCHIP +-------------------- -Capability: KVM_CAP_IRQCHIP -Architectures: x86 -Type: vm ioctl -Parameters: struct kvm_irqchip (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_IRQCHIP +:Architectures: x86 +:Type: vm ioctl +:Parameters: struct kvm_irqchip (in) +:Returns: 0 on success, -1 on error Sets the state of a kernel interrupt controller created with KVM_CREATE_IRQCHIP from a buffer provided by the caller. -struct kvm_irqchip { +:: + + struct kvm_irqchip { __u32 chip_id; /* 0 = PIC1, 1 = PIC2, 2 = IOAPIC */ __u32 pad; union { @@ -829,16 +910,17 @@ struct kvm_irqchip { struct kvm_pic_state pic; struct kvm_ioapic_state ioapic; } chip; -}; + }; 4.28 KVM_XEN_HVM_CONFIG +----------------------- -Capability: KVM_CAP_XEN_HVM -Architectures: x86 -Type: vm ioctl -Parameters: struct kvm_xen_hvm_config (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_XEN_HVM +:Architectures: x86 +:Type: vm ioctl +:Parameters: struct kvm_xen_hvm_config (in) +:Returns: 0 on success, -1 on error Sets the MSR that the Xen HVM guest uses to initialize its hypercall page, and provides the starting address and size of the hypercall @@ -846,7 +928,9 @@ blobs in userspace. When the guest writes the MSR, kvm copies one page of a blob (32- or 64-bit, depending on the vcpu mode) to guest memory. -struct kvm_xen_hvm_config { +:: + + struct kvm_xen_hvm_config { __u32 flags; __u32 msr; __u64 blob_addr_32; @@ -854,16 +938,17 @@ struct kvm_xen_hvm_config { __u8 blob_size_32; __u8 blob_size_64; __u8 pad2[30]; -}; + }; 4.29 KVM_GET_CLOCK +------------------ -Capability: KVM_CAP_ADJUST_CLOCK -Architectures: x86 -Type: vm ioctl -Parameters: struct kvm_clock_data (out) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_ADJUST_CLOCK +:Architectures: x86 +:Type: vm ioctl +:Parameters: struct kvm_clock_data (out) +:Returns: 0 on success, -1 on error Gets the current timestamp of kvmclock as seen by the current guest. In conjunction with KVM_SET_CLOCK, it is used to ensure monotonicity on scenarios @@ -880,47 +965,56 @@ with KVM_SET_CLOCK. KVM will try to make all VCPUs follow this clock, but the exact value read by each VCPU could differ, because the host TSC is not stable. -struct kvm_clock_data { +:: + + struct kvm_clock_data { __u64 clock; /* kvmclock current value */ __u32 flags; __u32 pad[9]; -}; + }; 4.30 KVM_SET_CLOCK +------------------ -Capability: KVM_CAP_ADJUST_CLOCK -Architectures: x86 -Type: vm ioctl -Parameters: struct kvm_clock_data (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_ADJUST_CLOCK +:Architectures: x86 +:Type: vm ioctl +:Parameters: struct kvm_clock_data (in) +:Returns: 0 on success, -1 on error Sets the current timestamp of kvmclock to the value specified in its parameter. In conjunction with KVM_GET_CLOCK, it is used to ensure monotonicity on scenarios such as migration. -struct kvm_clock_data { +:: + + struct kvm_clock_data { __u64 clock; /* kvmclock current value */ __u32 flags; __u32 pad[9]; -}; + }; 4.31 KVM_GET_VCPU_EVENTS +------------------------ -Capability: KVM_CAP_VCPU_EVENTS -Extended by: KVM_CAP_INTR_SHADOW -Architectures: x86, arm, arm64 -Type: vcpu ioctl -Parameters: struct kvm_vcpu_event (out) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_VCPU_EVENTS +:Extended by: KVM_CAP_INTR_SHADOW +:Architectures: x86, arm, arm64 +:Type: vcpu ioctl +:Parameters: struct kvm_vcpu_event (out) +:Returns: 0 on success, -1 on error X86: +^^^^ Gets currently pending exceptions, interrupts, and NMIs as well as related states of the vcpu. -struct kvm_vcpu_events { +:: + + struct kvm_vcpu_events { struct { __u8 injected; __u8 nr; @@ -951,7 +1045,7 @@ struct kvm_vcpu_events { __u8 reserved[27]; __u8 exception_has_payload; __u64 exception_payload; -}; + }; The following bits are defined in the flags field: @@ -967,6 +1061,7 @@ The following bits are defined in the flags field: KVM_CAP_EXCEPTION_PAYLOAD is enabled. ARM/ARM64: +^^^^^^^^^^ If the guest accesses a device that is being emulated by the host kernel in such a way that a real device would generate a physical SError, KVM may make @@ -1006,8 +1101,9 @@ It is not possible to read back a pending external abort (injected via KVM_SET_VCPU_EVENTS or otherwise) because such an exception is always delivered directly to the virtual CPU). +:: -struct kvm_vcpu_events { + struct kvm_vcpu_events { struct { __u8 serror_pending; __u8 serror_has_esr; @@ -1017,18 +1113,20 @@ struct kvm_vcpu_events { __u64 serror_esr; } exception; __u32 reserved[12]; -}; + }; 4.32 KVM_SET_VCPU_EVENTS +------------------------ -Capability: KVM_CAP_VCPU_EVENTS -Extended by: KVM_CAP_INTR_SHADOW -Architectures: x86, arm, arm64 -Type: vcpu ioctl -Parameters: struct kvm_vcpu_event (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_VCPU_EVENTS +:Extended by: KVM_CAP_INTR_SHADOW +:Architectures: x86, arm, arm64 +:Type: vcpu ioctl +:Parameters: struct kvm_vcpu_event (in) +:Returns: 0 on success, -1 on error X86: +^^^^ Set pending exceptions, interrupts, and NMIs as well as related states of the vcpu. @@ -1040,9 +1138,11 @@ from the update. These fields are nmi.pending, sipi_vector, smi.smm, smi.pending. Keep the corresponding bits in the flags field cleared to suppress overwriting the current in-kernel state. The bits are: -KVM_VCPUEVENT_VALID_NMI_PENDING - transfer nmi.pending to the kernel -KVM_VCPUEVENT_VALID_SIPI_VECTOR - transfer sipi_vector -KVM_VCPUEVENT_VALID_SMM - transfer the smi sub-struct. +=============================== ================================== +KVM_VCPUEVENT_VALID_NMI_PENDING transfer nmi.pending to the kernel +KVM_VCPUEVENT_VALID_SIPI_VECTOR transfer sipi_vector +KVM_VCPUEVENT_VALID_SMM transfer the smi sub-struct. +=============================== ================================== If KVM_CAP_INTR_SHADOW is available, KVM_VCPUEVENT_VALID_SHADOW can be set in the flags field to signal that interrupt.shadow contains a valid state and @@ -1056,6 +1156,7 @@ exception_has_payload, exception_payload, and exception.pending fields contain a valid state and shall be written into the VCPU. ARM/ARM64: +^^^^^^^^^^ User space may need to inject several types of events to the guest. @@ -1078,31 +1179,35 @@ See KVM_GET_VCPU_EVENTS for the data structure. 4.33 KVM_GET_DEBUGREGS +---------------------- -Capability: KVM_CAP_DEBUGREGS -Architectures: x86 -Type: vm ioctl -Parameters: struct kvm_debugregs (out) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_DEBUGREGS +:Architectures: x86 +:Type: vm ioctl +:Parameters: struct kvm_debugregs (out) +:Returns: 0 on success, -1 on error Reads debug registers from the vcpu. -struct kvm_debugregs { +:: + + struct kvm_debugregs { __u64 db[4]; __u64 dr6; __u64 dr7; __u64 flags; __u64 reserved[9]; -}; + }; 4.34 KVM_SET_DEBUGREGS +---------------------- -Capability: KVM_CAP_DEBUGREGS -Architectures: x86 -Type: vm ioctl -Parameters: struct kvm_debugregs (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_DEBUGREGS +:Architectures: x86 +:Type: vm ioctl +:Parameters: struct kvm_debugregs (in) +:Returns: 0 on success, -1 on error Writes debug registers into the vcpu. @@ -1111,24 +1216,27 @@ yet and must be cleared on entry. 4.35 KVM_SET_USER_MEMORY_REGION +------------------------------- -Capability: KVM_CAP_USER_MEMORY -Architectures: all -Type: vm ioctl -Parameters: struct kvm_userspace_memory_region (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_USER_MEMORY +:Architectures: all +:Type: vm ioctl +:Parameters: struct kvm_userspace_memory_region (in) +:Returns: 0 on success, -1 on error -struct kvm_userspace_memory_region { +:: + + struct kvm_userspace_memory_region { __u32 slot; __u32 flags; __u64 guest_phys_addr; __u64 memory_size; /* bytes */ __u64 userspace_addr; /* start of the userspace allocated memory */ -}; + }; -/* for kvm_memory_region::flags */ -#define KVM_MEM_LOG_DIRTY_PAGES (1UL << 0) -#define KVM_MEM_READONLY (1UL << 1) + /* for kvm_memory_region::flags */ + #define KVM_MEM_LOG_DIRTY_PAGES (1UL << 0) + #define KVM_MEM_READONLY (1UL << 1) This ioctl allows the user to create, modify or delete a guest physical memory slot. Bits 0-15 of "slot" specify the slot id and this value @@ -1174,12 +1282,13 @@ allocation and is deprecated. 4.36 KVM_SET_TSS_ADDR +--------------------- -Capability: KVM_CAP_SET_TSS_ADDR -Architectures: x86 -Type: vm ioctl -Parameters: unsigned long tss_address (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_SET_TSS_ADDR +:Architectures: x86 +:Type: vm ioctl +:Parameters: unsigned long tss_address (in) +:Returns: 0 on success, -1 on error This ioctl defines the physical address of a three-page region in the guest physical address space. The region must be within the first 4GB of the @@ -1193,21 +1302,24 @@ documentation when it pops into existence). 4.37 KVM_ENABLE_CAP +------------------- + +:Capability: KVM_CAP_ENABLE_CAP +:Architectures: mips, ppc, s390 +:Type: vcpu ioctl +:Parameters: struct kvm_enable_cap (in) +:Returns: 0 on success; -1 on error -Capability: KVM_CAP_ENABLE_CAP -Architectures: mips, ppc, s390 -Type: vcpu ioctl -Parameters: struct kvm_enable_cap (in) -Returns: 0 on success; -1 on error +:Capability: KVM_CAP_ENABLE_CAP_VM +:Architectures: all +:Type: vcpu ioctl +:Parameters: struct kvm_enable_cap (in) +:Returns: 0 on success; -1 on error -Capability: KVM_CAP_ENABLE_CAP_VM -Architectures: all -Type: vcpu ioctl -Parameters: struct kvm_enable_cap (in) -Returns: 0 on success; -1 on error +.. note:: -+Not all extensions are enabled by default. Using this ioctl the application -can enable an extension, making it available to the guest. + Not all extensions are enabled by default. Using this ioctl the application + can enable an extension, making it available to the guest. On systems that do not support this ioctl, it always fails. On systems that do support it, it only works for extensions that are supported for enablement. @@ -1215,76 +1327,91 @@ do support it, it only works for extensions that are supported for enablement. To check if a capability can be enabled, the KVM_CHECK_EXTENSION ioctl should be used. -struct kvm_enable_cap { +:: + + struct kvm_enable_cap { /* in */ __u32 cap; The capability that is supposed to get enabled. +:: + __u32 flags; A bitfield indicating future enhancements. Has to be 0 for now. +:: + __u64 args[4]; Arguments for enabling a feature. If a feature needs initial values to function properly, this is the place to put them. +:: + __u8 pad[64]; -}; + }; The vcpu ioctl should be used for vcpu-specific capabilities, the vm ioctl for vm-wide capabilities. 4.38 KVM_GET_MP_STATE +--------------------- + +:Capability: KVM_CAP_MP_STATE +:Architectures: x86, s390, arm, arm64 +:Type: vcpu ioctl +:Parameters: struct kvm_mp_state (out) +:Returns: 0 on success; -1 on error -Capability: KVM_CAP_MP_STATE -Architectures: x86, s390, arm, arm64 -Type: vcpu ioctl -Parameters: struct kvm_mp_state (out) -Returns: 0 on success; -1 on error +:: -struct kvm_mp_state { + struct kvm_mp_state { __u32 mp_state; -}; + }; Returns the vcpu's current "multiprocessing state" (though also valid on uniprocessor guests). Possible values are: - - KVM_MP_STATE_RUNNABLE: the vcpu is currently running [x86,arm/arm64] - - KVM_MP_STATE_UNINITIALIZED: the vcpu is an application processor (AP) + ========================== =============================================== + KVM_MP_STATE_RUNNABLE the vcpu is currently running [x86,arm/arm64] + KVM_MP_STATE_UNINITIALIZED the vcpu is an application processor (AP) which has not yet received an INIT signal [x86] - - KVM_MP_STATE_INIT_RECEIVED: the vcpu has received an INIT signal, and is + KVM_MP_STATE_INIT_RECEIVED the vcpu has received an INIT signal, and is now ready for a SIPI [x86] - - KVM_MP_STATE_HALTED: the vcpu has executed a HLT instruction and + KVM_MP_STATE_HALTED the vcpu has executed a HLT instruction and is waiting for an interrupt [x86] - - KVM_MP_STATE_SIPI_RECEIVED: the vcpu has just received a SIPI (vector + KVM_MP_STATE_SIPI_RECEIVED the vcpu has just received a SIPI (vector accessible via KVM_GET_VCPU_EVENTS) [x86] - - KVM_MP_STATE_STOPPED: the vcpu is stopped [s390,arm/arm64] - - KVM_MP_STATE_CHECK_STOP: the vcpu is in a special error state [s390] - - KVM_MP_STATE_OPERATING: the vcpu is operating (running or halted) + KVM_MP_STATE_STOPPED the vcpu is stopped [s390,arm/arm64] + KVM_MP_STATE_CHECK_STOP the vcpu is in a special error state [s390] + KVM_MP_STATE_OPERATING the vcpu is operating (running or halted) [s390] - - KVM_MP_STATE_LOAD: the vcpu is in a special load/startup state + KVM_MP_STATE_LOAD the vcpu is in a special load/startup state [s390] + ========================== =============================================== On x86, this ioctl is only useful after KVM_CREATE_IRQCHIP. Without an in-kernel irqchip, the multiprocessing state must be maintained by userspace on these architectures. For arm/arm64: +^^^^^^^^^^^^^^ The only states that are valid are KVM_MP_STATE_STOPPED and KVM_MP_STATE_RUNNABLE which reflect if the vcpu is paused or not. 4.39 KVM_SET_MP_STATE +--------------------- -Capability: KVM_CAP_MP_STATE -Architectures: x86, s390, arm, arm64 -Type: vcpu ioctl -Parameters: struct kvm_mp_state (in) -Returns: 0 on success; -1 on error +:Capability: KVM_CAP_MP_STATE +:Architectures: x86, s390, arm, arm64 +:Type: vcpu ioctl +:Parameters: struct kvm_mp_state (in) +:Returns: 0 on success; -1 on error Sets the vcpu's current "multiprocessing state"; see KVM_GET_MP_STATE for arguments. @@ -1294,17 +1421,19 @@ in-kernel irqchip, the multiprocessing state must be maintained by userspace on these architectures. For arm/arm64: +^^^^^^^^^^^^^^ The only states that are valid are KVM_MP_STATE_STOPPED and KVM_MP_STATE_RUNNABLE which reflect if the vcpu should be paused or not. 4.40 KVM_SET_IDENTITY_MAP_ADDR +------------------------------ -Capability: KVM_CAP_SET_IDENTITY_MAP_ADDR -Architectures: x86 -Type: vm ioctl -Parameters: unsigned long identity (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_SET_IDENTITY_MAP_ADDR +:Architectures: x86 +:Type: vm ioctl +:Parameters: unsigned long identity (in) +:Returns: 0 on success, -1 on error This ioctl defines the physical address of a one-page region in the guest physical address space. The region must be within the first 4GB of the @@ -1322,12 +1451,13 @@ documentation when it pops into existence). Fails if any VCPU has already been created. 4.41 KVM_SET_BOOT_CPU_ID +------------------------ -Capability: KVM_CAP_SET_BOOT_CPU_ID -Architectures: x86 -Type: vm ioctl -Parameters: unsigned long vcpu_id -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_SET_BOOT_CPU_ID +:Architectures: x86 +:Type: vm ioctl +:Parameters: unsigned long vcpu_id +:Returns: 0 on success, -1 on error Define which vcpu is the Bootstrap Processor (BSP). Values are the same as the vcpu id in KVM_CREATE_VCPU. If this ioctl is not called, the default @@ -1335,102 +1465,119 @@ is vcpu 0. 4.42 KVM_GET_XSAVE +------------------ -Capability: KVM_CAP_XSAVE -Architectures: x86 -Type: vcpu ioctl -Parameters: struct kvm_xsave (out) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_XSAVE +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_xsave (out) +:Returns: 0 on success, -1 on error -struct kvm_xsave { + +:: + + struct kvm_xsave { __u32 region[1024]; -}; + }; This ioctl would copy current vcpu's xsave struct to the userspace. 4.43 KVM_SET_XSAVE +------------------ + +:Capability: KVM_CAP_XSAVE +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_xsave (in) +:Returns: 0 on success, -1 on error -Capability: KVM_CAP_XSAVE -Architectures: x86 -Type: vcpu ioctl -Parameters: struct kvm_xsave (in) -Returns: 0 on success, -1 on error +:: -struct kvm_xsave { + + struct kvm_xsave { __u32 region[1024]; -}; + }; This ioctl would copy userspace's xsave struct to the kernel. 4.44 KVM_GET_XCRS +----------------- + +:Capability: KVM_CAP_XCRS +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_xcrs (out) +:Returns: 0 on success, -1 on error -Capability: KVM_CAP_XCRS -Architectures: x86 -Type: vcpu ioctl -Parameters: struct kvm_xcrs (out) -Returns: 0 on success, -1 on error +:: -struct kvm_xcr { + struct kvm_xcr { __u32 xcr; __u32 reserved; __u64 value; -}; + }; -struct kvm_xcrs { + struct kvm_xcrs { __u32 nr_xcrs; __u32 flags; struct kvm_xcr xcrs[KVM_MAX_XCRS]; __u64 padding[16]; -}; + }; This ioctl would copy current vcpu's xcrs to the userspace. 4.45 KVM_SET_XCRS +----------------- + +:Capability: KVM_CAP_XCRS +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_xcrs (in) +:Returns: 0 on success, -1 on error -Capability: KVM_CAP_XCRS -Architectures: x86 -Type: vcpu ioctl -Parameters: struct kvm_xcrs (in) -Returns: 0 on success, -1 on error +:: -struct kvm_xcr { + struct kvm_xcr { __u32 xcr; __u32 reserved; __u64 value; -}; + }; -struct kvm_xcrs { + struct kvm_xcrs { __u32 nr_xcrs; __u32 flags; struct kvm_xcr xcrs[KVM_MAX_XCRS]; __u64 padding[16]; -}; + }; This ioctl would set vcpu's xcr to the value userspace specified. 4.46 KVM_GET_SUPPORTED_CPUID +---------------------------- -Capability: KVM_CAP_EXT_CPUID -Architectures: x86 -Type: system ioctl -Parameters: struct kvm_cpuid2 (in/out) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_EXT_CPUID +:Architectures: x86 +:Type: system ioctl +:Parameters: struct kvm_cpuid2 (in/out) +:Returns: 0 on success, -1 on error -struct kvm_cpuid2 { +:: + + struct kvm_cpuid2 { __u32 nent; __u32 padding; struct kvm_cpuid_entry2 entries[0]; -}; + }; -#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0) -#define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1) -#define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2) + #define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0) + #define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1) + #define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2) -struct kvm_cpuid_entry2 { + struct kvm_cpuid_entry2 { __u32 function; __u32 index; __u32 flags; @@ -1439,7 +1586,7 @@ struct kvm_cpuid_entry2 { __u32 ecx; __u32 edx; __u32 padding[3]; -}; + }; This ioctl returns x86 cpuid features which are supported by both the hardware and kvm in its default configuration. Userspace can use the @@ -1467,10 +1614,16 @@ with unknown or unsupported features masked out. Some features (for example, x2apic), may not be present in the host cpu, but are exposed by kvm if it can emulate them efficiently. The fields in each entry are defined as follows: - function: the eax value used to obtain the entry - index: the ecx value used to obtain the entry (for entries that are + function: + the eax value used to obtain the entry + + index: + the ecx value used to obtain the entry (for entries that are affected by ecx) - flags: an OR of zero or more of the following: + + flags: + an OR of zero or more of the following: + KVM_CPUID_FLAG_SIGNIFCANT_INDEX: if the index field is valid KVM_CPUID_FLAG_STATEFUL_FUNC: @@ -1480,12 +1633,14 @@ emulate them efficiently. The fields in each entry are defined as follows: KVM_CPUID_FLAG_STATE_READ_NEXT: for KVM_CPUID_FLAG_STATEFUL_FUNC entries, set if this entry is the first entry to be read by a cpu - eax, ebx, ecx, edx: the values returned by the cpuid instruction for + + eax, ebx, ecx, edx: + the values returned by the cpuid instruction for this function/index combination The TSC deadline timer feature (CPUID leaf 1, ecx[24]) is always returned as false, since the feature depends on KVM_CREATE_IRQCHIP for local APIC -support. Instead it is reported via +support. Instead it is reported via:: ioctl(KVM_CHECK_EXTENSION, KVM_CAP_TSC_DEADLINE_TIMER) @@ -1494,18 +1649,21 @@ feature in userspace, then you can enable the feature for KVM_SET_CPUID2. 4.47 KVM_PPC_GET_PVINFO +----------------------- -Capability: KVM_CAP_PPC_GET_PVINFO -Architectures: ppc -Type: vm ioctl -Parameters: struct kvm_ppc_pvinfo (out) -Returns: 0 on success, !0 on error +:Capability: KVM_CAP_PPC_GET_PVINFO +:Architectures: ppc +:Type: vm ioctl +:Parameters: struct kvm_ppc_pvinfo (out) +:Returns: 0 on success, !0 on error -struct kvm_ppc_pvinfo { +:: + + struct kvm_ppc_pvinfo { __u32 flags; __u32 hcall[4]; __u8 pad[108]; -}; + }; This ioctl fetches PV specific information that need to be passed to the guest using the device tree or other means from vm context. @@ -1515,33 +1673,39 @@ The hcall array defines 4 instructions that make up a hypercall. If any additional field gets added to this structure later on, a bit for that additional piece of information will be set in the flags bitmap. -The flags bitmap is defined as: +The flags bitmap is defined as:: /* the host supports the ePAPR idle hcall #define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0) 4.52 KVM_SET_GSI_ROUTING +------------------------ -Capability: KVM_CAP_IRQ_ROUTING -Architectures: x86 s390 arm arm64 -Type: vm ioctl -Parameters: struct kvm_irq_routing (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_IRQ_ROUTING +:Architectures: x86 s390 arm arm64 +:Type: vm ioctl +:Parameters: struct kvm_irq_routing (in) +:Returns: 0 on success, -1 on error Sets the GSI routing table entries, overwriting any previously set entries. On arm/arm64, GSI routing has the following limitation: + - GSI routing does not apply to KVM_IRQ_LINE but only to KVM_IRQFD. -struct kvm_irq_routing { +:: + + struct kvm_irq_routing { __u32 nr; __u32 flags; struct kvm_irq_routing_entry entries[0]; -}; + }; No flags are specified so far, the corresponding field must be set to zero. -struct kvm_irq_routing_entry { +:: + + struct kvm_irq_routing_entry { __u32 gsi; __u32 type; __u32 flags; @@ -1553,15 +1717,16 @@ struct kvm_irq_routing_entry { struct kvm_irq_routing_hv_sint hv_sint; __u32 pad[8]; } u; -}; + }; -/* gsi routing entry types */ -#define KVM_IRQ_ROUTING_IRQCHIP 1 -#define KVM_IRQ_ROUTING_MSI 2 -#define KVM_IRQ_ROUTING_S390_ADAPTER 3 -#define KVM_IRQ_ROUTING_HV_SINT 4 + /* gsi routing entry types */ + #define KVM_IRQ_ROUTING_IRQCHIP 1 + #define KVM_IRQ_ROUTING_MSI 2 + #define KVM_IRQ_ROUTING_S390_ADAPTER 3 + #define KVM_IRQ_ROUTING_HV_SINT 4 flags: + - KVM_MSI_VALID_DEVID: used along with KVM_IRQ_ROUTING_MSI routing entry type, specifies that the devid field contains a valid value. The per-VM KVM_CAP_MSI_DEVID capability advertises the requirement to provide @@ -1569,12 +1734,14 @@ flags: never set the KVM_MSI_VALID_DEVID flag as the ioctl might fail. - zero otherwise -struct kvm_irq_routing_irqchip { +:: + + struct kvm_irq_routing_irqchip { __u32 irqchip; __u32 pin; -}; + }; -struct kvm_irq_routing_msi { + struct kvm_irq_routing_msi { __u32 address_lo; __u32 address_hi; __u32 data; @@ -1582,7 +1749,7 @@ struct kvm_irq_routing_msi { __u32 pad; __u32 devid; }; -}; + }; If KVM_MSI_VALID_DEVID is set, devid contains a unique device identifier for the device that wrote the MSI message. For PCI, this is usually a @@ -1593,39 +1760,43 @@ feature of KVM_CAP_X2APIC_API capability is enabled. If it is enabled, address_hi bits 31-8 provide bits 31-8 of the destination id. Bits 7-0 of address_hi must be zero. -struct kvm_irq_routing_s390_adapter { +:: + + struct kvm_irq_routing_s390_adapter { __u64 ind_addr; __u64 summary_addr; __u64 ind_offset; __u32 summary_offset; __u32 adapter_id; -}; + }; -struct kvm_irq_routing_hv_sint { + struct kvm_irq_routing_hv_sint { __u32 vcpu; __u32 sint; -}; + }; 4.55 KVM_SET_TSC_KHZ +-------------------- -Capability: KVM_CAP_TSC_CONTROL -Architectures: x86 -Type: vcpu ioctl -Parameters: virtual tsc_khz -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_TSC_CONTROL +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: virtual tsc_khz +:Returns: 0 on success, -1 on error Specifies the tsc frequency for the virtual machine. The unit of the frequency is KHz. 4.56 KVM_GET_TSC_KHZ +-------------------- -Capability: KVM_CAP_GET_TSC_KHZ -Architectures: x86 -Type: vcpu ioctl -Parameters: none -Returns: virtual tsc-khz on success, negative value on error +:Capability: KVM_CAP_GET_TSC_KHZ +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: none +:Returns: virtual tsc-khz on success, negative value on error Returns the tsc frequency of the guest. The unit of the return value is KHz. If the host has unstable tsc this ioctl returns -EIO instead as an @@ -1633,17 +1804,20 @@ error. 4.57 KVM_GET_LAPIC +------------------ -Capability: KVM_CAP_IRQCHIP -Architectures: x86 -Type: vcpu ioctl -Parameters: struct kvm_lapic_state (out) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_IRQCHIP +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_lapic_state (out) +:Returns: 0 on success, -1 on error -#define KVM_APIC_REG_SIZE 0x400 -struct kvm_lapic_state { +:: + + #define KVM_APIC_REG_SIZE 0x400 + struct kvm_lapic_state { char regs[KVM_APIC_REG_SIZE]; -}; + }; Reads the Local APIC registers and copies them into the input argument. The data format and layout are the same as documented in the architecture manual. @@ -1661,17 +1835,20 @@ always uses xAPIC format. 4.58 KVM_SET_LAPIC +------------------ -Capability: KVM_CAP_IRQCHIP -Architectures: x86 -Type: vcpu ioctl -Parameters: struct kvm_lapic_state (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_IRQCHIP +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_lapic_state (in) +:Returns: 0 on success, -1 on error -#define KVM_APIC_REG_SIZE 0x400 -struct kvm_lapic_state { +:: + + #define KVM_APIC_REG_SIZE 0x400 + struct kvm_lapic_state { char regs[KVM_APIC_REG_SIZE]; -}; + }; Copies the input argument into the Local APIC registers. The data format and layout are the same as documented in the architecture manual. @@ -1682,35 +1859,38 @@ See the note in KVM_GET_LAPIC. 4.59 KVM_IOEVENTFD +------------------ -Capability: KVM_CAP_IOEVENTFD -Architectures: all -Type: vm ioctl -Parameters: struct kvm_ioeventfd (in) -Returns: 0 on success, !0 on error +:Capability: KVM_CAP_IOEVENTFD +:Architectures: all +:Type: vm ioctl +:Parameters: struct kvm_ioeventfd (in) +:Returns: 0 on success, !0 on error This ioctl attaches or detaches an ioeventfd to a legal pio/mmio address within the guest. A guest write in the registered address will signal the provided event instead of triggering an exit. -struct kvm_ioeventfd { +:: + + struct kvm_ioeventfd { __u64 datamatch; __u64 addr; /* legal pio/mmio address */ __u32 len; /* 0, 1, 2, 4, or 8 bytes */ __s32 fd; __u32 flags; __u8 pad[36]; -}; + }; For the special case of virtio-ccw devices on s390, the ioevent is matched to a subchannel/virtqueue tuple instead. -The following flags are defined: +The following flags are defined:: -#define KVM_IOEVENTFD_FLAG_DATAMATCH (1 << kvm_ioeventfd_flag_nr_datamatch) -#define KVM_IOEVENTFD_FLAG_PIO (1 << kvm_ioeventfd_flag_nr_pio) -#define KVM_IOEVENTFD_FLAG_DEASSIGN (1 << kvm_ioeventfd_flag_nr_deassign) -#define KVM_IOEVENTFD_FLAG_VIRTIO_CCW_NOTIFY \ + #define KVM_IOEVENTFD_FLAG_DATAMATCH (1 << kvm_ioeventfd_flag_nr_datamatch) + #define KVM_IOEVENTFD_FLAG_PIO (1 << kvm_ioeventfd_flag_nr_pio) + #define KVM_IOEVENTFD_FLAG_DEASSIGN (1 << kvm_ioeventfd_flag_nr_deassign) + #define KVM_IOEVENTFD_FLAG_VIRTIO_CCW_NOTIFY \ (1 << kvm_ioeventfd_flag_nr_virtio_ccw_notify) If datamatch flag is set, the event will be signaled only if the written value @@ -1725,17 +1905,20 @@ The speedup may only apply to specific architectures, but the ioeventfd will work anyway. 4.60 KVM_DIRTY_TLB +------------------ + +:Capability: KVM_CAP_SW_TLB +:Architectures: ppc +:Type: vcpu ioctl +:Parameters: struct kvm_dirty_tlb (in) +:Returns: 0 on success, -1 on error -Capability: KVM_CAP_SW_TLB -Architectures: ppc -Type: vcpu ioctl -Parameters: struct kvm_dirty_tlb (in) -Returns: 0 on success, -1 on error +:: -struct kvm_dirty_tlb { + struct kvm_dirty_tlb { __u64 bitmap; __u32 num_dirty; -}; + }; This must be called whenever userspace has changed an entry in the shared TLB, prior to calling KVM_RUN on the associated vcpu. @@ -1758,23 +1941,26 @@ be set to the number of set bits in the bitmap. 4.62 KVM_CREATE_SPAPR_TCE +------------------------- -Capability: KVM_CAP_SPAPR_TCE -Architectures: powerpc -Type: vm ioctl -Parameters: struct kvm_create_spapr_tce (in) -Returns: file descriptor for manipulating the created TCE table +:Capability: KVM_CAP_SPAPR_TCE +:Architectures: powerpc +:Type: vm ioctl +:Parameters: struct kvm_create_spapr_tce (in) +:Returns: file descriptor for manipulating the created TCE table This creates a virtual TCE (translation control entry) table, which is an IOMMU for PAPR-style virtual I/O. It is used to translate logical addresses used in virtual I/O into guest physical addresses, and provides a scatter/gather capability for PAPR virtual I/O. -/* for KVM_CAP_SPAPR_TCE */ -struct kvm_create_spapr_tce { +:: + + /* for KVM_CAP_SPAPR_TCE */ + struct kvm_create_spapr_tce { __u64 liobn; __u32 window_size; -}; + }; The liobn field gives the logical IO bus number for which to create a TCE table. The window_size field specifies the size of the DMA window @@ -1794,12 +1980,13 @@ circumstances. 4.63 KVM_ALLOCATE_RMA +--------------------- -Capability: KVM_CAP_PPC_RMA -Architectures: powerpc -Type: vm ioctl -Parameters: struct kvm_allocate_rma (out) -Returns: file descriptor for mapping the allocated RMA +:Capability: KVM_CAP_PPC_RMA +:Architectures: powerpc +:Type: vm ioctl +:Parameters: struct kvm_allocate_rma (out) +:Returns: file descriptor for mapping the allocated RMA This allocates a Real Mode Area (RMA) from the pool allocated at boot time by the kernel. An RMA is a physically-contiguous, aligned region @@ -1808,10 +1995,12 @@ will be accessed by real-mode (MMU off) accesses in a KVM guest. POWER processors support a set of sizes for the RMA that usually includes 64MB, 128MB, 256MB and some larger powers of two. -/* for KVM_ALLOCATE_RMA */ -struct kvm_allocate_rma { +:: + + /* for KVM_ALLOCATE_RMA */ + struct kvm_allocate_rma { __u64 rma_size; -}; + }; The return value is a file descriptor which can be passed to mmap(2) to map the allocated RMA into userspace. The mapped area can then be @@ -1827,12 +2016,13 @@ because it supports the Virtual RMA (VRMA) facility. 4.64 KVM_NMI +------------ -Capability: KVM_CAP_USER_NMI -Architectures: x86 -Type: vcpu ioctl -Parameters: none -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_USER_NMI +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: none +:Returns: 0 on success, -1 on error Queues an NMI on the thread's vcpu. Note this is well defined only when KVM_CREATE_IRQCHIP has not been called, since this is an interface @@ -1853,14 +2043,16 @@ debugging. 4.65 KVM_S390_UCAS_MAP +---------------------- -Capability: KVM_CAP_S390_UCONTROL -Architectures: s390 -Type: vcpu ioctl -Parameters: struct kvm_s390_ucas_mapping (in) -Returns: 0 in case of success +:Capability: KVM_CAP_S390_UCONTROL +:Architectures: s390 +:Type: vcpu ioctl +:Parameters: struct kvm_s390_ucas_mapping (in) +:Returns: 0 in case of success + +The parameter is defined like this:: -The parameter is defined like this: struct kvm_s390_ucas_mapping { __u64 user_addr; __u64 vcpu_addr; @@ -1873,14 +2065,16 @@ be aligned by 1 megabyte. 4.66 KVM_S390_UCAS_UNMAP +------------------------ -Capability: KVM_CAP_S390_UCONTROL -Architectures: s390 -Type: vcpu ioctl -Parameters: struct kvm_s390_ucas_mapping (in) -Returns: 0 in case of success +:Capability: KVM_CAP_S390_UCONTROL +:Architectures: s390 +:Type: vcpu ioctl +:Parameters: struct kvm_s390_ucas_mapping (in) +:Returns: 0 in case of success + +The parameter is defined like this:: -The parameter is defined like this: struct kvm_s390_ucas_mapping { __u64 user_addr; __u64 vcpu_addr; @@ -1893,12 +2087,13 @@ All parameters need to be aligned by 1 megabyte. 4.67 KVM_S390_VCPU_FAULT +------------------------ -Capability: KVM_CAP_S390_UCONTROL -Architectures: s390 -Type: vcpu ioctl -Parameters: vcpu absolute address (in) -Returns: 0 in case of success +:Capability: KVM_CAP_S390_UCONTROL +:Architectures: s390 +:Type: vcpu ioctl +:Parameters: vcpu absolute address (in) +:Returns: 0 in case of success This call creates a page table entry on the virtual cpu's address space (for user controlled virtual machines) or the virtual machine's address @@ -1910,23 +2105,31 @@ prior to calling the KVM_RUN ioctl. 4.68 KVM_SET_ONE_REG +-------------------- + +:Capability: KVM_CAP_ONE_REG +:Architectures: all +:Type: vcpu ioctl +:Parameters: struct kvm_one_reg (in) +:Returns: 0 on success, negative value on failure -Capability: KVM_CAP_ONE_REG -Architectures: all -Type: vcpu ioctl -Parameters: struct kvm_one_reg (in) -Returns: 0 on success, negative value on failure Errors: -  ENOENT:   no such register -  EINVAL:   invalid register ID, or no such register -  EPERM:    (arm64) register access not allowed before vcpu finalization + + ====== ============================================================ +  ENOENT   no such register +  EINVAL   invalid register ID, or no such register +  EPERM    (arm64) register access not allowed before vcpu finalization + ====== ============================================================ + (These error codes are indicative only: do not rely on a specific error code being returned in a specific situation.) -struct kvm_one_reg { +:: + + struct kvm_one_reg { __u64 id; __u64 addr; -}; + }; Using this ioctl, a single vcpu register can be set to a specific value defined by user space with the passed in struct kvm_one_reg, where id @@ -1936,217 +2139,226 @@ and architecture specific registers. Each have their own range of operation and their own constants and width. To keep track of the implemented registers, find a list below: - Arch | Register | Width (bits) - | | - PPC | KVM_REG_PPC_HIOR | 64 - PPC | KVM_REG_PPC_IAC1 | 64 - PPC | KVM_REG_PPC_IAC2 | 64 - PPC | KVM_REG_PPC_IAC3 | 64 - PPC | KVM_REG_PPC_IAC4 | 64 - PPC | KVM_REG_PPC_DAC1 | 64 - PPC | KVM_REG_PPC_DAC2 | 64 - PPC | KVM_REG_PPC_DABR | 64 - PPC | KVM_REG_PPC_DSCR | 64 - PPC | KVM_REG_PPC_PURR | 64 - PPC | KVM_REG_PPC_SPURR | 64 - PPC | KVM_REG_PPC_DAR | 64 - PPC | KVM_REG_PPC_DSISR | 32 - PPC | KVM_REG_PPC_AMR | 64 - PPC | KVM_REG_PPC_UAMOR | 64 - PPC | KVM_REG_PPC_MMCR0 | 64 - PPC | KVM_REG_PPC_MMCR1 | 64 - PPC | KVM_REG_PPC_MMCRA | 64 - PPC | KVM_REG_PPC_MMCR2 | 64 - PPC | KVM_REG_PPC_MMCRS | 64 - PPC | KVM_REG_PPC_SIAR | 64 - PPC | KVM_REG_PPC_SDAR | 64 - PPC | KVM_REG_PPC_SIER | 64 - PPC | KVM_REG_PPC_PMC1 | 32 - PPC | KVM_REG_PPC_PMC2 | 32 - PPC | KVM_REG_PPC_PMC3 | 32 - PPC | KVM_REG_PPC_PMC4 | 32 - PPC | KVM_REG_PPC_PMC5 | 32 - PPC | KVM_REG_PPC_PMC6 | 32 - PPC | KVM_REG_PPC_PMC7 | 32 - PPC | KVM_REG_PPC_PMC8 | 32 - PPC | KVM_REG_PPC_FPR0 | 64 - ... - PPC | KVM_REG_PPC_FPR31 | 64 - PPC | KVM_REG_PPC_VR0 | 128 - ... - PPC | KVM_REG_PPC_VR31 | 128 - PPC | KVM_REG_PPC_VSR0 | 128 - ... - PPC | KVM_REG_PPC_VSR31 | 128 - PPC | KVM_REG_PPC_FPSCR | 64 - PPC | KVM_REG_PPC_VSCR | 32 - PPC | KVM_REG_PPC_VPA_ADDR | 64 - PPC | KVM_REG_PPC_VPA_SLB | 128 - PPC | KVM_REG_PPC_VPA_DTL | 128 - PPC | KVM_REG_PPC_EPCR | 32 - PPC | KVM_REG_PPC_EPR | 32 - PPC | KVM_REG_PPC_TCR | 32 - PPC | KVM_REG_PPC_TSR | 32 - PPC | KVM_REG_PPC_OR_TSR | 32 - PPC | KVM_REG_PPC_CLEAR_TSR | 32 - PPC | KVM_REG_PPC_MAS0 | 32 - PPC | KVM_REG_PPC_MAS1 | 32 - PPC | KVM_REG_PPC_MAS2 | 64 - PPC | KVM_REG_PPC_MAS7_3 | 64 - PPC | KVM_REG_PPC_MAS4 | 32 - PPC | KVM_REG_PPC_MAS6 | 32 - PPC | KVM_REG_PPC_MMUCFG | 32 - PPC | KVM_REG_PPC_TLB0CFG | 32 - PPC | KVM_REG_PPC_TLB1CFG | 32 - PPC | KVM_REG_PPC_TLB2CFG | 32 - PPC | KVM_REG_PPC_TLB3CFG | 32 - PPC | KVM_REG_PPC_TLB0PS | 32 - PPC | KVM_REG_PPC_TLB1PS | 32 - PPC | KVM_REG_PPC_TLB2PS | 32 - PPC | KVM_REG_PPC_TLB3PS | 32 - PPC | KVM_REG_PPC_EPTCFG | 32 - PPC | KVM_REG_PPC_ICP_STATE | 64 - PPC | KVM_REG_PPC_VP_STATE | 128 - PPC | KVM_REG_PPC_TB_OFFSET | 64 - PPC | KVM_REG_PPC_SPMC1 | 32 - PPC | KVM_REG_PPC_SPMC2 | 32 - PPC | KVM_REG_PPC_IAMR | 64 - PPC | KVM_REG_PPC_TFHAR | 64 - PPC | KVM_REG_PPC_TFIAR | 64 - PPC | KVM_REG_PPC_TEXASR | 64 - PPC | KVM_REG_PPC_FSCR | 64 - PPC | KVM_REG_PPC_PSPB | 32 - PPC | KVM_REG_PPC_EBBHR | 64 - PPC | KVM_REG_PPC_EBBRR | 64 - PPC | KVM_REG_PPC_BESCR | 64 - PPC | KVM_REG_PPC_TAR | 64 - PPC | KVM_REG_PPC_DPDES | 64 - PPC | KVM_REG_PPC_DAWR | 64 - PPC | KVM_REG_PPC_DAWRX | 64 - PPC | KVM_REG_PPC_CIABR | 64 - PPC | KVM_REG_PPC_IC | 64 - PPC | KVM_REG_PPC_VTB | 64 - PPC | KVM_REG_PPC_CSIGR | 64 - PPC | KVM_REG_PPC_TACR | 64 - PPC | KVM_REG_PPC_TCSCR | 64 - PPC | KVM_REG_PPC_PID | 64 - PPC | KVM_REG_PPC_ACOP | 64 - PPC | KVM_REG_PPC_VRSAVE | 32 - PPC | KVM_REG_PPC_LPCR | 32 - PPC | KVM_REG_PPC_LPCR_64 | 64 - PPC | KVM_REG_PPC_PPR | 64 - PPC | KVM_REG_PPC_ARCH_COMPAT | 32 - PPC | KVM_REG_PPC_DABRX | 32 - PPC | KVM_REG_PPC_WORT | 64 - PPC | KVM_REG_PPC_SPRG9 | 64 - PPC | KVM_REG_PPC_DBSR | 32 - PPC | KVM_REG_PPC_TIDR | 64 - PPC | KVM_REG_PPC_PSSCR | 64 - PPC | KVM_REG_PPC_DEC_EXPIRY | 64 - PPC | KVM_REG_PPC_PTCR | 64 - PPC | KVM_REG_PPC_TM_GPR0 | 64 - ... - PPC | KVM_REG_PPC_TM_GPR31 | 64 - PPC | KVM_REG_PPC_TM_VSR0 | 128 - ... - PPC | KVM_REG_PPC_TM_VSR63 | 128 - PPC | KVM_REG_PPC_TM_CR | 64 - PPC | KVM_REG_PPC_TM_LR | 64 - PPC | KVM_REG_PPC_TM_CTR | 64 - PPC | KVM_REG_PPC_TM_FPSCR | 64 - PPC | KVM_REG_PPC_TM_AMR | 64 - PPC | KVM_REG_PPC_TM_PPR | 64 - PPC | KVM_REG_PPC_TM_VRSAVE | 64 - PPC | KVM_REG_PPC_TM_VSCR | 32 - PPC | KVM_REG_PPC_TM_DSCR | 64 - PPC | KVM_REG_PPC_TM_TAR | 64 - PPC | KVM_REG_PPC_TM_XER | 64 - | | - MIPS | KVM_REG_MIPS_R0 | 64 - ... - MIPS | KVM_REG_MIPS_R31 | 64 - MIPS | KVM_REG_MIPS_HI | 64 - MIPS | KVM_REG_MIPS_LO | 64 - MIPS | KVM_REG_MIPS_PC | 64 - MIPS | KVM_REG_MIPS_CP0_INDEX | 32 - MIPS | KVM_REG_MIPS_CP0_ENTRYLO0 | 64 - MIPS | KVM_REG_MIPS_CP0_ENTRYLO1 | 64 - MIPS | KVM_REG_MIPS_CP0_CONTEXT | 64 - MIPS | KVM_REG_MIPS_CP0_CONTEXTCONFIG| 32 - MIPS | KVM_REG_MIPS_CP0_USERLOCAL | 64 - MIPS | KVM_REG_MIPS_CP0_XCONTEXTCONFIG| 64 - MIPS | KVM_REG_MIPS_CP0_PAGEMASK | 32 - MIPS | KVM_REG_MIPS_CP0_PAGEGRAIN | 32 - MIPS | KVM_REG_MIPS_CP0_SEGCTL0 | 64 - MIPS | KVM_REG_MIPS_CP0_SEGCTL1 | 64 - MIPS | KVM_REG_MIPS_CP0_SEGCTL2 | 64 - MIPS | KVM_REG_MIPS_CP0_PWBASE | 64 - MIPS | KVM_REG_MIPS_CP0_PWFIELD | 64 - MIPS | KVM_REG_MIPS_CP0_PWSIZE | 64 - MIPS | KVM_REG_MIPS_CP0_WIRED | 32 - MIPS | KVM_REG_MIPS_CP0_PWCTL | 32 - MIPS | KVM_REG_MIPS_CP0_HWRENA | 32 - MIPS | KVM_REG_MIPS_CP0_BADVADDR | 64 - MIPS | KVM_REG_MIPS_CP0_BADINSTR | 32 - MIPS | KVM_REG_MIPS_CP0_BADINSTRP | 32 - MIPS | KVM_REG_MIPS_CP0_COUNT | 32 - MIPS | KVM_REG_MIPS_CP0_ENTRYHI | 64 - MIPS | KVM_REG_MIPS_CP0_COMPARE | 32 - MIPS | KVM_REG_MIPS_CP0_STATUS | 32 - MIPS | KVM_REG_MIPS_CP0_INTCTL | 32 - MIPS | KVM_REG_MIPS_CP0_CAUSE | 32 - MIPS | KVM_REG_MIPS_CP0_EPC | 64 - MIPS | KVM_REG_MIPS_CP0_PRID | 32 - MIPS | KVM_REG_MIPS_CP0_EBASE | 64 - MIPS | KVM_REG_MIPS_CP0_CONFIG | 32 - MIPS | KVM_REG_MIPS_CP0_CONFIG1 | 32 - MIPS | KVM_REG_MIPS_CP0_CONFIG2 | 32 - MIPS | KVM_REG_MIPS_CP0_CONFIG3 | 32 - MIPS | KVM_REG_MIPS_CP0_CONFIG4 | 32 - MIPS | KVM_REG_MIPS_CP0_CONFIG5 | 32 - MIPS | KVM_REG_MIPS_CP0_CONFIG7 | 32 - MIPS | KVM_REG_MIPS_CP0_XCONTEXT | 64 - MIPS | KVM_REG_MIPS_CP0_ERROREPC | 64 - MIPS | KVM_REG_MIPS_CP0_KSCRATCH1 | 64 - MIPS | KVM_REG_MIPS_CP0_KSCRATCH2 | 64 - MIPS | KVM_REG_MIPS_CP0_KSCRATCH3 | 64 - MIPS | KVM_REG_MIPS_CP0_KSCRATCH4 | 64 - MIPS | KVM_REG_MIPS_CP0_KSCRATCH5 | 64 - MIPS | KVM_REG_MIPS_CP0_KSCRATCH6 | 64 - MIPS | KVM_REG_MIPS_CP0_MAAR(0..63) | 64 - MIPS | KVM_REG_MIPS_COUNT_CTL | 64 - MIPS | KVM_REG_MIPS_COUNT_RESUME | 64 - MIPS | KVM_REG_MIPS_COUNT_HZ | 64 - MIPS | KVM_REG_MIPS_FPR_32(0..31) | 32 - MIPS | KVM_REG_MIPS_FPR_64(0..31) | 64 - MIPS | KVM_REG_MIPS_VEC_128(0..31) | 128 - MIPS | KVM_REG_MIPS_FCR_IR | 32 - MIPS | KVM_REG_MIPS_FCR_CSR | 32 - MIPS | KVM_REG_MIPS_MSA_IR | 32 - MIPS | KVM_REG_MIPS_MSA_CSR | 32 + ======= =============================== ============ + Arch Register Width (bits) + ======= =============================== ============ + PPC KVM_REG_PPC_HIOR 64 + PPC KVM_REG_PPC_IAC1 64 + PPC KVM_REG_PPC_IAC2 64 + PPC KVM_REG_PPC_IAC3 64 + PPC KVM_REG_PPC_IAC4 64 + PPC KVM_REG_PPC_DAC1 64 + PPC KVM_REG_PPC_DAC2 64 + PPC KVM_REG_PPC_DABR 64 + PPC KVM_REG_PPC_DSCR 64 + PPC KVM_REG_PPC_PURR 64 + PPC KVM_REG_PPC_SPURR 64 + PPC KVM_REG_PPC_DAR 64 + PPC KVM_REG_PPC_DSISR 32 + PPC KVM_REG_PPC_AMR 64 + PPC KVM_REG_PPC_UAMOR 64 + PPC KVM_REG_PPC_MMCR0 64 + PPC KVM_REG_PPC_MMCR1 64 + PPC KVM_REG_PPC_MMCRA 64 + PPC KVM_REG_PPC_MMCR2 64 + PPC KVM_REG_PPC_MMCRS 64 + PPC KVM_REG_PPC_SIAR 64 + PPC KVM_REG_PPC_SDAR 64 + PPC KVM_REG_PPC_SIER 64 + PPC KVM_REG_PPC_PMC1 32 + PPC KVM_REG_PPC_PMC2 32 + PPC KVM_REG_PPC_PMC3 32 + PPC KVM_REG_PPC_PMC4 32 + PPC KVM_REG_PPC_PMC5 32 + PPC KVM_REG_PPC_PMC6 32 + PPC KVM_REG_PPC_PMC7 32 + PPC KVM_REG_PPC_PMC8 32 + PPC KVM_REG_PPC_FPR0 64 + ... + PPC KVM_REG_PPC_FPR31 64 + PPC KVM_REG_PPC_VR0 128 + ... + PPC KVM_REG_PPC_VR31 128 + PPC KVM_REG_PPC_VSR0 128 + ... + PPC KVM_REG_PPC_VSR31 128 + PPC KVM_REG_PPC_FPSCR 64 + PPC KVM_REG_PPC_VSCR 32 + PPC KVM_REG_PPC_VPA_ADDR 64 + PPC KVM_REG_PPC_VPA_SLB 128 + PPC KVM_REG_PPC_VPA_DTL 128 + PPC KVM_REG_PPC_EPCR 32 + PPC KVM_REG_PPC_EPR 32 + PPC KVM_REG_PPC_TCR 32 + PPC KVM_REG_PPC_TSR 32 + PPC KVM_REG_PPC_OR_TSR 32 + PPC KVM_REG_PPC_CLEAR_TSR 32 + PPC KVM_REG_PPC_MAS0 32 + PPC KVM_REG_PPC_MAS1 32 + PPC KVM_REG_PPC_MAS2 64 + PPC KVM_REG_PPC_MAS7_3 64 + PPC KVM_REG_PPC_MAS4 32 + PPC KVM_REG_PPC_MAS6 32 + PPC KVM_REG_PPC_MMUCFG 32 + PPC KVM_REG_PPC_TLB0CFG 32 + PPC KVM_REG_PPC_TLB1CFG 32 + PPC KVM_REG_PPC_TLB2CFG 32 + PPC KVM_REG_PPC_TLB3CFG 32 + PPC KVM_REG_PPC_TLB0PS 32 + PPC KVM_REG_PPC_TLB1PS 32 + PPC KVM_REG_PPC_TLB2PS 32 + PPC KVM_REG_PPC_TLB3PS 32 + PPC KVM_REG_PPC_EPTCFG 32 + PPC KVM_REG_PPC_ICP_STATE 64 + PPC KVM_REG_PPC_VP_STATE 128 + PPC KVM_REG_PPC_TB_OFFSET 64 + PPC KVM_REG_PPC_SPMC1 32 + PPC KVM_REG_PPC_SPMC2 32 + PPC KVM_REG_PPC_IAMR 64 + PPC KVM_REG_PPC_TFHAR 64 + PPC KVM_REG_PPC_TFIAR 64 + PPC KVM_REG_PPC_TEXASR 64 + PPC KVM_REG_PPC_FSCR 64 + PPC KVM_REG_PPC_PSPB 32 + PPC KVM_REG_PPC_EBBHR 64 + PPC KVM_REG_PPC_EBBRR 64 + PPC KVM_REG_PPC_BESCR 64 + PPC KVM_REG_PPC_TAR 64 + PPC KVM_REG_PPC_DPDES 64 + PPC KVM_REG_PPC_DAWR 64 + PPC KVM_REG_PPC_DAWRX 64 + PPC KVM_REG_PPC_CIABR 64 + PPC KVM_REG_PPC_IC 64 + PPC KVM_REG_PPC_VTB 64 + PPC KVM_REG_PPC_CSIGR 64 + PPC KVM_REG_PPC_TACR 64 + PPC KVM_REG_PPC_TCSCR 64 + PPC KVM_REG_PPC_PID 64 + PPC KVM_REG_PPC_ACOP 64 + PPC KVM_REG_PPC_VRSAVE 32 + PPC KVM_REG_PPC_LPCR 32 + PPC KVM_REG_PPC_LPCR_64 64 + PPC KVM_REG_PPC_PPR 64 + PPC KVM_REG_PPC_ARCH_COMPAT 32 + PPC KVM_REG_PPC_DABRX 32 + PPC KVM_REG_PPC_WORT 64 + PPC KVM_REG_PPC_SPRG9 64 + PPC KVM_REG_PPC_DBSR 32 + PPC KVM_REG_PPC_TIDR 64 + PPC KVM_REG_PPC_PSSCR 64 + PPC KVM_REG_PPC_DEC_EXPIRY 64 + PPC KVM_REG_PPC_PTCR 64 + PPC KVM_REG_PPC_TM_GPR0 64 + ... + PPC KVM_REG_PPC_TM_GPR31 64 + PPC KVM_REG_PPC_TM_VSR0 128 + ... + PPC KVM_REG_PPC_TM_VSR63 128 + PPC KVM_REG_PPC_TM_CR 64 + PPC KVM_REG_PPC_TM_LR 64 + PPC KVM_REG_PPC_TM_CTR 64 + PPC KVM_REG_PPC_TM_FPSCR 64 + PPC KVM_REG_PPC_TM_AMR 64 + PPC KVM_REG_PPC_TM_PPR 64 + PPC KVM_REG_PPC_TM_VRSAVE 64 + PPC KVM_REG_PPC_TM_VSCR 32 + PPC KVM_REG_PPC_TM_DSCR 64 + PPC KVM_REG_PPC_TM_TAR 64 + PPC KVM_REG_PPC_TM_XER 64 + + MIPS KVM_REG_MIPS_R0 64 + ... + MIPS KVM_REG_MIPS_R31 64 + MIPS KVM_REG_MIPS_HI 64 + MIPS KVM_REG_MIPS_LO 64 + MIPS KVM_REG_MIPS_PC 64 + MIPS KVM_REG_MIPS_CP0_INDEX 32 + MIPS KVM_REG_MIPS_CP0_ENTRYLO0 64 + MIPS KVM_REG_MIPS_CP0_ENTRYLO1 64 + MIPS KVM_REG_MIPS_CP0_CONTEXT 64 + MIPS KVM_REG_MIPS_CP0_CONTEXTCONFIG 32 + MIPS KVM_REG_MIPS_CP0_USERLOCAL 64 + MIPS KVM_REG_MIPS_CP0_XCONTEXTCONFIG 64 + MIPS KVM_REG_MIPS_CP0_PAGEMASK 32 + MIPS KVM_REG_MIPS_CP0_PAGEGRAIN 32 + MIPS KVM_REG_MIPS_CP0_SEGCTL0 64 + MIPS KVM_REG_MIPS_CP0_SEGCTL1 64 + MIPS KVM_REG_MIPS_CP0_SEGCTL2 64 + MIPS KVM_REG_MIPS_CP0_PWBASE 64 + MIPS KVM_REG_MIPS_CP0_PWFIELD 64 + MIPS KVM_REG_MIPS_CP0_PWSIZE 64 + MIPS KVM_REG_MIPS_CP0_WIRED 32 + MIPS KVM_REG_MIPS_CP0_PWCTL 32 + MIPS KVM_REG_MIPS_CP0_HWRENA 32 + MIPS KVM_REG_MIPS_CP0_BADVADDR 64 + MIPS KVM_REG_MIPS_CP0_BADINSTR 32 + MIPS KVM_REG_MIPS_CP0_BADINSTRP 32 + MIPS KVM_REG_MIPS_CP0_COUNT 32 + MIPS KVM_REG_MIPS_CP0_ENTRYHI 64 + MIPS KVM_REG_MIPS_CP0_COMPARE 32 + MIPS KVM_REG_MIPS_CP0_STATUS 32 + MIPS KVM_REG_MIPS_CP0_INTCTL 32 + MIPS KVM_REG_MIPS_CP0_CAUSE 32 + MIPS KVM_REG_MIPS_CP0_EPC 64 + MIPS KVM_REG_MIPS_CP0_PRID 32 + MIPS KVM_REG_MIPS_CP0_EBASE 64 + MIPS KVM_REG_MIPS_CP0_CONFIG 32 + MIPS KVM_REG_MIPS_CP0_CONFIG1 32 + MIPS KVM_REG_MIPS_CP0_CONFIG2 32 + MIPS KVM_REG_MIPS_CP0_CONFIG3 32 + MIPS KVM_REG_MIPS_CP0_CONFIG4 32 + MIPS KVM_REG_MIPS_CP0_CONFIG5 32 + MIPS KVM_REG_MIPS_CP0_CONFIG7 32 + MIPS KVM_REG_MIPS_CP0_XCONTEXT 64 + MIPS KVM_REG_MIPS_CP0_ERROREPC 64 + MIPS KVM_REG_MIPS_CP0_KSCRATCH1 64 + MIPS KVM_REG_MIPS_CP0_KSCRATCH2 64 + MIPS KVM_REG_MIPS_CP0_KSCRATCH3 64 + MIPS KVM_REG_MIPS_CP0_KSCRATCH4 64 + MIPS KVM_REG_MIPS_CP0_KSCRATCH5 64 + MIPS KVM_REG_MIPS_CP0_KSCRATCH6 64 + MIPS KVM_REG_MIPS_CP0_MAAR(0..63) 64 + MIPS KVM_REG_MIPS_COUNT_CTL 64 + MIPS KVM_REG_MIPS_COUNT_RESUME 64 + MIPS KVM_REG_MIPS_COUNT_HZ 64 + MIPS KVM_REG_MIPS_FPR_32(0..31) 32 + MIPS KVM_REG_MIPS_FPR_64(0..31) 64 + MIPS KVM_REG_MIPS_VEC_128(0..31) 128 + MIPS KVM_REG_MIPS_FCR_IR 32 + MIPS KVM_REG_MIPS_FCR_CSR 32 + MIPS KVM_REG_MIPS_MSA_IR 32 + MIPS KVM_REG_MIPS_MSA_CSR 32 + ======= =============================== ============ ARM registers are mapped using the lower 32 bits. The upper 16 of that is the register group type, or coprocessor number: -ARM core registers have the following id bit patterns: +ARM core registers have the following id bit patterns:: + 0x4020 0000 0010 -ARM 32-bit CP15 registers have the following id bit patterns: +ARM 32-bit CP15 registers have the following id bit patterns:: + 0x4020 0000 000F -ARM 64-bit CP15 registers have the following id bit patterns: +ARM 64-bit CP15 registers have the following id bit patterns:: + 0x4030 0000 000F -ARM CCSIDR registers are demultiplexed by CSSELR value: +ARM CCSIDR registers are demultiplexed by CSSELR value:: + 0x4020 0000 0011 00 -ARM 32-bit VFP control registers have the following id bit patterns: +ARM 32-bit VFP control registers have the following id bit patterns:: + 0x4020 0000 0012 1 -ARM 64-bit FP registers have the following id bit patterns: +ARM 64-bit FP registers have the following id bit patterns:: + 0x4030 0000 0012 0 -ARM firmware pseudo-registers have the following bit pattern: +ARM firmware pseudo-registers have the following bit pattern:: + 0x4030 0000 0014 @@ -2156,15 +2368,18 @@ that is the register group type, or coprocessor number: arm64 core/FP-SIMD registers have the following id bit patterns. Note that the size of the access is variable, as the kvm_regs structure contains elements ranging from 32 to 128 bits. The index is a 32bit -value in the kvm_regs structure seen as a 32bit array. +value in the kvm_regs structure seen as a 32bit array:: + 0x60x0 0000 0010 Specifically: + +======================= ========= ===== ======================================= Encoding Register Bits kvm_regs member ----------------------------------------------------------------- +======================= ========= ===== ======================================= 0x6030 0000 0010 0000 X0 64 regs.regs[0] 0x6030 0000 0010 0002 X1 64 regs.regs[1] - ... + ... 0x6030 0000 0010 003c X30 64 regs.regs[30] 0x6030 0000 0010 003e SP 64 regs.sp 0x6030 0000 0010 0040 PC 64 regs.pc @@ -2176,27 +2391,31 @@ Specifically: 0x6030 0000 0010 004c SPSR_UND 64 spsr[KVM_SPSR_UND] 0x6030 0000 0010 004e SPSR_IRQ 64 spsr[KVM_SPSR_IRQ] 0x6060 0000 0010 0050 SPSR_FIQ 64 spsr[KVM_SPSR_FIQ] - 0x6040 0000 0010 0054 V0 128 fp_regs.vregs[0] (*) - 0x6040 0000 0010 0058 V1 128 fp_regs.vregs[1] (*) - ... - 0x6040 0000 0010 00d0 V31 128 fp_regs.vregs[31] (*) + 0x6040 0000 0010 0054 V0 128 fp_regs.vregs[0] [1]_ + 0x6040 0000 0010 0058 V1 128 fp_regs.vregs[1] [1]_ + ... + 0x6040 0000 0010 00d0 V31 128 fp_regs.vregs[31] [1]_ 0x6020 0000 0010 00d4 FPSR 32 fp_regs.fpsr 0x6020 0000 0010 00d5 FPCR 32 fp_regs.fpcr +======================= ========= ===== ======================================= + +.. [1] These encodings are not accepted for SVE-enabled vcpus. See + KVM_ARM_VCPU_INIT. -(*) These encodings are not accepted for SVE-enabled vcpus. See - KVM_ARM_VCPU_INIT. + The equivalent register content can be accessed via bits [127:0] of + the corresponding SVE Zn registers instead for vcpus that have SVE + enabled (see below). - The equivalent register content can be accessed via bits [127:0] of - the corresponding SVE Zn registers instead for vcpus that have SVE - enabled (see below). +arm64 CCSIDR registers are demultiplexed by CSSELR value:: -arm64 CCSIDR registers are demultiplexed by CSSELR value: 0x6020 0000 0011 00 -arm64 system registers have the following id bit patterns: +arm64 system registers have the following id bit patterns:: + 0x6030 0000 0013 -WARNING: +.. warning:: + Two system register IDs do not follow the specified pattern. These are KVM_REG_ARM_TIMER_CVAL and KVM_REG_ARM_TIMER_CNT, which map to system registers CNTV_CVAL_EL0 and CNTVCT_EL0 respectively. These @@ -2205,10 +2424,12 @@ WARNING: derived from the register encoding for CNTV_CVAL_EL0. As this is API, it must remain this way. -arm64 firmware pseudo-registers have the following bit pattern: +arm64 firmware pseudo-registers have the following bit pattern:: + 0x6030 0000 0014 -arm64 SVE registers have the following bit patterns: +arm64 SVE registers have the following bit patterns:: + 0x6080 0000 0015 00 Zn bits[2048*slice + 2047 : 2048*slice] 0x6050 0000 0015 04 Pn bits[256*slice + 255 : 256*slice] 0x6050 0000 0015 060 FFR bits[256*slice + 255 : 256*slice] @@ -2216,7 +2437,7 @@ arm64 SVE registers have the following bit patterns: Access to register IDs where 2048 * slice >= 128 * max_vq will fail with ENOENT. max_vq is the vcpu's maximum supported vector length in 128-bit -quadwords: see (**) below. +quadwords: see [2]_ below. These registers are only accessible on vcpus for which SVE is enabled. See KVM_ARM_VCPU_INIT for details. @@ -2231,21 +2452,21 @@ lengths supported by the vcpu to be discovered and configured by userspace. When transferred to or from user memory via KVM_GET_ONE_REG or KVM_SET_ONE_REG, the value of this register is of type __u64[KVM_ARM64_SVE_VLS_WORDS], and encodes the set of vector lengths as -follows: +follows:: -__u64 vector_lengths[KVM_ARM64_SVE_VLS_WORDS]; + __u64 vector_lengths[KVM_ARM64_SVE_VLS_WORDS]; -if (vq >= SVE_VQ_MIN && vq <= SVE_VQ_MAX && - ((vector_lengths[(vq - KVM_ARM64_SVE_VQ_MIN) / 64] >> + if (vq >= SVE_VQ_MIN && vq <= SVE_VQ_MAX && + ((vector_lengths[(vq - KVM_ARM64_SVE_VQ_MIN) / 64] >> ((vq - KVM_ARM64_SVE_VQ_MIN) % 64)) & 1)) /* Vector length vq * 16 bytes supported */ -else + else /* Vector length vq * 16 bytes not supported */ -(**) The maximum value vq for which the above condition is true is -max_vq. This is the maximum vector length available to the guest on -this vcpu, and determines which register slices are visible through -this ioctl interface. +.. [2] The maximum value vq for which the above condition is true is + max_vq. This is the maximum vector length available to the guest on + this vcpu, and determines which register slices are visible through + this ioctl interface. (See Documentation/arm64/sve.rst for an explanation of the "vq" nomenclature.) @@ -2270,11 +2491,13 @@ write this register will fail with EPERM. MIPS registers are mapped using the lower 32 bits. The upper 16 of that is the register group type: -MIPS core registers (see above) have the following id bit patterns: +MIPS core registers (see above) have the following id bit patterns:: + 0x7030 0000 0000 MIPS CP0 registers (see KVM_REG_MIPS_CP0_* above) have the following id bit -patterns depending on whether they're 32-bit or 64-bit registers: +patterns depending on whether they're 32-bit or 64-bit registers:: + 0x7020 0000 0001 00 (32-bit) 0x7030 0000 0001 00 (64-bit) @@ -2285,10 +2508,12 @@ with the RI and XI bits (if they exist) in bits 63 and 62 respectively, and the PFNX field starting at bit 30. MIPS MAARs (see KVM_REG_MIPS_CP0_MAAR(*) above) have the following id bit -patterns: +patterns:: + 0x7030 0000 0001 01 -MIPS KVM control registers (see above) have the following id bit patterns: +MIPS KVM control registers (see above) have the following id bit patterns:: + 0x7030 0000 0002 MIPS FPU registers (see KVM_REG_MIPS_FPR_{32,64}() above) have the following @@ -2297,31 +2522,40 @@ always accessed according to the current guest FPU mode (Status.FR and Config5.FRE), i.e. as the guest would see them, and they become unpredictable if the guest FPU mode is changed. MIPS SIMD Architecture (MSA) vector registers (see KVM_REG_MIPS_VEC_128() above) have similar patterns as they -overlap the FPU registers: +overlap the FPU registers:: + 0x7020 0000 0003 00 <0:3> (32-bit FPU registers) 0x7030 0000 0003 00 <0:3> (64-bit FPU registers) 0x7040 0000 0003 00 <0:3> (128-bit MSA vector registers) MIPS FPU control registers (see KVM_REG_MIPS_FCR_{IR,CSR} above) have the -following id bit patterns: +following id bit patterns:: + 0x7020 0000 0003 01 <0:3> MIPS MSA control registers (see KVM_REG_MIPS_MSA_{IR,CSR} above) have the -following id bit patterns: +following id bit patterns:: + 0x7020 0000 0003 02 <0:3> 4.69 KVM_GET_ONE_REG +-------------------- + +:Capability: KVM_CAP_ONE_REG +:Architectures: all +:Type: vcpu ioctl +:Parameters: struct kvm_one_reg (in and out) +:Returns: 0 on success, negative value on failure -Capability: KVM_CAP_ONE_REG -Architectures: all -Type: vcpu ioctl -Parameters: struct kvm_one_reg (in and out) -Returns: 0 on success, negative value on failure Errors include: -  ENOENT:   no such register -  EINVAL:   invalid register ID, or no such register -  EPERM:    (arm64) register access not allowed before vcpu finalization + + ======== ============================================================ +  ENOENT   no such register +  EINVAL   invalid register ID, or no such register +  EPERM    (arm64) register access not allowed before vcpu finalization + ======== ============================================================ + (These error codes are indicative only: do not rely on a specific error code being returned in a specific situation.) @@ -2335,12 +2569,13 @@ list in 4.68. 4.70 KVM_KVMCLOCK_CTRL +---------------------- -Capability: KVM_CAP_KVMCLOCK_CTRL -Architectures: Any that implement pvclocks (currently x86 only) -Type: vcpu ioctl -Parameters: None -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_KVMCLOCK_CTRL +:Architectures: Any that implement pvclocks (currently x86 only) +:Type: vcpu ioctl +:Parameters: None +:Returns: 0 on success, -1 on error This signals to the host kernel that the specified guest is being paused by userspace. The host will set a flag in the pvclock structure that is checked @@ -2356,26 +2591,30 @@ after pausing the vcpu, but before it is resumed. 4.71 KVM_SIGNAL_MSI +------------------- -Capability: KVM_CAP_SIGNAL_MSI -Architectures: x86 arm arm64 -Type: vm ioctl -Parameters: struct kvm_msi (in) -Returns: >0 on delivery, 0 if guest blocked the MSI, and -1 on error +:Capability: KVM_CAP_SIGNAL_MSI +:Architectures: x86 arm arm64 +:Type: vm ioctl +:Parameters: struct kvm_msi (in) +:Returns: >0 on delivery, 0 if guest blocked the MSI, and -1 on error Directly inject a MSI message. Only valid with in-kernel irqchip that handles MSI messages. -struct kvm_msi { +:: + + struct kvm_msi { __u32 address_lo; __u32 address_hi; __u32 data; __u32 flags; __u32 devid; __u8 pad[12]; -}; + }; -flags: KVM_MSI_VALID_DEVID: devid contains a valid value. The per-VM +flags: + KVM_MSI_VALID_DEVID: devid contains a valid value. The per-VM KVM_CAP_MSI_DEVID capability advertises the requirement to provide the device ID. If this capability is not available, userspace should never set the KVM_MSI_VALID_DEVID flag as the ioctl might fail. @@ -2391,30 +2630,31 @@ address_hi must be zero. 4.71 KVM_CREATE_PIT2 +-------------------- -Capability: KVM_CAP_PIT2 -Architectures: x86 -Type: vm ioctl -Parameters: struct kvm_pit_config (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_PIT2 +:Architectures: x86 +:Type: vm ioctl +:Parameters: struct kvm_pit_config (in) +:Returns: 0 on success, -1 on error Creates an in-kernel device model for the i8254 PIT. This call is only valid after enabling in-kernel irqchip support via KVM_CREATE_IRQCHIP. The following -parameters have to be passed: +parameters have to be passed:: -struct kvm_pit_config { + struct kvm_pit_config { __u32 flags; __u32 pad[15]; -}; + }; -Valid flags are: +Valid flags are:: -#define KVM_PIT_SPEAKER_DUMMY 1 /* emulate speaker port stub */ + #define KVM_PIT_SPEAKER_DUMMY 1 /* emulate speaker port stub */ PIT timer interrupts may use a per-VM kernel thread for injection. If it -exists, this thread will have a name of the following pattern: +exists, this thread will have a name of the following pattern:: -kvm-pit/ + kvm-pit/ When running a guest with elevated priorities, the scheduling parameters of this thread may have to be adjusted accordingly. @@ -2423,37 +2663,39 @@ This IOCTL replaces the obsolete KVM_CREATE_PIT. 4.72 KVM_GET_PIT2 +----------------- -Capability: KVM_CAP_PIT_STATE2 -Architectures: x86 -Type: vm ioctl -Parameters: struct kvm_pit_state2 (out) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_PIT_STATE2 +:Architectures: x86 +:Type: vm ioctl +:Parameters: struct kvm_pit_state2 (out) +:Returns: 0 on success, -1 on error Retrieves the state of the in-kernel PIT model. Only valid after -KVM_CREATE_PIT2. The state is returned in the following structure: +KVM_CREATE_PIT2. The state is returned in the following structure:: -struct kvm_pit_state2 { + struct kvm_pit_state2 { struct kvm_pit_channel_state channels[3]; __u32 flags; __u32 reserved[9]; -}; + }; -Valid flags are: +Valid flags are:: -/* disable PIT in HPET legacy mode */ -#define KVM_PIT_FLAGS_HPET_LEGACY 0x00000001 + /* disable PIT in HPET legacy mode */ + #define KVM_PIT_FLAGS_HPET_LEGACY 0x00000001 This IOCTL replaces the obsolete KVM_GET_PIT. 4.73 KVM_SET_PIT2 +----------------- -Capability: KVM_CAP_PIT_STATE2 -Architectures: x86 -Type: vm ioctl -Parameters: struct kvm_pit_state2 (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_PIT_STATE2 +:Architectures: x86 +:Type: vm ioctl +:Parameters: struct kvm_pit_state2 (in) +:Returns: 0 on success, -1 on error Sets the state of the in-kernel PIT model. Only valid after KVM_CREATE_PIT2. See KVM_GET_PIT2 for details on struct kvm_pit_state2. @@ -2462,12 +2704,13 @@ This IOCTL replaces the obsolete KVM_SET_PIT. 4.74 KVM_PPC_GET_SMMU_INFO +-------------------------- -Capability: KVM_CAP_PPC_GET_SMMU_INFO -Architectures: powerpc -Type: vm ioctl -Parameters: None -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_PPC_GET_SMMU_INFO +:Architectures: powerpc +:Type: vm ioctl +:Parameters: None +:Returns: 0 on success, -1 on error This populates and returns a structure describing the features of the "Server" class MMU emulation supported by KVM. @@ -2475,7 +2718,7 @@ This can in turn be used by userspace to generate the appropriate device-tree properties for the guest operating system. The structure contains some global information, followed by an -array of supported segment page sizes: +array of supported segment page sizes:: struct kvm_ppc_smmu_info { __u64 flags; @@ -2503,7 +2746,7 @@ The "slb_size" field indicates how many SLB entries are supported The "sps" array contains 8 entries indicating the supported base page sizes for a segment in increasing order. Each entry is defined -as follow: +as follow:: struct kvm_ppc_one_seg_page_size { __u32 page_shift; /* Base page shift of segment (or 0) */ @@ -2524,7 +2767,7 @@ size provides the list of supported actual page sizes (which can be only larger or equal to the base page size), along with the corresponding encoding in the hash PTE. Similarly, the array is 8 entries sorted by increasing sizes and an entry with a "0" shift -is an empty entry and a terminator: +is an empty entry and a terminator:: struct kvm_ppc_one_page_size { __u32 page_shift; /* Page shift (or 0) */ @@ -2536,12 +2779,13 @@ PTE's RPN field (ie, it needs to be shifted left by 12 to OR it into the hash PTE second double word). 4.75 KVM_IRQFD +-------------- -Capability: KVM_CAP_IRQFD -Architectures: x86 s390 arm arm64 -Type: vm ioctl -Parameters: struct kvm_irqfd (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_IRQFD +:Architectures: x86 s390 arm arm64 +:Type: vm ioctl +:Parameters: struct kvm_irqfd (in) +:Returns: 0 on success, -1 on error Allows setting an eventfd to directly trigger a guest interrupt. kvm_irqfd.fd specifies the file descriptor to use as the eventfd and @@ -2565,6 +2809,7 @@ irqfd. The KVM_IRQFD_FLAG_RESAMPLE is only necessary on assignment and need not be specified with KVM_IRQFD_FLAG_DEASSIGN. On arm/arm64, gsi routing being supported, the following can happen: + - in case no routing entry is associated to this gsi, injection fails - in case the gsi is associated to an irqchip routing entry, irqchip.pin + 32 corresponds to the injected SPI ID. @@ -2573,12 +2818,13 @@ On arm/arm64, gsi routing being supported, the following can happen: to GICv3 ITS in-kernel emulation). 4.76 KVM_PPC_ALLOCATE_HTAB +-------------------------- -Capability: KVM_CAP_PPC_ALLOC_HTAB -Architectures: powerpc -Type: vm ioctl -Parameters: Pointer to u32 containing hash table order (in/out) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_PPC_ALLOC_HTAB +:Architectures: powerpc +:Type: vm ioctl +:Parameters: Pointer to u32 containing hash table order (in/out) +:Returns: 0 on success, -1 on error This requests the host kernel to allocate an MMU hash table for a guest using the PAPR paravirtualization interface. This only does @@ -2609,75 +2855,88 @@ real-mode area (VRMA) facility, the kernel will re-create the VMRA HPTEs on the next KVM_RUN of any vcpu. 4.77 KVM_S390_INTERRUPT +----------------------- -Capability: basic -Architectures: s390 -Type: vm ioctl, vcpu ioctl -Parameters: struct kvm_s390_interrupt (in) -Returns: 0 on success, -1 on error +:Capability: basic +:Architectures: s390 +:Type: vm ioctl, vcpu ioctl +:Parameters: struct kvm_s390_interrupt (in) +:Returns: 0 on success, -1 on error Allows to inject an interrupt to the guest. Interrupts can be floating (vm ioctl) or per cpu (vcpu ioctl), depending on the interrupt type. -Interrupt parameters are passed via kvm_s390_interrupt: +Interrupt parameters are passed via kvm_s390_interrupt:: -struct kvm_s390_interrupt { + struct kvm_s390_interrupt { __u32 type; __u32 parm; __u64 parm64; -}; + }; type can be one of the following: -KVM_S390_SIGP_STOP (vcpu) - sigp stop; optional flags in parm -KVM_S390_PROGRAM_INT (vcpu) - program check; code in parm -KVM_S390_SIGP_SET_PREFIX (vcpu) - sigp set prefix; prefix address in parm -KVM_S390_RESTART (vcpu) - restart -KVM_S390_INT_CLOCK_COMP (vcpu) - clock comparator interrupt -KVM_S390_INT_CPU_TIMER (vcpu) - CPU timer interrupt -KVM_S390_INT_VIRTIO (vm) - virtio external interrupt; external interrupt - parameters in parm and parm64 -KVM_S390_INT_SERVICE (vm) - sclp external interrupt; sclp parameter in parm -KVM_S390_INT_EMERGENCY (vcpu) - sigp emergency; source cpu in parm -KVM_S390_INT_EXTERNAL_CALL (vcpu) - sigp external call; source cpu in parm -KVM_S390_INT_IO(ai,cssid,ssid,schid) (vm) - compound value to indicate an - I/O interrupt (ai - adapter interrupt; cssid,ssid,schid - subchannel); - I/O interruption parameters in parm (subchannel) and parm64 (intparm, - interruption subclass) -KVM_S390_MCHK (vm, vcpu) - machine check interrupt; cr 14 bits in parm, - machine check interrupt code in parm64 (note that - machine checks needing further payload are not - supported by this ioctl) +KVM_S390_SIGP_STOP (vcpu) + - sigp stop; optional flags in parm +KVM_S390_PROGRAM_INT (vcpu) + - program check; code in parm +KVM_S390_SIGP_SET_PREFIX (vcpu) + - sigp set prefix; prefix address in parm +KVM_S390_RESTART (vcpu) + - restart +KVM_S390_INT_CLOCK_COMP (vcpu) + - clock comparator interrupt +KVM_S390_INT_CPU_TIMER (vcpu) + - CPU timer interrupt +KVM_S390_INT_VIRTIO (vm) + - virtio external interrupt; external interrupt + parameters in parm and parm64 +KVM_S390_INT_SERVICE (vm) + - sclp external interrupt; sclp parameter in parm +KVM_S390_INT_EMERGENCY (vcpu) + - sigp emergency; source cpu in parm +KVM_S390_INT_EXTERNAL_CALL (vcpu) + - sigp external call; source cpu in parm +KVM_S390_INT_IO(ai,cssid,ssid,schid) (vm) + - compound value to indicate an + I/O interrupt (ai - adapter interrupt; cssid,ssid,schid - subchannel); + I/O interruption parameters in parm (subchannel) and parm64 (intparm, + interruption subclass) +KVM_S390_MCHK (vm, vcpu) + - machine check interrupt; cr 14 bits in parm, machine check interrupt + code in parm64 (note that machine checks needing further payload are not + supported by this ioctl) This is an asynchronous vcpu ioctl and can be invoked from any thread. 4.78 KVM_PPC_GET_HTAB_FD +------------------------ -Capability: KVM_CAP_PPC_HTAB_FD -Architectures: powerpc -Type: vm ioctl -Parameters: Pointer to struct kvm_get_htab_fd (in) -Returns: file descriptor number (>= 0) on success, -1 on error +:Capability: KVM_CAP_PPC_HTAB_FD +:Architectures: powerpc +:Type: vm ioctl +:Parameters: Pointer to struct kvm_get_htab_fd (in) +:Returns: file descriptor number (>= 0) on success, -1 on error This returns a file descriptor that can be used either to read out the entries in the guest's hashed page table (HPT), or to write entries to initialize the HPT. The returned fd can only be written to if the KVM_GET_HTAB_WRITE bit is set in the flags field of the argument, and can only be read if that bit is clear. The argument struct looks like -this: +this:: -/* For KVM_PPC_GET_HTAB_FD */ -struct kvm_get_htab_fd { + /* For KVM_PPC_GET_HTAB_FD */ + struct kvm_get_htab_fd { __u64 flags; __u64 start_index; __u64 reserved[2]; -}; + }; -/* Values for kvm_get_htab_fd.flags */ -#define KVM_GET_HTAB_BOLTED_ONLY ((__u64)0x1) -#define KVM_GET_HTAB_WRITE ((__u64)0x2) + /* Values for kvm_get_htab_fd.flags */ + #define KVM_GET_HTAB_BOLTED_ONLY ((__u64)0x1) + #define KVM_GET_HTAB_WRITE ((__u64)0x2) -The `start_index' field gives the index in the HPT of the entry at +The 'start_index' field gives the index in the HPT of the entry at which to start reading. It is ignored when writing. Reads on the fd will initially supply information about all @@ -2692,29 +2951,34 @@ Data read or written is structured as a header (8 bytes) followed by a series of valid HPT entries (16 bytes) each. The header indicates how many valid HPT entries there are and how many invalid entries follow the valid entries. The invalid entries are not represented explicitly -in the stream. The header format is: +in the stream. The header format is:: -struct kvm_get_htab_header { + struct kvm_get_htab_header { __u32 index; __u16 n_valid; __u16 n_invalid; -}; + }; Writes to the fd create HPT entries starting at the index given in the -header; first `n_valid' valid entries with contents from the data -written, then `n_invalid' invalid entries, invalidating any previously +header; first 'n_valid' valid entries with contents from the data +written, then 'n_invalid' invalid entries, invalidating any previously valid entries found. 4.79 KVM_CREATE_DEVICE +---------------------- + +:Capability: KVM_CAP_DEVICE_CTRL +:Type: vm ioctl +:Parameters: struct kvm_create_device (in/out) +:Returns: 0 on success, -1 on error -Capability: KVM_CAP_DEVICE_CTRL -Type: vm ioctl -Parameters: struct kvm_create_device (in/out) -Returns: 0 on success, -1 on error Errors: - ENODEV: The device type is unknown or unsupported - EEXIST: Device already created, and this type of device may not + + ====== ======================================================= + ENODEV The device type is unknown or unsupported + EEXIST Device already created, and this type of device may not be instantiated multiple times + ====== ======================================================= Other error conditions may be defined by individual device types or have their standard meanings. @@ -2730,25 +2994,32 @@ Individual devices should not define flags. Attributes should be used for specifying any behavior that is not implied by the device type number. -struct kvm_create_device { +:: + + struct kvm_create_device { __u32 type; /* in: KVM_DEV_TYPE_xxx */ __u32 fd; /* out: device handle */ __u32 flags; /* in: KVM_CREATE_DEVICE_xxx */ -}; + }; 4.80 KVM_SET_DEVICE_ATTR/KVM_GET_DEVICE_ATTR +-------------------------------------------- + +:Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device, + KVM_CAP_VCPU_ATTRIBUTES for vcpu device +:Type: device ioctl, vm ioctl, vcpu ioctl +:Parameters: struct kvm_device_attr +:Returns: 0 on success, -1 on error -Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device, - KVM_CAP_VCPU_ATTRIBUTES for vcpu device -Type: device ioctl, vm ioctl, vcpu ioctl -Parameters: struct kvm_device_attr -Returns: 0 on success, -1 on error Errors: - ENXIO: The group or attribute is unknown/unsupported for this device + + ===== ============================================================= + ENXIO The group or attribute is unknown/unsupported for this device or hardware support is missing. - EPERM: The attribute cannot (currently) be accessed this way + EPERM The attribute cannot (currently) be accessed this way (e.g. read-only attribute, or attribute that only makes sense when the device is in a different state) + ===== ============================================================= Other error conditions may be defined by individual device types. @@ -2757,23 +3028,30 @@ semantics are device-specific. See individual device documentation in the "devices" directory. As with ONE_REG, the size of the data transferred is defined by the particular attribute. -struct kvm_device_attr { +:: + + struct kvm_device_attr { __u32 flags; /* no flags currently defined */ __u32 group; /* device-defined */ __u64 attr; /* group-defined */ __u64 addr; /* userspace address of attr data */ -}; + }; 4.81 KVM_HAS_DEVICE_ATTR +------------------------ + +:Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device, + KVM_CAP_VCPU_ATTRIBUTES for vcpu device +:Type: device ioctl, vm ioctl, vcpu ioctl +:Parameters: struct kvm_device_attr +:Returns: 0 on success, -1 on error -Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device, - KVM_CAP_VCPU_ATTRIBUTES for vcpu device -Type: device ioctl, vm ioctl, vcpu ioctl -Parameters: struct kvm_device_attr -Returns: 0 on success, -1 on error Errors: - ENXIO: The group or attribute is unknown/unsupported for this device + + ===== ============================================================= + ENXIO The group or attribute is unknown/unsupported for this device or hardware support is missing. + ===== ============================================================= Tests whether a device supports a particular attribute. A successful return indicates the attribute is implemented. It does not necessarily @@ -2781,15 +3059,20 @@ indicate that the attribute can be read or written in the device's current state. "addr" is ignored. 4.82 KVM_ARM_VCPU_INIT +---------------------- + +:Capability: basic +:Architectures: arm, arm64 +:Type: vcpu ioctl +:Parameters: struct kvm_vcpu_init (in) +:Returns: 0 on success; -1 on error -Capability: basic -Architectures: arm, arm64 -Type: vcpu ioctl -Parameters: struct kvm_vcpu_init (in) -Returns: 0 on success; -1 on error Errors: -  EINVAL:    the target is unknown, or the combination of features is invalid. -  ENOENT:    a features bit specified is unknown. + + ====== ================================================================= +  EINVAL    the target is unknown, or the combination of features is invalid. +  ENOENT    a features bit specified is unknown. + ====== ================================================================= This tells KVM what type of CPU to present to the guest, and what optional features it should have.  This will cause a reset of the cpu @@ -2805,6 +3088,7 @@ state. All calls to this function after the initial call must use the same target and same set of feature flags, otherwise EINVAL will be returned. Possible features: + - KVM_ARM_VCPU_POWER_OFF: Starts the CPU in a power-off state. Depends on KVM_CAP_ARM_PSCI. If not set, the CPU will be powered on and execute guest code when KVM_RUN is called. @@ -2861,14 +3145,19 @@ Possible features: no longer be written using KVM_SET_ONE_REG. 4.83 KVM_ARM_PREFERRED_TARGET +----------------------------- + +:Capability: basic +:Architectures: arm, arm64 +:Type: vm ioctl +:Parameters: struct struct kvm_vcpu_init (out) +:Returns: 0 on success; -1 on error -Capability: basic -Architectures: arm, arm64 -Type: vm ioctl -Parameters: struct struct kvm_vcpu_init (out) -Returns: 0 on success; -1 on error Errors: - ENODEV: no preferred target available for the host + + ====== ========================================== + ENODEV no preferred target available for the host + ====== ========================================== This queries KVM for preferred CPU target type which can be emulated by KVM on underlying host. @@ -2885,43 +3174,57 @@ in VCPU matching underlying host. 4.84 KVM_GET_REG_LIST +--------------------- + +:Capability: basic +:Architectures: arm, arm64, mips +:Type: vcpu ioctl +:Parameters: struct kvm_reg_list (in/out) +:Returns: 0 on success; -1 on error -Capability: basic -Architectures: arm, arm64, mips -Type: vcpu ioctl -Parameters: struct kvm_reg_list (in/out) -Returns: 0 on success; -1 on error Errors: -  E2BIG:     the reg index list is too big to fit in the array specified by + + ===== ============================================================== +  E2BIG     the reg index list is too big to fit in the array specified by             the user (the number required will be written into n). + ===== ============================================================== + +:: -struct kvm_reg_list { + struct kvm_reg_list { __u64 n; /* number of registers in reg[] */ __u64 reg[0]; -}; + }; This ioctl returns the guest registers that are supported for the KVM_GET_ONE_REG/KVM_SET_ONE_REG calls. 4.85 KVM_ARM_SET_DEVICE_ADDR (deprecated) +----------------------------------------- + +:Capability: KVM_CAP_ARM_SET_DEVICE_ADDR +:Architectures: arm, arm64 +:Type: vm ioctl +:Parameters: struct kvm_arm_device_address (in) +:Returns: 0 on success, -1 on error -Capability: KVM_CAP_ARM_SET_DEVICE_ADDR -Architectures: arm, arm64 -Type: vm ioctl -Parameters: struct kvm_arm_device_address (in) -Returns: 0 on success, -1 on error Errors: - ENODEV: The device id is unknown - ENXIO: Device not supported on current system - EEXIST: Address already set - E2BIG: Address outside guest physical address space - EBUSY: Address overlaps with other device range -struct kvm_arm_device_addr { + ====== ============================================ + ENODEV The device id is unknown + ENXIO Device not supported on current system + EEXIST Address already set + E2BIG Address outside guest physical address space + EBUSY Address overlaps with other device range + ====== ============================================ + +:: + + struct kvm_arm_device_addr { __u64 id; __u64 addr; -}; + }; Specify a device address in the guest's physical address space where guests can access emulated or directly exposed devices, which the host kernel needs @@ -2929,7 +3232,7 @@ to know about. The id field is an architecture specific identifier for a specific device. ARM/arm64 divides the id field into two parts, a device id and an -address type id specific to the individual device. +address type id specific to the individual device::  bits: | 63 ... 32 | 31 ... 16 | 15 ... 0 | field: | 0x00000000 | device id | addr type id | @@ -2947,12 +3250,13 @@ should be used instead. 4.86 KVM_PPC_RTAS_DEFINE_TOKEN +------------------------------ -Capability: KVM_CAP_PPC_RTAS -Architectures: ppc -Type: vm ioctl -Parameters: struct kvm_rtas_token_args -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_PPC_RTAS +:Architectures: ppc +:Type: vm ioctl +:Parameters: struct kvm_rtas_token_args +:Returns: 0 on success, -1 on error Defines a token value for a RTAS (Run Time Abstraction Services) service in order to allow it to be handled in the kernel. The @@ -2966,18 +3270,21 @@ calls by the guest for that service will be passed to userspace to be handled. 4.87 KVM_SET_GUEST_DEBUG +------------------------ -Capability: KVM_CAP_SET_GUEST_DEBUG -Architectures: x86, s390, ppc, arm64 -Type: vcpu ioctl -Parameters: struct kvm_guest_debug (in) -Returns: 0 on success; -1 on error +:Capability: KVM_CAP_SET_GUEST_DEBUG +:Architectures: x86, s390, ppc, arm64 +:Type: vcpu ioctl +:Parameters: struct kvm_guest_debug (in) +:Returns: 0 on success; -1 on error -struct kvm_guest_debug { +:: + + struct kvm_guest_debug { __u32 control; __u32 pad; struct kvm_guest_debug_arch arch; -}; + }; Set up the processor specific debug registers and configure vcpu for handling guest debug events. There are two parts to the structure, the @@ -3019,26 +3326,31 @@ KVM_EXIT_DEBUG with the kvm_debug_exit_arch part of the kvm_run structure containing architecture specific debug information. 4.88 KVM_GET_EMULATED_CPUID +--------------------------- + +:Capability: KVM_CAP_EXT_EMUL_CPUID +:Architectures: x86 +:Type: system ioctl +:Parameters: struct kvm_cpuid2 (in/out) +:Returns: 0 on success, -1 on error -Capability: KVM_CAP_EXT_EMUL_CPUID -Architectures: x86 -Type: system ioctl -Parameters: struct kvm_cpuid2 (in/out) -Returns: 0 on success, -1 on error +:: -struct kvm_cpuid2 { + struct kvm_cpuid2 { __u32 nent; __u32 flags; struct kvm_cpuid_entry2 entries[0]; -}; + }; The member 'flags' is used for passing flags from userspace. -#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0) -#define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1) -#define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2) +:: -struct kvm_cpuid_entry2 { + #define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0) + #define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1) + #define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2) + + struct kvm_cpuid_entry2 { __u32 function; __u32 index; __u32 flags; @@ -3047,7 +3359,7 @@ struct kvm_cpuid_entry2 { __u32 ecx; __u32 edx; __u32 padding[3]; -}; + }; This ioctl returns x86 cpuid features which are emulated by kvm.Userspace can use the information returned by this ioctl to query @@ -3072,10 +3384,14 @@ emulated efficiently and thus not included here. The fields in each entry are defined as follows: - function: the eax value used to obtain the entry - index: the ecx value used to obtain the entry (for entries that are + function: + the eax value used to obtain the entry + index: + the ecx value used to obtain the entry (for entries that are affected by ecx) - flags: an OR of zero or more of the following: + flags: + an OR of zero or more of the following: + KVM_CPUID_FLAG_SIGNIFCANT_INDEX: if the index field is valid KVM_CPUID_FLAG_STATEFUL_FUNC: @@ -3085,24 +3401,28 @@ The fields in each entry are defined as follows: KVM_CPUID_FLAG_STATE_READ_NEXT: for KVM_CPUID_FLAG_STATEFUL_FUNC entries, set if this entry is the first entry to be read by a cpu - eax, ebx, ecx, edx: the values returned by the cpuid instruction for + + eax, ebx, ecx, edx: + + the values returned by the cpuid instruction for this function/index combination 4.89 KVM_S390_MEM_OP +-------------------- -Capability: KVM_CAP_S390_MEM_OP -Architectures: s390 -Type: vcpu ioctl -Parameters: struct kvm_s390_mem_op (in) -Returns: = 0 on success, - < 0 on generic error (e.g. -EFAULT or -ENOMEM), - > 0 if an exception occurred while walking the page tables +:Capability: KVM_CAP_S390_MEM_OP +:Architectures: s390 +:Type: vcpu ioctl +:Parameters: struct kvm_s390_mem_op (in) +:Returns: = 0 on success, + < 0 on generic error (e.g. -EFAULT or -ENOMEM), + > 0 if an exception occurred while walking the page tables Read or write data from/to the logical (virtual) memory of a VCPU. -Parameters are specified via the following structure: +Parameters are specified via the following structure:: -struct kvm_s390_mem_op { + struct kvm_s390_mem_op { __u64 gaddr; /* the guest address */ __u64 flags; /* flags */ __u32 size; /* amount of bytes */ @@ -3110,7 +3430,7 @@ struct kvm_s390_mem_op { __u64 buf; /* buffer in userspace */ __u8 ar; /* the access register number */ __u8 reserved[31]; /* should be set to 0 */ -}; + }; The type of operation is specified in the "op" field. It is either KVM_S390_MEMOP_LOGICAL_READ for reading from logical memory space or @@ -3137,24 +3457,25 @@ The "reserved" field is meant for future extensions. It is not used by KVM with the currently defined set of flags. 4.90 KVM_S390_GET_SKEYS +----------------------- -Capability: KVM_CAP_S390_SKEYS -Architectures: s390 -Type: vm ioctl -Parameters: struct kvm_s390_skeys -Returns: 0 on success, KVM_S390_GET_KEYS_NONE if guest is not using storage - keys, negative value on error +:Capability: KVM_CAP_S390_SKEYS +:Architectures: s390 +:Type: vm ioctl +:Parameters: struct kvm_s390_skeys +:Returns: 0 on success, KVM_S390_GET_KEYS_NONE if guest is not using storage + keys, negative value on error This ioctl is used to get guest storage key values on the s390 -architecture. The ioctl takes parameters via the kvm_s390_skeys struct. +architecture. The ioctl takes parameters via the kvm_s390_skeys struct:: -struct kvm_s390_skeys { + struct kvm_s390_skeys { __u64 start_gfn; __u64 count; __u64 skeydata_addr; __u32 flags; __u32 reserved[9]; -}; + }; The start_gfn field is the number of the first guest frame whose storage keys you want to get. @@ -3168,12 +3489,13 @@ The skeydata_addr field is the address to a buffer large enough to hold count bytes. This buffer will be filled with storage key data by the ioctl. 4.91 KVM_S390_SET_SKEYS +----------------------- -Capability: KVM_CAP_S390_SKEYS -Architectures: s390 -Type: vm ioctl -Parameters: struct kvm_s390_skeys -Returns: 0 on success, negative value on error +:Capability: KVM_CAP_S390_SKEYS +:Architectures: s390 +:Type: vm ioctl +:Parameters: struct kvm_s390_skeys +:Returns: 0 on success, negative value on error This ioctl is used to set guest storage key values on the s390 architecture. The ioctl takes parameters via the kvm_s390_skeys struct. @@ -3195,21 +3517,27 @@ Note: If any architecturally invalid key value is found in the given data then the ioctl will return -EINVAL. 4.92 KVM_S390_IRQ +----------------- + +:Capability: KVM_CAP_S390_INJECT_IRQ +:Architectures: s390 +:Type: vcpu ioctl +:Parameters: struct kvm_s390_irq (in) +:Returns: 0 on success, -1 on error -Capability: KVM_CAP_S390_INJECT_IRQ -Architectures: s390 -Type: vcpu ioctl -Parameters: struct kvm_s390_irq (in) -Returns: 0 on success, -1 on error Errors: - EINVAL: interrupt type is invalid - type is KVM_S390_SIGP_STOP and flag parameter is invalid value + + + ====== ================================================================= + EINVAL interrupt type is invalid + type is KVM_S390_SIGP_STOP and flag parameter is invalid value, type is KVM_S390_INT_EXTERNAL_CALL and code is bigger - than the maximum of VCPUs - EBUSY: type is KVM_S390_SIGP_SET_PREFIX and vcpu is not stopped - type is KVM_S390_SIGP_STOP and a stop irq is already pending + than the maximum of VCPUs + EBUSY type is KVM_S390_SIGP_SET_PREFIX and vcpu is not stopped, + type is KVM_S390_SIGP_STOP and a stop irq is already pending, type is KVM_S390_INT_EXTERNAL_CALL and an external call interrupt - is already pending + is already pending + ====== ================================================================= Allows to inject an interrupt to the guest. @@ -3217,9 +3545,9 @@ Using struct kvm_s390_irq as a parameter allows to inject additional payload which is not possible via KVM_S390_INTERRUPT. -Interrupt parameters are passed via kvm_s390_irq: +Interrupt parameters are passed via kvm_s390_irq:: -struct kvm_s390_irq { + struct kvm_s390_irq { __u64 type; union { struct kvm_s390_io_info io; @@ -3232,44 +3560,45 @@ struct kvm_s390_irq { struct kvm_s390_mchk_info mchk; char reserved[64]; } u; -}; + }; type can be one of the following: -KVM_S390_SIGP_STOP - sigp stop; parameter in .stop -KVM_S390_PROGRAM_INT - program check; parameters in .pgm -KVM_S390_SIGP_SET_PREFIX - sigp set prefix; parameters in .prefix -KVM_S390_RESTART - restart; no parameters -KVM_S390_INT_CLOCK_COMP - clock comparator interrupt; no parameters -KVM_S390_INT_CPU_TIMER - CPU timer interrupt; no parameters -KVM_S390_INT_EMERGENCY - sigp emergency; parameters in .emerg -KVM_S390_INT_EXTERNAL_CALL - sigp external call; parameters in .extcall -KVM_S390_MCHK - machine check interrupt; parameters in .mchk +- KVM_S390_SIGP_STOP - sigp stop; parameter in .stop +- KVM_S390_PROGRAM_INT - program check; parameters in .pgm +- KVM_S390_SIGP_SET_PREFIX - sigp set prefix; parameters in .prefix +- KVM_S390_RESTART - restart; no parameters +- KVM_S390_INT_CLOCK_COMP - clock comparator interrupt; no parameters +- KVM_S390_INT_CPU_TIMER - CPU timer interrupt; no parameters +- KVM_S390_INT_EMERGENCY - sigp emergency; parameters in .emerg +- KVM_S390_INT_EXTERNAL_CALL - sigp external call; parameters in .extcall +- KVM_S390_MCHK - machine check interrupt; parameters in .mchk This is an asynchronous vcpu ioctl and can be invoked from any thread. 4.94 KVM_S390_GET_IRQ_STATE +--------------------------- -Capability: KVM_CAP_S390_IRQ_STATE -Architectures: s390 -Type: vcpu ioctl -Parameters: struct kvm_s390_irq_state (out) -Returns: >= number of bytes copied into buffer, - -EINVAL if buffer size is 0, - -ENOBUFS if buffer size is too small to fit all pending interrupts, - -EFAULT if the buffer address was invalid +:Capability: KVM_CAP_S390_IRQ_STATE +:Architectures: s390 +:Type: vcpu ioctl +:Parameters: struct kvm_s390_irq_state (out) +:Returns: >= number of bytes copied into buffer, + -EINVAL if buffer size is 0, + -ENOBUFS if buffer size is too small to fit all pending interrupts, + -EFAULT if the buffer address was invalid This ioctl allows userspace to retrieve the complete state of all currently pending interrupts in a single buffer. Use cases include migration and introspection. The parameter structure contains the address of a -userspace buffer and its length: +userspace buffer and its length:: -struct kvm_s390_irq_state { + struct kvm_s390_irq_state { __u64 buf; __u32 flags; /* will stay unused for compatibility reasons */ __u32 len; __u32 reserved[4]; /* will stay unused for compatibility reasons */ -}; + }; Userspace passes in the above struct and for each pending interrupt a struct kvm_s390_irq is copied to the provided buffer. @@ -3283,29 +3612,30 @@ If -ENOBUFS is returned the buffer provided was too small and userspace may retry with a bigger buffer. 4.95 KVM_S390_SET_IRQ_STATE - -Capability: KVM_CAP_S390_IRQ_STATE -Architectures: s390 -Type: vcpu ioctl -Parameters: struct kvm_s390_irq_state (in) -Returns: 0 on success, - -EFAULT if the buffer address was invalid, - -EINVAL for an invalid buffer length (see below), - -EBUSY if there were already interrupts pending, - errors occurring when actually injecting the +--------------------------- + +:Capability: KVM_CAP_S390_IRQ_STATE +:Architectures: s390 +:Type: vcpu ioctl +:Parameters: struct kvm_s390_irq_state (in) +:Returns: 0 on success, + -EFAULT if the buffer address was invalid, + -EINVAL for an invalid buffer length (see below), + -EBUSY if there were already interrupts pending, + errors occurring when actually injecting the interrupt. See KVM_S390_IRQ. This ioctl allows userspace to set the complete state of all cpu-local interrupts currently pending for the vcpu. It is intended for restoring interrupt state after a migration. The input parameter is a userspace buffer -containing a struct kvm_s390_irq_state: +containing a struct kvm_s390_irq_state:: -struct kvm_s390_irq_state { + struct kvm_s390_irq_state { __u64 buf; __u32 flags; /* will stay unused for compatibility reasons */ __u32 len; __u32 reserved[4]; /* will stay unused for compatibility reasons */ -}; + }; The restrictions for flags and reserved apply as well. (see KVM_S390_GET_IRQ_STATE) @@ -3320,20 +3650,22 @@ and it must not exceed (max_vcpus + 32) * sizeof(struct kvm_s390_irq), which is the maximum number of possibly pending cpu-local interrupts. 4.96 KVM_SMI +------------ -Capability: KVM_CAP_X86_SMM -Architectures: x86 -Type: vcpu ioctl -Parameters: none -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_X86_SMM +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: none +:Returns: 0 on success, -1 on error Queues an SMI on the thread's vcpu. 4.97 KVM_CAP_PPC_MULTITCE +------------------------- -Capability: KVM_CAP_PPC_MULTITCE -Architectures: ppc -Type: vm +:Capability: KVM_CAP_PPC_MULTITCE +:Architectures: ppc +:Type: vm This capability means the kernel is capable of handling hypercalls H_PUT_TCE_INDIRECT and H_STUFF_TCE without passing those into the user @@ -3355,26 +3687,27 @@ an implementation for these despite the in kernel acceleration. This capability is always enabled. 4.98 KVM_CREATE_SPAPR_TCE_64 +---------------------------- -Capability: KVM_CAP_SPAPR_TCE_64 -Architectures: powerpc -Type: vm ioctl -Parameters: struct kvm_create_spapr_tce_64 (in) -Returns: file descriptor for manipulating the created TCE table +:Capability: KVM_CAP_SPAPR_TCE_64 +:Architectures: powerpc +:Type: vm ioctl +:Parameters: struct kvm_create_spapr_tce_64 (in) +:Returns: file descriptor for manipulating the created TCE table This is an extension for KVM_CAP_SPAPR_TCE which only supports 32bit windows, described in 4.62 KVM_CREATE_SPAPR_TCE -This capability uses extended struct in ioctl interface: +This capability uses extended struct in ioctl interface:: -/* for KVM_CAP_SPAPR_TCE_64 */ -struct kvm_create_spapr_tce_64 { + /* for KVM_CAP_SPAPR_TCE_64 */ + struct kvm_create_spapr_tce_64 { __u64 liobn; __u32 page_shift; __u32 flags; __u64 offset; /* in pages */ __u64 size; /* in pages */ -}; + }; The aim of extension is to support an additional bigger DMA window with a variable page size. @@ -3387,12 +3720,13 @@ of IOMMU pages. The rest of functionality is identical to KVM_CREATE_SPAPR_TCE. 4.99 KVM_REINJECT_CONTROL +------------------------- -Capability: KVM_CAP_REINJECT_CONTROL -Architectures: x86 -Type: vm ioctl -Parameters: struct kvm_reinject_control (in) -Returns: 0 on success, +:Capability: KVM_CAP_REINJECT_CONTROL +:Architectures: x86 +:Type: vm ioctl +:Parameters: struct kvm_reinject_control (in) +:Returns: 0 on success, -EFAULT if struct kvm_reinject_control cannot be read, -ENXIO if KVM_CREATE_PIT or KVM_CREATE_PIT2 didn't succeed earlier. @@ -3402,21 +3736,24 @@ vector(s) that i8254 injects. Reinject mode dequeues a tick and injects its interrupt whenever there isn't a pending interrupt from i8254. !reinject mode injects an interrupt as soon as a tick arrives. -struct kvm_reinject_control { +:: + + struct kvm_reinject_control { __u8 pit_reinject; __u8 reserved[31]; -}; + }; pit_reinject = 0 (!reinject mode) is recommended, unless running an old operating system that uses the PIT for timing (e.g. Linux 2.4.x). 4.100 KVM_PPC_CONFIGURE_V3_MMU +------------------------------ -Capability: KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_HASH_MMU_V3 -Architectures: ppc -Type: vm ioctl -Parameters: struct kvm_ppc_mmuv3_cfg (in) -Returns: 0 on success, +:Capability: KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_HASH_MMU_V3 +:Architectures: ppc +:Type: vm ioctl +:Parameters: struct kvm_ppc_mmuv3_cfg (in) +:Returns: 0 on success, -EFAULT if struct kvm_ppc_mmuv3_cfg cannot be read, -EINVAL if the configuration is invalid @@ -3424,10 +3761,12 @@ This ioctl controls whether the guest will use radix or HPT (hashed page table) translation, and sets the pointer to the process table for the guest. -struct kvm_ppc_mmuv3_cfg { +:: + + struct kvm_ppc_mmuv3_cfg { __u64 flags; __u64 process_table; -}; + }; There are two bits that can be set in flags; KVM_PPC_MMUV3_RADIX and KVM_PPC_MMUV3_GTSE. KVM_PPC_MMUV3_RADIX, if set, configures the guest @@ -3442,12 +3781,13 @@ as the second doubleword of the partition table entry, as defined in the Power ISA V3.00, Book III section 5.7.6.1. 4.101 KVM_PPC_GET_RMMU_INFO +--------------------------- -Capability: KVM_CAP_PPC_RADIX_MMU -Architectures: ppc -Type: vm ioctl -Parameters: struct kvm_ppc_rmmu_info (out) -Returns: 0 on success, +:Capability: KVM_CAP_PPC_RADIX_MMU +:Architectures: ppc +:Type: vm ioctl +:Parameters: struct kvm_ppc_rmmu_info (out) +:Returns: 0 on success, -EFAULT if struct kvm_ppc_rmmu_info cannot be written, -EINVAL if no useful information can be returned @@ -3456,14 +3796,16 @@ containing supported radix tree geometries, and (b) a list that maps page sizes to put in the "AP" (actual page size) field for the tlbie (TLB invalidate entry) instruction. -struct kvm_ppc_rmmu_info { +:: + + struct kvm_ppc_rmmu_info { struct kvm_ppc_radix_geom { __u8 page_shift; __u8 level_bits[4]; __u8 pad[3]; } geometries[8]; __u32 ap_encodings[8]; -}; + }; The geometries[] field gives up to 8 supported geometries for the radix page table, in terms of the log base 2 of the smallest page @@ -3476,19 +3818,54 @@ encodings, encoded with the AP value in the top 3 bits and the log base 2 of the page size in the bottom 6 bits. 4.102 KVM_PPC_RESIZE_HPT_PREPARE +-------------------------------- -Capability: KVM_CAP_SPAPR_RESIZE_HPT -Architectures: powerpc -Type: vm ioctl -Parameters: struct kvm_ppc_resize_hpt (in) -Returns: 0 on successful completion, +:Capability: KVM_CAP_SPAPR_RESIZE_HPT +:Architectures: powerpc +:Type: vm ioctl +:Parameters: struct kvm_ppc_resize_hpt (in) +:Returns: 0 on successful completion, >0 if a new HPT is being prepared, the value is an estimated - number of milliseconds until preparation is complete + number of milliseconds until preparation is complete, -EFAULT if struct kvm_reinject_control cannot be read, - -EINVAL if the supplied shift or flags are invalid - -ENOMEM if unable to allocate the new HPT - -ENOSPC if there was a hash collision when moving existing - HPT entries to the new HPT + -EINVAL if the supplied shift or flags are invalid, + -ENOMEM if unable to allocate the new HPT, + -ENOSPC if there was a hash collision + +:: + + struct kvm_ppc_rmmu_info { + struct kvm_ppc_radix_geom { + __u8 page_shift; + __u8 level_bits[4]; + __u8 pad[3]; + } geometries[8]; + __u32 ap_encodings[8]; + }; + +The geometries[] field gives up to 8 supported geometries for the +radix page table, in terms of the log base 2 of the smallest page +size, and the number of bits indexed at each level of the tree, from +the PTE level up to the PGD level in that order. Any unused entries +will have 0 in the page_shift field. + +The ap_encodings gives the supported page sizes and their AP field +encodings, encoded with the AP value in the top 3 bits and the log +base 2 of the page size in the bottom 6 bits. + +4.102 KVM_PPC_RESIZE_HPT_PREPARE +-------------------------------- + +:Capability: KVM_CAP_SPAPR_RESIZE_HPT +:Architectures: powerpc +:Type: vm ioctl +:Parameters: struct kvm_ppc_resize_hpt (in) +:Returns: 0 on successful completion, + >0 if a new HPT is being prepared, the value is an estimated + number of milliseconds until preparation is complete, + -EFAULT if struct kvm_reinject_control cannot be read, + -EINVAL if the supplied shift or flags are invalid,when moving existing + HPT entries to the new HPT, -EIO on other error conditions Used to implement the PAPR extension for runtime resizing of a guest's @@ -3506,6 +3883,7 @@ requested in the parameters, discards the existing pending HPT and creates a new one as above. If called when there is a pending HPT of the size requested, will: + * If preparation of the pending HPT is already complete, return 0 * If preparation of the pending HPT has failed, return an error code, then discard the pending HPT. @@ -3522,26 +3900,29 @@ Normally this will be called repeatedly with the same parameters until it returns <= 0. The first call will initiate preparation, subsequent ones will monitor preparation until it completes or fails. -struct kvm_ppc_resize_hpt { +:: + + struct kvm_ppc_resize_hpt { __u64 flags; __u32 shift; __u32 pad; -}; + }; 4.103 KVM_PPC_RESIZE_HPT_COMMIT +------------------------------- -Capability: KVM_CAP_SPAPR_RESIZE_HPT -Architectures: powerpc -Type: vm ioctl -Parameters: struct kvm_ppc_resize_hpt (in) -Returns: 0 on successful completion, +:Capability: KVM_CAP_SPAPR_RESIZE_HPT +:Architectures: powerpc +:Type: vm ioctl +:Parameters: struct kvm_ppc_resize_hpt (in) +:Returns: 0 on successful completion, -EFAULT if struct kvm_reinject_control cannot be read, - -EINVAL if the supplied shift or flags are invalid + -EINVAL if the supplied shift or flags are invalid, -ENXIO is there is no pending HPT, or the pending HPT doesn't - have the requested size - -EBUSY if the pending HPT is not fully prepared + have the requested size, + -EBUSY if the pending HPT is not fully prepared, -ENOSPC if there was a hash collision when moving existing - HPT entries to the new HPT + HPT entries to the new HPT, -EIO on other error conditions Used to implement the PAPR extension for runtime resizing of a guest's @@ -3564,31 +3945,35 @@ HPT and the previous HPT will be discarded. On failure, the guest will still be operating on its previous HPT. -struct kvm_ppc_resize_hpt { +:: + + struct kvm_ppc_resize_hpt { __u64 flags; __u32 shift; __u32 pad; -}; + }; 4.104 KVM_X86_GET_MCE_CAP_SUPPORTED +----------------------------------- -Capability: KVM_CAP_MCE -Architectures: x86 -Type: system ioctl -Parameters: u64 mce_cap (out) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_MCE +:Architectures: x86 +:Type: system ioctl +:Parameters: u64 mce_cap (out) +:Returns: 0 on success, -1 on error Returns supported MCE capabilities. The u64 mce_cap parameter has the same format as the MSR_IA32_MCG_CAP register. Supported capabilities will have the corresponding bits set. 4.105 KVM_X86_SETUP_MCE +----------------------- -Capability: KVM_CAP_MCE -Architectures: x86 -Type: vcpu ioctl -Parameters: u64 mcg_cap (in) -Returns: 0 on success, +:Capability: KVM_CAP_MCE +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: u64 mcg_cap (in) +:Returns: 0 on success, -EFAULT if u64 mcg_cap cannot be read, -EINVAL if the requested number of banks is invalid, -EINVAL if requested MCE capability is not supported. @@ -3601,20 +3986,21 @@ checking for KVM_CAP_MCE. The supported capabilities can be retrieved with KVM_X86_GET_MCE_CAP_SUPPORTED. 4.106 KVM_X86_SET_MCE +--------------------- -Capability: KVM_CAP_MCE -Architectures: x86 -Type: vcpu ioctl -Parameters: struct kvm_x86_mce (in) -Returns: 0 on success, +:Capability: KVM_CAP_MCE +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_x86_mce (in) +:Returns: 0 on success, -EFAULT if struct kvm_x86_mce cannot be read, -EINVAL if the bank number is invalid, -EINVAL if VAL bit is not set in status field. Inject a machine check error (MCE) into the guest. The input -parameter is: +parameter is:: -struct kvm_x86_mce { + struct kvm_x86_mce { __u64 status; __u64 addr; __u64 misc; @@ -3622,7 +4008,7 @@ struct kvm_x86_mce { __u8 bank; __u8 pad1[7]; __u64 pad2[3]; -}; + }; If the MCE being reported is an uncorrected error, KVM will inject it as an MCE exception into the guest. If the guest @@ -3634,15 +4020,17 @@ store it in the corresponding bank (provided this bank is not holding a previously reported uncorrected error). 4.107 KVM_S390_GET_CMMA_BITS +---------------------------- -Capability: KVM_CAP_S390_CMMA_MIGRATION -Architectures: s390 -Type: vm ioctl -Parameters: struct kvm_s390_cmma_log (in, out) -Returns: 0 on success, a negative value on error +:Capability: KVM_CAP_S390_CMMA_MIGRATION +:Architectures: s390 +:Type: vm ioctl +:Parameters: struct kvm_s390_cmma_log (in, out) +:Returns: 0 on success, a negative value on error This ioctl is used to get the values of the CMMA bits on the s390 architecture. It is meant to be used in two scenarios: + - During live migration to save the CMMA values. Live migration needs to be enabled via the KVM_REQ_START_MIGRATION VM property. - To non-destructively peek at the CMMA values, with the flag @@ -3652,9 +4040,12 @@ The ioctl takes parameters via the kvm_s390_cmma_log struct. The desired values are written to a buffer whose location is indicated via the "values" member in the kvm_s390_cmma_log struct. The values in the input struct are also updated as needed. + Each CMMA value takes up one byte. -struct kvm_s390_cmma_log { +:: + + struct kvm_s390_cmma_log { __u64 start_gfn; __u32 count; __u32 flags; @@ -3663,7 +4054,7 @@ struct kvm_s390_cmma_log { __u64 mask; }; __u64 values; -}; + }; start_gfn is the number of the first guest frame whose CMMA values are to be retrieved, @@ -3724,12 +4115,13 @@ KVM_S390_CMMA_PEEK is not set but migration mode was not enabled, with present for the addresses (e.g. when using hugepages). 4.108 KVM_S390_SET_CMMA_BITS +---------------------------- -Capability: KVM_CAP_S390_CMMA_MIGRATION -Architectures: s390 -Type: vm ioctl -Parameters: struct kvm_s390_cmma_log (in) -Returns: 0 on success, a negative value on error +:Capability: KVM_CAP_S390_CMMA_MIGRATION +:Architectures: s390 +:Type: vm ioctl +:Parameters: struct kvm_s390_cmma_log (in) +:Returns: 0 on success, a negative value on error This ioctl is used to set the values of the CMMA bits on the s390 architecture. It is meant to be used during live migration to restore @@ -3737,16 +4129,18 @@ the CMMA values, but there are no restrictions on its use. The ioctl takes parameters via the kvm_s390_cmma_values struct. Each CMMA value takes up one byte. -struct kvm_s390_cmma_log { +:: + + struct kvm_s390_cmma_log { __u64 start_gfn; __u32 count; __u32 flags; union { __u64 remaining; __u64 mask; - }; + }; __u64 values; -}; + }; start_gfn indicates the starting guest frame number, @@ -3769,26 +4163,27 @@ or if no page table is present for the addresses (e.g. when using hugepages). 4.109 KVM_PPC_GET_CPU_CHAR +-------------------------- -Capability: KVM_CAP_PPC_GET_CPU_CHAR -Architectures: powerpc -Type: vm ioctl -Parameters: struct kvm_ppc_cpu_char (out) -Returns: 0 on successful completion +:Capability: KVM_CAP_PPC_GET_CPU_CHAR +:Architectures: powerpc +:Type: vm ioctl +:Parameters: struct kvm_ppc_cpu_char (out) +:Returns: 0 on successful completion, -EFAULT if struct kvm_ppc_cpu_char cannot be written This ioctl gives userspace information about certain characteristics of the CPU relating to speculative execution of instructions and possible information leakage resulting from speculative execution (see CVE-2017-5715, CVE-2017-5753 and CVE-2017-5754). The information is -returned in struct kvm_ppc_cpu_char, which looks like this: +returned in struct kvm_ppc_cpu_char, which looks like this:: -struct kvm_ppc_cpu_char { + struct kvm_ppc_cpu_char { __u64 character; /* characteristics of the CPU */ __u64 behaviour; /* recommended software behaviour */ __u64 character_mask; /* valid bits in character */ __u64 behaviour_mask; /* valid bits in behaviour */ -}; + }; For extensibility, the character_mask and behaviour_mask fields indicate which bits of character and behaviour have been filled in by @@ -3815,12 +4210,13 @@ These fields use the same bit definitions as the new H_GET_CPU_CHARACTERISTICS hypercall. 4.110 KVM_MEMORY_ENCRYPT_OP +--------------------------- -Capability: basic -Architectures: x86 -Type: system -Parameters: an opaque platform specific structure (in/out) -Returns: 0 on success; -1 on error +:Capability: basic +:Architectures: x86 +:Type: system +:Parameters: an opaque platform specific structure (in/out) +:Returns: 0 on success; -1 on error If the platform supports creating encrypted VMs then this ioctl can be used for issuing platform-specific memory encryption commands to manage those @@ -3831,12 +4227,13 @@ Currently, this ioctl is used for issuing Secure Encrypted Virtualization Documentation/virt/kvm/amd-memory-encryption.rst. 4.111 KVM_MEMORY_ENCRYPT_REG_REGION +----------------------------------- -Capability: basic -Architectures: x86 -Type: system -Parameters: struct kvm_enc_region (in) -Returns: 0 on success; -1 on error +:Capability: basic +:Architectures: x86 +:Type: system +:Parameters: struct kvm_enc_region (in) +:Returns: 0 on success; -1 on error This ioctl can be used to register a guest memory region which may contain encrypted data (e.g. guest RAM, SMRAM etc). @@ -3854,60 +4251,71 @@ swap or migrate (move) ciphertext pages. Hence, for now we pin the guest memory region registered with the ioctl. 4.112 KVM_MEMORY_ENCRYPT_UNREG_REGION +------------------------------------- -Capability: basic -Architectures: x86 -Type: system -Parameters: struct kvm_enc_region (in) -Returns: 0 on success; -1 on error +:Capability: basic +:Architectures: x86 +:Type: system +:Parameters: struct kvm_enc_region (in) +:Returns: 0 on success; -1 on error This ioctl can be used to unregister the guest memory region registered with KVM_MEMORY_ENCRYPT_REG_REGION ioctl above. 4.113 KVM_HYPERV_EVENTFD +------------------------ -Capability: KVM_CAP_HYPERV_EVENTFD -Architectures: x86 -Type: vm ioctl -Parameters: struct kvm_hyperv_eventfd (in) +:Capability: KVM_CAP_HYPERV_EVENTFD +:Architectures: x86 +:Type: vm ioctl +:Parameters: struct kvm_hyperv_eventfd (in) This ioctl (un)registers an eventfd to receive notifications from the guest on the specified Hyper-V connection id through the SIGNAL_EVENT hypercall, without causing a user exit. SIGNAL_EVENT hypercall with non-zero event flag number (bits 24-31) still triggers a KVM_EXIT_HYPERV_HCALL user exit. -struct kvm_hyperv_eventfd { +:: + + struct kvm_hyperv_eventfd { __u32 conn_id; __s32 fd; __u32 flags; __u32 padding[3]; -}; + }; -The conn_id field should fit within 24 bits: +The conn_id field should fit within 24 bits:: -#define KVM_HYPERV_CONN_ID_MASK 0x00ffffff + #define KVM_HYPERV_CONN_ID_MASK 0x00ffffff -The acceptable values for the flags field are: +The acceptable values for the flags field are:: -#define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0) + #define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0) -Returns: 0 on success, - -EINVAL if conn_id or flags is outside the allowed range - -ENOENT on deassign if the conn_id isn't registered - -EEXIST on assign if the conn_id is already registered +:Returns: 0 on success, + -EINVAL if conn_id or flags is outside the allowed range, + -ENOENT on deassign if the conn_id isn't registered, + -EEXIST on assign if the conn_id is already registered 4.114 KVM_GET_NESTED_STATE +-------------------------- + +:Capability: KVM_CAP_NESTED_STATE +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_nested_state (in/out) +:Returns: 0 on success, -1 on error -Capability: KVM_CAP_NESTED_STATE -Architectures: x86 -Type: vcpu ioctl -Parameters: struct kvm_nested_state (in/out) -Returns: 0 on success, -1 on error Errors: - E2BIG: the total state size exceeds the value of 'size' specified by + + ===== ============================================================= + E2BIG the total state size exceeds the value of 'size' specified by the user; the size required will be written into size. + ===== ============================================================= + +:: -struct kvm_nested_state { + struct kvm_nested_state { __u16 flags; __u16 format; __u32 size; @@ -3924,33 +4332,33 @@ struct kvm_nested_state { struct kvm_vmx_nested_state_data vmx[0]; struct kvm_svm_nested_state_data svm[0]; } data; -}; + }; -#define KVM_STATE_NESTED_GUEST_MODE 0x00000001 -#define KVM_STATE_NESTED_RUN_PENDING 0x00000002 -#define KVM_STATE_NESTED_EVMCS 0x00000004 + #define KVM_STATE_NESTED_GUEST_MODE 0x00000001 + #define KVM_STATE_NESTED_RUN_PENDING 0x00000002 + #define KVM_STATE_NESTED_EVMCS 0x00000004 -#define KVM_STATE_NESTED_FORMAT_VMX 0 -#define KVM_STATE_NESTED_FORMAT_SVM 1 + #define KVM_STATE_NESTED_FORMAT_VMX 0 + #define KVM_STATE_NESTED_FORMAT_SVM 1 -#define KVM_STATE_NESTED_VMX_VMCS_SIZE 0x1000 + #define KVM_STATE_NESTED_VMX_VMCS_SIZE 0x1000 -#define KVM_STATE_NESTED_VMX_SMM_GUEST_MODE 0x00000001 -#define KVM_STATE_NESTED_VMX_SMM_VMXON 0x00000002 + #define KVM_STATE_NESTED_VMX_SMM_GUEST_MODE 0x00000001 + #define KVM_STATE_NESTED_VMX_SMM_VMXON 0x00000002 -struct kvm_vmx_nested_state_hdr { + struct kvm_vmx_nested_state_hdr { __u64 vmxon_pa; __u64 vmcs12_pa; struct { __u16 flags; } smm; -}; + }; -struct kvm_vmx_nested_state_data { + struct kvm_vmx_nested_state_data { __u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE]; __u8 shadow_vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE]; -}; + }; This ioctl copies the vcpu's nested virtualization state from the kernel to userspace. @@ -3959,24 +4367,26 @@ The maximum size of the state can be retrieved by passing KVM_CAP_NESTED_STATE to the KVM_CHECK_EXTENSION ioctl(). 4.115 KVM_SET_NESTED_STATE +-------------------------- -Capability: KVM_CAP_NESTED_STATE -Architectures: x86 -Type: vcpu ioctl -Parameters: struct kvm_nested_state (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_NESTED_STATE +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_nested_state (in) +:Returns: 0 on success, -1 on error This copies the vcpu's kvm_nested_state struct from userspace to the kernel. For the definition of struct kvm_nested_state, see KVM_GET_NESTED_STATE. 4.116 KVM_(UN)REGISTER_COALESCED_MMIO +------------------------------------- -Capability: KVM_CAP_COALESCED_MMIO (for coalesced mmio) - KVM_CAP_COALESCED_PIO (for coalesced pio) -Architectures: all -Type: vm ioctl -Parameters: struct kvm_coalesced_mmio_zone -Returns: 0 on success, < 0 on error +:Capability: KVM_CAP_COALESCED_MMIO (for coalesced mmio) + KVM_CAP_COALESCED_PIO (for coalesced pio) +:Architectures: all +:Type: vm ioctl +:Parameters: struct kvm_coalesced_mmio_zone +:Returns: 0 on success, < 0 on error Coalesced I/O is a performance optimization that defers hardware register write emulation so that userspace exits are avoided. It is @@ -3998,15 +4408,18 @@ between coalesced mmio and pio except that coalesced pio records accesses to I/O ports. 4.117 KVM_CLEAR_DIRTY_LOG (vm ioctl) +------------------------------------ -Capability: KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 -Architectures: x86, arm, arm64, mips -Type: vm ioctl -Parameters: struct kvm_dirty_log (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 +:Architectures: x86, arm, arm64, mips +:Type: vm ioctl +:Parameters: struct kvm_dirty_log (in) +:Returns: 0 on success, -1 on error -/* for KVM_CLEAR_DIRTY_LOG */ -struct kvm_clear_dirty_log { +:: + + /* for KVM_CLEAR_DIRTY_LOG */ + struct kvm_clear_dirty_log { __u32 slot; __u32 num_pages; __u64 first_page; @@ -4014,7 +4427,7 @@ struct kvm_clear_dirty_log { void __user *dirty_bitmap; /* one bit per page */ __u64 padding; }; -}; + }; The ioctl clears the dirty status of pages in a memory slot, according to the bitmap that is passed in struct kvm_clear_dirty_log's dirty_bitmap @@ -4038,20 +4451,23 @@ However, it can always be used as long as KVM_CHECK_EXTENSION confirms that KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 is present. 4.118 KVM_GET_SUPPORTED_HV_CPUID +-------------------------------- + +:Capability: KVM_CAP_HYPERV_CPUID +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_cpuid2 (in/out) +:Returns: 0 on success, -1 on error -Capability: KVM_CAP_HYPERV_CPUID -Architectures: x86 -Type: vcpu ioctl -Parameters: struct kvm_cpuid2 (in/out) -Returns: 0 on success, -1 on error +:: -struct kvm_cpuid2 { + struct kvm_cpuid2 { __u32 nent; __u32 padding; struct kvm_cpuid_entry2 entries[0]; -}; + }; -struct kvm_cpuid_entry2 { + struct kvm_cpuid_entry2 { __u32 function; __u32 index; __u32 flags; @@ -4060,7 +4476,7 @@ struct kvm_cpuid_entry2 { __u32 ecx; __u32 edx; __u32 padding[3]; -}; + }; This ioctl returns x86 cpuid features leaves related to Hyper-V emulation in KVM. Userspace can use the information returned by this ioctl to construct @@ -4073,13 +4489,13 @@ KVM_GET_SUPPORTED_CPUID ioctl because some of them intersect with KVM feature leaves (0x40000000, 0x40000001). Currently, the following list of CPUID leaves are returned: - HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS - HYPERV_CPUID_INTERFACE - HYPERV_CPUID_VERSION - HYPERV_CPUID_FEATURES - HYPERV_CPUID_ENLIGHTMENT_INFO - HYPERV_CPUID_IMPLEMENT_LIMITS - HYPERV_CPUID_NESTED_FEATURES + - HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS + - HYPERV_CPUID_INTERFACE + - HYPERV_CPUID_VERSION + - HYPERV_CPUID_FEATURES + - HYPERV_CPUID_ENLIGHTMENT_INFO + - HYPERV_CPUID_IMPLEMENT_LIMITS + - HYPERV_CPUID_NESTED_FEATURES HYPERV_CPUID_NESTED_FEATURES leaf is only exposed when Enlightened VMCS was enabled on the corresponding vCPU (KVM_CAP_HYPERV_ENLIGHTENED_VMCS). @@ -4095,17 +4511,25 @@ number of valid entries in the 'entries' array, which is then filled. userspace should not expect to get any particular value there. 4.119 KVM_ARM_VCPU_FINALIZE +--------------------------- + +:Architectures: arm, arm64 +:Type: vcpu ioctl +:Parameters: int feature (in) +:Returns: 0 on success, -1 on error -Architectures: arm, arm64 -Type: vcpu ioctl -Parameters: int feature (in) -Returns: 0 on success, -1 on error Errors: - EPERM: feature not enabled, needs configuration, or already finalized - EINVAL: feature unknown or not present + + ====== ============================================================== + EPERM feature not enabled, needs configuration, or already finalized + EINVAL feature unknown or not present + ====== ============================================================== Recognised values for feature: + + ===== =========================================== arm64 KVM_ARM_VCPU_SVE (requires KVM_CAP_ARM_SVE) + ===== =========================================== Finalizes the configuration of the specified vcpu feature. @@ -4129,21 +4553,24 @@ See KVM_ARM_VCPU_INIT for details of vcpu features that require finalization using this ioctl. 4.120 KVM_SET_PMU_EVENT_FILTER +------------------------------ -Capability: KVM_CAP_PMU_EVENT_FILTER -Architectures: x86 -Type: vm ioctl -Parameters: struct kvm_pmu_event_filter (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_PMU_EVENT_FILTER +:Architectures: x86 +:Type: vm ioctl +:Parameters: struct kvm_pmu_event_filter (in) +:Returns: 0 on success, -1 on error -struct kvm_pmu_event_filter { +:: + + struct kvm_pmu_event_filter { __u32 action; __u32 nevents; __u32 fixed_counter_bitmap; __u32 flags; __u32 pad[4]; __u64 events[0]; -}; + }; This ioctl restricts the set of PMU events that the guest can program. The argument holds a list of events which will be allowed or denied. @@ -4154,20 +4581,26 @@ counters are controlled by the fixed_counter_bitmap. No flags are defined yet, the field must be zero. -Valid values for 'action': -#define KVM_PMU_EVENT_ALLOW 0 -#define KVM_PMU_EVENT_DENY 1 +Valid values for 'action':: + + #define KVM_PMU_EVENT_ALLOW 0 + #define KVM_PMU_EVENT_DENY 1 4.121 KVM_PPC_SVM_OFF +--------------------- + +:Capability: basic +:Architectures: powerpc +:Type: vm ioctl +:Parameters: none +:Returns: 0 on successful completion, -Capability: basic -Architectures: powerpc -Type: vm ioctl -Parameters: none -Returns: 0 on successful completion, Errors: - EINVAL: if ultravisor failed to terminate the secure guest - ENOMEM: if hypervisor failed to allocate new radix page tables for guest + + ====== ================================================================ + EINVAL if ultravisor failed to terminate the secure guest + ENOMEM if hypervisor failed to allocate new radix page tables for guest + ====== ================================================================ This ioctl is used to turn off the secure mode of the guest or transition the guest from secure mode to normal mode. This is invoked when the guest @@ -4178,35 +4611,38 @@ unpins the VPA pages and releases all the device pages that are used to track the secure pages by hypervisor. 4.122 KVM_S390_NORMAL_RESET +--------------------------- -Capability: KVM_CAP_S390_VCPU_RESETS -Architectures: s390 -Type: vcpu ioctl -Parameters: none -Returns: 0 +:Capability: KVM_CAP_S390_VCPU_RESETS +:Architectures: s390 +:Type: vcpu ioctl +:Parameters: none +:Returns: 0 This ioctl resets VCPU registers and control structures according to the cpu reset definition in the POP (Principles Of Operation). 4.123 KVM_S390_INITIAL_RESET +---------------------------- -Capability: none -Architectures: s390 -Type: vcpu ioctl -Parameters: none -Returns: 0 +:Capability: none +:Architectures: s390 +:Type: vcpu ioctl +:Parameters: none +:Returns: 0 This ioctl resets VCPU registers and control structures according to the initial cpu reset definition in the POP. However, the cpu is not put into ESA mode. This reset is a superset of the normal reset. 4.124 KVM_S390_CLEAR_RESET +-------------------------- -Capability: KVM_CAP_S390_VCPU_RESETS -Architectures: s390 -Type: vcpu ioctl -Parameters: none -Returns: 0 +:Capability: KVM_CAP_S390_VCPU_RESETS +:Architectures: s390 +:Type: vcpu ioctl +:Parameters: none +:Returns: 0 This ioctl resets VCPU registers and control structures according to the clear cpu reset definition in the POP. However, the cpu is not put @@ -4214,7 +4650,7 @@ into ESA mode. This reset is a superset of the initial reset. 5. The kvm_run structure ------------------------- +======================== Application code obtains a pointer to the kvm_run structure by mmap()ing a vcpu fd. From that point, application code can control @@ -4222,13 +4658,17 @@ execution by changing fields in kvm_run prior to calling the KVM_RUN ioctl, and obtain information about the reason KVM_RUN returned by looking up structure members. -struct kvm_run { +:: + + struct kvm_run { /* in */ __u8 request_interrupt_window; Request that KVM_RUN return when it becomes possible to inject external interrupts into the guest. Useful in conjunction with KVM_INTERRUPT. +:: + __u8 immediate_exit; This field is polled once when KVM_RUN starts; if non-zero, KVM_RUN @@ -4240,6 +4680,8 @@ a signal handler that sets run->immediate_exit to a non-zero value. This field is ignored if KVM_CAP_IMMEDIATE_EXIT is not available. +:: + __u8 padding1[6]; /* out */ @@ -4249,16 +4691,22 @@ When KVM_RUN has returned successfully (return value 0), this informs application code why KVM_RUN has returned. Allowable values for this field are detailed below. +:: + __u8 ready_for_interrupt_injection; If request_interrupt_window has been specified, this field indicates an interrupt can be injected now with KVM_INTERRUPT. +:: + __u8 if_flag; The value of the current interrupt flag. Only valid if in-kernel local APIC is not used. +:: + __u16 flags; More architecture-specific flags detailing state of the VCPU that may @@ -4266,17 +4714,23 @@ affect the device's behavior. The only currently defined flag is KVM_RUN_X86_SMM, which is valid on x86 machines and is set if the VCPU is in system management mode. +:: + /* in (pre_kvm_run), out (post_kvm_run) */ __u64 cr8; The value of the cr8 register. Only valid if in-kernel local APIC is not used. Both input and output. +:: + __u64 apic_base; The value of the APIC BASE msr. Only valid if in-kernel local APIC is not used. Both input and output. +:: + union { /* KVM_EXIT_UNKNOWN */ struct { @@ -4287,6 +4741,8 @@ If exit_reason is KVM_EXIT_UNKNOWN, the vcpu has exited due to unknown reasons. Further architecture-specific information is available in hardware_exit_reason. +:: + /* KVM_EXIT_FAIL_ENTRY */ struct { __u64 hardware_entry_failure_reason; @@ -4296,6 +4752,8 @@ If exit_reason is KVM_EXIT_FAIL_ENTRY, the vcpu could not be run due to unknown reasons. Further architecture-specific information is available in hardware_entry_failure_reason. +:: + /* KVM_EXIT_EXCEPTION */ struct { __u32 exception; @@ -4304,10 +4762,12 @@ available in hardware_entry_failure_reason. Unused. +:: + /* KVM_EXIT_IO */ struct { -#define KVM_EXIT_IO_IN 0 -#define KVM_EXIT_IO_OUT 1 + #define KVM_EXIT_IO_IN 0 + #define KVM_EXIT_IO_OUT 1 __u8 direction; __u8 size; /* bytes */ __u16 port; @@ -4321,6 +4781,8 @@ data_offset describes where the data is located (KVM_EXIT_IO_OUT) or where kvm expects application code to place the data for the next KVM_RUN invocation (KVM_EXIT_IO_IN). Data format is a packed array. +:: + /* KVM_EXIT_DEBUG */ struct { struct kvm_debug_exit_arch arch; @@ -4329,6 +4791,8 @@ KVM_RUN invocation (KVM_EXIT_IO_IN). Data format is a packed array. If the exit_reason is KVM_EXIT_DEBUG, then a vcpu is processing a debug event for which architecture specific information is returned. +:: + /* KVM_EXIT_MMIO */ struct { __u64 phys_addr; @@ -4346,14 +4810,19 @@ The 'data' member contains, in its first 'len' bytes, the value as it would appear if the VCPU performed a load or store of the appropriate width directly to the byte array. -NOTE: For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_PAPR and +.. note:: + + For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_PAPR and KVM_EXIT_EPR the corresponding + operations are complete (and guest state is consistent) only after userspace has re-entered the kernel with KVM_RUN. The kernel side will first finish incomplete operations and then check for pending signals. Userspace can re-enter the guest with an unmasked signal pending to complete pending operations. +:: + /* KVM_EXIT_HYPERCALL */ struct { __u64 nr; @@ -4365,7 +4834,10 @@ pending operations. Unused. This was once used for 'hypercall to userspace'. To implement such functionality, use KVM_EXIT_IO (x86) or KVM_EXIT_MMIO (all except s390). -Note KVM_EXIT_IO is significantly faster than KVM_EXIT_MMIO. + +.. note:: KVM_EXIT_IO is significantly faster than KVM_EXIT_MMIO. + +:: /* KVM_EXIT_TPR_ACCESS */ struct { @@ -4376,6 +4848,8 @@ Note KVM_EXIT_IO is significantly faster than KVM_EXIT_MMIO. To be documented (KVM_TPR_ACCESS_REPORTING). +:: + /* KVM_EXIT_S390_SIEIC */ struct { __u8 icptcode; @@ -4387,16 +4861,20 @@ To be documented (KVM_TPR_ACCESS_REPORTING). s390 specific. +:: + /* KVM_EXIT_S390_RESET */ -#define KVM_S390_RESET_POR 1 -#define KVM_S390_RESET_CLEAR 2 -#define KVM_S390_RESET_SUBSYSTEM 4 -#define KVM_S390_RESET_CPU_INIT 8 -#define KVM_S390_RESET_IPL 16 + #define KVM_S390_RESET_POR 1 + #define KVM_S390_RESET_CLEAR 2 + #define KVM_S390_RESET_SUBSYSTEM 4 + #define KVM_S390_RESET_CPU_INIT 8 + #define KVM_S390_RESET_IPL 16 __u64 s390_reset_flags; s390 specific. +:: + /* KVM_EXIT_S390_UCONTROL */ struct { __u64 trans_exc_code; @@ -4411,6 +4889,8 @@ in the cpu's lowcore are presented here as defined by the z Architecture Principles of Operation Book in the Chapter for Dynamic Address Translation (DAT) +:: + /* KVM_EXIT_DCR */ struct { __u32 dcrn; @@ -4420,6 +4900,8 @@ Principles of Operation Book in the Chapter for Dynamic Address Translation Deprecated - was used for 440 KVM. +:: + /* KVM_EXIT_OSI */ struct { __u64 gprs[32]; @@ -4433,6 +4915,8 @@ Userspace can now handle the hypercall and when it's done modify the gprs as necessary. Upon guest entry all guest GPRs will then be replaced by the values in this struct. +:: + /* KVM_EXIT_PAPR_HCALL */ struct { __u64 nr; @@ -4450,6 +4934,8 @@ The possible hypercalls are defined in the Power Architecture Platform Requirements (PAPR) document available from www.power.org (free developer registration required to access it). +:: + /* KVM_EXIT_S390_TSCH */ struct { __u16 subchannel_id; @@ -4466,6 +4952,8 @@ interrupt for the target subchannel has been dequeued and subchannel_id, subchannel_nr, io_int_parm and io_int_word contain the parameters for that interrupt. ipb is needed for instruction parameter decoding. +:: + /* KVM_EXIT_EPR */ struct { __u32 epr; @@ -4485,11 +4973,13 @@ It gets triggered whenever both KVM_CAP_PPC_EPR are enabled and an external interrupt has just been delivered into the guest. User space should put the acknowledged interrupt vector into the 'epr' field. +:: + /* KVM_EXIT_SYSTEM_EVENT */ struct { -#define KVM_SYSTEM_EVENT_SHUTDOWN 1 -#define KVM_SYSTEM_EVENT_RESET 2 -#define KVM_SYSTEM_EVENT_CRASH 3 + #define KVM_SYSTEM_EVENT_SHUTDOWN 1 + #define KVM_SYSTEM_EVENT_RESET 2 + #define KVM_SYSTEM_EVENT_CRASH 3 __u32 type; __u64 flags; } system_event; @@ -4502,18 +4992,21 @@ the system-level event type. The 'flags' field describes architecture specific flags for the system-level event. Valid values for 'type' are: - KVM_SYSTEM_EVENT_SHUTDOWN -- the guest has requested a shutdown of the + + - KVM_SYSTEM_EVENT_SHUTDOWN -- the guest has requested a shutdown of the VM. Userspace is not obliged to honour this, and if it does honour this does not need to destroy the VM synchronously (ie it may call KVM_RUN again before shutdown finally occurs). - KVM_SYSTEM_EVENT_RESET -- the guest has requested a reset of the VM. + - KVM_SYSTEM_EVENT_RESET -- the guest has requested a reset of the VM. As with SHUTDOWN, userspace can choose to ignore the request, or to schedule the reset to occur in the future and may call KVM_RUN again. - KVM_SYSTEM_EVENT_CRASH -- the guest crash occurred and the guest + - KVM_SYSTEM_EVENT_CRASH -- the guest crash occurred and the guest has requested a crash condition maintenance. Userspace can choose to ignore the request, or to gather VM memory core dump and/or reset/shutdown of the VM. +:: + /* KVM_EXIT_IOAPIC_EOI */ struct { __u8 vector; @@ -4526,9 +5019,11 @@ the userspace IOAPIC should process the EOI and retrigger the interrupt if it is still asserted. Vector is the LAPIC interrupt vector for which the EOI was received. +:: + struct kvm_hyperv_exit { -#define KVM_EXIT_HYPERV_SYNIC 1 -#define KVM_EXIT_HYPERV_HCALL 2 + #define KVM_EXIT_HYPERV_SYNIC 1 + #define KVM_EXIT_HYPERV_HCALL 2 __u32 type; union { struct { @@ -4546,14 +5041,20 @@ EOI was received. }; /* KVM_EXIT_HYPERV */ struct kvm_hyperv_exit hyperv; + Indicates that the VCPU exits into userspace to process some tasks related to Hyper-V emulation. + Valid values for 'type' are: - KVM_EXIT_HYPERV_SYNIC -- synchronously notify user-space about + + - KVM_EXIT_HYPERV_SYNIC -- synchronously notify user-space about + Hyper-V SynIC state change. Notification is used to remap SynIC event/message pages and to enable/disable SynIC messages/events processing in userspace. +:: + /* KVM_EXIT_ARM_NISV */ struct { __u64 esr_iss; @@ -4587,6 +5088,8 @@ Note that KVM does not skip the faulting instruction as it does for KVM_EXIT_MMIO, but userspace has to emulate any change to the processing state if it decides to decode and emulate the instruction. +:: + /* Fix the size of the union. */ char padding[256]; }; @@ -4611,18 +5114,20 @@ avoid some system call overhead if userspace has to handle the exit. Userspace can query the validity of the structure by checking kvm_valid_regs for specific bits. These bits are architecture specific and usually define the validity of a groups of registers. (e.g. one bit - for general purpose registers) +for general purpose registers) Please note that the kernel is allowed to use the kvm_run structure as the primary storage for certain register types. Therefore, the kernel may use the values in kvm_run even if the corresponding bit in kvm_dirty_regs is not set. -}; +:: + + }; 6. Capabilities that can be enabled on vCPUs --------------------------------------------- +============================================ There are certain capabilities that change the behavior of the virtual CPU or the virtual machine when enabled. To enable them, please see section 4.37. @@ -4631,23 +5136,28 @@ the virtual machine is when enabling them. The following information is provided along with the description: - Architectures: which instruction set architectures provide this ioctl. + Architectures: + which instruction set architectures provide this ioctl. x86 includes both i386 and x86_64. - Target: whether this is a per-vcpu or per-vm capability. + Target: + whether this is a per-vcpu or per-vm capability. - Parameters: what parameters are accepted by the capability. + Parameters: + what parameters are accepted by the capability. - Returns: the return value. General error numbers (EBADF, ENOMEM, EINVAL) + Returns: + the return value. General error numbers (EBADF, ENOMEM, EINVAL) are not detailed, but errors with specific meanings are. 6.1 KVM_CAP_PPC_OSI +------------------- -Architectures: ppc -Target: vcpu -Parameters: none -Returns: 0 on success; -1 on error +:Architectures: ppc +:Target: vcpu +:Parameters: none +:Returns: 0 on success; -1 on error This capability enables interception of OSI hypercalls that otherwise would be treated as normal system calls to be injected into the guest. OSI hypercalls @@ -4658,11 +5168,12 @@ When this capability is enabled, KVM_EXIT_OSI can occur. 6.2 KVM_CAP_PPC_PAPR +-------------------- -Architectures: ppc -Target: vcpu -Parameters: none -Returns: 0 on success; -1 on error +:Architectures: ppc +:Target: vcpu +:Parameters: none +:Returns: 0 on success; -1 on error This capability enables interception of PAPR hypercalls. PAPR hypercalls are done using the hypercall instruction "sc 1". @@ -4678,18 +5189,21 @@ When this capability is enabled, KVM_EXIT_PAPR_HCALL can occur. 6.3 KVM_CAP_SW_TLB +------------------ + +:Architectures: ppc +:Target: vcpu +:Parameters: args[0] is the address of a struct kvm_config_tlb +:Returns: 0 on success; -1 on error -Architectures: ppc -Target: vcpu -Parameters: args[0] is the address of a struct kvm_config_tlb -Returns: 0 on success; -1 on error +:: -struct kvm_config_tlb { + struct kvm_config_tlb { __u64 params; __u64 array; __u32 mmu_type; __u32 array_len; -}; + }; Configures the virtual CPU's TLB array, establishing a shared memory area between userspace and KVM. The "params" and "array" fields are userspace @@ -4708,6 +5222,7 @@ to tell KVM which entries have been changed, prior to calling KVM_RUN again on this vcpu. For mmu types KVM_MMU_FSL_BOOKE_NOHV and KVM_MMU_FSL_BOOKE_HV: + - The "params" field is of type "struct kvm_book3e_206_tlb_params". - The "array" field points to an array of type "struct kvm_book3e_206_tlb_entry". @@ -4721,11 +5236,12 @@ For mmu types KVM_MMU_FSL_BOOKE_NOHV and KVM_MMU_FSL_BOOKE_HV: hardware ignores this value for TLB0. 6.4 KVM_CAP_S390_CSS_SUPPORT +---------------------------- -Architectures: s390 -Target: vcpu -Parameters: none -Returns: 0 on success; -1 on error +:Architectures: s390 +:Target: vcpu +:Parameters: none +:Returns: 0 on success; -1 on error This capability enables support for handling of channel I/O instructions. @@ -4739,11 +5255,12 @@ Note that even though this capability is enabled per-vcpu, the complete virtual machine is affected. 6.5 KVM_CAP_PPC_EPR +------------------- -Architectures: ppc -Target: vcpu -Parameters: args[0] defines whether the proxy facility is active -Returns: 0 on success; -1 on error +:Architectures: ppc +:Target: vcpu +:Parameters: args[0] defines whether the proxy facility is active +:Returns: 0 on success; -1 on error This capability enables or disables the delivery of interrupts through the external proxy facility. @@ -4757,62 +5274,70 @@ When disabled (args[0] == 0), behavior is as if this facility is unsupported. When this capability is enabled, KVM_EXIT_EPR can occur. 6.6 KVM_CAP_IRQ_MPIC +-------------------- -Architectures: ppc -Parameters: args[0] is the MPIC device fd - args[1] is the MPIC CPU number for this vcpu +:Architectures: ppc +:Parameters: args[0] is the MPIC device fd; + args[1] is the MPIC CPU number for this vcpu This capability connects the vcpu to an in-kernel MPIC device. 6.7 KVM_CAP_IRQ_XICS +-------------------- -Architectures: ppc -Target: vcpu -Parameters: args[0] is the XICS device fd - args[1] is the XICS CPU number (server ID) for this vcpu +:Architectures: ppc +:Target: vcpu +:Parameters: args[0] is the XICS device fd; + args[1] is the XICS CPU number (server ID) for this vcpu This capability connects the vcpu to an in-kernel XICS device. 6.8 KVM_CAP_S390_IRQCHIP +------------------------ -Architectures: s390 -Target: vm -Parameters: none +:Architectures: s390 +:Target: vm +:Parameters: none This capability enables the in-kernel irqchip for s390. Please refer to "4.24 KVM_CREATE_IRQCHIP" for details. 6.9 KVM_CAP_MIPS_FPU +-------------------- -Architectures: mips -Target: vcpu -Parameters: args[0] is reserved for future use (should be 0). +:Architectures: mips +:Target: vcpu +:Parameters: args[0] is reserved for future use (should be 0). This capability allows the use of the host Floating Point Unit by the guest. It allows the Config1.FP bit to be set to enable the FPU in the guest. Once this is -done the KVM_REG_MIPS_FPR_* and KVM_REG_MIPS_FCR_* registers can be accessed -(depending on the current guest FPU register mode), and the Status.FR, +done the ``KVM_REG_MIPS_FPR_*`` and ``KVM_REG_MIPS_FCR_*`` registers can be +accessed (depending on the current guest FPU register mode), and the Status.FR, Config5.FRE bits are accessible via the KVM API and also from the guest, depending on them being supported by the FPU. 6.10 KVM_CAP_MIPS_MSA +--------------------- -Architectures: mips -Target: vcpu -Parameters: args[0] is reserved for future use (should be 0). +:Architectures: mips +:Target: vcpu +:Parameters: args[0] is reserved for future use (should be 0). This capability allows the use of the MIPS SIMD Architecture (MSA) by the guest. It allows the Config3.MSAP bit to be set to enable the use of MSA by the guest. -Once this is done the KVM_REG_MIPS_VEC_* and KVM_REG_MIPS_MSA_* registers can be -accessed, and the Config5.MSAEn bit is accessible via the KVM API and also from -the guest. +Once this is done the ``KVM_REG_MIPS_VEC_*`` and ``KVM_REG_MIPS_MSA_*`` +registers can be accessed, and the Config5.MSAEn bit is accessible via the +KVM API and also from the guest. 6.74 KVM_CAP_SYNC_REGS -Architectures: s390, x86 -Target: s390: always enabled, x86: vcpu -Parameters: none -Returns: x86: KVM_CHECK_EXTENSION returns a bit-array indicating which register -sets are supported (bitfields defined in arch/x86/include/uapi/asm/kvm.h). +---------------------- + +:Architectures: s390, x86 +:Target: s390: always enabled, x86: vcpu +:Parameters: none +:Returns: x86: KVM_CHECK_EXTENSION returns a bit-array indicating which register + sets are supported + (bitfields defined in arch/x86/include/uapi/asm/kvm.h). As described above in the kvm_sync_regs struct info in section 5 (kvm_run): KVM_CAP_SYNC_REGS "allow[s] userspace to access certain guest registers @@ -4825,6 +5350,7 @@ userspace. For s390 specifics, please refer to the source code. For x86: + - the register sets to be copied out to kvm_run are selectable by userspace (rather that all sets being copied out for every exit). - vcpu_events are available in addition to regs and sregs. @@ -4841,23 +5367,26 @@ into the vCPU even if they've been modified. Unused bitfields in the bitarrays must be set to zero. -struct kvm_sync_regs { +:: + + struct kvm_sync_regs { struct kvm_regs regs; struct kvm_sregs sregs; struct kvm_vcpu_events events; -}; + }; 6.75 KVM_CAP_PPC_IRQ_XIVE +------------------------- -Architectures: ppc -Target: vcpu -Parameters: args[0] is the XIVE device fd - args[1] is the XIVE CPU number (server ID) for this vcpu +:Architectures: ppc +:Target: vcpu +:Parameters: args[0] is the XIVE device fd; + args[1] is the XIVE CPU number (server ID) for this vcpu This capability connects the vcpu to an in-kernel XIVE device. 7. Capabilities that can be enabled on VMs ------------------------------------------- +========================================== There are certain capabilities that change the behavior of the virtual machine when enabled. To enable them, please see section 4.37. Below @@ -4866,20 +5395,24 @@ is when enabling them. The following information is provided along with the description: - Architectures: which instruction set architectures provide this ioctl. + Architectures: + which instruction set architectures provide this ioctl. x86 includes both i386 and x86_64. - Parameters: what parameters are accepted by the capability. + Parameters: + what parameters are accepted by the capability. - Returns: the return value. General error numbers (EBADF, ENOMEM, EINVAL) + Returns: + the return value. General error numbers (EBADF, ENOMEM, EINVAL) are not detailed, but errors with specific meanings are. 7.1 KVM_CAP_PPC_ENABLE_HCALL +---------------------------- -Architectures: ppc -Parameters: args[0] is the sPAPR hcall number - args[1] is 0 to disable, 1 to enable in-kernel handling +:Architectures: ppc +:Parameters: args[0] is the sPAPR hcall number; + args[1] is 0 to disable, 1 to enable in-kernel handling This capability controls whether individual sPAPR hypercalls (hcalls) get handled by the kernel or not. Enabling or disabling in-kernel @@ -4897,13 +5430,15 @@ implementation, the KVM_ENABLE_CAP ioctl will fail with an EINVAL error. 7.2 KVM_CAP_S390_USER_SIGP +-------------------------- -Architectures: s390 -Parameters: none +:Architectures: s390 +:Parameters: none This capability controls which SIGP orders will be handled completely in user space. With this capability enabled, all fast orders will be handled completely in the kernel: + - SENSE - SENSE RUNNING - EXTERNAL CALL @@ -4917,48 +5452,52 @@ in the hardware prior to interception). If this capability is not enabled, the old way of handling SIGP orders is used (partially in kernel and user space). 7.3 KVM_CAP_S390_VECTOR_REGISTERS +--------------------------------- -Architectures: s390 -Parameters: none -Returns: 0 on success, negative value on error +:Architectures: s390 +:Parameters: none +:Returns: 0 on success, negative value on error Allows use of the vector registers introduced with z13 processor, and provides for the synchronization between host and user space. Will return -EINVAL if the machine does not support vectors. 7.4 KVM_CAP_S390_USER_STSI +-------------------------- -Architectures: s390 -Parameters: none +:Architectures: s390 +:Parameters: none This capability allows post-handlers for the STSI instruction. After initial handling in the kernel, KVM exits to user space with KVM_EXIT_S390_STSI to allow user space to insert further data. Before exiting to userspace, kvm handlers should fill in s390_stsi field of -vcpu->run: -struct { +vcpu->run:: + + struct { __u64 addr; __u8 ar; __u8 reserved; __u8 fc; __u8 sel1; __u16 sel2; -} s390_stsi; + } s390_stsi; -@addr - guest address of STSI SYSIB -@fc - function code -@sel1 - selector 1 -@sel2 - selector 2 -@ar - access register number + @addr - guest address of STSI SYSIB + @fc - function code + @sel1 - selector 1 + @sel2 - selector 2 + @ar - access register number KVM handlers should exit to userspace with rc = -EREMOTE. 7.5 KVM_CAP_SPLIT_IRQCHIP +------------------------- -Architectures: x86 -Parameters: args[0] - number of routes reserved for userspace IOAPICs -Returns: 0 on success, -1 on error +:Architectures: x86 +:Parameters: args[0] - number of routes reserved for userspace IOAPICs +:Returns: 0 on success, -1 on error Create a local apic for each processor in the kernel. This can be used instead of KVM_CREATE_IRQCHIP if the userspace VMM wishes to emulate the @@ -4975,24 +5514,26 @@ Fails if VCPU has already been created, or if the irqchip is already in the kernel (i.e. KVM_CREATE_IRQCHIP has already been called). 7.6 KVM_CAP_S390_RI +------------------- -Architectures: s390 -Parameters: none +:Architectures: s390 +:Parameters: none Allows use of runtime-instrumentation introduced with zEC12 processor. Will return -EINVAL if the machine does not support runtime-instrumentation. Will return -EBUSY if a VCPU has already been created. 7.7 KVM_CAP_X2APIC_API +---------------------- -Architectures: x86 -Parameters: args[0] - features that should be enabled -Returns: 0 on success, -EINVAL when args[0] contains invalid features +:Architectures: x86 +:Parameters: args[0] - features that should be enabled +:Returns: 0 on success, -EINVAL when args[0] contains invalid features -Valid feature flags in args[0] are +Valid feature flags in args[0] are:: -#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) -#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1) + #define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) + #define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1) Enabling KVM_X2APIC_API_USE_32BIT_IDS changes the behavior of KVM_SET_GSI_ROUTING, KVM_SIGNAL_MSI, KVM_SET_LAPIC, and KVM_GET_LAPIC, @@ -5006,9 +5547,10 @@ without interrupt remapping. This is undesirable in logical mode, where 0xff represents CPUs 0-7 in cluster 0. 7.8 KVM_CAP_S390_USER_INSTR0 +---------------------------- -Architectures: s390 -Parameters: none +:Architectures: s390 +:Parameters: none With this capability enabled, all illegal instructions 0x0000 (2 bytes) will be intercepted and forwarded to user space. User space can use this @@ -5020,26 +5562,29 @@ This capability can be enabled dynamically even if VCPUs were already created and are running. 7.9 KVM_CAP_S390_GS +------------------- -Architectures: s390 -Parameters: none -Returns: 0 on success; -EINVAL if the machine does not support - guarded storage; -EBUSY if a VCPU has already been created. +:Architectures: s390 +:Parameters: none +:Returns: 0 on success; -EINVAL if the machine does not support + guarded storage; -EBUSY if a VCPU has already been created. Allows use of guarded storage for the KVM guest. 7.10 KVM_CAP_S390_AIS +--------------------- -Architectures: s390 -Parameters: none +:Architectures: s390 +:Parameters: none Allow use of adapter-interruption suppression. -Returns: 0 on success; -EBUSY if a VCPU has already been created. +:Returns: 0 on success; -EBUSY if a VCPU has already been created. 7.11 KVM_CAP_PPC_SMT +-------------------- -Architectures: ppc -Parameters: vsmt_mode, flags +:Architectures: ppc +:Parameters: vsmt_mode, flags Enabling this capability on a VM provides userspace with a way to set the desired virtual SMT mode (i.e. the number of virtual CPUs per @@ -5054,9 +5599,10 @@ The KVM_CAP_PPC_SMT_POSSIBLE capability indicates which virtual SMT modes are available. 7.12 KVM_CAP_PPC_FWNMI +---------------------- -Architectures: ppc -Parameters: none +:Architectures: ppc +:Parameters: none With this capability a machine check exception in the guest address space will cause KVM to exit the guest with NMI exit reason. This @@ -5065,17 +5611,18 @@ machine check handling routine. Without this capability KVM will branch to guests' 0x200 interrupt vector. 7.13 KVM_CAP_X86_DISABLE_EXITS +------------------------------ -Architectures: x86 -Parameters: args[0] defines which exits are disabled -Returns: 0 on success, -EINVAL when args[0] contains invalid exits +:Architectures: x86 +:Parameters: args[0] defines which exits are disabled +:Returns: 0 on success, -EINVAL when args[0] contains invalid exits -Valid bits in args[0] are +Valid bits in args[0] are:: -#define KVM_X86_DISABLE_EXITS_MWAIT (1 << 0) -#define KVM_X86_DISABLE_EXITS_HLT (1 << 1) -#define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2) -#define KVM_X86_DISABLE_EXITS_CSTATE (1 << 3) + #define KVM_X86_DISABLE_EXITS_MWAIT (1 << 0) + #define KVM_X86_DISABLE_EXITS_HLT (1 << 1) + #define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2) + #define KVM_X86_DISABLE_EXITS_CSTATE (1 << 3) Enabling this capability on a VM provides userspace with a way to no longer intercept some instructions for improved latency in some @@ -5087,12 +5634,13 @@ all such vmexits. Do not enable KVM_FEATURE_PV_UNHALT if you disable HLT exits. 7.14 KVM_CAP_S390_HPAGE_1M +-------------------------- -Architectures: s390 -Parameters: none -Returns: 0 on success, -EINVAL if hpage module parameter was not set - or cmma is enabled, or the VM has the KVM_VM_S390_UCONTROL - flag set +:Architectures: s390 +:Parameters: none +:Returns: 0 on success, -EINVAL if hpage module parameter was not set + or cmma is enabled, or the VM has the KVM_VM_S390_UCONTROL + flag set With this capability the KVM support for memory backing with 1m pages through hugetlbfs can be enabled for a VM. After the capability is @@ -5104,20 +5652,22 @@ While it is generally possible to create a huge page backed VM without this capability, the VM will not be able to run. 7.15 KVM_CAP_MSR_PLATFORM_INFO +------------------------------ -Architectures: x86 -Parameters: args[0] whether feature should be enabled or not +:Architectures: x86 +:Parameters: args[0] whether feature should be enabled or not With this capability, a guest may read the MSR_PLATFORM_INFO MSR. Otherwise, a #GP would be raised when the guest tries to access. Currently, this capability does not enable write permissions of this MSR for the guest. 7.16 KVM_CAP_PPC_NESTED_HV +-------------------------- -Architectures: ppc -Parameters: none -Returns: 0 on success, -EINVAL when the implementation doesn't support - nested-HV virtualization. +:Architectures: ppc +:Parameters: none +:Returns: 0 on success, -EINVAL when the implementation doesn't support + nested-HV virtualization. HV-KVM on POWER9 and later systems allows for "nested-HV" virtualization, which provides a way for a guest VM to run guests that @@ -5127,9 +5677,10 @@ the necessary functionality and on the facility being enabled with a kvm-hv module parameter. 7.17 KVM_CAP_EXCEPTION_PAYLOAD +------------------------------ -Architectures: x86 -Parameters: args[0] whether feature should be enabled or not +:Architectures: x86 +:Parameters: args[0] whether feature should be enabled or not With this capability enabled, CR2 will not be modified prior to the emulated VM-exit when L1 intercepts a #PF exception that occurs in @@ -5140,21 +5691,21 @@ L2. As a result, when KVM_GET_VCPU_EVENTS reports a pending #PF (or faulting address (or the new DR6 bits*) will be reported in the exception_payload field. Similarly, when userspace injects a #PF (or #DB) into L2 using KVM_SET_VCPU_EVENTS, it is expected to set -exception.has_payload and to put the faulting address (or the new DR6 -bits*) in the exception_payload field. +exception.has_payload and to put the faulting address - or the new DR6 +bits\ [#]_ - in the exception_payload field. This capability also enables exception.pending in struct kvm_vcpu_events, which allows userspace to distinguish between pending and injected exceptions. -* For the new DR6 bits, note that bit 16 is set iff the #DB exception - will clear DR6.RTM. +.. [#] For the new DR6 bits, note that bit 16 is set iff the #DB exception + will clear DR6.RTM. 7.18 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 -Architectures: x86, arm, arm64, mips -Parameters: args[0] whether feature should be enabled or not +:Architectures: x86, arm, arm64, mips +:Parameters: args[0] whether feature should be enabled or not With this capability enabled, KVM_GET_DIRTY_LOG will not automatically clear and write-protect all pages that are returned as dirty. @@ -5181,14 +5732,15 @@ KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 signals that those bugs are fixed. Userspace should not try to use KVM_CAP_MANUAL_DIRTY_LOG_PROTECT. 8. Other capabilities. ----------------------- +====================== This section lists capabilities that give information about other features of the KVM implementation. 8.1 KVM_CAP_PPC_HWRNG +--------------------- -Architectures: ppc +:Architectures: ppc This capability, if KVM_CHECK_EXTENSION indicates that it is available, means that that the kernel has an implementation of the @@ -5197,8 +5749,10 @@ If present, the kernel H_RANDOM handler can be enabled for guest use with the KVM_CAP_PPC_ENABLE_HCALL capability. 8.2 KVM_CAP_HYPERV_SYNIC +------------------------ + +:Architectures: x86 -Architectures: x86 This capability, if KVM_CHECK_EXTENSION indicates that it is available, means that that the kernel has an implementation of the Hyper-V Synthetic interrupt controller(SynIC). Hyper-V SynIC is @@ -5210,8 +5764,9 @@ will disable the use of APIC hardware virtualization even if supported by the CPU, as it's incompatible with SynIC auto-EOI behavior. 8.3 KVM_CAP_PPC_RADIX_MMU +------------------------- -Architectures: ppc +:Architectures: ppc This capability, if KVM_CHECK_EXTENSION indicates that it is available, means that that the kernel can support guests using the @@ -5219,8 +5774,9 @@ radix MMU defined in Power ISA V3.00 (as implemented in the POWER9 processor). 8.4 KVM_CAP_PPC_HASH_MMU_V3 +--------------------------- -Architectures: ppc +:Architectures: ppc This capability, if KVM_CHECK_EXTENSION indicates that it is available, means that that the kernel can support guests using the @@ -5228,8 +5784,9 @@ hashed page table MMU defined in Power ISA V3.00 (as implemented in the POWER9 processor), including in-memory segment tables. 8.5 KVM_CAP_MIPS_VZ +------------------- -Architectures: mips +:Architectures: mips This capability, if KVM_CHECK_EXTENSION on the main kvm handle indicates that it is available, means that full hardware assisted virtualization capabilities @@ -5247,16 +5804,19 @@ values (see below). All other values are reserved. This is to allow for the possibility of other hardware assisted virtualization implementations which may be incompatible with the MIPS VZ ASE. - 0: The trap & emulate implementation is in use to run guest code in user +== ========================================================================== + 0 The trap & emulate implementation is in use to run guest code in user mode. Guest virtual memory segments are rearranged to fit the guest in the user mode address space. - 1: The MIPS VZ ASE is in use, providing full hardware assisted + 1 The MIPS VZ ASE is in use, providing full hardware assisted virtualization, including standard guest virtual memory segments. +== ========================================================================== 8.6 KVM_CAP_MIPS_TE +------------------- -Architectures: mips +:Architectures: mips This capability, if KVM_CHECK_EXTENSION on the main kvm handle indicates that it is available, means that the trap & emulate implementation is available to @@ -5268,8 +5828,9 @@ If KVM_CHECK_EXTENSION on a kvm VM handle indicates that this capability is available, it means that the VM is using trap & emulate. 8.7 KVM_CAP_MIPS_64BIT +---------------------- -Architectures: mips +:Architectures: mips This capability indicates the supported architecture type of the guest, i.e. the supported register and address width. @@ -5279,22 +5840,26 @@ kvm VM handle correspond roughly to the CP0_Config.AT register field, and should be checked specifically against known values (see below). All other values are reserved. - 0: MIPS32 or microMIPS32. +== ======================================================================== + 0 MIPS32 or microMIPS32. Both registers and addresses are 32-bits wide. It will only be possible to run 32-bit guest code. - 1: MIPS64 or microMIPS64 with access only to 32-bit compatibility segments. + 1 MIPS64 or microMIPS64 with access only to 32-bit compatibility segments. Registers are 64-bits wide, but addresses are 32-bits wide. 64-bit guest code may run but cannot access MIPS64 memory segments. It will also be possible to run 32-bit guest code. - 2: MIPS64 or microMIPS64 with access to all address segments. + 2 MIPS64 or microMIPS64 with access to all address segments. Both registers and addresses are 64-bits wide. It will be possible to run 64-bit or 32-bit guest code. +== ======================================================================== 8.9 KVM_CAP_ARM_USER_IRQ +------------------------ + +:Architectures: arm, arm64 -Architectures: arm, arm64 This capability, if KVM_CHECK_EXTENSION indicates that it is available, means that if userspace creates a VM without an in-kernel interrupt controller, it will be notified of changes to the output level of in-kernel emulated devices, @@ -5321,7 +5886,7 @@ If KVM_CAP_ARM_USER_IRQ is supported, the KVM_CHECK_EXTENSION ioctl returns a number larger than 0 indicating the version of this capability is implemented and thereby which bits in in run->s.regs.device_irq_level can signal values. -Currently the following bits are defined for the device_irq_level bitmap: +Currently the following bits are defined for the device_irq_level bitmap:: KVM_CAP_ARM_USER_IRQ >= 1: @@ -5334,8 +5899,9 @@ indicated by returning a higher number from KVM_CHECK_EXTENSION and will be listed above. 8.10 KVM_CAP_PPC_SMT_POSSIBLE +----------------------------- -Architectures: ppc +:Architectures: ppc Querying this capability returns a bitmap indicating the possible virtual SMT modes that can be set using KVM_CAP_PPC_SMT. If bit N @@ -5343,8 +5909,9 @@ virtual SMT modes that can be set using KVM_CAP_PPC_SMT. If bit N available. 8.11 KVM_CAP_HYPERV_SYNIC2 +-------------------------- -Architectures: x86 +:Architectures: x86 This capability enables a newer version of Hyper-V Synthetic interrupt controller (SynIC). The only difference with KVM_CAP_HYPERV_SYNIC is that KVM @@ -5352,8 +5919,9 @@ doesn't clear SynIC message and event flags pages when they are enabled by writing to the respective MSRs. 8.12 KVM_CAP_HYPERV_VP_INDEX +---------------------------- -Architectures: x86 +:Architectures: x86 This capability indicates that userspace can load HV_X64_MSR_VP_INDEX msr. Its value is used to denote the target vcpu for a SynIC interrupt. For @@ -5361,47 +5929,53 @@ compatibilty, KVM initializes this msr to KVM's internal vcpu index. When this capability is absent, userspace can still query this msr's value. 8.13 KVM_CAP_S390_AIS_MIGRATION +------------------------------- -Architectures: s390 -Parameters: none +:Architectures: s390 +:Parameters: none This capability indicates if the flic device will be able to get/set the AIS states for migration via the KVM_DEV_FLIC_AISM_ALL attribute and allows to discover this without having to create a flic device. 8.14 KVM_CAP_S390_PSW +--------------------- -Architectures: s390 +:Architectures: s390 This capability indicates that the PSW is exposed via the kvm_run structure. 8.15 KVM_CAP_S390_GMAP +---------------------- -Architectures: s390 +:Architectures: s390 This capability indicates that the user space memory used as guest mapping can be anywhere in the user memory address space, as long as the memory slots are aligned and sized to a segment (1MB) boundary. 8.16 KVM_CAP_S390_COW +--------------------- -Architectures: s390 +:Architectures: s390 This capability indicates that the user space memory used as guest mapping can use copy-on-write semantics as well as dirty pages tracking via read-only page tables. 8.17 KVM_CAP_S390_BPB +--------------------- -Architectures: s390 +:Architectures: s390 This capability indicates that kvm will implement the interfaces to handle reset, migration and nested KVM for branch prediction blocking. The stfle facility 82 should not be provided to the guest without this capability. 8.18 KVM_CAP_HYPERV_TLBFLUSH +---------------------------- -Architectures: x86 +:Architectures: x86 This capability indicates that KVM supports paravirtualized Hyper-V TLB Flush hypercalls: @@ -5409,8 +5983,9 @@ HvFlushVirtualAddressSpace, HvFlushVirtualAddressSpaceEx, HvFlushVirtualAddressList, HvFlushVirtualAddressListEx. 8.19 KVM_CAP_ARM_INJECT_SERROR_ESR +---------------------------------- -Architectures: arm, arm64 +:Architectures: arm, arm64 This capability indicates that userspace can specify (via the KVM_SET_VCPU_EVENTS ioctl) the syndrome value reported to the guest when it @@ -5421,16 +5996,20 @@ CPU when the exception is taken. If this virtual SError is taken to EL1 using AArch64, this value will be reported in the ISS field of ESR_ELx. See KVM_CAP_VCPU_EVENTS for more details. + 8.20 KVM_CAP_HYPERV_SEND_IPI +---------------------------- -Architectures: x86 +:Architectures: x86 This capability indicates that KVM supports paravirtualized Hyper-V IPI send hypercalls: HvCallSendSyntheticClusterIpi, HvCallSendSyntheticClusterIpiEx. + 8.21 KVM_CAP_HYPERV_DIRECT_TLBFLUSH +----------------------------------- -Architecture: x86 +:Architecture: x86 This capability indicates that KVM running on top of Hyper-V hypervisor enables Direct TLB flush for its guests meaning that TLB flush diff --git a/Documentation/virt/kvm/arm/hyp-abi.txt b/Documentation/virt/kvm/arm/hyp-abi.rst similarity index 79% rename from Documentation/virt/kvm/arm/hyp-abi.txt rename to Documentation/virt/kvm/arm/hyp-abi.rst index a20a0bee268d3c3b834f71dc8956d57d27718adf..d1fc27d848e95d75ec5bada94d93f924fdf4c70c 100644 --- a/Documentation/virt/kvm/arm/hyp-abi.txt +++ b/Documentation/virt/kvm/arm/hyp-abi.rst @@ -1,4 +1,8 @@ -* Internal ABI between the kernel and HYP +.. SPDX-License-Identifier: GPL-2.0 + +======================================= +Internal ABI between the kernel and HYP +======================================= This file documents the interaction between the Linux kernel and the hypervisor layer when running Linux as a hypervisor (for example @@ -19,25 +23,31 @@ and only act on individual CPUs. Unless specified otherwise, any built-in hypervisor must implement these functions (see arch/arm{,64}/include/asm/virt.h): -* r0/x0 = HVC_SET_VECTORS - r1/x1 = vectors +* :: + + r0/x0 = HVC_SET_VECTORS + r1/x1 = vectors Set HVBAR/VBAR_EL2 to 'vectors' to enable a hypervisor. 'vectors' must be a physical address, and respect the alignment requirements of the architecture. Only implemented by the initial stubs, not by Linux hypervisors. -* r0/x0 = HVC_RESET_VECTORS +* :: + + r0/x0 = HVC_RESET_VECTORS Turn HYP/EL2 MMU off, and reset HVBAR/VBAR_EL2 to the initials stubs' exception vector value. This effectively disables an existing hypervisor. -* r0/x0 = HVC_SOFT_RESTART - r1/x1 = restart address - x2 = x0's value when entering the next payload (arm64) - x3 = x1's value when entering the next payload (arm64) - x4 = x2's value when entering the next payload (arm64) +* :: + + r0/x0 = HVC_SOFT_RESTART + r1/x1 = restart address + x2 = x0's value when entering the next payload (arm64) + x3 = x1's value when entering the next payload (arm64) + x4 = x2's value when entering the next payload (arm64) Mask all exceptions, disable the MMU, move the arguments into place (arm64 only), and jump to the restart address while at HYP/EL2. This diff --git a/Documentation/virt/kvm/arm/index.rst b/Documentation/virt/kvm/arm/index.rst new file mode 100644 index 0000000000000000000000000000000000000000..3e2b2aba90fcc114c5cd96a2ea1f75fe5bb3021b --- /dev/null +++ b/Documentation/virt/kvm/arm/index.rst @@ -0,0 +1,12 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=== +ARM +=== + +.. toctree:: + :maxdepth: 2 + + hyp-abi + psci + pvtime diff --git a/Documentation/virt/kvm/arm/psci.txt b/Documentation/virt/kvm/arm/psci.rst similarity index 60% rename from Documentation/virt/kvm/arm/psci.txt rename to Documentation/virt/kvm/arm/psci.rst index 559586fc9d379921c98a87841792055c15573082..d52c2e83b5b8d16c15c1431605f54c91d2d82a10 100644 --- a/Documentation/virt/kvm/arm/psci.txt +++ b/Documentation/virt/kvm/arm/psci.rst @@ -1,3 +1,9 @@ +.. SPDX-License-Identifier: GPL-2.0 + +========================================= +Power State Coordination Interface (PSCI) +========================================= + KVM implements the PSCI (Power State Coordination Interface) specification in order to provide services such as CPU on/off, reset and power-off to the guest. @@ -30,32 +36,42 @@ The following register is defined: - Affects the whole VM (even if the register view is per-vcpu) * KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: - Holds the state of the firmware support to mitigate CVE-2017-5715, as - offered by KVM to the guest via a HVC call. The workaround is described - under SMCCC_ARCH_WORKAROUND_1 in [1]. + Holds the state of the firmware support to mitigate CVE-2017-5715, as + offered by KVM to the guest via a HVC call. The workaround is described + under SMCCC_ARCH_WORKAROUND_1 in [1]. + Accepted values are: - KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL: KVM does not offer + + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL: + KVM does not offer firmware support for the workaround. The mitigation status for the guest is unknown. - KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL: The workaround HVC call is + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL: + The workaround HVC call is available to the guest and required for the mitigation. - KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED: The workaround HVC call + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED: + The workaround HVC call is available to the guest, but it is not needed on this VCPU. * KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: - Holds the state of the firmware support to mitigate CVE-2018-3639, as - offered by KVM to the guest via a HVC call. The workaround is described - under SMCCC_ARCH_WORKAROUND_2 in [1]. + Holds the state of the firmware support to mitigate CVE-2018-3639, as + offered by KVM to the guest via a HVC call. The workaround is described + under SMCCC_ARCH_WORKAROUND_2 in [1]_. + Accepted values are: - KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL: A workaround is not + + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL: + A workaround is not available. KVM does not offer firmware support for the workaround. - KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN: The workaround state is + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN: + The workaround state is unknown. KVM does not offer firmware support for the workaround. - KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL: The workaround is available, + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL: + The workaround is available, and can be disabled by a vCPU. If KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED is set, it is active for this vCPU. - KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED: The workaround is - always active on this vCPU or it is not needed. + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED: + The workaround is always active on this vCPU or it is not needed. -[1] https://developer.arm.com/-/media/developer/pdf/ARM_DEN_0070A_Firmware_interfaces_for_mitigating_CVE-2017-5715.pdf +.. [1] https://developer.arm.com/-/media/developer/pdf/ARM_DEN_0070A_Firmware_interfaces_for_mitigating_CVE-2017-5715.pdf diff --git a/Documentation/virt/kvm/devices/arm-vgic-its.txt b/Documentation/virt/kvm/devices/arm-vgic-its.rst similarity index 71% rename from Documentation/virt/kvm/devices/arm-vgic-its.txt rename to Documentation/virt/kvm/devices/arm-vgic-its.rst index eeaa95b893a89b7a94f66ad7750b88de69090ccc..6c304fd2b1b488a786a213944fb9846d8c191e52 100644 --- a/Documentation/virt/kvm/devices/arm-vgic-its.txt +++ b/Documentation/virt/kvm/devices/arm-vgic-its.rst @@ -1,3 +1,6 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=============================================== ARM Virtual Interrupt Translation Service (ITS) =============================================== @@ -12,22 +15,32 @@ There can be multiple ITS controllers per guest, each of them has to have a separate, non-overlapping MMIO region. -Groups: - KVM_DEV_ARM_VGIC_GRP_ADDR +Groups +====== + +KVM_DEV_ARM_VGIC_GRP_ADDR +------------------------- + Attributes: KVM_VGIC_ITS_ADDR_TYPE (rw, 64-bit) Base address in the guest physical address space of the GICv3 ITS control register frame. This address needs to be 64K aligned and the region covers 128K. + Errors: - -E2BIG: Address outside of addressable IPA range - -EINVAL: Incorrectly aligned address - -EEXIST: Address already configured - -EFAULT: Invalid user pointer for attr->addr. - -ENODEV: Incorrect attribute or the ITS is not supported. + ======= ================================================= + -E2BIG Address outside of addressable IPA range + -EINVAL Incorrectly aligned address + -EEXIST Address already configured + -EFAULT Invalid user pointer for attr->addr. + -ENODEV Incorrect attribute or the ITS is not supported. + ======= ================================================= + + +KVM_DEV_ARM_VGIC_GRP_CTRL +------------------------- - KVM_DEV_ARM_VGIC_GRP_CTRL Attributes: KVM_DEV_ARM_VGIC_CTRL_INIT request the initialization of the ITS, no additional parameter in @@ -58,16 +71,21 @@ Groups: "ITS Restore Sequence". Errors: - -ENXIO: ITS not properly configured as required prior to setting + + ======= ========================================================== + -ENXIO ITS not properly configured as required prior to setting this attribute - -ENOMEM: Memory shortage when allocating ITS internal data - -EINVAL: Inconsistent restored data - -EFAULT: Invalid guest ram access - -EBUSY: One or more VCPUS are running - -EACCES: The virtual ITS is backed by a physical GICv4 ITS, and the + -ENOMEM Memory shortage when allocating ITS internal data + -EINVAL Inconsistent restored data + -EFAULT Invalid guest ram access + -EBUSY One or more VCPUS are running + -EACCES The virtual ITS is backed by a physical GICv4 ITS, and the state is not available + ======= ========================================================== + +KVM_DEV_ARM_VGIC_GRP_ITS_REGS +----------------------------- - KVM_DEV_ARM_VGIC_GRP_ITS_REGS Attributes: The attr field of kvm_device_attr encodes the offset of the ITS register, relative to the ITS control frame base address @@ -78,6 +96,7 @@ Groups: be accessed with full length. Writes to read-only registers are ignored by the kernel except for: + - GITS_CREADR. It must be restored otherwise commands in the queue will be re-executed after restoring CWRITER. GITS_CREADR must be restored before restoring the GITS_CTLR which is likely to enable the @@ -91,30 +110,36 @@ Groups: For other registers, getting or setting a register has the same effect as reading/writing the register on real hardware. + Errors: - -ENXIO: Offset does not correspond to any supported register - -EFAULT: Invalid user pointer for attr->addr - -EINVAL: Offset is not 64-bit aligned - -EBUSY: one or more VCPUS are running - ITS Restore Sequence: - ------------------------- + ======= ==================================================== + -ENXIO Offset does not correspond to any supported register + -EFAULT Invalid user pointer for attr->addr + -EINVAL Offset is not 64-bit aligned + -EBUSY one or more VCPUS are running + ======= ==================================================== + +ITS Restore Sequence: +--------------------- The following ordering must be followed when restoring the GIC and the ITS: + a) restore all guest memory and create vcpus b) restore all redistributors c) provide the ITS base address (KVM_DEV_ARM_VGIC_GRP_ADDR) d) restore the ITS in the following order: - 1. Restore GITS_CBASER - 2. Restore all other GITS_ registers, except GITS_CTLR! - 3. Load the ITS table data (KVM_DEV_ARM_ITS_RESTORE_TABLES) - 4. Restore GITS_CTLR + + 1. Restore GITS_CBASER + 2. Restore all other ``GITS_`` registers, except GITS_CTLR! + 3. Load the ITS table data (KVM_DEV_ARM_ITS_RESTORE_TABLES) + 4. Restore GITS_CTLR Then vcpus can be started. - ITS Table ABI REV0: - ------------------- +ITS Table ABI REV0: +------------------- Revision 0 of the ABI only supports the features of a virtual GICv3, and does not support a virtual GICv4 with support for direct injection of virtual @@ -125,12 +150,13 @@ Then vcpus can be started. entries in the collection are listed in no particular order. All entries are 8 bytes. - Device Table Entry (DTE): + Device Table Entry (DTE):: - bits: | 63| 62 ... 49 | 48 ... 5 | 4 ... 0 | - values: | V | next | ITT_addr | Size | + bits: | 63| 62 ... 49 | 48 ... 5 | 4 ... 0 | + values: | V | next | ITT_addr | Size | + + where: - where; - V indicates whether the entry is valid. If not, other fields are not meaningful. - next: equals to 0 if this entry is the last one; otherwise it @@ -140,32 +166,34 @@ Then vcpus can be started. - Size specifies the supported number of bits for the EventID, minus one - Collection Table Entry (CTE): + Collection Table Entry (CTE):: - bits: | 63| 62 .. 52 | 51 ... 16 | 15 ... 0 | - values: | V | RES0 | RDBase | ICID | + bits: | 63| 62 .. 52 | 51 ... 16 | 15 ... 0 | + values: | V | RES0 | RDBase | ICID | where: + - V indicates whether the entry is valid. If not, other fields are not meaningful. - RES0: reserved field with Should-Be-Zero-or-Preserved behavior. - RDBase is the PE number (GICR_TYPER.Processor_Number semantic), - ICID is the collection ID - Interrupt Translation Entry (ITE): + Interrupt Translation Entry (ITE):: - bits: | 63 ... 48 | 47 ... 16 | 15 ... 0 | - values: | next | pINTID | ICID | + bits: | 63 ... 48 | 47 ... 16 | 15 ... 0 | + values: | next | pINTID | ICID | where: + - next: equals to 0 if this entry is the last one; otherwise it corresponds to the EventID offset to the next ITE capped by 2^16 -1. - pINTID is the physical LPI ID; if zero, it means the entry is not valid and other fields are not meaningful. - ICID is the collection ID - ITS Reset State: - ---------------- +ITS Reset State: +---------------- RESET returns the ITS to the same state that it was when first created and initialized. When the RESET command returns, the following things are diff --git a/Documentation/virt/kvm/devices/arm-vgic-v3.txt b/Documentation/virt/kvm/devices/arm-vgic-v3.rst similarity index 77% rename from Documentation/virt/kvm/devices/arm-vgic-v3.txt rename to Documentation/virt/kvm/devices/arm-vgic-v3.rst index ff290b43c8e513175990d76337653299f87d7a93..5dd3bff519783c36381877cca0c27286ec2b9c01 100644 --- a/Documentation/virt/kvm/devices/arm-vgic-v3.txt +++ b/Documentation/virt/kvm/devices/arm-vgic-v3.rst @@ -1,9 +1,12 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============================================================== ARM Virtual Generic Interrupt Controller v3 and later (VGICv3) ============================================================== Device types supported: - KVM_DEV_TYPE_ARM_VGIC_V3 ARM Generic Interrupt Controller v3.0 + - KVM_DEV_TYPE_ARM_VGIC_V3 ARM Generic Interrupt Controller v3.0 Only one VGIC instance may be instantiated through this API. The created VGIC will act as the VM interrupt controller, requiring emulated user-space devices @@ -15,7 +18,8 @@ Creating a guest GICv3 device requires a host GICv3 as well. Groups: KVM_DEV_ARM_VGIC_GRP_ADDR - Attributes: + Attributes: + KVM_VGIC_V3_ADDR_TYPE_DIST (rw, 64-bit) Base address in the guest physical address space of the GICv3 distributor register mappings. Only valid for KVM_DEV_TYPE_ARM_VGIC_V3. @@ -29,21 +33,25 @@ Groups: This address needs to be 64K aligned. KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION (rw, 64-bit) - The attribute data pointed to by kvm_device_attr.addr is a __u64 value: - bits: | 63 .... 52 | 51 .... 16 | 15 - 12 |11 - 0 - values: | count | base | flags | index + The attribute data pointed to by kvm_device_attr.addr is a __u64 value:: + + bits: | 63 .... 52 | 51 .... 16 | 15 - 12 |11 - 0 + values: | count | base | flags | index + - index encodes the unique redistributor region index - flags: reserved for future use, currently 0 - base field encodes bits [51:16] of the guest physical base address of the first redistributor in the region. - count encodes the number of redistributors in the region. Must be greater than 0. + There are two 64K pages for each redistributor in the region and redistributors are laid out contiguously within the region. Regions are filled with redistributors in the index order. The sum of all region count fields must be greater than or equal to the number of VCPUs. Redistributor regions must be registered in the incremental index order, starting from index 0. + The characteristics of a specific redistributor region can be read by presetting the index field in the attr data. Only valid for KVM_DEV_TYPE_ARM_VGIC_V3. @@ -52,23 +60,27 @@ Groups: KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION attributes. Errors: - -E2BIG: Address outside of addressable IPA range - -EINVAL: Incorrectly aligned address, bad redistributor region + + ======= ============================================================= + -E2BIG Address outside of addressable IPA range + -EINVAL Incorrectly aligned address, bad redistributor region count/index, mixed redistributor region attribute usage - -EEXIST: Address already configured - -ENOENT: Attempt to read the characteristics of a non existing + -EEXIST Address already configured + -ENOENT Attempt to read the characteristics of a non existing redistributor region - -ENXIO: The group or attribute is unknown/unsupported for this device + -ENXIO The group or attribute is unknown/unsupported for this device or hardware support is missing. - -EFAULT: Invalid user pointer for attr->addr. + -EFAULT Invalid user pointer for attr->addr. + ======= ============================================================= + + KVM_DEV_ARM_VGIC_GRP_DIST_REGS, KVM_DEV_ARM_VGIC_GRP_REDIST_REGS + Attributes: - KVM_DEV_ARM_VGIC_GRP_DIST_REGS - KVM_DEV_ARM_VGIC_GRP_REDIST_REGS - Attributes: - The attr field of kvm_device_attr encodes two values: - bits: | 63 .... 32 | 31 .... 0 | - values: | mpidr | offset | + The attr field of kvm_device_attr encodes two values:: + + bits: | 63 .... 32 | 31 .... 0 | + values: | mpidr | offset | All distributor regs are (rw, 32-bit) and kvm_device_attr.addr points to a __u32 value. 64-bit registers must be accessed by separately accessing the @@ -93,7 +105,8 @@ Groups: redistributor is accessed. The mpidr is ignored for the distributor. The mpidr encoding is based on the affinity information in the - architecture defined MPIDR, and the field is encoded as follows: + architecture defined MPIDR, and the field is encoded as follows:: + | 63 .... 56 | 55 .... 48 | 47 .... 40 | 39 .... 32 | | Aff3 | Aff2 | Aff1 | Aff0 | @@ -148,24 +161,30 @@ Groups: ignored. Errors: - -ENXIO: Getting or setting this register is not yet supported - -EBUSY: One or more VCPUs are running + + ====== ===================================================== + -ENXIO Getting or setting this register is not yet supported + -EBUSY One or more VCPUs are running + ====== ===================================================== KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS - Attributes: - The attr field of kvm_device_attr encodes two values: - bits: | 63 .... 32 | 31 .... 16 | 15 .... 0 | - values: | mpidr | RES | instr | + Attributes: + + The attr field of kvm_device_attr encodes two values:: + + bits: | 63 .... 32 | 31 .... 16 | 15 .... 0 | + values: | mpidr | RES | instr | The mpidr field encodes the CPU ID based on the affinity information in the - architecture defined MPIDR, and the field is encoded as follows: + architecture defined MPIDR, and the field is encoded as follows:: + | 63 .... 56 | 55 .... 48 | 47 .... 40 | 39 .... 32 | | Aff3 | Aff2 | Aff1 | Aff0 | The instr field encodes the system register to access based on the fields defined in the A64 instruction set encoding for system register access - (RES means the bits are reserved for future use and should be zero): + (RES means the bits are reserved for future use and should be zero):: | 15 ... 14 | 13 ... 11 | 10 ... 7 | 6 ... 3 | 2 ... 0 | | Op 0 | Op1 | CRn | CRm | Op2 | @@ -178,26 +197,35 @@ Groups: CPU interface registers access is not implemented for AArch32 mode. Error -ENXIO is returned when accessed in AArch32 mode. + Errors: - -ENXIO: Getting or setting this register is not yet supported - -EBUSY: VCPU is running - -EINVAL: Invalid mpidr or register value supplied + + ======= ===================================================== + -ENXIO Getting or setting this register is not yet supported + -EBUSY VCPU is running + -EINVAL Invalid mpidr or register value supplied + ======= ===================================================== KVM_DEV_ARM_VGIC_GRP_NR_IRQS - Attributes: + Attributes: + A value describing the number of interrupts (SGI, PPI and SPI) for this GIC instance, ranging from 64 to 1024, in increments of 32. kvm_device_attr.addr points to a __u32 value. Errors: - -EINVAL: Value set is out of the expected range - -EBUSY: Value has already be set. + + ======= ====================================== + -EINVAL Value set is out of the expected range + -EBUSY Value has already be set. + ======= ====================================== KVM_DEV_ARM_VGIC_GRP_CTRL - Attributes: + Attributes: + KVM_DEV_ARM_VGIC_CTRL_INIT request the initialization of the VGIC, no additional parameter in kvm_device_attr.addr. @@ -205,20 +233,26 @@ Groups: save all LPI pending bits into guest RAM pending tables. The first kB of the pending table is not altered by this operation. + Errors: - -ENXIO: VGIC not properly configured as required prior to calling - this attribute - -ENODEV: no online VCPU - -ENOMEM: memory shortage when allocating vgic internal data - -EFAULT: Invalid guest ram access - -EBUSY: One or more VCPUS are running + + ======= ======================================================== + -ENXIO VGIC not properly configured as required prior to calling + this attribute + -ENODEV no online VCPU + -ENOMEM memory shortage when allocating vgic internal data + -EFAULT Invalid guest ram access + -EBUSY One or more VCPUS are running + ======= ======================================================== KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO - Attributes: - The attr field of kvm_device_attr encodes the following values: - bits: | 63 .... 32 | 31 .... 10 | 9 .... 0 | - values: | mpidr | info | vINTID | + Attributes: + + The attr field of kvm_device_attr encodes the following values:: + + bits: | 63 .... 32 | 31 .... 10 | 9 .... 0 | + values: | mpidr | info | vINTID | The vINTID specifies which set of IRQs is reported on. @@ -228,6 +262,7 @@ Groups: VGIC_LEVEL_INFO_LINE_LEVEL: Get/Set the input level of the IRQ line for a set of 32 contiguously numbered interrupts. + vINTID must be a multiple of 32. kvm_device_attr.addr points to a __u32 value which will contain a @@ -243,9 +278,14 @@ Groups: reported with the same value regardless of the mpidr specified. The mpidr field encodes the CPU ID based on the affinity information in the - architecture defined MPIDR, and the field is encoded as follows: + architecture defined MPIDR, and the field is encoded as follows:: + | 63 .... 56 | 55 .... 48 | 47 .... 40 | 39 .... 32 | | Aff3 | Aff2 | Aff1 | Aff0 | + Errors: - -EINVAL: vINTID is not multiple of 32 or - info field is not VGIC_LEVEL_INFO_LINE_LEVEL + + ======= ============================================= + -EINVAL vINTID is not multiple of 32 or info field is + not VGIC_LEVEL_INFO_LINE_LEVEL + ======= ============================================= diff --git a/Documentation/virt/kvm/devices/arm-vgic.txt b/Documentation/virt/kvm/devices/arm-vgic.rst similarity index 66% rename from Documentation/virt/kvm/devices/arm-vgic.txt rename to Documentation/virt/kvm/devices/arm-vgic.rst index 97b6518148f87befcc2dab5fb250459607154525..40bdeea1d86e75b9b912f893ff8bf95b892cf839 100644 --- a/Documentation/virt/kvm/devices/arm-vgic.txt +++ b/Documentation/virt/kvm/devices/arm-vgic.rst @@ -1,8 +1,12 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================================================== ARM Virtual Generic Interrupt Controller v2 (VGIC) ================================================== Device types supported: - KVM_DEV_TYPE_ARM_VGIC_V2 ARM Generic Interrupt Controller v2.0 + + - KVM_DEV_TYPE_ARM_VGIC_V2 ARM Generic Interrupt Controller v2.0 Only one VGIC instance may be instantiated through either this API or the legacy KVM_CREATE_IRQCHIP API. The created VGIC will act as the VM interrupt @@ -17,7 +21,8 @@ create both a GICv3 and GICv2 device on the same VM. Groups: KVM_DEV_ARM_VGIC_GRP_ADDR - Attributes: + Attributes: + KVM_VGIC_V2_ADDR_TYPE_DIST (rw, 64-bit) Base address in the guest physical address space of the GIC distributor register mappings. Only valid for KVM_DEV_TYPE_ARM_VGIC_V2. @@ -27,19 +32,25 @@ Groups: Base address in the guest physical address space of the GIC virtual cpu interface register mappings. Only valid for KVM_DEV_TYPE_ARM_VGIC_V2. This address needs to be 4K aligned and the region covers 4 KByte. + Errors: - -E2BIG: Address outside of addressable IPA range - -EINVAL: Incorrectly aligned address - -EEXIST: Address already configured - -ENXIO: The group or attribute is unknown/unsupported for this device + + ======= ============================================================= + -E2BIG Address outside of addressable IPA range + -EINVAL Incorrectly aligned address + -EEXIST Address already configured + -ENXIO The group or attribute is unknown/unsupported for this device or hardware support is missing. - -EFAULT: Invalid user pointer for attr->addr. + -EFAULT Invalid user pointer for attr->addr. + ======= ============================================================= KVM_DEV_ARM_VGIC_GRP_DIST_REGS - Attributes: - The attr field of kvm_device_attr encodes two values: - bits: | 63 .... 40 | 39 .. 32 | 31 .... 0 | - values: | reserved | vcpu_index | offset | + Attributes: + + The attr field of kvm_device_attr encodes two values:: + + bits: | 63 .... 40 | 39 .. 32 | 31 .... 0 | + values: | reserved | vcpu_index | offset | All distributor regs are (rw, 32-bit) @@ -58,16 +69,22 @@ Groups: KVM_DEV_ARM_VGIC_GRP_DIST_REGS and KVM_DEV_ARM_VGIC_GRP_CPU_REGS) to ensure the expected behavior. Unless GICD_IIDR has been set from userspace, writes to the interrupt group registers (GICD_IGROUPR) are ignored. + Errors: - -ENXIO: Getting or setting this register is not yet supported - -EBUSY: One or more VCPUs are running - -EINVAL: Invalid vcpu_index supplied + + ======= ===================================================== + -ENXIO Getting or setting this register is not yet supported + -EBUSY One or more VCPUs are running + -EINVAL Invalid vcpu_index supplied + ======= ===================================================== KVM_DEV_ARM_VGIC_GRP_CPU_REGS - Attributes: - The attr field of kvm_device_attr encodes two values: - bits: | 63 .... 40 | 39 .. 32 | 31 .... 0 | - values: | reserved | vcpu_index | offset | + Attributes: + + The attr field of kvm_device_attr encodes two values:: + + bits: | 63 .... 40 | 39 .. 32 | 31 .... 0 | + values: | reserved | vcpu_index | offset | All CPU interface regs are (rw, 32-bit) @@ -101,27 +118,39 @@ Groups: value left by 3 places to obtain the actual priority mask level. Errors: - -ENXIO: Getting or setting this register is not yet supported - -EBUSY: One or more VCPUs are running - -EINVAL: Invalid vcpu_index supplied + + ======= ===================================================== + -ENXIO Getting or setting this register is not yet supported + -EBUSY One or more VCPUs are running + -EINVAL Invalid vcpu_index supplied + ======= ===================================================== KVM_DEV_ARM_VGIC_GRP_NR_IRQS - Attributes: + Attributes: + A value describing the number of interrupts (SGI, PPI and SPI) for this GIC instance, ranging from 64 to 1024, in increments of 32. Errors: - -EINVAL: Value set is out of the expected range - -EBUSY: Value has already be set, or GIC has already been initialized - with default values. + + ======= ============================================================= + -EINVAL Value set is out of the expected range + -EBUSY Value has already be set, or GIC has already been initialized + with default values. + ======= ============================================================= KVM_DEV_ARM_VGIC_GRP_CTRL - Attributes: + Attributes: + KVM_DEV_ARM_VGIC_CTRL_INIT request the initialization of the VGIC or ITS, no additional parameter in kvm_device_attr.addr. + Errors: - -ENXIO: VGIC not properly configured as required prior to calling - this attribute - -ENODEV: no online VCPU - -ENOMEM: memory shortage when allocating vgic internal data + + ======= ========================================================= + -ENXIO VGIC not properly configured as required prior to calling + this attribute + -ENODEV no online VCPU + -ENOMEM memory shortage when allocating vgic internal data + ======= ========================================================= diff --git a/Documentation/virt/kvm/devices/index.rst b/Documentation/virt/kvm/devices/index.rst new file mode 100644 index 0000000000000000000000000000000000000000..192cda7405c841f38c29987fa694b256c7923a41 --- /dev/null +++ b/Documentation/virt/kvm/devices/index.rst @@ -0,0 +1,19 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======= +Devices +======= + +.. toctree:: + :maxdepth: 2 + + arm-vgic-its + arm-vgic + arm-vgic-v3 + mpic + s390_flic + vcpu + vfio + vm + xics + xive diff --git a/Documentation/virt/kvm/devices/mpic.txt b/Documentation/virt/kvm/devices/mpic.rst similarity index 91% rename from Documentation/virt/kvm/devices/mpic.txt rename to Documentation/virt/kvm/devices/mpic.rst index 8257397adc3cc18a0733f58ee7c5b8a89bb0dfbe..55cefe030d41471e20c967adf076d71d13127720 100644 --- a/Documentation/virt/kvm/devices/mpic.txt +++ b/Documentation/virt/kvm/devices/mpic.rst @@ -1,9 +1,13 @@ +.. SPDX-License-Identifier: GPL-2.0 + +========================= MPIC interrupt controller ========================= Device types supported: - KVM_DEV_TYPE_FSL_MPIC_20 Freescale MPIC v2.0 - KVM_DEV_TYPE_FSL_MPIC_42 Freescale MPIC v4.2 + + - KVM_DEV_TYPE_FSL_MPIC_20 Freescale MPIC v2.0 + - KVM_DEV_TYPE_FSL_MPIC_42 Freescale MPIC v4.2 Only one MPIC instance, of any type, may be instantiated. The created MPIC will act as the system interrupt controller, connecting to each @@ -11,7 +15,8 @@ vcpu's interrupt inputs. Groups: KVM_DEV_MPIC_GRP_MISC - Attributes: + Attributes: + KVM_DEV_MPIC_BASE_ADDR (rw, 64-bit) Base address of the 256 KiB MPIC register space. Must be naturally aligned. A value of zero disables the mapping. diff --git a/Documentation/virt/kvm/devices/s390_flic.txt b/Documentation/virt/kvm/devices/s390_flic.rst similarity index 87% rename from Documentation/virt/kvm/devices/s390_flic.txt rename to Documentation/virt/kvm/devices/s390_flic.rst index a4e20a09017468b2e5a97e7782ad74aab1431de5..954190da7d0413a9ff3b9a6a3f8c5c29760c743e 100644 --- a/Documentation/virt/kvm/devices/s390_flic.txt +++ b/Documentation/virt/kvm/devices/s390_flic.rst @@ -1,3 +1,6 @@ +.. SPDX-License-Identifier: GPL-2.0 + +==================================== FLIC (floating interrupt controller) ==================================== @@ -31,8 +34,10 @@ Groups: Copies all floating interrupts into a buffer provided by userspace. When the buffer is too small it returns -ENOMEM, which is the indication for userspace to try again with a bigger buffer. + -ENOBUFS is returned when the allocation of a kernelspace buffer has failed. + -EFAULT is returned when copying data to userspace failed. All interrupts remain pending, i.e. are not deleted from the list of currently pending interrupts. @@ -60,38 +65,41 @@ Groups: KVM_DEV_FLIC_ADAPTER_REGISTER Register an I/O adapter interrupt source. Takes a kvm_s390_io_adapter - describing the adapter to register: + describing the adapter to register:: -struct kvm_s390_io_adapter { - __u32 id; - __u8 isc; - __u8 maskable; - __u8 swap; - __u8 flags; -}; + struct kvm_s390_io_adapter { + __u32 id; + __u8 isc; + __u8 maskable; + __u8 swap; + __u8 flags; + }; id contains the unique id for the adapter, isc the I/O interruption subclass to use, maskable whether this adapter may be masked (interrupts turned off), swap whether the indicators need to be byte swapped, and flags contains further characteristics of the adapter. + Currently defined values for 'flags' are: + - KVM_S390_ADAPTER_SUPPRESSIBLE: adapter is subject to AIS (adapter-interrupt-suppression) facility. This flag only has an effect if the AIS capability is enabled. + Unknown flag values are ignored. KVM_DEV_FLIC_ADAPTER_MODIFY Modifies attributes of an existing I/O adapter interrupt source. Takes - a kvm_s390_io_adapter_req specifying the adapter and the operation: + a kvm_s390_io_adapter_req specifying the adapter and the operation:: -struct kvm_s390_io_adapter_req { - __u32 id; - __u8 type; - __u8 mask; - __u16 pad0; - __u64 addr; -}; + struct kvm_s390_io_adapter_req { + __u32 id; + __u8 type; + __u8 mask; + __u16 pad0; + __u64 addr; + }; id specifies the adapter and type the operation. The supported operations are: @@ -103,8 +111,9 @@ struct kvm_s390_io_adapter_req { perform a gmap translation for the guest address provided in addr, pin a userspace page for the translated address and add it to the list of mappings - Note: A new mapping will be created unconditionally; therefore, - the calling code should avoid making duplicate mappings. + + .. note:: A new mapping will be created unconditionally; therefore, + the calling code should avoid making duplicate mappings. KVM_S390_IO_ADAPTER_UNMAP release a userspace page for the translated address specified in addr @@ -112,16 +121,17 @@ struct kvm_s390_io_adapter_req { KVM_DEV_FLIC_AISM modify the adapter-interruption-suppression mode for a given isc if the - AIS capability is enabled. Takes a kvm_s390_ais_req describing: + AIS capability is enabled. Takes a kvm_s390_ais_req describing:: -struct kvm_s390_ais_req { - __u8 isc; - __u16 mode; -}; + struct kvm_s390_ais_req { + __u8 isc; + __u16 mode; + }; isc contains the target I/O interruption subclass, mode the target adapter-interruption-suppression mode. The following modes are currently supported: + - KVM_S390_AIS_MODE_ALL: ALL-Interruptions Mode, i.e. airq injection is always allowed; - KVM_S390_AIS_MODE_SINGLE: SINGLE-Interruption Mode, i.e. airq @@ -139,12 +149,12 @@ struct kvm_s390_ais_req { KVM_DEV_FLIC_AISM_ALL Gets or sets the adapter-interruption-suppression mode for all ISCs. Takes - a kvm_s390_ais_all describing: + a kvm_s390_ais_all describing:: -struct kvm_s390_ais_all { - __u8 simm; /* Single-Interruption-Mode mask */ - __u8 nimm; /* No-Interruption-Mode mask * -}; + struct kvm_s390_ais_all { + __u8 simm; /* Single-Interruption-Mode mask */ + __u8 nimm; /* No-Interruption-Mode mask * + }; simm contains Single-Interruption-Mode mask for all ISCs, nimm contains No-Interruption-Mode mask for all ISCs. Each bit in simm and nimm corresponds @@ -159,5 +169,5 @@ ENXIO, as specified in the API documentation). It is not possible to conclude that a FLIC operation is unavailable based on the error code resulting from a usage attempt. -Note: The KVM_DEV_FLIC_CLEAR_IO_IRQ ioctl will return EINVAL in case a zero -schid is specified. +.. note:: The KVM_DEV_FLIC_CLEAR_IO_IRQ ioctl will return EINVAL in case a + zero schid is specified. diff --git a/Documentation/virt/kvm/devices/vcpu.rst b/Documentation/virt/kvm/devices/vcpu.rst new file mode 100644 index 0000000000000000000000000000000000000000..9963e680770a1a0e0d74e88b3cdd84d24be8c38d --- /dev/null +++ b/Documentation/virt/kvm/devices/vcpu.rst @@ -0,0 +1,114 @@ +.. SPDX-License-Identifier: GPL-2.0 + +====================== +Generic vcpu interface +====================== + +The virtual cpu "device" also accepts the ioctls KVM_SET_DEVICE_ATTR, +KVM_GET_DEVICE_ATTR, and KVM_HAS_DEVICE_ATTR. The interface uses the same struct +kvm_device_attr as other devices, but targets VCPU-wide settings and controls. + +The groups and attributes per virtual cpu, if any, are architecture specific. + +1. GROUP: KVM_ARM_VCPU_PMU_V3_CTRL +================================== + +:Architectures: ARM64 + +1.1. ATTRIBUTE: KVM_ARM_VCPU_PMU_V3_IRQ +--------------------------------------- + +:Parameters: in kvm_device_attr.addr the address for PMU overflow interrupt is a + pointer to an int + +Returns: + + ======= ======================================================== + -EBUSY The PMU overflow interrupt is already set + -ENXIO The overflow interrupt not set when attempting to get it + -ENODEV PMUv3 not supported + -EINVAL Invalid PMU overflow interrupt number supplied or + trying to set the IRQ number without using an in-kernel + irqchip. + ======= ======================================================== + +A value describing the PMUv3 (Performance Monitor Unit v3) overflow interrupt +number for this vcpu. This interrupt could be a PPI or SPI, but the interrupt +type must be same for each vcpu. As a PPI, the interrupt number is the same for +all vcpus, while as an SPI it must be a separate number per vcpu. + +1.2 ATTRIBUTE: KVM_ARM_VCPU_PMU_V3_INIT +--------------------------------------- + +:Parameters: no additional parameter in kvm_device_attr.addr + +Returns: + + ======= ====================================================== + -ENODEV PMUv3 not supported or GIC not initialized + -ENXIO PMUv3 not properly configured or in-kernel irqchip not + configured as required prior to calling this attribute + -EBUSY PMUv3 already initialized + ======= ====================================================== + +Request the initialization of the PMUv3. If using the PMUv3 with an in-kernel +virtual GIC implementation, this must be done after initializing the in-kernel +irqchip. + + +2. GROUP: KVM_ARM_VCPU_TIMER_CTRL +================================= + +:Architectures: ARM, ARM64 + +2.1. ATTRIBUTES: KVM_ARM_VCPU_TIMER_IRQ_VTIMER, KVM_ARM_VCPU_TIMER_IRQ_PTIMER +----------------------------------------------------------------------------- + +:Parameters: in kvm_device_attr.addr the address for the timer interrupt is a + pointer to an int + +Returns: + + ======= ================================= + -EINVAL Invalid timer interrupt number + -EBUSY One or more VCPUs has already run + ======= ================================= + +A value describing the architected timer interrupt number when connected to an +in-kernel virtual GIC. These must be a PPI (16 <= intid < 32). Setting the +attribute overrides the default values (see below). + +============================= ========================================== +KVM_ARM_VCPU_TIMER_IRQ_VTIMER The EL1 virtual timer intid (default: 27) +KVM_ARM_VCPU_TIMER_IRQ_PTIMER The EL1 physical timer intid (default: 30) +============================= ========================================== + +Setting the same PPI for different timers will prevent the VCPUs from running. +Setting the interrupt number on a VCPU configures all VCPUs created at that +time to use the number provided for a given timer, overwriting any previously +configured values on other VCPUs. Userspace should configure the interrupt +numbers on at least one VCPU after creating all VCPUs and before running any +VCPUs. + +3. GROUP: KVM_ARM_VCPU_PVTIME_CTRL +================================== + +:Architectures: ARM64 + +3.1 ATTRIBUTE: KVM_ARM_VCPU_PVTIME_IPA +-------------------------------------- + +:Parameters: 64-bit base address + +Returns: + + ======= ====================================== + -ENXIO Stolen time not implemented + -EEXIST Base address already set for this VCPU + -EINVAL Base address not 64 byte aligned + ======= ====================================== + +Specifies the base address of the stolen time structure for this VCPU. The +base address must be 64 byte aligned and exist within a valid guest memory +region. See Documentation/virt/kvm/arm/pvtime.txt for more information +including the layout of the stolen time structure. diff --git a/Documentation/virt/kvm/devices/vcpu.txt b/Documentation/virt/kvm/devices/vcpu.txt deleted file mode 100644 index 6f3bd64a05b0f432394bffcbfb31ee25a48e3035..0000000000000000000000000000000000000000 --- a/Documentation/virt/kvm/devices/vcpu.txt +++ /dev/null @@ -1,76 +0,0 @@ -Generic vcpu interface -==================================== - -The virtual cpu "device" also accepts the ioctls KVM_SET_DEVICE_ATTR, -KVM_GET_DEVICE_ATTR, and KVM_HAS_DEVICE_ATTR. The interface uses the same struct -kvm_device_attr as other devices, but targets VCPU-wide settings and controls. - -The groups and attributes per virtual cpu, if any, are architecture specific. - -1. GROUP: KVM_ARM_VCPU_PMU_V3_CTRL -Architectures: ARM64 - -1.1. ATTRIBUTE: KVM_ARM_VCPU_PMU_V3_IRQ -Parameters: in kvm_device_attr.addr the address for PMU overflow interrupt is a - pointer to an int -Returns: -EBUSY: The PMU overflow interrupt is already set - -ENXIO: The overflow interrupt not set when attempting to get it - -ENODEV: PMUv3 not supported - -EINVAL: Invalid PMU overflow interrupt number supplied or - trying to set the IRQ number without using an in-kernel - irqchip. - -A value describing the PMUv3 (Performance Monitor Unit v3) overflow interrupt -number for this vcpu. This interrupt could be a PPI or SPI, but the interrupt -type must be same for each vcpu. As a PPI, the interrupt number is the same for -all vcpus, while as an SPI it must be a separate number per vcpu. - -1.2 ATTRIBUTE: KVM_ARM_VCPU_PMU_V3_INIT -Parameters: no additional parameter in kvm_device_attr.addr -Returns: -ENODEV: PMUv3 not supported or GIC not initialized - -ENXIO: PMUv3 not properly configured or in-kernel irqchip not - configured as required prior to calling this attribute - -EBUSY: PMUv3 already initialized - -Request the initialization of the PMUv3. If using the PMUv3 with an in-kernel -virtual GIC implementation, this must be done after initializing the in-kernel -irqchip. - - -2. GROUP: KVM_ARM_VCPU_TIMER_CTRL -Architectures: ARM,ARM64 - -2.1. ATTRIBUTE: KVM_ARM_VCPU_TIMER_IRQ_VTIMER -2.2. ATTRIBUTE: KVM_ARM_VCPU_TIMER_IRQ_PTIMER -Parameters: in kvm_device_attr.addr the address for the timer interrupt is a - pointer to an int -Returns: -EINVAL: Invalid timer interrupt number - -EBUSY: One or more VCPUs has already run - -A value describing the architected timer interrupt number when connected to an -in-kernel virtual GIC. These must be a PPI (16 <= intid < 32). Setting the -attribute overrides the default values (see below). - -KVM_ARM_VCPU_TIMER_IRQ_VTIMER: The EL1 virtual timer intid (default: 27) -KVM_ARM_VCPU_TIMER_IRQ_PTIMER: The EL1 physical timer intid (default: 30) - -Setting the same PPI for different timers will prevent the VCPUs from running. -Setting the interrupt number on a VCPU configures all VCPUs created at that -time to use the number provided for a given timer, overwriting any previously -configured values on other VCPUs. Userspace should configure the interrupt -numbers on at least one VCPU after creating all VCPUs and before running any -VCPUs. - -3. GROUP: KVM_ARM_VCPU_PVTIME_CTRL -Architectures: ARM64 - -3.1 ATTRIBUTE: KVM_ARM_VCPU_PVTIME_IPA -Parameters: 64-bit base address -Returns: -ENXIO: Stolen time not implemented - -EEXIST: Base address already set for this VCPU - -EINVAL: Base address not 64 byte aligned - -Specifies the base address of the stolen time structure for this VCPU. The -base address must be 64 byte aligned and exist within a valid guest memory -region. See Documentation/virt/kvm/arm/pvtime.txt for more information -including the layout of the stolen time structure. diff --git a/Documentation/virt/kvm/devices/vfio.txt b/Documentation/virt/kvm/devices/vfio.rst similarity index 72% rename from Documentation/virt/kvm/devices/vfio.txt rename to Documentation/virt/kvm/devices/vfio.rst index 528c77c8022c66e846bb8a41cbacd999fcd069dc..2d20dc56106946c4b79c073789a44eaca91dfebf 100644 --- a/Documentation/virt/kvm/devices/vfio.txt +++ b/Documentation/virt/kvm/devices/vfio.rst @@ -1,8 +1,12 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=================== VFIO virtual device =================== Device types supported: - KVM_DEV_TYPE_VFIO + + - KVM_DEV_TYPE_VFIO Only one VFIO instance may be created per VM. The created device tracks VFIO groups in use by the VM and features of those groups @@ -23,14 +27,15 @@ KVM_DEV_VFIO_GROUP attributes: for the VFIO group. KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: attaches a guest visible TCE table allocated by sPAPR KVM. - kvm_device_attr.addr points to a struct: + kvm_device_attr.addr points to a struct:: + + struct kvm_vfio_spapr_tce { + __s32 groupfd; + __s32 tablefd; + }; - struct kvm_vfio_spapr_tce { - __s32 groupfd; - __s32 tablefd; - }; + where: - where - @groupfd is a file descriptor for a VFIO group; - @tablefd is a file descriptor for a TCE table allocated via - KVM_CREATE_SPAPR_TCE. + - @groupfd is a file descriptor for a VFIO group; + - @tablefd is a file descriptor for a TCE table allocated via + KVM_CREATE_SPAPR_TCE. diff --git a/Documentation/virt/kvm/devices/vm.txt b/Documentation/virt/kvm/devices/vm.rst similarity index 61% rename from Documentation/virt/kvm/devices/vm.txt rename to Documentation/virt/kvm/devices/vm.rst index 4ffb82b0246838d3022fb094b3996fa8de84e9ec..0aa5b1cfd700c485bbbb4385ff63a94e231c3dcf 100644 --- a/Documentation/virt/kvm/devices/vm.txt +++ b/Documentation/virt/kvm/devices/vm.rst @@ -1,5 +1,8 @@ +.. SPDX-License-Identifier: GPL-2.0 + +==================== Generic vm interface -==================================== +==================== The virtual machine "device" also accepts the ioctls KVM_SET_DEVICE_ATTR, KVM_GET_DEVICE_ATTR, and KVM_HAS_DEVICE_ATTR. The interface uses the same @@ -10,30 +13,38 @@ The groups and attributes per virtual machine, if any, are architecture specific. 1. GROUP: KVM_S390_VM_MEM_CTRL -Architectures: s390 +============================== + +:Architectures: s390 1.1. ATTRIBUTE: KVM_S390_VM_MEM_ENABLE_CMMA -Parameters: none -Returns: -EBUSY if a vcpu is already defined, otherwise 0 +------------------------------------------- + +:Parameters: none +:Returns: -EBUSY if a vcpu is already defined, otherwise 0 Enables Collaborative Memory Management Assist (CMMA) for the virtual machine. 1.2. ATTRIBUTE: KVM_S390_VM_MEM_CLR_CMMA -Parameters: none -Returns: -EINVAL if CMMA was not enabled - 0 otherwise +---------------------------------------- + +:Parameters: none +:Returns: -EINVAL if CMMA was not enabled; + 0 otherwise Clear the CMMA status for all guest pages, so any pages the guest marked as unused are again used any may not be reclaimed by the host. 1.3. ATTRIBUTE KVM_S390_VM_MEM_LIMIT_SIZE -Parameters: in attr->addr the address for the new limit of guest memory -Returns: -EFAULT if the given address is not accessible - -EINVAL if the virtual machine is of type UCONTROL - -E2BIG if the given guest memory is to big for that machine - -EBUSY if a vcpu is already defined - -ENOMEM if not enough memory is available for a new shadow guest mapping - 0 otherwise +----------------------------------------- + +:Parameters: in attr->addr the address for the new limit of guest memory +:Returns: -EFAULT if the given address is not accessible; + -EINVAL if the virtual machine is of type UCONTROL; + -E2BIG if the given guest memory is to big for that machine; + -EBUSY if a vcpu is already defined; + -ENOMEM if not enough memory is available for a new shadow guest mapping; + 0 otherwise. Allows userspace to query the actual limit and set a new limit for the maximum guest memory size. The limit will be rounded up to @@ -42,78 +53,92 @@ the number of page table levels. In the case that there is no limit we will set the limit to KVM_S390_NO_MEM_LIMIT (U64_MAX). 2. GROUP: KVM_S390_VM_CPU_MODEL -Architectures: s390 +=============================== + +:Architectures: s390 2.1. ATTRIBUTE: KVM_S390_VM_CPU_MACHINE (r/o) +--------------------------------------------- -Allows user space to retrieve machine and kvm specific cpu related information: +Allows user space to retrieve machine and kvm specific cpu related information:: -struct kvm_s390_vm_cpu_machine { + struct kvm_s390_vm_cpu_machine { __u64 cpuid; # CPUID of host __u32 ibc; # IBC level range offered by host __u8 pad[4]; __u64 fac_mask[256]; # set of cpu facilities enabled by KVM __u64 fac_list[256]; # set of cpu facilities offered by host -} + } -Parameters: address of buffer to store the machine related cpu data - of type struct kvm_s390_vm_cpu_machine* -Returns: -EFAULT if the given address is not accessible from kernel space - -ENOMEM if not enough memory is available to process the ioctl - 0 in case of success +:Parameters: address of buffer to store the machine related cpu data + of type struct kvm_s390_vm_cpu_machine* +:Returns: -EFAULT if the given address is not accessible from kernel space; + -ENOMEM if not enough memory is available to process the ioctl; + 0 in case of success. 2.2. ATTRIBUTE: KVM_S390_VM_CPU_PROCESSOR (r/w) +=============================================== -Allows user space to retrieve or request to change cpu related information for a vcpu: +Allows user space to retrieve or request to change cpu related information for a vcpu:: -struct kvm_s390_vm_cpu_processor { + struct kvm_s390_vm_cpu_processor { __u64 cpuid; # CPUID currently (to be) used by this vcpu __u16 ibc; # IBC level currently (to be) used by this vcpu __u8 pad[6]; __u64 fac_list[256]; # set of cpu facilities currently (to be) used - # by this vcpu -} + # by this vcpu + } KVM does not enforce or limit the cpu model data in any form. Take the information retrieved by means of KVM_S390_VM_CPU_MACHINE as hint for reasonable configuration setups. Instruction interceptions triggered by additionally set facility bits that are not handled by KVM need to by imlemented in the VM driver code. -Parameters: address of buffer to store/set the processor related cpu - data of type struct kvm_s390_vm_cpu_processor*. -Returns: -EBUSY in case 1 or more vcpus are already activated (only in write case) - -EFAULT if the given address is not accessible from kernel space - -ENOMEM if not enough memory is available to process the ioctl - 0 in case of success +:Parameters: address of buffer to store/set the processor related cpu + data of type struct kvm_s390_vm_cpu_processor*. +:Returns: -EBUSY in case 1 or more vcpus are already activated (only in write case); + -EFAULT if the given address is not accessible from kernel space; + -ENOMEM if not enough memory is available to process the ioctl; + 0 in case of success. + +.. _KVM_S390_VM_CPU_MACHINE_FEAT: 2.3. ATTRIBUTE: KVM_S390_VM_CPU_MACHINE_FEAT (r/o) +-------------------------------------------------- Allows user space to retrieve available cpu features. A feature is available if provided by the hardware and supported by kvm. In theory, cpu features could even be completely emulated by kvm. -struct kvm_s390_vm_cpu_feat { - __u64 feat[16]; # Bitmap (1 = feature available), MSB 0 bit numbering -}; +:: -Parameters: address of a buffer to load the feature list from. -Returns: -EFAULT if the given address is not accessible from kernel space. - 0 in case of success. + struct kvm_s390_vm_cpu_feat { + __u64 feat[16]; # Bitmap (1 = feature available), MSB 0 bit numbering + }; + +:Parameters: address of a buffer to load the feature list from. +:Returns: -EFAULT if the given address is not accessible from kernel space; + 0 in case of success. 2.4. ATTRIBUTE: KVM_S390_VM_CPU_PROCESSOR_FEAT (r/w) +---------------------------------------------------- Allows user space to retrieve or change enabled cpu features for all VCPUs of a VM. Features that are not available cannot be enabled. -See 2.3. for a description of the parameter struct. +See :ref:`KVM_S390_VM_CPU_MACHINE_FEAT` for +a description of the parameter struct. -Parameters: address of a buffer to store/load the feature list from. -Returns: -EFAULT if the given address is not accessible from kernel space. - -EINVAL if a cpu feature that is not available is to be enabled. - -EBUSY if at least one VCPU has already been defined. +:Parameters: address of a buffer to store/load the feature list from. +:Returns: -EFAULT if the given address is not accessible from kernel space; + -EINVAL if a cpu feature that is not available is to be enabled; + -EBUSY if at least one VCPU has already been defined; 0 in case of success. +.. _KVM_S390_VM_CPU_MACHINE_SUBFUNC: + 2.5. ATTRIBUTE: KVM_S390_VM_CPU_MACHINE_SUBFUNC (r/o) +----------------------------------------------------- Allows user space to retrieve available cpu subfunctions without any filtering done by a set IBC. These subfunctions are indicated to the guest VCPU via @@ -126,7 +151,9 @@ contained in the returned struct. If the affected instruction indicates subfunctions via a "test bit" mechanism, the subfunction codes are contained in the returned struct in MSB 0 bit numbering. -struct kvm_s390_vm_cpu_subfunc { +:: + + struct kvm_s390_vm_cpu_subfunc { u8 plo[32]; # always valid (ESA/390 feature) u8 ptff[16]; # valid with TOD-clock steering u8 kmac[16]; # valid with Message-Security-Assist @@ -143,13 +170,14 @@ struct kvm_s390_vm_cpu_subfunc { u8 kma[16]; # valid with Message-Security-Assist-Extension 8 u8 kdsa[16]; # valid with Message-Security-Assist-Extension 9 u8 reserved[1792]; # reserved for future instructions -}; + }; -Parameters: address of a buffer to load the subfunction blocks from. -Returns: -EFAULT if the given address is not accessible from kernel space. +:Parameters: address of a buffer to load the subfunction blocks from. +:Returns: -EFAULT if the given address is not accessible from kernel space; 0 in case of success. 2.6. ATTRIBUTE: KVM_S390_VM_CPU_PROCESSOR_SUBFUNC (r/w) +------------------------------------------------------- Allows user space to retrieve or change cpu subfunctions to be indicated for all VCPUs of a VM. This attribute will only be available if kernel and @@ -164,107 +192,125 @@ As long as no data has been written, a read will fail. The IBC will be used to determine available subfunctions in this case, this will guarantee backward compatibility. -See 2.5. for a description of the parameter struct. +See :ref:`KVM_S390_VM_CPU_MACHINE_SUBFUNC` for a +description of the parameter struct. -Parameters: address of a buffer to store/load the subfunction blocks from. -Returns: -EFAULT if the given address is not accessible from kernel space. - -EINVAL when reading, if there was no write yet. - -EBUSY if at least one VCPU has already been defined. +:Parameters: address of a buffer to store/load the subfunction blocks from. +:Returns: -EFAULT if the given address is not accessible from kernel space; + -EINVAL when reading, if there was no write yet; + -EBUSY if at least one VCPU has already been defined; 0 in case of success. 3. GROUP: KVM_S390_VM_TOD -Architectures: s390 +========================= + +:Architectures: s390 3.1. ATTRIBUTE: KVM_S390_VM_TOD_HIGH +------------------------------------ Allows user space to set/get the TOD clock extension (u8) (superseded by KVM_S390_VM_TOD_EXT). -Parameters: address of a buffer in user space to store the data (u8) to -Returns: -EFAULT if the given address is not accessible from kernel space +:Parameters: address of a buffer in user space to store the data (u8) to +:Returns: -EFAULT if the given address is not accessible from kernel space; -EINVAL if setting the TOD clock extension to != 0 is not supported 3.2. ATTRIBUTE: KVM_S390_VM_TOD_LOW +----------------------------------- Allows user space to set/get bits 0-63 of the TOD clock register as defined in the POP (u64). -Parameters: address of a buffer in user space to store the data (u64) to -Returns: -EFAULT if the given address is not accessible from kernel space +:Parameters: address of a buffer in user space to store the data (u64) to +:Returns: -EFAULT if the given address is not accessible from kernel space 3.3. ATTRIBUTE: KVM_S390_VM_TOD_EXT +----------------------------------- + Allows user space to set/get bits 0-63 of the TOD clock register as defined in the POP (u64). If the guest CPU model supports the TOD clock extension (u8), it also allows user space to get/set it. If the guest CPU model does not support it, it is stored as 0 and not allowed to be set to a value != 0. -Parameters: address of a buffer in user space to store the data - (kvm_s390_vm_tod_clock) to -Returns: -EFAULT if the given address is not accessible from kernel space +:Parameters: address of a buffer in user space to store the data + (kvm_s390_vm_tod_clock) to +:Returns: -EFAULT if the given address is not accessible from kernel space; -EINVAL if setting the TOD clock extension to != 0 is not supported 4. GROUP: KVM_S390_VM_CRYPTO -Architectures: s390 +============================ + +:Architectures: s390 4.1. ATTRIBUTE: KVM_S390_VM_CRYPTO_ENABLE_AES_KW (w/o) +------------------------------------------------------ Allows user space to enable aes key wrapping, including generating a new wrapping key. -Parameters: none -Returns: 0 +:Parameters: none +:Returns: 0 4.2. ATTRIBUTE: KVM_S390_VM_CRYPTO_ENABLE_DEA_KW (w/o) +------------------------------------------------------ Allows user space to enable dea key wrapping, including generating a new wrapping key. -Parameters: none -Returns: 0 +:Parameters: none +:Returns: 0 4.3. ATTRIBUTE: KVM_S390_VM_CRYPTO_DISABLE_AES_KW (w/o) +------------------------------------------------------- Allows user space to disable aes key wrapping, clearing the wrapping key. -Parameters: none -Returns: 0 +:Parameters: none +:Returns: 0 4.4. ATTRIBUTE: KVM_S390_VM_CRYPTO_DISABLE_DEA_KW (w/o) +------------------------------------------------------- Allows user space to disable dea key wrapping, clearing the wrapping key. -Parameters: none -Returns: 0 +:Parameters: none +:Returns: 0 5. GROUP: KVM_S390_VM_MIGRATION -Architectures: s390 +=============================== + +:Architectures: s390 5.1. ATTRIBUTE: KVM_S390_VM_MIGRATION_STOP (w/o) +------------------------------------------------ Allows userspace to stop migration mode, needed for PGSTE migration. Setting this attribute when migration mode is not active will have no effects. -Parameters: none -Returns: 0 +:Parameters: none +:Returns: 0 5.2. ATTRIBUTE: KVM_S390_VM_MIGRATION_START (w/o) +------------------------------------------------- Allows userspace to start migration mode, needed for PGSTE migration. Setting this attribute when migration mode is already active will have no effects. -Parameters: none -Returns: -ENOMEM if there is not enough free memory to start migration mode - -EINVAL if the state of the VM is invalid (e.g. no memory defined) +:Parameters: none +:Returns: -ENOMEM if there is not enough free memory to start migration mode; + -EINVAL if the state of the VM is invalid (e.g. no memory defined); 0 in case of success. 5.3. ATTRIBUTE: KVM_S390_VM_MIGRATION_STATUS (r/o) +-------------------------------------------------- Allows userspace to query the status of migration mode. -Parameters: address of a buffer in user space to store the data (u64) to; - the data itself is either 0 if migration mode is disabled or 1 - if it is enabled -Returns: -EFAULT if the given address is not accessible from kernel space +:Parameters: address of a buffer in user space to store the data (u64) to; + the data itself is either 0 if migration mode is disabled or 1 + if it is enabled +:Returns: -EFAULT if the given address is not accessible from kernel space; 0 in case of success. diff --git a/Documentation/virt/kvm/devices/xics.txt b/Documentation/virt/kvm/devices/xics.rst similarity index 84% rename from Documentation/virt/kvm/devices/xics.txt rename to Documentation/virt/kvm/devices/xics.rst index 423332dda7bc893104a4e12d3b71b482ea590c19..2d6927e0b776b370bdcb9213b8d5bfe40c990d4f 100644 --- a/Documentation/virt/kvm/devices/xics.txt +++ b/Documentation/virt/kvm/devices/xics.rst @@ -1,20 +1,31 @@ +.. SPDX-License-Identifier: GPL-2.0 + +========================= XICS interrupt controller +========================= Device type supported: KVM_DEV_TYPE_XICS Groups: 1. KVM_DEV_XICS_GRP_SOURCES - Attributes: One per interrupt source, indexed by the source number. + Attributes: + One per interrupt source, indexed by the source number. 2. KVM_DEV_XICS_GRP_CTRL - Attributes: - 2.1 KVM_DEV_XICS_NR_SERVERS (write only) + Attributes: + + 2.1 KVM_DEV_XICS_NR_SERVERS (write only) + The kvm_device_attr.addr points to a __u32 value which is the number of interrupt server numbers (ie, highest possible vcpu id plus one). + Errors: - -EINVAL: Value greater than KVM_MAX_VCPU_ID. - -EFAULT: Invalid user pointer for attr->addr. - -EBUSY: A vcpu is already connected to the device. + + ======= ========================================== + -EINVAL Value greater than KVM_MAX_VCPU_ID. + -EFAULT Invalid user pointer for attr->addr. + -EBUSY A vcpu is already connected to the device. + ======= ========================================== This device emulates the XICS (eXternal Interrupt Controller Specification) defined in PAPR. The XICS has a set of interrupt @@ -53,24 +64,29 @@ the interrupt source number. The 64 bit state word has the following bitfields, starting from the least-significant end of the word: * Destination (server number), 32 bits + This specifies where the interrupt should be sent, and is the interrupt server number specified for the destination vcpu. * Priority, 8 bits + This is the priority specified for this interrupt source, where 0 is the highest priority and 255 is the lowest. An interrupt with a priority of 255 will never be delivered. * Level sensitive flag, 1 bit + This bit is 1 for a level-sensitive interrupt source, or 0 for edge-sensitive (or MSI). * Masked flag, 1 bit + This bit is set to 1 if the interrupt is masked (cannot be delivered regardless of its priority), for example by the ibm,int-off RTAS call, or 0 if it is not masked. * Pending flag, 1 bit + This bit is 1 if the source has a pending interrupt, otherwise 0. Only one XICS instance may be created per VM. diff --git a/Documentation/virt/kvm/devices/xive.txt b/Documentation/virt/kvm/devices/xive.rst similarity index 62% rename from Documentation/virt/kvm/devices/xive.txt rename to Documentation/virt/kvm/devices/xive.rst index f5d1d6b5af61504dd501192e61c71d6333ceb83a..8bdf3dc38f01608dc466623b1e0511e6f8e918e6 100644 --- a/Documentation/virt/kvm/devices/xive.txt +++ b/Documentation/virt/kvm/devices/xive.rst @@ -1,8 +1,11 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=========================================================== POWER9 eXternal Interrupt Virtualization Engine (XIVE Gen1) -========================================================== +=========================================================== Device types supported: - KVM_DEV_TYPE_XIVE POWER9 XIVE Interrupt Controller generation 1 + - KVM_DEV_TYPE_XIVE POWER9 XIVE Interrupt Controller generation 1 This device acts as a VM interrupt controller. It provides the KVM interface to configure the interrupt sources of a VM in the underlying @@ -64,72 +67,100 @@ the legacy interrupt mode, referred as XICS (POWER7/8). * Groups: - 1. KVM_DEV_XIVE_GRP_CTRL - Provides global controls on the device +1. KVM_DEV_XIVE_GRP_CTRL + Provides global controls on the device + Attributes: 1.1 KVM_DEV_XIVE_RESET (write only) Resets the interrupt controller configuration for sources and event queues. To be used by kexec and kdump. + Errors: none 1.2 KVM_DEV_XIVE_EQ_SYNC (write only) Sync all the sources and queues and mark the EQ pages dirty. This to make sure that a consistent memory state is captured when migrating the VM. + Errors: none 1.3 KVM_DEV_XIVE_NR_SERVERS (write only) The kvm_device_attr.addr points to a __u32 value which is the number of interrupt server numbers (ie, highest possible vcpu id plus one). + Errors: - -EINVAL: Value greater than KVM_MAX_VCPU_ID. - -EFAULT: Invalid user pointer for attr->addr. - -EBUSY: A vCPU is already connected to the device. - 2. KVM_DEV_XIVE_GRP_SOURCE (write only) - Initializes a new source in the XIVE device and mask it. + ======= ========================================== + -EINVAL Value greater than KVM_MAX_VCPU_ID. + -EFAULT Invalid user pointer for attr->addr. + -EBUSY A vCPU is already connected to the device. + ======= ========================================== + +2. KVM_DEV_XIVE_GRP_SOURCE (write only) + Initializes a new source in the XIVE device and mask it. + Attributes: Interrupt source number (64-bit) - The kvm_device_attr.addr points to a __u64 value: - bits: | 63 .... 2 | 1 | 0 - values: | unused | level | type + + The kvm_device_attr.addr points to a __u64 value:: + + bits: | 63 .... 2 | 1 | 0 + values: | unused | level | type + - type: 0:MSI 1:LSI - level: assertion level in case of an LSI. + Errors: - -E2BIG: Interrupt source number is out of range - -ENOMEM: Could not create a new source block - -EFAULT: Invalid user pointer for attr->addr. - -ENXIO: Could not allocate underlying HW interrupt - 3. KVM_DEV_XIVE_GRP_SOURCE_CONFIG (write only) - Configures source targeting + ======= ========================================== + -E2BIG Interrupt source number is out of range + -ENOMEM Could not create a new source block + -EFAULT Invalid user pointer for attr->addr. + -ENXIO Could not allocate underlying HW interrupt + ======= ========================================== + +3. KVM_DEV_XIVE_GRP_SOURCE_CONFIG (write only) + Configures source targeting + Attributes: Interrupt source number (64-bit) - The kvm_device_attr.addr points to a __u64 value: - bits: | 63 .... 33 | 32 | 31 .. 3 | 2 .. 0 - values: | eisn | mask | server | priority + + The kvm_device_attr.addr points to a __u64 value:: + + bits: | 63 .... 33 | 32 | 31 .. 3 | 2 .. 0 + values: | eisn | mask | server | priority + - priority: 0-7 interrupt priority level - server: CPU number chosen to handle the interrupt - mask: mask flag (unused) - eisn: Effective Interrupt Source Number + Errors: - -ENOENT: Unknown source number - -EINVAL: Not initialized source number - -EINVAL: Invalid priority - -EINVAL: Invalid CPU number. - -EFAULT: Invalid user pointer for attr->addr. - -ENXIO: CPU event queues not configured or configuration of the - underlying HW interrupt failed - -EBUSY: No CPU available to serve interrupt - - 4. KVM_DEV_XIVE_GRP_EQ_CONFIG (read-write) - Configures an event queue of a CPU + + ======= ======================================================= + -ENOENT Unknown source number + -EINVAL Not initialized source number + -EINVAL Invalid priority + -EINVAL Invalid CPU number. + -EFAULT Invalid user pointer for attr->addr. + -ENXIO CPU event queues not configured or configuration of the + underlying HW interrupt failed + -EBUSY No CPU available to serve interrupt + ======= ======================================================= + +4. KVM_DEV_XIVE_GRP_EQ_CONFIG (read-write) + Configures an event queue of a CPU + Attributes: EQ descriptor identifier (64-bit) - The EQ descriptor identifier is a tuple (server, priority) : - bits: | 63 .... 32 | 31 .. 3 | 2 .. 0 - values: | unused | server | priority - The kvm_device_attr.addr points to : + + The EQ descriptor identifier is a tuple (server, priority):: + + bits: | 63 .... 32 | 31 .. 3 | 2 .. 0 + values: | unused | server | priority + + The kvm_device_attr.addr points to:: + struct kvm_ppc_xive_eq { __u32 flags; __u32 qshift; @@ -138,8 +169,9 @@ the legacy interrupt mode, referred as XICS (POWER7/8). __u32 qindex; __u8 pad[40]; }; + - flags: queue flags - KVM_XIVE_EQ_ALWAYS_NOTIFY (required) + KVM_XIVE_EQ_ALWAYS_NOTIFY (required) forces notification without using the coalescing mechanism provided by the XIVE END ESBs. - qshift: queue size (power of 2) @@ -147,22 +179,31 @@ the legacy interrupt mode, referred as XICS (POWER7/8). - qtoggle: current queue toggle bit - qindex: current queue index - pad: reserved for future use + Errors: - -ENOENT: Invalid CPU number - -EINVAL: Invalid priority - -EINVAL: Invalid flags - -EINVAL: Invalid queue size - -EINVAL: Invalid queue address - -EFAULT: Invalid user pointer for attr->addr. - -EIO: Configuration of the underlying HW failed - - 5. KVM_DEV_XIVE_GRP_SOURCE_SYNC (write only) - Synchronize the source to flush event notifications + + ======= ========================================= + -ENOENT Invalid CPU number + -EINVAL Invalid priority + -EINVAL Invalid flags + -EINVAL Invalid queue size + -EINVAL Invalid queue address + -EFAULT Invalid user pointer for attr->addr. + -EIO Configuration of the underlying HW failed + ======= ========================================= + +5. KVM_DEV_XIVE_GRP_SOURCE_SYNC (write only) + Synchronize the source to flush event notifications + Attributes: Interrupt source number (64-bit) + Errors: - -ENOENT: Unknown source number - -EINVAL: Not initialized source number + + ======= ============================= + -ENOENT Unknown source number + -EINVAL Not initialized source number + ======= ============================= * VCPU state @@ -175,11 +216,12 @@ the legacy interrupt mode, referred as XICS (POWER7/8). as it synthesizes the priorities of the pending interrupts. We capture a bit more to report debug information. - KVM_REG_PPC_VP_STATE (2 * 64bits) - bits: | 63 .... 32 | 31 .... 0 | - values: | TIMA word0 | TIMA word1 | - bits: | 127 .......... 64 | - values: | unused | + KVM_REG_PPC_VP_STATE (2 * 64bits):: + + bits: | 63 .... 32 | 31 .... 0 | + values: | TIMA word0 | TIMA word1 | + bits: | 127 .......... 64 | + values: | unused | * Migration: @@ -196,7 +238,7 @@ the legacy interrupt mode, referred as XICS (POWER7/8). 3. Capture the state of the source targeting, the EQs configuration and the state of thread interrupt context registers. - Restore is similar : + Restore is similar: 1. Restore the EQ configuration. As targeting depends on it. 2. Restore targeting diff --git a/Documentation/virt/kvm/halt-polling.txt b/Documentation/virt/kvm/halt-polling.rst similarity index 64% rename from Documentation/virt/kvm/halt-polling.txt rename to Documentation/virt/kvm/halt-polling.rst index 4f791b128dd27a0ed9bc4ad79eddc8794bcab2bd..4922e4a15f18412fa1ceb39cb5891fa0ee8839b6 100644 --- a/Documentation/virt/kvm/halt-polling.txt +++ b/Documentation/virt/kvm/halt-polling.rst @@ -1,3 +1,6 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=========================== The KVM halt polling system =========================== @@ -68,7 +71,8 @@ steady state polling interval but will only really do a good job for wakeups which come at an approximately constant rate, otherwise there will be constant adjustment of the polling interval. -[0] total block time: the time between when the halt polling function is +[0] total block time: + the time between when the halt polling function is invoked and a wakeup source received (irrespective of whether the scheduler is invoked within that function). @@ -81,31 +85,32 @@ shrunk. These variables are defined in include/linux/kvm_host.h and as module parameters in virt/kvm/kvm_main.c, or arch/powerpc/kvm/book3s_hv.c in the powerpc kvm-hv case. -Module Parameter | Description | Default Value --------------------------------------------------------------------------------- -halt_poll_ns | The global max polling | KVM_HALT_POLL_NS_DEFAULT - | interval which defines | - | the ceiling value of the | - | polling interval for | (per arch value) - | each vcpu. | --------------------------------------------------------------------------------- -halt_poll_ns_grow | The value by which the | 2 - | halt polling interval is | - | multiplied in the | - | grow_halt_poll_ns() | - | function. | --------------------------------------------------------------------------------- -halt_poll_ns_grow_start | The initial value to grow | 10000 - | to from zero in the | - | grow_halt_poll_ns() | - | function. | --------------------------------------------------------------------------------- -halt_poll_ns_shrink | The value by which the | 0 - | halt polling interval is | - | divided in the | - | shrink_halt_poll_ns() | - | function. | --------------------------------------------------------------------------------- ++-----------------------+---------------------------+-------------------------+ +|Module Parameter | Description | Default Value | ++-----------------------+---------------------------+-------------------------+ +|halt_poll_ns | The global max polling | KVM_HALT_POLL_NS_DEFAULT| +| | interval which defines | | +| | the ceiling value of the | | +| | polling interval for | (per arch value) | +| | each vcpu. | | ++-----------------------+---------------------------+-------------------------+ +|halt_poll_ns_grow | The value by which the | 2 | +| | halt polling interval is | | +| | multiplied in the | | +| | grow_halt_poll_ns() | | +| | function. | | ++-----------------------+---------------------------+-------------------------+ +|halt_poll_ns_grow_start| The initial value to grow | 10000 | +| | to from zero in the | | +| | grow_halt_poll_ns() | | +| | function. | | ++-----------------------+---------------------------+-------------------------+ +|halt_poll_ns_shrink | The value by which the | 0 | +| | halt polling interval is | | +| | divided in the | | +| | shrink_halt_poll_ns() | | +| | function. | | ++-----------------------+---------------------------+-------------------------+ These module parameters can be set from the debugfs files in: @@ -117,20 +122,19 @@ Note: that these module parameters are system wide values and are not able to Further Notes ============= -- Care should be taken when setting the halt_poll_ns module parameter as a -large value has the potential to drive the cpu usage to 100% on a machine which -would be almost entirely idle otherwise. This is because even if a guest has -wakeups during which very little work is done and which are quite far apart, if -the period is shorter than the global max polling interval (halt_poll_ns) then -the host will always poll for the entire block time and thus cpu utilisation -will go to 100%. - -- Halt polling essentially presents a trade off between power usage and latency -and the module parameters should be used to tune the affinity for this. Idle -cpu time is essentially converted to host kernel time with the aim of decreasing -latency when entering the guest. - -- Halt polling will only be conducted by the host when no other tasks are -runnable on that cpu, otherwise the polling will cease immediately and -schedule will be invoked to allow that other task to run. Thus this doesn't -allow a guest to denial of service the cpu. +- Care should be taken when setting the halt_poll_ns module parameter as a large value + has the potential to drive the cpu usage to 100% on a machine which would be almost + entirely idle otherwise. This is because even if a guest has wakeups during which very + little work is done and which are quite far apart, if the period is shorter than the + global max polling interval (halt_poll_ns) then the host will always poll for the + entire block time and thus cpu utilisation will go to 100%. + +- Halt polling essentially presents a trade off between power usage and latency and + the module parameters should be used to tune the affinity for this. Idle cpu time is + essentially converted to host kernel time with the aim of decreasing latency when + entering the guest. + +- Halt polling will only be conducted by the host when no other tasks are runnable on + that cpu, otherwise the polling will cease immediately and schedule will be invoked to + allow that other task to run. Thus this doesn't allow a guest to denial of service the + cpu. diff --git a/Documentation/virt/kvm/hypercalls.txt b/Documentation/virt/kvm/hypercalls.rst similarity index 55% rename from Documentation/virt/kvm/hypercalls.txt rename to Documentation/virt/kvm/hypercalls.rst index 5f6d291bd00459957170e3459452b290c55cc1a9..dbaf207e560d0f71c6a2f008e5958796034ff068 100644 --- a/Documentation/virt/kvm/hypercalls.txt +++ b/Documentation/virt/kvm/hypercalls.rst @@ -1,5 +1,9 @@ -Linux KVM Hypercall: +.. SPDX-License-Identifier: GPL-2.0 + +=================== +Linux KVM Hypercall =================== + X86: KVM Hypercalls have a three-byte sequence of either the vmcall or the vmmcall instruction. The hypervisor can replace it with instructions that are @@ -20,7 +24,7 @@ S390: For further information on the S390 diagnose call as supported by KVM, refer to Documentation/virt/kvm/s390-diag.txt. - PowerPC: +PowerPC: It uses R3-R10 and hypercall number in R11. R4-R11 are used as output registers. Return value is placed in R3. @@ -34,7 +38,8 @@ MIPS: the return value is placed in $2 (v0). KVM Hypercalls Documentation -=========================== +============================ + The template for each hypercall is: 1. Hypercall name. 2. Architecture(s) @@ -43,56 +48,64 @@ The template for each hypercall is: 1. KVM_HC_VAPIC_POLL_IRQ ------------------------ -Architecture: x86 -Status: active -Purpose: Trigger guest exit so that the host can check for pending -interrupts on reentry. + +:Architecture: x86 +:Status: active +:Purpose: Trigger guest exit so that the host can check for pending + interrupts on reentry. 2. KVM_HC_MMU_OP ------------------------- -Architecture: x86 -Status: deprecated. -Purpose: Support MMU operations such as writing to PTE, -flushing TLB, release PT. +---------------- + +:Architecture: x86 +:Status: deprecated. +:Purpose: Support MMU operations such as writing to PTE, + flushing TLB, release PT. 3. KVM_HC_FEATURES ------------------------- -Architecture: PPC -Status: active -Purpose: Expose hypercall availability to the guest. On x86 platforms, cpuid -used to enumerate which hypercalls are available. On PPC, either device tree -based lookup ( which is also what EPAPR dictates) OR KVM specific enumeration -mechanism (which is this hypercall) can be used. +------------------ + +:Architecture: PPC +:Status: active +:Purpose: Expose hypercall availability to the guest. On x86 platforms, cpuid + used to enumerate which hypercalls are available. On PPC, either + device tree based lookup ( which is also what EPAPR dictates) + OR KVM specific enumeration mechanism (which is this hypercall) + can be used. 4. KVM_HC_PPC_MAP_MAGIC_PAGE ------------------------- -Architecture: PPC -Status: active -Purpose: To enable communication between the hypervisor and guest there is a -shared page that contains parts of supervisor visible register state. -The guest can map this shared page to access its supervisor register through -memory using this hypercall. +---------------------------- + +:Architecture: PPC +:Status: active +:Purpose: To enable communication between the hypervisor and guest there is a + shared page that contains parts of supervisor visible register state. + The guest can map this shared page to access its supervisor register + through memory using this hypercall. 5. KVM_HC_KICK_CPU ------------------------- -Architecture: x86 -Status: active -Purpose: Hypercall used to wakeup a vcpu from HLT state -Usage example : A vcpu of a paravirtualized guest that is busywaiting in guest -kernel mode for an event to occur (ex: a spinlock to become available) can -execute HLT instruction once it has busy-waited for more than a threshold -time-interval. Execution of HLT instruction would cause the hypervisor to put -the vcpu to sleep until occurrence of an appropriate event. Another vcpu of the -same guest can wakeup the sleeping vcpu by issuing KVM_HC_KICK_CPU hypercall, -specifying APIC ID (a1) of the vcpu to be woken up. An additional argument (a0) -is used in the hypercall for future use. +------------------ + +:Architecture: x86 +:Status: active +:Purpose: Hypercall used to wakeup a vcpu from HLT state +:Usage example: + A vcpu of a paravirtualized guest that is busywaiting in guest + kernel mode for an event to occur (ex: a spinlock to become available) can + execute HLT instruction once it has busy-waited for more than a threshold + time-interval. Execution of HLT instruction would cause the hypervisor to put + the vcpu to sleep until occurrence of an appropriate event. Another vcpu of the + same guest can wakeup the sleeping vcpu by issuing KVM_HC_KICK_CPU hypercall, + specifying APIC ID (a1) of the vcpu to be woken up. An additional argument (a0) + is used in the hypercall for future use. 6. KVM_HC_CLOCK_PAIRING ------------------------- -Architecture: x86 -Status: active -Purpose: Hypercall used to synchronize host and guest clocks. +----------------------- +:Architecture: x86 +:Status: active +:Purpose: Hypercall used to synchronize host and guest clocks. + Usage: a0: guest physical address where host copies @@ -101,6 +114,8 @@ a0: guest physical address where host copies a1: clock_type, ATM only KVM_CLOCK_PAIRING_WALLCLOCK (0) is supported (corresponding to the host's CLOCK_REALTIME clock). + :: + struct kvm_clock_pairing { __s64 sec; __s64 nsec; @@ -123,15 +138,16 @@ Returns KVM_EOPNOTSUPP if the host does not use TSC clocksource, or if clock type is different than KVM_CLOCK_PAIRING_WALLCLOCK. 6. KVM_HC_SEND_IPI ------------------------- -Architecture: x86 -Status: active -Purpose: Send IPIs to multiple vCPUs. +------------------ + +:Architecture: x86 +:Status: active +:Purpose: Send IPIs to multiple vCPUs. -a0: lower part of the bitmap of destination APIC IDs -a1: higher part of the bitmap of destination APIC IDs -a2: the lowest APIC ID in bitmap -a3: APIC ICR +- a0: lower part of the bitmap of destination APIC IDs +- a1: higher part of the bitmap of destination APIC IDs +- a2: the lowest APIC ID in bitmap +- a3: APIC ICR The hypercall lets a guest send multicast IPIs, with at most 128 128 destinations per hypercall in 64-bit mode and 64 vCPUs per @@ -143,12 +159,13 @@ corresponds to the APIC ID a2+1, and so on. Returns the number of CPUs to which the IPIs were delivered successfully. 7. KVM_HC_SCHED_YIELD ------------------------- -Architecture: x86 -Status: active -Purpose: Hypercall used to yield if the IPI target vCPU is preempted +--------------------- + +:Architecture: x86 +:Status: active +:Purpose: Hypercall used to yield if the IPI target vCPU is preempted a0: destination APIC ID -Usage example: When sending a call-function IPI-many to vCPUs, yield if -any of the IPI target vCPUs was preempted. +:Usage example: When sending a call-function IPI-many to vCPUs, yield if + any of the IPI target vCPUs was preempted. diff --git a/Documentation/virt/kvm/index.rst b/Documentation/virt/kvm/index.rst index ada224a511fecab1b9813d508719c75464b189cc..774deaebf7fac762b44c022d034d7998b5dcde86 100644 --- a/Documentation/virt/kvm/index.rst +++ b/Documentation/virt/kvm/index.rst @@ -7,6 +7,22 @@ KVM .. toctree:: :maxdepth: 2 + api amd-memory-encryption cpuid + halt-polling + hypercalls + locking + mmu + msr + nested-vmx + ppc-pv + s390-diag + timekeeping vcpu-requests + + review-checklist + + arm/index + + devices/index diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst new file mode 100644 index 0000000000000000000000000000000000000000..c02291beac3fcd2f69bcce4c80cc126ee9217006 --- /dev/null +++ b/Documentation/virt/kvm/locking.rst @@ -0,0 +1,243 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================= +KVM Lock Overview +================= + +1. Acquisition Orders +--------------------- + +The acquisition orders for mutexes are as follows: + +- kvm->lock is taken outside vcpu->mutex + +- kvm->lock is taken outside kvm->slots_lock and kvm->irq_lock + +- kvm->slots_lock is taken outside kvm->irq_lock, though acquiring + them together is quite rare. + +On x86, vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock. + +Everything else is a leaf: no other lock is taken inside the critical +sections. + +2. Exception +------------ + +Fast page fault: + +Fast page fault is the fast path which fixes the guest page fault out of +the mmu-lock on x86. Currently, the page fault can be fast in one of the +following two cases: + +1. Access Tracking: The SPTE is not present, but it is marked for access + tracking i.e. the SPTE_SPECIAL_MASK is set. That means we need to + restore the saved R/X bits. This is described in more detail later below. + +2. Write-Protection: The SPTE is present and the fault is + caused by write-protect. That means we just need to change the W bit of + the spte. + +What we use to avoid all the race is the SPTE_HOST_WRITEABLE bit and +SPTE_MMU_WRITEABLE bit on the spte: + +- SPTE_HOST_WRITEABLE means the gfn is writable on host. +- SPTE_MMU_WRITEABLE means the gfn is writable on mmu. The bit is set when + the gfn is writable on guest mmu and it is not write-protected by shadow + page write-protection. + +On fast page fault path, we will use cmpxchg to atomically set the spte W +bit if spte.SPTE_HOST_WRITEABLE = 1 and spte.SPTE_WRITE_PROTECT = 1, or +restore the saved R/X bits if VMX_EPT_TRACK_ACCESS mask is set, or both. This +is safe because whenever changing these bits can be detected by cmpxchg. + +But we need carefully check these cases: + +1) The mapping from gfn to pfn + +The mapping from gfn to pfn may be changed since we can only ensure the pfn +is not changed during cmpxchg. This is a ABA problem, for example, below case +will happen: + ++------------------------------------------------------------------------+ +| At the beginning:: | +| | +| gpte = gfn1 | +| gfn1 is mapped to pfn1 on host | +| spte is the shadow page table entry corresponding with gpte and | +| spte = pfn1 | ++------------------------------------------------------------------------+ +| On fast page fault path: | ++------------------------------------+-----------------------------------+ +| CPU 0: | CPU 1: | ++------------------------------------+-----------------------------------+ +| :: | | +| | | +| old_spte = *spte; | | ++------------------------------------+-----------------------------------+ +| | pfn1 is swapped out:: | +| | | +| | spte = 0; | +| | | +| | pfn1 is re-alloced for gfn2. | +| | | +| | gpte is changed to point to | +| | gfn2 by the guest:: | +| | | +| | spte = pfn1; | ++------------------------------------+-----------------------------------+ +| :: | +| | +| if (cmpxchg(spte, old_spte, old_spte+W) | +| mark_page_dirty(vcpu->kvm, gfn1) | +| OOPS!!! | ++------------------------------------------------------------------------+ + +We dirty-log for gfn1, that means gfn2 is lost in dirty-bitmap. + +For direct sp, we can easily avoid it since the spte of direct sp is fixed +to gfn. For indirect sp, before we do cmpxchg, we call gfn_to_pfn_atomic() +to pin gfn to pfn, because after gfn_to_pfn_atomic(): + +- We have held the refcount of pfn that means the pfn can not be freed and + be reused for another gfn. +- The pfn is writable that means it can not be shared between different gfns + by KSM. + +Then, we can ensure the dirty bitmaps is correctly set for a gfn. + +Currently, to simplify the whole things, we disable fast page fault for +indirect shadow page. + +2) Dirty bit tracking + +In the origin code, the spte can be fast updated (non-atomically) if the +spte is read-only and the Accessed bit has already been set since the +Accessed bit and Dirty bit can not be lost. + +But it is not true after fast page fault since the spte can be marked +writable between reading spte and updating spte. Like below case: + ++------------------------------------------------------------------------+ +| At the beginning:: | +| | +| spte.W = 0 | +| spte.Accessed = 1 | ++------------------------------------+-----------------------------------+ +| CPU 0: | CPU 1: | ++------------------------------------+-----------------------------------+ +| In mmu_spte_clear_track_bits():: | | +| | | +| old_spte = *spte; | | +| | | +| | | +| /* 'if' condition is satisfied. */| | +| if (old_spte.Accessed == 1 && | | +| old_spte.W == 0) | | +| spte = 0ull; | | ++------------------------------------+-----------------------------------+ +| | on fast page fault path:: | +| | | +| | spte.W = 1 | +| | | +| | memory write on the spte:: | +| | | +| | spte.Dirty = 1 | ++------------------------------------+-----------------------------------+ +| :: | | +| | | +| else | | +| old_spte = xchg(spte, 0ull) | | +| if (old_spte.Accessed == 1) | | +| kvm_set_pfn_accessed(spte.pfn);| | +| if (old_spte.Dirty == 1) | | +| kvm_set_pfn_dirty(spte.pfn); | | +| OOPS!!! | | ++------------------------------------+-----------------------------------+ + +The Dirty bit is lost in this case. + +In order to avoid this kind of issue, we always treat the spte as "volatile" +if it can be updated out of mmu-lock, see spte_has_volatile_bits(), it means, +the spte is always atomically updated in this case. + +3) flush tlbs due to spte updated + +If the spte is updated from writable to readonly, we should flush all TLBs, +otherwise rmap_write_protect will find a read-only spte, even though the +writable spte might be cached on a CPU's TLB. + +As mentioned before, the spte can be updated to writable out of mmu-lock on +fast page fault path, in order to easily audit the path, we see if TLBs need +be flushed caused by this reason in mmu_spte_update() since this is a common +function to update spte (present -> present). + +Since the spte is "volatile" if it can be updated out of mmu-lock, we always +atomically update the spte, the race caused by fast page fault can be avoided, +See the comments in spte_has_volatile_bits() and mmu_spte_update(). + +Lockless Access Tracking: + +This is used for Intel CPUs that are using EPT but do not support the EPT A/D +bits. In this case, when the KVM MMU notifier is called to track accesses to a +page (via kvm_mmu_notifier_clear_flush_young), it marks the PTE as not-present +by clearing the RWX bits in the PTE and storing the original R & X bits in +some unused/ignored bits. In addition, the SPTE_SPECIAL_MASK is also set on the +PTE (using the ignored bit 62). When the VM tries to access the page later on, +a fault is generated and the fast page fault mechanism described above is used +to atomically restore the PTE to a Present state. The W bit is not saved when +the PTE is marked for access tracking and during restoration to the Present +state, the W bit is set depending on whether or not it was a write access. If +it wasn't, then the W bit will remain clear until a write access happens, at +which time it will be set using the Dirty tracking mechanism described above. + +3. Reference +------------ + +:Name: kvm_lock +:Type: mutex +:Arch: any +:Protects: - vm_list + +:Name: kvm_count_lock +:Type: raw_spinlock_t +:Arch: any +:Protects: - hardware virtualization enable/disable +:Comment: 'raw' because hardware enabling/disabling must be atomic /wrt + migration. + +:Name: kvm_arch::tsc_write_lock +:Type: raw_spinlock +:Arch: x86 +:Protects: - kvm_arch::{last_tsc_write,last_tsc_nsec,last_tsc_offset} + - tsc offset in vmcb +:Comment: 'raw' because updating the tsc offsets must not be preempted. + +:Name: kvm->mmu_lock +:Type: spinlock_t +:Arch: any +:Protects: -shadow page/shadow tlb entry +:Comment: it is a spinlock since it is used in mmu notifier. + +:Name: kvm->srcu +:Type: srcu lock +:Arch: any +:Protects: - kvm->memslots + - kvm->buses +:Comment: The srcu read lock must be held while accessing memslots (e.g. + when using gfn_to_* functions) and while accessing in-kernel + MMIO/PIO address->device structure mapping (kvm->buses). + The srcu index can be stored in kvm_vcpu->srcu_idx per vcpu + if it is needed by multiple functions. + +:Name: blocked_vcpu_on_cpu_lock +:Type: spinlock_t +:Arch: x86 +:Protects: blocked_vcpu_on_cpu +:Comment: This is a per-CPU lock and it is used for VT-d posted-interrupts. + When VT-d posted-interrupts is supported and the VM has assigned + devices, we put the blocked vCPU on the list blocked_vcpu_on_cpu + protected by blocked_vcpu_on_cpu_lock, when VT-d hardware issues + wakeup notification event since external interrupts from the + assigned devices happens, we will find the vCPU on the list to + wakeup. diff --git a/Documentation/virt/kvm/locking.txt b/Documentation/virt/kvm/locking.txt deleted file mode 100644 index 635cd6eaf71495e081de44774e489d622323fcf4..0000000000000000000000000000000000000000 --- a/Documentation/virt/kvm/locking.txt +++ /dev/null @@ -1,215 +0,0 @@ -KVM Lock Overview -================= - -1. Acquisition Orders ---------------------- - -The acquisition orders for mutexes are as follows: - -- kvm->lock is taken outside vcpu->mutex - -- kvm->lock is taken outside kvm->slots_lock and kvm->irq_lock - -- kvm->slots_lock is taken outside kvm->irq_lock, though acquiring - them together is quite rare. - -On x86, vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock. - -Everything else is a leaf: no other lock is taken inside the critical -sections. - -2: Exception ------------- - -Fast page fault: - -Fast page fault is the fast path which fixes the guest page fault out of -the mmu-lock on x86. Currently, the page fault can be fast in one of the -following two cases: - -1. Access Tracking: The SPTE is not present, but it is marked for access -tracking i.e. the SPTE_SPECIAL_MASK is set. That means we need to -restore the saved R/X bits. This is described in more detail later below. - -2. Write-Protection: The SPTE is present and the fault is -caused by write-protect. That means we just need to change the W bit of the -spte. - -What we use to avoid all the race is the SPTE_HOST_WRITEABLE bit and -SPTE_MMU_WRITEABLE bit on the spte: -- SPTE_HOST_WRITEABLE means the gfn is writable on host. -- SPTE_MMU_WRITEABLE means the gfn is writable on mmu. The bit is set when - the gfn is writable on guest mmu and it is not write-protected by shadow - page write-protection. - -On fast page fault path, we will use cmpxchg to atomically set the spte W -bit if spte.SPTE_HOST_WRITEABLE = 1 and spte.SPTE_WRITE_PROTECT = 1, or -restore the saved R/X bits if VMX_EPT_TRACK_ACCESS mask is set, or both. This -is safe because whenever changing these bits can be detected by cmpxchg. - -But we need carefully check these cases: -1): The mapping from gfn to pfn -The mapping from gfn to pfn may be changed since we can only ensure the pfn -is not changed during cmpxchg. This is a ABA problem, for example, below case -will happen: - -At the beginning: -gpte = gfn1 -gfn1 is mapped to pfn1 on host -spte is the shadow page table entry corresponding with gpte and -spte = pfn1 - - VCPU 0 VCPU0 -on fast page fault path: - - old_spte = *spte; - pfn1 is swapped out: - spte = 0; - - pfn1 is re-alloced for gfn2. - - gpte is changed to point to - gfn2 by the guest: - spte = pfn1; - - if (cmpxchg(spte, old_spte, old_spte+W) - mark_page_dirty(vcpu->kvm, gfn1) - OOPS!!! - -We dirty-log for gfn1, that means gfn2 is lost in dirty-bitmap. - -For direct sp, we can easily avoid it since the spte of direct sp is fixed -to gfn. For indirect sp, before we do cmpxchg, we call gfn_to_pfn_atomic() -to pin gfn to pfn, because after gfn_to_pfn_atomic(): -- We have held the refcount of pfn that means the pfn can not be freed and - be reused for another gfn. -- The pfn is writable that means it can not be shared between different gfns - by KSM. - -Then, we can ensure the dirty bitmaps is correctly set for a gfn. - -Currently, to simplify the whole things, we disable fast page fault for -indirect shadow page. - -2): Dirty bit tracking -In the origin code, the spte can be fast updated (non-atomically) if the -spte is read-only and the Accessed bit has already been set since the -Accessed bit and Dirty bit can not be lost. - -But it is not true after fast page fault since the spte can be marked -writable between reading spte and updating spte. Like below case: - -At the beginning: -spte.W = 0 -spte.Accessed = 1 - - VCPU 0 VCPU0 -In mmu_spte_clear_track_bits(): - - old_spte = *spte; - - /* 'if' condition is satisfied. */ - if (old_spte.Accessed == 1 && - old_spte.W == 0) - spte = 0ull; - on fast page fault path: - spte.W = 1 - memory write on the spte: - spte.Dirty = 1 - - - else - old_spte = xchg(spte, 0ull) - - - if (old_spte.Accessed == 1) - kvm_set_pfn_accessed(spte.pfn); - if (old_spte.Dirty == 1) - kvm_set_pfn_dirty(spte.pfn); - OOPS!!! - -The Dirty bit is lost in this case. - -In order to avoid this kind of issue, we always treat the spte as "volatile" -if it can be updated out of mmu-lock, see spte_has_volatile_bits(), it means, -the spte is always atomically updated in this case. - -3): flush tlbs due to spte updated -If the spte is updated from writable to readonly, we should flush all TLBs, -otherwise rmap_write_protect will find a read-only spte, even though the -writable spte might be cached on a CPU's TLB. - -As mentioned before, the spte can be updated to writable out of mmu-lock on -fast page fault path, in order to easily audit the path, we see if TLBs need -be flushed caused by this reason in mmu_spte_update() since this is a common -function to update spte (present -> present). - -Since the spte is "volatile" if it can be updated out of mmu-lock, we always -atomically update the spte, the race caused by fast page fault can be avoided, -See the comments in spte_has_volatile_bits() and mmu_spte_update(). - -Lockless Access Tracking: - -This is used for Intel CPUs that are using EPT but do not support the EPT A/D -bits. In this case, when the KVM MMU notifier is called to track accesses to a -page (via kvm_mmu_notifier_clear_flush_young), it marks the PTE as not-present -by clearing the RWX bits in the PTE and storing the original R & X bits in -some unused/ignored bits. In addition, the SPTE_SPECIAL_MASK is also set on the -PTE (using the ignored bit 62). When the VM tries to access the page later on, -a fault is generated and the fast page fault mechanism described above is used -to atomically restore the PTE to a Present state. The W bit is not saved when -the PTE is marked for access tracking and during restoration to the Present -state, the W bit is set depending on whether or not it was a write access. If -it wasn't, then the W bit will remain clear until a write access happens, at -which time it will be set using the Dirty tracking mechanism described above. - -3. Reference ------------- - -Name: kvm_lock -Type: mutex -Arch: any -Protects: - vm_list - -Name: kvm_count_lock -Type: raw_spinlock_t -Arch: any -Protects: - hardware virtualization enable/disable -Comment: 'raw' because hardware enabling/disabling must be atomic /wrt - migration. - -Name: kvm_arch::tsc_write_lock -Type: raw_spinlock -Arch: x86 -Protects: - kvm_arch::{last_tsc_write,last_tsc_nsec,last_tsc_offset} - - tsc offset in vmcb -Comment: 'raw' because updating the tsc offsets must not be preempted. - -Name: kvm->mmu_lock -Type: spinlock_t -Arch: any -Protects: -shadow page/shadow tlb entry -Comment: it is a spinlock since it is used in mmu notifier. - -Name: kvm->srcu -Type: srcu lock -Arch: any -Protects: - kvm->memslots - - kvm->buses -Comment: The srcu read lock must be held while accessing memslots (e.g. - when using gfn_to_* functions) and while accessing in-kernel - MMIO/PIO address->device structure mapping (kvm->buses). - The srcu index can be stored in kvm_vcpu->srcu_idx per vcpu - if it is needed by multiple functions. - -Name: blocked_vcpu_on_cpu_lock -Type: spinlock_t -Arch: x86 -Protects: blocked_vcpu_on_cpu -Comment: This is a per-CPU lock and it is used for VT-d posted-interrupts. - When VT-d posted-interrupts is supported and the VM has assigned - devices, we put the blocked vCPU on the list blocked_vcpu_on_cpu - protected by blocked_vcpu_on_cpu_lock, when VT-d hardware issues - wakeup notification event since external interrupts from the - assigned devices happens, we will find the vCPU on the list to - wakeup. diff --git a/Documentation/virt/kvm/mmu.txt b/Documentation/virt/kvm/mmu.rst similarity index 94% rename from Documentation/virt/kvm/mmu.txt rename to Documentation/virt/kvm/mmu.rst index dadb29e8738fea131243a6cb8567a5fd5b6895c1..60981887d20b847ee5fa71719a04d44e6d2b8a65 100644 --- a/Documentation/virt/kvm/mmu.txt +++ b/Documentation/virt/kvm/mmu.rst @@ -1,3 +1,6 @@ +.. SPDX-License-Identifier: GPL-2.0 + +====================== The x86 kvm shadow mmu ====================== @@ -7,27 +10,37 @@ physical addresses to host physical addresses. The mmu code attempts to satisfy the following requirements: -- correctness: the guest should not be able to determine that it is running +- correctness: + the guest should not be able to determine that it is running on an emulated mmu except for timing (we attempt to comply with the specification, not emulate the characteristics of a particular implementation such as tlb size) -- security: the guest must not be able to touch host memory not assigned +- security: + the guest must not be able to touch host memory not assigned to it -- performance: minimize the performance penalty imposed by the mmu -- scaling: need to scale to large memory and large vcpu guests -- hardware: support the full range of x86 virtualization hardware -- integration: Linux memory management code must be in control of guest memory +- performance: + minimize the performance penalty imposed by the mmu +- scaling: + need to scale to large memory and large vcpu guests +- hardware: + support the full range of x86 virtualization hardware +- integration: + Linux memory management code must be in control of guest memory so that swapping, page migration, page merging, transparent hugepages, and similar features work without change -- dirty tracking: report writes to guest memory to enable live migration +- dirty tracking: + report writes to guest memory to enable live migration and framebuffer-based displays -- footprint: keep the amount of pinned kernel memory low (most memory +- footprint: + keep the amount of pinned kernel memory low (most memory should be shrinkable) -- reliability: avoid multipage or GFP_ATOMIC allocations +- reliability: + avoid multipage or GFP_ATOMIC allocations Acronyms ======== +==== ==================================================================== pfn host page frame number hpa host physical address hva host virtual address @@ -41,6 +54,7 @@ pte page table entry (used also to refer generically to paging structure gpte guest pte (referring to gfns) spte shadow pte (referring to pfns) tdp two dimensional paging (vendor neutral term for NPT and EPT) +==== ==================================================================== Virtual and real hardware supported =================================== @@ -90,11 +104,13 @@ Events The mmu is driven by events, some from the guest, some from the host. Guest generated events: + - writes to control registers (especially cr3) - invlpg/invlpga instruction execution - access to missing or protected translations Host generated events: + - changes in the gpa->hpa translation (either through gpa->hva changes or through hva->hpa changes) - memory pressure (the shrinker) @@ -117,16 +133,19 @@ Leaf ptes point at guest pages. The following table shows translations encoded by leaf ptes, with higher-level translations in parentheses: - Non-nested guests: + Non-nested guests:: + nonpaging: gpa->hpa paging: gva->gpa->hpa paging, tdp: (gva->)gpa->hpa - Nested guests: + + Nested guests:: + non-tdp: ngva->gpa->hpa (*) tdp: (ngva->)ngpa->gpa->hpa -(*) the guest hypervisor will encode the ngva->gpa translation into its page - tables if npt is not present + (*) the guest hypervisor will encode the ngva->gpa translation into its page + tables if npt is not present Shadow pages contain the following information: role.level: @@ -291,28 +310,41 @@ Handling a page fault is performed as follows: - if the RSV bit of the error code is set, the page fault is caused by guest accessing MMIO and cached MMIO information is available. + - walk shadow page table - check for valid generation number in the spte (see "Fast invalidation of MMIO sptes" below) - cache the information to vcpu->arch.mmio_gva, vcpu->arch.mmio_access and vcpu->arch.mmio_gfn, and call the emulator + - If both P bit and R/W bit of error code are set, this could possibly be handled as a "fast page fault" (fixed without taking the MMU lock). See the description in Documentation/virt/kvm/locking.txt. + - if needed, walk the guest page tables to determine the guest translation (gva->gpa or ngpa->gpa) + - if permissions are insufficient, reflect the fault back to the guest + - determine the host page + - if this is an mmio request, there is no host page; cache the info to vcpu->arch.mmio_gva, vcpu->arch.mmio_access and vcpu->arch.mmio_gfn + - walk the shadow page table to find the spte for the translation, instantiating missing intermediate page tables as necessary + - If this is an mmio request, cache the mmio info to the spte and set some reserved bit on the spte (see callers of kvm_mmu_set_mmio_spte_mask) + - try to unsynchronize the page + - if successful, we can let the guest continue and modify the gpte + - emulate the instruction + - if failed, unshadow the page and let the guest continue + - update any translations that were modified by the instruction invlpg handling: @@ -324,10 +356,12 @@ invlpg handling: Guest control register updates: - mov to cr3 + - look up new shadow roots - synchronize newly reachable shadow pages - mov to cr0/cr4/efer + - set up mmu context for new paging mode - look up new shadow roots - synchronize newly reachable shadow pages @@ -358,6 +392,7 @@ on fault type: (user write faults generate a #PF) In the first case there are two additional complications: + - if CR4.SMEP is enabled: since we've turned the page into a kernel page, the kernel may now execute it. We handle this by also setting spte.nx. If we get a user fetch or read fault, we'll change spte.u=1 and @@ -446,4 +481,3 @@ Further reading - NPT presentation from KVM Forum 2008 http://www.linux-kvm.org/images/c/c8/KvmForum2008%24kdf2008_21.pdf - diff --git a/Documentation/virt/kvm/msr.txt b/Documentation/virt/kvm/msr.rst similarity index 74% rename from Documentation/virt/kvm/msr.txt rename to Documentation/virt/kvm/msr.rst index df1f4338b3caf3e466e783fec42b767cef1ad72c..33892036672d4facfb07294ef09bc29adfe648fe 100644 --- a/Documentation/virt/kvm/msr.txt +++ b/Documentation/virt/kvm/msr.rst @@ -1,6 +1,10 @@ -KVM-specific MSRs. -Glauber Costa , Red Hat Inc, 2010 -===================================================== +.. SPDX-License-Identifier: GPL-2.0 + +================= +KVM-specific MSRs +================= + +:Author: Glauber Costa , Red Hat Inc, 2010 KVM makes use of some custom MSRs to service some requests. @@ -9,34 +13,39 @@ Custom MSRs have a range reserved for them, that goes from but they are deprecated and their use is discouraged. Custom MSR list --------- +--------------- The current supported Custom MSR list is: -MSR_KVM_WALL_CLOCK_NEW: 0x4b564d00 +MSR_KVM_WALL_CLOCK_NEW: + 0x4b564d00 - data: 4-byte alignment physical address of a memory area which must be +data: + 4-byte alignment physical address of a memory area which must be in guest RAM. This memory is expected to hold a copy of the following - structure: + structure:: - struct pvclock_wall_clock { + struct pvclock_wall_clock { u32 version; u32 sec; u32 nsec; - } __attribute__((__packed__)); + } __attribute__((__packed__)); whose data will be filled in by the hypervisor. The hypervisor is only guaranteed to update this data at the moment of MSR write. Users that want to reliably query this information more than once have to write more than once to this MSR. Fields have the following meanings: - version: guest has to check version before and after grabbing + version: + guest has to check version before and after grabbing time information and check that they are both equal and even. An odd version indicates an in-progress update. - sec: number of seconds for wallclock at time of boot. + sec: + number of seconds for wallclock at time of boot. - nsec: number of nanoseconds for wallclock at time of boot. + nsec: + number of nanoseconds for wallclock at time of boot. In order to get the current wallclock time, the system_time from MSR_KVM_SYSTEM_TIME_NEW needs to be added. @@ -47,13 +56,15 @@ MSR_KVM_WALL_CLOCK_NEW: 0x4b564d00 Availability of this MSR must be checked via bit 3 in 0x4000001 cpuid leaf prior to usage. -MSR_KVM_SYSTEM_TIME_NEW: 0x4b564d01 +MSR_KVM_SYSTEM_TIME_NEW: + 0x4b564d01 - data: 4-byte aligned physical address of a memory area which must be in +data: + 4-byte aligned physical address of a memory area which must be in guest RAM, plus an enable bit in bit 0. This memory is expected to hold - a copy of the following structure: + a copy of the following structure:: - struct pvclock_vcpu_time_info { + struct pvclock_vcpu_time_info { u32 version; u32 pad0; u64 tsc_timestamp; @@ -62,7 +73,7 @@ MSR_KVM_SYSTEM_TIME_NEW: 0x4b564d01 s8 tsc_shift; u8 flags; u8 pad[2]; - } __attribute__((__packed__)); /* 32 bytes */ + } __attribute__((__packed__)); /* 32 bytes */ whose data will be filled in by the hypervisor periodically. Only one write, or registration, is needed for each VCPU. The interval between @@ -72,23 +83,28 @@ MSR_KVM_SYSTEM_TIME_NEW: 0x4b564d01 Fields have the following meanings: - version: guest has to check version before and after grabbing + version: + guest has to check version before and after grabbing time information and check that they are both equal and even. An odd version indicates an in-progress update. - tsc_timestamp: the tsc value at the current VCPU at the time + tsc_timestamp: + the tsc value at the current VCPU at the time of the update of this structure. Guests can subtract this value from current tsc to derive a notion of elapsed time since the structure update. - system_time: a host notion of monotonic time, including sleep + system_time: + a host notion of monotonic time, including sleep time at the time this structure was last updated. Unit is nanoseconds. - tsc_to_system_mul: multiplier to be used when converting + tsc_to_system_mul: + multiplier to be used when converting tsc-related quantity to nanoseconds - tsc_shift: shift to be used when converting tsc-related + tsc_shift: + shift to be used when converting tsc-related quantity to nanoseconds. This shift will ensure that multiplication with tsc_to_system_mul does not overflow. A positive value denotes a left shift, a negative value @@ -96,7 +112,7 @@ MSR_KVM_SYSTEM_TIME_NEW: 0x4b564d01 The conversion from tsc to nanoseconds involves an additional right shift by 32 bits. With this information, guests can - derive per-CPU time by doing: + derive per-CPU time by doing:: time = (current_tsc - tsc_timestamp) if (tsc_shift >= 0) @@ -106,29 +122,34 @@ MSR_KVM_SYSTEM_TIME_NEW: 0x4b564d01 time = (time * tsc_to_system_mul) >> 32 time = time + system_time - flags: bits in this field indicate extended capabilities + flags: + bits in this field indicate extended capabilities coordinated between the guest and the hypervisor. Availability of specific flags has to be checked in 0x40000001 cpuid leaf. Current flags are: - flag bit | cpuid bit | meaning - ------------------------------------------------------------- - | | time measures taken across - 0 | 24 | multiple cpus are guaranteed to - | | be monotonic - ------------------------------------------------------------- - | | guest vcpu has been paused by - 1 | N/A | the host - | | See 4.70 in api.txt - ------------------------------------------------------------- + + +-----------+--------------+----------------------------------+ + | flag bit | cpuid bit | meaning | + +-----------+--------------+----------------------------------+ + | | | time measures taken across | + | 0 | 24 | multiple cpus are guaranteed to | + | | | be monotonic | + +-----------+--------------+----------------------------------+ + | | | guest vcpu has been paused by | + | 1 | N/A | the host | + | | | See 4.70 in api.txt | + +-----------+--------------+----------------------------------+ Availability of this MSR must be checked via bit 3 in 0x4000001 cpuid leaf prior to usage. -MSR_KVM_WALL_CLOCK: 0x11 +MSR_KVM_WALL_CLOCK: + 0x11 - data and functioning: same as MSR_KVM_WALL_CLOCK_NEW. Use that instead. +data and functioning: + same as MSR_KVM_WALL_CLOCK_NEW. Use that instead. This MSR falls outside the reserved KVM range and may be removed in the future. Its usage is deprecated. @@ -136,9 +157,11 @@ MSR_KVM_WALL_CLOCK: 0x11 Availability of this MSR must be checked via bit 0 in 0x4000001 cpuid leaf prior to usage. -MSR_KVM_SYSTEM_TIME: 0x12 +MSR_KVM_SYSTEM_TIME: + 0x12 - data and functioning: same as MSR_KVM_SYSTEM_TIME_NEW. Use that instead. +data and functioning: + same as MSR_KVM_SYSTEM_TIME_NEW. Use that instead. This MSR falls outside the reserved KVM range and may be removed in the future. Its usage is deprecated. @@ -146,7 +169,7 @@ MSR_KVM_SYSTEM_TIME: 0x12 Availability of this MSR must be checked via bit 0 in 0x4000001 cpuid leaf prior to usage. - The suggested algorithm for detecting kvmclock presence is then: + The suggested algorithm for detecting kvmclock presence is then:: if (!kvm_para_available()) /* refer to cpuid.txt */ return NON_PRESENT; @@ -163,8 +186,11 @@ MSR_KVM_SYSTEM_TIME: 0x12 } else return NON_PRESENT; -MSR_KVM_ASYNC_PF_EN: 0x4b564d02 - data: Bits 63-6 hold 64-byte aligned physical address of a +MSR_KVM_ASYNC_PF_EN: + 0x4b564d02 + +data: + Bits 63-6 hold 64-byte aligned physical address of a 64 byte memory area which must be in guest RAM and must be zeroed. Bits 5-3 are reserved and should be zero. Bit 0 is 1 when asynchronous page faults are enabled on the vcpu 0 when @@ -200,20 +226,22 @@ MSR_KVM_ASYNC_PF_EN: 0x4b564d02 Currently type 2 APF will be always delivered on the same vcpu as type 1 was, but guest should not rely on that. -MSR_KVM_STEAL_TIME: 0x4b564d03 +MSR_KVM_STEAL_TIME: + 0x4b564d03 - data: 64-byte alignment physical address of a memory area which must be +data: + 64-byte alignment physical address of a memory area which must be in guest RAM, plus an enable bit in bit 0. This memory is expected to - hold a copy of the following structure: + hold a copy of the following structure:: - struct kvm_steal_time { + struct kvm_steal_time { __u64 steal; __u32 version; __u32 flags; __u8 preempted; __u8 u8_pad[3]; __u32 pad[11]; - } + } whose data will be filled in by the hypervisor periodically. Only one write, or registration, is needed for each VCPU. The interval between @@ -224,25 +252,32 @@ MSR_KVM_STEAL_TIME: 0x4b564d03 Fields have the following meanings: - version: a sequence counter. In other words, guest has to check + version: + a sequence counter. In other words, guest has to check this field before and after grabbing time information and make sure they are both equal and even. An odd version indicates an in-progress update. - flags: At this point, always zero. May be used to indicate + flags: + At this point, always zero. May be used to indicate changes in this structure in the future. - steal: the amount of time in which this vCPU did not run, in + steal: + the amount of time in which this vCPU did not run, in nanoseconds. Time during which the vcpu is idle, will not be reported as steal time. - preempted: indicate the vCPU who owns this struct is running or + preempted: + indicate the vCPU who owns this struct is running or not. Non-zero values mean the vCPU has been preempted. Zero means the vCPU is not preempted. NOTE, it is always zero if the the hypervisor doesn't support this field. -MSR_KVM_EOI_EN: 0x4b564d04 - data: Bit 0 is 1 when PV end of interrupt is enabled on the vcpu; 0 +MSR_KVM_EOI_EN: + 0x4b564d04 + +data: + Bit 0 is 1 when PV end of interrupt is enabled on the vcpu; 0 when disabled. Bit 1 is reserved and must be zero. When PV end of interrupt is enabled (bit 0 set), bits 63-2 hold a 4-byte aligned physical address of a 4 byte memory area which must be in guest RAM and @@ -274,11 +309,13 @@ MSR_KVM_EOI_EN: 0x4b564d04 clear it using a single CPU instruction, such as test and clear, or compare and exchange. -MSR_KVM_POLL_CONTROL: 0x4b564d05 +MSR_KVM_POLL_CONTROL: + 0x4b564d05 + Control host-side polling. - data: Bit 0 enables (1) or disables (0) host-side HLT polling logic. +data: + Bit 0 enables (1) or disables (0) host-side HLT polling logic. KVM guests can request the host not to poll on HLT, for example if they are performing polling themselves. - diff --git a/Documentation/virt/kvm/nested-vmx.txt b/Documentation/virt/kvm/nested-vmx.rst similarity index 90% rename from Documentation/virt/kvm/nested-vmx.txt rename to Documentation/virt/kvm/nested-vmx.rst index 97eb1353e9624463d846dee3f944ac69c6b1704a..592b0ab6970b14fed9f5f57e8790a426a331695b 100644 --- a/Documentation/virt/kvm/nested-vmx.txt +++ b/Documentation/virt/kvm/nested-vmx.rst @@ -1,3 +1,6 @@ +.. SPDX-License-Identifier: GPL-2.0 + +========== Nested VMX ========== @@ -41,9 +44,9 @@ No modifications are required to user space (qemu). However, qemu's default emulated CPU type (qemu64) does not list the "VMX" CPU feature, so it must be explicitly enabled, by giving qemu one of the following options: - -cpu host (emulated CPU has all features of the real CPU) + - cpu host (emulated CPU has all features of the real CPU) - -cpu qemu64,+vmx (add just the vmx feature to a named CPU type) + - cpu qemu64,+vmx (add just the vmx feature to a named CPU type) ABIs @@ -75,6 +78,8 @@ of this structure changes, this can break live migration across KVM versions. VMCS12_REVISION (from vmx.c) should be changed if struct vmcs12 or its inner struct shadow_vmcs is ever changed. +:: + typedef u64 natural_width; struct __packed vmcs12 { /* According to the Intel spec, a VMCS region must start with @@ -220,21 +225,21 @@ Authors ------- These patches were written by: - Abel Gordon, abelg il.ibm.com - Nadav Har'El, nyh il.ibm.com - Orit Wasserman, oritw il.ibm.com - Ben-Ami Yassor, benami il.ibm.com - Muli Ben-Yehuda, muli il.ibm.com + - Abel Gordon, abelg il.ibm.com + - Nadav Har'El, nyh il.ibm.com + - Orit Wasserman, oritw il.ibm.com + - Ben-Ami Yassor, benami il.ibm.com + - Muli Ben-Yehuda, muli il.ibm.com With contributions by: - Anthony Liguori, aliguori us.ibm.com - Mike Day, mdday us.ibm.com - Michael Factor, factor il.ibm.com - Zvi Dubitzky, dubi il.ibm.com + - Anthony Liguori, aliguori us.ibm.com + - Mike Day, mdday us.ibm.com + - Michael Factor, factor il.ibm.com + - Zvi Dubitzky, dubi il.ibm.com And valuable reviews by: - Avi Kivity, avi redhat.com - Gleb Natapov, gleb redhat.com - Marcelo Tosatti, mtosatti redhat.com - Kevin Tian, kevin.tian intel.com - and others. + - Avi Kivity, avi redhat.com + - Gleb Natapov, gleb redhat.com + - Marcelo Tosatti, mtosatti redhat.com + - Kevin Tian, kevin.tian intel.com + - and others. diff --git a/Documentation/virt/kvm/ppc-pv.txt b/Documentation/virt/kvm/ppc-pv.rst similarity index 91% rename from Documentation/virt/kvm/ppc-pv.txt rename to Documentation/virt/kvm/ppc-pv.rst index e26115ce4258bdefb369a73ecb3371108bce2393..5fdb907670be01ecdf1e44fbcaa99dbc2480985e 100644 --- a/Documentation/virt/kvm/ppc-pv.txt +++ b/Documentation/virt/kvm/ppc-pv.rst @@ -1,3 +1,6 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================================= The PPC KVM paravirtual interface ================================= @@ -34,8 +37,9 @@ up the hypercall. To call a hypercall, just call these instructions. The parameters are as follows: + ======== ================ ================ Register IN OUT - + ======== ================ ================ r0 - volatile r3 1st parameter Return code r4 2nd parameter 1st output value @@ -47,6 +51,7 @@ The parameters are as follows: r10 8th parameter 7th output value r11 hypercall number 8th output value r12 - volatile + ======== ================ ================ Hypercall definitions are shared in generic code, so the same hypercall numbers apply for x86 and powerpc alike with the exception that each KVM hypercall @@ -54,11 +59,13 @@ also needs to be ORed with the KVM vendor code which is (42 << 16). Return codes can be as follows: + ==== ========================= Code Meaning - + ==== ========================= 0 Success 12 Hypercall not implemented <0 Error + ==== ========================= The magic page ============== @@ -72,7 +79,7 @@ desired location. The first parameter indicates the effective address when the MMU is enabled. The second parameter indicates the address in real mode, if applicable to the target. For now, we always map the page to -4096. This way we can access it using absolute load and store functions. The following -instruction reads the first field of the magic page: +instruction reads the first field of the magic page:: ld rX, -4096(0) @@ -93,8 +100,10 @@ a bitmap of available features inside the magic page. The following enhancements to the magic page are currently available: + ============================ ======================================= KVM_MAGIC_FEAT_SR Maps SR registers r/w in the magic page KVM_MAGIC_FEAT_MAS0_TO_SPRG7 Maps MASn, ESR, PIR and high SPRGs + ============================ ======================================= For enhanced features in the magic page, please check for the existence of the feature before using them! @@ -121,8 +130,8 @@ when entering the guest or don't have any impact on the hypervisor's behavior. The following bits are safe to be set inside the guest: - MSR_EE - MSR_RI + - MSR_EE + - MSR_RI If any other bit changes in the MSR, please still use mtmsr(d). @@ -138,9 +147,9 @@ guest. Implementing any of those mappings is optional, as the instruction traps also act on the shared page. So calling privileged instructions still works as before. +======================= ================================ From To -==== == - +======================= ================================ mfmsr rX ld rX, magic_page->msr mfsprg rX, 0 ld rX, magic_page->sprg0 mfsprg rX, 1 ld rX, magic_page->sprg1 @@ -173,7 +182,7 @@ mtsrin rX, rY b [BookE only] wrteei [0|1] b - +======================= ================================ Some instructions require more logic to determine what's going on than a load or store instruction can deliver. To enable patching of those, we keep some @@ -191,6 +200,7 @@ for example. Hypercall ABIs in KVM on PowerPC ================================= + 1) KVM hypercalls (ePAPR) These are ePAPR compliant hypercall implementation (mentioned above). Even diff --git a/Documentation/virt/kvm/review-checklist.txt b/Documentation/virt/kvm/review-checklist.rst similarity index 95% rename from Documentation/virt/kvm/review-checklist.txt rename to Documentation/virt/kvm/review-checklist.rst index 499af499e296fcbdf78e6d65651246a8dc33d10e..1f86a9d3f7057117e30e14add987a5faa8a3f2a0 100644 --- a/Documentation/virt/kvm/review-checklist.txt +++ b/Documentation/virt/kvm/review-checklist.rst @@ -1,3 +1,6 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================================ Review checklist for kvm patches ================================ diff --git a/Documentation/virt/kvm/s390-diag.txt b/Documentation/virt/kvm/s390-diag.rst similarity index 90% rename from Documentation/virt/kvm/s390-diag.txt rename to Documentation/virt/kvm/s390-diag.rst index 7c52e5f8b210357075cc115500638c4b5841bab9..eaac4864d3d62e1c1f35ab7a2518ebf6f293d2d1 100644 --- a/Documentation/virt/kvm/s390-diag.txt +++ b/Documentation/virt/kvm/s390-diag.rst @@ -1,3 +1,6 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============================= The s390 DIAGNOSE call on KVM ============================= @@ -16,12 +19,12 @@ DIAGNOSE calls by the guest cause a mandatory intercept. This implies all supported DIAGNOSE calls need to be handled by either KVM or its userspace. -All DIAGNOSE calls supported by KVM use the RS-a format: +All DIAGNOSE calls supported by KVM use the RS-a format:: --------------------------------------- -| '83' | R1 | R3 | B2 | D2 | --------------------------------------- -0 8 12 16 20 31 + -------------------------------------- + | '83' | R1 | R3 | B2 | D2 | + -------------------------------------- + 0 8 12 16 20 31 The second-operand address (obtained by the base/displacement calculation) is not used to address data. Instead, bits 48-63 of this address specify diff --git a/Documentation/virt/kvm/timekeeping.txt b/Documentation/virt/kvm/timekeeping.rst similarity index 85% rename from Documentation/virt/kvm/timekeeping.txt rename to Documentation/virt/kvm/timekeeping.rst index 76808a17ad84f108f0e895e2aa6ea1bf8d63d500..21ae7efa29ba19bdb6f0a67208e02931cc5f15fc 100644 --- a/Documentation/virt/kvm/timekeeping.txt +++ b/Documentation/virt/kvm/timekeeping.rst @@ -1,17 +1,21 @@ +.. SPDX-License-Identifier: GPL-2.0 - Timekeeping Virtualization for X86-Based Architectures +====================================================== +Timekeeping Virtualization for X86-Based Architectures +====================================================== - Zachary Amsden - Copyright (c) 2010, Red Hat. All rights reserved. +:Author: Zachary Amsden +:Copyright: (c) 2010, Red Hat. All rights reserved. -1) Overview -2) Timing Devices -3) TSC Hardware -4) Virtualization Problems +.. Contents -========================================================================= + 1) Overview + 2) Timing Devices + 3) TSC Hardware + 4) Virtualization Problems -1) Overview +1. Overview +=========== One of the most complicated parts of the X86 platform, and specifically, the virtualization of this platform is the plethora of timing devices available @@ -27,15 +31,15 @@ The purpose of this document is to collect data and information relevant to timekeeping which may be difficult to find elsewhere, specifically, information relevant to KVM and hardware-based virtualization. -========================================================================= - -2) Timing Devices +2. Timing Devices +================= First we discuss the basic hardware devices available. TSC and the related KVM clock are special enough to warrant a full exposition and are described in the following section. -2.1) i8254 - PIT +2.1. i8254 - PIT +---------------- One of the first timer devices available is the programmable interrupt timer, or PIT. The PIT has a fixed frequency 1.193182 MHz base clock and three @@ -50,13 +54,13 @@ The PIT uses I/O ports 0x40 - 0x43. Access to the 16-bit counters is done using single or multiple byte access to the I/O ports. There are 6 modes available, but not all modes are available to all timers, as only timer 2 has a connected gate input, required for modes 1 and 5. The gate line is -controlled by port 61h, bit 0, as illustrated in the following diagram. +controlled by port 61h, bit 0, as illustrated in the following diagram:: - -------------- ---------------- -| | | | -| 1.1932 MHz |---------->| CLOCK OUT | ---------> IRQ 0 -| Clock | | | | - -------------- | +->| GATE TIMER 0 | + -------------- ---------------- + | | | | + | 1.1932 MHz|---------->| CLOCK OUT | ---------> IRQ 0 + | Clock | | | | + -------------- | +->| GATE TIMER 0 | | ---------------- | | ---------------- @@ -70,29 +74,33 @@ controlled by port 61h, bit 0, as illustrated in the following diagram. | | | |------>| CLOCK OUT | ---------> Port 61h, bit 5 | | | -Port 61h, bit 0 ---------->| GATE TIMER 2 | \_.---- ____ + Port 61h, bit 0 -------->| GATE TIMER 2 | \_.---- ____ ---------------- _| )--|LPF|---Speaker / *---- \___/ -Port 61h, bit 1 -----------------------------------/ + Port 61h, bit 1 ---------------------------------/ The timer modes are now described. -Mode 0: Single Timeout. This is a one-shot software timeout that counts down +Mode 0: Single Timeout. + This is a one-shot software timeout that counts down when the gate is high (always true for timers 0 and 1). When the count reaches zero, the output goes high. -Mode 1: Triggered One-shot. The output is initially set high. When the gate +Mode 1: Triggered One-shot. + The output is initially set high. When the gate line is set high, a countdown is initiated (which does not stop if the gate is lowered), during which the output is set low. When the count reaches zero, the output goes high. -Mode 2: Rate Generator. The output is initially set high. When the countdown +Mode 2: Rate Generator. + The output is initially set high. When the countdown reaches 1, the output goes low for one count and then returns high. The value is reloaded and the countdown automatically resumes. If the gate line goes low, the count is halted. If the output is low when the gate is lowered, the output automatically goes high (this only affects timer 2). -Mode 3: Square Wave. This generates a high / low square wave. The count +Mode 3: Square Wave. + This generates a high / low square wave. The count determines the length of the pulse, which alternates between high and low when zero is reached. The count only proceeds when gate is high and is automatically reloaded on reaching zero. The count is decremented twice at @@ -103,12 +111,14 @@ Mode 3: Square Wave. This generates a high / low square wave. The count values are not observed when reading. This is the intended mode for timer 2, which generates sine-like tones by low-pass filtering the square wave output. -Mode 4: Software Strobe. After programming this mode and loading the counter, +Mode 4: Software Strobe. + After programming this mode and loading the counter, the output remains high until the counter reaches zero. Then the output goes low for 1 clock cycle and returns high. The counter is not reloaded. Counting only occurs when gate is high. -Mode 5: Hardware Strobe. After programming and loading the counter, the +Mode 5: Hardware Strobe. + After programming and loading the counter, the output remains high. When the gate is raised, a countdown is initiated (which does not stop if the gate is lowered). When the counter reaches zero, the output goes low for 1 clock cycle and then returns high. The counter is @@ -118,49 +128,49 @@ In addition to normal binary counting, the PIT supports BCD counting. The command port, 0x43 is used to set the counter and mode for each of the three timers. -PIT commands, issued to port 0x43, using the following bit encoding: +PIT commands, issued to port 0x43, using the following bit encoding:: -Bit 7-4: Command (See table below) -Bit 3-1: Mode (000 = Mode 0, 101 = Mode 5, 11X = undefined) -Bit 0 : Binary (0) / BCD (1) + Bit 7-4: Command (See table below) + Bit 3-1: Mode (000 = Mode 0, 101 = Mode 5, 11X = undefined) + Bit 0 : Binary (0) / BCD (1) -Command table: +Command table:: -0000 - Latch Timer 0 count for port 0x40 + 0000 - Latch Timer 0 count for port 0x40 sample and hold the count to be read in port 0x40; additional commands ignored until counter is read; mode bits ignored. -0001 - Set Timer 0 LSB mode for port 0x40 + 0001 - Set Timer 0 LSB mode for port 0x40 set timer to read LSB only and force MSB to zero; mode bits set timer mode -0010 - Set Timer 0 MSB mode for port 0x40 + 0010 - Set Timer 0 MSB mode for port 0x40 set timer to read MSB only and force LSB to zero; mode bits set timer mode -0011 - Set Timer 0 16-bit mode for port 0x40 + 0011 - Set Timer 0 16-bit mode for port 0x40 set timer to read / write LSB first, then MSB; mode bits set timer mode -0100 - Latch Timer 1 count for port 0x41 - as described above -0101 - Set Timer 1 LSB mode for port 0x41 - as described above -0110 - Set Timer 1 MSB mode for port 0x41 - as described above -0111 - Set Timer 1 16-bit mode for port 0x41 - as described above + 0100 - Latch Timer 1 count for port 0x41 - as described above + 0101 - Set Timer 1 LSB mode for port 0x41 - as described above + 0110 - Set Timer 1 MSB mode for port 0x41 - as described above + 0111 - Set Timer 1 16-bit mode for port 0x41 - as described above -1000 - Latch Timer 2 count for port 0x42 - as described above -1001 - Set Timer 2 LSB mode for port 0x42 - as described above -1010 - Set Timer 2 MSB mode for port 0x42 - as described above -1011 - Set Timer 2 16-bit mode for port 0x42 as described above + 1000 - Latch Timer 2 count for port 0x42 - as described above + 1001 - Set Timer 2 LSB mode for port 0x42 - as described above + 1010 - Set Timer 2 MSB mode for port 0x42 - as described above + 1011 - Set Timer 2 16-bit mode for port 0x42 as described above -1101 - General counter latch + 1101 - General counter latch Latch combination of counters into corresponding ports Bit 3 = Counter 2 Bit 2 = Counter 1 Bit 1 = Counter 0 Bit 0 = Unused -1110 - Latch timer status + 1110 - Latch timer status Latch combination of counter mode into corresponding ports Bit 3 = Counter 2 Bit 2 = Counter 1 @@ -177,7 +187,8 @@ Command table: Bit 3-1 = Mode Bit 0 = Binary (0) / BCD mode (1) -2.2) RTC +2.2. RTC +-------- The second device which was available in the original PC was the MC146818 real time clock. The original device is now obsolete, and usually emulated by the @@ -201,21 +212,21 @@ in progress, as indicated in the status register. The clock uses a 32.768kHz crystal, so bits 6-4 of register A should be programmed to a 32kHz divider if the RTC is to count seconds. -This is the RAM map originally used for the RTC/CMOS: - -Location Size Description ------------------------------------------- -00h byte Current second (BCD) -01h byte Seconds alarm (BCD) -02h byte Current minute (BCD) -03h byte Minutes alarm (BCD) -04h byte Current hour (BCD) -05h byte Hours alarm (BCD) -06h byte Current day of week (BCD) -07h byte Current day of month (BCD) -08h byte Current month (BCD) -09h byte Current year (BCD) -0Ah byte Register A +This is the RAM map originally used for the RTC/CMOS:: + + Location Size Description + ------------------------------------------ + 00h byte Current second (BCD) + 01h byte Seconds alarm (BCD) + 02h byte Current minute (BCD) + 03h byte Minutes alarm (BCD) + 04h byte Current hour (BCD) + 05h byte Hours alarm (BCD) + 06h byte Current day of week (BCD) + 07h byte Current day of month (BCD) + 08h byte Current month (BCD) + 09h byte Current year (BCD) + 0Ah byte Register A bit 7 = Update in progress bit 6-4 = Divider for clock 000 = 4.194 MHz @@ -234,7 +245,7 @@ Location Size Description 1101 = 125 mS 1110 = 250 mS 1111 = 500 mS -0Bh byte Register B + 0Bh byte Register B bit 7 = Run (0) / Halt (1) bit 6 = Periodic interrupt enable bit 5 = Alarm interrupt enable @@ -243,19 +254,20 @@ Location Size Description bit 2 = BCD calendar (0) / Binary (1) bit 1 = 12-hour mode (0) / 24-hour mode (1) bit 0 = 0 (DST off) / 1 (DST enabled) -OCh byte Register C (read only) + OCh byte Register C (read only) bit 7 = interrupt request flag (IRQF) bit 6 = periodic interrupt flag (PF) bit 5 = alarm interrupt flag (AF) bit 4 = update interrupt flag (UF) bit 3-0 = reserved -ODh byte Register D (read only) + ODh byte Register D (read only) bit 7 = RTC has power bit 6-0 = reserved -32h byte Current century BCD (*) + 32h byte Current century BCD (*) (*) location vendor specific and now determined from ACPI global tables -2.3) APIC +2.3. APIC +--------- On Pentium and later processors, an on-board timer is available to each CPU as part of the Advanced Programmable Interrupt Controller. The APIC is @@ -276,7 +288,8 @@ timer is programmed through the LVT (local vector timer) register, is capable of one-shot or periodic operation, and is based on the bus clock divided down by the programmable divider register. -2.4) HPET +2.4. HPET +--------- HPET is quite complex, and was originally intended to replace the PIT / RTC support of the X86 PC. It remains to be seen whether that will be the case, as @@ -297,7 +310,8 @@ indicated through ACPI tables by the BIOS. Detailed specification of the HPET is beyond the current scope of this document, as it is also very well documented elsewhere. -2.5) Offboard Timers +2.5. Offboard Timers +-------------------- Several cards, both proprietary (watchdog boards) and commonplace (e1000) have timing chips built into the cards which may have registers which are accessible @@ -307,9 +321,8 @@ general frowned upon as not playing by the agreed rules of the game. Such a timer device would require additional support to be virtualized properly and is not considered important at this time as no known operating system does this. -========================================================================= - -3) TSC Hardware +3. TSC Hardware +=============== The TSC or time stamp counter is relatively simple in theory; it counts instruction cycles issued by the processor, which can be used as a measure of @@ -340,7 +353,8 @@ allows the guest visible TSC to be offset by a constant. Newer implementations promise to allow the TSC to additionally be scaled, but this hardware is not yet widely available. -3.1) TSC synchronization +3.1. TSC synchronization +------------------------ The TSC is a CPU-local clock in most implementations. This means, on SMP platforms, the TSCs of different CPUs may start at different times depending @@ -357,7 +371,8 @@ practice, getting a perfectly synchronized TSC will not be possible unless all values are read from the same clock, which generally only is possible on single socket systems or those with special hardware support. -3.2) TSC and CPU hotplug +3.2. TSC and CPU hotplug +------------------------ As touched on already, CPUs which arrive later than the boot time of the system may not have a TSC value that is synchronized with the rest of the system. @@ -367,7 +382,8 @@ a guarantee. This can have the effect of bringing a system from a state where TSC is synchronized back to a state where TSC synchronization flaws, however small, may be exposed to the OS and any virtualization environment. -3.3) TSC and multi-socket / NUMA +3.3. TSC and multi-socket / NUMA +-------------------------------- Multi-socket systems, especially large multi-socket systems are likely to have individual clocksources rather than a single, universally distributed clock. @@ -385,7 +401,8 @@ standards for telecommunications and computer equipment. It is recommended not to trust the TSCs to remain synchronized on NUMA or multiple socket systems for these reasons. -3.4) TSC and C-states +3.4. TSC and C-states +--------------------- C-states, or idling states of the processor, especially C1E and deeper sleep states may be problematic for TSC as well. The TSC may stop advancing in such @@ -396,7 +413,8 @@ based on CPU and chipset identifications. The TSC in such a case may be corrected by catching it up to a known external clocksource. -3.5) TSC frequency change / P-states +3.5. TSC frequency change / P-states +------------------------------------ To make things slightly more interesting, some CPUs may change frequency. They may or may not run the TSC at the same rate, and because the frequency change @@ -416,14 +434,16 @@ other processors. In such cases, the TSC on halted CPUs could advance faster than that of non-halted processors. AMD Turion processors are known to have this problem. -3.6) TSC and STPCLK / T-states +3.6. TSC and STPCLK / T-states +------------------------------ External signals given to the processor may also have the effect of stopping the TSC. This is typically done for thermal emergency power control to prevent an overheating condition, and typically, there is no way to detect that this condition has happened. -3.7) TSC virtualization - VMX +3.7. TSC virtualization - VMX +----------------------------- VMX provides conditional trapping of RDTSC, RDMSR, WRMSR and RDTSCP instructions, which is enough for full virtualization of TSC in any manner. In @@ -431,14 +451,16 @@ addition, VMX allows passing through the host TSC plus an additional TSC_OFFSET field specified in the VMCS. Special instructions must be used to read and write the VMCS field. -3.8) TSC virtualization - SVM +3.8. TSC virtualization - SVM +----------------------------- SVM provides conditional trapping of RDTSC, RDMSR, WRMSR and RDTSCP instructions, which is enough for full virtualization of TSC in any manner. In addition, SVM allows passing through the host TSC plus an additional offset field specified in the SVM control block. -3.9) TSC feature bits in Linux +3.9. TSC feature bits in Linux +------------------------------ In summary, there is no way to guarantee the TSC remains in perfect synchronization unless it is explicitly guaranteed by the architecture. Even @@ -448,13 +470,16 @@ despite being locally consistent. The following feature bits are used by Linux to signal various TSC attributes, but they can only be taken to be meaningful for UP or single node systems. -X86_FEATURE_TSC : The TSC is available in hardware -X86_FEATURE_RDTSCP : The RDTSCP instruction is available -X86_FEATURE_CONSTANT_TSC : The TSC rate is unchanged with P-states -X86_FEATURE_NONSTOP_TSC : The TSC does not stop in C-states -X86_FEATURE_TSC_RELIABLE : TSC sync checks are skipped (VMware) +========================= ======================================= +X86_FEATURE_TSC The TSC is available in hardware +X86_FEATURE_RDTSCP The RDTSCP instruction is available +X86_FEATURE_CONSTANT_TSC The TSC rate is unchanged with P-states +X86_FEATURE_NONSTOP_TSC The TSC does not stop in C-states +X86_FEATURE_TSC_RELIABLE TSC sync checks are skipped (VMware) +========================= ======================================= -4) Virtualization Problems +4. Virtualization Problems +========================== Timekeeping is especially problematic for virtualization because a number of challenges arise. The most obvious problem is that time is now shared between @@ -473,7 +498,8 @@ BIOS, but not in such an extreme fashion. However, the fact that SMM mode may cause similar problems to virtualization makes it a good justification for solving many of these problems on bare metal. -4.1) Interrupt clocking +4.1. Interrupt clocking +----------------------- One of the most immediate problems that occurs with legacy operating systems is that the system timekeeping routines are often designed to keep track of @@ -502,7 +528,8 @@ thus requires interrupt slewing to keep proper time. It does use a low enough rate (ed: is it 18.2 Hz?) however that it has not yet been a problem in practice. -4.2) TSC sampling and serialization +4.2. TSC sampling and serialization +----------------------------------- As the highest precision time source available, the cycle counter of the CPU has aroused much interest from developers. As explained above, this timer has @@ -524,7 +551,8 @@ it may be necessary for an implementation to guard against "backwards" reads of the TSC as seen from other CPUs, even in an otherwise perfectly synchronized system. -4.3) Timespec aliasing +4.3. Timespec aliasing +---------------------- Additionally, this lack of serialization from the TSC poses another challenge when using results of the TSC when measured against another time source. As @@ -548,7 +576,8 @@ This aliasing requires care in the computation and recalibration of kvmclock and any other values derived from TSC computation (such as TSC virtualization itself). -4.4) Migration +4.4. Migration +-------------- Migration of a virtual machine raises problems for timekeeping in two ways. First, the migration itself may take time, during which interrupts cannot be @@ -566,7 +595,8 @@ always be caught up to the original rate. KVM clock avoids these problems by simply storing multipliers and offsets against the TSC for the guest to convert back into nanosecond resolution values. -4.5) Scheduling +4.5. Scheduling +--------------- Since scheduling may be based on precise timing and firing of interrupts, the scheduling algorithms of an operating system may be adversely affected by @@ -579,7 +609,8 @@ In an attempt to work around this, several implementations have provided a paravirtualized scheduler clock, which reveals the true amount of CPU time for which a virtual machine has been running. -4.6) Watchdogs +4.6. Watchdogs +-------------- Watchdog timers, such as the lock detector in Linux may fire accidentally when running under hardware virtualization due to timer interrupts being delayed or @@ -587,7 +618,8 @@ misinterpretation of the passage of real time. Usually, these warnings are spurious and can be ignored, but in some circumstances it may be necessary to disable such detection. -4.7) Delays and precision timing +4.7. Delays and precision timing +-------------------------------- Precise timing and delays may not be possible in a virtualized system. This can happen if the system is controlling physical hardware, or issues delays to @@ -600,7 +632,8 @@ The second issue may cause performance problems, but this is unlikely to be a significant issue. In many cases these delays may be eliminated through configuration or paravirtualization. -4.8) Covert channels and leaks +4.8. Covert channels and leaks +------------------------------ In addition to the above problems, time information will inevitably leak to the guest about the host in anything but a perfect implementation of virtualized diff --git a/Documentation/virt/uml/UserModeLinux-HOWTO.txt b/Documentation/virt/uml/user_mode_linux.rst similarity index 74% rename from Documentation/virt/uml/UserModeLinux-HOWTO.txt rename to Documentation/virt/uml/user_mode_linux.rst index 87b80f589e1c0163c68365b4a67d623c3563dbc9..de0f0b2c9d5bd5fac524941b8c433f0dc2a2efec 100644 --- a/Documentation/virt/uml/UserModeLinux-HOWTO.txt +++ b/Documentation/virt/uml/user_mode_linux.rst @@ -1,12 +1,17 @@ - User Mode Linux HOWTO - User Mode Linux Core Team - Mon Nov 18 14:16:16 EST 2002 +.. SPDX-License-Identifier: GPL-2.0 - This document describes the use and abuse of Jeff Dike's User Mode - Linux: a port of the Linux kernel as a normal Intel Linux process. - ______________________________________________________________________ +===================== +User Mode Linux HOWTO +===================== - Table of Contents +:Author: User Mode Linux Core Team +:Last-updated: Sat Jan 25 16:07:55 CET 2020 + +This document describes the use and abuse of Jeff Dike's User Mode +Linux: a port of the Linux kernel as a normal Intel Linux process. + + +.. Table of Contents 1. Introduction @@ -132,19 +137,19 @@ 15.5 Other contributions - ______________________________________________________________________ - - 1. Introduction +1. Introduction +================ Welcome to User Mode Linux. It's going to be fun. - 1.1. How is User Mode Linux Different? +1.1. How is User Mode Linux Different? +--------------------------------------- Normally, the Linux Kernel talks straight to your hardware (video card, keyboard, hard drives, etc), and any programs which run ask the - kernel to operate the hardware, like so: + kernel to operate the hardware, like so:: @@ -160,10 +165,10 @@ The User Mode Linux Kernel is different; instead of talking to the - hardware, it talks to a `real' Linux kernel (called the `host kernel' + hardware, it talks to a `real` Linux kernel (called the `host kernel` from now on), like any other program. Programs can then run inside User-Mode Linux as if they were running under a normal kernel, like - so: + so:: @@ -181,7 +186,8 @@ - 1.2. Why Would I Want User Mode Linux? +1.2. Why Would I Want User Mode Linux? +--------------------------------------- 1. If User Mode Linux crashes, your host kernel is still fine. @@ -204,83 +210,41 @@ +.. _Compiling_the_kernel_and_modules: - - 2. Compiling the kernel and modules +2. Compiling the kernel and modules +==================================== - 2.1. Compiling the kernel +2.1. Compiling the kernel +-------------------------- Compiling the user mode kernel is just like compiling any other - kernel. Let's go through the steps, using 2.4.0-prerelease (current - as of this writing) as an example: - - - 1. Download the latest UML patch from - - the download page - . - - - 3. Make a directory and unpack the kernel into it. - + https://mirrors.edge.kernel.org/pub/linux/kernel/v5.x/linux-5.4.14.tar.xz + 2. Make a directory and unpack the kernel into it:: host% mkdir ~/uml - - - - - host% cd ~/uml - - - - - - host% - tar -xzvf linux-2.4.0-prerelease.tar.bz2 - - - - - - - 4. Apply the patch using - - - - host% - cd ~/uml/linux - - - host% - bzcat uml-patch-2.4.0-prerelease.bz2 | patch -p1 + tar xvf linux-5.4.14.tar.xz - - - - - 5. Run your favorite config; `make xconfig ARCH=um' is the most - convenient. `make config ARCH=um' and 'make menuconfig ARCH=um' + 3. Run your favorite config; ``make xconfig ARCH=um`` is the most + convenient. ``make config ARCH=um`` and ``make menuconfig ARCH=um`` will work as well. The defaults will give you a useful kernel. If you want to change something, go ahead, it probably won't hurt anything. @@ -288,44 +252,20 @@ Note: If the host is configured with a 2G/2G address space split rather than the usual 3G/1G split, then the packaged UML binaries - will not run. They will immediately segfault. See ``UML on 2G/2G - hosts'' for the scoop on running UML on your system. - - - - 6. Finish with `make linux ARCH=um': the result is a file called - `linux' in the top directory of your source tree. - - Make sure that you don't build this kernel in /usr/src/linux. On some - distributions, /usr/include/asm is a link into this pool. The user- - mode build changes the other end of that link, and things that include - stop compiling. - - The sources are also available from cvs at the project's cvs page, - which has directions on getting the sources. You can also browse the - CVS pool from there. + will not run. They will immediately segfault. See + :ref:`UML_on_2G/2G_hosts` for the scoop on running UML on your system. - If you get the CVS sources, you will have to check them out into an - empty directory. You will then have to copy each file into the - corresponding directory in the appropriate kernel pool. - If you don't have the latest kernel pool, you can get the - corresponding user-mode sources with + 4. Finish with ``make linux ARCH=um``: the result is a file called + ``linux`` in the top directory of your source tree. - host% cvs co -r v_2_3_x linux - - - - where 'x' is the version in your pool. Note that you will not get the - bug fixes and enhancements that have gone into subsequent releases. - - - 2.2. Compiling and installing kernel modules +2.2. Compiling and installing kernel modules +--------------------------------------------- UML modules are built in the same way as the native kernel (with the - exception of the 'ARCH=um' that you always need for UML): + exception of the 'ARCH=um' that you always need for UML):: host% make modules ARCH=um @@ -337,12 +277,12 @@ the user-mode pool. Modules from the native kernel won't work. You can install them by using ftp or something to copy them into the - virtual machine and dropping them into /lib/modules/`uname -r`. + virtual machine and dropping them into ``/lib/modules/$(uname -r)``. You can also get the kernel build process to install them as follows: 1. with the kernel not booted, mount the root filesystem in the top - level of the kernel pool: + level of the kernel pool:: host% mount root_fs mnt -o loop @@ -352,7 +292,7 @@ - 2. run + 2. run:: host% @@ -363,7 +303,7 @@ - 3. unmount the filesystem + 3. unmount the filesystem:: host% umount mnt @@ -381,27 +321,28 @@ as modules, especially filesystems and network protocols and filters, so most symbols which need to be exported probably already are. However, if you do find symbols that need exporting, let us - know, and + know at http://user-mode-linux.sourceforge.net/, and they'll be "taken care of". - 2.3. Compiling and installing uml_utilities +2.3. Compiling and installing uml_utilities +-------------------------------------------- Many features of the UML kernel require a user-space helper program, so a uml_utilities package is distributed separately from the kernel patch which provides these helpers. Included within this is: - o port-helper - Used by consoles which connect to xterms or ports + - port-helper - Used by consoles which connect to xterms or ports - o tunctl - Configuration tool to create and delete tap devices + - tunctl - Configuration tool to create and delete tap devices - o uml_net - Setuid binary for automatic tap device configuration + - uml_net - Setuid binary for automatic tap device configuration - o uml_switch - User-space virtual switch required for daemon + - uml_switch - User-space virtual switch required for daemon transport - The uml_utilities tree is compiled with: + The uml_utilities tree is compiled with:: host# @@ -423,38 +364,42 @@ - 3. Running UML and logging in +3. Running UML and logging in +============================== - 3.1. Running UML +3.1. Running UML +----------------- - It runs on 2.2.15 or later, and all 2.4 kernels. + It runs on 2.2.15 or later, and all kernel versions since 2.4. Booting UML is straightforward. Simply run 'linux': it will try to - mount the file `root_fs' in the current directory. You do not need to - run it as root. If your root filesystem is not named `root_fs', then - you need to put a `ubd0=root_fs_whatever' switch on the linux command + mount the file ``root_fs`` in the current directory. You do not need to + run it as root. If your root filesystem is not named ``root_fs``, then + you need to put a ``ubd0=root_fs_whatever`` switch on the linux command line. You will need a filesystem to boot UML from. There are a number - available for download from here . There are also several tools - which can be + available for download from http://user-mode-linux.sourceforge.net. + There are also several tools at + http://user-mode-linux.sourceforge.net/ which can be used to generate UML-compatible filesystem images from media. The kernel will boot up and present you with a login prompt. - Note: If the host is configured with a 2G/2G address space split +Note: + If the host is configured with a 2G/2G address space split rather than the usual 3G/1G split, then the packaged UML binaries will - not run. They will immediately segfault. See ``UML on 2G/2G hosts'' + not run. They will immediately segfault. See :ref:`UML_on_2G/2G_hosts` for the scoop on running UML on your system. - 3.2. Logging in +3.2. Logging in +---------------- @@ -468,22 +413,22 @@ There are a couple of other ways to log in: - o On a virtual console + - On a virtual console Each virtual console that is configured (i.e. the device exists in /dev and /etc/inittab runs a getty on it) will come up in its own - xterm. If you get tired of the xterms, read ``Setting up serial - lines and consoles'' to see how to attach the consoles to - something else, like host ptys. + xterm. If you get tired of the xterms, read + :ref:`setting_up_serial_lines_and_consoles` to see how to attach + the consoles to something else, like host ptys. - o Over the serial line + - Over the serial line - In the boot output, find a line that looks like: + In the boot output, find a line that looks like:: @@ -493,7 +438,7 @@ Attach your favorite terminal program to the corresponding tty. I.e. - for minicom, the command would be + for minicom, the command would be:: host% minicom -o -p /dev/ttyp1 @@ -503,37 +448,40 @@ - o Over the net + - Over the net If the network is running, then you can telnet to the virtual - machine and log in to it. See ``Setting up the network'' to learn + machine and log in to it. See :ref:`Setting_up_the_network` to learn about setting up a virtual network. When you're done using it, run halt, and the kernel will bring itself down and the process will exit. - 3.3. Examples +3.3. Examples +-------------- Here are some examples of UML in action: - o A login session + - A login session http://user-mode-linux.sourceforge.net/old/login.html - o A virtual network + - A virtual network http://user-mode-linux.sourceforge.net/old/net.html +.. _UML_on_2G/2G_hosts: +4. UML on 2G/2G hosts +====================== - 4. UML on 2G/2G hosts - - 4.1. Introduction +4.1. Introduction +------------------ Most Linux machines are configured so that the kernel occupies the @@ -546,7 +494,8 @@ - 4.2. The problem +4.2. The problem +----------------- The prebuilt UML binaries on this site will not run on 2G/2G hosts @@ -558,13 +507,14 @@ - 4.3. The solution +4.3. The solution +------------------ The fix for this is to rebuild UML from source after enabling CONFIG_HOST_2G_2G (under 'General Setup'). This will cause UML to load itself in the top .5G of that smaller process address space, - where it will run fine. See ``Compiling the kernel and modules'' if + where it will run fine. See :ref:`Compiling_the_kernel_and_modules` if you need help building UML from source. @@ -573,10 +523,11 @@ +.. _setting_up_serial_lines_and_consoles: - - 5. Setting up serial lines and consoles +5. Setting up serial lines and consoles +======================================== It is possible to attach UML serial lines and consoles to many types @@ -584,22 +535,23 @@ You can attach them to host ptys, ttys, file descriptors, and ports. - This allows you to do things like + This allows you to do things like: - o have a UML console appear on an unused host console, + - have a UML console appear on an unused host console, - o hook two virtual machines together by having one attach to a pty + - hook two virtual machines together by having one attach to a pty and having the other attach to the corresponding tty - o make a virtual machine accessible from the net by attaching a + - make a virtual machine accessible from the net by attaching a console to a port on the host. - The general format of the command line option is device=channel. + The general format of the command line option is ``device=channel``. - 5.1. Specifying the device +5.1. Specifying the device +--------------------------- Devices are specified with "con" or "ssl" (console or serial line, respectively), optionally with a device number if you are talking @@ -613,7 +565,7 @@ A specific device name will override a less general "con=" or "ssl=". So, for example, you can assign a pty to each of the serial lines - except for the first two like this: + except for the first two like this:: ssl=pty ssl0=tty:/dev/tty0 ssl1=tty:/dev/tty1 @@ -626,13 +578,14 @@ - 5.2. Specifying the channel +5.2. Specifying the channel +---------------------------- There are a number of different types of channels to attach a UML device to, each with a different way of specifying exactly what to attach to. - o pseudo-terminals - device=pty pts terminals - device=pts + - pseudo-terminals - device=pty pts terminals - device=pts This will cause UML to allocate a free host pseudo-terminal for the @@ -640,23 +593,23 @@ log. You access it by attaching a terminal program to the corresponding tty: - o screen /dev/pts/n + - screen /dev/pts/n - o screen /dev/ttyxx + - screen /dev/ttyxx - o minicom -o -p /dev/ttyxx - minicom seems not able to handle pts + - minicom -o -p /dev/ttyxx - minicom seems not able to handle pts devices - o kermit - start it up, 'open' the device, then 'connect' + - kermit - start it up, 'open' the device, then 'connect' - o terminals - device=tty:tty device file + - terminals - device=tty:tty device file - This will make UML attach the device to the specified tty (i.e + This will make UML attach the device to the specified tty (i.e:: con1=tty:/dev/tty3 @@ -672,7 +625,7 @@ - o xterms - device=xterm + - xterms - device=xterm UML will run an xterm and the device will be attached to it. @@ -681,12 +634,12 @@ - o Port - device=port:port number + - Port - device=port:port number This will attach the UML devices to the specified host port. Attaching console 1 to the host's port 9000 would be done like - this: + this:: con1=port:9000 @@ -694,7 +647,7 @@ - Attaching all the serial lines to that port would be done similarly: + Attaching all the serial lines to that port would be done similarly:: ssl=port:9000 @@ -702,8 +655,8 @@ - You access these devices by telnetting to that port. Each active tel- - net session gets a different device. If there are more telnets to a + You access these devices by telnetting to that port. Each active + telnet session gets a different device. If there are more telnets to a port than UML devices attached to it, then the extra telnet sessions will block until an existing telnet detaches, or until another device becomes active (i.e. by being activated in /etc/inittab). @@ -725,13 +678,13 @@ - o already-existing file descriptors - device=file descriptor + - already-existing file descriptors - device=file descriptor If you set up a file descriptor on the UML command line, you can attach a UML device to it. This is most commonly used to put the main console back on stdin and stdout after assigning all the other - consoles to something else: + consoles to something else:: con0=fd:0,fd:1 con=pts @@ -743,7 +696,7 @@ - o Nothing - device=null + - Nothing - device=null This allows the device to be opened, in contrast to 'none', but @@ -754,7 +707,7 @@ - o None - device=none + - None - device=none This causes the device to disappear. @@ -762,7 +715,7 @@ You can also specify different input and output channels for a device - by putting a comma between them: + by putting a comma between them:: ssl3=tty:/dev/tty2,xterm @@ -785,14 +738,15 @@ - 5.3. Examples +5.3. Examples +-------------- There are a number of interesting things you can do with this capability. First, this is how you get rid of those bleeding console xterms by - attaching them to host ptys: + attaching them to host ptys:: con=pty con0=fd:0,fd:1 @@ -802,7 +756,7 @@ This will make a UML console take over an unused host virtual console, so that when you switch to it, you will see the UML login prompt - rather than the host login prompt: + rather than the host login prompt:: con1=tty:/dev/tty6 @@ -813,7 +767,7 @@ You can attach two virtual machines together with what amounts to a serial line as follows: - Run one UML with a serial line attached to a pty - + Run one UML with a serial line attached to a pty:: ssl1=pty @@ -825,7 +779,7 @@ that it got /dev/ptyp1). Boot the other UML with a serial line attached to the corresponding - tty - + tty:: ssl1=tty:/dev/ttyp1 @@ -838,7 +792,10 @@ prompt of the other virtual machine. - 6. Setting up the network +.. _setting_up_the_network: + +6. Setting up the network +========================== @@ -858,19 +815,19 @@ There are currently five transport types available for a UML virtual machine to exchange packets with other hosts: - o ethertap + - ethertap - o TUN/TAP + - TUN/TAP - o Multicast + - Multicast - o a switch daemon + - a switch daemon - o slip + - slip - o slirp + - slirp - o pcap + - pcap The TUN/TAP, ethertap, slip, and slirp transports allow a UML instance to exchange packets with the host. They may be directed @@ -893,28 +850,28 @@ With so many host transports, which one should you use? Here's when you should use each one: - o ethertap - if you want access to the host networking and it is + - ethertap - if you want access to the host networking and it is running 2.2 - o TUN/TAP - if you want access to the host networking and it is + - TUN/TAP - if you want access to the host networking and it is running 2.4. Also, the TUN/TAP transport is able to use a preconfigured device, allowing it to avoid using the setuid uml_net helper, which is a security advantage. - o Multicast - if you want a purely virtual network and you don't want + - Multicast - if you want a purely virtual network and you don't want to set up anything but the UML - o a switch daemon - if you want a purely virtual network and you + - a switch daemon - if you want a purely virtual network and you don't mind running the daemon in order to get somewhat better performance - o slip - there is no particular reason to run the slip backend unless + - slip - there is no particular reason to run the slip backend unless ethertap and TUN/TAP are just not available for some reason - o slirp - if you don't have root access on the host to setup + - slirp - if you don't have root access on the host to setup networking, or if you don't want to allocate an IP to your UML - o pcap - not much use for actual network connectivity, but great for + - pcap - not much use for actual network connectivity, but great for monitoring traffic on the host Ethertap is available on 2.4 and works fine. TUN/TAP is preferred @@ -926,7 +883,8 @@ exploit the helper's root privileges. - 6.1. General setup +6.1. General setup +------------------- First, you must have the virtual network enabled in your UML. If are running a prebuilt kernel from this site, everything is already @@ -938,7 +896,7 @@ The next step is to provide a network device to the virtual machine. This is done by describing it on the kernel command line. - The general format is + The general format is:: eth = , @@ -947,7 +905,7 @@ For example, a virtual ethernet device may be attached to a host - ethertap device as follows: + ethertap device as follows:: eth0=ethertap,tap0,fe:fd:0:0:0:1,192.168.0.254 @@ -978,7 +936,7 @@ You can also add devices to a UML and remove them at runtime. See the - ``The Management Console'' page for details. + :ref:`The_Management_Console` page for details. The sections below describe this in more detail. @@ -995,7 +953,8 @@ - 6.2. Userspace daemons +6.2. Userspace daemons +----------------------- You will likely need the setuid helper, or the switch daemon, or both. They are both installed with the RPM and deb, so if you've installed @@ -1011,7 +970,8 @@ - 6.3. Specifying ethernet addresses +6.3. Specifying ethernet addresses +----------------------------------- Below, you will see that the TUN/TAP, ethertap, and daemon interfaces allow you to specify hardware addresses for the virtual ethernet @@ -1023,21 +983,21 @@ sufficient to guarantee a unique hardware address for the device. A couple of exceptions are: - o Another set of virtual ethernet devices are on the same network and + - Another set of virtual ethernet devices are on the same network and they are assigned hardware addresses using a different scheme which may conflict with the UML IP address-based scheme - o You aren't going to use the device for IP networking, so you don't + - You aren't going to use the device for IP networking, so you don't assign the device an IP address If you let the driver provide the hardware address, you should make sure that the device IP address is known before the interface is - brought up. So, inside UML, this will guarantee that: + brought up. So, inside UML, this will guarantee that:: - UML# - ifconfig eth0 192.168.0.250 up + UML# + ifconfig eth0 192.168.0.250 up @@ -1049,13 +1009,14 @@ - 6.4. UML interface setup +6.4. UML interface setup +------------------------- Once the network devices have been described on the command line, you should boot UML and log in. - The first thing to do is bring the interface up: + The first thing to do is bring the interface up:: UML# ifconfig ethn ip-address up @@ -1067,7 +1028,7 @@ To reach the rest of the world, you should set a default route to the - host: + host:: UML# route add default gw host ip @@ -1075,7 +1036,7 @@ - Again, with host ip of 192.168.0.4: + Again, with host ip of 192.168.0.4:: UML# route add default gw 192.168.0.4 @@ -1097,29 +1058,25 @@ Note: If you can't communicate with other hosts on your physical ethernet, it's probably because of a network route that's automatically set up. If you run 'route -n' and see a route that - looks like this: + looks like this:: - Destination Gateway Genmask Flags Metric Ref Use Iface - 192.168.0.0 0.0.0.0 255.255.255.0 U 0 0 0 eth0 + Destination Gateway Genmask Flags Metric Ref Use Iface + 192.168.0.0 0.0.0.0 255.255.255.0 U 0 0 0 eth0 with a mask that's not 255.255.255.255, then replace it with a route - to your host: + to your host:: UML# route del -net 192.168.0.0 dev eth0 netmask 255.255.255.0 - - - - UML# route add -host 192.168.0.4 dev eth0 @@ -1131,7 +1088,8 @@ - 6.5. Multicast +6.5. Multicast +--------------- The simplest way to set up a virtual network between multiple UMLs is to use the mcast transport. This was written by Harald Welte and is @@ -1142,7 +1100,7 @@ messages when you bring the device up inside UML. - To use it, run two UMLs with + To use it, run two UMLs with:: eth0=mcast @@ -1151,16 +1109,12 @@ on their command lines. Log in, configure the ethernet device in each - machine with different IP addresses: + machine with different IP addresses:: UML1# ifconfig eth0 192.168.0.254 - - - - UML2# ifconfig eth0 192.168.0.253 @@ -1168,7 +1122,7 @@ and they should be able to talk to each other. - The full set of command line options for this transport are + The full set of command line options for this transport are:: @@ -1177,16 +1131,11 @@ - - Harald's original README is here and explains these in detail, as well as - some other issues. - There is also a related point-to-point only "ucast" transport. This is useful when your network does not support multicast, and all network connections are simple point to point links. - The full set of command line options for this transport are + The full set of command line options for this transport are:: ethn=ucast,ethernet address,remote address,listen port,remote port @@ -1194,7 +1143,8 @@ - 6.6. TUN/TAP with the uml_net helper +6.6. TUN/TAP with the uml_net helper +------------------------------------- TUN/TAP is the preferred mechanism on 2.4 to exchange packets with the host. The TUN/TAP backend has been in UML since 2.4.9-3um. @@ -1216,7 +1166,7 @@ kernel or as the tun.o module. The format of the command line switch to attach a device to a TUN/TAP - device is + device is:: eth =tuntap,,, @@ -1226,7 +1176,7 @@ For example, this argument will attach the UML's eth0 to the next available tap device and assign an ethernet address to it based on its - IP address + IP address:: eth0=tuntap,,,192.168.0.254 @@ -1247,10 +1197,10 @@ There are a couple potential problems with running the TUN/TAP transport on a 2.4 host kernel - o TUN/TAP seems not to work on 2.4.3 and earlier. Upgrade the host + - TUN/TAP seems not to work on 2.4.3 and earlier. Upgrade the host kernel or use the ethertap transport. - o With an upgraded kernel, TUN/TAP may fail with + - With an upgraded kernel, TUN/TAP may fail with:: File descriptor in bad state @@ -1263,13 +1213,12 @@ make sure that /usr/src/linux points to the headers for the running kernel. - These were pointed out by Tim Robinson in - name="this uml- - user post"> . + These were pointed out by Tim Robinson in the past. - 6.7. TUN/TAP with a preconfigured tap device +6.7. TUN/TAP with a preconfigured tap device +--------------------------------------------- If you prefer not to have UML use uml_net (which is somewhat insecure), with UML 2.4.17-11, you can set up a TUN/TAP device @@ -1277,8 +1226,8 @@ there is no need for root assistance. Setting up the device is done as follows: - o Create the device with tunctl (available from the UML utilities - tarball) + - Create the device with tunctl (available from the UML utilities + tarball):: @@ -1291,8 +1240,8 @@ where uid is the user id or username that UML will be run as. This will tell you what device was created. - o Configure the device IP (change IP addresses and device name to - suit) + - Configure the device IP (change IP addresses and device name to + suit):: @@ -1303,8 +1252,8 @@ - o Set up routing and arping if desired - this is my recipe, there are - other ways of doing the same thing + - Set up routing and arping if desired - this is my recipe, there are + other ways of doing the same thing:: host# @@ -1313,19 +1262,9 @@ host# route add -host 192.168.0.253 dev tap0 - - - - - host# bash -c 'echo 1 > /proc/sys/net/ipv4/conf/tap0/proxy_arp' - - - - - host# arp -Ds 192.168.0.253 eth0 pub @@ -1338,76 +1277,43 @@ utility which reads the information from a config file and sets up devices at boot time. - o Rather than using up two IPs and ARPing for one of them, you can + - Rather than using up two IPs and ARPing for one of them, you can also provide direct access to your LAN by the UML by using a - bridge. + bridge:: host# brctl addbr br0 - - - - host# ifconfig eth0 0.0.0.0 promisc up - - - - host# ifconfig tap0 0.0.0.0 promisc up - - - - host# ifconfig br0 192.168.0.1 netmask 255.255.255.0 up - - - - - - host# - brctl stp br0 off - - - - + host# + brctl stp br0 off host# brctl setfd br0 1 - - - - host# brctl sethello br0 1 - - - - host# brctl addif br0 eth0 - - - - host# brctl addif br0 tap0 @@ -1417,12 +1323,12 @@ Note that 'br0' should be setup using ifconfig with the existing IP address of eth0, as eth0 no longer has its own IP. - o + - Also, the /dev/net/tun device must be writable by the user running UML in order for the UML to use the device that's been configured - for it. The simplest thing to do is + for it. The simplest thing to do is:: host# chmod 666 /dev/net/tun @@ -1438,14 +1344,14 @@ devices and chgrp /dev/net/tun to that group with mode 664 or 660. - o Once the device is set up, run UML with 'eth0=tuntap,device name' + - Once the device is set up, run UML with 'eth0=tuntap,device name' (i.e. 'eth0=tuntap,tap0') on the command line (or do it with the mconsole config command). - o Bring the eth device up in UML and you're in business. + - Bring the eth device up in UML and you're in business. If you don't want that tap device any more, you can make it non- - persistent with + persistent with:: host# tunctl -d tap device @@ -1455,7 +1361,7 @@ Finally, tunctl has a -b (for brief mode) switch which causes it to output only the name of the tap device it created. This makes it - suitable for capture by a script: + suitable for capture by a script:: host# TAP=`tunctl -u 1000 -b` @@ -1465,7 +1371,8 @@ - 6.8. Ethertap +6.8. Ethertap +-------------- Ethertap is the general mechanism on 2.2 for userspace processes to exchange packets with the kernel. @@ -1473,7 +1380,7 @@ To use this transport, you need to describe the virtual network device - on the UML command line. The general format for this is + on the UML command line. The general format for this is:: eth =ethertap, , , @@ -1481,7 +1388,7 @@ - So, the previous example + So, the previous example:: eth0=ethertap,tap0,fe:fd:0:0:0:1,192.168.0.254 @@ -1521,7 +1428,7 @@ If you want to set things up yourself, you need to make sure that the appropriate /dev entry exists. If it doesn't, become root and create - it as follows: + it as follows:: mknod /dev/tap c 36 + 16 @@ -1529,7 +1436,7 @@ - For example, this is how to create /dev/tap0: + For example, this is how to create /dev/tap0:: mknod /dev/tap0 c 36 0 + 16 @@ -1539,7 +1446,7 @@ You also need to make sure that the host kernel has ethertap support. If ethertap is enabled as a module, you apparently need to insmod - ethertap once for each ethertap device you want to enable. So, + ethertap once for each ethertap device you want to enable. So,:: host# @@ -1549,7 +1456,7 @@ will give you the tap0 interface. To get the tap1 interface, you need - to run + to run:: host# @@ -1561,7 +1468,8 @@ - 6.9. The switch daemon +6.9. The switch daemon +----------------------- Note: This is the daemon formerly known as uml_router, but which was renamed so the network weenies of the world would stop growling at me. @@ -1577,7 +1485,7 @@ sockets. - If you want it to listen on a different pair of sockets, use + If you want it to listen on a different pair of sockets, use:: -unix control socket data socket @@ -1586,7 +1494,7 @@ - If you want it to act as a hub rather than a switch, use + If you want it to act as a hub rather than a switch, use:: -hub @@ -1596,7 +1504,7 @@ If you want the switch to be connected to host networking (allowing - the umls to get access to the outside world through the host), use + the umls to get access to the outside world through the host), use:: -tap tap0 @@ -1610,7 +1518,7 @@ device than tap0, specify that instead of tap0. - uml_switch can be backgrounded as follows + uml_switch can be backgrounded as follows:: host% @@ -1623,7 +1531,7 @@ stdin for EOF. When it sees that, it exits. - The general format of the kernel command line switch is + The general format of the kernel command line switch is:: @@ -1639,7 +1547,8 @@ how to communicate with the daemon. You should only specify them if you told the daemon to use different sockets than the default. So, if you ran the daemon with no arguments, running the UML on the same - machine with + machine with:: + eth0=daemon @@ -1649,7 +1558,8 @@ - 6.10. Slip +6.10. Slip +----------- Slip is another, less general, mechanism for a process to communicate with the host networking. In contrast to the ethertap interface, @@ -1658,7 +1568,7 @@ IP. - The general format of the command line switch is + The general format of the command line switch is:: @@ -1681,7 +1591,8 @@ - 6.11. Slirp +6.11. Slirp +------------ slirp uses an external program, usually /usr/bin/slirp, to provide IP only networking connectivity through the host. This is similar to IP @@ -1691,7 +1602,7 @@ root access or setuid binaries on the host. - The general format of the command line switch for slirp is: + The general format of the command line switch for slirp is:: @@ -1716,7 +1627,7 @@ The eth0 interface on UML should be set up with the IP 10.2.0.15, although you can use anything as long as it is not used by a network you will be connecting to. The default route on UML should be set to - use + use:: UML# @@ -1737,10 +1648,11 @@ - 6.12. pcap +6.12. pcap +----------- The pcap transport is attached to a UML ethernet device on the command - line or with uml_mconsole with the following syntax: + line or with uml_mconsole with the following syntax:: @@ -1762,7 +1674,7 @@ expression optimizer is used. - Example: + Example:: @@ -1777,7 +1689,8 @@ - 6.13. Setting up the host yourself +6.13. Setting up the host yourself +----------------------------------- If you don't specify an address for the host side of the ethertap or slip device, UML won't do any setup on the host. So this is what is @@ -1785,19 +1698,15 @@ 192.168.0.251 and a UML-side IP of 192.168.0.250 - adjust to suit your own network): - o The device needs to be configured with its IP address. Tap devices + - The device needs to be configured with its IP address. Tap devices are also configured with an mtu of 1484. Slip devices are configured with a point-to-point address pointing at the UML ip - address. + address:: host# ifconfig tap0 arp mtu 1484 192.168.0.251 up - - - - host# ifconfig sl0 192.168.0.251 pointopoint 192.168.0.250 up @@ -1805,7 +1714,7 @@ - o If a tap device is being set up, a route is set to the UML IP. + - If a tap device is being set up, a route is set to the UML IP:: UML# route add -host 192.168.0.250 gw 192.168.0.251 @@ -1814,8 +1723,8 @@ - o To allow other hosts on your network to see the virtual machine, - proxy arp is set up for it. + - To allow other hosts on your network to see the virtual machine, + proxy arp is set up for it:: host# arp -Ds 192.168.0.250 eth0 pub @@ -1824,7 +1733,7 @@ - o Finally, the host is set up to route packets. + - Finally, the host is set up to route packets:: host# echo 1 > /proc/sys/net/ipv4/ip_forward @@ -1838,12 +1747,14 @@ - 7. Sharing Filesystems between Virtual Machines +7. Sharing Filesystems between Virtual Machines +================================================ - 7.1. A warning +7.1. A warning +--------------- Don't attempt to share filesystems simply by booting two UMLs from the same file. That's the same thing as booting two physical machines @@ -1851,7 +1762,8 @@ - 7.2. Using layered block devices +7.2. Using layered block devices +--------------------------------- The way to share a filesystem between two virtual machines is to use the copy-on-write (COW) layering capability of the ubd block driver. @@ -1872,7 +1784,7 @@ To add a copy-on-write layer to an existing block device file, simply - add the name of the COW file to the appropriate ubd switch: + add the name of the COW file to the appropriate ubd switch:: ubd0=root_fs_cow,root_fs_debian_22 @@ -1883,7 +1795,7 @@ where 'root_fs_cow' is the private COW file and 'root_fs_debian_22' is the existing shared filesystem. The COW file need not exist. If it doesn't, the driver will create and initialize it. Once the COW file - has been initialized, it can be used on its own on the command line: + has been initialized, it can be used on its own on the command line:: ubd0=root_fs_cow @@ -1896,14 +1808,16 @@ - 7.3. Note! +7.3. Note! +----------- When checking the size of the COW file in order to see the gobs of space that you're saving, make sure you use 'ls -ls' to see the actual disk consumption rather than the length of the file. The COW file is sparse, so the length will be very different from the disk usage. Here is a 'ls -l' of a COW file and backing file from one boot and - shutdown: + shutdown:: + host% ls -l cow.debian debian2.2 -rw-r--r-- 1 jdike jdike 492504064 Aug 6 21:16 cow.debian -rwxrw-rw- 1 jdike jdike 537919488 Aug 6 20:42 debian2.2 @@ -1911,7 +1825,7 @@ - Doesn't look like much saved space, does it? Well, here's 'ls -ls': + Doesn't look like much saved space, does it? Well, here's 'ls -ls':: host% ls -ls cow.debian debian2.2 @@ -1926,7 +1840,8 @@ - 7.4. Another warning +7.4. Another warning +--------------------- Once a filesystem is being used as a readonly backing file for a COW file, do not boot directly from it or modify it in any way. Doing so @@ -1952,7 +1867,8 @@ - 7.5. uml_moo : Merging a COW file with its backing file +7.5. uml_moo : Merging a COW file with its backing file +-------------------------------------------------------- Depending on how you use UML and COW devices, it may be advisable to merge the changes in the COW file into the backing file every once in @@ -1961,7 +1877,7 @@ - The utility that does this is uml_moo. Its usage is + The utility that does this is uml_moo. Its usage is:: host% uml_moo COW file new backing file @@ -1991,8 +1907,8 @@ uml_moo is installed with the UML deb and RPM. If you didn't install UML from one of those packages, you can also get it from the UML - utilities tar file in tools/moo. + utilities http://user-mode-linux.sourceforge.net/utilities tar file + in tools/moo. @@ -2001,7 +1917,8 @@ - 8. Creating filesystems +8. Creating filesystems +======================== You may want to create and mount new UML filesystems, either because @@ -2015,13 +1932,14 @@ should be easy to translate to the filesystem of your choice. - 8.1. Create the filesystem file +8.1. Create the filesystem file +================================ dd is your friend. All you need to do is tell dd to create an empty file of the appropriate size. I usually make it sparse to save time and to avoid allocating disk space until it's actually used. For example, the following command will create a sparse 100 meg file full - of zeroes. + of zeroes:: host% @@ -2034,9 +1952,9 @@ 8.2. Assign the file to a UML device - Add an argument like the following to the UML command line: + Add an argument like the following to the UML command line:: - ubd4=new_filesystem + ubd4=new_filesystem @@ -2053,7 +1971,7 @@ etc), then get them into UML by way of the net or hostfs. - Make the new filesystem on the device assigned to the new file: + Make the new filesystem on the device assigned to the new file:: host# mkreiserfs /dev/ubd/4 @@ -2077,7 +1995,7 @@ - Now, mount it: + Now, mount it:: UML# @@ -2096,7 +2014,8 @@ - 9. Host file access +9. Host file access +==================== If you want to access files on the host machine from inside UML, you @@ -2112,10 +2031,11 @@ files contained in it just as you would on the host. - 9.1. Using hostfs +9.1. Using hostfs +------------------ To begin with, make sure that hostfs is available inside the virtual - machine with + machine with:: UML# cat /proc/filesystems @@ -2127,7 +2047,7 @@ module and available inside the virtual machine, and insmod it. - Now all you need to do is run mount: + Now all you need to do is run mount:: UML# mount none /mnt/host -t hostfs @@ -2139,7 +2059,7 @@ If you don't want to mount the host root directory, then you can - specify a subdirectory to mount with the -o switch to mount: + specify a subdirectory to mount with the -o switch to mount:: UML# mount none /mnt/home -t hostfs -o /home @@ -2151,13 +2071,14 @@ - 9.2. hostfs as the root filesystem +9.2. hostfs as the root filesystem +----------------------------------- It's possible to boot from a directory hierarchy on the host using hostfs rather than using the standard filesystem in a file. To start, you need that hierarchy. The easiest way is to loop mount - an existing root_fs file: + an existing root_fs file:: host# mount root_fs uml_root_dir -o loop @@ -2166,15 +2087,15 @@ You need to change the filesystem type of / in etc/fstab to be - 'hostfs', so that line looks like this: + 'hostfs', so that line looks like this:: - /dev/ubd/0 / hostfs defaults 1 1 + /dev/ubd/0 / hostfs defaults 1 1 Then you need to chown to yourself all the files in that directory - that are owned by root. This worked for me: + that are owned by root. This worked for me:: host# find . -uid 0 -exec chown jdike {} \; @@ -2183,7 +2104,7 @@ Next, make sure that your UML kernel has hostfs compiled in, not as a - module. Then run UML with the boot device pointing at that directory: + module. Then run UML with the boot device pointing at that directory:: ubd0=/path/to/uml/root/directory @@ -2194,41 +2115,35 @@ UML should then boot as it does normally. - 9.3. Building hostfs +9.3. Building hostfs +--------------------- If you need to build hostfs because it's not in your kernel, you have two choices: - o Compiling hostfs into the kernel: + - Compiling hostfs into the kernel: Reconfigure the kernel and set the 'Host filesystem' option under - o Compiling hostfs as a module: + - Compiling hostfs as a module: Reconfigure the kernel and set the 'Host filesystem' option under be in arch/um/fs/hostfs/hostfs.o. Install that in - /lib/modules/`uname -r`/fs in the virtual machine, boot it up, and + ``/lib/modules/$(uname -r)/fs`` in the virtual machine, boot it up, and:: UML# insmod hostfs +.. _The_Management_Console: - - - - - - - - - - 10. The Management Console +10. The Management Console +=========================== @@ -2240,15 +2155,15 @@ There are a number of things you can do with the mconsole interface: - o get the kernel version + - get the kernel version - o add and remove devices + - add and remove devices - o halt or reboot the machine + - halt or reboot the machine - o Send SysRq commands + - Send SysRq commands - o Pause and resume the UML + - Pause and resume the UML You need the mconsole client (uml_mconsole) which is present in CVS @@ -2257,7 +2172,7 @@ You also need CONFIG_MCONSOLE (under 'General Setup') enabled in UML. - When you boot UML, you'll see a line like: + When you boot UML, you'll see a line like:: mconsole initialized on /home/jdike/.uml/umlNJ32yL/mconsole @@ -2265,7 +2180,7 @@ - If you specify a unique machine id one the UML command line, i.e. + If you specify a unique machine id one the UML command line, i.e.:: umid=debian @@ -2273,7 +2188,7 @@ - you'll see this + you'll see this:: mconsole initialized on /home/jdike/.uml/debian/mconsole @@ -2282,7 +2197,7 @@ That file is the socket that uml_mconsole will use to communicate with - UML. Run it with either the umid or the full path as its argument: + UML. Run it with either the umid or the full path as its argument:: host% uml_mconsole debian @@ -2290,7 +2205,7 @@ - or + or:: host% uml_mconsole /home/jdike/.uml/debian/mconsole @@ -2300,30 +2215,31 @@ You'll get a prompt, at which you can run one of these commands: - o version + - version - o halt + - halt - o reboot + - reboot - o config + - config - o remove + - remove - o sysrq + - sysrq - o help + - help - o cad + - cad - o stop + - stop - o go + - go - 10.1. version +10.1. version +-------------- - This takes no arguments. It prints the UML version. + This takes no arguments. It prints the UML version:: (mconsole) version @@ -2342,11 +2258,12 @@ - 10.2. halt and reboot +10.2. halt and reboot +---------------------- These take no arguments. They shut the machine down immediately, with no syncing of disks and no clean shutdown of userspace. So, they are - pretty close to crashing the machine. + pretty close to crashing the machine:: (mconsole) halt @@ -2357,34 +2274,36 @@ - 10.3. config +10.3. config +------------- "config" adds a new device to the virtual machine. Currently the ubd and network drivers support this. It takes one argument, which is the - device to add, with the same syntax as the kernel command line. + device to add, with the same syntax as the kernel command line:: - (mconsole) - config ubd3=/home/jdike/incoming/roots/root_fs_debian22 + (mconsole) + config ubd3=/home/jdike/incoming/roots/root_fs_debian22 - OK - (mconsole) config eth1=mcast - OK + OK + (mconsole) config eth1=mcast + OK - 10.4. remove +10.4. remove +------------- "remove" deletes a device from the system. Its argument is just the name of the device to be removed. The device must be idle in whatever sense the driver considers necessary. In the case of the ubd driver, the removed block device must not be mounted, swapped on, or otherwise - open, and in the case of the network driver, the device must be down. + open, and in the case of the network driver, the device must be down:: (mconsole) remove ubd3 @@ -2397,7 +2316,8 @@ - 10.5. sysrq +10.5. sysrq +------------ This takes one argument, which is a single letter. It calls the generic kernel's SysRq driver, which does whatever is called for by @@ -2407,19 +2327,21 @@ - 10.6. help +10.6. help +----------- "help" returns a string listing the valid commands and what each one does. - 10.7. cad +10.7. cad +---------- This invokes the Ctl-Alt-Del action on init. What exactly this ends up doing is up to /etc/inittab. Normally, it reboots the machine. With UML, this is usually not desired, so if a halt would be better, - then find the section of inittab that looks like this + then find the section of inittab that looks like this:: # What to do when CTRL-ALT-DEL is pressed. @@ -2432,7 +2354,8 @@ - 10.8. stop +10.8. stop +----------- This puts the UML in a loop reading mconsole requests until a 'go' mconsole command is received. This is very useful for making backups @@ -2448,7 +2371,8 @@ - 10.9. go +10.9. go +--------- This resumes a UML after being paused by a 'stop' command. Note that when the UML has resumed, TCP connections may have timed out and if @@ -2460,9 +2384,10 @@ +.. _Kernel_debugging: - - 11. Kernel debugging +11. Kernel debugging +===================== Note: The interface that makes debugging, as described here, possible @@ -2477,15 +2402,16 @@ In order to debug the kernel, you need build it from source. See - ``Compiling the kernel and modules'' for information on doing that. + :ref:`Compiling_the_kernel_and_modules` for information on doing that. Make sure that you enable CONFIG_DEBUGSYM and CONFIG_PT_PROXY during - the config. These will compile the kernel with -g, and enable the + the config. These will compile the kernel with ``-g``, and enable the ptrace proxy so that gdb works with UML, respectively. - 11.1. Starting the kernel under gdb +11.1. Starting the kernel under gdb +------------------------------------ You can have the kernel running under the control of gdb from the beginning by putting 'debug' on the command line. You will get an @@ -2498,7 +2424,11 @@ There is a transcript of a debugging session here , with breakpoints being set in the scheduler and in an interrupt handler. - 11.2. Examining sleeping processes + + +11.2. Examining sleeping processes +----------------------------------- + Not every bug is evident in the currently running process. Sometimes, processes hang in the kernel when they shouldn't because they've @@ -2516,7 +2446,7 @@ Now what you do is this: - o detach from the current thread + - detach from the current thread:: (UML gdb) det @@ -2525,7 +2455,7 @@ - o attach to the thread you are interested in + - attach to the thread you are interested in:: (UML gdb) att @@ -2534,7 +2464,7 @@ - o look at its stack and anything else of interest + - look at its stack and anything else of interest:: (UML gdb) bt @@ -2545,18 +2475,14 @@ Note that you can't do anything at this point that requires that a process execute, e.g. calling a function - o when you're done looking at that process, reattach to the current - thread and continue it + - when you're done looking at that process, reattach to the current + thread and continue it:: (UML gdb) att 1 - - - - (UML gdb) c @@ -2569,12 +2495,13 @@ - 11.3. Running ddd on UML +11.3. Running ddd on UML +------------------------- ddd works on UML, but requires a special kludge. The process goes like this: - o Start ddd + - Start ddd:: host% ddd linux @@ -2583,14 +2510,14 @@ - o With ps, get the pid of the gdb that ddd started. You can ask the + - With ps, get the pid of the gdb that ddd started. You can ask the gdb to tell you, but for some reason that confuses things and causes a hang. - o run UML with 'debug=parent gdb-pid=' added to the command line + - run UML with 'debug=parent gdb-pid=' added to the command line - it will just sit there after you hit return - o type 'att 1' to the ddd gdb and you will see something like + - type 'att 1' to the ddd gdb and you will see something like:: 0xa013dc51 in __kill () @@ -2602,12 +2529,14 @@ - o At this point, type 'c', UML will boot up, and you can use ddd just + - At this point, type 'c', UML will boot up, and you can use ddd just as you do on any other process. - 11.4. Debugging modules +11.4. Debugging modules +------------------------ + gdb has support for debugging code which is dynamically loaded into the process. This support is what is needed to debug kernel modules @@ -2629,7 +2558,8 @@ First, you must tell it where your modules are. There is a list in - the script that looks like this: + the script that looks like this:: + set MODULE_PATHS { "fat" "/usr/src/uml/linux-2.4.18/fs/fat/fat.o" "isofs" "/usr/src/uml/linux-2.4.18/fs/isofs/isofs.o" @@ -2641,9 +2571,7 @@ You change that to list the names and paths of the modules that you are going to debug. Then you run it from the toplevel directory of - your UML pool and it basically tells you what to do: - - + your UML pool and it basically tells you what to do:: ******** GDB pid is 21903 ******** @@ -2666,7 +2594,7 @@ After you run UML and it sits there doing nothing, you hit return at - the 'att 1' and continue it: + the 'att 1' and continue it:: Attaching to program: /home/jdike/linux/2.4/um/./linux, process 1 @@ -2678,63 +2606,48 @@ At this point, you debug normally. When you insmod something, the - expect magic will kick in and you'll see something like: - - - - - - - - - - - - - - - - - - *** Module hostfs loaded *** - Breakpoint 1, sys_init_module (name_user=0x805abb0 "hostfs", - mod_user=0x8070e00) at module.c:349 - 349 char *name, *n_name, *name_tmp = NULL; - (UML gdb) finish - Run till exit from #0 sys_init_module (name_user=0x805abb0 "hostfs", - mod_user=0x8070e00) at module.c:349 - 0xa00e2e23 in execute_syscall (r=0xa8140284) at syscall_kern.c:411 - 411 else res = EXECUTE_SYSCALL(syscall, regs); - Value returned is $1 = 0 - (UML gdb) - p/x (int)module_list + module_list->size_of_struct - - $2 = 0xa9021054 - (UML gdb) symbol-file ./linux - Load new symbol table from "./linux"? (y or n) y - Reading symbols from ./linux... - done. - (UML gdb) - add-symbol-file /home/jdike/linux/2.4/um/arch/um/fs/hostfs/hostfs.o 0xa9021054 - - add symbol table from file "/home/jdike/linux/2.4/um/arch/um/fs/hostfs/hostfs.o" at - .text_addr = 0xa9021054 - (y or n) y - - Reading symbols from /home/jdike/linux/2.4/um/arch/um/fs/hostfs/hostfs.o... - done. - (UML gdb) p *module_list - $1 = {size_of_struct = 84, next = 0xa0178720, name = 0xa9022de0 "hostfs", - size = 9016, uc = {usecount = {counter = 0}, pad = 0}, flags = 1, - nsyms = 57, ndeps = 0, syms = 0xa9023170, deps = 0x0, refs = 0x0, - init = 0xa90221f0 , cleanup = 0xa902222c , - ex_table_start = 0x0, ex_table_end = 0x0, persist_start = 0x0, - persist_end = 0x0, can_unload = 0, runsize = 0, kallsyms_start = 0x0, - kallsyms_end = 0x0, - archdata_start = 0x1b855
, - archdata_end = 0xe5890000
, - kernel_data = 0xf689c35d
} - >> Finished loading symbols for hostfs ... + expect magic will kick in and you'll see something like:: + + + *** Module hostfs loaded *** + Breakpoint 1, sys_init_module (name_user=0x805abb0 "hostfs", + mod_user=0x8070e00) at module.c:349 + 349 char *name, *n_name, *name_tmp = NULL; + (UML gdb) finish + Run till exit from #0 sys_init_module (name_user=0x805abb0 "hostfs", + mod_user=0x8070e00) at module.c:349 + 0xa00e2e23 in execute_syscall (r=0xa8140284) at syscall_kern.c:411 + 411 else res = EXECUTE_SYSCALL(syscall, regs); + Value returned is $1 = 0 + (UML gdb) + p/x (int)module_list + module_list->size_of_struct + + $2 = 0xa9021054 + (UML gdb) symbol-file ./linux + Load new symbol table from "./linux"? (y or n) y + Reading symbols from ./linux... + done. + (UML gdb) + add-symbol-file /home/jdike/linux/2.4/um/arch/um/fs/hostfs/hostfs.o 0xa9021054 + + add symbol table from file "/home/jdike/linux/2.4/um/arch/um/fs/hostfs/hostfs.o" at + .text_addr = 0xa9021054 + (y or n) y + + Reading symbols from /home/jdike/linux/2.4/um/arch/um/fs/hostfs/hostfs.o... + done. + (UML gdb) p *module_list + $1 = {size_of_struct = 84, next = 0xa0178720, name = 0xa9022de0 "hostfs", + size = 9016, uc = {usecount = {counter = 0}, pad = 0}, flags = 1, + nsyms = 57, ndeps = 0, syms = 0xa9023170, deps = 0x0, refs = 0x0, + init = 0xa90221f0 , cleanup = 0xa902222c , + ex_table_start = 0x0, ex_table_end = 0x0, persist_start = 0x0, + persist_end = 0x0, can_unload = 0, runsize = 0, kallsyms_start = 0x0, + kallsyms_end = 0x0, + archdata_start = 0x1b855
, + archdata_end = 0xe5890000
, + kernel_data = 0xf689c35d
} + >> Finished loading symbols for hostfs ... @@ -2744,7 +2657,7 @@ Boot the kernel under the debugger and load the module with insmod or - modprobe. With gdb, do: + modprobe. With gdb, do:: (UML gdb) p module_list @@ -2758,12 +2671,12 @@ the name fields until find the module you want to debug. Take the address of that structure, and add module.size_of_struct (which in 2.4.10 kernels is 96 (0x60)) to it. Gdb can make this hard addition - for you :-): + for you :-):: - (UML gdb) - printf "%#x\n", (int)module_list module_list->size_of_struct + (UML gdb) + printf "%#x\n", (int)module_list module_list->size_of_struct @@ -2771,7 +2684,7 @@ The offset from the module start occasionally changes (before 2.4.0, it was module.size_of_struct + 4), so it's a good idea to check the init and cleanup addresses once in a while, as describe below. Now - do: + do:: (UML gdb) @@ -2786,7 +2699,7 @@ If there's any doubt that you got the offset right, like breakpoints appear not to work, or they're appearing in the wrong place, you can check it by looking at the module structure. The init and cleanup - fields should look like: + fields should look like:: init = 0x588066b0 , cleanup = 0x588066c0 @@ -2801,7 +2714,7 @@ When you want to load in a new version of the module, you need to get gdb to forget about the old one. The only way I've found to do that - is to tell gdb to forget about all symbols that it knows about: + is to tell gdb to forget about all symbols that it knows about:: (UML gdb) symbol-file @@ -2809,7 +2722,7 @@ - Then reload the symbols from the kernel binary: + Then reload the symbols from the kernel binary:: (UML gdb) symbol-file /path/to/kernel @@ -2823,17 +2736,19 @@ - 11.5. Attaching gdb to the kernel +11.5. Attaching gdb to the kernel +---------------------------------- If you don't have the kernel running under gdb, you can attach gdb to it later by sending the tracing thread a SIGUSR1. The first line of - the console output identifies its pid: + the console output identifies its pid:: + tracing thread pid = 20093 - When you send it the signal: + When you send it the signal:: host% kill -USR1 20093 @@ -2845,7 +2760,7 @@ If you have the mconsole compiled into UML, then the mconsole client - can be used to start gdb: + can be used to start gdb:: (mconsole) (mconsole) config gdb=xterm @@ -2857,7 +2772,8 @@ - 11.6. Using alternate debuggers +11.6. Using alternate debuggers +-------------------------------- UML has support for attaching to an already running debugger rather than starting gdb itself. This is present in CVS as of 17 Apr 2001. @@ -2886,7 +2802,7 @@ An example of an alternate debugger is strace. You can strace the actual kernel as follows: - o Run the following in a shell + - Run the following in a shell:: host% @@ -2894,13 +2810,13 @@ - o Run UML with 'debug' and 'gdb-pid=' with the pid printed out + - Run UML with 'debug' and 'gdb-pid=' with the pid printed out by the previous command - o Hit return in the shell, and UML will start running, and strace + - Hit return in the shell, and UML will start running, and strace output will start accumulating in the output file. - Note that this is different from running + Note that this is different from running:: host% strace ./linux @@ -2917,95 +2833,57 @@ - 12. Kernel debugging examples +12. Kernel debugging examples +============================== - 12.1. The case of the hung fsck +12.1. The case of the hung fsck +-------------------------------- When booting up the kernel, fsck failed, and dropped me into a shell - to fix things up. I ran fsck -y, which hung: - - - - - - - - - - - - - - - - - - - - - - - - - + to fix things up. I ran fsck -y, which hung:: + Setting hostname uml [ OK ] + Checking root filesystem + /dev/fhd0 was not cleanly unmounted, check forced. + Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780. + /dev/fhd0: UNEXPECTED INCONSISTENCY; RUN fsck MANUALLY. + (i.e., without -a or -p options) + [ FAILED ] + *** An error occurred during the file system check. + *** Dropping you to a shell; the system will reboot + *** when you leave the shell. + Give root password for maintenance + (or type Control-D for normal startup): + [root@uml /root]# fsck -y /dev/fhd0 + fsck -y /dev/fhd0 + Parallelizing fsck version 1.14 (9-Jan-1999) + e2fsck 1.14, 9-Jan-1999 for EXT2 FS 0.5b, 95/08/09 + /dev/fhd0 contains a file system with errors, check forced. + Pass 1: Checking inodes, blocks, and sizes + Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780. Ignore error? yes + Inode 19780, i_blocks is 1548, should be 540. Fix? yes + Pass 2: Checking directory structure + Error reading block 49405 (Attempt to read block from filesystem resulted in short read). Ignore error? yes + Directory inode 11858, block 0, offset 0: directory corrupted + Salvage? yes + Missing '.' in directory inode 11858. + Fix? yes - - - Setting hostname uml [ OK ] - Checking root filesystem - /dev/fhd0 was not cleanly unmounted, check forced. - Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780. - - /dev/fhd0: UNEXPECTED INCONSISTENCY; RUN fsck MANUALLY. - (i.e., without -a or -p options) - [ FAILED ] - - *** An error occurred during the file system check. - *** Dropping you to a shell; the system will reboot - *** when you leave the shell. - Give root password for maintenance - (or type Control-D for normal startup): - - [root@uml /root]# fsck -y /dev/fhd0 - fsck -y /dev/fhd0 - Parallelizing fsck version 1.14 (9-Jan-1999) - e2fsck 1.14, 9-Jan-1999 for EXT2 FS 0.5b, 95/08/09 - /dev/fhd0 contains a file system with errors, check forced. - Pass 1: Checking inodes, blocks, and sizes - Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780. Ignore error? yes - - Inode 19780, i_blocks is 1548, should be 540. Fix? yes - - Pass 2: Checking directory structure - Error reading block 49405 (Attempt to read block from filesystem resulted in short read). Ignore error? yes - - Directory inode 11858, block 0, offset 0: directory corrupted - Salvage? yes - - Missing '.' in directory inode 11858. - Fix? yes - - Missing '..' in directory inode 11858. - Fix? yes - - - + Missing '..' in directory inode 11858. + Fix? yes The standard drill in this sort of situation is to fire up gdb on the signal thread, which, in this case, was pid 1935. In another window, - I run gdb and attach pid 1935. - - + I run gdb and attach pid 1935:: ~/linux/2.3.26/um 1016: gdb linux @@ -3022,11 +2900,7 @@ 0x100756d9 in __wait4 () - - - - - Let's see what's currently running: + Let's see what's currently running:: @@ -3041,7 +2915,7 @@ reason and never woke up. - Let's guess that the last process in the process list is fsck: + Let's guess that the last process in the process list is fsck:: @@ -3052,7 +2926,7 @@ - It is, so let's see what it thinks it's up to: + It is, so let's see what it thinks it's up to:: @@ -3068,8 +2942,6 @@ - - The interesting things here are the fact that its .thread.syscall.id is __NR_write (see the big switch in arch/um/kernel/syscall_kern.c or the defines in include/asm-um/arch/unistd.h), and that it never @@ -3081,30 +2953,20 @@ The fact that it never returned from write means that its stack should be fairly interesting. Its pid is 1980 (.thread.extern_pid). That process is being ptraced by the signal thread, so it must be detached - before gdb can attach it: - - - - - - + before gdb can attach it:: + (gdb) call detach(1980) - (gdb) call detach(1980) - - Program received signal SIGSEGV, Segmentation fault. - - The program being debugged stopped while in a function called from GDB. - When the function (detach) is done executing, GDB will silently - stop (instead of continuing to evaluate the expression containing - the function call). - (gdb) call detach(1980) - $15 = 0 - - - + Program received signal SIGSEGV, Segmentation fault. + + The program being debugged stopped while in a function called from GDB. + When the function (detach) is done executing, GDB will silently + stop (instead of continuing to evaluate the expression containing + the function call). + (gdb) call detach(1980) + $15 = 0 The first detach segfaults for some reason, and the second one @@ -3112,7 +2974,7 @@ Now I detach from the signal thread, attach to the fsck thread, and - look at its stack: + look at its stack:: (gdb) det @@ -3152,14 +3014,14 @@ - The interesting things here are : + The interesting things here are: - o There are two segfaults on this stack (frames 9 and 14) + - There are two segfaults on this stack (frames 9 and 14) - o The first faulting address (frame 11) is 0x50000800 + - The first faulting address (frame 11) is 0x50000800:: - (gdb) p (void *)1342179328 - $16 = (void *) 0x50000800 + (gdb) p (void *)1342179328 + $16 = (void *) 0x50000800 @@ -3175,7 +3037,7 @@ However, the more immediate problem is that second segfault and I'm going to concentrate on that. First, I want to see where the fault - happened, so I have to go look at the sigcontent struct in frame 8: + happened, so I have to go look at the sigcontent struct in frame 8:: @@ -3211,7 +3073,7 @@ - That's not very useful, so I'll try a more manual method: + That's not very useful, so I'll try a more manual method:: (gdb) p *((struct sigcontext *) (&sig + 1)) @@ -3224,7 +3086,7 @@ - The ip is in handle_mm_fault: + The ip is in handle_mm_fault:: (gdb) p (void *)268480945 @@ -3236,7 +3098,7 @@ - Specifically, it's in pte_alloc: + Specifically, it's in pte_alloc:: (gdb) i line *$20 @@ -3249,7 +3111,7 @@ To find where in handle_mm_fault this is, I'll jump forward in the - code until I see an address in that procedure: + code until I see an address in that procedure:: @@ -3286,21 +3148,21 @@ Something is apparently wrong with the page tables or vma_structs, so - lets go back to frame 11 and have a look at them: + lets go back to frame 11 and have a look at them:: - #11 0x1006c0aa in segv (address=1342179328, is_write=2) at trap_kern.c:50 - 50 handle_mm_fault(current, vma, address, is_write); - (gdb) call pgd_offset_proc(vma->vm_mm, address) - $22 = (pgd_t *) 0x80a548c + #11 0x1006c0aa in segv (address=1342179328, is_write=2) at trap_kern.c:50 + 50 handle_mm_fault(current, vma, address, is_write); + (gdb) call pgd_offset_proc(vma->vm_mm, address) + $22 = (pgd_t *) 0x80a548c That's pretty bogus. Page tables aren't supposed to be in process - text or data areas. Let's see what's in the vma: + text or data areas. Let's see what's in the vma:: (gdb) p *vma @@ -3325,12 +3187,9 @@ - - This also pretty bogus. With all of the 0x80xxxxx and 0xaffffxxx addresses, this is looking like a stack was plonked down on top of - these structures. Maybe it's a stack overflow from the next page: - + these structures. Maybe it's a stack overflow from the next page:: (gdb) p vma @@ -3338,52 +3197,36 @@ - - That's towards the lower quarter of the page, so that would have to - have been pretty heavy stack overflow: - - - - - - - - - - - - - - - (gdb) x/100x $25 - 0x507d2434: 0x507d2434 0x00000000 0x08048000 0x080a4f8c - 0x507d2444: 0x00000000 0x080a79e0 0x080a8c94 0x080d1000 - 0x507d2454: 0xaffffdb0 0xaffffe63 0xaffffe7a 0xaffffe7a - 0x507d2464: 0xafffffec 0x00000062 0x0000008a 0x00000000 - 0x507d2474: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d2484: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d2494: 0x00000000 0x00000000 0x507d2fe0 0x00000000 - 0x507d24a4: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d24b4: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d24c4: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d24d4: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d24e4: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d24f4: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d2504: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d2514: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d2524: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d2534: 0x00000000 0x00000000 0x507d25dc 0x00000000 - 0x507d2544: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d2554: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d2564: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d2574: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d2584: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d2594: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d25a4: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d25b4: 0x00000000 0x00000000 0x00000000 0x00000000 - - + have been pretty heavy stack overflow:: + + + (gdb) x/100x $25 + 0x507d2434: 0x507d2434 0x00000000 0x08048000 0x080a4f8c + 0x507d2444: 0x00000000 0x080a79e0 0x080a8c94 0x080d1000 + 0x507d2454: 0xaffffdb0 0xaffffe63 0xaffffe7a 0xaffffe7a + 0x507d2464: 0xafffffec 0x00000062 0x0000008a 0x00000000 + 0x507d2474: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d2484: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d2494: 0x00000000 0x00000000 0x507d2fe0 0x00000000 + 0x507d24a4: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d24b4: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d24c4: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d24d4: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d24e4: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d24f4: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d2504: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d2514: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d2524: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d2534: 0x00000000 0x00000000 0x507d25dc 0x00000000 + 0x507d2544: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d2554: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d2564: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d2574: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d2584: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d2594: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d25a4: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d25b4: 0x00000000 0x00000000 0x00000000 0x00000000 @@ -3399,65 +3242,53 @@ on will be somewhat clearer. - 12.2. Episode 2: The case of the hung fsck +12.2. Episode 2: The case of the hung fsck +------------------------------------------- After setting a trap in the SEGV handler for accesses to the signal thread's stack, I reran the kernel. - fsck hung again, this time by hitting the trap: - - + fsck hung again, this time by hitting the trap:: + Setting hostname uml [ OK ] + Checking root filesystem + /dev/fhd0 contains a file system with errors, check forced. + Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780. + /dev/fhd0: UNEXPECTED INCONSISTENCY; RUN fsck MANUALLY. + (i.e., without -a or -p options) + [ FAILED ] + *** An error occurred during the file system check. + *** Dropping you to a shell; the system will reboot + *** when you leave the shell. + Give root password for maintenance + (or type Control-D for normal startup): + [root@uml /root]# fsck -y /dev/fhd0 + fsck -y /dev/fhd0 + Parallelizing fsck version 1.14 (9-Jan-1999) + e2fsck 1.14, 9-Jan-1999 for EXT2 FS 0.5b, 95/08/09 + /dev/fhd0 contains a file system with errors, check forced. + Pass 1: Checking inodes, blocks, and sizes + Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780. Ignore error? yes + Pass 2: Checking directory structure + Error reading block 49405 (Attempt to read block from filesystem resulted in short read). Ignore error? yes + Directory inode 11858, block 0, offset 0: directory corrupted + Salvage? yes + Missing '.' in directory inode 11858. + Fix? yes + Missing '..' in directory inode 11858. + Fix? yes - - - - Setting hostname uml [ OK ] - Checking root filesystem - /dev/fhd0 contains a file system with errors, check forced. - Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780. - - /dev/fhd0: UNEXPECTED INCONSISTENCY; RUN fsck MANUALLY. - (i.e., without -a or -p options) - [ FAILED ] - - *** An error occurred during the file system check. - *** Dropping you to a shell; the system will reboot - *** when you leave the shell. - Give root password for maintenance - (or type Control-D for normal startup): - - [root@uml /root]# fsck -y /dev/fhd0 - fsck -y /dev/fhd0 - Parallelizing fsck version 1.14 (9-Jan-1999) - e2fsck 1.14, 9-Jan-1999 for EXT2 FS 0.5b, 95/08/09 - /dev/fhd0 contains a file system with errors, check forced. - Pass 1: Checking inodes, blocks, and sizes - Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780. Ignore error? yes - - Pass 2: Checking directory structure - Error reading block 49405 (Attempt to read block from filesystem resulted in short read). Ignore error? yes - - Directory inode 11858, block 0, offset 0: directory corrupted - Salvage? yes - - Missing '.' in directory inode 11858. - Fix? yes - - Missing '..' in directory inode 11858. - Fix? yes - - Untested (4127) [100fe44c]: trap_kern.c line 31 + Untested (4127) [100fe44c]: trap_kern.c line 31 @@ -3465,7 +3296,7 @@ I need to get the signal thread to detach from pid 4127 so that I can attach to it with gdb. This is done by sending it a SIGUSR1, which is - caught by the signal thread, which detaches the process: + caught by the signal thread, which detaches the process:: kill -USR1 4127 @@ -3474,31 +3305,20 @@ - Now I can run gdb on it: - - - - - - - + Now I can run gdb on it:: - - - - - ~/linux/2.3.26/um 1034: gdb linux - GNU gdb 4.17.0.11 with Linux support - Copyright 1998 Free Software Foundation, Inc. - GDB is free software, covered by the GNU General Public License, and you are - welcome to change it and/or distribute copies of it under certain conditions. - Type "show copying" to see the conditions. - There is absolutely no warranty for GDB. Type "show warranty" for details. - This GDB was configured as "i386-redhat-linux"... - (gdb) att 4127 - Attaching to program `/home/dike/linux/2.3.26/um/linux', Pid 4127 - 0x10075891 in __libc_nanosleep () + ~/linux/2.3.26/um 1034: gdb linux + GNU gdb 4.17.0.11 with Linux support + Copyright 1998 Free Software Foundation, Inc. + GDB is free software, covered by the GNU General Public License, and you are + welcome to change it and/or distribute copies of it under certain conditions. + Type "show copying" to see the conditions. + There is absolutely no warranty for GDB. Type "show warranty" for details. + This GDB was configured as "i386-redhat-linux"... + (gdb) att 4127 + Attaching to program `/home/dike/linux/2.3.26/um/linux', Pid 4127 + 0x10075891 in __libc_nanosleep () @@ -3506,7 +3326,7 @@ The backtrace shows that it was in a write and that the fault address (address in frame 3) is 0x50000800, which is right in the middle of - the signal thread's stack page: + the signal thread's stack page:: (gdb) bt @@ -3540,58 +3360,48 @@ - - Going up the stack to the segv_handler frame and looking at where in the code the access happened shows that it happened near line 110 of - block_dev.c: - - - - - - - - - - (gdb) up - #1 0x1007584d in __sleep (seconds=1000000) - at ../sysdeps/unix/sysv/linux/sleep.c:78 - ../sysdeps/unix/sysv/linux/sleep.c:78: No such file or directory. - (gdb) - #2 0x1006ce9a in stop () at user_util.c:191 - 191 while(1) sleep(1000000); - (gdb) - #3 0x1006bf88 in segv (address=1342179328, is_write=2) at trap_kern.c:31 - 31 KERN_UNTESTED(); - (gdb) - #4 0x1006c628 in segv_handler (sc=0x5006eaf8) at trap_user.c:174 - 174 segv(sc->cr2, sc->err & 2); - (gdb) p *sc - $1 = {gs = 0, __gsh = 0, fs = 0, __fsh = 0, es = 43, __esh = 0, ds = 43, - __dsh = 0, edi = 1342179328, esi = 134973440, ebp = 1342631484, - esp = 1342630864, ebx = 256, edx = 0, ecx = 256, eax = 1024, trapno = 14, - err = 6, eip = 268550834, cs = 35, __csh = 0, eflags = 66070, - esp_at_signal = 1342630864, ss = 43, __ssh = 0, fpstate = 0x0, oldmask = 0, - cr2 = 1342179328} - (gdb) p (void *)268550834 - $2 = (void *) 0x1001c2b2 - (gdb) i sym $2 - block_write + 1090 in section .text - (gdb) i line *$2 - Line 209 of "/home/dike/linux/2.3.26/um/include/asm/arch/string.h" - starts at address 0x1001c2a1 - and ends at 0x1001c2bf . - (gdb) i line *0x1001c2c0 - Line 110 of "block_dev.c" starts at address 0x1001c2bf - and ends at 0x1001c2e3 . - - + block_dev.c:: + + + + (gdb) up + #1 0x1007584d in __sleep (seconds=1000000) + at ../sysdeps/unix/sysv/linux/sleep.c:78 + ../sysdeps/unix/sysv/linux/sleep.c:78: No such file or directory. + (gdb) + #2 0x1006ce9a in stop () at user_util.c:191 + 191 while(1) sleep(1000000); + (gdb) + #3 0x1006bf88 in segv (address=1342179328, is_write=2) at trap_kern.c:31 + 31 KERN_UNTESTED(); + (gdb) + #4 0x1006c628 in segv_handler (sc=0x5006eaf8) at trap_user.c:174 + 174 segv(sc->cr2, sc->err & 2); + (gdb) p *sc + $1 = {gs = 0, __gsh = 0, fs = 0, __fsh = 0, es = 43, __esh = 0, ds = 43, + __dsh = 0, edi = 1342179328, esi = 134973440, ebp = 1342631484, + esp = 1342630864, ebx = 256, edx = 0, ecx = 256, eax = 1024, trapno = 14, + err = 6, eip = 268550834, cs = 35, __csh = 0, eflags = 66070, + esp_at_signal = 1342630864, ss = 43, __ssh = 0, fpstate = 0x0, oldmask = 0, + cr2 = 1342179328} + (gdb) p (void *)268550834 + $2 = (void *) 0x1001c2b2 + (gdb) i sym $2 + block_write + 1090 in section .text + (gdb) i line *$2 + Line 209 of "/home/dike/linux/2.3.26/um/include/asm/arch/string.h" + starts at address 0x1001c2a1 + and ends at 0x1001c2bf . + (gdb) i line *0x1001c2c0 + Line 110 of "block_dev.c" starts at address 0x1001c2bf + and ends at 0x1001c2e3 . Looking at the source shows that the fault happened during a call to - copy_from_user to copy the data into the kernel: + copy_from_user to copy the data into the kernel:: 107 count -= chars; @@ -3601,10 +3411,8 @@ - - p is the pointer which must contain 0x50000800, since buf contains - 0x80b8800 (frame 8 above). It is defined as: + 0x80b8800 (frame 8 above). It is defined as:: p = offset + bh->b_data; @@ -3615,24 +3423,22 @@ I need to figure out what bh is, and it just so happens that bh is passed as an argument to mark_buffer_uptodate and mark_buffer_dirty a - few lines later, so I do a little disassembly: - - + few lines later, so I do a little disassembly:: - (gdb) disas 0x1001c2bf 0x1001c2e0 - Dump of assembler code from 0x1001c2bf to 0x1001c2d0: - 0x1001c2bf : addl %eax,0xc(%ebp) - 0x1001c2c2 : movl 0xfffffdd4(%ebp),%edx - 0x1001c2c8 : btsl $0x0,0x18(%edx) - 0x1001c2cd : btsl $0x1,0x18(%edx) - 0x1001c2d2 : sbbl %ecx,%ecx - 0x1001c2d4 : testl %ecx,%ecx - 0x1001c2d6 : jne 0x1001c2e3 - 0x1001c2d8 : pushl $0x0 - 0x1001c2da : pushl %edx - 0x1001c2db : call 0x1001819c <__mark_buffer_dirty> - End of assembler dump. + (gdb) disas 0x1001c2bf 0x1001c2e0 + Dump of assembler code from 0x1001c2bf to 0x1001c2d0: + 0x1001c2bf : addl %eax,0xc(%ebp) + 0x1001c2c2 : movl 0xfffffdd4(%ebp),%edx + 0x1001c2c8 : btsl $0x0,0x18(%edx) + 0x1001c2cd : btsl $0x1,0x18(%edx) + 0x1001c2d2 : sbbl %ecx,%ecx + 0x1001c2d4 : testl %ecx,%ecx + 0x1001c2d6 : jne 0x1001c2e3 + 0x1001c2d8 : pushl $0x0 + 0x1001c2da : pushl %edx + 0x1001c2db : call 0x1001819c <__mark_buffer_dirty> + End of assembler dump. @@ -3640,7 +3446,7 @@ At that point, bh is in %edx (address 0x1001c2da), which is calculated at 0x1001c2c2 as %ebp + 0xfffffdd4, so I figure exactly what that is, - taking %ebp from the sigcontext_struct above: + taking %ebp from the sigcontext_struct above:: (gdb) p (void *)1342631484 @@ -3657,7 +3463,7 @@ Now, I look at the structure to see what's in it, and particularly, - what its b_data field contains: + what its b_data field contains:: (gdb) p *((struct buffer_head *)0x50100200) @@ -3682,18 +3488,18 @@ The b_page field is a pointer to the page_struct representing the 0x50000000 page. Looking at it shows the kernel's idea of the state - of that page: + of that page:: - (gdb) p *$13.b_page - $17 = {list = {next = 0x50004a5c, prev = 0x100c5174}, mapping = 0x0, - index = 0, next_hash = 0x0, count = {counter = 1}, flags = 132, lru = { - next = 0x50008460, prev = 0x50019350}, wait = { - lock = , task_list = {next = 0x50004024, - prev = 0x50004024}, __magic = 1342193708, __creator = 0}, - pprev_hash = 0x0, buffers = 0x501002c0, virtual = 1342177280, - zone = 0x100c5160} + (gdb) p *$13.b_page + $17 = {list = {next = 0x50004a5c, prev = 0x100c5174}, mapping = 0x0, + index = 0, next_hash = 0x0, count = {counter = 1}, flags = 132, lru = { + next = 0x50008460, prev = 0x50019350}, wait = { + lock = , task_list = {next = 0x50004024, + prev = 0x50004024}, __magic = 1342193708, __creator = 0}, + pprev_hash = 0x0, buffers = 0x501002c0, virtual = 1342177280, + zone = 0x100c5160} @@ -3702,7 +3508,7 @@ Some sanity-checking: the virtual field shows the "virtual" address of this page, which in this kernel is the same as its "physical" address, and the page_struct itself should be mem_map[0], since it represents - the first page of memory: + the first page of memory:: @@ -3719,7 +3525,7 @@ Now to check out the page_struct itself. In particular, the flags - field shows whether the page is considered free or not: + field shows whether the page is considered free or not:: (gdb) p (void *)132 @@ -3739,7 +3545,7 @@ In my setup_arch procedure, I have the following code which looks just - fine: + fine:: @@ -3762,7 +3568,7 @@ Stepping into init_bootmem, and looking at bootmem_map before looking - at what it contains shows the following: + at what it contains shows the following:: @@ -3788,18 +3594,20 @@ - 13. What to do when UML doesn't work +13. What to do when UML doesn't work +===================================== - 13.1. Strange compilation errors when you build from source +13.1. Strange compilation errors when you build from source +------------------------------------------------------------ As of test11, it is necessary to have "ARCH=um" in the environment or on the make command line for all steps in building UML, including clean, distclean, or mrproper, config, menuconfig, or xconfig, dep, and linux. If you forget for any of them, the i386 build seems to - contaminate the UML build. If this happens, start from scratch with + contaminate the UML build. If this happens, start from scratch with:: host% @@ -3811,7 +3619,7 @@ and repeat the build process with ARCH=um on all the steps. - See ``Compiling the kernel and modules'' for more details. + See :ref:`Compiling_the_kernel_and_modules` for more details. Another cause of strange compilation errors is building UML in @@ -3824,11 +3632,11 @@ - 13.3. A variety of panics and hangs with /tmp on a reiserfs filesys- - tem +13.3. A variety of panics and hangs with /tmp on a reiserfs filesystem +----------------------------------------------------------------------- I saw this on reiserfs 3.5.21 and it seems to be fixed in 3.5.27. - Panics preceded by + Panics preceded by:: Detaching pid nnnn @@ -3854,17 +3662,19 @@ - 13.5. UML doesn't work when /tmp is an NFS filesystem +13.5. UML doesn't work when /tmp is an NFS filesystem +------------------------------------------------------ This seems to be a similar situation with the ReiserFS problem above. Some versions of NFS seems not to handle mmap correctly, which UML depends on. The workaround is have /tmp be a non-NFS directory. - 13.6. UML hangs on boot when compiled with gprof support +13.6. UML hangs on boot when compiled with gprof support +--------------------------------------------------------- If you build UML with gprof support and, early in the boot, it does - this + this:: kernel BUG at page_alloc.c:100! @@ -3878,10 +3688,11 @@ - 13.7. syslogd dies with a SIGTERM on startup +13.7. syslogd dies with a SIGTERM on startup +--------------------------------------------- The exact boot error depends on the distribution that you're booting, - but Debian produces this: + but Debian produces this:: /etc/rc2.d/S10sysklogd: line 49: 93 Terminated @@ -3891,23 +3702,21 @@ This is a syslogd bug. There's a race between a parent process - installing a signal handler and its child sending the signal. See - this uml-devel post for the details. + installing a signal handler and its child sending the signal. - 13.8. TUN/TAP networking doesn't work on a 2.4 host +13.8. TUN/TAP networking doesn't work on a 2.4 host +---------------------------------------------------- - There are a couple of problems which were - name="pointed - out"> by Tim Robinson + There are a couple of problems which were reported by + Tim Robinson - o It doesn't work on hosts running 2.4.7 (or thereabouts) or earlier. + - It doesn't work on hosts running 2.4.7 (or thereabouts) or earlier. The fix is to upgrade to something more recent and then read the next item. - o If you see + - If you see:: File descriptor in bad state @@ -3921,8 +3730,8 @@ - 13.9. You can network to the host but not to other machines on the - net +13.9. You can network to the host but not to other machines on the net +======================================================================= If you can connect to the host, and the host can connect to UML, but you cannot connect to any other machines, then you may need to enable @@ -3930,7 +3739,7 @@ using private IP addresses (192.168.x.x or 10.x.x.x) for host/UML networking, rather than the public address space that your host is connected to. UML does not enable IP Masquerading, so you will need - to create a static rule to enable it: + to create a static rule to enable it:: host% @@ -3944,11 +3753,11 @@ Documentation on IP Masquerading, and SNAT, can be found at - www.netfilter.org . + http://www.netfilter.org. If you can reach the local net, but not the outside Internet, then - that is usually a routing problem. The UML needs a default route: + that is usually a routing problem. The UML needs a default route:: UML# @@ -3972,7 +3781,8 @@ - 13.10. I have no root and I want to scream +13.10. I have no root and I want to scream +=========================================== Thanks to Birgit Wahlich for telling me about this strange one. It turns out that there's a limit of six environment variables on the @@ -3987,14 +3797,16 @@ - 13.11. UML build conflict between ptrace.h and ucontext.h +13.11. UML build conflict between ptrace.h and ucontext.h +========================================================== On some older systems, /usr/include/asm/ptrace.h and /usr/include/sys/ucontext.h define the same names. So, when they're included together, the defines from one completely mess up the parsing - of the other, producing errors like: + of the other, producing errors like:: + /usr/include/sys/ucontext.h:47: parse error before - `10' + `10` @@ -4007,7 +3819,8 @@ - 13.12. The UML BogoMips is exactly half the host's BogoMips +13.12. The UML BogoMips is exactly half the host's BogoMips +------------------------------------------------------------ On i386 kernels, there are two ways of running the loop that is used to calculate the BogoMips rating, using the TSC if it's there or using @@ -4019,15 +3832,17 @@ - 13.13. When you run UML, it immediately segfaults +13.13. When you run UML, it immediately segfaults +-------------------------------------------------- If the host is configured with the 2G/2G address space split, that's - why. See ``UML on 2G/2G hosts'' for the details on getting UML to + why. See ref:`UML_on_2G/2G_hosts` for the details on getting UML to run on your host. - 13.14. xterms appear, then immediately disappear +13.14. xterms appear, then immediately disappear +------------------------------------------------- If you're running an up to date kernel with an old release of uml_utilities, the port-helper program will not work properly, so @@ -4039,7 +3854,8 @@ - 13.15. Any other panic, hang, or strange behavior +13.15. Any other panic, hang, or strange behavior +-------------------------------------------------- If you're seeing truly strange behavior, such as hangs or panics that happen in random places, or you try running the debugger to see what's @@ -4057,9 +3873,13 @@ it and that a fix is imminent. - If you want to be super-helpful, read ``Diagnosing Problems'' and + If you want to be super-helpful, read :ref:`Diagnosing_Problems` and follow the instructions contained therein. - 14. Diagnosing Problems + +.. _Diagnosing_Problems: + +14. Diagnosing Problems +======================== If you get UML to crash, hang, or otherwise misbehave, you should @@ -4074,21 +3894,22 @@ For any diagnosis, you're going to need to build a debugging kernel. The binaries from this site aren't debuggable. If you haven't done - this before, read about ``Compiling the kernel and modules'' and - ``Kernel debugging'' UML first. + this before, read about :ref:`Compiling_the_kernel_and_modules` and + :ref:`Kernel_debugging` UML first. - 14.1. Case 1 : Normal kernel panics +14.1. Case 1 : Normal kernel panics +------------------------------------ The most common case is for a normal thread to panic. To debug this, you will need to run it under the debugger (add 'debug' to the command line). An xterm will start up with gdb running inside it. Continue - it when it stops in start_kernel and make it crash. Now ^C gdb and + it when it stops in start_kernel and make it crash. Now ``^C gdb`` and If the panic was a "Kernel mode fault", then there will be a segv frame on the stack and I'm going to want some more information. The - stack might look something like this: + stack might look something like this:: (UML gdb) backtrace @@ -4107,7 +3928,7 @@ I'm going to want to see the symbol and line information for the value - of ip in the segv frame. In this case, you would do the following: + of ip in the segv frame. In this case, you would do the following:: (UML gdb) i sym 268849158 @@ -4115,7 +3936,7 @@ - and + and:: (UML gdb) i line *268849158 @@ -4128,7 +3949,8 @@ to get that information from the faulting ip. - 14.2. Case 2 : Tracing thread panics +14.2. Case 2 : Tracing thread panics +------------------------------------- The less common and more painful case is when the tracing thread panics. In this case, the kernel debugger will be useless because it @@ -4136,7 +3958,7 @@ do is get a backtrace from the tracing thread. This is done by figuring out what its pid is, firing up gdb, and attaching it to that pid. You can figure out the tracing thread pid by looking at the - first line of the console output, which will look like this: + first line of the console output, which will look like this:: tracing thread pid = 15851 @@ -4145,7 +3967,7 @@ or by running ps on the host and finding the line that looks like - this: + this:: jdike 15851 4.5 0.4 132568 1104 pts/0 S 21:34 0:05 ./linux [(tracing thread)] @@ -4164,7 +3986,7 @@ 14.3. Case 3 : Tracing thread panics caused by other threads However, there are cases where the misbehavior of another thread - caused the problem. The most common panic of this type is: + caused the problem. The most common panic of this type is:: wait_for_stop failed to wait for to stop with @@ -4177,7 +3999,7 @@ debugger is defunct and without some fancy footwork, another gdb can't attach to it. So, this is how the fancy footwork goes: - In a shell: + In a shell:: host% kill -STOP pid @@ -4185,7 +4007,7 @@ - Run gdb on the tracing thread as described in case 2 and do: + Run gdb on the tracing thread as described in case 2 and do:: (host gdb) call detach(pid) @@ -4193,7 +4015,7 @@ If you get a segfault, do it again. It always works the second time. - Detach from the tracing thread and attach to that other thread: + Detach from the tracing thread and attach to that other thread:: (host gdb) detach @@ -4209,7 +4031,7 @@ If gdb hangs when attaching to that process, go back to a shell and - do: + do:: host% @@ -4218,7 +4040,7 @@ - And then get the backtrace: + And then get the backtrace:: (host gdb) backtrace @@ -4227,13 +4049,14 @@ - 14.4. Case 4 : Hangs +14.4. Case 4 : Hangs +--------------------- Hangs seem to be fairly rare, but they sometimes happen. When a hang happens, we need a backtrace from the offending process. Run the kernel debugger as described in case 1 and get a backtrace. If the current process is not the idle thread, then send in the backtrace. - You can tell that it's the idle thread if the stack looks like this: + You can tell that it's the idle thread if the stack looks like this:: #0 0x100b1401 in __libc_nanosleep () @@ -4257,7 +4080,8 @@ - 15. Thanks +15. Thanks +=========== A number of people have helped this project in various ways, and this @@ -4274,20 +4098,21 @@ bookkeeping lapses and I forget about contributions. - 15.1. Code and Documentation +15.1. Code and Documentation +----------------------------- Rusty Russell - - o wrote the HOWTO + - wrote the HOWTO + http://user-mode-linux.sourceforge.net/old/UserModeLinux-HOWTO.html - o prodded me into making this project official and putting it on + - prodded me into making this project official and putting it on SourceForge - o came up with the way cool UML logo + - came up with the way cool UML logo + http://user-mode-linux.sourceforge.net/uml-small.png - o redid the config process + - redid the config process Peter Moulder - Fixed my config and build @@ -4296,34 +4121,32 @@ Bill Stearns - - o HOWTO updates + - HOWTO updates - o lots of bug reports + - lots of bug reports - o lots of testing + - lots of testing - o dedicated a box (uml.ists.dartmouth.edu) to support UML development + - dedicated a box (uml.ists.dartmouth.edu) to support UML development - o wrote the mkrootfs script, which allows bootable filesystems of + - wrote the mkrootfs script, which allows bootable filesystems of RPM-based distributions to be cranked out - o cranked out a large number of filesystems with said script + - cranked out a large number of filesystems with said script Jim Leu - Wrote the virtual ethernet driver and associated usermode tools - Lars Brinkhoff - Contributed the ptrace - proxy from his own project to allow easier - kernel debugging + Lars Brinkhoff http://lars.nocrew.org/ - Contributed the ptrace + proxy from his own project to allow easier kernel debugging Andrea Arcangeli - Redid some of the early boot code so that it would work on machines with Large File Support - Chris Emerson - Did - the first UML port to Linux/ppc + Chris Emerson - Did the first UML port to Linux/ppc Harald Welte - Wrote the multicast @@ -4338,7 +4161,7 @@ wrote the iomem emulation support - Henrik Nordstrom - Provided a variety + Henrik Nordstrom http://hem.passagen.se/hno/ - Provided a variety of patches, fixes, and clues @@ -4373,190 +4196,193 @@ submitted patches for the slip transport and lots of other things. - David Coulson - + David Coulson http://davidcoulson.net - - o Set up the usermodelinux.org site, + - Set up the http://usermodelinux.org site, which is a great way of keeping the UML user community on top of UML goings-on. - o Site documentation and updates + - Site documentation and updates - o Nifty little UML management daemon UMLd - + - Nifty little UML management daemon UMLd - o Lots of testing and bug reports + - Lots of testing and bug reports - 15.2. Flushing out bugs +15.2. Flushing out bugs +------------------------ - o Yuri Pudgorodsky + - Yuri Pudgorodsky - o Gerald Britton + - Gerald Britton - o Ian Wehrman + - Ian Wehrman - o Gord Lamb + - Gord Lamb - o Eugene Koontz + - Eugene Koontz - o John H. Hartman + - John H. Hartman - o Anders Karlsson + - Anders Karlsson - o Daniel Phillips + - Daniel Phillips - o John Fremlin + - John Fremlin - o Rainer Burgstaller + - Rainer Burgstaller - o James Stevenson + - James Stevenson - o Matt Clay + - Matt Clay - o Cliff Jefferies + - Cliff Jefferies - o Geoff Hoff + - Geoff Hoff - o Lennert Buytenhek + - Lennert Buytenhek - o Al Viro + - Al Viro - o Frank Klingenhoefer + - Frank Klingenhoefer - o Livio Baldini Soares + - Livio Baldini Soares - o Jon Burgess + - Jon Burgess - o Petru Paler + - Petru Paler - o Paul + - Paul - o Chris Reahard + - Chris Reahard - o Sverker Nilsson + - Sverker Nilsson - o Gong Su + - Gong Su - o johan verrept + - johan verrept - o Bjorn Eriksson + - Bjorn Eriksson - o Lorenzo Allegrucci + - Lorenzo Allegrucci - o Muli Ben-Yehuda + - Muli Ben-Yehuda - o David Mansfield + - David Mansfield - o Howard Goff + - Howard Goff - o Mike Anderson + - Mike Anderson - o John Byrne + - John Byrne - o Sapan J. Batia + - Sapan J. Batia - o Iris Huang + - Iris Huang - o Jan Hudec + - Jan Hudec - o Voluspa + - Voluspa - 15.3. Buglets and clean-ups +15.3. Buglets and clean-ups +---------------------------- - o Dave Zarzycki + - Dave Zarzycki - o Adam Lazur + - Adam Lazur - o Boria Feigin + - Boria Feigin - o Brian J. Murrell + - Brian J. Murrell - o JS + - JS - o Roman Zippel + - Roman Zippel - o Wil Cooley + - Wil Cooley - o Ayelet Shemesh + - Ayelet Shemesh - o Will Dyson + - Will Dyson - o Sverker Nilsson + - Sverker Nilsson - o dvorak + - dvorak - o v.naga srinivas + - v.naga srinivas - o Shlomi Fish + - Shlomi Fish - o Roger Binns + - Roger Binns - o johan verrept + - johan verrept - o MrChuoi + - MrChuoi - o Peter Cleve + - Peter Cleve - o Vincent Guffens + - Vincent Guffens - o Nathan Scott + - Nathan Scott - o Patrick Caulfield + - Patrick Caulfield - o jbearce + - jbearce - o Catalin Marinas + - Catalin Marinas - o Shane Spencer + - Shane Spencer - o Zou Min + - Zou Min - o Ryan Boder + - Ryan Boder - o Lorenzo Colitti + - Lorenzo Colitti - o Gwendal Grignou + - Gwendal Grignou - o Andre' Breiler + - Andre' Breiler - o Tsutomu Yasuda + - Tsutomu Yasuda - 15.4. Case Studies +15.4. Case Studies +------------------- - o Jon Wright + - Jon Wright - o William McEwan + - William McEwan - o Michael Richardson + - Michael Richardson - 15.5. Other contributions +15.5. Other contributions +-------------------------- Bill Carr made the Red Hat mkrootfs script work with RH 6.2. Michael Jennings sent in some material which - is now gracing the top of the index page of this site. + is now gracing the top of the index page + http://user-mode-linux.sourceforge.net/ of this site. - SGI (and more specifically Ralf Baechle ) gave me an account on oss.sgi.com - . The bandwidth there made it possible to + SGI (and more specifically Ralf Baechle ) gave me an account on oss.sgi.com. + The bandwidth there made it possible to produce most of the filesystems available on the project download page. @@ -4573,17 +4399,5 @@ Chris Reahard built a specialized root filesystem for running a DNS server jailed inside UML. It's available from the download - page in the Jail + http://user-mode-linux.sourceforge.net/old/dl-sf.html page in the Jail Filesystems section. - - - - - - - - - - - - diff --git a/Documentation/x86/index.rst b/Documentation/x86/index.rst index a8de2fbc1caad73319ee40b2c16a2ec83642ea7e..265d9e9a093b8d3810b2148b3f794dfa58c0b473 100644 --- a/Documentation/x86/index.rst +++ b/Documentation/x86/index.rst @@ -19,7 +19,6 @@ x86-specific Documentation tlb mtrr pat - intel_mpx intel-iommu intel_txt amd-memory-encryption diff --git a/MAINTAINERS b/MAINTAINERS index 38fe2f3f7b6f290e67168db75a1881cfbcc5be8b..cc1d18cb5d186e2995b5202d1a63903ed10f0183 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -693,7 +693,7 @@ ALLWINNER CPUFREQ DRIVER M: Yangtao Li L: linux-pm@vger.kernel.org S: Maintained -F: Documentation/devicetree/bindings/opp/sun50i-nvmem-cpufreq.txt +F: Documentation/devicetree/bindings/opp/allwinner,sun50i-h6-operating-points.yaml F: drivers/cpufreq/sun50i-cpufreq-nvmem.c ALLWINNER CRYPTO DRIVERS @@ -2796,11 +2796,11 @@ F: drivers/block/aoe/ ATHEROS 71XX/9XXX GPIO DRIVER M: Alban Bedel +S: Maintained W: https://github.com/AlbanBedel/linux T: git git://github.com/AlbanBedel/linux -S: Maintained -F: drivers/gpio/gpio-ath79.c F: Documentation/devicetree/bindings/gpio/gpio-ath79.txt +F: drivers/gpio/gpio-ath79.c ATHEROS 71XX/9XXX USB PHY DRIVER M: Alban Bedel @@ -3422,8 +3422,8 @@ BROADCOM BRCMSTB GPIO DRIVER M: Gregory Fong L: bcm-kernel-feedback-list@broadcom.com S: Supported -F: drivers/gpio/gpio-brcmstb.c F: Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.txt +F: drivers/gpio/gpio-brcmstb.c BROADCOM BRCMSTB I2C DRIVER M: Kamal Dasu @@ -3481,8 +3481,8 @@ BROADCOM KONA GPIO DRIVER M: Ray Jui L: bcm-kernel-feedback-list@broadcom.com S: Supported -F: drivers/gpio/gpio-bcm-kona.c F: Documentation/devicetree/bindings/gpio/brcm,kona-gpio.txt +F: drivers/gpio/gpio-bcm-kona.c BROADCOM NETXTREME-E ROCE DRIVER M: Selvin Xavier @@ -3597,8 +3597,8 @@ F: sound/pci/bt87x.c BT8XXGPIO DRIVER M: Michael Buesch -W: http://bu3sch.de/btgpio.php S: Maintained +W: http://bu3sch.de/btgpio.php F: drivers/gpio/gpio-bt8xx.c BTRFS FILE SYSTEM @@ -3649,6 +3649,7 @@ F: sound/pci/oxygen/ C-SKY ARCHITECTURE M: Guo Ren +L: linux-csky@vger.kernel.org T: git https://github.com/c-sky/csky-linux.git S: Supported F: arch/csky/ @@ -3909,7 +3910,7 @@ S: Supported F: Documentation/filesystems/ceph.txt F: fs/ceph/ -CERTIFICATE HANDLING: +CERTIFICATE HANDLING M: David Howells M: David Woodhouse L: keyrings@vger.kernel.org @@ -3919,7 +3920,7 @@ F: certs/ F: scripts/sign-file.c F: scripts/extract-cert.c -CERTIFIED WIRELESS USB (WUSB) SUBSYSTEM: +CERTIFIED WIRELESS USB (WUSB) SUBSYSTEM L: devel@driverdev.osuosl.org S: Obsolete F: drivers/staging/wusbcore/ @@ -4016,7 +4017,7 @@ M: Cheng-Yi Chiang S: Maintained R: Enric Balletbo i Serra R: Guenter Roeck -F: Documentation/devicetree/bindings/sound/google,cros-ec-codec.txt +F: Documentation/devicetree/bindings/sound/google,cros-ec-codec.yaml F: sound/soc/codecs/cros_ec_codec.* CIRRUS LOGIC AUDIO CODEC DRIVERS @@ -4072,7 +4073,6 @@ F: drivers/scsi/snic/ CISCO VIC ETHERNET NIC DRIVER M: Christian Benvenuti M: Govindarajulu Varadarajan <_govind@gmx.com> -M: Parvi Kaustubhi S: Supported F: drivers/net/ethernet/cisco/enic/ @@ -4474,7 +4474,7 @@ L: linux-media@vger.kernel.org T: git git://linuxtv.org/media_tree.git S: Maintained F: drivers/media/platform/sunxi/sun6i-csi/ -F: Documentation/devicetree/bindings/media/sun6i-csi.txt +F: Documentation/devicetree/bindings/media/allwinner,sun6i-a31-csi.yaml CW1200 WLAN driver M: Solomon Peachy @@ -4571,7 +4571,7 @@ F: drivers/infiniband/hw/cxgb4/ F: include/uapi/rdma/cxgb4-abi.h CXGB4VF ETHERNET DRIVER (CXGB4VF) -M: Casey Leedom +M: Vishal Kulkarni L: netdev@vger.kernel.org W: http://www.chelsio.com S: Supported @@ -5667,7 +5667,7 @@ L: dri-devel@lists.freedesktop.org T: git git://anongit.freedesktop.org/drm/drm-misc S: Maintained F: drivers/gpu/drm/stm -F: Documentation/devicetree/bindings/display/st,stm32-ltdc.txt +F: Documentation/devicetree/bindings/display/st,stm32-ltdc.yaml DRM DRIVERS FOR TI LCDC M: Jyri Sarha @@ -5932,12 +5932,12 @@ S: Maintained F: drivers/media/dvb-frontends/ec100* ECRYPT FILE SYSTEM -M: Tyler Hicks +M: Tyler Hicks L: ecryptfs@vger.kernel.org W: http://ecryptfs.org W: https://launchpad.net/ecryptfs T: git git://git.kernel.org/pub/scm/linux/kernel/git/tyhicks/ecryptfs.git -S: Supported +S: Odd Fixes F: Documentation/filesystems/ecryptfs.txt F: fs/ecryptfs/ @@ -6197,7 +6197,6 @@ S: Supported F: drivers/scsi/be2iscsi/ Emulex 10Gbps NIC BE2, BE3-R, Lancer, Skyhawk-R DRIVER (be2net) -M: Sathya Perla M: Ajit Khaparde M: Sriharsha Basavapatna M: Somnath Kotur @@ -7047,7 +7046,7 @@ L: kvm@vger.kernel.org S: Supported F: drivers/uio/uio_pci_generic.c -GENERIC VDSO LIBRARY: +GENERIC VDSO LIBRARY M: Andy Lutomirski M: Thomas Gleixner M: Vincenzo Frascino @@ -7143,18 +7142,18 @@ GPIO SUBSYSTEM M: Linus Walleij M: Bartosz Golaszewski L: linux-gpio@vger.kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio.git S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio.git +F: Documentation/ABI/obsolete/sysfs-gpio +F: Documentation/ABI/testing/gpio-cdev +F: Documentation/admin-guide/gpio/ F: Documentation/devicetree/bindings/gpio/ F: Documentation/driver-api/gpio/ -F: Documentation/admin-guide/gpio/ -F: Documentation/ABI/testing/gpio-cdev -F: Documentation/ABI/obsolete/sysfs-gpio F: drivers/gpio/ +F: include/asm-generic/gpio.h F: include/linux/gpio/ F: include/linux/gpio.h F: include/linux/of_gpio.h -F: include/asm-generic/gpio.h F: include/uapi/linux/gpio.h F: tools/gpio/ @@ -7737,7 +7736,7 @@ Hyper-V CORE AND DRIVERS M: "K. Y. Srinivasan" M: Haiyang Zhang M: Stephen Hemminger -M: Sasha Levin +M: Wei Liu T: git git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux.git L: linux-hyperv@vger.kernel.org S: Supported @@ -8055,8 +8054,8 @@ F: drivers/scsi/ips.* ICH LPC AND GPIO DRIVER M: Peter Tyser S: Maintained -F: drivers/mfd/lpc_ich.c F: drivers/gpio/gpio-ich.c +F: drivers/mfd/lpc_ich.c ICY I2C DRIVER M: Max Staudt @@ -8392,7 +8391,7 @@ M: Joonas Lahtinen M: Rodrigo Vivi L: intel-gfx@lists.freedesktop.org W: https://01.org/linuxgraphics/ -B: https://01.org/linuxgraphics/documentation/how-report-bugs +B: https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs C: irc://chat.freenode.net/intel-gfx Q: http://patchwork.freedesktop.org/project/intel-gfx/ T: git git://anongit.freedesktop.org/drm-intel @@ -9278,7 +9277,7 @@ F: include/keys/trusted-type.h F: security/keys/trusted.c F: include/keys/trusted.h -KEYS/KEYRINGS: +KEYS/KEYRINGS M: David Howells M: Jarkko Sakkinen L: keyrings@vger.kernel.org @@ -10163,7 +10162,7 @@ MAXBOTIX ULTRASONIC RANGER IIO DRIVER M: Andreas Klinger L: linux-iio@vger.kernel.org S: Maintained -F: Documentation/devicetree/bindings/iio/proximity/maxbotix,mb1232.txt +F: Documentation/devicetree/bindings/iio/proximity/maxbotix,mb1232.yaml F: drivers/iio/proximity/mb1232.c MAXIM MAX77650 PMIC MFD DRIVER @@ -10466,7 +10465,7 @@ M: Hugues Fruchet L: linux-media@vger.kernel.org T: git git://linuxtv.org/media_tree.git S: Supported -F: Documentation/devicetree/bindings/media/st,stm32-dcmi.txt +F: Documentation/devicetree/bindings/media/st,stm32-dcmi.yaml F: drivers/media/platform/stm32/stm32-dcmi.c MEDIA DRIVERS FOR NVIDIA TEGRA - VDE @@ -11114,14 +11113,12 @@ S: Maintained F: drivers/usb/image/microtek.* MIPS -M: Ralf Baechle -M: Paul Burton +M: Thomas Bogendoerfer L: linux-mips@vger.kernel.org W: http://www.linux-mips.org/ -T: git git://git.linux-mips.org/pub/scm/ralf/linux.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/mips/linux.git -Q: http://patchwork.linux-mips.org/project/linux-mips/list/ -S: Supported +Q: https://patchwork.kernel.org/project/linux-mips/list/ +S: Maintained F: Documentation/devicetree/bindings/mips/ F: Documentation/mips/ F: arch/mips/ @@ -11484,7 +11481,7 @@ F: drivers/scsi/mac_scsi.* F: drivers/scsi/sun3_scsi.* F: drivers/scsi/sun3_scsi_vme.c -NCSI LIBRARY: +NCSI LIBRARY M: Samuel Mendoza-Jonas S: Maintained F: net/ncsi/ @@ -12740,7 +12737,7 @@ M: Tom Joseph L: linux-pci@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/pci/cdns,*.txt -F: drivers/pci/controller/pcie-cadence* +F: drivers/pci/controller/cadence/ PCI DRIVER FOR FREESCALE LAYERSCAPE M: Minghuan Lian @@ -12953,7 +12950,6 @@ M: Robert Richter L: linux-pci@vger.kernel.org L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Supported -F: Documentation/devicetree/bindings/pci/pci-thunder-* F: drivers/pci/controller/pci-thunder-* PCIE DRIVER FOR HISILICON @@ -13512,7 +13508,7 @@ L: linuxppc-dev@lists.ozlabs.org S: Maintained F: drivers/block/ps3vram.c -PSAMPLE PACKET SAMPLING SUPPORT: +PSAMPLE PACKET SAMPLING SUPPORT M: Yotam Gigi S: Maintained F: net/psample @@ -14228,7 +14224,7 @@ F: include/dt-bindings/reset/ F: include/linux/reset.h F: include/linux/reset/ F: include/linux/reset-controller.h -K: \b(?:devm_|of_)?reset_control(?:ler_[a-z]+|_[a-z_]+)?\b +K: \b(?:devm_|of_)?reset_control(?:ler_[a-z]+|_[a-z_]+)?\b RESTARTABLE SEQUENCES SUPPORT M: Mathieu Desnoyers @@ -14582,10 +14578,10 @@ F: drivers/media/pci/saa7146/ F: include/media/drv-intf/saa7146* SAFESETID SECURITY MODULE -M: Micah Morton -S: Supported -F: security/safesetid/ -F: Documentation/admin-guide/LSM/SafeSetID.rst +M: Micah Morton +S: Supported +F: security/safesetid/ +F: Documentation/admin-guide/LSM/SafeSetID.rst SAMSUNG AUDIO (ASoC) DRIVERS M: Krzysztof Kozlowski @@ -15923,7 +15919,7 @@ F: drivers/*/stm32-*timer* F: drivers/pwm/pwm-stm32* F: include/linux/*/stm32-*tim* F: Documentation/ABI/testing/*timer-stm32 -F: Documentation/devicetree/bindings/*/stm32-*timer* +F: Documentation/devicetree/bindings/*/*stm32-*timer* F: Documentation/devicetree/bindings/pwm/pwm-stm32* STMMAC ETHERNET DRIVER @@ -16075,20 +16071,22 @@ F: Documentation/devicetree/bindings/reset/snps,axs10x-reset.txt SYNOPSYS CREG GPIO DRIVER M: Eugeniy Paltsev S: Maintained -F: drivers/gpio/gpio-creg-snps.c F: Documentation/devicetree/bindings/gpio/snps,creg-gpio.txt +F: drivers/gpio/gpio-creg-snps.c SYNOPSYS DESIGNWARE 8250 UART DRIVER R: Andy Shevchenko S: Maintained F: drivers/tty/serial/8250/8250_dw.c +F: drivers/tty/serial/8250/8250_dwlib.* +F: drivers/tty/serial/8250/8250_lpss.c SYNOPSYS DESIGNWARE APB GPIO DRIVER M: Hoan Tran L: linux-gpio@vger.kernel.org S: Maintained -F: drivers/gpio/gpio-dwapb.c F: Documentation/devicetree/bindings/gpio/snps-dwapb-gpio.txt +F: drivers/gpio/gpio-dwapb.c SYNOPSYS DESIGNWARE AXI DMAC DRIVER M: Eugeniy Paltsev @@ -16552,8 +16550,8 @@ M: Michael Jamet M: Mika Westerberg M: Yehezkel Bernat L: linux-usb@vger.kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/westeri/thunderbolt.git S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/westeri/thunderbolt.git F: Documentation/admin-guide/thunderbolt.rst F: drivers/thunderbolt/ F: include/linux/thunderbolt.h @@ -17080,7 +17078,7 @@ S: Maintained F: Documentation/admin-guide/ufs.rst F: fs/ufs/ -UHID USERSPACE HID IO DRIVER: +UHID USERSPACE HID IO DRIVER M: David Herrmann L: linux-input@vger.kernel.org S: Maintained @@ -17094,18 +17092,18 @@ S: Maintained F: drivers/usb/common/ulpi.c F: include/linux/ulpi/ -ULTRA-WIDEBAND (UWB) SUBSYSTEM: +ULTRA-WIDEBAND (UWB) SUBSYSTEM L: devel@driverdev.osuosl.org S: Obsolete F: drivers/staging/uwb/ -UNICODE SUBSYSTEM: +UNICODE SUBSYSTEM M: Gabriel Krisman Bertazi L: linux-fsdevel@vger.kernel.org S: Supported F: fs/unicode/ -UNICORE32 ARCHITECTURE: +UNICORE32 ARCHITECTURE M: Guan Xuetao W: http://mprc.pku.edu.cn/~guanxuetao/linux S: Maintained @@ -17392,11 +17390,14 @@ F: drivers/usb/ F: include/linux/usb.h F: include/linux/usb/ -USB TYPEC PI3USB30532 MUX DRIVER -M: Hans de Goede +USB TYPEC BUS FOR ALTERNATE MODES +M: Heikki Krogerus L: linux-usb@vger.kernel.org S: Maintained -F: drivers/usb/typec/mux/pi3usb30532.c +F: Documentation/ABI/testing/sysfs-bus-typec +F: Documentation/driver-api/usb/typec_bus.rst +F: drivers/usb/typec/altmodes/ +F: include/linux/usb/typec_altmode.h USB TYPEC CLASS M: Heikki Krogerus @@ -17407,14 +17408,11 @@ F: Documentation/driver-api/usb/typec.rst F: drivers/usb/typec/ F: include/linux/usb/typec.h -USB TYPEC BUS FOR ALTERNATE MODES -M: Heikki Krogerus +USB TYPEC PI3USB30532 MUX DRIVER +M: Hans de Goede L: linux-usb@vger.kernel.org S: Maintained -F: Documentation/ABI/testing/sysfs-bus-typec -F: Documentation/driver-api/usb/typec_bus.rst -F: drivers/usb/typec/altmodes/ -F: include/linux/usb/typec_altmode.h +F: drivers/usb/typec/mux/pi3usb30532.c USB TYPEC PORT CONTROLLER DRIVERS M: Guenter Roeck @@ -17791,7 +17789,7 @@ F: include/linux/vbox_utils.h F: include/uapi/linux/vbox*.h F: drivers/virt/vboxguest/ -VIRTUAL BOX SHARED FOLDER VFS DRIVER: +VIRTUAL BOX SHARED FOLDER VFS DRIVER M: Hans de Goede L: linux-fsdevel@vger.kernel.org S: Maintained @@ -18414,8 +18412,8 @@ M: Nandor Han M: Semi Malinen L: linux-gpio@vger.kernel.org S: Maintained -F: drivers/gpio/gpio-xra1403.c F: Documentation/devicetree/bindings/gpio/gpio-xra1403.txt +F: drivers/gpio/gpio-xra1403.c XTENSA XTFPGA PLATFORM SUPPORT M: Max Filippov diff --git a/Makefile b/Makefile index 84b71845c43f328ca56e7cfa5d6880220068abc2..e56bf7ef182dea0cccb56352e243438b1dc99415 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 6 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc7 NAME = Kleptomaniac Octopus # *DOCUMENTATION* @@ -68,6 +68,7 @@ unexport GREP_OPTIONS # # If KBUILD_VERBOSE equals 0 then the above command will be hidden. # If KBUILD_VERBOSE equals 1 then the above command is displayed. +# If KBUILD_VERBOSE equals 2 then give the reason why each target is rebuilt. # # To put more focus on warnings, be less verbose as default # Use 'make V=1' to see the full commands @@ -1238,7 +1239,7 @@ ifneq ($(dtstree),) %.dtb: include/config/kernel.release scripts_dtc $(Q)$(MAKE) $(build)=$(dtstree) $(dtstree)/$@ -PHONY += dtbs dtbs_install dt_binding_check +PHONY += dtbs dtbs_install dtbs_check dtbs dtbs_check: include/config/kernel.release scripts_dtc $(Q)$(MAKE) $(build)=$(dtstree) @@ -1258,6 +1259,7 @@ PHONY += scripts_dtc scripts_dtc: scripts_basic $(Q)$(MAKE) $(build)=scripts/dtc +PHONY += dt_binding_check dt_binding_check: scripts_dtc $(Q)$(MAKE) $(build)=Documentation/devicetree/bindings @@ -1802,7 +1804,7 @@ existing-targets := $(wildcard $(sort $(targets))) -include $(foreach f,$(existing-targets),$(dir $(f)).$(notdir $(f)).cmd) -endif # config-targets +endif # config-build endif # mixed-build endif # need-sub-make diff --git a/arch/Kconfig b/arch/Kconfig index 98de654b79b312eca4737efff9b6b1460cb94f37..17fe351cdde08ab849b3b7f7763c4cdb307c61d2 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -738,8 +738,9 @@ config HAVE_STACK_VALIDATION config HAVE_RELIABLE_STACKTRACE bool help - Architecture has a save_stack_trace_tsk_reliable() function which - only returns a stack trace if it can guarantee the trace is reliable. + Architecture has either save_stack_trace_tsk_reliable() or + arch_stack_walk_reliable() function which only returns a stack trace + if it can guarantee the trace is reliable. config HAVE_ARCH_HASH bool diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index ff2a393b635c5681f5ce6c9edd1a1d20efd6ea10..7124ab82dfa31fb32f9701419fcd199e9f2569c2 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -154,7 +154,7 @@ config ARC_CPU_HS help Support for ARC HS38x Cores based on ARCv2 ISA The notable features are: - - SMP configurations of upto 4 core with coherency + - SMP configurations of up to 4 cores with coherency - Optional L2 Cache and IO-Coherency - Revised Interrupt Architecture (multiple priorites, reg banks, auto stack switch, auto regfile save/restore) @@ -192,7 +192,7 @@ config ARC_SMP_HALT_ON_RESET help In SMP configuration cores can be configured as Halt-on-reset or they could all start at same time. For Halt-on-reset, non - masters are parked until Master kicks them so they can start of + masters are parked until Master kicks them so they can start off at designated entry point. For other case, all jump to common entry point and spin wait for Master's signal. diff --git a/arch/arc/configs/nps_defconfig b/arch/arc/configs/nps_defconfig index 07f26ed39f024158466f2b5d6f4c0cb2cf115060..f7a978dfdf1d3668660aad6c29468fa7e97fe06c 100644 --- a/arch/arc/configs/nps_defconfig +++ b/arch/arc/configs/nps_defconfig @@ -21,8 +21,6 @@ CONFIG_MODULES=y CONFIG_MODULE_FORCE_LOAD=y CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARC_PLAT_EZNPS=y CONFIG_SMP=y CONFIG_NR_CPUS=4096 diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig index 5dd470b6609ebf2e061e1b48e98c86f5ef175056..bf39a0091679c766fa54f7670b4d351bf50dc6c8 100644 --- a/arch/arc/configs/nsimosci_defconfig +++ b/arch/arc/configs/nsimosci_defconfig @@ -20,8 +20,6 @@ CONFIG_ISA_ARCOMPACT=y CONFIG_KPROBES=y CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARC_BUILTIN_DTB_NAME="nsimosci" # CONFIG_COMPACTION is not set CONFIG_NET=y diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig index 3532e86f7bff690b4906d8c7f9ea8e9d6a5db117..7121bd71c543ad3232e2ca97eb01a7ddda1e9921 100644 --- a/arch/arc/configs/nsimosci_hs_defconfig +++ b/arch/arc/configs/nsimosci_hs_defconfig @@ -19,8 +19,6 @@ CONFIG_PERF_EVENTS=y CONFIG_KPROBES=y CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ISA_ARCV2=y CONFIG_ARC_BUILTIN_DTB_NAME="nsimosci_hs" # CONFIG_COMPACTION is not set diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig index d90448bee064f3604631966dcd0e67253a44226f..f9863b294a707ef569bf36aa08592bf8ca48b5f2 100644 --- a/arch/arc/configs/nsimosci_hs_smp_defconfig +++ b/arch/arc/configs/nsimosci_hs_smp_defconfig @@ -14,8 +14,6 @@ CONFIG_PERF_EVENTS=y CONFIG_KPROBES=y CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ISA_ARCV2=y CONFIG_SMP=y # CONFIG_ARC_TIMERS_64BIT is not set diff --git a/arch/arc/include/asm/fpu.h b/arch/arc/include/asm/fpu.h index 64347250fdf55e58453e90982e90182ee68b1fc4..006bcf88a7a5f21284ddb2fb015d4a75924b4490 100644 --- a/arch/arc/include/asm/fpu.h +++ b/arch/arc/include/asm/fpu.h @@ -43,6 +43,8 @@ extern void fpu_init_task(struct pt_regs *regs); #endif /* !CONFIG_ISA_ARCOMPACT */ +struct task_struct; + extern void fpu_save_restore(struct task_struct *p, struct task_struct *n); #else /* !CONFIG_ARC_FPU_SAVE_RESTORE */ diff --git a/arch/arc/include/asm/linkage.h b/arch/arc/include/asm/linkage.h index d9ee43c6b7dbc2c698960365e8bbe78d0f087ddb..fe19f1d412e71896b324e28278fc52cae13e1a38 100644 --- a/arch/arc/include/asm/linkage.h +++ b/arch/arc/include/asm/linkage.h @@ -29,6 +29,8 @@ .endm #define ASM_NL ` /* use '`' to mark new line in macro */ +#define __ALIGN .align 4 +#define __ALIGN_STR __stringify(__ALIGN) /* annotation for data we want in DCCM - if enabled in .config */ .macro ARCFP_DATA nm diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index e1c647490f00e91069671f5aeb9871830cb9be83..aa41af6ef4ac6eccca426d72810c726423391de8 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -8,11 +8,11 @@ #include #include #include -#include #include #include #include #include +#include #include #include #include diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c index b79886a6cec8a72398720fa839df2e2917aa523e..d2999503fb8a5f1095419a673bd317f4e4690c6c 100644 --- a/arch/arc/kernel/troubleshoot.c +++ b/arch/arc/kernel/troubleshoot.c @@ -104,8 +104,7 @@ static void show_faulting_vma(unsigned long address) if (IS_ERR(nm)) nm = "?"; } - pr_info(" @off 0x%lx in [%s]\n" - " VMA: 0x%08lx to 0x%08lx\n", + pr_info(" @off 0x%lx in [%s] VMA: 0x%08lx to 0x%08lx\n", vma->vm_start < TASK_UNMAPPED_BASE ? address : address - vma->vm_start, nm, vma->vm_start, vma->vm_end); @@ -120,8 +119,6 @@ static void show_ecr_verbose(struct pt_regs *regs) unsigned int vec, cause_code; unsigned long address; - pr_info("\n[ECR ]: 0x%08lx => ", regs->event); - /* For Data fault, this is data address not instruction addr */ address = current->thread.fault_address; @@ -130,10 +127,10 @@ static void show_ecr_verbose(struct pt_regs *regs) /* For DTLB Miss or ProtV, display the memory involved too */ if (vec == ECR_V_DTLB_MISS) { - pr_cont("Invalid %s @ 0x%08lx by insn @ 0x%08lx\n", + pr_cont("Invalid %s @ 0x%08lx by insn @ %pS\n", (cause_code == 0x01) ? "Read" : ((cause_code == 0x02) ? "Write" : "EX"), - address, regs->ret); + address, (void *)regs->ret); } else if (vec == ECR_V_ITLB_MISS) { pr_cont("Insn could not be fetched\n"); } else if (vec == ECR_V_MACH_CHK) { @@ -191,31 +188,31 @@ void show_regs(struct pt_regs *regs) show_ecr_verbose(regs); - pr_info("[EFA ]: 0x%08lx\n[BLINK ]: %pS\n[ERET ]: %pS\n", - current->thread.fault_address, - (void *)regs->blink, (void *)regs->ret); - if (user_mode(regs)) show_faulting_vma(regs->ret); /* faulting code, not data */ - pr_info("[STAT32]: 0x%08lx", regs->status32); + pr_info("ECR: 0x%08lx EFA: 0x%08lx ERET: 0x%08lx\n", + regs->event, current->thread.fault_address, regs->ret); + + pr_info("STAT32: 0x%08lx", regs->status32); #define STS_BIT(r, bit) r->status32 & STATUS_##bit##_MASK ? #bit" " : "" #ifdef CONFIG_ISA_ARCOMPACT - pr_cont(" : %2s%2s%2s%2s%2s%2s%2s\n", + pr_cont(" [%2s%2s%2s%2s%2s%2s%2s]", (regs->status32 & STATUS_U_MASK) ? "U " : "K ", STS_BIT(regs, DE), STS_BIT(regs, AE), STS_BIT(regs, A2), STS_BIT(regs, A1), STS_BIT(regs, E2), STS_BIT(regs, E1)); #else - pr_cont(" : %2s%2s%2s%2s\n", + pr_cont(" [%2s%2s%2s%2s]", STS_BIT(regs, IE), (regs->status32 & STATUS_U_MASK) ? "U " : "K ", STS_BIT(regs, DE), STS_BIT(regs, AE)); #endif - pr_info("BTA: 0x%08lx\t SP: 0x%08lx\t FP: 0x%08lx\n", - regs->bta, regs->sp, regs->fp); + pr_cont(" BTA: 0x%08lx\n", regs->bta); + pr_info("BLK: %pS\n SP: 0x%08lx FP: 0x%08lx\n", + (void *)regs->blink, regs->sp, regs->fp); pr_info("LPS: 0x%08lx\tLPE: 0x%08lx\tLPC: 0x%08lx\n", regs->lp_start, regs->lp_end, regs->lp_count); diff --git a/arch/arm/Makefile b/arch/arm/Makefile index db857d07114f18240ac7d2deec2710f7b838cf1a..1fc32b611f8a4de487695fe42f86847f53d898e1 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -307,13 +307,15 @@ endif ifeq ($(CONFIG_STACKPROTECTOR_PER_TASK),y) prepare: stack_protector_prepare stack_protector_prepare: prepare0 - $(eval KBUILD_CFLAGS += \ + $(eval SSP_PLUGIN_CFLAGS := \ -fplugin-arg-arm_ssp_per_task_plugin-tso=$(shell \ awk '{if ($$2 == "THREAD_SZ_ORDER") print $$3;}'\ include/generated/asm-offsets.h) \ -fplugin-arg-arm_ssp_per_task_plugin-offset=$(shell \ awk '{if ($$2 == "TI_STACK_CANARY") print $$3;}'\ include/generated/asm-offsets.h)) + $(eval KBUILD_CFLAGS += $(SSP_PLUGIN_CFLAGS)) + $(eval GCC_PLUGINS_CFLAGS += $(SSP_PLUGIN_CFLAGS)) endif all: $(notdir $(KBUILD_IMAGE)) diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile index da599c3a1193433207b6e2b2bdd44a6bb8a76647..9c11e7490292f0e0031b2dfb4f7e0386b3bcee38 100644 --- a/arch/arm/boot/compressed/Makefile +++ b/arch/arm/boot/compressed/Makefile @@ -101,7 +101,6 @@ clean-files += piggy_data lib1funcs.S ashldi3.S bswapsdi2.S \ $(libfdt) $(libfdt_hdrs) hyp-stub.S KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING -KBUILD_CFLAGS += $(DISABLE_ARM_SSP_PER_TASK_PLUGIN) ifeq ($(CONFIG_FUNCTION_TRACER),y) ORIG_CFLAGS := $(KBUILD_CFLAGS) @@ -117,7 +116,8 @@ CFLAGS_fdt_ro.o := $(nossp-flags-y) CFLAGS_fdt_rw.o := $(nossp-flags-y) CFLAGS_fdt_wip.o := $(nossp-flags-y) -ccflags-y := -fpic $(call cc-option,-mno-single-pic-base,) -fno-builtin -I$(obj) +ccflags-y := -fpic $(call cc-option,-mno-single-pic-base,) -fno-builtin \ + -I$(obj) $(DISABLE_ARM_SSP_PER_TASK_PLUGIN) asflags-y := -DZIMAGE # Supply kernel BSS size to the decompressor via a linker symbol. diff --git a/arch/arm/boot/dts/am437x-idk-evm.dts b/arch/arm/boot/dts/am437x-idk-evm.dts index f3ced6df0c9b272461f394b090905dd7ee4af6da..9f66f96d09c91661a0917e4abcdf701086059ba4 100644 --- a/arch/arm/boot/dts/am437x-idk-evm.dts +++ b/arch/arm/boot/dts/am437x-idk-evm.dts @@ -526,11 +526,11 @@ &cpu0_opp_table { * Supply voltage supervisor on board will not allow opp50 so * disable it and set opp100 as suspend OPP. */ - opp50@300000000 { + opp50-300000000 { status = "disabled"; }; - opp100@600000000 { + opp100-600000000 { opp-suspend; }; }; diff --git a/arch/arm/boot/dts/bcm2711-rpi-4-b.dts b/arch/arm/boot/dts/bcm2711-rpi-4-b.dts index 1b5a835f66bd3de475e8229cc2302576f3c57b45..efea891b1a76ea0a32fd74950bd1fa179a73acfe 100644 --- a/arch/arm/boot/dts/bcm2711-rpi-4-b.dts +++ b/arch/arm/boot/dts/bcm2711-rpi-4-b.dts @@ -21,6 +21,7 @@ memory@0 { aliases { ethernet0 = &genet; + pcie0 = &pcie0; }; leds { @@ -31,6 +32,8 @@ act { pwr { label = "PWR"; gpios = <&expgpio 2 GPIO_ACTIVE_LOW>; + default-state = "keep"; + linux,default-trigger = "default-on"; }; }; diff --git a/arch/arm/boot/dts/bcm2837-rpi-3-a-plus.dts b/arch/arm/boot/dts/bcm2837-rpi-3-a-plus.dts index 66ab35eccba7bbc0f753ac99ce0763a8b1f5af9c..28be0332c1c810e6fe727802ce7af4458f70029f 100644 --- a/arch/arm/boot/dts/bcm2837-rpi-3-a-plus.dts +++ b/arch/arm/boot/dts/bcm2837-rpi-3-a-plus.dts @@ -26,6 +26,8 @@ act { pwr { label = "PWR"; gpios = <&expgpio 2 GPIO_ACTIVE_LOW>; + default-state = "keep"; + linux,default-trigger = "default-on"; }; }; }; diff --git a/arch/arm/boot/dts/bcm2837-rpi-3-b-plus.dts b/arch/arm/boot/dts/bcm2837-rpi-3-b-plus.dts index 74ed6d04780703d8c3197c39716baecad5cafcb5..37343148643dbfafb9d89d7eb091b401fafb4aa0 100644 --- a/arch/arm/boot/dts/bcm2837-rpi-3-b-plus.dts +++ b/arch/arm/boot/dts/bcm2837-rpi-3-b-plus.dts @@ -27,6 +27,8 @@ act { pwr { label = "PWR"; gpios = <&expgpio 2 GPIO_ACTIVE_LOW>; + default-state = "keep"; + linux,default-trigger = "default-on"; }; }; diff --git a/arch/arm/boot/dts/dra7-evm.dts b/arch/arm/boot/dts/dra7-evm.dts index de7f85efaa5120a765abf05eb34780b8000994d2..af06a55d1c5c6374eae5f41c874c2b40872b75ef 100644 --- a/arch/arm/boot/dts/dra7-evm.dts +++ b/arch/arm/boot/dts/dra7-evm.dts @@ -61,10 +61,10 @@ aic_dvdd: fixedregulator-aic_dvdd { regulator-max-microvolt = <1800000>; }; - evm_3v3: fixedregulator-evm3v3 { + vsys_3v3: fixedregulator-vsys3v3 { /* Output of Cntlr A of TPS43351-Q1 on dra7-evm */ compatible = "regulator-fixed"; - regulator-name = "evm_3v3"; + regulator-name = "vsys_3v3"; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; vin-supply = <&evm_12v0>; diff --git a/arch/arm/boot/dts/dra7-l4.dtsi b/arch/arm/boot/dts/dra7-l4.dtsi index fc418834890d4c9d5d323b8acf6e76d0170e41de..2119a78e9c153605acc99eb83de65940257a76ef 100644 --- a/arch/arm/boot/dts/dra7-l4.dtsi +++ b/arch/arm/boot/dts/dra7-l4.dtsi @@ -3474,6 +3474,7 @@ timer13: timer@0 { clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER13_CLKCTRL 24>; clock-names = "fck"; interrupts = ; + ti,timer-pwm; }; }; @@ -3501,6 +3502,7 @@ timer14: timer@0 { clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER14_CLKCTRL 24>; clock-names = "fck"; interrupts = ; + ti,timer-pwm; }; }; @@ -3528,6 +3530,7 @@ timer15: timer@0 { clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER15_CLKCTRL 24>; clock-names = "fck"; interrupts = ; + ti,timer-pwm; }; }; @@ -3555,6 +3558,7 @@ timer16: timer@0 { clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER16_CLKCTRL 24>; clock-names = "fck"; interrupts = ; + ti,timer-pwm; }; }; diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index d78b684e7fca0330d760502d9f45168bb1996b5e..4305051bb76965ed6048bb30e5b91ee74f41c72a 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -184,6 +184,7 @@ pcie1_rc: pcie@51000000 { device_type = "pci"; ranges = <0x81000000 0 0 0x03000 0 0x00010000 0x82000000 0 0x20013000 0x13000 0 0xffed000>; + dma-ranges = <0x02000000 0x0 0x00000000 0x00000000 0x1 0x00000000>; bus-range = <0x00 0xff>; #interrupt-cells = <1>; num-lanes = <1>; @@ -238,6 +239,7 @@ pcie2_rc: pcie@51800000 { device_type = "pci"; ranges = <0x81000000 0 0 0x03000 0 0x00010000 0x82000000 0 0x30013000 0x13000 0 0xffed000>; + dma-ranges = <0x02000000 0x0 0x00000000 0x00000000 0x1 0x00000000>; bus-range = <0x00 0xff>; #interrupt-cells = <1>; num-lanes = <1>; diff --git a/arch/arm/boot/dts/dra76x.dtsi b/arch/arm/boot/dts/dra76x.dtsi index 2f7539afef2be823a3fb732b31d19b86d12e9e13..42b8a205b64f8abac147f8da63716ce1fb1026a9 100644 --- a/arch/arm/boot/dts/dra76x.dtsi +++ b/arch/arm/boot/dts/dra76x.dtsi @@ -128,3 +128,8 @@ &rtctarget { &usb4_tm { status = "disabled"; }; + +&mmc3 { + /* dra76x is not affected by i887 */ + max-frequency = <96000000>; +}; diff --git a/arch/arm/boot/dts/dra7xx-clocks.dtsi b/arch/arm/boot/dts/dra7xx-clocks.dtsi index 55cef4cac5f16f5c858b8c04d7c4c4895d1d6fef..dc0a93bccbf1e2aa5413e2ef6f14ab0b609eb421 100644 --- a/arch/arm/boot/dts/dra7xx-clocks.dtsi +++ b/arch/arm/boot/dts/dra7xx-clocks.dtsi @@ -796,16 +796,6 @@ video2_div_clk: video2_div_clk { clock-div = <1>; }; - ipu1_gfclk_mux: ipu1_gfclk_mux@520 { - #clock-cells = <0>; - compatible = "ti,mux-clock"; - clocks = <&dpll_abe_m2x2_ck>, <&dpll_core_h22x2_ck>; - ti,bit-shift = <24>; - reg = <0x0520>; - assigned-clocks = <&ipu1_gfclk_mux>; - assigned-clock-parents = <&dpll_core_h22x2_ck>; - }; - dummy_ck: dummy_ck { #clock-cells = <0>; compatible = "fixed-clock"; @@ -1564,6 +1554,8 @@ ipu1_clkctrl: ipu1-clkctrl@20 { compatible = "ti,clkctrl"; reg = <0x20 0x4>; #clock-cells = <2>; + assigned-clocks = <&ipu1_clkctrl DRA7_IPU1_MMU_IPU1_CLKCTRL 24>; + assigned-clock-parents = <&dpll_core_h22x2_ck>; }; ipu_clkctrl: ipu-clkctrl@50 { diff --git a/arch/arm/boot/dts/imx6dl-colibri-eval-v3.dts b/arch/arm/boot/dts/imx6dl-colibri-eval-v3.dts index cd075621de52dfa73b925ed9a35d1f828a9cda8e..84fcc203a2e48179c4ff27395a0a5e15746aaddb 100644 --- a/arch/arm/boot/dts/imx6dl-colibri-eval-v3.dts +++ b/arch/arm/boot/dts/imx6dl-colibri-eval-v3.dts @@ -275,7 +275,7 @@ &weim { /* SRAM on Colibri nEXT_CS0 */ sram@0,0 { - compatible = "cypress,cy7c1019dv33-10zsxi, mtd-ram"; + compatible = "cypress,cy7c1019dv33-10zsxi", "mtd-ram"; reg = <0 0 0x00010000>; #address-cells = <1>; #size-cells = <1>; @@ -286,7 +286,7 @@ sram@0,0 { /* SRAM on Colibri nEXT_CS1 */ sram@1,0 { - compatible = "cypress,cy7c1019dv33-10zsxi, mtd-ram"; + compatible = "cypress,cy7c1019dv33-10zsxi", "mtd-ram"; reg = <1 0 0x00010000>; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/imx6qdl-phytec-phycore-som.dtsi b/arch/arm/boot/dts/imx6qdl-phytec-phycore-som.dtsi index 978dc1c2ff1b8b3c9b0dd76a99ed911f8994790c..4d18952658f841f3503f722038549a9f2aee99b6 100644 --- a/arch/arm/boot/dts/imx6qdl-phytec-phycore-som.dtsi +++ b/arch/arm/boot/dts/imx6qdl-phytec-phycore-som.dtsi @@ -192,7 +192,6 @@ &usdhc4 { pinctrl-0 = <&pinctrl_usdhc4>; bus-width = <8>; non-removable; - vmmc-supply = <&vdd_emmc_1p8>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/imx7-colibri.dtsi b/arch/arm/boot/dts/imx7-colibri.dtsi index d05be3f0e2a722f4165b6d2450e1fcf397e7ef02..04717cf69db07cd4049e52aefce6ef3542df3f3c 100644 --- a/arch/arm/boot/dts/imx7-colibri.dtsi +++ b/arch/arm/boot/dts/imx7-colibri.dtsi @@ -336,7 +336,6 @@ &usdhc3 { assigned-clock-rates = <400000000>; bus-width = <8>; fsl,tuning-step = <2>; - max-frequency = <100000000>; vmmc-supply = <®_module_3v3>; vqmmc-supply = <®_DCDC3>; non-removable; diff --git a/arch/arm/boot/dts/imx7d.dtsi b/arch/arm/boot/dts/imx7d.dtsi index 92f6d0c2a74f6544912f211f055c6083748b8138..4c22828df55f31522b2708e7aa353312857215ab 100644 --- a/arch/arm/boot/dts/imx7d.dtsi +++ b/arch/arm/boot/dts/imx7d.dtsi @@ -44,7 +44,7 @@ opp-792000000 { opp-hz = /bits/ 64 <792000000>; opp-microvolt = <1000000>; clock-latency-ns = <150000>; - opp-supported-hw = <0xd>, <0xf>; + opp-supported-hw = <0xd>, <0x7>; opp-suspend; }; @@ -52,7 +52,7 @@ opp-996000000 { opp-hz = /bits/ 64 <996000000>; opp-microvolt = <1100000>; clock-latency-ns = <150000>; - opp-supported-hw = <0xc>, <0xf>; + opp-supported-hw = <0xc>, <0x7>; opp-suspend; }; @@ -60,7 +60,7 @@ opp-1200000000 { opp-hz = /bits/ 64 <1200000000>; opp-microvolt = <1225000>; clock-latency-ns = <150000>; - opp-supported-hw = <0x8>, <0xf>; + opp-supported-hw = <0x8>, <0x3>; opp-suspend; }; }; diff --git a/arch/arm/boot/dts/ls1021a.dtsi b/arch/arm/boot/dts/ls1021a.dtsi index 0855b1fe98e0d2ffc04ac48b940c6c6ef1f868d1..760a68c163c834213e396c55620152ce97967dd2 100644 --- a/arch/arm/boot/dts/ls1021a.dtsi +++ b/arch/arm/boot/dts/ls1021a.dtsi @@ -747,7 +747,7 @@ dcu: dcu@2ce0000 { }; mdio0: mdio@2d24000 { - compatible = "fsl,etsec2-mdio"; + compatible = "gianfar"; device_type = "mdio"; #address-cells = <1>; #size-cells = <0>; @@ -756,7 +756,7 @@ mdio0: mdio@2d24000 { }; mdio1: mdio@2d64000 { - compatible = "fsl,etsec2-mdio"; + compatible = "gianfar"; device_type = "mdio"; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/motorola-mapphone-common.dtsi b/arch/arm/boot/dts/motorola-mapphone-common.dtsi index 85665506f4f80142162342c49b7c6a1e6aa27eee..b6e82b165f5c5a6c5b4e719ca03fd98c6f931958 100644 --- a/arch/arm/boot/dts/motorola-mapphone-common.dtsi +++ b/arch/arm/boot/dts/motorola-mapphone-common.dtsi @@ -182,6 +182,14 @@ vibrator { pwm-names = "enable", "direction"; direction-duty-cycle-ns = <10000000>; }; + + backlight: backlight { + compatible = "led-backlight"; + + leds = <&backlight_led>; + brightness-levels = <31 63 95 127 159 191 223 255>; + default-brightness-level = <6>; + }; }; &dss { @@ -205,6 +213,8 @@ lcd0: display { vddi-supply = <&lcd_regulator>; reset-gpios = <&gpio4 5 GPIO_ACTIVE_HIGH>; /* gpio101 */ + backlight = <&backlight>; + width-mm = <50>; height-mm = <89>; @@ -393,12 +403,11 @@ led-controller@38 { ramp-up-us = <1024>; ramp-down-us = <8193>; - led@0 { + backlight_led: led@0 { reg = <0>; led-sources = <2>; ti,led-mode = <0>; label = ":backlight"; - linux,default-trigger = "backlight"; }; led@1 { diff --git a/arch/arm/boot/dts/r8a7779.dtsi b/arch/arm/boot/dts/r8a7779.dtsi index beb9885e6ffca7a521ffb670f44ddd8be639a287..c0999e27e9b145e31ae341af3709fbd6d1a7a933 100644 --- a/arch/arm/boot/dts/r8a7779.dtsi +++ b/arch/arm/boot/dts/r8a7779.dtsi @@ -377,7 +377,7 @@ tmu2: timer@ffd82000 { }; sata: sata@fc600000 { - compatible = "renesas,sata-r8a7779", "renesas,rcar-sata"; + compatible = "renesas,sata-r8a7779"; reg = <0xfc600000 0x200000>; interrupts = ; clocks = <&mstp1_clks R8A7779_CLK_SATA>; diff --git a/arch/arm/boot/dts/stih410-b2260.dts b/arch/arm/boot/dts/stih410-b2260.dts index 4fbd8e9eb5b76d102dce79c44666130f1f7c9431..e2bb5978314620452c5ad2fd80cf1786bf1b5543 100644 --- a/arch/arm/boot/dts/stih410-b2260.dts +++ b/arch/arm/boot/dts/stih410-b2260.dts @@ -178,9 +178,6 @@ ethernet0: dwmac@9630000 { phy-mode = "rgmii"; pinctrl-0 = <&pinctrl_rgmii1 &pinctrl_rgmii1_mdio_1>; - snps,phy-bus-name = "stmmac"; - snps,phy-bus-id = <0>; - snps,phy-addr = <0>; snps,reset-gpio = <&pio0 7 0>; snps,reset-active-low; snps,reset-delays-us = <0 10000 1000000>; diff --git a/arch/arm/boot/dts/stihxxx-b2120.dtsi b/arch/arm/boot/dts/stihxxx-b2120.dtsi index 60e11045ad762af74e47a70335abac94b162b403..d051f080e52ec36a55f62e0d6f642a08ec21b6d9 100644 --- a/arch/arm/boot/dts/stihxxx-b2120.dtsi +++ b/arch/arm/boot/dts/stihxxx-b2120.dtsi @@ -46,7 +46,7 @@ simple-audio-card,dai-link@1 { /* DAC */ format = "i2s"; mclk-fs = <256>; - frame-inversion = <1>; + frame-inversion; cpu { sound-dai = <&sti_uni_player2>; }; diff --git a/arch/arm/configs/am200epdkit_defconfig b/arch/arm/configs/am200epdkit_defconfig index 622436f44783461ebd145d2879d2b5a45ffeb343..f56ac394caf10b4d6218ea24ae895d9b1795be10 100644 --- a/arch/arm/configs/am200epdkit_defconfig +++ b/arch/arm/configs/am200epdkit_defconfig @@ -11,8 +11,6 @@ CONFIG_SLAB=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_PXA=y CONFIG_ARCH_GUMSTIX=y CONFIG_PCCARD=y diff --git a/arch/arm/configs/axm55xx_defconfig b/arch/arm/configs/axm55xx_defconfig index f53634af014ba5407fafe49c0b9269f8af341be7..6ea7dafa4c9ea561826d2cd391d05ae823e451ee 100644 --- a/arch/arm/configs/axm55xx_defconfig +++ b/arch/arm/configs/axm55xx_defconfig @@ -25,7 +25,6 @@ CONFIG_EMBEDDED=y CONFIG_PROFILING=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y -# CONFIG_IOSCHED_DEADLINE is not set CONFIG_ARCH_AXXIA=y CONFIG_GPIO_PCA953X=y CONFIG_ARM_LPAE=y diff --git a/arch/arm/configs/bcm2835_defconfig b/arch/arm/configs/bcm2835_defconfig index 519ff58e67b3057b4b506f8e0a5b9c964a527eb8..0afcae9f7cf8a0411e53ebd658d9a0efd93b9c49 100644 --- a/arch/arm/configs/bcm2835_defconfig +++ b/arch/arm/configs/bcm2835_defconfig @@ -178,6 +178,7 @@ CONFIG_SCHED_TRACER=y CONFIG_STACK_TRACER=y CONFIG_FUNCTION_PROFILER=y CONFIG_TEST_KSTRTOX=y +CONFIG_DEBUG_FS=y CONFIG_KGDB=y CONFIG_KGDB_KDB=y CONFIG_STRICT_DEVMEM=y diff --git a/arch/arm/configs/clps711x_defconfig b/arch/arm/configs/clps711x_defconfig index c255dab36bdec8d31747751fcf24850d4be2ff46..63a153f5cf683efe1b80e38d904284585a1b67ac 100644 --- a/arch/arm/configs/clps711x_defconfig +++ b/arch/arm/configs/clps711x_defconfig @@ -7,7 +7,6 @@ CONFIG_EMBEDDED=y CONFIG_SLOB=y CONFIG_JUMP_LABEL=y CONFIG_PARTITION_ADVANCED=y -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_CLPS711X=y CONFIG_ARCH_AUTCPU12=y CONFIG_ARCH_CDB89712=y diff --git a/arch/arm/configs/cns3420vb_defconfig b/arch/arm/configs/cns3420vb_defconfig index 89df0a55a0655924a5b099906c6a67d1b3eee1b8..66a80b46038d1e318920ea3fae213dd6c2bdbb13 100644 --- a/arch/arm/configs/cns3420vb_defconfig +++ b/arch/arm/configs/cns3420vb_defconfig @@ -17,7 +17,7 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y # CONFIG_BLK_DEV_BSG is not set -CONFIG_IOSCHED_CFQ=m +CONFIG_IOSCHED_BFQ=m CONFIG_ARCH_MULTI_V6=y #CONFIG_ARCH_MULTI_V7 is not set CONFIG_ARCH_CNS3XXX=y diff --git a/arch/arm/configs/colibri_pxa300_defconfig b/arch/arm/configs/colibri_pxa300_defconfig index 446134c70a335759ef5399c845f6b4621273f0bf..0dae3b18528400905deb609fa67acedd9f7f6729 100644 --- a/arch/arm/configs/colibri_pxa300_defconfig +++ b/arch/arm/configs/colibri_pxa300_defconfig @@ -43,7 +43,6 @@ CONFIG_USB_ANNOUNCE_NEW_DEVICES=y CONFIG_USB_MON=y CONFIG_USB_STORAGE=y CONFIG_MMC=y -# CONFIG_MMC_BLOCK_BOUNCE is not set CONFIG_MMC_PXA=y CONFIG_EXT3_FS=y CONFIG_NFS_FS=y diff --git a/arch/arm/configs/collie_defconfig b/arch/arm/configs/collie_defconfig index e6df11e906bade8bf8335d035bc74d66231c5a35..36384fd575f8ed8b7a71cd49e0d4e0ddbb1ef03a 100644 --- a/arch/arm/configs/collie_defconfig +++ b/arch/arm/configs/collie_defconfig @@ -7,8 +7,6 @@ CONFIG_EXPERT=y # CONFIG_BASE_FULL is not set # CONFIG_EPOLL is not set CONFIG_SLOB=y -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_SA1100=y CONFIG_SA1100_COLLIE=y CONFIG_PCCARD=y diff --git a/arch/arm/configs/davinci_all_defconfig b/arch/arm/configs/davinci_all_defconfig index 231f8973bbb2d8ca242eef675b2c4fbed6ba554b..b5ba8d731a25e82964267cb43d159ec314a15f59 100644 --- a/arch/arm/configs/davinci_all_defconfig +++ b/arch/arm/configs/davinci_all_defconfig @@ -15,8 +15,6 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y CONFIG_PARTITION_ADVANCED=y -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_MULTIPLATFORM=y CONFIG_ARCH_MULTI_V7=n CONFIG_ARCH_MULTI_V5=y diff --git a/arch/arm/configs/efm32_defconfig b/arch/arm/configs/efm32_defconfig index 10ea92513a69d07843ea38a598c0bb6409fcd97e..46213f0530c4af6138b5c8905c5af6d513766dfc 100644 --- a/arch/arm/configs/efm32_defconfig +++ b/arch/arm/configs/efm32_defconfig @@ -12,8 +12,6 @@ CONFIG_EMBEDDED=y # CONFIG_VM_EVENT_COUNTERS is not set # CONFIG_SLUB_DEBUG is not set # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set # CONFIG_MMU is not set CONFIG_ARM_SINGLE_ARMV7M=y CONFIG_ARCH_EFM32=y diff --git a/arch/arm/configs/ep93xx_defconfig b/arch/arm/configs/ep93xx_defconfig index ef2d2a820c30b20a76285d9301666542656fb71d..cd16fb6eb8e63e7c1c85eba78919db25f4dbf702 100644 --- a/arch/arm/configs/ep93xx_defconfig +++ b/arch/arm/configs/ep93xx_defconfig @@ -11,7 +11,6 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set CONFIG_PARTITION_ADVANCED=y -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_EP93XX=y CONFIG_CRUNCH=y CONFIG_MACH_ADSSPHERE=y diff --git a/arch/arm/configs/eseries_pxa_defconfig b/arch/arm/configs/eseries_pxa_defconfig index 56452fa03d56782329cd4d7fb257b643b9cf3279..046f4dc2e18e34de0de2dcdeb2b53fd2b68e8474 100644 --- a/arch/arm/configs/eseries_pxa_defconfig +++ b/arch/arm/configs/eseries_pxa_defconfig @@ -9,8 +9,6 @@ CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_PXA=y CONFIG_ARCH_PXA_ESERIES=y # CONFIG_ARM_THUMB is not set diff --git a/arch/arm/configs/ezx_defconfig b/arch/arm/configs/ezx_defconfig index 4e28771beecdb7d53aaf74953b03202ed955b503..bd7b7f945e0188734ca54e156fcf848bf1295933 100644 --- a/arch/arm/configs/ezx_defconfig +++ b/arch/arm/configs/ezx_defconfig @@ -14,7 +14,6 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_PXA=y CONFIG_PXA_EZX=y CONFIG_NO_HZ=y diff --git a/arch/arm/configs/h3600_defconfig b/arch/arm/configs/h3600_defconfig index 4d91e41cb628bf0982f9245bdba2a74dff1b053a..c02b3e4096101a4096da59fbb575e428ac7db656 100644 --- a/arch/arm/configs/h3600_defconfig +++ b/arch/arm/configs/h3600_defconfig @@ -5,8 +5,6 @@ CONFIG_LOG_BUF_SHIFT=14 CONFIG_BLK_DEV_INITRD=y CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_SA1100=y CONFIG_SA1100_H3600=y CONFIG_PCCARD=y diff --git a/arch/arm/configs/h5000_defconfig b/arch/arm/configs/h5000_defconfig index 3946c608732724b01d79d2dd97a41e5fbb8b27df..f5a338fefda8ed34842f9ba3245ded25b2539ea8 100644 --- a/arch/arm/configs/h5000_defconfig +++ b/arch/arm/configs/h5000_defconfig @@ -10,7 +10,6 @@ CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_PXA=y CONFIG_MACH_H5000=y CONFIG_AEABI=y diff --git a/arch/arm/configs/imote2_defconfig b/arch/arm/configs/imote2_defconfig index 770469f61c3e44bc92de074577ba20e3521c4be8..05c5515fa8710fd428ab8e8384e517472c7b6b47 100644 --- a/arch/arm/configs/imote2_defconfig +++ b/arch/arm/configs/imote2_defconfig @@ -13,7 +13,6 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_PXA=y CONFIG_MACH_INTELMOTE2=y CONFIG_NO_HZ=y diff --git a/arch/arm/configs/imx_v4_v5_defconfig b/arch/arm/configs/imx_v4_v5_defconfig index 2b2d617e279d4232793e2bf0bb235813ba0e6061..3df90fc383983d2b9e902690d2b3285e8a8308f7 100644 --- a/arch/arm/configs/imx_v4_v5_defconfig +++ b/arch/arm/configs/imx_v4_v5_defconfig @@ -32,8 +32,6 @@ CONFIG_KPROBES=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y diff --git a/arch/arm/configs/lpc18xx_defconfig b/arch/arm/configs/lpc18xx_defconfig index e518168a06276363988558da66884a5440d3a613..be882ea0eee4662ecb631648edb2466e06de3dfc 100644 --- a/arch/arm/configs/lpc18xx_defconfig +++ b/arch/arm/configs/lpc18xx_defconfig @@ -1,4 +1,3 @@ -CONFIG_CROSS_COMPILE="arm-linux-gnueabihf-" CONFIG_HIGH_RES_TIMERS=y CONFIG_PREEMPT=y CONFIG_BLK_DEV_INITRD=y @@ -28,10 +27,7 @@ CONFIG_FLASH_SIZE=0x00080000 CONFIG_ZBOOT_ROM_TEXT=0x0 CONFIG_ZBOOT_ROM_BSS=0x0 CONFIG_ARM_APPENDED_DTB=y -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_BINFMT_FLAT=y CONFIG_BINFMT_ZFLAT=y CONFIG_BINFMT_SHARED_FLAT=y diff --git a/arch/arm/configs/magician_defconfig b/arch/arm/configs/magician_defconfig index e6486c95922065e353889585e69fc6d16595899c..d2e684f6565a161f2b277eaab76de7484a67de78 100644 --- a/arch/arm/configs/magician_defconfig +++ b/arch/arm/configs/magician_defconfig @@ -9,8 +9,6 @@ CONFIG_SLAB=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_PXA=y CONFIG_MACH_H4700=y CONFIG_MACH_MAGICIAN=y diff --git a/arch/arm/configs/moxart_defconfig b/arch/arm/configs/moxart_defconfig index 45d27190c9c96e56009dd1116bd7bc4cedf6a946..6834e97af34861b4df3ab8c12dd7ace7b0d4efc2 100644 --- a/arch/arm/configs/moxart_defconfig +++ b/arch/arm/configs/moxart_defconfig @@ -15,7 +15,6 @@ CONFIG_EMBEDDED=y # CONFIG_SLUB_DEBUG is not set # CONFIG_COMPAT_BRK is not set # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set CONFIG_ARCH_MULTI_V4=y # CONFIG_ARCH_MULTI_V7 is not set CONFIG_ARCH_MOXART=y diff --git a/arch/arm/configs/mxs_defconfig b/arch/arm/configs/mxs_defconfig index 2773899c21b384ff4e0672c942a61cee90840350..a9c6f32a9b1c9d04ddca4ea9d7690aadcb143a40 100644 --- a/arch/arm/configs/mxs_defconfig +++ b/arch/arm/configs/mxs_defconfig @@ -25,8 +25,6 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y CONFIG_BLK_DEV_INTEGRITY=y -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y diff --git a/arch/arm/configs/omap1_defconfig b/arch/arm/configs/omap1_defconfig index 0c43c589f191c991b0bf017935776a1eba98c18d..3b6e7452609ba9010934f7ea8a6bcab9dbdbfa3a 100644 --- a/arch/arm/configs/omap1_defconfig +++ b/arch/arm/configs/omap1_defconfig @@ -18,8 +18,6 @@ CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_OMAP=y CONFIG_ARCH_OMAP1=y CONFIG_OMAP_RESET_CLOCKS=y diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig index c32c338f770426bcb6c97e7a36ca2bd34b241b00..847f9874ccc4ad53b5ef58df5c316112aefe7350 100644 --- a/arch/arm/configs/omap2plus_defconfig +++ b/arch/arm/configs/omap2plus_defconfig @@ -375,6 +375,7 @@ CONFIG_BACKLIGHT_GENERIC=m CONFIG_BACKLIGHT_PWM=m CONFIG_BACKLIGHT_PANDORA=m CONFIG_BACKLIGHT_GPIO=m +CONFIG_BACKLIGHT_LED=m CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y CONFIG_LOGO=y diff --git a/arch/arm/configs/palmz72_defconfig b/arch/arm/configs/palmz72_defconfig index 4a3fd82c2a0c4a99cec375277c1cb25685efadc3..b47c8abe85bcc657759aaed0f28fb6e9869d825a 100644 --- a/arch/arm/configs/palmz72_defconfig +++ b/arch/arm/configs/palmz72_defconfig @@ -7,8 +7,6 @@ CONFIG_SLAB=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_PXA=y CONFIG_ARCH_PXA_PALM=y # CONFIG_MACH_PALMTX is not set diff --git a/arch/arm/configs/pcm027_defconfig b/arch/arm/configs/pcm027_defconfig index a8c53228b0c180cc90f2f6493b0331986e19ddb3..e97a158081fc755abe281c75841581ad66002245 100644 --- a/arch/arm/configs/pcm027_defconfig +++ b/arch/arm/configs/pcm027_defconfig @@ -13,8 +13,6 @@ CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_PXA=y CONFIG_MACH_PCM027=y CONFIG_MACH_PCM990_BASEBOARD=y diff --git a/arch/arm/configs/pleb_defconfig b/arch/arm/configs/pleb_defconfig index f0541b060cfaf64f4efb9ee7a16b78a9d9040e9c..2170148b975cedd7462623183241aac3620d62b3 100644 --- a/arch/arm/configs/pleb_defconfig +++ b/arch/arm/configs/pleb_defconfig @@ -6,8 +6,6 @@ CONFIG_EXPERT=y # CONFIG_HOTPLUG is not set # CONFIG_SHMEM is not set CONFIG_MODULES=y -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_SA1100=y CONFIG_SA1100_PLEB=y CONFIG_ZBOOT_ROM_TEXT=0x0 diff --git a/arch/arm/configs/realview_defconfig b/arch/arm/configs/realview_defconfig index 8a056cc0c1ec21285d891e2ac68311ff4bfcbc01..70e2c74a9f32d79d92e47a8d355e9cced1b4d700 100644 --- a/arch/arm/configs/realview_defconfig +++ b/arch/arm/configs/realview_defconfig @@ -8,7 +8,6 @@ CONFIG_SLAB=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_MULTI_V6=y CONFIG_ARCH_REALVIEW=y CONFIG_MACH_REALVIEW_EB=y diff --git a/arch/arm/configs/sama5_defconfig b/arch/arm/configs/sama5_defconfig index 27f6135c4ee73dc23e3b213582e426e833d5aafe..bab7861443dcf5330d87386261037beccc418671 100644 --- a/arch/arm/configs/sama5_defconfig +++ b/arch/arm/configs/sama5_defconfig @@ -14,8 +14,6 @@ CONFIG_MODULE_FORCE_LOAD=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_AT91=y CONFIG_SOC_SAMA5D2=y CONFIG_SOC_SAMA5D3=y @@ -182,7 +180,6 @@ CONFIG_USB_GADGET=y CONFIG_USB_ATMEL_USBA=y CONFIG_USB_G_SERIAL=y CONFIG_MMC=y -# CONFIG_MMC_BLOCK_BOUNCE is not set CONFIG_MMC_SDHCI=y CONFIG_MMC_SDHCI_PLTFM=y CONFIG_MMC_SDHCI_OF_AT91=y diff --git a/arch/arm/configs/socfpga_defconfig b/arch/arm/configs/socfpga_defconfig index fe2e1e82e23399dacdc4dbe6a68fd1957fd0f4df..e73c97b0f5b09b898b69e51d171c9f5d7fcec48d 100644 --- a/arch/arm/configs/socfpga_defconfig +++ b/arch/arm/configs/socfpga_defconfig @@ -157,6 +157,7 @@ CONFIG_NLS_ISO8859_1=y CONFIG_PRINTK_TIME=y CONFIG_DEBUG_INFO=y CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_FS=y CONFIG_DETECT_HUNG_TASK=y # CONFIG_SCHED_DEBUG is not set CONFIG_FUNCTION_TRACER=y diff --git a/arch/arm/configs/stm32_defconfig b/arch/arm/configs/stm32_defconfig index 152321d2893eb97d38cc40508e2e266e22c4ef9c..551db328009dd697194718dd349d6223febb0122 100644 --- a/arch/arm/configs/stm32_defconfig +++ b/arch/arm/configs/stm32_defconfig @@ -14,8 +14,6 @@ CONFIG_EMBEDDED=y # CONFIG_VM_EVENT_COUNTERS is not set # CONFIG_SLUB_DEBUG is not set # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set # CONFIG_MMU is not set CONFIG_ARCH_STM32=y CONFIG_CPU_V7M_NUM_IRQ=240 diff --git a/arch/arm/configs/sunxi_defconfig b/arch/arm/configs/sunxi_defconfig index 3f5d727efc41138a4a4c511c6d2f35120f5b8f51..e9fb57374b9f3ef521a45caf4a8e93d994b6f701 100644 --- a/arch/arm/configs/sunxi_defconfig +++ b/arch/arm/configs/sunxi_defconfig @@ -85,6 +85,7 @@ CONFIG_BATTERY_AXP20X=y CONFIG_AXP20X_POWER=y CONFIG_THERMAL=y CONFIG_CPU_THERMAL=y +CONFIG_SUN8I_THERMAL=y CONFIG_WATCHDOG=y CONFIG_SUNXI_WATCHDOG=y CONFIG_MFD_AC100=y diff --git a/arch/arm/configs/u300_defconfig b/arch/arm/configs/u300_defconfig index 8223397db047eb7939b03be3dceff1b7558d847b..543f07338100e0c064eb4c668324c3190072cf0c 100644 --- a/arch/arm/configs/u300_defconfig +++ b/arch/arm/configs/u300_defconfig @@ -11,7 +11,6 @@ CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set CONFIG_PARTITION_ADVANCED=y -# CONFIG_IOSCHED_CFQ is not set # CONFIG_ARCH_MULTI_V7 is not set CONFIG_ARCH_U300=y CONFIG_MACH_U300_SPIDUMMY=y @@ -46,7 +45,6 @@ CONFIG_FB=y CONFIG_BACKLIGHT_CLASS_DEVICE=y # CONFIG_USB_SUPPORT is not set CONFIG_MMC=y -# CONFIG_MMC_BLOCK_BOUNCE is not set CONFIG_MMC_ARMMMCI=y CONFIG_RTC_CLASS=y # CONFIG_RTC_HCTOSYS is not set diff --git a/arch/arm/configs/vexpress_defconfig b/arch/arm/configs/vexpress_defconfig index 25753552277ad18f973d7e0877dc2d741d014f6d..c01baf7d6e37c228bc8441747d1c8018de1213fc 100644 --- a/arch/arm/configs/vexpress_defconfig +++ b/arch/arm/configs/vexpress_defconfig @@ -15,8 +15,6 @@ CONFIG_OPROFILE=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_VEXPRESS=y CONFIG_ARCH_VEXPRESS_DCSCB=y CONFIG_ARCH_VEXPRESS_TC2_PM=y diff --git a/arch/arm/configs/viper_defconfig b/arch/arm/configs/viper_defconfig index 2ff16168d9c2892df5b5ba31f1cd8cbcdaa2ec99..989599ce53008213f9be251bc2f4f6f605abdbcb 100644 --- a/arch/arm/configs/viper_defconfig +++ b/arch/arm/configs/viper_defconfig @@ -9,7 +9,6 @@ CONFIG_SLAB=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_PXA=y CONFIG_ARCH_VIPER=y CONFIG_IWMMXT=y diff --git a/arch/arm/configs/zeus_defconfig b/arch/arm/configs/zeus_defconfig index aa3023c9a01196b43ec816094ee8302d7d197dd8..d3b98c4d225bec5470a72fca0ab0e9f1982da139 100644 --- a/arch/arm/configs/zeus_defconfig +++ b/arch/arm/configs/zeus_defconfig @@ -4,7 +4,6 @@ CONFIG_LOG_BUF_SHIFT=13 CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_PXA=y CONFIG_MACH_ARCOM_ZEUS=y CONFIG_PCCARD=m @@ -137,7 +136,6 @@ CONFIG_USB_MASS_STORAGE=m CONFIG_USB_G_SERIAL=m CONFIG_USB_G_PRINTER=m CONFIG_MMC=y -# CONFIG_MMC_BLOCK_BOUNCE is not set CONFIG_MMC_PXA=y CONFIG_NEW_LEDS=y CONFIG_LEDS_CLASS=m diff --git a/arch/arm/configs/zx_defconfig b/arch/arm/configs/zx_defconfig index 4d2ef785ed344f9c4d77cbbf9130128da307c423..a046a492bfa73442cb17dee01746cce7f45ea3eb 100644 --- a/arch/arm/configs/zx_defconfig +++ b/arch/arm/configs/zx_defconfig @@ -16,7 +16,6 @@ CONFIG_EMBEDDED=y CONFIG_PERF_EVENTS=y CONFIG_SLAB=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_ZX=y CONFIG_SOC_ZX296702=y # CONFIG_SWP_EMULATE is not set diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index c3314b286a61ea6feac86430fd576e834156dbe8..a827b4d60d389f3936a8185c4769f01fe9397226 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -392,9 +392,6 @@ static inline void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) {} static inline void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu) {} static inline void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu) {} -static inline void kvm_arm_vhe_guest_enter(void) {} -static inline void kvm_arm_vhe_guest_exit(void) {} - #define KVM_BP_HARDEN_UNKNOWN -1 #define KVM_BP_HARDEN_WA_NEEDED 0 #define KVM_BP_HARDEN_NOT_REQUIRED 1 diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c index 2a5ff69c28e68d195630c12bd9c05fc1bdf051b2..10499d44964a27f3e1998fe698526bfa7636c2de 100644 --- a/arch/arm/kernel/ftrace.c +++ b/arch/arm/kernel/ftrace.c @@ -78,13 +78,10 @@ static int ftrace_modify_code(unsigned long pc, unsigned long old, { unsigned long replaced; - if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) { + if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) old = __opcode_to_mem_thumb32(old); - new = __opcode_to_mem_thumb32(new); - } else { + else old = __opcode_to_mem_arm(old); - new = __opcode_to_mem_arm(new); - } if (validate) { if (probe_kernel_read(&replaced, (void *)pc, MCOUNT_INSN_SIZE)) diff --git a/arch/arm/kernel/patch.c b/arch/arm/kernel/patch.c index d0a05a3bdb9652450ea4a6e1cdc6036c945ab42a..e9e828b6bb30622d026f89f9f25bbc96bb2ea3a7 100644 --- a/arch/arm/kernel/patch.c +++ b/arch/arm/kernel/patch.c @@ -16,10 +16,10 @@ struct patch { unsigned int insn; }; +#ifdef CONFIG_MMU static DEFINE_RAW_SPINLOCK(patch_lock); static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags) - __acquires(&patch_lock) { unsigned int uintaddr = (uintptr_t) addr; bool module = !core_kernel_text(uintaddr); @@ -34,8 +34,6 @@ static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags) if (flags) raw_spin_lock_irqsave(&patch_lock, *flags); - else - __acquire(&patch_lock); set_fixmap(fixmap, page_to_phys(page)); @@ -43,15 +41,19 @@ static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags) } static void __kprobes patch_unmap(int fixmap, unsigned long *flags) - __releases(&patch_lock) { clear_fixmap(fixmap); if (flags) raw_spin_unlock_irqrestore(&patch_lock, *flags); - else - __release(&patch_lock); } +#else +static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags) +{ + return addr; +} +static void __kprobes patch_unmap(int fixmap, unsigned long *flags) { } +#endif void __kprobes __patch_text_real(void *addr, unsigned int insn, bool remap) { @@ -64,8 +66,6 @@ void __kprobes __patch_text_real(void *addr, unsigned int insn, bool remap) if (remap) waddr = patch_map(addr, FIX_TEXT_POKE0, &flags); - else - __acquire(&patch_lock); if (thumb2 && __opcode_is_thumb16(insn)) { *(u16 *)waddr = __opcode_to_mem_thumb16(insn); @@ -102,8 +102,7 @@ void __kprobes __patch_text_real(void *addr, unsigned int insn, bool remap) if (waddr != addr) { flush_kernel_vmap_range(waddr, twopage ? size / 2 : size); patch_unmap(FIX_TEXT_POKE0, &flags); - } else - __release(&patch_lock); + } flush_icache_range((uintptr_t)(addr), (uintptr_t)(addr) + size); diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c index c89ac1b9d28b2969facdd11ca57b64189caf5d5a..e0330a25e1c6df38f672b0c662fe801278088110 100644 --- a/arch/arm/kernel/vdso.c +++ b/arch/arm/kernel/vdso.c @@ -94,6 +94,8 @@ static bool __init cntvct_functional(void) * this. */ np = of_find_compatible_node(NULL, NULL, "arm,armv7-timer"); + if (!np) + np = of_find_compatible_node(NULL, NULL, "arm,armv8-timer"); if (!np) goto out_put; diff --git a/arch/arm/lib/copy_from_user.S b/arch/arm/lib/copy_from_user.S index 95b2e1ce559cb198016b5281d2e3b463b3ad0fac..f8016e3db65d7f628327ed7600f24943c210ea7f 100644 --- a/arch/arm/lib/copy_from_user.S +++ b/arch/arm/lib/copy_from_user.S @@ -118,7 +118,7 @@ ENTRY(arm_copy_from_user) ENDPROC(arm_copy_from_user) - .pushsection .fixup,"ax" + .pushsection .text.fixup,"ax" .align 0 copy_abort_preamble ldmfd sp!, {r1, r2, r3} diff --git a/arch/arm/mach-imx/Makefile b/arch/arm/mach-imx/Makefile index 35ff620537e62b3fab1759730a53b6cb8d4a5d9b..03506ce4614934675e772cce4a74386ead086fae 100644 --- a/arch/arm/mach-imx/Makefile +++ b/arch/arm/mach-imx/Makefile @@ -91,6 +91,8 @@ AFLAGS_suspend-imx6.o :=-Wa,-march=armv7-a obj-$(CONFIG_SOC_IMX6) += suspend-imx6.o obj-$(CONFIG_SOC_IMX53) += suspend-imx53.o endif +AFLAGS_resume-imx6.o :=-Wa,-march=armv7-a +obj-$(CONFIG_SOC_IMX6) += resume-imx6.o obj-$(CONFIG_SOC_IMX6) += pm-imx6.o obj-$(CONFIG_SOC_IMX1) += mach-imx1.o diff --git a/arch/arm/mach-imx/common.h b/arch/arm/mach-imx/common.h index 912aeceb4ff81cc8cb2c41c2fd91b2757032335d..5aa5796cff0e19280208379ceae42df22da4c452 100644 --- a/arch/arm/mach-imx/common.h +++ b/arch/arm/mach-imx/common.h @@ -109,17 +109,17 @@ void imx_cpu_die(unsigned int cpu); int imx_cpu_kill(unsigned int cpu); #ifdef CONFIG_SUSPEND -void v7_cpu_resume(void); void imx53_suspend(void __iomem *ocram_vbase); extern const u32 imx53_suspend_sz; void imx6_suspend(void __iomem *ocram_vbase); #else -static inline void v7_cpu_resume(void) {} static inline void imx53_suspend(void __iomem *ocram_vbase) {} static const u32 imx53_suspend_sz; static inline void imx6_suspend(void __iomem *ocram_vbase) {} #endif +void v7_cpu_resume(void); + void imx6_pm_ccm_init(const char *ccm_compat); void imx6q_pm_init(void); void imx6dl_pm_init(void); diff --git a/arch/arm/mach-imx/resume-imx6.S b/arch/arm/mach-imx/resume-imx6.S new file mode 100644 index 0000000000000000000000000000000000000000..5bd1ba7ef15b61cb98d1bd2d3af4e85acc5ec632 --- /dev/null +++ b/arch/arm/mach-imx/resume-imx6.S @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright 2014 Freescale Semiconductor, Inc. + */ + +#include +#include +#include +#include +#include "hardware.h" + +/* + * The following code must assume it is running from physical address + * where absolute virtual addresses to the data section have to be + * turned into relative ones. + */ + +ENTRY(v7_cpu_resume) + bl v7_invalidate_l1 +#ifdef CONFIG_CACHE_L2X0 + bl l2c310_early_resume +#endif + b cpu_resume +ENDPROC(v7_cpu_resume) diff --git a/arch/arm/mach-imx/suspend-imx6.S b/arch/arm/mach-imx/suspend-imx6.S index 062391ff13dae207b35c15fb3a56e9c1c65b70a5..1eabf2d2834be79c6a6a695262ca4f1af2edcfc2 100644 --- a/arch/arm/mach-imx/suspend-imx6.S +++ b/arch/arm/mach-imx/suspend-imx6.S @@ -327,17 +327,3 @@ resume: ret lr ENDPROC(imx6_suspend) - -/* - * The following code must assume it is running from physical address - * where absolute virtual addresses to the data section have to be - * turned into relative ones. - */ - -ENTRY(v7_cpu_resume) - bl v7_invalidate_l1 -#ifdef CONFIG_CACHE_L2X0 - bl l2c310_early_resume -#endif - b cpu_resume -ENDPROC(v7_cpu_resume) diff --git a/arch/arm/mach-meson/Kconfig b/arch/arm/mach-meson/Kconfig index 01f0f4b765e00c980c855389256681d9d7293912..75034fe197e3be0d04e7043d14312dbfa0107f69 100644 --- a/arch/arm/mach-meson/Kconfig +++ b/arch/arm/mach-meson/Kconfig @@ -9,7 +9,6 @@ menuconfig ARCH_MESON select CACHE_L2X0 select PINCTRL select PINCTRL_MESON - select COMMON_CLK select HAVE_ARM_SCU if SMP select HAVE_ARM_TWD if SMP diff --git a/arch/arm/mach-npcm/Kconfig b/arch/arm/mach-npcm/Kconfig index 880bc2a5cadaa95a9f4551979c3f6d6b8ffab435..7f7002dc2b21fec89afd25529c87d7ca16630cf2 100644 --- a/arch/arm/mach-npcm/Kconfig +++ b/arch/arm/mach-npcm/Kconfig @@ -11,7 +11,7 @@ config ARCH_NPCM7XX depends on ARCH_MULTI_V7 select PINCTRL_NPCM7XX select NPCM7XX_TIMER - select ARCH_REQUIRE_GPIOLIB + select GPIOLIB select CACHE_L2X0 select ARM_GIC select HAVE_ARM_TWD if SMP diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile index e1135b9d67c65c3e2080d36d2b54b40033bd5b4f..5017a3be0ff016f8c33afabad821caca8f25a9ca 100644 --- a/arch/arm/mach-omap2/Makefile +++ b/arch/arm/mach-omap2/Makefile @@ -16,7 +16,7 @@ hwmod-common = omap_hwmod.o omap_hwmod_reset.o \ clock-common = clock.o secure-common = omap-smc.o omap-secure.o -obj-$(CONFIG_ARCH_OMAP2) += $(omap-2-3-common) $(hwmod-common) $(secure-common) +obj-$(CONFIG_ARCH_OMAP2) += $(omap-2-3-common) $(hwmod-common) obj-$(CONFIG_ARCH_OMAP3) += $(omap-2-3-common) $(hwmod-common) $(secure-common) obj-$(CONFIG_ARCH_OMAP4) += $(hwmod-common) $(secure-common) obj-$(CONFIG_SOC_AM33XX) += $(hwmod-common) $(secure-common) diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c index f280472336657dbbb1fe544d27e08ddfc2277cfa..27608d1026cbced98b22f25678d4e92827cd8758 100644 --- a/arch/arm/mach-omap2/io.c +++ b/arch/arm/mach-omap2/io.c @@ -431,7 +431,6 @@ void __init omap2420_init_early(void) omap_hwmod_init_postsetup(); omap_clk_soc_init = omap2420_dt_clk_init; rate_table = omap2420_rate_table; - omap_secure_init(); } void __init omap2420_init_late(void) @@ -456,7 +455,6 @@ void __init omap2430_init_early(void) omap_hwmod_init_postsetup(); omap_clk_soc_init = omap2430_dt_clk_init; rate_table = omap2430_rate_table; - omap_secure_init(); } void __init omap2430_init_late(void) diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts index f82f25c1a5f97be47d4593be9850ac0c5c7f0f32..d5dc12878dfe495b136b894ed45ebd3e07f929dd 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts @@ -327,7 +327,7 @@ &sd_emmc_a { #size-cells = <0>; bus-width = <4>; - max-frequency = <50000000>; + max-frequency = <60000000>; non-removable; disable-wp; diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1-sei610.dts b/arch/arm64/boot/dts/amlogic/meson-sm1-sei610.dts index a8bb3fa9fec98e994ce2876b95e81e86b8369c02..cb1b48f5b8b1cdf4d4c5cb98198c2df1006cf177 100644 --- a/arch/arm64/boot/dts/amlogic/meson-sm1-sei610.dts +++ b/arch/arm64/boot/dts/amlogic/meson-sm1-sei610.dts @@ -593,6 +593,7 @@ bluetooth { compatible = "brcm,bcm43438-bt"; interrupt-parent = <&gpio_intc>; interrupts = <95 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "host-wakeup"; shutdown-gpios = <&gpio GPIOX_17 GPIO_ACTIVE_HIGH>; max-speed = <2000000>; clocks = <&wifi32k>; diff --git a/arch/arm64/boot/dts/arm/fvp-base-revc.dts b/arch/arm64/boot/dts/arm/fvp-base-revc.dts index 62ab0d54ff71ed4f513837d24fdfae1a743f773f..335fff76245167467fbdf3932ec42e0a84c0c586 100644 --- a/arch/arm64/boot/dts/arm/fvp-base-revc.dts +++ b/arch/arm64/boot/dts/arm/fvp-base-revc.dts @@ -161,10 +161,10 @@ pci: pci@40000000 { bus-range = <0x0 0x1>; reg = <0x0 0x40000000 0x0 0x10000000>; ranges = <0x2000000 0x0 0x50000000 0x0 0x50000000 0x0 0x10000000>; - interrupt-map = <0 0 0 1 &gic GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>, - <0 0 0 2 &gic GIC_SPI 169 IRQ_TYPE_LEVEL_HIGH>, - <0 0 0 3 &gic GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>, - <0 0 0 4 &gic GIC_SPI 171 IRQ_TYPE_LEVEL_HIGH>; + interrupt-map = <0 0 0 1 &gic 0 0 GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 2 &gic 0 0 GIC_SPI 169 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 3 &gic 0 0 GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 4 &gic 0 0 GIC_SPI 171 IRQ_TYPE_LEVEL_HIGH>; interrupt-map-mask = <0x0 0x0 0x0 0x7>; msi-map = <0x0 &its 0x0 0x10000>; iommu-map = <0x0 &smmu 0x0 0x10000>; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043-post.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043-post.dtsi index 6082ae02213642878e5a659c51fc6fe7fd506df2..d237162a874462604ba4a170cf068809d0d34836 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1043-post.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1043-post.dtsi @@ -20,6 +20,8 @@ &soc { }; &fman0 { + fsl,erratum-a050385; + /* these aliases provide the FMan ports mapping */ enet0: ethernet@e0000 { }; diff --git a/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts b/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts index d3d26cca7d526c63b8a6f5d4be201c9cfbbfb60c..13460a360c6af7bc0dba24184c20523b332184ce 100644 --- a/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts +++ b/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts @@ -52,11 +52,6 @@ ethphy0: ethernet-phy@0 { compatible = "ethernet-phy-ieee802.3-c22"; reg = <0>; }; - - ethphy1: ethernet-phy@1 { - compatible = "ethernet-phy-ieee802.3-c22"; - reg = <1>; - }; }; }; diff --git a/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi b/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi index e1d357eaad7c364333d826cc45d00e2d9fca8ab2..d8c44d3ca15acb7ab2751533972eeab372803419 100644 --- a/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi +++ b/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi @@ -102,7 +102,7 @@ base_fpga_region { }; gmac0: ethernet@ff800000 { - compatible = "altr,socfpga-stmmac", "snps,dwmac-3.74a", "snps,dwmac"; + compatible = "altr,socfpga-stmmac-a10-s10", "snps,dwmac-3.74a", "snps,dwmac"; reg = <0xff800000 0x2000>; interrupts = <0 90 4>; interrupt-names = "macirq"; @@ -118,7 +118,7 @@ gmac0: ethernet@ff800000 { }; gmac1: ethernet@ff802000 { - compatible = "altr,socfpga-stmmac", "snps,dwmac-3.74a", "snps,dwmac"; + compatible = "altr,socfpga-stmmac-a10-s10", "snps,dwmac-3.74a", "snps,dwmac"; reg = <0xff802000 0x2000>; interrupts = <0 91 4>; interrupt-names = "macirq"; @@ -134,7 +134,7 @@ gmac1: ethernet@ff802000 { }; gmac2: ethernet@ff804000 { - compatible = "altr,socfpga-stmmac", "snps,dwmac-3.74a", "snps,dwmac"; + compatible = "altr,socfpga-stmmac-a10-s10", "snps,dwmac-3.74a", "snps,dwmac"; reg = <0xff804000 0x2000>; interrupts = <0 92 4>; interrupt-names = "macirq"; diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 0f212889c931a83db236f3ad8c7cdcac0235e7c6..4db223dbc549936c1dcef9b0832731c28a32112a 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -452,6 +452,7 @@ CONFIG_THERMAL_GOV_POWER_ALLOCATOR=y CONFIG_CPU_THERMAL=y CONFIG_THERMAL_EMULATION=y CONFIG_QORIQ_THERMAL=m +CONFIG_SUN8I_THERMAL=y CONFIG_ROCKCHIP_THERMAL=m CONFIG_RCAR_THERMAL=y CONFIG_RCAR_GEN3_THERMAL=y @@ -547,6 +548,7 @@ CONFIG_ROCKCHIP_DW_MIPI_DSI=y CONFIG_ROCKCHIP_INNO_HDMI=y CONFIG_DRM_RCAR_DU=m CONFIG_DRM_SUN4I=m +CONFIG_DRM_SUN6I_DSI=m CONFIG_DRM_SUN8I_DW_HDMI=m CONFIG_DRM_SUN8I_MIXER=m CONFIG_DRM_MSM=m @@ -681,7 +683,7 @@ CONFIG_RTC_DRV_SNVS=m CONFIG_RTC_DRV_IMX_SC=m CONFIG_RTC_DRV_XGENE=y CONFIG_DMADEVICES=y -CONFIG_DMA_BCM2835=m +CONFIG_DMA_BCM2835=y CONFIG_DMA_SUN6I=m CONFIG_FSL_EDMA=y CONFIG_IMX_SDMA=y @@ -771,7 +773,7 @@ CONFIG_ARCH_R8A774A1=y CONFIG_ARCH_R8A774B1=y CONFIG_ARCH_R8A774C0=y CONFIG_ARCH_R8A7795=y -CONFIG_ARCH_R8A7796=y +CONFIG_ARCH_R8A77960=y CONFIG_ARCH_R8A77961=y CONFIG_ARCH_R8A77965=y CONFIG_ARCH_R8A77970=y diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h index 25fec4bde43af6f66bbb0e170a888d154eb82535..a358e97572c14c58d55d732926cf3f211a71a410 100644 --- a/arch/arm64/include/asm/arch_gicv3.h +++ b/arch/arm64/include/asm/arch_gicv3.h @@ -32,7 +32,7 @@ static inline void gic_write_eoir(u32 irq) isb(); } -static inline void gic_write_dir(u32 irq) +static __always_inline void gic_write_dir(u32 irq) { write_sysreg_s(irq, SYS_ICC_DIR_EL1); isb(); diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h index 806e9dc2a852a43d54f9eeb89122684553971b16..a4d1b5f771f6baebd64c3c291be937e84eddd397 100644 --- a/arch/arm64/include/asm/cache.h +++ b/arch/arm64/include/asm/cache.h @@ -69,7 +69,7 @@ static inline int icache_is_aliasing(void) return test_bit(ICACHEF_ALIASING, &__icache_flags); } -static inline int icache_is_vpipt(void) +static __always_inline int icache_is_vpipt(void) { return test_bit(ICACHEF_VPIPT, &__icache_flags); } diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h index 665c78e0665a65ea89f40442bef31b55bebf9147..e6cca3d4acf702f060bb35996ead0762566de7b6 100644 --- a/arch/arm64/include/asm/cacheflush.h +++ b/arch/arm64/include/asm/cacheflush.h @@ -145,7 +145,7 @@ extern void copy_to_user_page(struct vm_area_struct *, struct page *, #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page *); -static inline void __flush_icache_all(void) +static __always_inline void __flush_icache_all(void) { if (cpus_have_const_cap(ARM64_HAS_CACHE_DIC)) return; diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 92ef9539874a663b3bd693c4e834a5cf134a21d6..2a746b99e937f489cac93452fe4a11dfbc1c17d8 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -435,13 +435,13 @@ cpuid_feature_extract_signed_field(u64 features, int field) return cpuid_feature_extract_signed_field_width(features, field, 4); } -static inline unsigned int __attribute_const__ +static __always_inline unsigned int __attribute_const__ cpuid_feature_extract_unsigned_field_width(u64 features, int field, int width) { return (u64)(features << (64 - width - field)) >> (64 - width); } -static inline unsigned int __attribute_const__ +static __always_inline unsigned int __attribute_const__ cpuid_feature_extract_unsigned_field(u64 features, int field) { return cpuid_feature_extract_unsigned_field_width(features, field, 4); @@ -564,7 +564,7 @@ static inline bool system_supports_mixed_endian(void) return val == 0x1; } -static inline bool system_supports_fpsimd(void) +static __always_inline bool system_supports_fpsimd(void) { return !cpus_have_const_cap(ARM64_HAS_NO_FPSIMD); } @@ -575,13 +575,13 @@ static inline bool system_uses_ttbr0_pan(void) !cpus_have_const_cap(ARM64_HAS_PAN); } -static inline bool system_supports_sve(void) +static __always_inline bool system_supports_sve(void) { return IS_ENABLED(CONFIG_ARM64_SVE) && cpus_have_const_cap(ARM64_SVE); } -static inline bool system_supports_cnp(void) +static __always_inline bool system_supports_cnp(void) { return IS_ENABLED(CONFIG_ARM64_CNP) && cpus_have_const_cap(ARM64_HAS_CNP); diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h index b87c6e276ab194e4d80cf85150c844c94ee2d5b5..7a6e81ca23a8e0ed5a11013fc74f3ca82cefd1c5 100644 --- a/arch/arm64/include/asm/exception.h +++ b/arch/arm64/include/asm/exception.h @@ -33,7 +33,6 @@ static inline u32 disr_to_esr(u64 disr) asmlinkage void enter_from_user_mode(void); void do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs); -void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs); void do_undefinstr(struct pt_regs *regs); asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr); void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr, @@ -47,7 +46,4 @@ void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr); void do_cp15instr(unsigned int esr, struct pt_regs *regs); void do_el0_svc(struct pt_regs *regs); void do_el0_svc_compat(struct pt_regs *regs); -void do_el0_ia_bp_hardening(unsigned long addr, unsigned int esr, - struct pt_regs *regs); - #endif /* __ASM_EXCEPTION_H */ diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h index 4e531f57147d122aec8c87a800a08e33400b3c51..6facd1308e7c28c54ef35e762652f7cdb364322e 100644 --- a/arch/arm64/include/asm/io.h +++ b/arch/arm64/include/asm/io.h @@ -34,7 +34,7 @@ static inline void __raw_writew(u16 val, volatile void __iomem *addr) } #define __raw_writel __raw_writel -static inline void __raw_writel(u32 val, volatile void __iomem *addr) +static __always_inline void __raw_writel(u32 val, volatile void __iomem *addr) { asm volatile("str %w0, [%1]" : : "rZ" (val), "r" (addr)); } @@ -69,7 +69,7 @@ static inline u16 __raw_readw(const volatile void __iomem *addr) } #define __raw_readl __raw_readl -static inline u32 __raw_readl(const volatile void __iomem *addr) +static __always_inline u32 __raw_readl(const volatile void __iomem *addr) { u32 val; asm volatile(ALTERNATIVE("ldr %w0, [%1]", diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 688c63412cc27922aa2b5faba8d8fc808bef674b..f658dda123645f53462586cf9b4798e8349177cb 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -36,7 +36,7 @@ void kvm_inject_undef32(struct kvm_vcpu *vcpu); void kvm_inject_dabt32(struct kvm_vcpu *vcpu, unsigned long addr); void kvm_inject_pabt32(struct kvm_vcpu *vcpu, unsigned long addr); -static inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu) +static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu) { return !(vcpu->arch.hcr_el2 & HCR_RW); } @@ -127,7 +127,7 @@ static inline void vcpu_set_vsesr(struct kvm_vcpu *vcpu, u64 vsesr) vcpu->arch.vsesr_el2 = vsesr; } -static inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu) +static __always_inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu) { return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pc; } @@ -153,17 +153,17 @@ static inline void vcpu_write_elr_el1(const struct kvm_vcpu *vcpu, unsigned long *__vcpu_elr_el1(vcpu) = v; } -static inline unsigned long *vcpu_cpsr(const struct kvm_vcpu *vcpu) +static __always_inline unsigned long *vcpu_cpsr(const struct kvm_vcpu *vcpu) { return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pstate; } -static inline bool vcpu_mode_is_32bit(const struct kvm_vcpu *vcpu) +static __always_inline bool vcpu_mode_is_32bit(const struct kvm_vcpu *vcpu) { return !!(*vcpu_cpsr(vcpu) & PSR_MODE32_BIT); } -static inline bool kvm_condition_valid(const struct kvm_vcpu *vcpu) +static __always_inline bool kvm_condition_valid(const struct kvm_vcpu *vcpu) { if (vcpu_mode_is_32bit(vcpu)) return kvm_condition_valid32(vcpu); @@ -181,13 +181,13 @@ static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu) * coming from a read of ESR_EL2. Otherwise, it may give the wrong result on * AArch32 with banked registers. */ -static inline unsigned long vcpu_get_reg(const struct kvm_vcpu *vcpu, +static __always_inline unsigned long vcpu_get_reg(const struct kvm_vcpu *vcpu, u8 reg_num) { return (reg_num == 31) ? 0 : vcpu_gp_regs(vcpu)->regs.regs[reg_num]; } -static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num, +static __always_inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num, unsigned long val) { if (reg_num != 31) @@ -264,12 +264,12 @@ static inline bool vcpu_mode_priv(const struct kvm_vcpu *vcpu) return mode != PSR_MODE_EL0t; } -static inline u32 kvm_vcpu_get_hsr(const struct kvm_vcpu *vcpu) +static __always_inline u32 kvm_vcpu_get_hsr(const struct kvm_vcpu *vcpu) { return vcpu->arch.fault.esr_el2; } -static inline int kvm_vcpu_get_condition(const struct kvm_vcpu *vcpu) +static __always_inline int kvm_vcpu_get_condition(const struct kvm_vcpu *vcpu) { u32 esr = kvm_vcpu_get_hsr(vcpu); @@ -279,12 +279,12 @@ static inline int kvm_vcpu_get_condition(const struct kvm_vcpu *vcpu) return -1; } -static inline unsigned long kvm_vcpu_get_hfar(const struct kvm_vcpu *vcpu) +static __always_inline unsigned long kvm_vcpu_get_hfar(const struct kvm_vcpu *vcpu) { return vcpu->arch.fault.far_el2; } -static inline phys_addr_t kvm_vcpu_get_fault_ipa(const struct kvm_vcpu *vcpu) +static __always_inline phys_addr_t kvm_vcpu_get_fault_ipa(const struct kvm_vcpu *vcpu) { return ((phys_addr_t)vcpu->arch.fault.hpfar_el2 & HPFAR_MASK) << 8; } @@ -299,7 +299,7 @@ static inline u32 kvm_vcpu_hvc_get_imm(const struct kvm_vcpu *vcpu) return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_xVC_IMM_MASK; } -static inline bool kvm_vcpu_dabt_isvalid(const struct kvm_vcpu *vcpu) +static __always_inline bool kvm_vcpu_dabt_isvalid(const struct kvm_vcpu *vcpu) { return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_ISV); } @@ -319,17 +319,17 @@ static inline bool kvm_vcpu_dabt_issf(const struct kvm_vcpu *vcpu) return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SF); } -static inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu) +static __always_inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu) { return (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT; } -static inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu) +static __always_inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu) { return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_S1PTW); } -static inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu) +static __always_inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu) { return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WNR) || kvm_vcpu_dabt_iss1tw(vcpu); /* AF/DBM update */ @@ -340,18 +340,18 @@ static inline bool kvm_vcpu_dabt_is_cm(const struct kvm_vcpu *vcpu) return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_CM); } -static inline unsigned int kvm_vcpu_dabt_get_as(const struct kvm_vcpu *vcpu) +static __always_inline unsigned int kvm_vcpu_dabt_get_as(const struct kvm_vcpu *vcpu) { return 1 << ((kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT); } /* This one is not specific to Data Abort */ -static inline bool kvm_vcpu_trap_il_is32bit(const struct kvm_vcpu *vcpu) +static __always_inline bool kvm_vcpu_trap_il_is32bit(const struct kvm_vcpu *vcpu) { return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_IL); } -static inline u8 kvm_vcpu_trap_get_class(const struct kvm_vcpu *vcpu) +static __always_inline u8 kvm_vcpu_trap_get_class(const struct kvm_vcpu *vcpu) { return ESR_ELx_EC(kvm_vcpu_get_hsr(vcpu)); } @@ -361,17 +361,17 @@ static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu) return kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_IABT_LOW; } -static inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu) +static __always_inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu) { return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_FSC; } -static inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vcpu) +static __always_inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vcpu) { return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_FSC_TYPE; } -static inline bool kvm_vcpu_dabt_isextabt(const struct kvm_vcpu *vcpu) +static __always_inline bool kvm_vcpu_dabt_isextabt(const struct kvm_vcpu *vcpu) { switch (kvm_vcpu_trap_get_fault(vcpu)) { case FSC_SEA: @@ -390,7 +390,7 @@ static inline bool kvm_vcpu_dabt_isextabt(const struct kvm_vcpu *vcpu) } } -static inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu) +static __always_inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu) { u32 esr = kvm_vcpu_get_hsr(vcpu); return ESR_ELx_SYS64_ISS_RT(esr); @@ -504,7 +504,7 @@ static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu, return data; /* Leave LE untouched */ } -static inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr) +static __always_inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr) { if (vcpu_mode_is_32bit(vcpu)) kvm_skip_instr32(vcpu, is_wide_instr); @@ -519,7 +519,7 @@ static inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr) * Skip an instruction which has been emulated at hyp while most guest sysregs * are live. */ -static inline void __hyp_text __kvm_skip_instr(struct kvm_vcpu *vcpu) +static __always_inline void __hyp_text __kvm_skip_instr(struct kvm_vcpu *vcpu) { *vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR); vcpu->arch.ctxt.gp_regs.regs.pstate = read_sysreg_el2(SYS_SPSR); diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index d87aa609d2b6f3e49a5b44ccd523b89753289846..57fd46acd05823ed650a34bf16d7412013f7607c 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -626,38 +626,6 @@ static inline void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr) {} static inline void kvm_clr_pmu_events(u32 clr) {} #endif -static inline void kvm_arm_vhe_guest_enter(void) -{ - local_daif_mask(); - - /* - * Having IRQs masked via PMR when entering the guest means the GIC - * will not signal the CPU of interrupts of lower priority, and the - * only way to get out will be via guest exceptions. - * Naturally, we want to avoid this. - * - * local_daif_mask() already sets GIC_PRIO_PSR_I_SET, we just need a - * dsb to ensure the redistributor is forwards EL2 IRQs to the CPU. - */ - pmr_sync(); -} - -static inline void kvm_arm_vhe_guest_exit(void) -{ - /* - * local_daif_restore() takes care to properly restore PSTATE.DAIF - * and the GIC PMR if the host is using IRQ priorities. - */ - local_daif_restore(DAIF_PROCCTX_NOIRQ); - - /* - * When we exit from the guest we change a number of CPU configuration - * parameters, such as traps. Make sure these changes take effect - * before running the host or additional guests. - */ - isb(); -} - #define KVM_BP_HARDEN_UNKNOWN -1 #define KVM_BP_HARDEN_WA_NEEDED 0 #define KVM_BP_HARDEN_NOT_REQUIRED 1 diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index a3a6a2ba9a635efd7feec4542f4c0b281052521c..fe57f60f06a8944fff74b2e3f1ed5de6d1790626 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -47,6 +47,13 @@ #define read_sysreg_el2(r) read_sysreg_elx(r, _EL2, _EL1) #define write_sysreg_el2(v,r) write_sysreg_elx(v, r, _EL2, _EL1) +/* + * Without an __arch_swab32(), we fall back to ___constant_swab32(), but the + * static inline can allow the compiler to out-of-line this. KVM always wants + * the macro version as its always inlined. + */ +#define __kvm_swab32(x) ___constant_swab32(x) + int __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu); void __vgic_v3_save_state(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 53d846f1bfe70497b81d2457c9a6eefe543fc61f..785762860c63fd5c435f575cffdf22f2c69d8b27 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -93,7 +93,7 @@ void kvm_update_va_mask(struct alt_instr *alt, __le32 *origptr, __le32 *updptr, int nr_inst); void kvm_compute_layout(void); -static inline unsigned long __kern_hyp_va(unsigned long v) +static __always_inline unsigned long __kern_hyp_va(unsigned long v) { asm volatile(ALTERNATIVE_CB("and %0, %0, #1\n" "ror %0, %0, #1\n" @@ -473,6 +473,7 @@ static inline int kvm_write_guest_lock(struct kvm *kvm, gpa_t gpa, extern void *__kvm_bp_vect_base; extern int __kvm_harden_el2_vector_slot; +/* This is only called on a VHE system */ static inline void *kvm_get_hyp_vector(void) { struct bp_hardening_data *data = arm64_get_bp_hardening_data(); diff --git a/arch/arm64/include/asm/lse.h b/arch/arm64/include/asm/lse.h index d429f7701c3670101b62540f79c65ec711cba4d1..5d10051c3e62e839808d9ee0a56e0274d934589a 100644 --- a/arch/arm64/include/asm/lse.h +++ b/arch/arm64/include/asm/lse.h @@ -6,7 +6,7 @@ #ifdef CONFIG_ARM64_LSE_ATOMICS -#define __LSE_PREAMBLE ".arch armv8-a+lse\n" +#define __LSE_PREAMBLE ".arch_extension lse\n" #include #include diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index a4f9ca5479b063a012ec400c5ee623594d44e693..4d94676e5a8b6b08e0043b09bf7728ec1eb15642 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -213,7 +213,7 @@ static inline unsigned long kaslr_offset(void) ((__force __typeof__(addr))sign_extend64((__force u64)(addr), 55)) #define untagged_addr(addr) ({ \ - u64 __addr = (__force u64)addr; \ + u64 __addr = (__force u64)(addr); \ __addr &= __untagged_addr(__addr); \ (__force __typeof__(addr))__addr; \ }) diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index e4d862420bb4051714f8052b01d84e817678f857..d79ce6df9e127c16fda0b11a64716674f16419e7 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -29,11 +29,9 @@ typedef struct { */ #define ASID(mm) ((mm)->context.id.counter & 0xffff) -extern bool arm64_use_ng_mappings; - static inline bool arm64_kernel_unmapped_at_el0(void) { - return arm64_use_ng_mappings; + return cpus_have_const_cap(ARM64_UNMAP_KERNEL_AT_EL0); } typedef void (*bp_hardening_cb_t)(void); diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index 6f87839f02491b5161452ea76b05eeef47821ed6..1305e28225fc77bb5c0a8a2bbd6ed8540934c835 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -23,11 +23,13 @@ #include +extern bool arm64_use_ng_mappings; + #define _PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED) #define _PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S) -#define PTE_MAYBE_NG (arm64_kernel_unmapped_at_el0() ? PTE_NG : 0) -#define PMD_MAYBE_NG (arm64_kernel_unmapped_at_el0() ? PMD_SECT_NG : 0) +#define PTE_MAYBE_NG (arm64_use_ng_mappings ? PTE_NG : 0) +#define PMD_MAYBE_NG (arm64_use_ng_mappings ? PMD_SECT_NG : 0) #define PROT_DEFAULT (_PROT_DEFAULT | PTE_MAYBE_NG) #define PROT_SECT_DEFAULT (_PROT_SECT_DEFAULT | PMD_MAYBE_NG) diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h index 102404dc1e135d3e533cbf4549cb8db4a858b379..9083d6992603e6e26aa3ad120bf3fd6f9cc4720a 100644 --- a/arch/arm64/include/asm/spinlock.h +++ b/arch/arm64/include/asm/spinlock.h @@ -18,6 +18,10 @@ * See: * https://lore.kernel.org/lkml/20200110100612.GC2827@hirez.programming.kicks-ass.net */ -#define vcpu_is_preempted(cpu) false +#define vcpu_is_preempted vcpu_is_preempted +static inline bool vcpu_is_preempted(int cpu) +{ + return false; +} #endif /* __ASM_SPINLOCK_H */ diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 1dd22da1c3a95985ad22331c5f59975edefedf6a..803039d504de609b188e62abd2fc102f00d73db5 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -25,8 +25,8 @@ #define __NR_compat_gettimeofday 78 #define __NR_compat_sigreturn 119 #define __NR_compat_rt_sigreturn 173 -#define __NR_compat_clock_getres 247 #define __NR_compat_clock_gettime 263 +#define __NR_compat_clock_getres 264 #define __NR_compat_clock_gettime64 403 #define __NR_compat_clock_getres_time64 406 diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h index 0958ed6191aa344dcc84c965cc1f1e410a53540f..61fd26752adcb3bf19f55a7d6e3f03b8581f686e 100644 --- a/arch/arm64/include/asm/virt.h +++ b/arch/arm64/include/asm/virt.h @@ -83,7 +83,7 @@ static inline bool is_kernel_in_hyp_mode(void) return read_sysreg(CurrentEL) == CurrentEL_EL2; } -static inline bool has_vhe(void) +static __always_inline bool has_vhe(void) { if (cpus_have_const_cap(ARM64_HAS_VIRT_HOST_EXTN)) return true; diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c index 53b8a4ee64ff0cb68f959b4562d0ae0b64c14ac5..91a83104c6e8a37848d534872d6642812b40daba 100644 --- a/arch/arm64/kernel/kaslr.c +++ b/arch/arm64/kernel/kaslr.c @@ -11,6 +11,7 @@ #include #include +#include #include #include #include diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index bbb0f0c145f6f5e4201ec728064fe992b9ee801c..00626057a384a5c38330f20d0c5d11148c4f3fd2 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -466,6 +466,13 @@ static void ssbs_thread_switch(struct task_struct *next) if (unlikely(next->flags & PF_KTHREAD)) return; + /* + * If all CPUs implement the SSBS extension, then we just need to + * context-switch the PSTATE field. + */ + if (cpu_have_feature(cpu_feature(SSBS))) + return; + /* If the mitigation is enabled, then we leave SSBS clear. */ if ((arm64_get_ssbd_state() == ARM64_SSBD_FORCE_ENABLE) || test_tsk_thread_flag(next, TIF_SSBD)) @@ -608,8 +615,6 @@ long get_tagged_addr_ctrl(void) * only prevents the tagged address ABI enabling via prctl() and does not * disable it for tasks that already opted in to the relaxed ABI. */ -static int zero; -static int one = 1; static struct ctl_table tagged_addr_sysctl_table[] = { { @@ -618,8 +623,8 @@ static struct ctl_table tagged_addr_sysctl_table[] = { .data = &tagged_addr_disabled, .maxlen = sizeof(int), .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, { } }; diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index d4ed9a19d8fe7f8a63946edbfb934bbe8d58a442..5407bf5d98ac5ec4a0a19be90bb638525b0d2325 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -958,11 +958,22 @@ void tick_broadcast(const struct cpumask *mask) } #endif +/* + * The number of CPUs online, not counting this CPU (which may not be + * fully online and so not counted in num_online_cpus()). + */ +static inline unsigned int num_other_online_cpus(void) +{ + unsigned int this_cpu_online = cpu_online(smp_processor_id()); + + return num_online_cpus() - this_cpu_online; +} + void smp_send_stop(void) { unsigned long timeout; - if (num_online_cpus() > 1) { + if (num_other_online_cpus()) { cpumask_t mask; cpumask_copy(&mask, cpu_online_mask); @@ -975,10 +986,10 @@ void smp_send_stop(void) /* Wait up to one second for other CPUs to stop */ timeout = USEC_PER_SEC; - while (num_online_cpus() > 1 && timeout--) + while (num_other_online_cpus() && timeout--) udelay(1); - if (num_online_cpus() > 1) + if (num_other_online_cpus()) pr_warn("SMP: failed to stop secondary CPUs %*pbl\n", cpumask_pr_args(cpu_online_mask)); @@ -1001,7 +1012,11 @@ void crash_smp_send_stop(void) cpus_stopped = 1; - if (num_online_cpus() == 1) { + /* + * If this cpu is the only one alive at this point in time, online or + * not, there are no stop messages to be sent around, so just back out. + */ + if (num_other_online_cpus() == 0) { sdei_mask_local_cpu(); return; } @@ -1009,7 +1024,7 @@ void crash_smp_send_stop(void) cpumask_copy(&mask, cpu_online_mask); cpumask_clear_cpu(smp_processor_id(), &mask); - atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1); + atomic_set(&waiting_for_crash_ipi, num_other_online_cpus()); pr_crit("SMP: stopping secondary CPUs\n"); smp_cross_call(&mask, IPI_CPU_CRASH_STOP); diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c index 73f06d4b3aae5317267ae372e1128d78f5b53fce..eebbc8d7123e08f1571b6b6dbfa9d74adc5c16c7 100644 --- a/arch/arm64/kernel/time.c +++ b/arch/arm64/kernel/time.c @@ -23,7 +23,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index dfe8dd1725128405a1661a946782d812695d2d15..925086b46136f3cefd629ce28a9995a21bf38b71 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -625,7 +625,7 @@ static void __hyp_text __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt) } /* Switch to the guest for VHE systems running in EL2 */ -int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) +static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *host_ctxt; struct kvm_cpu_context *guest_ctxt; @@ -678,7 +678,42 @@ int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) return exit_code; } -NOKPROBE_SYMBOL(kvm_vcpu_run_vhe); +NOKPROBE_SYMBOL(__kvm_vcpu_run_vhe); + +int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) +{ + int ret; + + local_daif_mask(); + + /* + * Having IRQs masked via PMR when entering the guest means the GIC + * will not signal the CPU of interrupts of lower priority, and the + * only way to get out will be via guest exceptions. + * Naturally, we want to avoid this. + * + * local_daif_mask() already sets GIC_PRIO_PSR_I_SET, we just need a + * dsb to ensure the redistributor is forwards EL2 IRQs to the CPU. + */ + pmr_sync(); + + ret = __kvm_vcpu_run_vhe(vcpu); + + /* + * local_daif_restore() takes care to properly restore PSTATE.DAIF + * and the GIC PMR if the host is using IRQ priorities. + */ + local_daif_restore(DAIF_PROCCTX_NOIRQ); + + /* + * When we exit from the guest we change a number of CPU configuration + * parameters, such as traps. Make sure these changes take effect + * before running the host or additional guests. + */ + isb(); + + return ret; +} /* Switch to the guest for legacy non-VHE systems */ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu) diff --git a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c index 29ee1feba4eb7de12d55d8c8a99f64e2577e73e5..4f3a087e36d51c6e53d2fedc9370b1edcdbca0c9 100644 --- a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c +++ b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c @@ -69,14 +69,14 @@ int __hyp_text __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu) u32 data = vcpu_get_reg(vcpu, rd); if (__is_be(vcpu)) { /* guest pre-swabbed data, undo this for writel() */ - data = swab32(data); + data = __kvm_swab32(data); } writel_relaxed(data, addr); } else { u32 data = readl_relaxed(addr); if (__is_be(vcpu)) { /* guest expects swabbed data */ - data = swab32(data); + data = __kvm_swab32(data); } vcpu_set_reg(vcpu, rd, data); } diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c index 8ef73e89d51485950b0bc05689c64120b8fedebc..d89bb22589f660fb34a5786a243167245d0f4754 100644 --- a/arch/arm64/mm/context.c +++ b/arch/arm64/mm/context.c @@ -260,14 +260,26 @@ asmlinkage void post_ttbr_update_workaround(void) CONFIG_CAVIUM_ERRATUM_27456)); } -static int asids_init(void) +static int asids_update_limit(void) { - asid_bits = get_cpu_asid_bits(); + unsigned long num_available_asids = NUM_USER_ASIDS; + + if (arm64_kernel_unmapped_at_el0()) + num_available_asids /= 2; /* * Expect allocation after rollover to fail if we don't have at least * one more ASID than CPUs. ASID #0 is reserved for init_mm. */ - WARN_ON(NUM_USER_ASIDS - 1 <= num_possible_cpus()); + WARN_ON(num_available_asids - 1 <= num_possible_cpus()); + pr_info("ASID allocator initialised with %lu entries\n", + num_available_asids); + return 0; +} +arch_initcall(asids_update_limit); + +static int asids_init(void) +{ + asid_bits = get_cpu_asid_bits(); atomic64_set(&asid_generation, ASID_FIRST_VERSION); asid_map = kcalloc(BITS_TO_LONGS(NUM_USER_ASIDS), sizeof(*asid_map), GFP_KERNEL); @@ -282,8 +294,6 @@ static int asids_init(void) */ if (IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0)) set_kpti_asid_bits(); - - pr_info("ASID allocator initialised with %lu entries\n", NUM_USER_ASIDS); return 0; } early_initcall(asids_init); diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig index da09c884cc305f20ba912c3b1ecd3b9ea54f8bbc..047427f71d835a6022023c7d69e7a42864d9caac 100644 --- a/arch/csky/Kconfig +++ b/arch/csky/Kconfig @@ -9,7 +9,6 @@ config CSKY select ARCH_USE_QUEUED_RWLOCKS if NR_CPUS>2 select COMMON_CLK select CLKSRC_MMIO - select CLKSRC_OF select CSKY_MPINTC if CPU_CK860 select CSKY_MP_TIMER if CPU_CK860 select CSKY_APB_INTC @@ -37,6 +36,7 @@ config CSKY select GX6605S_TIMER if CPU_CK610 select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_AUDITSYSCALL + select HAVE_COPY_THREAD_TLS select HAVE_DYNAMIC_FTRACE select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_GRAPH_TRACER @@ -47,8 +47,8 @@ config CSKY select HAVE_PERF_EVENTS select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP - select HAVE_DMA_API_DEBUG select HAVE_DMA_CONTIGUOUS + select HAVE_STACKPROTECTOR select HAVE_SYSCALL_TRACEPOINTS select MAY_HAVE_SPARSE_IRQ select MODULES_USE_ELF_RELA if MODULES @@ -59,6 +59,11 @@ config CSKY select TIMER_OF select USB_ARCH_HAS_EHCI select USB_ARCH_HAS_OHCI + select GENERIC_PCI_IOMAP + select HAVE_PCI + select PCI_DOMAINS_GENERIC if PCI + select PCI_SYSCALL if PCI + select PCI_MSI if PCI config CPU_HAS_CACHEV2 bool @@ -75,7 +80,7 @@ config CPU_HAS_TLBI config CPU_HAS_LDSTEX bool help - For SMP, CPU needs "ldex&stex" instrcutions to atomic operations. + For SMP, CPU needs "ldex&stex" instructions for atomic operations. config CPU_NEED_TLBSYNC bool @@ -188,6 +193,40 @@ config CPU_PM_STOP bool "stop" endchoice +menuconfig HAVE_TCM + bool "Tightly-Coupled/Sram Memory" + select GENERIC_ALLOCATOR + help + The implementation are not only used by TCM (Tightly-Coupled Meory) + but also used by sram on SOC bus. It follow existed linux tcm + software interface, so that old tcm application codes could be + re-used directly. + +if HAVE_TCM +config ITCM_RAM_BASE + hex "ITCM ram base" + default 0xffffffff + +config ITCM_NR_PAGES + int "Page count of ITCM size: NR*4KB" + range 1 256 + default 32 + +config HAVE_DTCM + bool "DTCM Support" + +config DTCM_RAM_BASE + hex "DTCM ram base" + depends on HAVE_DTCM + default 0xffffffff + +config DTCM_NR_PAGES + int "Page count of DTCM size: NR*4KB" + depends on HAVE_DTCM + range 1 256 + default 32 +endif + config CPU_HAS_VDSP bool "CPU has VDSP coprocessor" depends on CPU_HAS_FPU && CPU_HAS_FPUV2 @@ -196,6 +235,10 @@ config CPU_HAS_FPU bool "CPU has FPU coprocessor" depends on CPU_CK807 || CPU_CK810 || CPU_CK860 +config CPU_HAS_ICACHE_INS + bool "CPU has Icache invalidate instructions" + depends on CPU_HAS_CACHEV2 + config CPU_HAS_TEE bool "CPU has Trusted Execution Environment" depends on CPU_CK810 @@ -235,4 +278,6 @@ config HOTPLUG_CPU Say N if you want to disable CPU hotplug. endmenu +source "arch/csky/Kconfig.platforms" + source "kernel/Kconfig.hz" diff --git a/arch/csky/Kconfig.platforms b/arch/csky/Kconfig.platforms new file mode 100644 index 0000000000000000000000000000000000000000..639e17f4eacbae24c00a45d90e5a576666fded69 --- /dev/null +++ b/arch/csky/Kconfig.platforms @@ -0,0 +1,9 @@ +menu "Platform drivers selection" + +config ARCH_CSKY_DW_APB_ICTL + bool "Select dw-apb interrupt controller" + select DW_APB_ICTL + default y + help + This enables support for snps dw-apb-ictl +endmenu diff --git a/arch/csky/abiv1/inc/abi/cacheflush.h b/arch/csky/abiv1/inc/abi/cacheflush.h index 79ef9e8c1afddc1a520fb56cd2817be38e4cae4c..d3e04208d53c23e36eee552e89e484ef81d8f2c5 100644 --- a/arch/csky/abiv1/inc/abi/cacheflush.h +++ b/arch/csky/abiv1/inc/abi/cacheflush.h @@ -48,9 +48,8 @@ extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, u #define flush_icache_page(vma, page) do {} while (0); #define flush_icache_range(start, end) cache_wbinv_range(start, end) - -#define flush_icache_user_range(vma,page,addr,len) \ - flush_dcache_page(page) +#define flush_icache_mm_range(mm, start, end) cache_wbinv_range(start, end) +#define flush_icache_deferred(mm) do {} while (0); #define copy_from_user_page(vma, page, vaddr, dst, src, len) \ do { \ diff --git a/arch/csky/abiv1/inc/abi/entry.h b/arch/csky/abiv1/inc/abi/entry.h index 7ab78bd0f3b13f7e52be13445314ef956566fa73..f35a9f3315ee6f62b126eb54b46f72a90d22da41 100644 --- a/arch/csky/abiv1/inc/abi/entry.h +++ b/arch/csky/abiv1/inc/abi/entry.h @@ -16,14 +16,16 @@ #define LSAVE_A4 40 #define LSAVE_A5 44 +#define usp ss1 + .macro USPTOKSP - mtcr sp, ss1 + mtcr sp, usp mfcr sp, ss0 .endm .macro KSPTOUSP mtcr sp, ss0 - mfcr sp, ss1 + mfcr sp, usp .endm .macro SAVE_ALL epc_inc @@ -45,7 +47,13 @@ add lr, r13 stw lr, (sp, 8) + mov lr, sp + addi lr, 32 + addi lr, 32 + addi lr, 16 + bt 2f mfcr lr, ss1 +2: stw lr, (sp, 16) stw a0, (sp, 20) @@ -79,9 +87,10 @@ ldw a0, (sp, 12) mtcr a0, epsr btsti a0, 31 + bt 1f ldw a0, (sp, 16) mtcr a0, ss1 - +1: ldw a0, (sp, 24) ldw a1, (sp, 28) ldw a2, (sp, 32) @@ -102,9 +111,9 @@ addi sp, 32 addi sp, 8 - bt 1f + bt 2f KSPTOUSP -1: +2: rte .endm diff --git a/arch/csky/abiv2/cacheflush.c b/arch/csky/abiv2/cacheflush.c index 5bb887b275e1213e4e6e9e77b894a7ef490d06c7..790f1ebfba44ba925ccd94f1927b61e03137dbc6 100644 --- a/arch/csky/abiv2/cacheflush.c +++ b/arch/csky/abiv2/cacheflush.c @@ -6,46 +6,80 @@ #include #include -void flush_icache_page(struct vm_area_struct *vma, struct page *page) +void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, + pte_t *pte) { - unsigned long start; + unsigned long addr; + struct page *page; - start = (unsigned long) kmap_atomic(page); + page = pfn_to_page(pte_pfn(*pte)); + if (page == ZERO_PAGE(0)) + return; - cache_wbinv_range(start, start + PAGE_SIZE); + if (test_and_set_bit(PG_dcache_clean, &page->flags)) + return; - kunmap_atomic((void *)start); -} + addr = (unsigned long) kmap_atomic(page); -void flush_icache_user_range(struct vm_area_struct *vma, struct page *page, - unsigned long vaddr, int len) -{ - unsigned long kaddr; + dcache_wb_range(addr, addr + PAGE_SIZE); - kaddr = (unsigned long) kmap_atomic(page) + (vaddr & ~PAGE_MASK); + if (vma->vm_flags & VM_EXEC) + icache_inv_range(addr, addr + PAGE_SIZE); + + kunmap_atomic((void *) addr); +} - cache_wbinv_range(kaddr, kaddr + len); +void flush_icache_deferred(struct mm_struct *mm) +{ + unsigned int cpu = smp_processor_id(); + cpumask_t *mask = &mm->context.icache_stale_mask; - kunmap_atomic((void *)kaddr); + if (cpumask_test_cpu(cpu, mask)) { + cpumask_clear_cpu(cpu, mask); + /* + * Ensure the remote hart's writes are visible to this hart. + * This pairs with a barrier in flush_icache_mm. + */ + smp_mb(); + local_icache_inv_all(NULL); + } } -void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, - pte_t *pte) +void flush_icache_mm_range(struct mm_struct *mm, + unsigned long start, unsigned long end) { - unsigned long addr, pfn; - struct page *page; + unsigned int cpu; + cpumask_t others, *mask; - pfn = pte_pfn(*pte); - if (unlikely(!pfn_valid(pfn))) - return; + preempt_disable(); - page = pfn_to_page(pfn); - if (page == ZERO_PAGE(0)) +#ifdef CONFIG_CPU_HAS_ICACHE_INS + if (mm == current->mm) { + icache_inv_range(start, end); + preempt_enable(); return; + } +#endif - addr = (unsigned long) kmap_atomic(page); + /* Mark every hart's icache as needing a flush for this MM. */ + mask = &mm->context.icache_stale_mask; + cpumask_setall(mask); - cache_wbinv_range(addr, addr + PAGE_SIZE); + /* Flush this hart's I$ now, and mark it as flushed. */ + cpu = smp_processor_id(); + cpumask_clear_cpu(cpu, mask); + local_icache_inv_all(NULL); - kunmap_atomic((void *) addr); + /* + * Flush the I$ of other harts concurrently executing, and mark them as + * flushed. + */ + cpumask_andnot(&others, mm_cpumask(mm), cpumask_of(cpu)); + + if (mm != current->active_mm || !cpumask_empty(&others)) { + on_each_cpu_mask(&others, local_icache_inv_all, NULL, 1); + cpumask_clear(mask); + } + + preempt_enable(); } diff --git a/arch/csky/abiv2/inc/abi/cacheflush.h b/arch/csky/abiv2/inc/abi/cacheflush.h index b8db5e0b2fe3c6448907398cba030c7d9abb9223..a565e00c3f70b2e51420cf61650c59cf68c199dc 100644 --- a/arch/csky/abiv2/inc/abi/cacheflush.h +++ b/arch/csky/abiv2/inc/abi/cacheflush.h @@ -13,24 +13,27 @@ #define flush_cache_all() do { } while (0) #define flush_cache_mm(mm) do { } while (0) #define flush_cache_dup_mm(mm) do { } while (0) +#define flush_cache_range(vma, start, end) do { } while (0) +#define flush_cache_page(vma, vmaddr, pfn) do { } while (0) -#define flush_cache_range(vma, start, end) \ - do { \ - if (vma->vm_flags & VM_EXEC) \ - icache_inv_all(); \ - } while (0) +#define PG_dcache_clean PG_arch_1 + +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 +static inline void flush_dcache_page(struct page *page) +{ + if (test_bit(PG_dcache_clean, &page->flags)) + clear_bit(PG_dcache_clean, &page->flags); +} -#define flush_cache_page(vma, vmaddr, pfn) do { } while (0) -#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 -#define flush_dcache_page(page) do { } while (0) #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) +#define flush_icache_page(vma, page) do { } while (0) #define flush_icache_range(start, end) cache_wbinv_range(start, end) -void flush_icache_page(struct vm_area_struct *vma, struct page *page); -void flush_icache_user_range(struct vm_area_struct *vma, struct page *page, - unsigned long vaddr, int len); +void flush_icache_mm_range(struct mm_struct *mm, + unsigned long start, unsigned long end); +void flush_icache_deferred(struct mm_struct *mm); #define flush_cache_vmap(start, end) do { } while (0) #define flush_cache_vunmap(start, end) do { } while (0) @@ -38,7 +41,13 @@ void flush_icache_user_range(struct vm_area_struct *vma, struct page *page, #define copy_to_user_page(vma, page, vaddr, dst, src, len) \ do { \ memcpy(dst, src, len); \ - cache_wbinv_range((unsigned long)dst, (unsigned long)dst + len); \ + if (vma->vm_flags & VM_EXEC) { \ + dcache_wb_range((unsigned long)dst, \ + (unsigned long)dst + len); \ + flush_icache_mm_range(current->mm, \ + (unsigned long)dst, \ + (unsigned long)dst + len); \ + } \ } while (0) #define copy_from_user_page(vma, page, vaddr, dst, src, len) \ memcpy(dst, src, len) diff --git a/arch/csky/abiv2/inc/abi/entry.h b/arch/csky/abiv2/inc/abi/entry.h index 9897a16b45e5dcc75b4e6638a8ecd1153be661e9..94a7a58765dffe6a0b28bb1acb36bf6c380fbbb6 100644 --- a/arch/csky/abiv2/inc/abi/entry.h +++ b/arch/csky/abiv2/inc/abi/entry.h @@ -31,7 +31,13 @@ mfcr lr, epsr stw lr, (sp, 12) + btsti lr, 31 + bf 1f + addi lr, sp, 152 + br 2f +1: mfcr lr, usp +2: stw lr, (sp, 16) stw a0, (sp, 20) @@ -64,8 +70,10 @@ mtcr a0, epc ldw a0, (sp, 12) mtcr a0, epsr + btsti a0, 31 ldw a0, (sp, 16) mtcr a0, usp + mtcr a0, ss0 #ifdef CONFIG_CPU_HAS_HILO ldw a0, (sp, 140) @@ -86,6 +94,9 @@ addi sp, 40 ldm r16-r30, (sp) addi sp, 72 + bf 1f + mfcr sp, ss0 +1: rte .endm diff --git a/arch/csky/configs/defconfig b/arch/csky/configs/defconfig index 7ef42895dfb03b294c77b0f9687054cfe9d94571..af722e4dfb47d8239c969b25834e9b231a9b4244 100644 --- a/arch/csky/configs/defconfig +++ b/arch/csky/configs/defconfig @@ -10,9 +10,6 @@ CONFIG_BSD_PROCESS_ACCT=y CONFIG_BSD_PROCESS_ACCT_V3=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y -CONFIG_DEFAULT_DEADLINE=y -CONFIG_CPU_CK807=y -CONFIG_CPU_HAS_FPU=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -27,10 +24,7 @@ CONFIG_SERIAL_NONSTANDARD=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_OF_PLATFORM=y -CONFIG_TTY_PRINTK=y # CONFIG_VGA_CONSOLE is not set -CONFIG_CSKY_MPTIMER=y -CONFIG_GX6605S_TIMER=y CONFIG_PM_DEVFREQ=y CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND=y CONFIG_DEVFREQ_GOV_PERFORMANCE=y @@ -56,6 +50,4 @@ CONFIG_CRAMFS=y CONFIG_ROMFS_FS=y CONFIG_NFS_FS=y CONFIG_PRINTK_TIME=y -CONFIG_DEBUG_INFO=y -CONFIG_DEBUG_FS=y CONFIG_MAGIC_SYSRQ=y diff --git a/arch/csky/include/asm/Kbuild b/arch/csky/include/asm/Kbuild index bc15a26c782f9268fc47d1617594881d8d9bec29..4130e3eaa766711685f776b8b22cb234edce5379 100644 --- a/arch/csky/include/asm/Kbuild +++ b/arch/csky/include/asm/Kbuild @@ -28,7 +28,6 @@ generic-y += local64.h generic-y += mm-arch-hooks.h generic-y += mmiowb.h generic-y += module.h -generic-y += pci.h generic-y += percpu.h generic-y += preempt.h generic-y += qrwlock.h diff --git a/arch/csky/include/asm/cache.h b/arch/csky/include/asm/cache.h index 1d5fc2f78fd7e8c634b87e61eb9219fbc4f67ba3..4b5c09bf1d25e3a9b9720bd58f99effcdab09610 100644 --- a/arch/csky/include/asm/cache.h +++ b/arch/csky/include/asm/cache.h @@ -16,6 +16,7 @@ void dcache_wb_line(unsigned long start); void icache_inv_range(unsigned long start, unsigned long end); void icache_inv_all(void); +void local_icache_inv_all(void *priv); void dcache_wb_range(unsigned long start, unsigned long end); void dcache_wbinv_all(void); diff --git a/arch/csky/include/asm/cacheflush.h b/arch/csky/include/asm/cacheflush.h index a96da67261ae51fd67f48291489ef709874ac148..f0b8f25429a27f723c191888f624b53c0d778529 100644 --- a/arch/csky/include/asm/cacheflush.h +++ b/arch/csky/include/asm/cacheflush.h @@ -4,6 +4,7 @@ #ifndef __ASM_CSKY_CACHEFLUSH_H #define __ASM_CSKY_CACHEFLUSH_H +#include #include #endif /* __ASM_CSKY_CACHEFLUSH_H */ diff --git a/arch/csky/include/asm/fixmap.h b/arch/csky/include/asm/fixmap.h index 380ff0a307df02095f1585d021984a7167007b2b..81f9477d5330c95e2c964294fb782a5aea3aeaf0 100644 --- a/arch/csky/include/asm/fixmap.h +++ b/arch/csky/include/asm/fixmap.h @@ -5,12 +5,16 @@ #define __ASM_CSKY_FIXMAP_H #include +#include #ifdef CONFIG_HIGHMEM #include #include #endif enum fixed_addresses { +#ifdef CONFIG_HAVE_TCM + FIX_TCM = TCM_NR_PAGES, +#endif #ifdef CONFIG_HIGHMEM FIX_KMAP_BEGIN, FIX_KMAP_END = FIX_KMAP_BEGIN + (KM_TYPE_NR * NR_CPUS) - 1, @@ -18,10 +22,13 @@ enum fixed_addresses { __end_of_fixed_addresses }; -#define FIXADDR_TOP 0xffffc000 #define FIXADDR_SIZE (__end_of_fixed_addresses << PAGE_SHIFT) #define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) #include +extern void fixrange_init(unsigned long start, unsigned long end, + pgd_t *pgd_base); +extern void __init fixaddr_init(void); + #endif /* __ASM_CSKY_FIXMAP_H */ diff --git a/arch/csky/include/asm/memory.h b/arch/csky/include/asm/memory.h new file mode 100644 index 0000000000000000000000000000000000000000..a65c6759f53753307774b38d7e22d02939f6bde5 --- /dev/null +++ b/arch/csky/include/asm/memory.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __ASM_CSKY_MEMORY_H +#define __ASM_CSKY_MEMORY_H + +#include +#include +#include +#include + +#define FIXADDR_TOP _AC(0xffffc000, UL) +#define PKMAP_BASE _AC(0xff800000, UL) +#define VMALLOC_START _AC(0xc0008000, UL) +#define VMALLOC_END (PKMAP_BASE - (PAGE_SIZE * 2)) + +#ifdef CONFIG_HAVE_TCM +#ifdef CONFIG_HAVE_DTCM +#define TCM_NR_PAGES (CONFIG_ITCM_NR_PAGES + CONFIG_DTCM_NR_PAGES) +#else +#define TCM_NR_PAGES (CONFIG_ITCM_NR_PAGES) +#endif +#define FIXADDR_TCM _AC(FIXADDR_TOP - (TCM_NR_PAGES * PAGE_SIZE), UL) +#endif + +#endif diff --git a/arch/csky/include/asm/mmu.h b/arch/csky/include/asm/mmu.h index b382a14ea4ec72535393b4a6962b1f1020ab0b7e..26fbb1d15df08ea711f73efe26b39bc356312cc0 100644 --- a/arch/csky/include/asm/mmu.h +++ b/arch/csky/include/asm/mmu.h @@ -7,6 +7,7 @@ typedef struct { atomic64_t asid; void *vdso; + cpumask_t icache_stale_mask; } mm_context_t; #endif /* __ASM_CSKY_MMU_H */ diff --git a/arch/csky/include/asm/mmu_context.h b/arch/csky/include/asm/mmu_context.h index 0285b0ad18b6f2bce9276396461f9a1ffc2ed2f2..abdf1f1cb6ec991248ac17d7dc63881c479616ef 100644 --- a/arch/csky/include/asm/mmu_context.h +++ b/arch/csky/include/asm/mmu_context.h @@ -43,5 +43,7 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next, TLBMISS_HANDLER_SETUP_PGD(next->pgd); write_mmu_entryhi(next->context.asid.counter); + + flush_icache_deferred(next); } #endif /* __ASM_CSKY_MMU_CONTEXT_H */ diff --git a/arch/csky/include/asm/pci.h b/arch/csky/include/asm/pci.h new file mode 100644 index 0000000000000000000000000000000000000000..ebc765b1f78b5f1f71b9eded7da3f60d2fcf25e1 --- /dev/null +++ b/arch/csky/include/asm/pci.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __ASM_CSKY_PCI_H +#define __ASM_CSKY_PCI_H + +#include +#include +#include + +#include + +#define PCIBIOS_MIN_IO 0 +#define PCIBIOS_MIN_MEM 0 + +/* C-SKY shim does not initialize PCI bus */ +#define pcibios_assign_all_busses() 1 + +extern int isa_dma_bridge_buggy; + +#ifdef CONFIG_PCI +static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel) +{ + /* no legacy IRQ on csky */ + return -ENODEV; +} + +static inline int pci_proc_domain(struct pci_bus *bus) +{ + /* always show the domain in /proc */ + return 1; +} +#endif /* CONFIG_PCI */ + +#endif /* __ASM_CSKY_PCI_H */ diff --git a/arch/csky/include/asm/pgtable.h b/arch/csky/include/asm/pgtable.h index 4b2a41e15f2e4231b0c1905eb3ec38628359fe33..9b7764cb76450f8d205e0996047d2866ae55d0eb 100644 --- a/arch/csky/include/asm/pgtable.h +++ b/arch/csky/include/asm/pgtable.h @@ -5,6 +5,7 @@ #define __ASM_CSKY_PGTABLE_H #include +#include #include #include #include @@ -16,11 +17,6 @@ #define USER_PTRS_PER_PGD (0x80000000UL/PGDIR_SIZE) #define FIRST_USER_ADDRESS 0UL -#define PKMAP_BASE (0xff800000) - -#define VMALLOC_START (0xc0008000) -#define VMALLOC_END (PKMAP_BASE - 2*PAGE_SIZE) - /* * C-SKY is two-level paging structure: */ diff --git a/arch/csky/include/asm/stackprotector.h b/arch/csky/include/asm/stackprotector.h new file mode 100644 index 0000000000000000000000000000000000000000..d7cd4e51edd965e0a3a67e62214074b799be701c --- /dev/null +++ b/arch/csky/include/asm/stackprotector.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_STACKPROTECTOR_H +#define _ASM_STACKPROTECTOR_H 1 + +#include +#include + +extern unsigned long __stack_chk_guard; + +/* + * Initialize the stackprotector canary value. + * + * NOTE: this must only be called from functions that never return, + * and it must always be inlined. + */ +static __always_inline void boot_init_stack_canary(void) +{ + unsigned long canary; + + /* Try to get a semi random initial value. */ + get_random_bytes(&canary, sizeof(canary)); + canary ^= LINUX_VERSION_CODE; + canary &= CANARY_MASK; + + current->stack_canary = canary; + __stack_chk_guard = current->stack_canary; +} + +#endif /* __ASM_SH_STACKPROTECTOR_H */ diff --git a/arch/csky/include/asm/tcm.h b/arch/csky/include/asm/tcm.h new file mode 100644 index 0000000000000000000000000000000000000000..2b135cefb73f2f49684cd5e9b92f403740f21a37 --- /dev/null +++ b/arch/csky/include/asm/tcm.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __ASM_CSKY_TCM_H +#define __ASM_CSKY_TCM_H + +#ifndef CONFIG_HAVE_TCM +#error "You should not be including tcm.h unless you have a TCM!" +#endif + +#include + +/* Tag variables with this */ +#define __tcmdata __section(.tcm.data) +/* Tag constants with this */ +#define __tcmconst __section(.tcm.rodata) +/* Tag functions inside TCM called from outside TCM with this */ +#define __tcmfunc __section(.tcm.text) noinline +/* Tag function inside TCM called from inside TCM with this */ +#define __tcmlocalfunc __section(.tcm.text) + +void *tcm_alloc(size_t len); +void tcm_free(void *addr, size_t len); + +#endif diff --git a/arch/csky/include/uapi/asm/unistd.h b/arch/csky/include/uapi/asm/unistd.h index 211c983c7282d13f3b75150e686c8e815fd7777b..ba40189297338d1de36b9cff54d76f0746b344c6 100644 --- a/arch/csky/include/uapi/asm/unistd.h +++ b/arch/csky/include/uapi/asm/unistd.h @@ -1,7 +1,10 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ // Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd. +#define __ARCH_WANT_STAT64 +#define __ARCH_WANT_NEW_STAT #define __ARCH_WANT_SYS_CLONE +#define __ARCH_WANT_SYS_CLONE3 #define __ARCH_WANT_SET_GET_RLIMIT #define __ARCH_WANT_TIME32_SYSCALLS #include diff --git a/arch/csky/kernel/atomic.S b/arch/csky/kernel/atomic.S index 5b84f11485aeb8c6794699c54250cf8c54f5a91d..3821ef9b75672d8a5af90839ffa7f95cfdb4da50 100644 --- a/arch/csky/kernel/atomic.S +++ b/arch/csky/kernel/atomic.S @@ -17,10 +17,12 @@ ENTRY(csky_cmpxchg) mfcr a3, epc addi a3, TRAP0_SIZE - subi sp, 8 + subi sp, 16 stw a3, (sp, 0) mfcr a3, epsr stw a3, (sp, 4) + mfcr a3, usp + stw a3, (sp, 8) psrset ee #ifdef CONFIG_CPU_HAS_LDSTEX @@ -47,7 +49,9 @@ ENTRY(csky_cmpxchg) mtcr a3, epc ldw a3, (sp, 4) mtcr a3, epsr - addi sp, 8 + ldw a3, (sp, 8) + mtcr a3, usp + addi sp, 16 KSPTOUSP rte END(csky_cmpxchg) diff --git a/arch/csky/kernel/process.c b/arch/csky/kernel/process.c index f320d9248a225fe31941129ccd2b4225c47f36d1..f7b231ca269a0dbc2b5fd76dbffcb5429fb01c6d 100644 --- a/arch/csky/kernel/process.c +++ b/arch/csky/kernel/process.c @@ -16,6 +16,12 @@ struct cpuinfo_csky cpu_data[NR_CPUS]; +#ifdef CONFIG_STACKPROTECTOR +#include +unsigned long __stack_chk_guard __read_mostly; +EXPORT_SYMBOL(__stack_chk_guard); +#endif + asmlinkage void ret_from_fork(void); asmlinkage void ret_from_kernel_thread(void); @@ -34,10 +40,11 @@ unsigned long thread_saved_pc(struct task_struct *tsk) return sw->r15; } -int copy_thread(unsigned long clone_flags, +int copy_thread_tls(unsigned long clone_flags, unsigned long usp, unsigned long kthread_arg, - struct task_struct *p) + struct task_struct *p, + unsigned long tls) { struct switch_stack *childstack; struct pt_regs *childregs = task_pt_regs(p); @@ -64,7 +71,7 @@ int copy_thread(unsigned long clone_flags, childregs->usp = usp; if (clone_flags & CLONE_SETTLS) task_thread_info(p)->tp_value = childregs->tls - = childregs->regs[0]; + = tls; childregs->a0 = 0; childstack->r15 = (unsigned long) ret_from_fork; diff --git a/arch/csky/kernel/setup.c b/arch/csky/kernel/setup.c index 52eaf31ba27fc95a44f8e4ce377d776110ad1142..3821e55742f46f0070688f1e81161aefb8760f5c 100644 --- a/arch/csky/kernel/setup.c +++ b/arch/csky/kernel/setup.c @@ -47,9 +47,6 @@ static void __init csky_memblock_init(void) signed long size; memblock_reserve(__pa(_stext), _end - _stext); -#ifdef CONFIG_BLK_DEV_INITRD - memblock_reserve(__pa(initrd_start), initrd_end - initrd_start); -#endif early_init_fdt_reserve_self(); early_init_fdt_scan_reserved_mem(); @@ -133,6 +130,8 @@ void __init setup_arch(char **cmdline_p) sparse_init(); + fixaddr_init(); + #ifdef CONFIG_HIGHMEM kmap_init(); #endif diff --git a/arch/csky/kernel/smp.c b/arch/csky/kernel/smp.c index b753d382e4cef53f45350e1108518096934d826a..0bb0954d557090c359b7e80bd30957ad0826b196 100644 --- a/arch/csky/kernel/smp.c +++ b/arch/csky/kernel/smp.c @@ -120,7 +120,7 @@ void __init setup_smp_ipi(void) int rc; if (ipi_irq == 0) - panic("%s IRQ mapping failed\n", __func__); + return; rc = request_percpu_irq(ipi_irq, handle_ipi, "IPI Interrupt", &ipi_dummy_dev); diff --git a/arch/csky/kernel/time.c b/arch/csky/kernel/time.c index b5fc9447d93f2307f892ec0afa9fbda3e59a0294..52379d866fe45f2839afdcbca2216224fd455d33 100644 --- a/arch/csky/kernel/time.c +++ b/arch/csky/kernel/time.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd. -#include #include +#include void __init time_init(void) { diff --git a/arch/csky/kernel/vmlinux.lds.S b/arch/csky/kernel/vmlinux.lds.S index 2ff37beaf2bf38af39db8c44f58554e832f9909e..f05b413df32849f6000834e2445c1dbb194cdfc7 100644 --- a/arch/csky/kernel/vmlinux.lds.S +++ b/arch/csky/kernel/vmlinux.lds.S @@ -2,6 +2,7 @@ #include #include +#include OUTPUT_ARCH(csky) ENTRY(_start) @@ -53,6 +54,54 @@ SECTIONS RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE) _edata = .; +#ifdef CONFIG_HAVE_TCM + .tcm_start : { + . = ALIGN(PAGE_SIZE); + __tcm_start = .; + } + + .text_data_tcm FIXADDR_TCM : AT(__tcm_start) + { + . = ALIGN(4); + __stcm_text_data = .; + *(.tcm.text) + *(.tcm.rodata) +#ifndef CONFIG_HAVE_DTCM + *(.tcm.data) +#endif + . = ALIGN(4); + __etcm_text_data = .; + } + + . = ADDR(.tcm_start) + SIZEOF(.tcm_start) + SIZEOF(.text_data_tcm); + +#ifdef CONFIG_HAVE_DTCM + #define ITCM_SIZE CONFIG_ITCM_NR_PAGES * PAGE_SIZE + + .dtcm_start : { + __dtcm_start = .; + } + + .data_tcm FIXADDR_TCM + ITCM_SIZE : AT(__dtcm_start) + { + . = ALIGN(4); + __stcm_data = .; + *(.tcm.data) + . = ALIGN(4); + __etcm_data = .; + } + + . = ADDR(.dtcm_start) + SIZEOF(.data_tcm); + + .tcm_end : AT(ADDR(.dtcm_start) + SIZEOF(.data_tcm)) { +#else + .tcm_end : AT(ADDR(.tcm_start) + SIZEOF(.text_data_tcm)) { +#endif + . = ALIGN(PAGE_SIZE); + __tcm_end = .; + } +#endif + EXCEPTION_TABLE(L1_CACHE_BYTES) BSS_SECTION(L1_CACHE_BYTES, PAGE_SIZE, L1_CACHE_BYTES) VBR_BASE diff --git a/arch/csky/mm/Makefile b/arch/csky/mm/Makefile index c94ef648109865e5662edeb1a61c9685426340fa..6e7696e55f71131dd1fde113ecdf177bbe01844c 100644 --- a/arch/csky/mm/Makefile +++ b/arch/csky/mm/Makefile @@ -1,8 +1,10 @@ # SPDX-License-Identifier: GPL-2.0-only ifeq ($(CONFIG_CPU_HAS_CACHEV2),y) obj-y += cachev2.o +CFLAGS_REMOVE_cachev2.o = $(CC_FLAGS_FTRACE) else obj-y += cachev1.o +CFLAGS_REMOVE_cachev1.o = $(CC_FLAGS_FTRACE) endif obj-y += dma-mapping.o @@ -14,3 +16,4 @@ obj-y += syscache.o obj-y += tlb.o obj-y += asid.o obj-y += context.o +obj-$(CONFIG_HAVE_TCM) += tcm.o diff --git a/arch/csky/mm/cachev1.c b/arch/csky/mm/cachev1.c index 494ec912abff072ed0a85ba6d6c2b313a27001f2..5a5a9804a0e3d468baa2ff7444d91265d35f9783 100644 --- a/arch/csky/mm/cachev1.c +++ b/arch/csky/mm/cachev1.c @@ -94,6 +94,11 @@ void icache_inv_all(void) cache_op_all(INS_CACHE|CACHE_INV, 0); } +void local_icache_inv_all(void *priv) +{ + cache_op_all(INS_CACHE|CACHE_INV, 0); +} + void dcache_wb_range(unsigned long start, unsigned long end) { cache_op_range(start, end, DATA_CACHE|CACHE_CLR, 0); diff --git a/arch/csky/mm/cachev2.c b/arch/csky/mm/cachev2.c index b61be6518e214bbed8d8704a6d36b76d1520f479..bc419f8039d3144ddaa14d7e9a1a6352869c9970 100644 --- a/arch/csky/mm/cachev2.c +++ b/arch/csky/mm/cachev2.c @@ -3,15 +3,25 @@ #include #include +#include #include #include -inline void dcache_wb_line(unsigned long start) +#define INS_CACHE (1 << 0) +#define CACHE_INV (1 << 4) + +void local_icache_inv_all(void *priv) { - asm volatile("dcache.cval1 %0\n"::"r"(start):"memory"); + mtcr("cr17", INS_CACHE|CACHE_INV); sync_is(); } +void icache_inv_all(void) +{ + on_each_cpu(local_icache_inv_all, NULL, 1); +} + +#ifdef CONFIG_CPU_HAS_ICACHE_INS void icache_inv_range(unsigned long start, unsigned long end) { unsigned long i = start & ~(L1_CACHE_BYTES - 1); @@ -20,43 +30,32 @@ void icache_inv_range(unsigned long start, unsigned long end) asm volatile("icache.iva %0\n"::"r"(i):"memory"); sync_is(); } - -void icache_inv_all(void) +#else +void icache_inv_range(unsigned long start, unsigned long end) { - asm volatile("icache.ialls\n":::"memory"); - sync_is(); + icache_inv_all(); } +#endif -void dcache_wb_range(unsigned long start, unsigned long end) +inline void dcache_wb_line(unsigned long start) { - unsigned long i = start & ~(L1_CACHE_BYTES - 1); - - for (; i < end; i += L1_CACHE_BYTES) - asm volatile("dcache.cval1 %0\n"::"r"(i):"memory"); + asm volatile("dcache.cval1 %0\n"::"r"(start):"memory"); sync_is(); } -void dcache_inv_range(unsigned long start, unsigned long end) +void dcache_wb_range(unsigned long start, unsigned long end) { unsigned long i = start & ~(L1_CACHE_BYTES - 1); for (; i < end; i += L1_CACHE_BYTES) - asm volatile("dcache.civa %0\n"::"r"(i):"memory"); + asm volatile("dcache.cval1 %0\n"::"r"(i):"memory"); sync_is(); } void cache_wbinv_range(unsigned long start, unsigned long end) { - unsigned long i = start & ~(L1_CACHE_BYTES - 1); - - for (; i < end; i += L1_CACHE_BYTES) - asm volatile("dcache.cval1 %0\n"::"r"(i):"memory"); - sync_is(); - - i = start & ~(L1_CACHE_BYTES - 1); - for (; i < end; i += L1_CACHE_BYTES) - asm volatile("icache.iva %0\n"::"r"(i):"memory"); - sync_is(); + dcache_wb_range(start, end); + icache_inv_range(start, end); } EXPORT_SYMBOL(cache_wbinv_range); diff --git a/arch/csky/mm/highmem.c b/arch/csky/mm/highmem.c index 3317b774f6dc145eae07b562689d975404279bb9..813129145f3da77c87a516f2f33bf48d8592ed18 100644 --- a/arch/csky/mm/highmem.c +++ b/arch/csky/mm/highmem.c @@ -117,85 +117,29 @@ struct page *kmap_atomic_to_page(void *ptr) return pte_page(*pte); } -static void __init fixrange_init(unsigned long start, unsigned long end, - pgd_t *pgd_base) +static void __init kmap_pages_init(void) { -#ifdef CONFIG_HIGHMEM - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - int i, j, k; unsigned long vaddr; - - vaddr = start; - i = __pgd_offset(vaddr); - j = __pud_offset(vaddr); - k = __pmd_offset(vaddr); - pgd = pgd_base + i; - - for ( ; (i < PTRS_PER_PGD) && (vaddr != end); pgd++, i++) { - pud = (pud_t *)pgd; - for ( ; (j < PTRS_PER_PUD) && (vaddr != end); pud++, j++) { - pmd = (pmd_t *)pud; - for (; (k < PTRS_PER_PMD) && (vaddr != end); pmd++, k++) { - if (pmd_none(*pmd)) { - pte = (pte_t *) memblock_alloc_low(PAGE_SIZE, PAGE_SIZE); - if (!pte) - panic("%s: Failed to allocate %lu bytes align=%lx\n", - __func__, PAGE_SIZE, - PAGE_SIZE); - - set_pmd(pmd, __pmd(__pa(pte))); - BUG_ON(pte != pte_offset_kernel(pmd, 0)); - } - vaddr += PMD_SIZE; - } - k = 0; - } - j = 0; - } -#endif -} - -void __init fixaddr_kmap_pages_init(void) -{ - unsigned long vaddr; - pgd_t *pgd_base; -#ifdef CONFIG_HIGHMEM pgd_t *pgd; pmd_t *pmd; pud_t *pud; pte_t *pte; -#endif - pgd_base = swapper_pg_dir; - - /* - * Fixed mappings: - */ - vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK; - fixrange_init(vaddr, 0, pgd_base); - -#ifdef CONFIG_HIGHMEM - /* - * Permanent kmaps: - */ + vaddr = PKMAP_BASE; - fixrange_init(vaddr, vaddr + PAGE_SIZE*LAST_PKMAP, pgd_base); + fixrange_init(vaddr, vaddr + PAGE_SIZE*LAST_PKMAP, swapper_pg_dir); pgd = swapper_pg_dir + __pgd_offset(vaddr); pud = (pud_t *)pgd; pmd = pmd_offset(pud, vaddr); pte = pte_offset_kernel(pmd, vaddr); pkmap_page_table = pte; -#endif } void __init kmap_init(void) { unsigned long vaddr; - fixaddr_kmap_pages_init(); + kmap_pages_init(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN); diff --git a/arch/csky/mm/init.c b/arch/csky/mm/init.c index d4c2292ea46bc6cf0825c6af3b9499338577d329..cb64d8647a78b3eb9529b962e6267361e3c15897 100644 --- a/arch/csky/mm/init.c +++ b/arch/csky/mm/init.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -31,10 +32,50 @@ pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_bss; pte_t invalid_pte_table[PTRS_PER_PTE] __page_aligned_bss; +EXPORT_SYMBOL(invalid_pte_table); unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss; EXPORT_SYMBOL(empty_zero_page); +#ifdef CONFIG_BLK_DEV_INITRD +static void __init setup_initrd(void) +{ + unsigned long size; + + if (initrd_start >= initrd_end) { + pr_err("initrd not found or empty"); + goto disable; + } + + if (__pa(initrd_end) > PFN_PHYS(max_low_pfn)) { + pr_err("initrd extends beyond end of memory"); + goto disable; + } + + size = initrd_end - initrd_start; + + if (memblock_is_region_reserved(__pa(initrd_start), size)) { + pr_err("INITRD: 0x%08lx+0x%08lx overlaps in-use memory region", + __pa(initrd_start), size); + goto disable; + } + + memblock_reserve(__pa(initrd_start), size); + + pr_info("Initial ramdisk at: 0x%p (%lu bytes)\n", + (void *)(initrd_start), size); + + initrd_below_start_ok = 1; + + return; + +disable: + initrd_start = initrd_end = 0; + + pr_err(" - disabling initrd\n"); +} +#endif + void __init mem_init(void) { #ifdef CONFIG_HIGHMEM @@ -46,6 +87,10 @@ void __init mem_init(void) #endif high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT); +#ifdef CONFIG_BLK_DEV_INITRD + setup_initrd(); +#endif + memblock_free_all(); #ifdef CONFIG_HIGHMEM @@ -101,3 +146,50 @@ void __init pre_mmu_init(void) /* Setup page mask to 4k */ write_mmu_pagemask(0); } + +void __init fixrange_init(unsigned long start, unsigned long end, + pgd_t *pgd_base) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + int i, j, k; + unsigned long vaddr; + + vaddr = start; + i = __pgd_offset(vaddr); + j = __pud_offset(vaddr); + k = __pmd_offset(vaddr); + pgd = pgd_base + i; + + for ( ; (i < PTRS_PER_PGD) && (vaddr != end); pgd++, i++) { + pud = (pud_t *)pgd; + for ( ; (j < PTRS_PER_PUD) && (vaddr != end); pud++, j++) { + pmd = (pmd_t *)pud; + for (; (k < PTRS_PER_PMD) && (vaddr != end); pmd++, k++) { + if (pmd_none(*pmd)) { + pte = (pte_t *) memblock_alloc_low(PAGE_SIZE, PAGE_SIZE); + if (!pte) + panic("%s: Failed to allocate %lu bytes align=%lx\n", + __func__, PAGE_SIZE, + PAGE_SIZE); + + set_pmd(pmd, __pmd(__pa(pte))); + BUG_ON(pte != pte_offset_kernel(pmd, 0)); + } + vaddr += PMD_SIZE; + } + k = 0; + } + j = 0; + } +} + +void __init fixaddr_init(void) +{ + unsigned long vaddr; + + vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK; + fixrange_init(vaddr, vaddr + PMD_SIZE, swapper_pg_dir); +} diff --git a/arch/csky/mm/syscache.c b/arch/csky/mm/syscache.c index c4645e4e97f4b70d4cc23be29f20cd3aaaff5db0..ffade2f9a4c87914af5c8322fdfc1b9600a204c1 100644 --- a/arch/csky/mm/syscache.c +++ b/arch/csky/mm/syscache.c @@ -3,7 +3,7 @@ #include #include -#include +#include #include SYSCALL_DEFINE3(cacheflush, @@ -13,17 +13,14 @@ SYSCALL_DEFINE3(cacheflush, { switch (cache) { case ICACHE: - icache_inv_range((unsigned long)addr, - (unsigned long)addr + bytes); - break; + case BCACHE: + flush_icache_mm_range(current->mm, + (unsigned long)addr, + (unsigned long)addr + bytes); case DCACHE: dcache_wb_range((unsigned long)addr, (unsigned long)addr + bytes); break; - case BCACHE: - cache_wbinv_range((unsigned long)addr, - (unsigned long)addr + bytes); - break; default: return -EINVAL; } diff --git a/arch/csky/mm/tcm.c b/arch/csky/mm/tcm.c new file mode 100644 index 0000000000000000000000000000000000000000..ddeb36328819960ac275ca1febf13fc4ad628677 --- /dev/null +++ b/arch/csky/mm/tcm.c @@ -0,0 +1,169 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include +#include + +#if (CONFIG_ITCM_RAM_BASE == 0xffffffff) +#error "You should define ITCM_RAM_BASE" +#endif + +#ifdef CONFIG_HAVE_DTCM +#if (CONFIG_DTCM_RAM_BASE == 0xffffffff) +#error "You should define DTCM_RAM_BASE" +#endif + +#if (CONFIG_DTCM_RAM_BASE == CONFIG_ITCM_RAM_BASE) +#error "You should define correct DTCM_RAM_BASE" +#endif +#endif + +extern char __tcm_start, __tcm_end, __dtcm_start; + +static struct gen_pool *tcm_pool; + +static void __init tcm_mapping_init(void) +{ + pte_t *tcm_pte; + unsigned long vaddr, paddr; + int i; + + paddr = CONFIG_ITCM_RAM_BASE; + + if (pfn_valid(PFN_DOWN(CONFIG_ITCM_RAM_BASE))) + goto panic; + +#ifndef CONFIG_HAVE_DTCM + for (i = 0; i < TCM_NR_PAGES; i++) { +#else + for (i = 0; i < CONFIG_ITCM_NR_PAGES; i++) { +#endif + vaddr = __fix_to_virt(FIX_TCM - i); + + tcm_pte = + pte_offset_kernel((pmd_t *)pgd_offset_k(vaddr), vaddr); + + set_pte(tcm_pte, pfn_pte(__phys_to_pfn(paddr), PAGE_KERNEL)); + + flush_tlb_one(vaddr); + + paddr = paddr + PAGE_SIZE; + } + +#ifdef CONFIG_HAVE_DTCM + if (pfn_valid(PFN_DOWN(CONFIG_DTCM_RAM_BASE))) + goto panic; + + paddr = CONFIG_DTCM_RAM_BASE; + + for (i = 0; i < CONFIG_DTCM_NR_PAGES; i++) { + vaddr = __fix_to_virt(FIX_TCM - CONFIG_ITCM_NR_PAGES - i); + + tcm_pte = + pte_offset_kernel((pmd_t *) pgd_offset_k(vaddr), vaddr); + + set_pte(tcm_pte, pfn_pte(__phys_to_pfn(paddr), PAGE_KERNEL)); + + flush_tlb_one(vaddr); + + paddr = paddr + PAGE_SIZE; + } +#endif + +#ifndef CONFIG_HAVE_DTCM + memcpy((void *)__fix_to_virt(FIX_TCM), + &__tcm_start, &__tcm_end - &__tcm_start); + + pr_info("%s: mapping tcm va:0x%08lx to pa:0x%08x\n", + __func__, __fix_to_virt(FIX_TCM), CONFIG_ITCM_RAM_BASE); + + pr_info("%s: __tcm_start va:0x%08lx size:%d\n", + __func__, (unsigned long)&__tcm_start, &__tcm_end - &__tcm_start); +#else + memcpy((void *)__fix_to_virt(FIX_TCM), + &__tcm_start, &__dtcm_start - &__tcm_start); + + pr_info("%s: mapping itcm va:0x%08lx to pa:0x%08x\n", + __func__, __fix_to_virt(FIX_TCM), CONFIG_ITCM_RAM_BASE); + + pr_info("%s: __itcm_start va:0x%08lx size:%d\n", + __func__, (unsigned long)&__tcm_start, &__dtcm_start - &__tcm_start); + + memcpy((void *)__fix_to_virt(FIX_TCM - CONFIG_ITCM_NR_PAGES), + &__dtcm_start, &__tcm_end - &__dtcm_start); + + pr_info("%s: mapping dtcm va:0x%08lx to pa:0x%08x\n", + __func__, __fix_to_virt(FIX_TCM - CONFIG_ITCM_NR_PAGES), + CONFIG_DTCM_RAM_BASE); + + pr_info("%s: __dtcm_start va:0x%08lx size:%d\n", + __func__, (unsigned long)&__dtcm_start, &__tcm_end - &__dtcm_start); + +#endif + return; +panic: + panic("TCM init error"); +} + +void *tcm_alloc(size_t len) +{ + unsigned long vaddr; + + if (!tcm_pool) + return NULL; + + vaddr = gen_pool_alloc(tcm_pool, len); + if (!vaddr) + return NULL; + + return (void *) vaddr; +} +EXPORT_SYMBOL(tcm_alloc); + +void tcm_free(void *addr, size_t len) +{ + gen_pool_free(tcm_pool, (unsigned long) addr, len); +} +EXPORT_SYMBOL(tcm_free); + +static int __init tcm_setup_pool(void) +{ +#ifndef CONFIG_HAVE_DTCM + u32 pool_size = (u32) (TCM_NR_PAGES * PAGE_SIZE) + - (u32) (&__tcm_end - &__tcm_start); + + u32 tcm_pool_start = __fix_to_virt(FIX_TCM) + + (u32) (&__tcm_end - &__tcm_start); +#else + u32 pool_size = (u32) (CONFIG_DTCM_NR_PAGES * PAGE_SIZE) + - (u32) (&__tcm_end - &__dtcm_start); + + u32 tcm_pool_start = __fix_to_virt(FIX_TCM - CONFIG_ITCM_NR_PAGES) + + (u32) (&__tcm_end - &__dtcm_start); +#endif + int ret; + + tcm_pool = gen_pool_create(2, -1); + + ret = gen_pool_add(tcm_pool, tcm_pool_start, pool_size, -1); + if (ret) { + pr_err("%s: gen_pool add failed!\n", __func__); + return ret; + } + + pr_info("%s: Added %d bytes @ 0x%08x to memory pool\n", + __func__, pool_size, tcm_pool_start); + + return 0; +} + +static int __init tcm_init(void) +{ + tcm_mapping_init(); + + tcm_setup_pool(); + + return 0; +} +arch_initcall(tcm_init); diff --git a/arch/mips/boot/dts/ingenic/ci20.dts b/arch/mips/boot/dts/ingenic/ci20.dts index 37b93166bf22d17947aa878657d269d84bbdd097..c340f947baa03a4d5e0cb8e0f79a3a72aeccd4e8 100644 --- a/arch/mips/boot/dts/ingenic/ci20.dts +++ b/arch/mips/boot/dts/ingenic/ci20.dts @@ -4,6 +4,8 @@ #include "jz4780.dtsi" #include #include +#include +#include / { compatible = "img,ci20", "ingenic,jz4780"; @@ -163,63 +165,71 @@ act8600: act8600@5a { regulators { vddcore: SUDCDC1 { - regulator-name = "VDDCORE"; + regulator-name = "DCDC_REG1"; regulator-min-microvolt = <1100000>; regulator-max-microvolt = <1100000>; regulator-always-on; }; vddmem: SUDCDC2 { - regulator-name = "VDDMEM"; + regulator-name = "DCDC_REG2"; regulator-min-microvolt = <1500000>; regulator-max-microvolt = <1500000>; regulator-always-on; }; vcc_33: SUDCDC3 { - regulator-name = "VCC33"; + regulator-name = "DCDC_REG3"; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; regulator-always-on; }; vcc_50: SUDCDC4 { - regulator-name = "VCC50"; + regulator-name = "SUDCDC_REG4"; regulator-min-microvolt = <5000000>; regulator-max-microvolt = <5000000>; regulator-always-on; }; vcc_25: LDO_REG5 { - regulator-name = "VCC25"; + regulator-name = "LDO_REG5"; regulator-min-microvolt = <2500000>; regulator-max-microvolt = <2500000>; regulator-always-on; }; wifi_io: LDO_REG6 { - regulator-name = "WIFIIO"; + regulator-name = "LDO_REG6"; regulator-min-microvolt = <2500000>; regulator-max-microvolt = <2500000>; regulator-always-on; }; vcc_28: LDO_REG7 { - regulator-name = "VCC28"; + regulator-name = "LDO_REG7"; regulator-min-microvolt = <2800000>; regulator-max-microvolt = <2800000>; regulator-always-on; }; vcc_15: LDO_REG8 { - regulator-name = "VCC15"; + regulator-name = "LDO_REG8"; regulator-min-microvolt = <1500000>; regulator-max-microvolt = <1500000>; regulator-always-on; }; - vcc_18: LDO_REG9 { - regulator-name = "VCC18"; - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <1800000>; + vrtc_18: LDO_REG9 { + regulator-name = "LDO_REG9"; + /* Despite the datasheet stating 3.3V + * for REG9 and the driver expecting that, + * REG9 outputs 1.8V. + * Likely the CI20 uses a proprietary + * factory programmed chip variant. + * Since this is a simple on/off LDO the + * exact values do not matter. + */ + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; regulator-always-on; }; vcc_11: LDO_REG10 { - regulator-name = "VCC11"; - regulator-min-microvolt = <1100000>; - regulator-max-microvolt = <1100000>; + regulator-name = "LDO_REG10"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; regulator-always-on; }; }; @@ -261,7 +271,9 @@ &i2c4 { rtc@51 { compatible = "nxp,pcf8563"; reg = <0x51>; - interrupts = <110>; + + interrupt-parent = <&gpf>; + interrupts = <30 IRQ_TYPE_LEVEL_LOW>; }; }; diff --git a/arch/mips/boot/dts/ingenic/jz4740.dtsi b/arch/mips/boot/dts/ingenic/jz4740.dtsi index 5accda2767bea4d641116206dc470c8b34775a9b..a3301bab9231ae4a2f65859c5713f1b746b7239d 100644 --- a/arch/mips/boot/dts/ingenic/jz4740.dtsi +++ b/arch/mips/boot/dts/ingenic/jz4740.dtsi @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include +#include / { #address-cells = <1>; @@ -45,14 +46,6 @@ cgu: jz4740-cgu@10000000 { #clock-cells = <1>; }; - watchdog: watchdog@10002000 { - compatible = "ingenic,jz4740-watchdog"; - reg = <0x10002000 0x10>; - - clocks = <&cgu JZ4740_CLK_RTC>; - clock-names = "rtc"; - }; - tcu: timer@10002000 { compatible = "ingenic,jz4740-tcu", "simple-mfd"; reg = <0x10002000 0x1000>; @@ -73,6 +66,14 @@ &cgu JZ4740_CLK_PCLK interrupt-parent = <&intc>; interrupts = <23 22 21>; + + watchdog: watchdog@0 { + compatible = "ingenic,jz4740-watchdog"; + reg = <0x0 0xc>; + + clocks = <&tcu TCU_CLK_WDT>; + clock-names = "wdt"; + }; }; rtc_dev: rtc@10003000 { diff --git a/arch/mips/boot/dts/ingenic/jz4780.dtsi b/arch/mips/boot/dts/ingenic/jz4780.dtsi index f928329b034b374de13a9d1e0570824a2e7d92c4..bb89653d16a321ab4bb9d136b96bff8eb8d0b2d0 100644 --- a/arch/mips/boot/dts/ingenic/jz4780.dtsi +++ b/arch/mips/boot/dts/ingenic/jz4780.dtsi @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include +#include #include / { @@ -67,6 +68,14 @@ &cgu JZ4780_CLK_EXCLK interrupt-parent = <&intc>; interrupts = <27 26 25>; + + watchdog: watchdog@0 { + compatible = "ingenic,jz4780-watchdog"; + reg = <0x0 0xc>; + + clocks = <&tcu TCU_CLK_WDT>; + clock-names = "wdt"; + }; }; rtc_dev: rtc@10003000 { @@ -348,14 +357,6 @@ i2c4: i2c@10054000 { status = "disabled"; }; - watchdog: watchdog@10002000 { - compatible = "ingenic,jz4780-watchdog"; - reg = <0x10002000 0x10>; - - clocks = <&cgu JZ4780_CLK_RTCLK>; - clock-names = "rtc"; - }; - nemc: nemc@13410000 { compatible = "ingenic,jz4780-nemc"; reg = <0x13410000 0x10000>; diff --git a/arch/mips/boot/dts/ingenic/x1000.dtsi b/arch/mips/boot/dts/ingenic/x1000.dtsi index 4994c695a1a73ba0bf0b4ca3dd5d3a4591ea75c7..147f7d5c243a2fe5c6cfc3a639f5e4c3299fa7ea 100644 --- a/arch/mips/boot/dts/ingenic/x1000.dtsi +++ b/arch/mips/boot/dts/ingenic/x1000.dtsi @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include #include #include @@ -72,7 +73,7 @@ wdt: watchdog@0 { compatible = "ingenic,x1000-watchdog", "ingenic,jz4780-watchdog"; reg = <0x0 0x10>; - clocks = <&cgu X1000_CLK_RTCLK>; + clocks = <&tcu TCU_CLK_WDT>; clock-names = "wdt"; }; }; @@ -158,7 +159,6 @@ gpd: gpio@3 { i2c0: i2c-controller@10050000 { compatible = "ingenic,x1000-i2c"; reg = <0x10050000 0x1000>; - #address-cells = <1>; #size-cells = <0>; @@ -173,7 +173,6 @@ i2c0: i2c-controller@10050000 { i2c1: i2c-controller@10051000 { compatible = "ingenic,x1000-i2c"; reg = <0x10051000 0x1000>; - #address-cells = <1>; #size-cells = <0>; @@ -188,7 +187,6 @@ i2c1: i2c-controller@10051000 { i2c2: i2c-controller@10052000 { compatible = "ingenic,x1000-i2c"; reg = <0x10052000 0x1000>; - #address-cells = <1>; #size-cells = <0>; diff --git a/arch/mips/include/asm/sync.h b/arch/mips/include/asm/sync.h index 7c6a1095f556268700909ba31b5b24c1b6d9dc6a..aabd097933fe97f599361dd002d6e9f2fcdd999b 100644 --- a/arch/mips/include/asm/sync.h +++ b/arch/mips/include/asm/sync.h @@ -155,9 +155,11 @@ * effective barrier as noted by commit 6b07d38aaa52 ("MIPS: Octeon: Use * optimized memory barrier primitives."). Here we specify that the affected * sync instructions should be emitted twice. + * Note that this expression is evaluated by the assembler (not the compiler), + * and that the assembler evaluates '==' as 0 or -1, not 0 or 1. */ #ifdef CONFIG_CPU_CAVIUM_OCTEON -# define __SYNC_rpt(type) (1 + (type == __SYNC_wmb)) +# define __SYNC_rpt(type) (1 - (type == __SYNC_wmb)) #else # define __SYNC_rpt(type) 1 #endif diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 1ac2752fb7919ea26fb1caf5470ea3887887beb0..a7b469d89e2cc5e9679136d48a582356d56e0398 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -605,7 +605,8 @@ static void __init bootcmdline_init(char **cmdline_p) * If we're configured to take boot arguments from DT, look for those * now. */ - if (IS_ENABLED(CONFIG_MIPS_CMDLINE_FROM_DTB)) + if (IS_ENABLED(CONFIG_MIPS_CMDLINE_FROM_DTB) || + IS_ENABLED(CONFIG_MIPS_CMDLINE_DTB_EXTEND)) of_scan_flat_dt(bootcmdline_scan_chosen, &dt_bootargs); #endif diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c index 6176b9acba950e7189c48752498a9bb79f3648ad..d0d832ab3d3b86192b57c30f2c8c9e90820965ea 100644 --- a/arch/mips/kernel/vpe.c +++ b/arch/mips/kernel/vpe.c @@ -134,7 +134,7 @@ void release_vpe(struct vpe *v) { list_del(&v->list); if (v->load_addr) - release_progmem(v); + release_progmem(v->load_addr); kfree(v); } diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile index aa89a41dc5dddef97aa080366aa47eb743dfe0eb..d7fe8408603e85583e013337e5df1c87d9ada7cb 100644 --- a/arch/mips/vdso/Makefile +++ b/arch/mips/vdso/Makefile @@ -33,6 +33,7 @@ endif cflags-vdso := $(ccflags-vdso) \ $(filter -W%,$(filter-out -Wa$(comma)%,$(KBUILD_CFLAGS))) \ -O3 -g -fPIC -fno-strict-aliasing -fno-common -fno-builtin -G 0 \ + -mrelax-pic-calls $(call cc-option, -mexplicit-relocs) \ -fno-stack-protector -fno-jump-tables -DDISABLE_BRANCH_PROFILING \ $(call cc-option, -fno-asynchronous-unwind-tables) \ $(call cc-option, -fno-stack-protector) @@ -51,6 +52,8 @@ endif CFLAGS_REMOVE_vgettimeofday.o = -pg +DISABLE_VDSO := n + # # For the pre-R6 code in arch/mips/vdso/vdso.h for locating # the base address of VDSO, the linker will emit a R_MIPS_PC32 @@ -64,11 +67,24 @@ CFLAGS_REMOVE_vgettimeofday.o = -pg ifndef CONFIG_CPU_MIPSR6 ifeq ($(call ld-ifversion, -lt, 225000000, y),y) $(warning MIPS VDSO requires binutils >= 2.25) - obj-vdso-y := $(filter-out vgettimeofday.o, $(obj-vdso-y)) - ccflags-vdso += -DDISABLE_MIPS_VDSO + DISABLE_VDSO := y endif endif +# +# GCC (at least up to version 9.2) appears to emit function calls that make use +# of the GOT when targeting microMIPS, which we can't use in the VDSO due to +# the lack of relocations. As such, we disable the VDSO for microMIPS builds. +# +ifdef CONFIG_CPU_MICROMIPS + DISABLE_VDSO := y +endif + +ifeq ($(DISABLE_VDSO),y) + obj-vdso-y := $(filter-out vgettimeofday.o, $(obj-vdso-y)) + ccflags-vdso += -DDISABLE_MIPS_VDSO +endif + # VDSO linker flags. VDSO_LDFLAGS := \ -Wl,-Bsymbolic -Wl,--no-undefined -Wl,-soname=linux-vdso.so.1 \ @@ -81,12 +97,18 @@ GCOV_PROFILE := n UBSAN_SANITIZE := n KCOV_INSTRUMENT := n +# Check that we don't have PIC 'jalr t9' calls left +quiet_cmd_vdso_mips_check = VDSOCHK $@ + cmd_vdso_mips_check = if $(OBJDUMP) --disassemble $@ | egrep -h "jalr.*t9" > /dev/null; \ + then (echo >&2 "$@: PIC 'jalr t9' calls are not supported"; \ + rm -f $@; /bin/false); fi + # # Shared build commands. # quiet_cmd_vdsold_and_vdso_check = LD $@ - cmd_vdsold_and_vdso_check = $(cmd_vdsold); $(cmd_vdso_check) + cmd_vdsold_and_vdso_check = $(cmd_vdsold); $(cmd_vdso_check); $(cmd_vdso_mips_check) quiet_cmd_vdsold = VDSO $@ cmd_vdsold = $(CC) $(c_flags) $(VDSO_LDFLAGS) \ diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index 86332080399a57d461c3a0efbd1ac2b3debeb9ab..080a0bf8e54bb9cd6267e38adacb2dc15150b401 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -295,8 +295,13 @@ static inline bool pfn_valid(unsigned long pfn) /* * Some number of bits at the level of the page table that points to * a hugepte are used to encode the size. This masks those bits. + * On 8xx, HW assistance requires 4k alignment for the hugepte. */ +#ifdef CONFIG_PPC_8xx +#define HUGEPD_SHIFT_MASK 0xfff +#else #define HUGEPD_SHIFT_MASK 0x3f +#endif #ifndef __ASSEMBLY__ diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 8387698bd5b629692fc676143e39202ed7b47f66..eedcbfb9a6ff38d874b027c2d639519b83ebba24 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -168,6 +168,10 @@ struct thread_struct { unsigned long srr1; unsigned long dar; unsigned long dsisr; +#ifdef CONFIG_PPC_BOOK3S_32 + unsigned long r0, r3, r4, r5, r6, r8, r9, r11; + unsigned long lr, ctr; +#endif #endif /* Debug Registers */ struct debug_reg debug; diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index c25e562f1cd9d3f1d4fdf93b70bc2f698c2c4427..fcf24a365fc014b0490c957a16c8a9bfd55fc2fd 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -132,6 +132,18 @@ int main(void) OFFSET(SRR1, thread_struct, srr1); OFFSET(DAR, thread_struct, dar); OFFSET(DSISR, thread_struct, dsisr); +#ifdef CONFIG_PPC_BOOK3S_32 + OFFSET(THR0, thread_struct, r0); + OFFSET(THR3, thread_struct, r3); + OFFSET(THR4, thread_struct, r4); + OFFSET(THR5, thread_struct, r5); + OFFSET(THR6, thread_struct, r6); + OFFSET(THR8, thread_struct, r8); + OFFSET(THR9, thread_struct, r9); + OFFSET(THR11, thread_struct, r11); + OFFSET(THLR, thread_struct, lr); + OFFSET(THCTR, thread_struct, ctr); +#endif #endif #ifdef CONFIG_SPE OFFSET(THREAD_EVR0, thread_struct, evr[0]); diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index e745abc5457a0bb5f0560a695f00a7925ff29386..245be4fafe134a95c468ee7086ce2f985231dd3e 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -2193,11 +2193,13 @@ static struct cpu_spec * __init setup_cpu_spec(unsigned long offset, * oprofile_cpu_type already has a value, then we are * possibly overriding a real PVR with a logical one, * and, in that case, keep the current value for - * oprofile_cpu_type. + * oprofile_cpu_type. Futhermore, let's ensure that the + * fix for the PMAO bug is enabled on compatibility mode. */ if (old.oprofile_cpu_type != NULL) { t->oprofile_cpu_type = old.oprofile_cpu_type; t->oprofile_type = old.oprofile_type; + t->cpu_features |= old.cpu_features & CPU_FTR_PMAO_BUG; } } diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index a1eaffe868de4d76cbb8c401ddb175671e336ef4..7b048cee767c746fefe8a75cb991fb94fe757164 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -1184,6 +1184,17 @@ void eeh_handle_special_event(void) eeh_pe_state_mark(pe, EEH_PE_RECOVERING); eeh_handle_normal_event(pe); } else { + eeh_for_each_pe(pe, tmp_pe) + eeh_pe_for_each_dev(tmp_pe, edev, tmp_edev) + edev->mode &= ~EEH_DEV_NO_HANDLER; + + /* Notify all devices to be down */ + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true); + eeh_set_channel_state(pe, pci_channel_io_perm_failure); + eeh_pe_report( + "error_detected(permanent failure)", pe, + eeh_report_failure, NULL); + pci_lock_rescan_remove(); list_for_each_entry(hose, &hose_list, list_node) { phb_pe = eeh_phb_pe_get(hose); @@ -1192,16 +1203,6 @@ void eeh_handle_special_event(void) (phb_pe->state & EEH_PE_RECOVERING)) continue; - eeh_for_each_pe(pe, tmp_pe) - eeh_pe_for_each_dev(tmp_pe, edev, tmp_edev) - edev->mode &= ~EEH_DEV_NO_HANDLER; - - /* Notify all devices to be down */ - eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true); - eeh_set_channel_state(pe, pci_channel_io_perm_failure); - eeh_pe_report( - "error_detected(permanent failure)", pe, - eeh_report_failure, NULL); bus = eeh_pe_bus_get(phb_pe); if (!bus) { pr_err("%s: Cannot find PCI bus for " diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 0713daa651d9e469b2acedfea00d15f12ce6be70..16af0d8d90a8641ae2d43b29cef9d691a08f06e2 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -783,7 +783,7 @@ fast_exception_return: 1: lis r3,exc_exit_restart_end@ha addi r3,r3,exc_exit_restart_end@l cmplw r12,r3 -#if CONFIG_PPC_BOOK3S_601 +#ifdef CONFIG_PPC_BOOK3S_601 bge 2b #else bge 3f @@ -791,7 +791,7 @@ fast_exception_return: lis r4,exc_exit_restart@ha addi r4,r4,exc_exit_restart@l cmplw r12,r4 -#if CONFIG_PPC_BOOK3S_601 +#ifdef CONFIG_PPC_BOOK3S_601 blt 2b #else blt 3f @@ -1354,12 +1354,17 @@ _GLOBAL(enter_rtas) mtspr SPRN_SRR0,r8 mtspr SPRN_SRR1,r9 RFI -1: tophys(r9,r1) +1: tophys_novmstack r9, r1 +#ifdef CONFIG_VMAP_STACK + li r0, MSR_KERNEL & ~MSR_IR /* can take DTLB miss */ + mtmsr r0 + isync +#endif lwz r8,INT_FRAME_SIZE+4(r9) /* get return address */ lwz r9,8(r9) /* original msr value */ addi r1,r1,INT_FRAME_SIZE li r0,0 - tophys(r7, r2) + tophys_novmstack r7, r2 stw r0, THREAD + RTAS_SP(r7) mtspr SPRN_SRR0,r8 mtspr SPRN_SRR1,r9 diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index 0493fcac6409508394932ea267e2f28c2f690f32..97c887950c3ca19d3156b8cc1e7aca6ceaef79f7 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -290,17 +290,55 @@ MachineCheck: 7: EXCEPTION_PROLOG_2 addi r3,r1,STACK_FRAME_OVERHEAD #ifdef CONFIG_PPC_CHRP - bne cr1,1f +#ifdef CONFIG_VMAP_STACK + mfspr r4, SPRN_SPRG_THREAD + tovirt(r4, r4) + lwz r4, RTAS_SP(r4) + cmpwi cr1, r4, 0 #endif - EXC_XFER_STD(0x200, machine_check_exception) -#ifdef CONFIG_PPC_CHRP -1: b machine_check_in_rtas + beq cr1, machine_check_tramp + b machine_check_in_rtas +#else + b machine_check_tramp #endif /* Data access exception. */ . = 0x300 DO_KVM 0x300 DataAccess: +#ifdef CONFIG_VMAP_STACK + mtspr SPRN_SPRG_SCRATCH0,r10 + mfspr r10, SPRN_SPRG_THREAD +BEGIN_MMU_FTR_SECTION + stw r11, THR11(r10) + mfspr r10, SPRN_DSISR + mfcr r11 +#ifdef CONFIG_PPC_KUAP + andis. r10, r10, (DSISR_BAD_FAULT_32S | DSISR_DABRMATCH | DSISR_PROTFAULT)@h +#else + andis. r10, r10, (DSISR_BAD_FAULT_32S | DSISR_DABRMATCH)@h +#endif + mfspr r10, SPRN_SPRG_THREAD + beq hash_page_dsi +.Lhash_page_dsi_cont: + mtcr r11 + lwz r11, THR11(r10) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) + mtspr SPRN_SPRG_SCRATCH1,r11 + mfspr r11, SPRN_DAR + stw r11, DAR(r10) + mfspr r11, SPRN_DSISR + stw r11, DSISR(r10) + mfspr r11, SPRN_SRR0 + stw r11, SRR0(r10) + mfspr r11, SPRN_SRR1 /* check whether user or kernel */ + stw r11, SRR1(r10) + mfcr r10 + andi. r11, r11, MSR_PR + + EXCEPTION_PROLOG_1 + b handle_page_fault_tramp_1 +#else /* CONFIG_VMAP_STACK */ EXCEPTION_PROLOG handle_dar_dsisr=1 get_and_save_dar_dsisr_on_stack r4, r5, r11 BEGIN_MMU_FTR_SECTION @@ -316,11 +354,32 @@ BEGIN_MMU_FTR_SECTION FTR_SECTION_ELSE b handle_page_fault_tramp_2 ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_HPTE_TABLE) +#endif /* CONFIG_VMAP_STACK */ /* Instruction access exception. */ . = 0x400 DO_KVM 0x400 InstructionAccess: +#ifdef CONFIG_VMAP_STACK + mtspr SPRN_SPRG_SCRATCH0,r10 + mtspr SPRN_SPRG_SCRATCH1,r11 + mfspr r10, SPRN_SPRG_THREAD + mfspr r11, SPRN_SRR0 + stw r11, SRR0(r10) + mfspr r11, SPRN_SRR1 /* check whether user or kernel */ + stw r11, SRR1(r10) + mfcr r10 +BEGIN_MMU_FTR_SECTION + andis. r11, r11, SRR1_ISI_NOPT@h /* no pte found? */ + bne hash_page_isi +.Lhash_page_isi_cont: + mfspr r11, SPRN_SRR1 /* check whether user or kernel */ +END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) + andi. r11, r11, MSR_PR + + EXCEPTION_PROLOG_1 + EXCEPTION_PROLOG_2 +#else /* CONFIG_VMAP_STACK */ EXCEPTION_PROLOG andis. r0,r9,SRR1_ISI_NOPT@h /* no pte found? */ beq 1f /* if so, try to put a PTE */ @@ -329,6 +388,7 @@ InstructionAccess: BEGIN_MMU_FTR_SECTION bl hash_page END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) +#endif /* CONFIG_VMAP_STACK */ 1: mr r4,r12 andis. r5,r9,DSISR_SRR1_MATCH_32S@h /* Filter relevant SRR1 bits */ stw r4, _DAR(r11) @@ -344,7 +404,7 @@ Alignment: EXCEPTION_PROLOG handle_dar_dsisr=1 save_dar_dsisr_on_stack r4, r5, r11 addi r3,r1,STACK_FRAME_OVERHEAD - EXC_XFER_STD(0x600, alignment_exception) + b alignment_exception_tramp /* Program check exception */ EXCEPTION(0x700, ProgramCheck, program_check_exception, EXC_XFER_STD) @@ -645,15 +705,100 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_NEED_DTLB_SW_LRU) . = 0x3000 +machine_check_tramp: + EXC_XFER_STD(0x200, machine_check_exception) + +alignment_exception_tramp: + EXC_XFER_STD(0x600, alignment_exception) + handle_page_fault_tramp_1: +#ifdef CONFIG_VMAP_STACK + EXCEPTION_PROLOG_2 handle_dar_dsisr=1 +#endif lwz r4, _DAR(r11) lwz r5, _DSISR(r11) /* fall through */ handle_page_fault_tramp_2: EXC_XFER_LITE(0x300, handle_page_fault) +#ifdef CONFIG_VMAP_STACK +.macro save_regs_thread thread + stw r0, THR0(\thread) + stw r3, THR3(\thread) + stw r4, THR4(\thread) + stw r5, THR5(\thread) + stw r6, THR6(\thread) + stw r8, THR8(\thread) + stw r9, THR9(\thread) + mflr r0 + stw r0, THLR(\thread) + mfctr r0 + stw r0, THCTR(\thread) +.endm + +.macro restore_regs_thread thread + lwz r0, THLR(\thread) + mtlr r0 + lwz r0, THCTR(\thread) + mtctr r0 + lwz r0, THR0(\thread) + lwz r3, THR3(\thread) + lwz r4, THR4(\thread) + lwz r5, THR5(\thread) + lwz r6, THR6(\thread) + lwz r8, THR8(\thread) + lwz r9, THR9(\thread) +.endm + +hash_page_dsi: + save_regs_thread r10 + mfdsisr r3 + mfdar r4 + mfsrr0 r5 + mfsrr1 r9 + rlwinm r3, r3, 32 - 15, _PAGE_RW /* DSISR_STORE -> _PAGE_RW */ + bl hash_page + mfspr r10, SPRN_SPRG_THREAD + restore_regs_thread r10 + b .Lhash_page_dsi_cont + +hash_page_isi: + mr r11, r10 + mfspr r10, SPRN_SPRG_THREAD + save_regs_thread r10 + li r3, 0 + lwz r4, SRR0(r10) + lwz r9, SRR1(r10) + bl hash_page + mfspr r10, SPRN_SPRG_THREAD + restore_regs_thread r10 + mr r10, r11 + b .Lhash_page_isi_cont + + .globl fast_hash_page_return +fast_hash_page_return: + andis. r10, r9, SRR1_ISI_NOPT@h /* Set on ISI, cleared on DSI */ + mfspr r10, SPRN_SPRG_THREAD + restore_regs_thread r10 + bne 1f + + /* DSI */ + mtcr r11 + lwz r11, THR11(r10) + mfspr r10, SPRN_SPRG_SCRATCH0 + SYNC + RFI + +1: /* ISI */ + mtcr r11 + mfspr r11, SPRN_SPRG_SCRATCH1 + mfspr r10, SPRN_SPRG_SCRATCH0 + SYNC + RFI + stack_overflow: vmap_stack_overflow_exception +#endif AltiVecUnavailable: EXCEPTION_PROLOG diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h index a6a5fbbf8504ae3cd5d5104076cec9358873dabb..9db162f79fe6e650fd61be32dd80bda9ea844f08 100644 --- a/arch/powerpc/kernel/head_32.h +++ b/arch/powerpc/kernel/head_32.h @@ -64,11 +64,25 @@ .endm .macro EXCEPTION_PROLOG_2 handle_dar_dsisr=0 +#if defined(CONFIG_VMAP_STACK) && defined(CONFIG_PPC_BOOK3S) +BEGIN_MMU_FTR_SECTION + mtcr r10 +FTR_SECTION_ELSE + stw r10, _CCR(r11) +ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_HPTE_TABLE) +#else stw r10,_CCR(r11) /* save registers */ +#endif + mfspr r10, SPRN_SPRG_SCRATCH0 stw r12,GPR12(r11) stw r9,GPR9(r11) - mfspr r10,SPRN_SPRG_SCRATCH0 stw r10,GPR10(r11) +#if defined(CONFIG_VMAP_STACK) && defined(CONFIG_PPC_BOOK3S) +BEGIN_MMU_FTR_SECTION + mfcr r10 + stw r10, _CCR(r11) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) +#endif mfspr r12,SPRN_SPRG_SCRATCH1 stw r12,GPR11(r11) mflr r10 @@ -83,6 +97,11 @@ stw r10, _DSISR(r11) .endif lwz r9, SRR1(r12) +#if defined(CONFIG_VMAP_STACK) && defined(CONFIG_PPC_BOOK3S) +BEGIN_MMU_FTR_SECTION + andi. r10, r9, MSR_PR +END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) +#endif lwz r12, SRR0(r12) #else mfspr r12,SPRN_SRR0 diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 9922306ae51244f9dcd0ed1f2f3ffac4603aabee..073a651787df8ab65847aa428fa1d9216d57a231 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -256,7 +256,7 @@ InstructionTLBMiss: * set. All other Linux PTE bits control the behavior * of the MMU. */ - rlwimi r10, r10, 0, 0x0f00 /* Clear bits 20-23 */ + rlwinm r10, r10, 0, ~0x0f00 /* Clear bits 20-23 */ rlwimi r10, r10, 4, 0x0400 /* Copy _PAGE_EXEC into bit 21 */ ori r10, r10, RPN_PATTERN | 0x200 /* Set 22 and 24-27 */ mtspr SPRN_MI_RPN, r10 /* Update TLB entry */ diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 2462cd7c565c6053f4866447b148ab0b7b3391c9..d0854320bb50fdd65eadbadb50ffcddc0bedc592 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -331,11 +331,13 @@ int hw_breakpoint_handler(struct die_args *args) } info->type &= ~HW_BRK_TYPE_EXTRANEOUS_IRQ; - if (!dar_within_range(regs->dar, info)) - info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ; - - if (!IS_ENABLED(CONFIG_PPC_8xx) && !stepping_handler(regs, bp, info)) - goto out; + if (IS_ENABLED(CONFIG_PPC_8xx)) { + if (!dar_within_range(regs->dar, info)) + info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ; + } else { + if (!stepping_handler(regs, bp, info)) + goto out; + } /* * As a policy, the callback is invoked in a 'trigger-after-execute' diff --git a/arch/powerpc/kernel/idle_6xx.S b/arch/powerpc/kernel/idle_6xx.S index 0ffdd18b9f268b2b75f3c305505deb89fb6d09de..433d97bea1f3b8eb2e7554c317c9600a41d53b08 100644 --- a/arch/powerpc/kernel/idle_6xx.S +++ b/arch/powerpc/kernel/idle_6xx.S @@ -166,7 +166,11 @@ BEGIN_FTR_SECTION mfspr r9,SPRN_HID0 andis. r9,r9,HID0_NAP@h beq 1f +#ifdef CONFIG_VMAP_STACK + addis r9, r11, nap_save_msscr0@ha +#else addis r9,r11,(nap_save_msscr0-KERNELBASE)@ha +#endif lwz r9,nap_save_msscr0@l(r9) mtspr SPRN_MSSCR0, r9 sync @@ -174,7 +178,11 @@ BEGIN_FTR_SECTION 1: END_FTR_SECTION_IFSET(CPU_FTR_NAP_DISABLE_L2_PR) BEGIN_FTR_SECTION +#ifdef CONFIG_VMAP_STACK + addis r9, r11, nap_save_hid1@ha +#else addis r9,r11,(nap_save_hid1-KERNELBASE)@ha +#endif lwz r9,nap_save_hid1@l(r9) mtspr SPRN_HID1, r9 END_FTR_SECTION_IFSET(CPU_FTR_DUAL_PLL_750FX) diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index e6c30cee6abf1748e52fe5a4ae9a0fbc01c3274a..d215f95545537ababac1eb849baab01df0e1642a 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -200,14 +200,27 @@ unsigned long get_tm_stackpointer(struct task_struct *tsk) * normal/non-checkpointed stack pointer. */ + unsigned long ret = tsk->thread.regs->gpr[1]; + #ifdef CONFIG_PPC_TRANSACTIONAL_MEM BUG_ON(tsk != current); if (MSR_TM_ACTIVE(tsk->thread.regs->msr)) { + preempt_disable(); tm_reclaim_current(TM_CAUSE_SIGNAL); if (MSR_TM_TRANSACTIONAL(tsk->thread.regs->msr)) - return tsk->thread.ckpt_regs.gpr[1]; + ret = tsk->thread.ckpt_regs.gpr[1]; + + /* + * If we treclaim, we must clear the current thread's TM bits + * before re-enabling preemption. Otherwise we might be + * preempted and have the live MSR[TS] changed behind our back + * (tm_recheckpoint_new_task() would recheckpoint). Besides, we + * enter the signal handler in non-transactional state. + */ + tsk->thread.regs->msr &= ~MSR_TS_MASK; + preempt_enable(); } #endif - return tsk->thread.regs->gpr[1]; + return ret; } diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 98600b276f764d957fe5f8d91386c921a288cc90..1b090a76b4444729c4b8614b72277c1643539e92 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -489,19 +489,11 @@ static int save_user_regs(struct pt_regs *regs, struct mcontext __user *frame, */ static int save_tm_user_regs(struct pt_regs *regs, struct mcontext __user *frame, - struct mcontext __user *tm_frame, int sigret) + struct mcontext __user *tm_frame, int sigret, + unsigned long msr) { - unsigned long msr = regs->msr; - WARN_ON(tm_suspend_disabled); - /* Remove TM bits from thread's MSR. The MSR in the sigcontext - * just indicates to userland that we were doing a transaction, but we - * don't want to return in transactional state. This also ensures - * that flush_fp_to_thread won't set TIF_RESTORE_TM again. - */ - regs->msr &= ~MSR_TS_MASK; - /* Save both sets of general registers */ if (save_general_regs(¤t->thread.ckpt_regs, frame) || save_general_regs(regs, tm_frame)) @@ -912,6 +904,10 @@ int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset, int sigret; unsigned long tramp; struct pt_regs *regs = tsk->thread.regs; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* Save the thread's msr before get_tm_stackpointer() changes it */ + unsigned long msr = regs->msr; +#endif BUG_ON(tsk != current); @@ -944,13 +940,13 @@ int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset, #ifdef CONFIG_PPC_TRANSACTIONAL_MEM tm_frame = &rt_sf->uc_transact.uc_mcontext; - if (MSR_TM_ACTIVE(regs->msr)) { + if (MSR_TM_ACTIVE(msr)) { if (__put_user((unsigned long)&rt_sf->uc_transact, &rt_sf->uc.uc_link) || __put_user((unsigned long)tm_frame, &rt_sf->uc_transact.uc_regs)) goto badframe; - if (save_tm_user_regs(regs, frame, tm_frame, sigret)) + if (save_tm_user_regs(regs, frame, tm_frame, sigret, msr)) goto badframe; } else @@ -1369,6 +1365,10 @@ int handle_signal32(struct ksignal *ksig, sigset_t *oldset, int sigret; unsigned long tramp; struct pt_regs *regs = tsk->thread.regs; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* Save the thread's msr before get_tm_stackpointer() changes it */ + unsigned long msr = regs->msr; +#endif BUG_ON(tsk != current); @@ -1402,9 +1402,9 @@ int handle_signal32(struct ksignal *ksig, sigset_t *oldset, #ifdef CONFIG_PPC_TRANSACTIONAL_MEM tm_mctx = &frame->mctx_transact; - if (MSR_TM_ACTIVE(regs->msr)) { + if (MSR_TM_ACTIVE(msr)) { if (save_tm_user_regs(regs, &frame->mctx, &frame->mctx_transact, - sigret)) + sigret, msr)) goto badframe; } else diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 117515564ec7a6e2d13ecdeba37e3973934fba10..84ed2e77ef9c3f5e039cf8f65921b5124e0bb226 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -192,7 +192,8 @@ static long setup_sigcontext(struct sigcontext __user *sc, static long setup_tm_sigcontexts(struct sigcontext __user *sc, struct sigcontext __user *tm_sc, struct task_struct *tsk, - int signr, sigset_t *set, unsigned long handler) + int signr, sigset_t *set, unsigned long handler, + unsigned long msr) { /* When CONFIG_ALTIVEC is set, we _always_ setup v_regs even if the * process never used altivec yet (MSR_VEC is zero in pt_regs of @@ -207,12 +208,11 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc, elf_vrreg_t __user *tm_v_regs = sigcontext_vmx_regs(tm_sc); #endif struct pt_regs *regs = tsk->thread.regs; - unsigned long msr = tsk->thread.regs->msr; long err = 0; BUG_ON(tsk != current); - BUG_ON(!MSR_TM_ACTIVE(regs->msr)); + BUG_ON(!MSR_TM_ACTIVE(msr)); WARN_ON(tm_suspend_disabled); @@ -222,13 +222,6 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc, */ msr |= tsk->thread.ckpt_regs.msr & (MSR_FP | MSR_VEC | MSR_VSX); - /* Remove TM bits from thread's MSR. The MSR in the sigcontext - * just indicates to userland that we were doing a transaction, but we - * don't want to return in transactional state. This also ensures - * that flush_fp_to_thread won't set TIF_RESTORE_TM again. - */ - regs->msr &= ~MSR_TS_MASK; - #ifdef CONFIG_ALTIVEC err |= __put_user(v_regs, &sc->v_regs); err |= __put_user(tm_v_regs, &tm_sc->v_regs); @@ -824,6 +817,10 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, unsigned long newsp = 0; long err = 0; struct pt_regs *regs = tsk->thread.regs; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* Save the thread's msr before get_tm_stackpointer() changes it */ + unsigned long msr = regs->msr; +#endif BUG_ON(tsk != current); @@ -841,7 +838,7 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, err |= __put_user(0, &frame->uc.uc_flags); err |= __save_altstack(&frame->uc.uc_stack, regs->gpr[1]); #ifdef CONFIG_PPC_TRANSACTIONAL_MEM - if (MSR_TM_ACTIVE(regs->msr)) { + if (MSR_TM_ACTIVE(msr)) { /* The ucontext_t passed to userland points to the second * ucontext_t (for transactional state) with its uc_link ptr. */ @@ -849,7 +846,8 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, err |= setup_tm_sigcontexts(&frame->uc.uc_mcontext, &frame->uc_transact.uc_mcontext, tsk, ksig->sig, NULL, - (unsigned long)ksig->ka.sa.sa_handler); + (unsigned long)ksig->ka.sa.sa_handler, + msr); } else #endif { diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index b4c89a1acebb83b75b1151e1a29aae89704f66ed..a32d478a7f41de22c1841262790ca60fc72ca376 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -303,6 +303,12 @@ SECTIONS *(.branch_lt) } +#ifdef CONFIG_DEBUG_INFO_BTF + .BTF : AT(ADDR(.BTF) - LOAD_OFFSET) { + *(.BTF) + } +#endif + .opd : AT(ADDR(.opd) - LOAD_OFFSET) { __start_opd = .; KEEP(*(.opd)) diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 729a0f12a752f659ed56b9ffc4a5199418838083..db3a87319642af9bc145ee54458a68aea3e2d34d 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -1817,6 +1817,7 @@ static void kvmppc_core_vcpu_free_pr(struct kvm_vcpu *vcpu) { struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu); + kvmppc_mmu_destroy_pr(vcpu); free_page((unsigned long)vcpu->arch.shared & PAGE_MASK); #ifdef CONFIG_KVM_BOOK3S_32_HANDLER kfree(vcpu->arch.shadow_vcpu); diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 1af96fb5dc6fbedb7e03aa0a97ff4b06159f262e..302e9dccdd6d79ae8d945c4d730aae4ca036c277 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -759,7 +759,6 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) return 0; out_vcpu_uninit: - kvmppc_mmu_destroy(vcpu); kvmppc_subarch_vcpu_uninit(vcpu); return err; } @@ -792,7 +791,6 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) kvmppc_core_vcpu_free(vcpu); - kvmppc_mmu_destroy(vcpu); kvmppc_subarch_vcpu_uninit(vcpu); } diff --git a/arch/powerpc/mm/book3s32/hash_low.S b/arch/powerpc/mm/book3s32/hash_low.S index c11b0a005196675271839c20a9a0c89cf2253f13..2015c4f962380940700d84bcc32af9d4961b80ea 100644 --- a/arch/powerpc/mm/book3s32/hash_low.S +++ b/arch/powerpc/mm/book3s32/hash_low.S @@ -25,12 +25,6 @@ #include #include -#ifdef CONFIG_VMAP_STACK -#define ADDR_OFFSET 0 -#else -#define ADDR_OFFSET PAGE_OFFSET -#endif - #ifdef CONFIG_SMP .section .bss .align 2 @@ -53,8 +47,8 @@ mmu_hash_lock: .text _GLOBAL(hash_page) #ifdef CONFIG_SMP - lis r8, (mmu_hash_lock - ADDR_OFFSET)@h - ori r8, r8, (mmu_hash_lock - ADDR_OFFSET)@l + lis r8, (mmu_hash_lock - PAGE_OFFSET)@h + ori r8, r8, (mmu_hash_lock - PAGE_OFFSET)@l lis r0,0x0fff b 10f 11: lwz r6,0(r8) @@ -72,12 +66,9 @@ _GLOBAL(hash_page) cmplw 0,r4,r0 ori r3,r3,_PAGE_USER|_PAGE_PRESENT /* test low addresses as user */ mfspr r5, SPRN_SPRG_PGDIR /* phys page-table root */ -#ifdef CONFIG_VMAP_STACK - tovirt(r5, r5) -#endif blt+ 112f /* assume user more likely */ - lis r5, (swapper_pg_dir - ADDR_OFFSET)@ha /* if kernel address, use */ - addi r5 ,r5 ,(swapper_pg_dir - ADDR_OFFSET)@l /* kernel page table */ + lis r5, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */ + addi r5 ,r5 ,(swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */ rlwimi r3,r9,32-12,29,29 /* MSR_PR -> _PAGE_USER */ 112: #ifndef CONFIG_PTE_64BIT @@ -89,9 +80,6 @@ _GLOBAL(hash_page) lwzx r8,r8,r5 /* Get L1 entry */ rlwinm. r8,r8,0,0,20 /* extract pt base address */ #endif -#ifdef CONFIG_VMAP_STACK - tovirt(r8, r8) -#endif #ifdef CONFIG_SMP beq- hash_page_out /* return if no mapping */ #else @@ -143,30 +131,36 @@ retry: bne- retry /* retry if someone got there first */ mfsrin r3,r4 /* get segment reg for segment */ +#ifndef CONFIG_VMAP_STACK mfctr r0 stw r0,_CTR(r11) +#endif bl create_hpte /* add the hash table entry */ #ifdef CONFIG_SMP eieio - lis r8, (mmu_hash_lock - ADDR_OFFSET)@ha + lis r8, (mmu_hash_lock - PAGE_OFFSET)@ha li r0,0 - stw r0, (mmu_hash_lock - ADDR_OFFSET)@l(r8) + stw r0, (mmu_hash_lock - PAGE_OFFSET)@l(r8) #endif +#ifdef CONFIG_VMAP_STACK + b fast_hash_page_return +#else /* Return from the exception */ lwz r5,_CTR(r11) mtctr r5 lwz r0,GPR0(r11) lwz r8,GPR8(r11) b fast_exception_return +#endif #ifdef CONFIG_SMP hash_page_out: eieio - lis r8, (mmu_hash_lock - ADDR_OFFSET)@ha + lis r8, (mmu_hash_lock - PAGE_OFFSET)@ha li r0,0 - stw r0, (mmu_hash_lock - ADDR_OFFSET)@l(r8) + stw r0, (mmu_hash_lock - PAGE_OFFSET)@l(r8) blr #endif /* CONFIG_SMP */ @@ -341,7 +335,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT) patch_site 1f, patch__hash_page_A1 patch_site 2f, patch__hash_page_A2 /* Get the address of the primary PTE group in the hash table (r3) */ -0: lis r0, (Hash_base - ADDR_OFFSET)@h /* base address of hash table */ +0: lis r0, (Hash_base - PAGE_OFFSET)@h /* base address of hash table */ 1: rlwimi r0,r3,LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT /* VSID -> hash */ 2: rlwinm r3,r4,20+LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT /* PI -> hash */ xor r3,r3,r0 /* make primary hash */ @@ -355,10 +349,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT) beq+ 10f /* no PTE: go look for an empty slot */ tlbie r4 - lis r4, (htab_hash_searches - ADDR_OFFSET)@ha - lwz r6, (htab_hash_searches - ADDR_OFFSET)@l(r4) + lis r4, (htab_hash_searches - PAGE_OFFSET)@ha + lwz r6, (htab_hash_searches - PAGE_OFFSET)@l(r4) addi r6,r6,1 /* count how many searches we do */ - stw r6, (htab_hash_searches - ADDR_OFFSET)@l(r4) + stw r6, (htab_hash_searches - PAGE_OFFSET)@l(r4) /* Search the primary PTEG for a PTE whose 1st (d)word matches r5 */ mtctr r0 @@ -390,10 +384,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT) beq+ found_empty /* update counter of times that the primary PTEG is full */ - lis r4, (primary_pteg_full - ADDR_OFFSET)@ha - lwz r6, (primary_pteg_full - ADDR_OFFSET)@l(r4) + lis r4, (primary_pteg_full - PAGE_OFFSET)@ha + lwz r6, (primary_pteg_full - PAGE_OFFSET)@l(r4) addi r6,r6,1 - stw r6, (primary_pteg_full - ADDR_OFFSET)@l(r4) + stw r6, (primary_pteg_full - PAGE_OFFSET)@l(r4) patch_site 0f, patch__hash_page_C /* Search the secondary PTEG for an empty slot */ @@ -427,8 +421,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT) * lockup here but that shouldn't happen */ -1: lis r4, (next_slot - ADDR_OFFSET)@ha /* get next evict slot */ - lwz r6, (next_slot - ADDR_OFFSET)@l(r4) +1: lis r4, (next_slot - PAGE_OFFSET)@ha /* get next evict slot */ + lwz r6, (next_slot - PAGE_OFFSET)@l(r4) addi r6,r6,HPTE_SIZE /* search for candidate */ andi. r6,r6,7*HPTE_SIZE stw r6,next_slot@l(r4) diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c index 0a1c65a2c56553cf36836af6bc30ef2424489980..f888cbb109b9134daee3176b37988b250ef008f5 100644 --- a/arch/powerpc/mm/book3s32/mmu.c +++ b/arch/powerpc/mm/book3s32/mmu.c @@ -413,7 +413,7 @@ void __init MMU_init_hw(void) void __init MMU_init_hw_patch(void) { unsigned int hmask = Hash_mask >> (16 - LG_HPTEG_SIZE); - unsigned int hash; + unsigned int hash = (unsigned int)Hash - PAGE_OFFSET; if (ppc_md.progress) ppc_md.progress("hash:patch", 0x345); @@ -425,11 +425,6 @@ void __init MMU_init_hw_patch(void) /* * Patch up the instructions in hashtable.S:create_hpte */ - if (IS_ENABLED(CONFIG_VMAP_STACK)) - hash = (unsigned int)Hash; - else - hash = (unsigned int)Hash - PAGE_OFFSET; - modify_instruction_site(&patch__hash_page_A0, 0xffff, hash >> 16); modify_instruction_site(&patch__hash_page_A1, 0x7c0, hash_mb << 6); modify_instruction_site(&patch__hash_page_A2, 0x7c0, hash_mb2 << 6); @@ -439,8 +434,7 @@ void __init MMU_init_hw_patch(void) /* * Patch up the instructions in hashtable.S:flush_hash_page */ - modify_instruction_site(&patch__flush_hash_A0, 0xffff, - ((unsigned int)Hash - PAGE_OFFSET) >> 16); + modify_instruction_site(&patch__flush_hash_A0, 0xffff, hash >> 16); modify_instruction_site(&patch__flush_hash_A1, 0x7c0, hash_mb << 6); modify_instruction_site(&patch__flush_hash_A2, 0x7c0, hash_mb2 << 6); modify_instruction_site(&patch__flush_hash_B, 0xffff, hmask); diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 73d4873fc7f85442eafc08399446bc176fd82b9a..33b3461d91e8db0e7b19f569a5c20d06a9a827be 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -53,20 +53,24 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, if (pshift >= pdshift) { cachep = PGT_CACHE(PTE_T_ORDER); num_hugepd = 1 << (pshift - pdshift); + new = NULL; } else if (IS_ENABLED(CONFIG_PPC_8xx)) { - cachep = PGT_CACHE(PTE_INDEX_SIZE); + cachep = NULL; num_hugepd = 1; + new = pte_alloc_one(mm); } else { cachep = PGT_CACHE(pdshift - pshift); num_hugepd = 1; + new = NULL; } - if (!cachep) { + if (!cachep && !new) { WARN_ONCE(1, "No page table cache created for hugetlb tables"); return -ENOMEM; } - new = kmem_cache_alloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL)); + if (cachep) + new = kmem_cache_alloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL)); BUG_ON(pshift > HUGEPD_SHIFT_MASK); BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK); @@ -97,7 +101,10 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, if (i < num_hugepd) { for (i = i - 1 ; i >= 0; i--, hpdp--) *hpdp = __hugepd(0); - kmem_cache_free(cachep, new); + if (cachep) + kmem_cache_free(cachep, new); + else + pte_free(mm, new); } else { kmemleak_ignore(new); } @@ -324,8 +331,7 @@ static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshif if (shift >= pdshift) hugepd_free(tlb, hugepte); else if (IS_ENABLED(CONFIG_PPC_8xx)) - pgtable_free_tlb(tlb, hugepte, - get_hugepd_cache_index(PTE_INDEX_SIZE)); + pgtable_free_tlb(tlb, hugepte, 0); else pgtable_free_tlb(tlb, hugepte, get_hugepd_cache_index(pdshift - shift)); @@ -639,12 +645,13 @@ static int __init hugetlbpage_init(void) * if we have pdshift and shift value same, we don't * use pgt cache for hugepd. */ - if (pdshift > shift && IS_ENABLED(CONFIG_PPC_8xx)) - pgtable_cache_add(PTE_INDEX_SIZE); - else if (pdshift > shift) - pgtable_cache_add(pdshift - shift); - else if (IS_ENABLED(CONFIG_PPC_FSL_BOOK3E) || IS_ENABLED(CONFIG_PPC_8xx)) + if (pdshift > shift) { + if (!IS_ENABLED(CONFIG_PPC_8xx)) + pgtable_cache_add(pdshift - shift); + } else if (IS_ENABLED(CONFIG_PPC_FSL_BOOK3E) || + IS_ENABLED(CONFIG_PPC_8xx)) { pgtable_cache_add(PTE_T_ORDER); + } configured = true; } diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c index 16dd95bd0749d851410fce5ae727a0e9edfdb563..d2bed3fcb7194ec065e107b71786797359fd8257 100644 --- a/arch/powerpc/mm/kasan/kasan_init_32.c +++ b/arch/powerpc/mm/kasan/kasan_init_32.c @@ -120,12 +120,6 @@ static void __init kasan_unmap_early_shadow_vmalloc(void) unsigned long k_cur; phys_addr_t pa = __pa(kasan_early_shadow_page); - if (!early_mmu_has_feature(MMU_FTR_HPTE_TABLE)) { - int ret = kasan_init_shadow_page_tables(k_start, k_end); - - if (ret) - panic("kasan: kasan_init_shadow_page_tables() failed"); - } for (k_cur = k_start & PAGE_MASK; k_cur < k_end; k_cur += PAGE_SIZE) { pmd_t *pmd = pmd_offset(pud_offset(pgd_offset_k(k_cur), k_cur), k_cur); pte_t *ptep = pte_offset_kernel(pmd, k_cur); @@ -143,7 +137,8 @@ void __init kasan_mmu_init(void) int ret; struct memblock_region *reg; - if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE)) { + if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE) || + IS_ENABLED(CONFIG_KASAN_VMALLOC)) { ret = kasan_init_shadow_page_tables(KASAN_SHADOW_START, KASAN_SHADOW_END); if (ret) @@ -185,8 +180,7 @@ u8 __initdata early_hash[256 << 10] __aligned(256 << 10) = {0}; static void __init kasan_early_hash_table(void) { - unsigned int hash = IS_ENABLED(CONFIG_VMAP_STACK) ? (unsigned int)early_hash : - __pa(early_hash); + unsigned int hash = __pa(early_hash); modify_instruction_site(&patch__hash_page_A0, 0xffff, hash >> 16); modify_instruction_site(&patch__flush_hash_A0, 0xffff, hash >> 16); diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index ef7b1119b2e296c41753fb4c17489c4834237e01..1c07d5a3f54318cdf7f315b3fa517b73698b028b 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -373,7 +373,9 @@ static inline bool flush_coherent_icache(unsigned long addr) */ if (cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) { mb(); /* sync */ + allow_read_from_user((const void __user *)addr, L1_CACHE_BYTES); icbi((void *)addr); + prevent_read_from_user((const void __user *)addr, L1_CACHE_BYTES); mb(); /* sync */ isync(); return true; diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index e8c84d265602bc57bf47b49243a2044d93f2336d..0ec9640335bb3544548bcf3c391b2dd946621f4b 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -3435,6 +3435,11 @@ getstring(char *s, int size) int c; c = skipbl(); + if (c == '\n') { + *s = 0; + return; + } + do { if( size > 1 ){ *s++ = c; diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 73f029eae0cce91d89cfff9206e86324b716f46f..1a3b5a5276be26cdc052eca8d997864735802316 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -121,6 +121,7 @@ config ARCH_FLATMEM_ENABLE config ARCH_SPARSEMEM_ENABLE def_bool y + depends on MMU select SPARSEMEM_VMEMMAP_ENABLE config ARCH_SELECT_MEMORY_MODEL diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs index d325b67d00dfcf70c4f3cf89e68e3964eec62a06..3078b2de0b2d50171835e3775d0f85a70869a819 100644 --- a/arch/riscv/Kconfig.socs +++ b/arch/riscv/Kconfig.socs @@ -10,4 +10,28 @@ config SOC_SIFIVE help This enables support for SiFive SoC platform hardware. +config SOC_VIRT + bool "QEMU Virt Machine" + select VIRTIO_PCI + select VIRTIO_BALLOON + select VIRTIO_MMIO + select VIRTIO_CONSOLE + select VIRTIO_NET + select NET_9P_VIRTIO + select VIRTIO_BLK + select SCSI_VIRTIO + select DRM_VIRTIO_GPU + select HW_RANDOM_VIRTIO + select RPMSG_CHAR + select RPMSG_VIRTIO + select CRYPTO_DEV_VIRTIO + select VIRTIO_INPUT + select POWER_RESET_SYSCON + select POWER_RESET_SYSCON_POWEROFF + select GOLDFISH + select RTC_DRV_GOLDFISH + select SIFIVE_PLIC + help + This enables support for QEMU Virt Machine. + endmenu diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index b9009a2fbaf5c4dd7965f75264dee93539308019..259cb53d7f20e04e872d3b3f68f34b1e28789f10 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -13,8 +13,10 @@ LDFLAGS_vmlinux := ifeq ($(CONFIG_DYNAMIC_FTRACE),y) LDFLAGS_vmlinux := --no-relax endif -KBUILD_AFLAGS_MODULE += -fPIC -KBUILD_CFLAGS_MODULE += -fPIC + +ifeq ($(CONFIG_64BIT)$(CONFIG_CMODEL_MEDLOW),yy) +KBUILD_CFLAGS_MODULE += -mcmodel=medany +endif export BITS ifeq ($(CONFIG_ARCH_RV64I),y) diff --git a/arch/riscv/boot/.gitignore b/arch/riscv/boot/.gitignore index 8dab0bb6ae667c5f89da8aca74a0a3bb61dcfaa9..8a45a37d2af4ccf129e4de4002529c853b224d8a 100644 --- a/arch/riscv/boot/.gitignore +++ b/arch/riscv/boot/.gitignore @@ -1,2 +1,4 @@ Image Image.gz +loader +loader.lds diff --git a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts index 609198cb1163756e9c00d6c8f70e8a8b2440c7a0..4a2729f5ca3f0113be3e02e72f9c427fe02207cc 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts @@ -2,6 +2,7 @@ /* Copyright (c) 2018-2019 SiFive, Inc */ #include "fu540-c000.dtsi" +#include /* Clock frequency (in Hz) of the PCB crystal for rtcclk */ #define RTCCLK_FREQ 1000000 @@ -41,6 +42,10 @@ rtcclk: rtcclk { clock-frequency = ; clock-output-names = "rtcclk"; }; + gpio-restart { + compatible = "gpio-restart"; + gpios = <&gpio 10 GPIO_ACTIVE_LOW>; + }; }; &uart0 { diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index e2ff95cb3390f1750746d433e1877c45855b73f6..c8f0842030676a73553e8175e751b12aacb417d5 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -15,6 +15,7 @@ CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y CONFIG_BPF_SYSCALL=y CONFIG_SOC_SIFIVE=y +CONFIG_SOC_VIRT=y CONFIG_SMP=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y @@ -30,7 +31,6 @@ CONFIG_IP_PNP_BOOTP=y CONFIG_IP_PNP_RARP=y CONFIG_NETLINK_DIAG=y CONFIG_NET_9P=y -CONFIG_NET_9P_VIRTIO=y CONFIG_PCI=y CONFIG_PCIEPORTBUS=y CONFIG_PCI_HOST_GENERIC=y @@ -38,15 +38,12 @@ CONFIG_PCIE_XILINX=y CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y CONFIG_BLK_DEV_LOOP=y -CONFIG_VIRTIO_BLK=y CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y -CONFIG_SCSI_VIRTIO=y CONFIG_ATA=y CONFIG_SATA_AHCI=y CONFIG_SATA_AHCI_PLATFORM=y CONFIG_NETDEVICES=y -CONFIG_VIRTIO_NET=y CONFIG_MACB=y CONFIG_E1000E=y CONFIG_R8169=y @@ -57,15 +54,13 @@ CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_OF_PLATFORM=y CONFIG_SERIAL_EARLYCON_RISCV_SBI=y CONFIG_HVC_RISCV_SBI=y -CONFIG_VIRTIO_CONSOLE=y CONFIG_HW_RANDOM=y -CONFIG_HW_RANDOM_VIRTIO=y CONFIG_SPI=y CONFIG_SPI_SIFIVE=y # CONFIG_PTP_1588_CLOCK is not set +CONFIG_POWER_RESET=y CONFIG_DRM=y CONFIG_DRM_RADEON=y -CONFIG_DRM_VIRTIO_GPU=y CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_USB=y CONFIG_USB_XHCI_HCD=y @@ -78,12 +73,7 @@ CONFIG_USB_STORAGE=y CONFIG_USB_UAS=y CONFIG_MMC=y CONFIG_MMC_SPI=y -CONFIG_VIRTIO_PCI=y -CONFIG_VIRTIO_BALLOON=y -CONFIG_VIRTIO_INPUT=y -CONFIG_VIRTIO_MMIO=y -CONFIG_RPMSG_CHAR=y -CONFIG_RPMSG_VIRTIO=y +CONFIG_RTC_CLASS=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_AUTOFS4_FS=y @@ -98,7 +88,6 @@ CONFIG_NFS_V4_2=y CONFIG_ROOT_NFS=y CONFIG_9P_FS=y CONFIG_CRYPTO_USER_API_HASH=y -CONFIG_CRYPTO_DEV_VIRTIO=y CONFIG_PRINTK_TIME=y CONFIG_DEBUG_FS=y CONFIG_DEBUG_PAGEALLOC=y diff --git a/arch/riscv/configs/rv32_defconfig b/arch/riscv/configs/rv32_defconfig index eb519407c841b3327898680cd4c1893165900eb4..a844920a261fa473358f5da753ef88a8b39de52f 100644 --- a/arch/riscv/configs/rv32_defconfig +++ b/arch/riscv/configs/rv32_defconfig @@ -14,6 +14,7 @@ CONFIG_CHECKPOINT_RESTORE=y CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y CONFIG_BPF_SYSCALL=y +CONFIG_SOC_VIRT=y CONFIG_ARCH_RV32I=y CONFIG_SMP=y CONFIG_MODULES=y @@ -30,7 +31,6 @@ CONFIG_IP_PNP_BOOTP=y CONFIG_IP_PNP_RARP=y CONFIG_NETLINK_DIAG=y CONFIG_NET_9P=y -CONFIG_NET_9P_VIRTIO=y CONFIG_PCI=y CONFIG_PCIEPORTBUS=y CONFIG_PCI_HOST_GENERIC=y @@ -38,15 +38,12 @@ CONFIG_PCIE_XILINX=y CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y CONFIG_BLK_DEV_LOOP=y -CONFIG_VIRTIO_BLK=y CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y -CONFIG_SCSI_VIRTIO=y CONFIG_ATA=y CONFIG_SATA_AHCI=y CONFIG_SATA_AHCI_PLATFORM=y CONFIG_NETDEVICES=y -CONFIG_VIRTIO_NET=y CONFIG_MACB=y CONFIG_E1000E=y CONFIG_R8169=y @@ -57,13 +54,11 @@ CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_OF_PLATFORM=y CONFIG_SERIAL_EARLYCON_RISCV_SBI=y CONFIG_HVC_RISCV_SBI=y -CONFIG_VIRTIO_CONSOLE=y CONFIG_HW_RANDOM=y -CONFIG_HW_RANDOM_VIRTIO=y # CONFIG_PTP_1588_CLOCK is not set +CONFIG_POWER_RESET=y CONFIG_DRM=y CONFIG_DRM_RADEON=y -CONFIG_DRM_VIRTIO_GPU=y CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_USB=y CONFIG_USB_XHCI_HCD=y @@ -74,13 +69,7 @@ CONFIG_USB_OHCI_HCD=y CONFIG_USB_OHCI_HCD_PLATFORM=y CONFIG_USB_STORAGE=y CONFIG_USB_UAS=y -CONFIG_VIRTIO_PCI=y -CONFIG_VIRTIO_BALLOON=y -CONFIG_VIRTIO_INPUT=y -CONFIG_VIRTIO_MMIO=y -CONFIG_RPMSG_CHAR=y -CONFIG_RPMSG_VIRTIO=y -CONFIG_SIFIVE_PLIC=y +CONFIG_RTC_CLASS=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_AUTOFS4_FS=y @@ -95,7 +84,6 @@ CONFIG_NFS_V4_2=y CONFIG_ROOT_NFS=y CONFIG_9P_FS=y CONFIG_CRYPTO_USER_API_HASH=y -CONFIG_CRYPTO_DEV_VIRTIO=y CONFIG_PRINTK_TIME=y CONFIG_DEBUG_FS=y CONFIG_DEBUG_PAGEALLOC=y diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h index 435b65532e2945703cc17a9e5c4f7613a0d5b6b8..8e18d2c64399df91e0619852bfd5c9a4757cdc37 100644 --- a/arch/riscv/include/asm/csr.h +++ b/arch/riscv/include/asm/csr.h @@ -72,6 +72,16 @@ #define EXC_LOAD_PAGE_FAULT 13 #define EXC_STORE_PAGE_FAULT 15 +/* PMP configuration */ +#define PMP_R 0x01 +#define PMP_W 0x02 +#define PMP_X 0x04 +#define PMP_A 0x18 +#define PMP_A_TOR 0x08 +#define PMP_A_NA4 0x10 +#define PMP_A_NAPOT 0x18 +#define PMP_L 0x80 + /* symbolic CSR names: */ #define CSR_CYCLE 0xc00 #define CSR_TIME 0xc01 @@ -100,6 +110,8 @@ #define CSR_MCAUSE 0x342 #define CSR_MTVAL 0x343 #define CSR_MIP 0x344 +#define CSR_PMPCFG0 0x3a0 +#define CSR_PMPADDR0 0x3b0 #define CSR_MHARTID 0xf14 #ifdef CONFIG_RISCV_M_MODE diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h index 42347d0981e7e4634a28d40d7675a417ac76b869..49350c8bd7b09b0f8193b3415c084db3d707d549 100644 --- a/arch/riscv/include/asm/syscall.h +++ b/arch/riscv/include/asm/syscall.h @@ -28,13 +28,6 @@ static inline int syscall_get_nr(struct task_struct *task, return regs->a7; } -static inline void syscall_set_nr(struct task_struct *task, - struct pt_regs *regs, - int sysno) -{ - regs->a7 = sysno; -} - static inline void syscall_rollback(struct task_struct *task, struct pt_regs *regs) { diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index bad4d85b5e91810332719af05cb8d66009cf8982..208702d8c18eeac291ca8ef21eeec977d93af570 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -228,20 +228,13 @@ check_syscall_nr: /* Check to make sure we don't jump to a bogus syscall number. */ li t0, __NR_syscalls la s0, sys_ni_syscall - /* - * The tracer can change syscall number to valid/invalid value. - * We use syscall_set_nr helper in syscall_trace_enter thus we - * cannot trust the current value in a7 and have to reload from - * the current task pt_regs. - */ - REG_L a7, PT_A7(sp) /* * Syscall number held in a7. * If syscall number is above allowed value, redirect to ni_syscall. */ bge a7, t0, 1f /* - * Check if syscall is rejected by tracer or seccomp, i.e., a7 == -1. + * Check if syscall is rejected by tracer, i.e., a7 == -1. * If yes, we pretend it was executed. */ li t1, -1 @@ -334,6 +327,7 @@ work_resched: handle_syscall_trace_enter: move a0, sp call do_syscall_trace_enter + move t0, a0 REG_L a0, PT_A0(sp) REG_L a1, PT_A1(sp) REG_L a2, PT_A2(sp) @@ -342,6 +336,7 @@ handle_syscall_trace_enter: REG_L a5, PT_A5(sp) REG_L a6, PT_A6(sp) REG_L a7, PT_A7(sp) + bnez t0, ret_from_syscall_rejected j check_syscall_nr handle_syscall_trace_exit: move a0, sp diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 271860fc2c3f02a5d50552339a005004444ab456..85f2073e7fe4abee5dcb97f91cd2f07cf9d9f9e7 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -58,6 +58,12 @@ _start_kernel: /* Reset all registers except ra, a0, a1 */ call reset_regs + /* Setup a PMP to permit access to all of memory. */ + li a0, -1 + csrw CSR_PMPADDR0, a0 + li a0, (PMP_A_NAPOT | PMP_R | PMP_W | PMP_X) + csrw CSR_PMPCFG0, a0 + /* * The hartid in a0 is expected later on, and we have no firmware * to hand it to us. diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c index b7401858d872f37c496a3306b44a462df9e634a7..8bbe5dbe1341b663f02e08f094fd9e72a7fb2aad 100644 --- a/arch/riscv/kernel/module.c +++ b/arch/riscv/kernel/module.c @@ -8,6 +8,10 @@ #include #include #include +#include +#include +#include +#include static int apply_r_riscv_32_rela(struct module *me, u32 *location, Elf_Addr v) { @@ -386,3 +390,15 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, return 0; } + +#if defined(CONFIG_MMU) && defined(CONFIG_64BIT) +#define VMALLOC_MODULE_START \ + max(PFN_ALIGN((unsigned long)&_end - SZ_2G), VMALLOC_START) +void *module_alloc(unsigned long size) +{ + return __vmalloc_node_range(size, 1, VMALLOC_MODULE_START, + VMALLOC_END, GFP_KERNEL, + PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE, + __builtin_return_address(0)); +} +#endif diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c index 407464201b91efe42fb3002bd78dd5498e729c55..444dc7b0fd78c5cdc04887ffa4f6fea50b99a992 100644 --- a/arch/riscv/kernel/ptrace.c +++ b/arch/riscv/kernel/ptrace.c @@ -148,21 +148,19 @@ long arch_ptrace(struct task_struct *child, long request, * Allows PTRACE_SYSCALL to work. These are called from entry.S in * {handle,ret_from}_syscall. */ -__visible void do_syscall_trace_enter(struct pt_regs *regs) +__visible int do_syscall_trace_enter(struct pt_regs *regs) { if (test_thread_flag(TIF_SYSCALL_TRACE)) if (tracehook_report_syscall_entry(regs)) - syscall_set_nr(current, regs, -1); + return -1; /* * Do the secure computing after ptrace; failures should be fast. * If this fails we might have return value in a0 from seccomp * (via SECCOMP_RET_ERRNO/TRACE). */ - if (secure_computing() == -1) { - syscall_set_nr(current, regs, -1); - return; - } + if (secure_computing() == -1) + return -1; #ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) @@ -170,6 +168,7 @@ __visible void do_syscall_trace_enter(struct pt_regs *regs) #endif audit_syscall_entry(regs->a7, regs->a0, regs->a1, regs->a2, regs->a3); + return 0; } __visible void do_syscall_trace_exit(struct pt_regs *regs) diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index f4cad5163bf2c0160f64e828ba07e2d3b84623d2..ffb3d94bf0cc2782f5777e1423f6a3fc4310099f 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -156,6 +156,6 @@ void __init trap_init(void) csr_write(CSR_SCRATCH, 0); /* Set the exception vector address */ csr_write(CSR_TVEC, &handle_exception); - /* Enable all interrupts */ - csr_write(CSR_IE, -1); + /* Enable interrupts */ + csr_write(CSR_IE, IE_SIE | IE_EIE); } diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 965a8cf4829ca33bfde4754bf47db0b8b17c6611..fab855963c730653f3d4ee677f3371a5f3ee5bd7 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -131,7 +131,7 @@ void __init setup_bootmem(void) for_each_memblock(memory, reg) { phys_addr_t end = reg->base + reg->size; - if (reg->base <= vmlinux_end && vmlinux_end <= end) { + if (reg->base <= vmlinux_start && vmlinux_end <= end) { mem_size = min(reg->size, (phys_addr_t)-PAGE_OFFSET); /* diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index f0cc860405871d0457d6dc0fdc83fb3a0350a2c5..ec0ca90dd9000f339a3d8a739d59e84df386d0dc 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -19,18 +19,20 @@ asmlinkage void __init kasan_early_init(void) for (i = 0; i < PTRS_PER_PTE; ++i) set_pte(kasan_early_shadow_pte + i, mk_pte(virt_to_page(kasan_early_shadow_page), - PAGE_KERNEL)); + PAGE_KERNEL)); for (i = 0; i < PTRS_PER_PMD; ++i) set_pmd(kasan_early_shadow_pmd + i, - pfn_pmd(PFN_DOWN(__pa((uintptr_t)kasan_early_shadow_pte)), - __pgprot(_PAGE_TABLE))); + pfn_pmd(PFN_DOWN + (__pa((uintptr_t) kasan_early_shadow_pte)), + __pgprot(_PAGE_TABLE))); for (i = KASAN_SHADOW_START; i < KASAN_SHADOW_END; i += PGDIR_SIZE, ++pgd) set_pgd(pgd, - pfn_pgd(PFN_DOWN(__pa(((uintptr_t)kasan_early_shadow_pmd))), - __pgprot(_PAGE_TABLE))); + pfn_pgd(PFN_DOWN + (__pa(((uintptr_t) kasan_early_shadow_pmd))), + __pgprot(_PAGE_TABLE))); /* init for swapper_pg_dir */ pgd = pgd_offset_k(KASAN_SHADOW_START); @@ -38,37 +40,43 @@ asmlinkage void __init kasan_early_init(void) for (i = KASAN_SHADOW_START; i < KASAN_SHADOW_END; i += PGDIR_SIZE, ++pgd) set_pgd(pgd, - pfn_pgd(PFN_DOWN(__pa(((uintptr_t)kasan_early_shadow_pmd))), - __pgprot(_PAGE_TABLE))); + pfn_pgd(PFN_DOWN + (__pa(((uintptr_t) kasan_early_shadow_pmd))), + __pgprot(_PAGE_TABLE))); flush_tlb_all(); } static void __init populate(void *start, void *end) { - unsigned long i; + unsigned long i, offset; unsigned long vaddr = (unsigned long)start & PAGE_MASK; unsigned long vend = PAGE_ALIGN((unsigned long)end); unsigned long n_pages = (vend - vaddr) / PAGE_SIZE; + unsigned long n_ptes = + ((n_pages + PTRS_PER_PTE) & -PTRS_PER_PTE) / PTRS_PER_PTE; unsigned long n_pmds = - (n_pages % PTRS_PER_PTE) ? n_pages / PTRS_PER_PTE + 1 : - n_pages / PTRS_PER_PTE; + ((n_ptes + PTRS_PER_PMD) & -PTRS_PER_PMD) / PTRS_PER_PMD; + + pte_t *pte = + memblock_alloc(n_ptes * PTRS_PER_PTE * sizeof(pte_t), PAGE_SIZE); + pmd_t *pmd = + memblock_alloc(n_pmds * PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE); pgd_t *pgd = pgd_offset_k(vaddr); - pmd_t *pmd = memblock_alloc(n_pmds * sizeof(pmd_t), PAGE_SIZE); - pte_t *pte = memblock_alloc(n_pages * sizeof(pte_t), PAGE_SIZE); for (i = 0; i < n_pages; i++) { phys_addr_t phys = memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE); - - set_pte(pte + i, pfn_pte(PHYS_PFN(phys), PAGE_KERNEL)); + set_pte(&pte[i], pfn_pte(PHYS_PFN(phys), PAGE_KERNEL)); } - for (i = 0; i < n_pmds; ++pgd, i += PTRS_PER_PMD) - set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(((uintptr_t)(pmd + i)))), + for (i = 0, offset = 0; i < n_ptes; i++, offset += PTRS_PER_PTE) + set_pmd(&pmd[i], + pfn_pmd(PFN_DOWN(__pa(&pte[offset])), __pgprot(_PAGE_TABLE))); - for (i = 0; i < n_pages; ++pmd, i += PTRS_PER_PTE) - set_pmd(pmd, pfn_pmd(PFN_DOWN(__pa((uintptr_t)(pte + i))), + for (i = 0, offset = 0; i < n_pmds; i++, offset += PTRS_PER_PMD) + set_pgd(&pgd[i], + pfn_pgd(PFN_DOWN(__pa(&pmd[offset])), __pgprot(_PAGE_TABLE))); flush_tlb_all(); @@ -81,7 +89,8 @@ void __init kasan_init(void) unsigned long i; kasan_populate_early_shadow((void *)KASAN_SHADOW_START, - (void *)kasan_mem_to_shadow((void *)VMALLOC_END)); + (void *)kasan_mem_to_shadow((void *) + VMALLOC_END)); for_each_memblock(memory, reg) { void *start = (void *)__va(reg->base); @@ -90,14 +99,14 @@ void __init kasan_init(void) if (start >= end) break; - populate(kasan_mem_to_shadow(start), - kasan_mem_to_shadow(end)); + populate(kasan_mem_to_shadow(start), kasan_mem_to_shadow(end)); }; for (i = 0; i < PTRS_PER_PTE; i++) set_pte(&kasan_early_shadow_pte[i], mk_pte(virt_to_page(kasan_early_shadow_page), - __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_ACCESSED))); + __pgprot(_PAGE_PRESENT | _PAGE_READ | + _PAGE_ACCESSED))); memset(kasan_early_shadow_page, 0, PAGE_SIZE); init_task.kasan_depth = 0; diff --git a/arch/s390/Makefile b/arch/s390/Makefile index e0e3a465bbfd6fd15eb44ab8675af10c171c2e01..8dfa2cf1f05c7a9028683aa1900e0975d27863e9 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -146,7 +146,7 @@ all: bzImage #KBUILD_IMAGE is necessary for packaging targets like rpm-pkg, deb-pkg... KBUILD_IMAGE := $(boot)/bzImage -install: vmlinux +install: $(Q)$(MAKE) $(build)=$(boot) $@ bzImage: vmlinux diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile index e2c47d3a1c891b7bf5bb783f156ca902c69f1fdf..0ff9261c915e3fa64369b9e484c3baaed909b6aa 100644 --- a/arch/s390/boot/Makefile +++ b/arch/s390/boot/Makefile @@ -70,7 +70,7 @@ $(obj)/compressed/vmlinux: $(obj)/startup.a FORCE $(obj)/startup.a: $(OBJECTS) FORCE $(call if_changed,ar) -install: $(CONFIGURE) $(obj)/bzImage +install: sh -x $(srctree)/$(obj)/install.sh $(KERNELRELEASE) $(obj)/bzImage \ System.map "$(INSTALL_PATH)" diff --git a/arch/s390/boot/kaslr.c b/arch/s390/boot/kaslr.c index 5d12352545c558d4f5598fd074048029cfd6218a..5591243d673e82cea561c5df4c9e6ac19c55ed6f 100644 --- a/arch/s390/boot/kaslr.c +++ b/arch/s390/boot/kaslr.c @@ -75,7 +75,7 @@ static unsigned long get_random(unsigned long limit) *(unsigned long *) prng.parm_block ^= seed; for (i = 0; i < 16; i++) { cpacf_kmc(CPACF_KMC_PRNG, prng.parm_block, - (char *) entropy, (char *) entropy, + (u8 *) entropy, (u8 *) entropy, sizeof(entropy)); memcpy(prng.parm_block, entropy, sizeof(entropy)); } diff --git a/arch/s390/boot/uv.c b/arch/s390/boot/uv.c index ed007f4a6444ff84b7c7abac01b442459e619458..3f501159ee9fc2ac1200219337859a03bb02c99f 100644 --- a/arch/s390/boot/uv.c +++ b/arch/s390/boot/uv.c @@ -15,7 +15,8 @@ void uv_query_info(void) if (!test_facility(158)) return; - if (uv_call(0, (uint64_t)&uvcb)) + /* rc==0x100 means that there is additional data we do not process */ + if (uv_call(0, (uint64_t)&uvcb) && uvcb.header.rc != 0x100) return; if (test_bit_inv(BIT_UVC_CMD_SET_SHARED_ACCESS, (unsigned long *)uvcb.inst_calls_list) && diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 2e60c80395ab084afbe4713fbc8816f42bea3f60..0c86ba19fa2bcdb0ca9ce4627366b59714b379eb 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -53,6 +53,7 @@ CONFIG_VFIO_AP=m CONFIG_CRASH_DUMP=y CONFIG_HIBERNATION=y CONFIG_PM_DEBUG=y +CONFIG_PROTECTED_VIRTUALIZATION_GUEST=y CONFIG_CMM=m CONFIG_APPLDATA_BASE=y CONFIG_KVM=m @@ -474,7 +475,6 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_EMULEX is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_GOOGLE is not set -# CONFIG_NET_VENDOR_HP is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set @@ -684,7 +684,6 @@ CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_CRC32=m -CONFIG_CRYPTO_XXHASH=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD128=m CONFIG_CRYPTO_RMD160=m @@ -748,7 +747,6 @@ CONFIG_DEBUG_INFO_DWARF4=y CONFIG_GDB_SCRIPTS=y CONFIG_FRAME_WARN=1024 CONFIG_HEADERS_INSTALL=y -CONFIG_HEADERS_CHECK=y CONFIG_DEBUG_SECTION_MISMATCH=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_PAGEALLOC=y @@ -772,9 +770,9 @@ CONFIG_DEBUG_MEMORY_INIT=y CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m CONFIG_DEBUG_PER_CPU_MAPS=y CONFIG_DEBUG_SHIRQ=y +CONFIG_PANIC_ON_OOPS=y CONFIG_DETECT_HUNG_TASK=y CONFIG_WQ_WATCHDOG=y -CONFIG_PANIC_ON_OOPS=y CONFIG_DEBUG_TIMEKEEPING=y CONFIG_PROVE_LOCKING=y CONFIG_LOCK_STAT=y @@ -783,9 +781,20 @@ CONFIG_DEBUG_ATOMIC_SLEEP=y CONFIG_DEBUG_LOCKING_API_SELFTESTS=y CONFIG_DEBUG_SG=y CONFIG_DEBUG_NOTIFIERS=y +CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_DEBUG_CREDENTIALS=y CONFIG_RCU_TORTURE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=300 +CONFIG_LATENCYTOP=y +CONFIG_FUNCTION_PROFILER=y +CONFIG_STACK_TRACER=y +CONFIG_IRQSOFF_TRACER=y +CONFIG_PREEMPT_TRACER=y +CONFIG_SCHED_TRACER=y +CONFIG_FTRACE_SYSCALLS=y +CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_HIST_TRIGGERS=y +CONFIG_S390_PTDUMP=y CONFIG_NOTIFIER_ERROR_INJECTION=m CONFIG_NETDEV_NOTIFIER_ERROR_INJECT=m CONFIG_FAULT_INJECTION=y @@ -796,15 +805,6 @@ CONFIG_FAIL_IO_TIMEOUT=y CONFIG_FAIL_FUTEX=y CONFIG_FAULT_INJECTION_DEBUG_FS=y CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y -CONFIG_LATENCYTOP=y -CONFIG_IRQSOFF_TRACER=y -CONFIG_PREEMPT_TRACER=y -CONFIG_SCHED_TRACER=y -CONFIG_FTRACE_SYSCALLS=y -CONFIG_STACK_TRACER=y -CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_FUNCTION_PROFILER=y -CONFIG_HIST_TRIGGERS=y CONFIG_LKDTM=m CONFIG_TEST_LIST_SORT=y CONFIG_TEST_SORT=y @@ -814,5 +814,3 @@ CONFIG_INTERVAL_TREE_TEST=m CONFIG_PERCPU_TEST=m CONFIG_ATOMIC64_SELFTEST=y CONFIG_TEST_BPF=m -CONFIG_BUG_ON_DATA_CORRUPTION=y -CONFIG_S390_PTDUMP=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 25f79984958219506566216ca4a34db0e49a31e4..6b27d861a9a306e03cb7f319339cabf16a0c6de3 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -53,6 +53,7 @@ CONFIG_VFIO_AP=m CONFIG_CRASH_DUMP=y CONFIG_HIBERNATION=y CONFIG_PM_DEBUG=y +CONFIG_PROTECTED_VIRTUALIZATION_GUEST=y CONFIG_CMM=m CONFIG_APPLDATA_BASE=y CONFIG_KVM=m @@ -470,7 +471,6 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_EMULEX is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_GOOGLE is not set -# CONFIG_NET_VENDOR_HP is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set @@ -677,7 +677,6 @@ CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_CRC32=m -CONFIG_CRYPTO_XXHASH=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD128=m CONFIG_CRYPTO_RMD160=m @@ -739,18 +738,18 @@ CONFIG_DEBUG_SECTION_MISMATCH=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_MEMORY_INIT=y CONFIG_PANIC_ON_OOPS=y +CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_RCU_TORTURE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=60 CONFIG_LATENCYTOP=y +CONFIG_FUNCTION_PROFILER=y +CONFIG_STACK_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y -CONFIG_STACK_TRACER=y CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_FUNCTION_PROFILER=y CONFIG_HIST_TRIGGERS=y +CONFIG_S390_PTDUMP=y CONFIG_LKDTM=m CONFIG_PERCPU_TEST=m CONFIG_ATOMIC64_SELFTEST=y CONFIG_TEST_BPF=m -CONFIG_BUG_ON_DATA_CORRUPTION=y -CONFIG_S390_PTDUMP=y diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index 85e944f04c70ec68a64fd25622d1faf4cfdd5f90..1019efd85b9dc952126fa455dcde0fa7187ab112 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -42,7 +42,7 @@ void __storage_key_init_range(unsigned long start, unsigned long end); static inline void storage_key_init_range(unsigned long start, unsigned long end) { - if (PAGE_DEFAULT_KEY) + if (PAGE_DEFAULT_KEY != 0) __storage_key_init_range(start, end); } diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 137a3920ca3632907ca17b515aed4045a8d4888c..6d7c3b7e928101d78d6a678b8fd9e2c3ccb239ab 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -752,6 +752,12 @@ static inline int pmd_write(pmd_t pmd) return (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE) != 0; } +#define pud_write pud_write +static inline int pud_write(pud_t pud) +{ + return (pud_val(pud) & _REGION3_ENTRY_WRITE) != 0; +} + static inline int pmd_dirty(pmd_t pmd) { return (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) != 0; diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 361ef5eda46895270f781407cbd684dd5eb1ac1e..aadb3d0e2adc767c862f4455a6a9c3949691b856 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -84,7 +84,6 @@ void s390_update_cpu_mhz(void); void cpu_detect_mhz_feature(void); extern const struct seq_operations cpuinfo_op; -extern int sysctl_ieee_emulation_warnings; extern void execve_tail(void); extern void __bpon(void); diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h index 71e3f0146cda084920c40b7736c01d45e5b0a594..1e3517b0518beb27d8dc7e2d7ea2b378d4f36993 100644 --- a/arch/s390/include/asm/qdio.h +++ b/arch/s390/include/asm/qdio.h @@ -201,7 +201,7 @@ struct slib { * @scount: SBAL count * @sflags: whole SBAL flags * @length: length - * @addr: address + * @addr: absolute data address */ struct qdio_buffer_element { u8 eflags; @@ -211,7 +211,7 @@ struct qdio_buffer_element { u8 scount; u8 sflags; u32 length; - void *addr; + u64 addr; } __attribute__ ((packed, aligned(16))); /** @@ -227,7 +227,7 @@ struct qdio_buffer { * @sbal: absolute SBAL address */ struct sl_element { - unsigned long sbal; + u64 sbal; } __attribute__ ((packed)); /** diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h index 670f14a228e55bb42c4cc516b660f91431a4cb0a..6bf3a45ccfec203e2234cfa0883c5fdef6749fdc 100644 --- a/arch/s390/include/asm/timex.h +++ b/arch/s390/include/asm/timex.h @@ -155,7 +155,7 @@ static inline void get_tod_clock_ext(char *clk) static inline unsigned long long get_tod_clock(void) { - unsigned char clk[STORE_CLOCK_EXT_SIZE]; + char clk[STORE_CLOCK_EXT_SIZE]; get_tod_clock_ext(clk); return *((unsigned long long *)&clk[1]); diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index d7ff30e45589935890ad1c1f67c0f36eaa4d480e..c2e6d4ba4e2369db946ecb6339045d91c1715c88 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -3268,7 +3268,10 @@ static void kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu) /* Initial reset is a superset of the normal reset */ kvm_arch_vcpu_ioctl_normal_reset(vcpu); - /* this equals initial cpu reset in pop, but we don't switch to ESA */ + /* + * This equals initial cpu reset in pop, but we don't switch to ESA. + * We do not only reset the internal data, but also ... + */ vcpu->arch.sie_block->gpsw.mask = 0; vcpu->arch.sie_block->gpsw.addr = 0; kvm_s390_set_prefix(vcpu, 0); @@ -3278,6 +3281,19 @@ static void kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu) memset(vcpu->arch.sie_block->gcr, 0, sizeof(vcpu->arch.sie_block->gcr)); vcpu->arch.sie_block->gcr[0] = CR0_INITIAL_MASK; vcpu->arch.sie_block->gcr[14] = CR14_INITIAL_MASK; + + /* ... the data in sync regs */ + memset(vcpu->run->s.regs.crs, 0, sizeof(vcpu->run->s.regs.crs)); + vcpu->run->s.regs.ckc = 0; + vcpu->run->s.regs.crs[0] = CR0_INITIAL_MASK; + vcpu->run->s.regs.crs[14] = CR14_INITIAL_MASK; + vcpu->run->psw_addr = 0; + vcpu->run->psw_mask = 0; + vcpu->run->s.regs.todpr = 0; + vcpu->run->s.regs.cputm = 0; + vcpu->run->s.regs.ckc = 0; + vcpu->run->s.regs.pp = 0; + vcpu->run->s.regs.gbea = 1; vcpu->run->s.regs.fpc = 0; vcpu->arch.sie_block->gbea = 1; vcpu->arch.sie_block->pp = 0; diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index bc61ea18e88d90bc183b80c34cbfc4f372c343de..60716d18ce5afd0d0f4c9277ea0342b9ddadc9d9 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -424,7 +424,7 @@ static void zpci_map_resources(struct pci_dev *pdev) if (zpci_use_mio(zdev)) pdev->resource[i].start = - (resource_size_t __force) zdev->bars[i].mio_wb; + (resource_size_t __force) zdev->bars[i].mio_wt; else pdev->resource[i].start = (resource_size_t __force) pci_iomap_range_fh(pdev, i, 0, 0); @@ -531,7 +531,7 @@ static int zpci_setup_bus_resources(struct zpci_dev *zdev, flags |= IORESOURCE_MEM_64; if (zpci_use_mio(zdev)) - addr = (unsigned long) zdev->bars[i].mio_wb; + addr = (unsigned long) zdev->bars[i].mio_wt; else addr = ZPCI_ADDR(entry); size = 1UL << zdev->bars[i].size; diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 94df0868804bcb4b9b37f7abf4985ac95158c4f8..513a55562d7508eaf75d3efc954b0a786956bbd1 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -194,9 +194,10 @@ avx2_instr :=$(call as-instr,vpbroadcastb %xmm0$(comma)%ymm1,-DCONFIG_AS_AVX2=1) avx512_instr :=$(call as-instr,vpmovm2b %k1$(comma)%zmm5,-DCONFIG_AS_AVX512=1) sha1_ni_instr :=$(call as-instr,sha1msg1 %xmm0$(comma)%xmm1,-DCONFIG_AS_SHA1_NI=1) sha256_ni_instr :=$(call as-instr,sha256msg1 %xmm0$(comma)%xmm1,-DCONFIG_AS_SHA256_NI=1) +adx_instr := $(call as-instr,adox %r10$(comma)%r10,-DCONFIG_AS_ADX=1) -KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(avx512_instr) $(sha1_ni_instr) $(sha256_ni_instr) -KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(avx512_instr) $(sha1_ni_instr) $(sha256_ni_instr) +KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(avx512_instr) $(sha1_ni_instr) $(sha256_ni_instr) $(adx_instr) +KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(avx512_instr) $(sha1_ni_instr) $(sha256_ni_instr) $(adx_instr) KBUILD_LDFLAGS := -m elf_$(UTS_MACHINE) diff --git a/arch/x86/boot/compressed/kaslr_64.c b/arch/x86/boot/compressed/kaslr_64.c index 748456c365f4691af041753c63d6991f9bc8b4b8..9557c5a15b91e29a6465e502599960aad87e3e60 100644 --- a/arch/x86/boot/compressed/kaslr_64.c +++ b/arch/x86/boot/compressed/kaslr_64.c @@ -29,9 +29,6 @@ #define __PAGE_OFFSET __PAGE_OFFSET_BASE #include "../../mm/ident_map.c" -/* Used by pgtable.h asm code to force instruction serialization. */ -unsigned long __force_order; - /* Used to track our page table allocation area. */ struct alloc_pgt_data { unsigned char *pgt_buf; diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile index b69e00bf20b82e4653cb7b563aa132efa43f0838..8c2e9eadee8a0ff349c324cdfc310e6910fad1b8 100644 --- a/arch/x86/crypto/Makefile +++ b/arch/x86/crypto/Makefile @@ -11,6 +11,7 @@ avx2_supported := $(call as-instr,vpgatherdd %ymm0$(comma)(%eax$(comma)%ymm1\ avx512_supported :=$(call as-instr,vpmovm2b %k1$(comma)%zmm5,yes,no) sha1_ni_supported :=$(call as-instr,sha1msg1 %xmm0$(comma)%xmm1,yes,no) sha256_ni_supported :=$(call as-instr,sha256msg1 %xmm0$(comma)%xmm1,yes,no) +adx_supported := $(call as-instr,adox %r10$(comma)%r10,yes,no) obj-$(CONFIG_CRYPTO_GLUE_HELPER_X86) += glue_helper.o @@ -39,7 +40,11 @@ obj-$(CONFIG_CRYPTO_AEGIS128_AESNI_SSE2) += aegis128-aesni.o obj-$(CONFIG_CRYPTO_NHPOLY1305_SSE2) += nhpoly1305-sse2.o obj-$(CONFIG_CRYPTO_NHPOLY1305_AVX2) += nhpoly1305-avx2.o -obj-$(CONFIG_CRYPTO_CURVE25519_X86) += curve25519-x86_64.o + +# These modules require the assembler to support ADX. +ifeq ($(adx_supported),yes) + obj-$(CONFIG_CRYPTO_CURVE25519_X86) += curve25519-x86_64.o +endif # These modules require assembler to support AVX. ifeq ($(avx_supported),yes) diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index 1f22b6bbda68d1bac825f7f25351f308e96f1f6f..39eb276d02775756880365aecc78aaebb93b0005 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -250,6 +250,7 @@ static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] = [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, [PERF_COUNT_HW_CACHE_REFERENCES] = 0xff60, + [PERF_COUNT_HW_CACHE_MISSES] = 0x0964, [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2, [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3, [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x0287, diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c index a6ea07f2aa8482d6ea0835b4a745245c039b352e..4d867a752f0ecd0f79656341edfba56fc1d40fc3 100644 --- a/arch/x86/events/amd/uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -190,15 +190,12 @@ static int amd_uncore_event_init(struct perf_event *event) /* * NB and Last level cache counters (MSRs) are shared across all cores - * that share the same NB / Last level cache. Interrupts can be directed - * to a single target core, however, event counts generated by processes - * running on other cores cannot be masked out. So we do not support - * sampling and per-thread events. + * that share the same NB / Last level cache. On family 16h and below, + * Interrupts can be directed to a single target core, however, event + * counts generated by processes running on other cores cannot be masked + * out. So we do not support sampling and per-thread events via + * CAP_NO_INTERRUPT, and we do not enable counter overflow interrupts: */ - if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK) - return -EINVAL; - - /* and we do not enable counter overflow interrupts */ hwc->config = event->attr.config & AMD64_RAW_EVENT_MASK_NB; hwc->idx = -1; @@ -306,7 +303,7 @@ static struct pmu amd_nb_pmu = { .start = amd_uncore_start, .stop = amd_uncore_stop, .read = amd_uncore_read, - .capabilities = PERF_PMU_CAP_NO_EXCLUDE, + .capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT, }; static struct pmu amd_llc_pmu = { @@ -317,7 +314,7 @@ static struct pmu amd_llc_pmu = { .start = amd_uncore_start, .stop = amd_uncore_stop, .read = amd_uncore_read, - .capabilities = PERF_PMU_CAP_NO_EXCLUDE, + .capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT, }; static struct amd_uncore *amd_uncore_alloc(unsigned int cpu) diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 3be51aa06e67ec2e5b893af82096b43db5c3f23a..dff6623804c2835b1b67731341301a884edd4ef3 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4765,6 +4765,7 @@ __init int intel_pmu_init(void) break; case INTEL_FAM6_ATOM_TREMONT_D: + case INTEL_FAM6_ATOM_TREMONT: x86_pmu.late_ack = true; memcpy(hw_cache_event_ids, glp_hw_cache_event_ids, sizeof(hw_cache_event_ids)); diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index e1daf4151e11608bfc519562657177bfcd11755e..4814c964692cb1a5d779660c2ececd247350283b 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -40,17 +40,18 @@ * Model specific counters: * MSR_CORE_C1_RES: CORE C1 Residency Counter * perf code: 0x00 - * Available model: SLM,AMT,GLM,CNL + * Available model: SLM,AMT,GLM,CNL,TNT * Scope: Core (each processor core has a MSR) * MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter * perf code: 0x01 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,GLM, - * CNL,KBL,CML + * CNL,KBL,CML,TNT * Scope: Core * MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, - * SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL + * SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL, + * TNT * Scope: Core * MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter * perf code: 0x03 @@ -60,17 +61,18 @@ * MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter. * perf code: 0x00 * Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL, - * KBL,CML,ICL,TGL + * KBL,CML,ICL,TGL,TNT * Scope: Package (physical package) * MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter. * perf code: 0x01 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL, - * GLM,CNL,KBL,CML,ICL,TGL + * GLM,CNL,KBL,CML,ICL,TGL,TNT * Scope: Package (physical package) * MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter. * perf code: 0x02 - * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW - * SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL + * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, + * SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL, + * TNT * Scope: Package (physical package) * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter. * perf code: 0x03 @@ -87,7 +89,8 @@ * Scope: Package (physical package) * MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter. * perf code: 0x06 - * Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL + * Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL, + * TNT * Scope: Package (physical package) * */ @@ -640,8 +643,9 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT, glm_cstates), X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_D, glm_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_ATOM_TREMONT_D, glm_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_ATOM_TREMONT, glm_cstates), X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_L, icl_cstates), X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE, icl_cstates), diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 4b94ae4ae369a37235981538e3316de60da7246a..dc43cc124e096768a6eb81af96271b1dec6d3211 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1714,6 +1714,8 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count) old = ((s64)(prev_raw_count << shift) >> shift); local64_add(new - old + count * period, &event->count); + local64_set(&hwc->period_left, -new); + perf_event_update_userpage(event); return 0; diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index 6f86650b3f77d73cc5dd6ebec2dbca8241a18ed2..a949f6f55991dc5dd1756288cecad675fe55f78f 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -75,8 +75,9 @@ static bool test_intel(int idx, void *data) case INTEL_FAM6_ATOM_GOLDMONT: case INTEL_FAM6_ATOM_GOLDMONT_D: - case INTEL_FAM6_ATOM_GOLDMONT_PLUS: + case INTEL_FAM6_ATOM_TREMONT_D: + case INTEL_FAM6_ATOM_TREMONT: case INTEL_FAM6_XEON_PHI_KNL: case INTEL_FAM6_XEON_PHI_KNM: diff --git a/arch/x86/include/asm/io_bitmap.h b/arch/x86/include/asm/io_bitmap.h index 02c6ef8f7667725b2730e049a2a51d78caec650e..07344d82e88ee6b28e4bb2040932eb1135a3b4a3 100644 --- a/arch/x86/include/asm/io_bitmap.h +++ b/arch/x86/include/asm/io_bitmap.h @@ -19,7 +19,14 @@ struct task_struct; void io_bitmap_share(struct task_struct *tsk); void io_bitmap_exit(void); -void tss_update_io_bitmap(void); +void native_tss_update_io_bitmap(void); + +#ifdef CONFIG_PARAVIRT_XXL +#include +#else +#define tss_update_io_bitmap native_tss_update_io_bitmap +#endif + #else static inline void io_bitmap_share(struct task_struct *tsk) { } static inline void io_bitmap_exit(void) { } diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 03946eb3e2b9e5162c6f20fff85bf1747ad8431a..c06e8353efd3297ee44878b91f58798dd04b0664 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -292,6 +292,14 @@ enum x86emul_mode { #define X86EMUL_SMM_MASK (1 << 6) #define X86EMUL_SMM_INSIDE_NMI_MASK (1 << 7) +/* + * fastop functions are declared as taking a never-defined fastop parameter, + * so they can't be called from C directly. + */ +struct fastop; + +typedef void (*fastop_t)(struct fastop *); + struct x86_emulate_ctxt { const struct x86_emulate_ops *ops; @@ -324,7 +332,10 @@ struct x86_emulate_ctxt { struct operand src; struct operand src2; struct operand dst; - int (*execute)(struct x86_emulate_ctxt *ctxt); + union { + int (*execute)(struct x86_emulate_ctxt *ctxt); + fastop_t fop; + }; int (*check_perm)(struct x86_emulate_ctxt *ctxt); /* * The following six fields are cleared together, @@ -349,7 +360,6 @@ struct x86_emulate_ctxt { u64 d; unsigned long _eip; struct operand memop; - /* Fields above regs are cleared together. */ unsigned long _regs[NR_VCPU_REGS]; struct operand *memopp; struct fetch_cache fetch; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 4dffbc10d3f8970dbe750cbd4f453c6bd94e56c6..98959e8cd4489877946d091a9bb5ee297790dbe3 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -781,9 +781,19 @@ struct kvm_vcpu_arch { u64 msr_kvm_poll_control; /* - * Indicate whether the access faults on its page table in guest - * which is set when fix page fault and used to detect unhandeable - * instruction. + * Indicates the guest is trying to write a gfn that contains one or + * more of the PTEs used to translate the write itself, i.e. the access + * is changing its own translation in the guest page tables. KVM exits + * to userspace if emulation of the faulting instruction fails and this + * flag is set, as KVM cannot make forward progress. + * + * If emulation fails for a write to guest page tables, KVM unprotects + * (zaps) the shadow page for the target gfn and resumes the guest to + * retry the non-emulatable instruction (on hardware). Unprotecting the + * gfn doesn't allow forward progress for a self-changing access because + * doing so also zaps the translation for the gfn, i.e. retrying the + * instruction will hit a !PRESENT fault, which results in a new shadow + * page and sends KVM back to square one. */ bool write_fault_to_shadow_pgtable; @@ -1112,6 +1122,7 @@ struct kvm_x86_ops { int (*handle_exit)(struct kvm_vcpu *vcpu, enum exit_fastpath_completion exit_fastpath); int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu); + void (*update_emulated_instruction)(struct kvm_vcpu *vcpu); void (*set_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask); u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu); void (*patch_hypercall)(struct kvm_vcpu *vcpu, @@ -1136,7 +1147,7 @@ struct kvm_x86_ops { void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu); void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa); - void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector); + int (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector); int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu); int (*set_tss_addr)(struct kvm *kvm, unsigned int addr); int (*set_identity_map_addr)(struct kvm *kvm, u64 ident_addr); diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index ebe1685e92dda2bfd6795b45a92924de8a8f9451..d5e517d1c3ddc5c9ac6e594500d87524168b143d 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -512,6 +512,8 @@ #define MSR_K7_HWCR 0xc0010015 #define MSR_K7_HWCR_SMMLOCK_BIT 0 #define MSR_K7_HWCR_SMMLOCK BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT) +#define MSR_K7_HWCR_IRPERF_EN_BIT 30 +#define MSR_K7_HWCR_IRPERF_EN BIT_ULL(MSR_K7_HWCR_IRPERF_EN_BIT) #define MSR_K7_FID_VID_CTL 0xc0010041 #define MSR_K7_FID_VID_STATUS 0xc0010042 diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 86e7317eb31f9a11c3f3b638f0882929b76af777..694d8daf498376ef7e91a1a3026638e275378cab 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -295,6 +295,13 @@ static inline void write_idt_entry(gate_desc *dt, int entry, const gate_desc *g) PVOP_VCALL3(cpu.write_idt_entry, dt, entry, g); } +#ifdef CONFIG_X86_IOPL_IOPERM +static inline void tss_update_io_bitmap(void) +{ + PVOP_VCALL0(cpu.update_io_bitmap); +} +#endif + static inline void paravirt_activate_mm(struct mm_struct *prev, struct mm_struct *next) { diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 84812964d3dd6f0ae5a68763251b4bd4f8af5f7e..732f62e04ddb851f47248013fac01bd62633aaf7 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -140,6 +140,10 @@ struct pv_cpu_ops { void (*load_sp0)(unsigned long sp0); +#ifdef CONFIG_X86_IOPL_IOPERM + void (*update_io_bitmap)(void); +#endif + void (*wbinvd)(void); /* cpuid emulation, mostly so that caps bits can be disabled */ diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 2a85287b368521b317529e2bbd619287d8b85481..8521af3fef27f4fb103de37879c14724a9c3fe69 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -72,7 +72,7 @@ #define SECONDARY_EXEC_MODE_BASED_EPT_EXEC VMCS_CONTROL_BIT(MODE_BASED_EPT_EXEC) #define SECONDARY_EXEC_PT_USE_GPA VMCS_CONTROL_BIT(PT_USE_GPA) #define SECONDARY_EXEC_TSC_SCALING VMCS_CONTROL_BIT(TSC_SCALING) -#define SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE 0x04000000 +#define SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE VMCS_CONTROL_BIT(USR_WAIT_PAUSE) #define PIN_BASED_EXT_INTR_MASK VMCS_CONTROL_BIT(INTR_EXITING) #define PIN_BASED_NMI_EXITING VMCS_CONTROL_BIT(NMI_EXITING) diff --git a/arch/x86/include/asm/vmxfeatures.h b/arch/x86/include/asm/vmxfeatures.h index a50e4a0de31538fb90e1e5c98f05f68cfc153e9e..9915990fd8cfab51a9cd287017e2d71d93f1f3f0 100644 --- a/arch/x86/include/asm/vmxfeatures.h +++ b/arch/x86/include/asm/vmxfeatures.h @@ -81,6 +81,7 @@ #define VMX_FEATURE_MODE_BASED_EPT_EXEC ( 2*32+ 22) /* "ept_mode_based_exec" Enable separate EPT EXEC bits for supervisor vs. user */ #define VMX_FEATURE_PT_USE_GPA ( 2*32+ 24) /* "" Processor Trace logs GPAs */ #define VMX_FEATURE_TSC_SCALING ( 2*32+ 25) /* Scale hardware TSC when read in guest */ +#define VMX_FEATURE_USR_WAIT_PAUSE ( 2*32+ 26) /* Enable TPAUSE, UMONITOR, UMWAIT in guest */ #define VMX_FEATURE_ENCLV_EXITING ( 2*32+ 28) /* "" VM-Exit on ENCLV (leaf dependent) */ #endif /* _ASM_X86_VMXFEATURES_H */ diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 503d3f42da1676791d2c4f4a70bfad35743daf4c..3f3f780c8c6500e1a1ea52bc0585af93699572fe 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -390,6 +390,7 @@ struct kvm_sync_regs { #define KVM_STATE_NESTED_GUEST_MODE 0x00000001 #define KVM_STATE_NESTED_RUN_PENDING 0x00000002 #define KVM_STATE_NESTED_EVMCS 0x00000004 +#define KVM_STATE_NESTED_MTF_PENDING 0x00000008 #define KVM_STATE_NESTED_SMM_GUEST_MODE 0x00000001 #define KVM_STATE_NESTED_SMM_VMXON 0x00000002 diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 2c5676b0a6e7f72c70e6fbab2a8ae485e14e9220..48293d15f1e1d69705dfb7d0d1d780256db78e7c 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -838,13 +838,15 @@ static void free_moved_vector(struct apic_chip_data *apicd) bool managed = apicd->is_managed; /* - * This should never happen. Managed interrupts are not - * migrated except on CPU down, which does not involve the - * cleanup vector. But try to keep the accounting correct - * nevertheless. + * Managed interrupts are usually not migrated away + * from an online CPU, but CPU isolation 'managed_irq' + * can make that happen. + * 1) Activation does not take the isolation into account + * to keep the code simple + * 2) Migration away from an isolated CPU can happen when + * a non-isolated CPU which is in the calculated + * affinity mask comes online. */ - WARN_ON_ONCE(managed); - trace_vector_free_moved(apicd->irq, cpu, vector, managed); irq_matrix_free(vector_matrix, cpu, vector, managed); per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index ac83a0fef6285d9901bf44b2b5169ab9fef89698..1f875fbe13846a9bfc00582173e6aedc571cd3ca 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -28,6 +28,7 @@ static const int amd_erratum_383[]; static const int amd_erratum_400[]; +static const int amd_erratum_1054[]; static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum); /* @@ -972,6 +973,15 @@ static void init_amd(struct cpuinfo_x86 *c) /* AMD CPUs don't reset SS attributes on SYSRET, Xen does. */ if (!cpu_has(c, X86_FEATURE_XENPV)) set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); + + /* + * Turn on the Instructions Retired free counter on machines not + * susceptible to erratum #1054 "Instructions Retired Performance + * Counter May Be Inaccurate". + */ + if (cpu_has(c, X86_FEATURE_IRPERF) && + !cpu_has_amd_erratum(c, amd_erratum_1054)) + msr_set_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT); } #ifdef CONFIG_X86_32 @@ -1099,6 +1109,10 @@ static const int amd_erratum_400[] = static const int amd_erratum_383[] = AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf)); +/* #1054: Instructions Retired Performance Counter May Be Inaccurate */ +static const int amd_erratum_1054[] = + AMD_OSVW_ERRATUM(0, AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf)); + static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) { diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 52c9bfbbdb2a04dbdbd7288de4bcfe7be8f44851..4cdb123ff66a8dddd24a69987f78c37af7e28b8a 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -445,7 +445,7 @@ static __always_inline void setup_pku(struct cpuinfo_x86 *c) * cpuid bit to be set. We need to ensure that we * update that bit in this CPU's "cpu_info". */ - get_cpu_cap(c); + set_cpu_cap(c, X86_FEATURE_OSPKE); } #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index b3a50d962851cec722df10623dbc90e6a3f16985..52de616a806559d6e0a25a5f65e3bef721432f48 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -1163,9 +1163,12 @@ static const struct sysfs_ops threshold_ops = { .store = store, }; +static void threshold_block_release(struct kobject *kobj); + static struct kobj_type threshold_ktype = { .sysfs_ops = &threshold_ops, .default_attrs = default_attrs, + .release = threshold_block_release, }; static const char *get_name(unsigned int bank, struct threshold_block *b) @@ -1198,8 +1201,9 @@ static const char *get_name(unsigned int bank, struct threshold_block *b) return buf_mcatype; } -static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank, - unsigned int block, u32 address) +static int allocate_threshold_blocks(unsigned int cpu, struct threshold_bank *tb, + unsigned int bank, unsigned int block, + u32 address) { struct threshold_block *b = NULL; u32 low, high; @@ -1243,16 +1247,12 @@ static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank, INIT_LIST_HEAD(&b->miscj); - if (per_cpu(threshold_banks, cpu)[bank]->blocks) { - list_add(&b->miscj, - &per_cpu(threshold_banks, cpu)[bank]->blocks->miscj); - } else { - per_cpu(threshold_banks, cpu)[bank]->blocks = b; - } + if (tb->blocks) + list_add(&b->miscj, &tb->blocks->miscj); + else + tb->blocks = b; - err = kobject_init_and_add(&b->kobj, &threshold_ktype, - per_cpu(threshold_banks, cpu)[bank]->kobj, - get_name(bank, b)); + err = kobject_init_and_add(&b->kobj, &threshold_ktype, tb->kobj, get_name(bank, b)); if (err) goto out_free; recurse: @@ -1260,7 +1260,7 @@ static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank, if (!address) return 0; - err = allocate_threshold_blocks(cpu, bank, block, address); + err = allocate_threshold_blocks(cpu, tb, bank, block, address); if (err) goto out_free; @@ -1345,8 +1345,6 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) goto out_free; } - per_cpu(threshold_banks, cpu)[bank] = b; - if (is_shared_bank(bank)) { refcount_set(&b->cpus, 1); @@ -1357,9 +1355,13 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) } } - err = allocate_threshold_blocks(cpu, bank, 0, msr_ops.misc(bank)); - if (!err) - goto out; + err = allocate_threshold_blocks(cpu, b, bank, 0, msr_ops.misc(bank)); + if (err) + goto out_free; + + per_cpu(threshold_banks, cpu)[bank] = b; + + return 0; out_free: kfree(b); @@ -1368,8 +1370,12 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) return err; } -static void deallocate_threshold_block(unsigned int cpu, - unsigned int bank) +static void threshold_block_release(struct kobject *kobj) +{ + kfree(to_block(kobj)); +} + +static void deallocate_threshold_block(unsigned int cpu, unsigned int bank) { struct threshold_block *pos = NULL; struct threshold_block *tmp = NULL; @@ -1379,13 +1385,11 @@ static void deallocate_threshold_block(unsigned int cpu, return; list_for_each_entry_safe(pos, tmp, &head->blocks->miscj, miscj) { - kobject_put(&pos->kobj); list_del(&pos->miscj); - kfree(pos); + kobject_put(&pos->kobj); } - kfree(per_cpu(threshold_banks, cpu)[bank]->blocks); - per_cpu(threshold_banks, cpu)[bank]->blocks = NULL; + kobject_put(&head->blocks->kobj); } static void __threshold_remove_blocks(struct threshold_bank *b) diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index 5627b1091b85639eb800a592d882832d81d1a941..f996ffb887bc09ca2ea64d221f14ef86f3c0006a 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -493,17 +493,18 @@ static void intel_ppin_init(struct cpuinfo_x86 *c) return; if ((val & 3UL) == 1UL) { - /* PPIN available but disabled: */ + /* PPIN locked in disabled mode */ return; } - /* If PPIN is disabled, but not locked, try to enable: */ - if (!(val & 3UL)) { + /* If PPIN is disabled, try to enable */ + if (!(val & 2UL)) { wrmsrl_safe(MSR_PPIN_CTL, val | 2UL); rdmsrl_safe(MSR_PPIN_CTL, &val); } - if ((val & 3UL) == 2UL) + /* Is the enable bit set? */ + if (val & 2UL) set_cpu_cap(c, X86_FEATURE_INTEL_PPIN); } } diff --git a/arch/x86/kernel/cpu/mce/therm_throt.c b/arch/x86/kernel/cpu/mce/therm_throt.c index 58b4ee3cda7774c096cbbac4841976344bbe79a0..f36dc07420851b90759349d7ffe3caf3eac34012 100644 --- a/arch/x86/kernel/cpu/mce/therm_throt.c +++ b/arch/x86/kernel/cpu/mce/therm_throt.c @@ -486,9 +486,14 @@ static int thermal_throttle_offline(unsigned int cpu) { struct thermal_state *state = &per_cpu(thermal_state, cpu); struct device *dev = get_cpu_device(cpu); + u32 l; + + /* Mask the thermal vector before draining evtl. pending work */ + l = apic_read(APIC_LVTTHMR); + apic_write(APIC_LVTTHMR, l | APIC_LVT_MASKED); - cancel_delayed_work(&state->package_throttle.therm_work); - cancel_delayed_work(&state->core_throttle.therm_work); + cancel_delayed_work_sync(&state->package_throttle.therm_work); + cancel_delayed_work_sync(&state->core_throttle.therm_work); state->package_throttle.rate_control_active = false; state->core_throttle.rate_control_active = false; diff --git a/arch/x86/kernel/ima_arch.c b/arch/x86/kernel/ima_arch.c index 4d4f5d9faac314ad5fe5c21a05e72c873ec42d65..23054909c8ddfa4258fc9004877f6ceb88ef0786 100644 --- a/arch/x86/kernel/ima_arch.c +++ b/arch/x86/kernel/ima_arch.c @@ -10,8 +10,6 @@ extern struct boot_params boot_params; static enum efi_secureboot_mode get_sb_mode(void) { - efi_char16_t efi_SecureBoot_name[] = L"SecureBoot"; - efi_char16_t efi_SetupMode_name[] = L"SecureBoot"; efi_guid_t efi_variable_guid = EFI_GLOBAL_VARIABLE_GUID; efi_status_t status; unsigned long size; @@ -25,7 +23,7 @@ static enum efi_secureboot_mode get_sb_mode(void) } /* Get variable contents into buffer */ - status = efi.get_variable(efi_SecureBoot_name, &efi_variable_guid, + status = efi.get_variable(L"SecureBoot", &efi_variable_guid, NULL, &size, &secboot); if (status == EFI_NOT_FOUND) { pr_info("ima: secureboot mode disabled\n"); @@ -38,7 +36,7 @@ static enum efi_secureboot_mode get_sb_mode(void) } size = sizeof(setupmode); - status = efi.get_variable(efi_SetupMode_name, &efi_variable_guid, + status = efi.get_variable(L"SetupMode", &efi_variable_guid, NULL, &size, &setupmode); if (status != EFI_SUCCESS) /* ignore unknown SetupMode */ diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index d817f255aed8e0b083bb04dfbce257c8c3b02a58..6efe0410fb728995ea8944ecd984840b6f30778e 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -425,7 +425,29 @@ static void __init sev_map_percpu_data(void) } } +static bool pv_tlb_flush_supported(void) +{ + return (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && + !kvm_para_has_hint(KVM_HINTS_REALTIME) && + kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)); +} + +static DEFINE_PER_CPU(cpumask_var_t, __pv_cpu_mask); + #ifdef CONFIG_SMP + +static bool pv_ipi_supported(void) +{ + return kvm_para_has_feature(KVM_FEATURE_PV_SEND_IPI); +} + +static bool pv_sched_yield_supported(void) +{ + return (kvm_para_has_feature(KVM_FEATURE_PV_SCHED_YIELD) && + !kvm_para_has_hint(KVM_HINTS_REALTIME) && + kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)); +} + #define KVM_IPI_CLUSTER_SIZE (2 * BITS_PER_LONG) static void __send_ipi_mask(const struct cpumask *mask, int vector) @@ -490,12 +512,12 @@ static void kvm_send_ipi_mask(const struct cpumask *mask, int vector) static void kvm_send_ipi_mask_allbutself(const struct cpumask *mask, int vector) { unsigned int this_cpu = smp_processor_id(); - struct cpumask new_mask; + struct cpumask *new_mask = this_cpu_cpumask_var_ptr(__pv_cpu_mask); const struct cpumask *local_mask; - cpumask_copy(&new_mask, mask); - cpumask_clear_cpu(this_cpu, &new_mask); - local_mask = &new_mask; + cpumask_copy(new_mask, mask); + cpumask_clear_cpu(this_cpu, new_mask); + local_mask = new_mask; __send_ipi_mask(local_mask, vector); } @@ -575,7 +597,6 @@ static void __init kvm_apf_trap_init(void) update_intr_gate(X86_TRAP_PF, async_page_fault); } -static DEFINE_PER_CPU(cpumask_var_t, __pv_tlb_mask); static void kvm_flush_tlb_others(const struct cpumask *cpumask, const struct flush_tlb_info *info) @@ -583,7 +604,7 @@ static void kvm_flush_tlb_others(const struct cpumask *cpumask, u8 state; int cpu; struct kvm_steal_time *src; - struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_tlb_mask); + struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_cpu_mask); cpumask_copy(flushmask, cpumask); /* @@ -619,11 +640,10 @@ static void __init kvm_guest_init(void) pv_ops.time.steal_clock = kvm_steal_clock; } - if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && - !kvm_para_has_hint(KVM_HINTS_REALTIME) && - kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { + if (pv_tlb_flush_supported()) { pv_ops.mmu.flush_tlb_others = kvm_flush_tlb_others; pv_ops.mmu.tlb_remove_table = tlb_remove_table; + pr_info("KVM setup pv remote TLB flush\n"); } if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) @@ -632,9 +652,7 @@ static void __init kvm_guest_init(void) #ifdef CONFIG_SMP smp_ops.smp_prepare_cpus = kvm_smp_prepare_cpus; smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu; - if (kvm_para_has_feature(KVM_FEATURE_PV_SCHED_YIELD) && - !kvm_para_has_hint(KVM_HINTS_REALTIME) && - kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { + if (pv_sched_yield_supported()) { smp_ops.send_call_func_ipi = kvm_smp_send_call_func_ipi; pr_info("KVM setup pv sched yield\n"); } @@ -700,7 +718,7 @@ static uint32_t __init kvm_detect(void) static void __init kvm_apic_init(void) { #if defined(CONFIG_SMP) - if (kvm_para_has_feature(KVM_FEATURE_PV_SEND_IPI)) + if (pv_ipi_supported()) kvm_setup_pv_ipi(); #endif } @@ -732,26 +750,31 @@ static __init int activate_jump_labels(void) } arch_initcall(activate_jump_labels); -static __init int kvm_setup_pv_tlb_flush(void) +static __init int kvm_alloc_cpumask(void) { int cpu; + bool alloc = false; if (!kvm_para_available() || nopv) return 0; - if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && - !kvm_para_has_hint(KVM_HINTS_REALTIME) && - kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { + if (pv_tlb_flush_supported()) + alloc = true; + +#if defined(CONFIG_SMP) + if (pv_ipi_supported()) + alloc = true; +#endif + + if (alloc) for_each_possible_cpu(cpu) { - zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu), + zalloc_cpumask_var_node(per_cpu_ptr(&__pv_cpu_mask, cpu), GFP_KERNEL, cpu_to_node(cpu)); } - pr_info("KVM setup pv remote TLB flush\n"); - } return 0; } -arch_initcall(kvm_setup_pv_tlb_flush); +arch_initcall(kvm_alloc_cpumask); #ifdef CONFIG_PARAVIRT_SPINLOCKS diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 789f5e4f89defc97f1daaf801c9929d616237b55..c131ba4e70ef8229d2c9f1722f88d100f942489e 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -30,6 +30,7 @@ #include #include #include +#include /* * nop stub, which must not clobber anything *including the stack* to @@ -341,6 +342,10 @@ struct paravirt_patch_template pv_ops = { .cpu.iret = native_iret, .cpu.swapgs = native_swapgs, +#ifdef CONFIG_X86_IOPL_IOPERM + .cpu.update_io_bitmap = native_tss_update_io_bitmap, +#endif + .cpu.start_context_switch = paravirt_nop, .cpu.end_context_switch = paravirt_nop, diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 839b5244e3b7e17767fc69bc610ac7c9a487c7fd..3053c85e0e42db9abbb5261673fa78e897efe20e 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -374,7 +374,7 @@ static void tss_copy_io_bitmap(struct tss_struct *tss, struct io_bitmap *iobm) /** * tss_update_io_bitmap - Update I/O bitmap before exiting to usermode */ -void tss_update_io_bitmap(void) +void native_tss_update_io_bitmap(void) { struct tss_struct *tss = this_cpu_ptr(&cpu_tss_rw); struct thread_struct *t = ¤t->thread; diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 991019d5eee1e03c21bd20a6e88ee209696304e0..9fea0757db9226653c611233470ae092fda6e762 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -59,6 +59,19 @@ config KVM If unsure, say N. +config KVM_WERROR + bool "Compile KVM with -Werror" + # KASAN may cause the build to fail due to larger frames + default y if X86_64 && !KASAN + # We use the dependency on !COMPILE_TEST to not be enabled + # blindly in allmodconfig or allyesconfig configurations + depends on (X86_64 && !KASAN) || !COMPILE_TEST + depends on EXPERT + help + Add -Werror to the build flags for KVM. + + If in doubt, say "N". + config KVM_INTEL tristate "KVM for Intel (and compatible) processors support" depends on KVM && IA32_FEAT_CTL diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index b19ef421084dff20ba0ce8b61c98c0c8878ef41b..e553f0fdd87d47dbd0fe4dc5cb79f5e5421e0e64 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 ccflags-y += -Iarch/x86/kvm +ccflags-$(CONFIG_KVM_WERROR) += -Werror KVM := ../../../virt/kvm diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index ddbc61984227c3dbee763ed3759e9a5351f32606..bc00642e5d3b7b158cb410ed6d39a1724661904b 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -191,25 +191,6 @@ #define NR_FASTOP (ilog2(sizeof(ulong)) + 1) #define FASTOP_SIZE 8 -/* - * fastop functions have a special calling convention: - * - * dst: rax (in/out) - * src: rdx (in/out) - * src2: rcx (in) - * flags: rflags (in/out) - * ex: rsi (in:fastop pointer, out:zero if exception) - * - * Moreover, they are all exactly FASTOP_SIZE bytes long, so functions for - * different operand sizes can be reached by calculation, rather than a jump - * table (which would be bigger than the code). - * - * fastop functions are declared as taking a never-defined fastop parameter, - * so they can't be called from C directly. - */ - -struct fastop; - struct opcode { u64 flags : 56; u64 intercept : 8; @@ -311,8 +292,19 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt) #define ON64(x) #endif -typedef void (*fastop_t)(struct fastop *); - +/* + * fastop functions have a special calling convention: + * + * dst: rax (in/out) + * src: rdx (in/out) + * src2: rcx (in) + * flags: rflags (in/out) + * ex: rsi (in:fastop pointer, out:zero if exception) + * + * Moreover, they are all exactly FASTOP_SIZE bytes long, so functions for + * different operand sizes can be reached by calculation, rather than a jump + * table (which would be bigger than the code). + */ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop); #define __FOP_FUNC(name) \ @@ -5181,6 +5173,7 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) ctxt->fetch.ptr = ctxt->fetch.data; ctxt->fetch.end = ctxt->fetch.data + insn_len; ctxt->opcode_len = 1; + ctxt->intercept = x86_intercept_none; if (insn_len > 0) memcpy(ctxt->fetch.data, insn, insn_len); else { @@ -5683,7 +5676,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) if (ctxt->execute) { if (ctxt->d & Fastop) - rc = fastop(ctxt, (fastop_t)ctxt->execute); + rc = fastop(ctxt, ctxt->fop); else rc = ctxt->execute(ctxt); if (rc != X86EMUL_CONTINUE) diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 7668fed1ce6527767fbf6c8e10647c6627686f58..750ff0b294047cf83b2c28f72cfbd057375fc7b1 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -378,12 +378,15 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) if (e->fields.delivery_mode == APIC_DM_FIXED) { struct kvm_lapic_irq irq; - irq.shorthand = APIC_DEST_NOSHORT; irq.vector = e->fields.vector; irq.delivery_mode = e->fields.delivery_mode << 8; - irq.dest_id = e->fields.dest_id; irq.dest_mode = kvm_lapic_irq_dest_mode(!!e->fields.dest_mode); + irq.level = false; + irq.trig_mode = e->fields.trig_mode; + irq.shorthand = APIC_DEST_NOSHORT; + irq.dest_id = e->fields.dest_id; + irq.msi_redir_hint = false; bitmap_zero(&vcpu_bitmap, 16); kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq, &vcpu_bitmap); diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 79afa0bb5f410f701e18370b38f9aeb182f53cfc..c47d2acec52934eae639a8c4b347fbfa660caca6 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -417,7 +417,7 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, kvm_set_msi_irq(vcpu->kvm, entry, &irq); - if (irq.level && + if (irq.trig_mode && kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT, irq.dest_id, irq.dest_mode)) __set_bit(irq.vector, ioapic_handled_vectors); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index eafc631d305cc1951273c8d17fb0c5d17621dd49..e3099c642fecfbbb6cd7b4df4a0df2a9b8091d73 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -627,9 +627,11 @@ static inline bool pv_eoi_enabled(struct kvm_vcpu *vcpu) static bool pv_eoi_get_pending(struct kvm_vcpu *vcpu) { u8 val; - if (pv_eoi_get_user(vcpu, &val) < 0) + if (pv_eoi_get_user(vcpu, &val) < 0) { printk(KERN_WARNING "Can't read EOI MSR value: 0x%llx\n", (unsigned long long)vcpu->arch.pv_eoi.msr_val); + return false; + } return val & 0x1; } @@ -1046,11 +1048,8 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, apic->regs + APIC_TMR); } - if (vcpu->arch.apicv_active) - kvm_x86_ops->deliver_posted_interrupt(vcpu, vector); - else { + if (kvm_x86_ops->deliver_posted_interrupt(vcpu, vector)) { kvm_lapic_set_irr(vector, apic); - kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); } @@ -1080,9 +1079,6 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, result = 1; /* assumes that there are only KVM_APIC_INIT/SIPI */ apic->pending_events = (1UL << KVM_APIC_INIT); - /* make sure pending_events is visible before sending - * the request */ - smp_wmb(); kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); } diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index d55674f44a18b52ac81b9daa3088a7ba442fe2cc..a647601c9e1c1ddc06dfb030b81cf74d61b97db6 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -102,6 +102,19 @@ static inline void kvm_mmu_load_cr3(struct kvm_vcpu *vcpu) kvm_get_active_pcid(vcpu)); } +int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, + bool prefault); + +static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + u32 err, bool prefault) +{ +#ifdef CONFIG_RETPOLINE + if (likely(vcpu->arch.mmu->page_fault == kvm_tdp_page_fault)) + return kvm_tdp_page_fault(vcpu, cr2_or_gpa, err, prefault); +#endif + return vcpu->arch.mmu->page_fault(vcpu, cr2_or_gpa, err, prefault); +} + /* * Currently, we have two sorts of write-protection, a) the first one * write-protects guest page to sync the guest modification, b) another one is diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 7011a4e54866728815cae8deb1c7bdcc5e6320ec..87e9ba27ada14bd7dc932ed518be82e0fb49321a 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4219,8 +4219,8 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, } EXPORT_SYMBOL_GPL(kvm_handle_page_fault); -static int tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, - bool prefault) +int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, + bool prefault) { int max_level; @@ -4925,7 +4925,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) return; context->mmu_role.as_u64 = new_role.as_u64; - context->page_fault = tdp_page_fault; + context->page_fault = kvm_tdp_page_fault; context->sync_page = nonpaging_sync_page; context->invlpg = nonpaging_invlpg; context->update_pte = nonpaging_update_pte; @@ -5436,9 +5436,8 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, } if (r == RET_PF_INVALID) { - r = vcpu->arch.mmu->page_fault(vcpu, cr2_or_gpa, - lower_32_bits(error_code), - false); + r = kvm_mmu_do_page_fault(vcpu, cr2_or_gpa, + lower_32_bits(error_code), false); WARN_ON(r == RET_PF_INVALID); } diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 4e1ef047366344c8704651e0b1f3eeddbda74b51..e4c8a4cbf40706367c1ef69b1b524c14de0e27fa 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -33,7 +33,7 @@ #define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT #define PT_HAVE_ACCESSED_DIRTY(mmu) true #ifdef CONFIG_X86_64 - #define PT_MAX_FULL_LEVELS 4 + #define PT_MAX_FULL_LEVELS PT64_ROOT_MAX_LEVEL #define CMPXCHG cmpxchg #else #define CMPXCHG cmpxchg64 diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index 3c6522b84ff1175a64fef95e119e213c272bc873..ffcd96fc02d0a4892ee4573d9a7a2791f4cf0c69 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -339,7 +339,7 @@ TRACE_EVENT( /* These depend on page entry type, so compute them now. */ __field(bool, r) __field(bool, x) - __field(u8, u) + __field(signed char, u) ), TP_fast_assign( diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index a3e32d61d60ceb2d403a425bf92aa6e5d9cae578..91000501756ec04214ca14f6083440d2a351d1a4 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -57,11 +57,13 @@ MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); +#ifdef MODULE static const struct x86_cpu_id svm_cpu_id[] = { X86_FEATURE_MATCH(X86_FEATURE_SVM), {} }; MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id); +#endif #define IOPM_ALLOC_ORDER 2 #define MSRPM_ALLOC_ORDER 1 @@ -1005,33 +1007,32 @@ static void svm_cpu_uninit(int cpu) static int svm_cpu_init(int cpu) { struct svm_cpu_data *sd; - int r; sd = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL); if (!sd) return -ENOMEM; sd->cpu = cpu; - r = -ENOMEM; sd->save_area = alloc_page(GFP_KERNEL); if (!sd->save_area) - goto err_1; + goto free_cpu_data; if (svm_sev_enabled()) { - r = -ENOMEM; sd->sev_vmcbs = kmalloc_array(max_sev_asid + 1, sizeof(void *), GFP_KERNEL); if (!sd->sev_vmcbs) - goto err_1; + goto free_save_area; } per_cpu(svm_data, cpu) = sd; return 0; -err_1: +free_save_area: + __free_page(sd->save_area); +free_cpu_data: kfree(sd); - return r; + return -ENOMEM; } @@ -1350,6 +1351,24 @@ static __init void svm_adjust_mmio_mask(void) kvm_mmu_set_mmio_spte_mask(mask, mask, PT_WRITABLE_MASK | PT_USER_MASK); } +static void svm_hardware_teardown(void) +{ + int cpu; + + if (svm_sev_enabled()) { + bitmap_free(sev_asid_bitmap); + bitmap_free(sev_reclaim_asid_bitmap); + + sev_flush_asids(); + } + + for_each_possible_cpu(cpu) + svm_cpu_uninit(cpu); + + __free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER); + iopm_base = 0; +} + static __init int svm_hardware_setup(void) { int cpu; @@ -1463,29 +1482,10 @@ static __init int svm_hardware_setup(void) return 0; err: - __free_pages(iopm_pages, IOPM_ALLOC_ORDER); - iopm_base = 0; + svm_hardware_teardown(); return r; } -static __exit void svm_hardware_unsetup(void) -{ - int cpu; - - if (svm_sev_enabled()) { - bitmap_free(sev_asid_bitmap); - bitmap_free(sev_reclaim_asid_bitmap); - - sev_flush_asids(); - } - - for_each_possible_cpu(cpu) - svm_cpu_uninit(cpu); - - __free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER); - iopm_base = 0; -} - static void init_seg(struct vmcb_seg *seg) { seg->selector = 0; @@ -2175,7 +2175,6 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) u32 dummy; u32 eax = 1; - vcpu->arch.microcode_version = 0x01000065; svm->spec_ctrl = 0; svm->virt_spec_ctrl = 0; @@ -2197,8 +2196,9 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) static int avic_init_vcpu(struct vcpu_svm *svm) { int ret; + struct kvm_vcpu *vcpu = &svm->vcpu; - if (!kvm_vcpu_apicv_active(&svm->vcpu)) + if (!avic || !irqchip_in_kernel(vcpu->kvm)) return 0; ret = avic_init_backing_page(&svm->vcpu); @@ -2266,6 +2266,7 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu) init_vmcb(svm); svm_init_osvw(vcpu); + vcpu->arch.microcode_version = 0x01000065; return 0; @@ -5232,6 +5233,9 @@ static void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) struct vmcb *vmcb = svm->vmcb; bool activated = kvm_vcpu_apicv_active(vcpu); + if (!avic) + return; + if (activated) { /** * During AVIC temporary deactivation, guest could update @@ -5255,8 +5259,11 @@ static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) return; } -static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) +static int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) { + if (!vcpu->arch.apicv_active) + return -1; + kvm_lapic_set_irr(vec, vcpu->arch.apic); smp_mb__after_atomic(); @@ -5268,6 +5275,8 @@ static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) put_cpu(); } else kvm_vcpu_wake_up(vcpu); + + return 0; } static bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu) @@ -6303,7 +6312,8 @@ static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu, enum exit_fastpath_completion *exit_fastpath) { if (!is_guest_mode(vcpu) && - to_svm(vcpu)->vmcb->control.exit_code == EXIT_REASON_MSR_WRITE) + to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_MSR && + to_svm(vcpu)->vmcb->control.exit_info_1) *exit_fastpath = handle_fastpath_set_msr_irqoff(vcpu); } @@ -7378,7 +7388,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .cpu_has_kvm_support = has_svm, .disabled_by_bios = is_disabled, .hardware_setup = svm_hardware_setup, - .hardware_unsetup = svm_hardware_unsetup, + .hardware_unsetup = svm_hardware_teardown, .check_processor_compatibility = svm_check_processor_compat, .hardware_enable = svm_hardware_enable, .hardware_disable = svm_hardware_disable, @@ -7433,6 +7443,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .run = svm_vcpu_run, .handle_exit = handle_exit, .skip_emulated_instruction = skip_emulated_instruction, + .update_emulated_instruction = NULL, .set_interrupt_shadow = svm_set_interrupt_shadow, .get_interrupt_shadow = svm_get_interrupt_shadow, .patch_hypercall = svm_patch_hypercall, diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 283bdb7071af604453e081f30baec3bcdd938dac..f486e260624740e8fd57683b001beb4737593c60 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -12,6 +12,7 @@ extern bool __read_mostly enable_ept; extern bool __read_mostly enable_unrestricted_guest; extern bool __read_mostly enable_ept_ad_bits; extern bool __read_mostly enable_pml; +extern bool __read_mostly enable_apicv; extern int __read_mostly pt_mode; #define PT_MODE_SYSTEM 0 diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 657c2eda357cdb47af83468f327045e49ee69a6c..9750e590c89d75e14c174e8ae64df2ccdfd25d61 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -224,7 +224,7 @@ static inline void nested_release_evmcs(struct kvm_vcpu *vcpu) return; kvm_vcpu_unmap(vcpu, &vmx->nested.hv_evmcs_map, true); - vmx->nested.hv_evmcs_vmptr = -1ull; + vmx->nested.hv_evmcs_vmptr = 0; vmx->nested.hv_evmcs = NULL; } @@ -544,7 +544,8 @@ static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1, } } -static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) { +static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) +{ int msr; for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { @@ -1922,7 +1923,8 @@ static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu, if (!nested_enlightened_vmentry(vcpu, &evmcs_gpa)) return 1; - if (unlikely(evmcs_gpa != vmx->nested.hv_evmcs_vmptr)) { + if (unlikely(!vmx->nested.hv_evmcs || + evmcs_gpa != vmx->nested.hv_evmcs_vmptr)) { if (!vmx->nested.hv_evmcs) vmx->nested.current_vmptr = -1ull; @@ -1981,7 +1983,7 @@ static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu, } /* - * Clean fields data can't de used on VMLAUNCH and when we switch + * Clean fields data can't be used on VMLAUNCH and when we switch * between different L2 guests as KVM keeps a single VMCS12 per L1. */ if (from_launch || evmcs_gpa_changed) @@ -3160,10 +3162,10 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, * or KVM_SET_NESTED_STATE). Otherwise it's called from vmlaunch/vmresume. * * Returns: - * NVMX_ENTRY_SUCCESS: Entered VMX non-root mode - * NVMX_ENTRY_VMFAIL: Consistency check VMFail - * NVMX_ENTRY_VMEXIT: Consistency check VMExit - * NVMX_ENTRY_KVM_INTERNAL_ERROR: KVM internal error + * NVMX_VMENTRY_SUCCESS: Entered VMX non-root mode + * NVMX_VMENTRY_VMFAIL: Consistency check VMFail + * NVMX_VMENTRY_VMEXIT: Consistency check VMExit + * NVMX_VMENTRY_KVM_INTERNAL_ERROR: KVM internal error */ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) @@ -3575,25 +3577,80 @@ static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu, nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, intr_info, exit_qual); } +/* + * Returns true if a debug trap is pending delivery. + * + * In KVM, debug traps bear an exception payload. As such, the class of a #DB + * exception may be inferred from the presence of an exception payload. + */ +static inline bool vmx_pending_dbg_trap(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.exception.pending && + vcpu->arch.exception.nr == DB_VECTOR && + vcpu->arch.exception.payload; +} + +/* + * Certain VM-exits set the 'pending debug exceptions' field to indicate a + * recognized #DB (data or single-step) that has yet to be delivered. Since KVM + * represents these debug traps with a payload that is said to be compatible + * with the 'pending debug exceptions' field, write the payload to the VMCS + * field if a VM-exit is delivered before the debug trap. + */ +static void nested_vmx_update_pending_dbg(struct kvm_vcpu *vcpu) +{ + if (vmx_pending_dbg_trap(vcpu)) + vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, + vcpu->arch.exception.payload); +} + static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long exit_qual; bool block_nested_events = vmx->nested.nested_run_pending || kvm_event_needs_reinjection(vcpu); + bool mtf_pending = vmx->nested.mtf_pending; struct kvm_lapic *apic = vcpu->arch.apic; + /* + * Clear the MTF state. If a higher priority VM-exit is delivered first, + * this state is discarded. + */ + vmx->nested.mtf_pending = false; + if (lapic_in_kernel(vcpu) && test_bit(KVM_APIC_INIT, &apic->pending_events)) { if (block_nested_events) return -EBUSY; + nested_vmx_update_pending_dbg(vcpu); clear_bit(KVM_APIC_INIT, &apic->pending_events); nested_vmx_vmexit(vcpu, EXIT_REASON_INIT_SIGNAL, 0, 0); return 0; } + /* + * Process any exceptions that are not debug traps before MTF. + */ + if (vcpu->arch.exception.pending && + !vmx_pending_dbg_trap(vcpu) && + nested_vmx_check_exception(vcpu, &exit_qual)) { + if (block_nested_events) + return -EBUSY; + nested_vmx_inject_exception_vmexit(vcpu, exit_qual); + return 0; + } + + if (mtf_pending) { + if (block_nested_events) + return -EBUSY; + nested_vmx_update_pending_dbg(vcpu); + nested_vmx_vmexit(vcpu, EXIT_REASON_MONITOR_TRAP_FLAG, 0, 0); + return 0; + } + if (vcpu->arch.exception.pending && - nested_vmx_check_exception(vcpu, &exit_qual)) { + nested_vmx_check_exception(vcpu, &exit_qual)) { if (block_nested_events) return -EBUSY; nested_vmx_inject_exception_vmexit(vcpu, exit_qual); @@ -5256,24 +5313,17 @@ static int handle_vmfunc(struct kvm_vcpu *vcpu) return 1; } - -static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, - struct vmcs12 *vmcs12) +/* + * Return true if an IO instruction with the specified port and size should cause + * a VM-exit into L1. + */ +bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port, + int size) { - unsigned long exit_qualification; + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); gpa_t bitmap, last_bitmap; - unsigned int port; - int size; u8 b; - if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) - return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING); - - exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - - port = exit_qualification >> 16; - size = (exit_qualification & 7) + 1; - last_bitmap = (gpa_t)-1; b = -1; @@ -5300,8 +5350,26 @@ static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, return false; } +static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) +{ + unsigned long exit_qualification; + unsigned short port; + int size; + + if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) + return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING); + + exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + + port = exit_qualification >> 16; + size = (exit_qualification & 7) + 1; + + return nested_vmx_check_io_bitmaps(vcpu, port, size); +} + /* - * Return 1 if we should exit from L2 to L1 to handle an MSR access access, + * Return 1 if we should exit from L2 to L1 to handle an MSR access, * rather than handle it ourselves in L0. I.e., check whether L1 expressed * disinterest in the current event (read or write a specific MSR) by using an * MSR bitmap. This may be the case even when L0 doesn't use MSR bitmaps. @@ -5683,6 +5751,9 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, if (vmx->nested.nested_run_pending) kvm_state.flags |= KVM_STATE_NESTED_RUN_PENDING; + + if (vmx->nested.mtf_pending) + kvm_state.flags |= KVM_STATE_NESTED_MTF_PENDING; } } @@ -5863,6 +5934,9 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, vmx->nested.nested_run_pending = !!(kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING); + vmx->nested.mtf_pending = + !!(kvm_state->flags & KVM_STATE_NESTED_MTF_PENDING); + ret = -EINVAL; if (nested_cpu_has_shadow_vmcs(vmcs12) && vmcs12->vmcs_link_pointer != -1ull) { @@ -5920,8 +5994,7 @@ void nested_vmx_set_vmcs_shadowing_bitmap(void) * bit in the high half is on if the corresponding bit in the control field * may be on. See also vmx_control_verify(). */ -void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps, - bool apicv) +void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) { /* * Note that as a general rule, the high half of the MSRs (bits in @@ -5948,7 +6021,7 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps, PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING | PIN_BASED_VIRTUAL_NMIS | - (apicv ? PIN_BASED_POSTED_INTR : 0); + (enable_apicv ? PIN_BASED_POSTED_INTR : 0); msrs->pinbased_ctls_high |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | PIN_BASED_VMX_PREEMPTION_TIMER; diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index fc874d4ead0f07613eaa95880ee623f490e04418..9aeda46f473ee380f6764b59641805e5a343fec1 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -17,8 +17,7 @@ enum nvmx_vmentry_status { }; void vmx_leave_nested(struct kvm_vcpu *vcpu); -void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps, - bool apicv); +void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps); void nested_vmx_hardware_unsetup(void); __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)); void nested_vmx_set_vmcs_shadowing_bitmap(void); @@ -34,6 +33,8 @@ int vmx_get_vmx_msr(struct nested_vmx_msrs *msrs, u32 msr_index, u64 *pdata); int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, u32 vmx_instruction_info, bool wr, int len, gva_t *ret); void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu); +bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port, + int size); static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu) { @@ -175,6 +176,11 @@ static inline bool nested_cpu_has_virtual_nmis(struct vmcs12 *vmcs12) return vmcs12->pin_based_vm_exec_control & PIN_BASED_VIRTUAL_NMIS; } +static inline int nested_cpu_has_mtf(struct vmcs12 *vmcs12) +{ + return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_TRAP_FLAG); +} + static inline int nested_cpu_has_ept(struct vmcs12 *vmcs12) { return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_EPT); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 9a6664886f2eff53fa478088dc65d488f7806667..26f8f31563e9b7b766d2fdbda135592085b3f148 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -64,11 +64,13 @@ MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); +#ifdef MODULE static const struct x86_cpu_id vmx_cpu_id[] = { X86_FEATURE_MATCH(X86_FEATURE_VMX), {} }; MODULE_DEVICE_TABLE(x86cpu, vmx_cpu_id); +#endif bool __read_mostly enable_vpid = 1; module_param_named(vpid, enable_vpid, bool, 0444); @@ -95,7 +97,7 @@ module_param(emulate_invalid_guest_state, bool, S_IRUGO); static bool __read_mostly fasteoi = 1; module_param(fasteoi, bool, S_IRUGO); -static bool __read_mostly enable_apicv = 1; +bool __read_mostly enable_apicv = 1; module_param(enable_apicv, bool, S_IRUGO); /* @@ -1175,6 +1177,10 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) vmx->guest_msrs[i].mask); } + + if (vmx->nested.need_vmcs12_to_shadow_sync) + nested_sync_vmcs12_to_shadow(vcpu); + if (vmx->guest_state_loaded) return; @@ -1599,6 +1605,40 @@ static int skip_emulated_instruction(struct kvm_vcpu *vcpu) return 1; } + +/* + * Recognizes a pending MTF VM-exit and records the nested state for later + * delivery. + */ +static void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + struct vcpu_vmx *vmx = to_vmx(vcpu); + + if (!is_guest_mode(vcpu)) + return; + + /* + * Per the SDM, MTF takes priority over debug-trap exceptions besides + * T-bit traps. As instruction emulation is completed (i.e. at the + * instruction boundary), any #DB exception pending delivery must be a + * debug-trap. Record the pending MTF state to be delivered in + * vmx_check_nested_events(). + */ + if (nested_cpu_has_mtf(vmcs12) && + (!vcpu->arch.exception.pending || + vcpu->arch.exception.nr == DB_VECTOR)) + vmx->nested.mtf_pending = true; + else + vmx->nested.mtf_pending = false; +} + +static int vmx_skip_emulated_instruction(struct kvm_vcpu *vcpu) +{ + vmx_update_emulated_instruction(vcpu); + return skip_emulated_instruction(vcpu); +} + static void vmx_clear_hlt(struct kvm_vcpu *vcpu) { /* @@ -2298,6 +2338,17 @@ static void hardware_disable(void) kvm_cpu_vmxoff(); } +/* + * There is no X86_FEATURE for SGX yet, but anyway we need to query CPUID + * directly instead of going through cpu_has(), to ensure KVM is trapping + * ENCLS whenever it's supported in hardware. It does not matter whether + * the host OS supports or has enabled SGX. + */ +static bool cpu_has_sgx(void) +{ + return cpuid_eax(0) >= 0x12 && (cpuid_eax(0x12) & BIT(0)); +} + static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, u32 msr, u32 *result) { @@ -2378,8 +2429,9 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | SECONDARY_EXEC_PT_USE_GPA | SECONDARY_EXEC_PT_CONCEAL_VMX | - SECONDARY_EXEC_ENABLE_VMFUNC | - SECONDARY_EXEC_ENCLS_EXITING; + SECONDARY_EXEC_ENABLE_VMFUNC; + if (cpu_has_sgx()) + opt2 |= SECONDARY_EXEC_ENCLS_EXITING; if (adjust_vmx_controls(min2, opt2, MSR_IA32_VMX_PROCBASED_CTLS2, &_cpu_based_2nd_exec_control) < 0) @@ -2947,6 +2999,9 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) static int get_ept_level(struct kvm_vcpu *vcpu) { + /* Nested EPT currently only supports 4-level walks. */ + if (is_guest_mode(vcpu) && nested_cpu_has_ept(get_vmcs12(vcpu))) + return 4; if (cpu_has_vmx_ept_5levels() && (cpuid_maxphyaddr(vcpu) > 48)) return 5; return 4; @@ -3815,24 +3870,29 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, * 2. If target vcpu isn't running(root mode), kick it to pick up the * interrupt from PIR in next vmentry. */ -static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) +static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) { struct vcpu_vmx *vmx = to_vmx(vcpu); int r; r = vmx_deliver_nested_posted_interrupt(vcpu, vector); if (!r) - return; + return 0; + + if (!vcpu->arch.apicv_active) + return -1; if (pi_test_and_set_pir(vector, &vmx->pi_desc)) - return; + return 0; /* If a previous notification has sent the IPI, nothing to do. */ if (pi_test_and_set_on(&vmx->pi_desc)) - return; + return 0; if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false)) kvm_vcpu_kick(vcpu); + + return 0; } /* @@ -4238,7 +4298,6 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmx->msr_ia32_umwait_control = 0; - vcpu->arch.microcode_version = 0x100000000ULL; vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val(); vmx->hv_deadline_tsc = -1; kvm_set_cr8(vcpu, 0); @@ -6480,8 +6539,11 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) vmcs_write32(PLE_WINDOW, vmx->ple_window); } - if (vmx->nested.need_vmcs12_to_shadow_sync) - nested_sync_vmcs12_to_shadow(vcpu); + /* + * We did this in prepare_switch_to_guest, because it needs to + * be within srcu_read_lock. + */ + WARN_ON_ONCE(vmx->nested.need_vmcs12_to_shadow_sync); if (kvm_register_is_dirty(vcpu, VCPU_REGS_RSP)) vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]); @@ -6755,14 +6817,14 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) if (nested) nested_vmx_setup_ctls_msrs(&vmx->nested.msrs, - vmx_capability.ept, - kvm_vcpu_apicv_active(vcpu)); + vmx_capability.ept); else memset(&vmx->nested.msrs, 0, sizeof(vmx->nested.msrs)); vmx->nested.posted_intr_nv = -1; vmx->nested.current_vmptr = -1ull; + vcpu->arch.microcode_version = 0x100000000ULL; vmx->msr_ia32_feature_control_valid_bits = FEAT_CTL_LOCKED; /* @@ -6836,8 +6898,7 @@ static int __init vmx_check_processor_compat(void) if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0) return -EIO; if (nested) - nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept, - enable_apicv); + nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept); if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) { printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n", smp_processor_id()); @@ -7098,6 +7159,40 @@ static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu) to_vmx(vcpu)->req_immediate_exit = true; } +static int vmx_check_intercept_io(struct kvm_vcpu *vcpu, + struct x86_instruction_info *info) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + unsigned short port; + bool intercept; + int size; + + if (info->intercept == x86_intercept_in || + info->intercept == x86_intercept_ins) { + port = info->src_val; + size = info->dst_bytes; + } else { + port = info->dst_val; + size = info->src_bytes; + } + + /* + * If the 'use IO bitmaps' VM-execution control is 0, IO instruction + * VM-exits depend on the 'unconditional IO exiting' VM-execution + * control. + * + * Otherwise, IO instruction VM-exits are controlled by the IO bitmaps. + */ + if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) + intercept = nested_cpu_has(vmcs12, + CPU_BASED_UNCOND_IO_EXITING); + else + intercept = nested_vmx_check_io_bitmaps(vcpu, port, size); + + /* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED. */ + return intercept ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE; +} + static int vmx_check_intercept(struct kvm_vcpu *vcpu, struct x86_instruction_info *info, enum x86_intercept_stage stage) @@ -7105,19 +7200,45 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + switch (info->intercept) { /* * RDPID causes #UD if disabled through secondary execution controls. * Because it is marked as EmulateOnUD, we need to intercept it here. */ - if (info->intercept == x86_intercept_rdtscp && - !nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) { - ctxt->exception.vector = UD_VECTOR; - ctxt->exception.error_code_valid = false; - return X86EMUL_PROPAGATE_FAULT; - } + case x86_intercept_rdtscp: + if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) { + ctxt->exception.vector = UD_VECTOR; + ctxt->exception.error_code_valid = false; + return X86EMUL_PROPAGATE_FAULT; + } + break; + + case x86_intercept_in: + case x86_intercept_ins: + case x86_intercept_out: + case x86_intercept_outs: + return vmx_check_intercept_io(vcpu, info); + + case x86_intercept_lgdt: + case x86_intercept_lidt: + case x86_intercept_lldt: + case x86_intercept_ltr: + case x86_intercept_sgdt: + case x86_intercept_sidt: + case x86_intercept_sldt: + case x86_intercept_str: + if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_DESC)) + return X86EMUL_CONTINUE; + + /* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED. */ + break; /* TODO: check more intercepts... */ - return X86EMUL_CONTINUE; + default: + break; + } + + return X86EMUL_UNHANDLEABLE; } #ifdef CONFIG_X86_64 @@ -7699,7 +7820,7 @@ static __init int hardware_setup(void) if (nested) { nested_vmx_setup_ctls_msrs(&vmcs_config.nested, - vmx_capability.ept, enable_apicv); + vmx_capability.ept); r = nested_vmx_hardware_setup(kvm_vmx_exit_handlers); if (r) @@ -7783,7 +7904,8 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .run = vmx_vcpu_run, .handle_exit = vmx_handle_exit, - .skip_emulated_instruction = skip_emulated_instruction, + .skip_emulated_instruction = vmx_skip_emulated_instruction, + .update_emulated_instruction = vmx_update_emulated_instruction, .set_interrupt_shadow = vmx_set_interrupt_shadow, .get_interrupt_shadow = vmx_get_interrupt_shadow, .patch_hypercall = vmx_patch_hypercall, diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 7f42cf3dcd7002bd41c3702b457bfc507c800978..e64da06c70092362ed29964fcc12c7bab6a2a228 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -150,6 +150,9 @@ struct nested_vmx { /* L2 must run next, and mustn't decide to exit to L1. */ bool nested_run_pending; + /* Pending MTF VM-exit into L1. */ + bool mtf_pending; + struct loaded_vmcs vmcs02; /* diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index fbabb2f06273b831ad15a97e4be9289ac3c0e15d..3156e25b077495c823594f84004491ffcc782551 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -438,6 +438,14 @@ void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu) * for #DB exceptions under VMX. */ vcpu->arch.dr6 ^= payload & DR6_RTM; + + /* + * The #DB payload is defined as compatible with the 'pending + * debug exceptions' field under VMX, not DR6. While bit 12 is + * defined in the 'pending debug exceptions' field (enabled + * breakpoint), it is reserved and must be zero in DR6. + */ + vcpu->arch.dr6 &= ~BIT(12); break; case PF_VECTOR: vcpu->arch.cr2 = payload; @@ -490,19 +498,7 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu, vcpu->arch.exception.error_code = error_code; vcpu->arch.exception.has_payload = has_payload; vcpu->arch.exception.payload = payload; - /* - * In guest mode, payload delivery should be deferred, - * so that the L1 hypervisor can intercept #PF before - * CR2 is modified (or intercept #DB before DR6 is - * modified under nVMX). However, for ABI - * compatibility with KVM_GET_VCPU_EVENTS and - * KVM_SET_VCPU_EVENTS, we can't delay payload - * delivery unless userspace has enabled this - * functionality via the per-VM capability, - * KVM_CAP_EXCEPTION_PAYLOAD. - */ - if (!vcpu->kvm->arch.exception_payload_enabled || - !is_guest_mode(vcpu)) + if (!is_guest_mode(vcpu)) kvm_deliver_exception_payload(vcpu); return; } @@ -2448,7 +2444,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) vcpu->hv_clock.tsc_timestamp = tsc_timestamp; vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset; vcpu->last_guest_tsc = tsc_timestamp; - WARN_ON(vcpu->hv_clock.system_time < 0); + WARN_ON((s64)vcpu->hv_clock.system_time < 0); /* If the host uses TSC clocksource, then it is stable */ pvclock_flags = 0; @@ -3795,6 +3791,21 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, { process_nmi(vcpu); + /* + * In guest mode, payload delivery should be deferred, + * so that the L1 hypervisor can intercept #PF before + * CR2 is modified (or intercept #DB before DR6 is + * modified under nVMX). Unless the per-VM capability, + * KVM_CAP_EXCEPTION_PAYLOAD, is set, we may not defer the delivery of + * an exception payload and handle after a KVM_GET_VCPU_EVENTS. Since we + * opportunistically defer the exception payload, deliver it if the + * capability hasn't been requested before processing a + * KVM_GET_VCPU_EVENTS. + */ + if (!vcpu->kvm->arch.exception_payload_enabled && + vcpu->arch.exception.pending && vcpu->arch.exception.has_payload) + kvm_deliver_exception_payload(vcpu); + /* * The API doesn't provide the instruction length for software * exceptions, so don't report them. As long as the guest RIP @@ -6880,6 +6891,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, kvm_rip_write(vcpu, ctxt->eip); if (r && ctxt->tf) r = kvm_vcpu_do_singlestep(vcpu); + if (kvm_x86_ops->update_emulated_instruction) + kvm_x86_ops->update_emulated_instruction(vcpu); __kvm_set_rflags(vcpu, ctxt->eflags); } @@ -7177,14 +7190,16 @@ static void kvm_timer_init(void) if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { #ifdef CONFIG_CPU_FREQ - struct cpufreq_policy policy; + struct cpufreq_policy *policy; int cpu; - memset(&policy, 0, sizeof(policy)); cpu = get_cpu(); - cpufreq_get_policy(&policy, cpu); - if (policy.cpuinfo.max_freq) - max_tsc_khz = policy.cpuinfo.max_freq; + policy = cpufreq_cpu_get(cpu); + if (policy) { + if (policy->cpuinfo.max_freq) + max_tsc_khz = policy->cpuinfo.max_freq; + cpufreq_cpu_put(policy); + } put_cpu(); #endif cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block, @@ -7295,12 +7310,12 @@ int kvm_arch_init(void *opaque) } if (!ops->cpu_has_kvm_support()) { - printk(KERN_ERR "kvm: no hardware support\n"); + pr_err_ratelimited("kvm: no hardware support\n"); r = -EOPNOTSUPP; goto out; } if (ops->disabled_by_bios()) { - printk(KERN_ERR "kvm: disabled by bios\n"); + pr_err_ratelimited("kvm: disabled by bios\n"); r = -EOPNOTSUPP; goto out; } @@ -8942,7 +8957,6 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index, kvm_rip_write(vcpu, ctxt->eip); kvm_set_rflags(vcpu, ctxt->eflags); - kvm_make_request(KVM_REQ_EVENT, vcpu); return 1; } EXPORT_SYMBOL_GPL(kvm_task_switch); @@ -10182,7 +10196,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) work->arch.cr3 != vcpu->arch.mmu->get_cr3(vcpu)) return; - vcpu->arch.mmu->page_fault(vcpu, work->cr2_or_gpa, 0, true); + kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true); } static inline u32 kvm_async_pf_hash_fn(gfn_t gfn) diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 64229dad7eab6ce868957491431b62b51a2bee95..69309cd56fdf3fb28c8b7732297471ba69f46686 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -363,13 +363,8 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, { const struct ptdump_range ptdump_ranges[] = { #ifdef CONFIG_X86_64 - -#define normalize_addr_shift (64 - (__VIRTUAL_MASK_SHIFT + 1)) -#define normalize_addr(u) ((signed long)((u) << normalize_addr_shift) >> \ - normalize_addr_shift) - {0, PTRS_PER_PGD * PGD_LEVEL_MULT / 2}, - {normalize_addr(PTRS_PER_PGD * PGD_LEVEL_MULT / 2), ~0UL}, + {GUARD_HOLE_END_ADDR, ~0UL}, #else {0, ~0UL}, #endif diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index fa4ea09593abb0b3f63cee1b910f78f4828789b6..629fdf13f846562a9884a71e5c65d11319642b22 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -190,7 +190,7 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address) return pmd_k; } -void vmalloc_sync_all(void) +static void vmalloc_sync(void) { unsigned long address; @@ -217,6 +217,16 @@ void vmalloc_sync_all(void) } } +void vmalloc_sync_mappings(void) +{ + vmalloc_sync(); +} + +void vmalloc_sync_unmappings(void) +{ + vmalloc_sync(); +} + /* * 32-bit: * @@ -319,11 +329,23 @@ static void dump_pagetable(unsigned long address) #else /* CONFIG_X86_64: */ -void vmalloc_sync_all(void) +void vmalloc_sync_mappings(void) { + /* + * 64-bit mappings might allocate new p4d/pud pages + * that need to be propagated to all tasks' PGDs. + */ sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END); } +void vmalloc_sync_unmappings(void) +{ + /* + * Unmappings never allocate or free p4d/pud pages. + * No work is required here. + */ +} + /* * 64-bit: * diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 44e4beb4239f93bb83876bd21ab6f8007460be71..935a91e1fd7744a6af7e5e3bd1206ad4d197b067 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -106,6 +106,19 @@ static unsigned int __ioremap_check_encrypted(struct resource *res) return 0; } +/* + * The EFI runtime services data area is not covered by walk_mem_res(), but must + * be mapped encrypted when SEV is active. + */ +static void __ioremap_check_other(resource_size_t addr, struct ioremap_desc *desc) +{ + if (!sev_active()) + return; + + if (efi_mem_type(addr) == EFI_RUNTIME_SERVICES_DATA) + desc->flags |= IORES_MAP_ENCRYPTED; +} + static int __ioremap_collect_map_flags(struct resource *res, void *arg) { struct ioremap_desc *desc = arg; @@ -124,6 +137,9 @@ static int __ioremap_collect_map_flags(struct resource *res, void *arg) * To avoid multiple resource walks, this function walks resources marked as * IORESOURCE_MEM and IORESOURCE_BUSY and looking for system RAM and/or a * resource described not as IORES_DESC_NONE (e.g. IORES_DESC_ACPI_TABLES). + * + * After that, deal with misc other ranges in __ioremap_check_other() which do + * not fall into the above category. */ static void __ioremap_check_mem(resource_size_t addr, unsigned long size, struct ioremap_desc *desc) @@ -135,6 +151,8 @@ static void __ioremap_check_mem(resource_size_t addr, unsigned long size, memset(desc, 0, sizeof(struct ioremap_desc)); walk_mem_res(start, end, desc, __ioremap_collect_map_flags); + + __ioremap_check_other(addr, desc); } /* diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index fa8506e76bbeba3eb7b2efc75ff96767d41f6b6b..d19a2edd63cb224e33408d094d0df58f6ed3508c 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -180,7 +180,7 @@ void efi_sync_low_kernel_mappings(void) static inline phys_addr_t virt_to_phys_or_null_size(void *va, unsigned long size) { - bool bad_size; + phys_addr_t pa; if (!va) return 0; @@ -188,16 +188,13 @@ virt_to_phys_or_null_size(void *va, unsigned long size) if (virt_addr_valid(va)) return virt_to_phys(va); - /* - * A fully aligned variable on the stack is guaranteed not to - * cross a page bounary. Try to catch strings on the stack by - * checking that 'size' is a power of two. - */ - bad_size = size > PAGE_SIZE || !is_power_of_2(size); + pa = slow_virt_to_phys(va); - WARN_ON(!IS_ALIGNED((unsigned long)va, size) || bad_size); + /* check if the object crosses a page boundary */ + if (WARN_ON((pa ^ (pa + size - 1)) & PAGE_MASK)) + return 0; - return slow_virt_to_phys(va); + return pa; } #define virt_to_phys_or_null(addr) \ @@ -568,85 +565,25 @@ efi_thunk_set_virtual_address_map(unsigned long memory_map_size, static efi_status_t efi_thunk_get_time(efi_time_t *tm, efi_time_cap_t *tc) { - efi_status_t status; - u32 phys_tm, phys_tc; - unsigned long flags; - - spin_lock(&rtc_lock); - spin_lock_irqsave(&efi_runtime_lock, flags); - - phys_tm = virt_to_phys_or_null(tm); - phys_tc = virt_to_phys_or_null(tc); - - status = efi_thunk(get_time, phys_tm, phys_tc); - - spin_unlock_irqrestore(&efi_runtime_lock, flags); - spin_unlock(&rtc_lock); - - return status; + return EFI_UNSUPPORTED; } static efi_status_t efi_thunk_set_time(efi_time_t *tm) { - efi_status_t status; - u32 phys_tm; - unsigned long flags; - - spin_lock(&rtc_lock); - spin_lock_irqsave(&efi_runtime_lock, flags); - - phys_tm = virt_to_phys_or_null(tm); - - status = efi_thunk(set_time, phys_tm); - - spin_unlock_irqrestore(&efi_runtime_lock, flags); - spin_unlock(&rtc_lock); - - return status; + return EFI_UNSUPPORTED; } static efi_status_t efi_thunk_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending, efi_time_t *tm) { - efi_status_t status; - u32 phys_enabled, phys_pending, phys_tm; - unsigned long flags; - - spin_lock(&rtc_lock); - spin_lock_irqsave(&efi_runtime_lock, flags); - - phys_enabled = virt_to_phys_or_null(enabled); - phys_pending = virt_to_phys_or_null(pending); - phys_tm = virt_to_phys_or_null(tm); - - status = efi_thunk(get_wakeup_time, phys_enabled, - phys_pending, phys_tm); - - spin_unlock_irqrestore(&efi_runtime_lock, flags); - spin_unlock(&rtc_lock); - - return status; + return EFI_UNSUPPORTED; } static efi_status_t efi_thunk_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm) { - efi_status_t status; - u32 phys_tm; - unsigned long flags; - - spin_lock(&rtc_lock); - spin_lock_irqsave(&efi_runtime_lock, flags); - - phys_tm = virt_to_phys_or_null(tm); - - status = efi_thunk(set_wakeup_time, enabled, phys_tm); - - spin_unlock_irqrestore(&efi_runtime_lock, flags); - spin_unlock(&rtc_lock); - - return status; + return EFI_UNSUPPORTED; } static unsigned long efi_name_size(efi_char16_t *name) @@ -658,6 +595,8 @@ static efi_status_t efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor, u32 *attr, unsigned long *data_size, void *data) { + u8 buf[24] __aligned(8); + efi_guid_t *vnd = PTR_ALIGN((efi_guid_t *)buf, sizeof(*vnd)); efi_status_t status; u32 phys_name, phys_vendor, phys_attr; u32 phys_data_size, phys_data; @@ -665,14 +604,19 @@ efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor, spin_lock_irqsave(&efi_runtime_lock, flags); + *vnd = *vendor; + phys_data_size = virt_to_phys_or_null(data_size); - phys_vendor = virt_to_phys_or_null(vendor); + phys_vendor = virt_to_phys_or_null(vnd); phys_name = virt_to_phys_or_null_size(name, efi_name_size(name)); phys_attr = virt_to_phys_or_null(attr); phys_data = virt_to_phys_or_null_size(data, *data_size); - status = efi_thunk(get_variable, phys_name, phys_vendor, - phys_attr, phys_data_size, phys_data); + if (!phys_name || (data && !phys_data)) + status = EFI_INVALID_PARAMETER; + else + status = efi_thunk(get_variable, phys_name, phys_vendor, + phys_attr, phys_data_size, phys_data); spin_unlock_irqrestore(&efi_runtime_lock, flags); @@ -683,19 +627,25 @@ static efi_status_t efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor, u32 attr, unsigned long data_size, void *data) { + u8 buf[24] __aligned(8); + efi_guid_t *vnd = PTR_ALIGN((efi_guid_t *)buf, sizeof(*vnd)); u32 phys_name, phys_vendor, phys_data; efi_status_t status; unsigned long flags; spin_lock_irqsave(&efi_runtime_lock, flags); + *vnd = *vendor; + phys_name = virt_to_phys_or_null_size(name, efi_name_size(name)); - phys_vendor = virt_to_phys_or_null(vendor); + phys_vendor = virt_to_phys_or_null(vnd); phys_data = virt_to_phys_or_null_size(data, data_size); - /* If data_size is > sizeof(u32) we've got problems */ - status = efi_thunk(set_variable, phys_name, phys_vendor, - attr, data_size, phys_data); + if (!phys_name || !phys_data) + status = EFI_INVALID_PARAMETER; + else + status = efi_thunk(set_variable, phys_name, phys_vendor, + attr, data_size, phys_data); spin_unlock_irqrestore(&efi_runtime_lock, flags); @@ -707,6 +657,8 @@ efi_thunk_set_variable_nonblocking(efi_char16_t *name, efi_guid_t *vendor, u32 attr, unsigned long data_size, void *data) { + u8 buf[24] __aligned(8); + efi_guid_t *vnd = PTR_ALIGN((efi_guid_t *)buf, sizeof(*vnd)); u32 phys_name, phys_vendor, phys_data; efi_status_t status; unsigned long flags; @@ -714,13 +666,17 @@ efi_thunk_set_variable_nonblocking(efi_char16_t *name, efi_guid_t *vendor, if (!spin_trylock_irqsave(&efi_runtime_lock, flags)) return EFI_NOT_READY; + *vnd = *vendor; + phys_name = virt_to_phys_or_null_size(name, efi_name_size(name)); - phys_vendor = virt_to_phys_or_null(vendor); + phys_vendor = virt_to_phys_or_null(vnd); phys_data = virt_to_phys_or_null_size(data, data_size); - /* If data_size is > sizeof(u32) we've got problems */ - status = efi_thunk(set_variable, phys_name, phys_vendor, - attr, data_size, phys_data); + if (!phys_name || !phys_data) + status = EFI_INVALID_PARAMETER; + else + status = efi_thunk(set_variable, phys_name, phys_vendor, + attr, data_size, phys_data); spin_unlock_irqrestore(&efi_runtime_lock, flags); @@ -732,39 +688,36 @@ efi_thunk_get_next_variable(unsigned long *name_size, efi_char16_t *name, efi_guid_t *vendor) { + u8 buf[24] __aligned(8); + efi_guid_t *vnd = PTR_ALIGN((efi_guid_t *)buf, sizeof(*vnd)); efi_status_t status; u32 phys_name_size, phys_name, phys_vendor; unsigned long flags; spin_lock_irqsave(&efi_runtime_lock, flags); + *vnd = *vendor; + phys_name_size = virt_to_phys_or_null(name_size); - phys_vendor = virt_to_phys_or_null(vendor); + phys_vendor = virt_to_phys_or_null(vnd); phys_name = virt_to_phys_or_null_size(name, *name_size); - status = efi_thunk(get_next_variable, phys_name_size, - phys_name, phys_vendor); + if (!phys_name) + status = EFI_INVALID_PARAMETER; + else + status = efi_thunk(get_next_variable, phys_name_size, + phys_name, phys_vendor); spin_unlock_irqrestore(&efi_runtime_lock, flags); + *vendor = *vnd; return status; } static efi_status_t efi_thunk_get_next_high_mono_count(u32 *count) { - efi_status_t status; - u32 phys_count; - unsigned long flags; - - spin_lock_irqsave(&efi_runtime_lock, flags); - - phys_count = virt_to_phys_or_null(count); - status = efi_thunk(get_next_high_mono_count, phys_count); - - spin_unlock_irqrestore(&efi_runtime_lock, flags); - - return status; + return EFI_UNSUPPORTED; } static void diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 1f756ffffe8b3159dade936c5eecda8d847900b8..507f4fb88fa7fd184d1bba278a9ebaa8c8039f37 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -72,6 +72,9 @@ #include #include #include +#ifdef CONFIG_X86_IOPL_IOPERM +#include +#endif #ifdef CONFIG_ACPI #include @@ -837,6 +840,25 @@ static void xen_load_sp0(unsigned long sp0) this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0); } +#ifdef CONFIG_X86_IOPL_IOPERM +static void xen_update_io_bitmap(void) +{ + struct physdev_set_iobitmap iobitmap; + struct tss_struct *tss = this_cpu_ptr(&cpu_tss_rw); + + native_tss_update_io_bitmap(); + + iobitmap.bitmap = (uint8_t *)(&tss->x86_tss) + + tss->x86_tss.io_bitmap_base; + if (tss->x86_tss.io_bitmap_base == IO_BITMAP_OFFSET_INVALID) + iobitmap.nr_ports = 0; + else + iobitmap.nr_ports = IO_BITMAP_BITS; + + HYPERVISOR_physdev_op(PHYSDEVOP_set_iobitmap, &iobitmap); +} +#endif + static void xen_io_delay(void) { } @@ -896,14 +918,15 @@ static u64 xen_read_msr_safe(unsigned int msr, int *err) static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high) { int ret; +#ifdef CONFIG_X86_64 + unsigned int which; + u64 base; +#endif ret = 0; switch (msr) { #ifdef CONFIG_X86_64 - unsigned which; - u64 base; - case MSR_FS_BASE: which = SEGBASE_FS; goto set; case MSR_KERNEL_GS_BASE: which = SEGBASE_GS_USER; goto set; case MSR_GS_BASE: which = SEGBASE_GS_KERNEL; goto set; @@ -1046,6 +1069,9 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .write_idt_entry = xen_write_idt_entry, .load_sp0 = xen_load_sp0, +#ifdef CONFIG_X86_IOPL_IOPERM + .update_io_bitmap = xen_update_io_bitmap, +#endif .io_delay = xen_io_delay, /* Xen takes care of %gs when switching to usermode for us */ diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index 09b69a3ed490362a13ff290b5d46ee1b477277ad..f0ff6654af2894359e54395fe72d0ce03f207406 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -610,12 +610,13 @@ struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd, */ entity = &bfqg->entity; for_each_entity(entity) { - bfqg = container_of(entity, struct bfq_group, entity); - if (bfqg != bfqd->root_group) { - parent = bfqg_parent(bfqg); + struct bfq_group *curr_bfqg = container_of(entity, + struct bfq_group, entity); + if (curr_bfqg != bfqd->root_group) { + parent = bfqg_parent(curr_bfqg); if (!parent) parent = bfqd->root_group; - bfq_group_set_parent(bfqg, parent); + bfq_group_set_parent(curr_bfqg, parent); } } diff --git a/block/blk-core.c b/block/blk-core.c index 089e890ab208fd01efbda68aea4fdb47aaab1353..60dc9552ef8de53f9ba4b5b2f996e93825731275 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1663,12 +1663,6 @@ int kblockd_schedule_work(struct work_struct *work) } EXPORT_SYMBOL(kblockd_schedule_work); -int kblockd_schedule_work_on(int cpu, struct work_struct *work) -{ - return queue_work_on(cpu, kblockd_workqueue, work); -} -EXPORT_SYMBOL(kblockd_schedule_work_on); - int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay) { diff --git a/block/blk-flush.c b/block/blk-flush.c index 3f977c517960e61dca951551d437b52abcacd588..5cc775bdb06acbfac9dbfa79551d97f28c5a97cb 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -412,7 +412,7 @@ void blk_insert_flush(struct request *rq) */ if ((policy & REQ_FSEQ_DATA) && !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) { - blk_mq_request_bypass_insert(rq, false); + blk_mq_request_bypass_insert(rq, false, false); return; } diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 27ca68621137ad5418e647c859b39b12a588f9c2..9a599cc28c290c7d79ef6512c5173a4ee7605bc5 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -1318,7 +1318,7 @@ static bool iocg_is_idle(struct ioc_gq *iocg) return false; /* is something in flight? */ - if (atomic64_read(&iocg->done_vtime) < atomic64_read(&iocg->vtime)) + if (atomic64_read(&iocg->done_vtime) != atomic64_read(&iocg->vtime)) return false; return true; diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index ca22afd47b3dcce1ea72da7f4a6218c4ac9d85b5..74cedea560348167ab951c53dc3d8e14fe4f70dc 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -361,13 +361,19 @@ static bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx, bool has_sched, struct request *rq) { - /* dispatch flush rq directly */ - if (rq->rq_flags & RQF_FLUSH_SEQ) { - spin_lock(&hctx->lock); - list_add(&rq->queuelist, &hctx->dispatch); - spin_unlock(&hctx->lock); + /* + * dispatch flush and passthrough rq directly + * + * passthrough request has to be added to hctx->dispatch directly. + * For some reason, device may be in one situation which can't + * handle FS request, so STS_RESOURCE is always returned and the + * FS request will be added to hctx->dispatch. However passthrough + * request may be required at that time for fixing the problem. If + * passthrough request is added to scheduler queue, there isn't any + * chance to dispatch it given we prioritize requests in hctx->dispatch. + */ + if ((rq->rq_flags & RQF_FLUSH_SEQ) || blk_rq_is_passthrough(rq)) return true; - } if (has_sched) rq->rq_flags |= RQF_SORTED; @@ -391,8 +397,32 @@ void blk_mq_sched_insert_request(struct request *rq, bool at_head, WARN_ON(e && (rq->tag != -1)); - if (blk_mq_sched_bypass_insert(hctx, !!e, rq)) + if (blk_mq_sched_bypass_insert(hctx, !!e, rq)) { + /* + * Firstly normal IO request is inserted to scheduler queue or + * sw queue, meantime we add flush request to dispatch queue( + * hctx->dispatch) directly and there is at most one in-flight + * flush request for each hw queue, so it doesn't matter to add + * flush request to tail or front of the dispatch queue. + * + * Secondly in case of NCQ, flush request belongs to non-NCQ + * command, and queueing it will fail when there is any + * in-flight normal IO request(NCQ command). When adding flush + * rq to the front of hctx->dispatch, it is easier to introduce + * extra time to flush rq's latency because of S_SCHED_RESTART + * compared with adding to the tail of dispatch queue, then + * chance of flush merge is increased, and less flush requests + * will be issued to controller. It is observed that ~10% time + * is saved in blktests block/004 on disk attached to AHCI/NCQ + * drive when adding flush rq to the front of hctx->dispatch. + * + * Simply queue flush rq to the front of hctx->dispatch so that + * intensive flush workloads can benefit in case of NCQ HW. + */ + at_head = (rq->rq_flags & RQF_FLUSH_SEQ) ? true : at_head; + blk_mq_request_bypass_insert(rq, at_head, false); goto run; + } if (e && e->type->ops.insert_requests) { LIST_HEAD(list); diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index fbacde454718583555b38f07d0fe88ad89b712c3..586c9d6e904ab8aade50bea050a5a973bb2a273e 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -183,8 +183,8 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data) return tag + tag_offset; } -void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags *tags, - struct blk_mq_ctx *ctx, unsigned int tag) +void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx, + unsigned int tag) { if (!blk_mq_tag_is_reserved(tags, tag)) { const int real_tag = tag - tags->nr_reserved_tags; diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h index 15bc74acb57eca1c56bf0564cb000c002ea08618..2b8321efb68206cce7a865e801bf5d980629a487 100644 --- a/block/blk-mq-tag.h +++ b/block/blk-mq-tag.h @@ -26,8 +26,8 @@ extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, unsigned int r extern void blk_mq_free_tags(struct blk_mq_tags *tags); extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data); -extern void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags *tags, - struct blk_mq_ctx *ctx, unsigned int tag); +extern void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx, + unsigned int tag); extern int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags **tags, unsigned int depth, bool can_grow); diff --git a/block/blk-mq.c b/block/blk-mq.c index a12b1763508d3194853b6d33a057a62da62ea0e0..d92088dec6c359afd83642af362372b651b3d7e9 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -477,9 +477,9 @@ static void __blk_mq_free_request(struct request *rq) blk_pm_mark_last_busy(rq); rq->mq_hctx = NULL; if (rq->tag != -1) - blk_mq_put_tag(hctx, hctx->tags, ctx, rq->tag); + blk_mq_put_tag(hctx->tags, ctx, rq->tag); if (sched_tag != -1) - blk_mq_put_tag(hctx, hctx->sched_tags, ctx, sched_tag); + blk_mq_put_tag(hctx->sched_tags, ctx, sched_tag); blk_mq_sched_restart(hctx); blk_queue_exit(q); } @@ -735,7 +735,7 @@ static void blk_mq_requeue_work(struct work_struct *work) * merge. */ if (rq->rq_flags & RQF_DONTPREP) - blk_mq_request_bypass_insert(rq, false); + blk_mq_request_bypass_insert(rq, false, false); else blk_mq_sched_insert_request(rq, true, false, false); } @@ -1286,7 +1286,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list, q->mq_ops->commit_rqs(hctx); spin_lock(&hctx->lock); - list_splice_init(list, &hctx->dispatch); + list_splice_tail_init(list, &hctx->dispatch); spin_unlock(&hctx->lock); /* @@ -1677,12 +1677,16 @@ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, * Should only be used carefully, when the caller knows we want to * bypass a potential IO scheduler on the target device. */ -void blk_mq_request_bypass_insert(struct request *rq, bool run_queue) +void blk_mq_request_bypass_insert(struct request *rq, bool at_head, + bool run_queue) { struct blk_mq_hw_ctx *hctx = rq->mq_hctx; spin_lock(&hctx->lock); - list_add_tail(&rq->queuelist, &hctx->dispatch); + if (at_head) + list_add(&rq->queuelist, &hctx->dispatch); + else + list_add_tail(&rq->queuelist, &hctx->dispatch); spin_unlock(&hctx->lock); if (run_queue) @@ -1849,7 +1853,7 @@ static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, if (bypass_insert) return BLK_STS_RESOURCE; - blk_mq_request_bypass_insert(rq, run_queue); + blk_mq_request_bypass_insert(rq, false, run_queue); return BLK_STS_OK; } @@ -1876,7 +1880,7 @@ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, ret = __blk_mq_try_issue_directly(hctx, rq, cookie, false, true); if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) - blk_mq_request_bypass_insert(rq, true); + blk_mq_request_bypass_insert(rq, false, true); else if (ret != BLK_STS_OK) blk_mq_end_request(rq, ret); @@ -1910,7 +1914,7 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, if (ret != BLK_STS_OK) { if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) { - blk_mq_request_bypass_insert(rq, + blk_mq_request_bypass_insert(rq, false, list_empty(list)); break; } @@ -3398,7 +3402,6 @@ static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb) } static unsigned long blk_mq_poll_nsecs(struct request_queue *q, - struct blk_mq_hw_ctx *hctx, struct request *rq) { unsigned long ret = 0; @@ -3431,7 +3434,6 @@ static unsigned long blk_mq_poll_nsecs(struct request_queue *q, } static bool blk_mq_poll_hybrid_sleep(struct request_queue *q, - struct blk_mq_hw_ctx *hctx, struct request *rq) { struct hrtimer_sleeper hs; @@ -3451,7 +3453,7 @@ static bool blk_mq_poll_hybrid_sleep(struct request_queue *q, if (q->poll_nsec > 0) nsecs = q->poll_nsec; else - nsecs = blk_mq_poll_nsecs(q, hctx, rq); + nsecs = blk_mq_poll_nsecs(q, rq); if (!nsecs) return false; @@ -3506,7 +3508,7 @@ static bool blk_mq_poll_hybrid(struct request_queue *q, return false; } - return blk_mq_poll_hybrid_sleep(q, hctx, rq); + return blk_mq_poll_hybrid_sleep(q, rq); } /** diff --git a/block/blk-mq.h b/block/blk-mq.h index eaaca8fc1c2874e77e9fce95964444ddaf280745..10bfdfb494faf4035f8be143f1cf6e47e32fe50c 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -66,7 +66,8 @@ int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, */ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, bool at_head); -void blk_mq_request_bypass_insert(struct request *rq, bool run_queue); +void blk_mq_request_bypass_insert(struct request *rq, bool at_head, + bool run_queue); void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx, struct list_head *list); @@ -199,7 +200,7 @@ static inline bool blk_mq_get_dispatch_budget(struct blk_mq_hw_ctx *hctx) static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx, struct request *rq) { - blk_mq_put_tag(hctx, hctx->tags, rq->mq_ctx, rq->tag); + blk_mq_put_tag(hctx->tags, rq->mq_ctx, rq->tag); rq->tag = -1; if (rq->rq_flags & RQF_MQ_INFLIGHT) { diff --git a/block/genhd.c b/block/genhd.c index ff6268970ddc069f84b3977069cca72ba10627c6..9c2e13ce0d19554a01eb72c03d5c0fcba7a67a5a 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -301,6 +301,42 @@ struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector) } EXPORT_SYMBOL_GPL(disk_map_sector_rcu); +/** + * disk_has_partitions + * @disk: gendisk of interest + * + * Walk through the partition table and check if valid partition exists. + * + * CONTEXT: + * Don't care. + * + * RETURNS: + * True if the gendisk has at least one valid non-zero size partition. + * Otherwise false. + */ +bool disk_has_partitions(struct gendisk *disk) +{ + struct disk_part_tbl *ptbl; + int i; + bool ret = false; + + rcu_read_lock(); + ptbl = rcu_dereference(disk->part_tbl); + + /* Iterate partitions skipping the whole device at index 0 */ + for (i = 1; i < ptbl->len; i++) { + if (rcu_dereference(ptbl->part[i])) { + ret = true; + break; + } + } + + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL_GPL(disk_has_partitions); + /* * Can be deleted altogether. Later. * diff --git a/crypto/Kconfig b/crypto/Kconfig index cdb51d4272d0cc7c972fe0aa1db5a612af4cc89c..c24a47406f8f57b7550a98a20654fde836d212d0 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -136,8 +136,6 @@ config CRYPTO_USER Userspace configuration for cryptographic instantiations such as cbc(aes). -if CRYPTO_MANAGER2 - config CRYPTO_MANAGER_DISABLE_TESTS bool "Disable run-time self tests" default y @@ -155,8 +153,6 @@ config CRYPTO_MANAGER_EXTRA_TESTS This is intended for developer use only, as these tests take much longer to run than the normal self tests. -endif # if CRYPTO_MANAGER2 - config CRYPTO_GF128MUL tristate diff --git a/crypto/hash_info.c b/crypto/hash_info.c index c754cb75dd1a96a5f52b39ed17adc6be45347345..a49ff96bde7784f9095ac7ecab8ff65124b7b17c 100644 --- a/crypto/hash_info.c +++ b/crypto/hash_info.c @@ -26,7 +26,7 @@ const char *const hash_algo_name[HASH_ALGO__LAST] = { [HASH_ALGO_TGR_128] = "tgr128", [HASH_ALGO_TGR_160] = "tgr160", [HASH_ALGO_TGR_192] = "tgr192", - [HASH_ALGO_SM3_256] = "sm3-256", + [HASH_ALGO_SM3_256] = "sm3", [HASH_ALGO_STREEBOG_256] = "streebog256", [HASH_ALGO_STREEBOG_512] = "streebog512", }; diff --git a/crypto/testmgr.c b/crypto/testmgr.c index 88f33c0efb2331a0922e10e8d017597a49ccc52c..ccb3d60729fc58c760dbd96b087aabe7bf2c1917 100644 --- a/crypto/testmgr.c +++ b/crypto/testmgr.c @@ -4436,6 +4436,15 @@ static const struct alg_test_desc alg_test_descs[] = { .cipher = __VECS(tf_cbc_tv_template) }, }, { +#if IS_ENABLED(CONFIG_CRYPTO_PAES_S390) + .alg = "cbc-paes-s390", + .fips_allowed = 1, + .test = alg_test_skcipher, + .suite = { + .cipher = __VECS(aes_cbc_tv_template) + } + }, { +#endif .alg = "cbcmac(aes)", .fips_allowed = 1, .test = alg_test_hash, @@ -4587,6 +4596,15 @@ static const struct alg_test_desc alg_test_descs[] = { .cipher = __VECS(tf_ctr_tv_template) } }, { +#if IS_ENABLED(CONFIG_CRYPTO_PAES_S390) + .alg = "ctr-paes-s390", + .fips_allowed = 1, + .test = alg_test_skcipher, + .suite = { + .cipher = __VECS(aes_ctr_tv_template) + } + }, { +#endif .alg = "cts(cbc(aes))", .test = alg_test_skcipher, .fips_allowed = 1, @@ -4879,6 +4897,15 @@ static const struct alg_test_desc alg_test_descs[] = { .cipher = __VECS(xtea_tv_template) } }, { +#if IS_ENABLED(CONFIG_CRYPTO_PAES_S390) + .alg = "ecb-paes-s390", + .fips_allowed = 1, + .test = alg_test_skcipher, + .suite = { + .cipher = __VECS(aes_tv_template) + } + }, { +#endif .alg = "ecdh", .test = alg_test_kpp, .fips_allowed = 1, @@ -5465,6 +5492,15 @@ static const struct alg_test_desc alg_test_descs[] = { .cipher = __VECS(tf_xts_tv_template) } }, { +#if IS_ENABLED(CONFIG_CRYPTO_PAES_S390) + .alg = "xts-paes-s390", + .fips_allowed = 1, + .test = alg_test_skcipher, + .suite = { + .cipher = __VECS(aes_xts_tv_template) + } + }, { +#endif .alg = "xts4096(paes)", .test = alg_test_null, .fips_allowed = 1, diff --git a/drivers/acpi/acpi_watchdog.c b/drivers/acpi/acpi_watchdog.c index b5516b04ffc07b95a5869678f0886499fa9553bc..6e9ec6e3fe47d63ea9adf07e540ac2a223379a06 100644 --- a/drivers/acpi/acpi_watchdog.c +++ b/drivers/acpi/acpi_watchdog.c @@ -55,12 +55,14 @@ static bool acpi_watchdog_uses_rtc(const struct acpi_table_wdat *wdat) } #endif +static bool acpi_no_watchdog; + static const struct acpi_table_wdat *acpi_watchdog_get_wdat(void) { const struct acpi_table_wdat *wdat = NULL; acpi_status status; - if (acpi_disabled) + if (acpi_disabled || acpi_no_watchdog) return NULL; status = acpi_get_table(ACPI_SIG_WDAT, 0, @@ -88,6 +90,14 @@ bool acpi_has_watchdog(void) } EXPORT_SYMBOL_GPL(acpi_has_watchdog); +/* ACPI watchdog can be disabled on boot command line */ +static int __init disable_acpi_watchdog(char *str) +{ + acpi_no_watchdog = true; + return 1; +} +__setup("acpi_no_watchdog", disable_acpi_watchdog); + void __init acpi_watchdog_init(void) { const struct acpi_wdat_entry *entries; @@ -126,12 +136,11 @@ void __init acpi_watchdog_init(void) gas = &entries[i].register_region; res.start = gas->address; + res.end = res.start + ACPI_ACCESS_BYTE_WIDTH(gas->access_width) - 1; if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) { res.flags = IORESOURCE_MEM; - res.end = res.start + ALIGN(gas->access_width, 4) - 1; } else if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_IO) { res.flags = IORESOURCE_IO; - res.end = res.start + gas->access_width - 1; } else { pr_warn("Unsupported address space: %u\n", gas->space_id); diff --git a/drivers/acpi/acpica/achware.h b/drivers/acpi/acpica/achware.h index 67f282e9e0af17500dde847bc8d4943a51e877be..6ad0517553d5e8f8386e4945cc562f31eb2dfd66 100644 --- a/drivers/acpi/acpica/achware.h +++ b/drivers/acpi/acpica/achware.h @@ -101,6 +101,8 @@ acpi_status acpi_hw_enable_all_runtime_gpes(void); acpi_status acpi_hw_enable_all_wakeup_gpes(void); +u8 acpi_hw_check_all_gpes(void); + acpi_status acpi_hw_enable_runtime_gpe_block(struct acpi_gpe_xrupt_info *gpe_xrupt_info, struct acpi_gpe_block_info *gpe_block, diff --git a/drivers/acpi/acpica/evevent.c b/drivers/acpi/acpica/evevent.c index 8c83d8c620dc3deb10dc9a5a61b75bd6b2b0251b..789d5e920aaf7084058512e09467b554a9b5120d 100644 --- a/drivers/acpi/acpica/evevent.c +++ b/drivers/acpi/acpica/evevent.c @@ -265,4 +265,49 @@ static u32 acpi_ev_fixed_event_dispatch(u32 event) handler) (acpi_gbl_fixed_event_handlers[event].context)); } +/******************************************************************************* + * + * FUNCTION: acpi_any_fixed_event_status_set + * + * PARAMETERS: None + * + * RETURN: TRUE or FALSE + * + * DESCRIPTION: Checks the PM status register for active fixed events + * + ******************************************************************************/ + +u32 acpi_any_fixed_event_status_set(void) +{ + acpi_status status; + u32 in_status; + u32 in_enable; + u32 i; + + status = acpi_hw_register_read(ACPI_REGISTER_PM1_ENABLE, &in_enable); + if (ACPI_FAILURE(status)) { + return (FALSE); + } + + status = acpi_hw_register_read(ACPI_REGISTER_PM1_STATUS, &in_status); + if (ACPI_FAILURE(status)) { + return (FALSE); + } + + /* + * Check for all possible Fixed Events and dispatch those that are active + */ + for (i = 0; i < ACPI_NUM_FIXED_EVENTS; i++) { + + /* Both the status and enable bits must be on for this event */ + + if ((in_status & acpi_gbl_fixed_event_info[i].status_bit_mask) && + (in_enable & acpi_gbl_fixed_event_info[i].enable_bit_mask)) { + return (TRUE); + } + } + + return (FALSE); +} + #endif /* !ACPI_REDUCED_HARDWARE */ diff --git a/drivers/acpi/acpica/evxfgpe.c b/drivers/acpi/acpica/evxfgpe.c index 2c39ff2a7406900ea593f6d7f886253410444379..f2de66bfd8a7cd8aea8c91954bf337cf14d4fc63 100644 --- a/drivers/acpi/acpica/evxfgpe.c +++ b/drivers/acpi/acpica/evxfgpe.c @@ -795,6 +795,38 @@ acpi_status acpi_enable_all_wakeup_gpes(void) ACPI_EXPORT_SYMBOL(acpi_enable_all_wakeup_gpes) +/****************************************************************************** + * + * FUNCTION: acpi_any_gpe_status_set + * + * PARAMETERS: None + * + * RETURN: Whether or not the status bit is set for any GPE + * + * DESCRIPTION: Check the status bits of all enabled GPEs and return TRUE if any + * of them is set or FALSE otherwise. + * + ******************************************************************************/ +u32 acpi_any_gpe_status_set(void) +{ + acpi_status status; + u8 ret; + + ACPI_FUNCTION_TRACE(acpi_any_gpe_status_set); + + status = acpi_ut_acquire_mutex(ACPI_MTX_EVENTS); + if (ACPI_FAILURE(status)) { + return (FALSE); + } + + ret = acpi_hw_check_all_gpes(); + (void)acpi_ut_release_mutex(ACPI_MTX_EVENTS); + + return (ret); +} + +ACPI_EXPORT_SYMBOL(acpi_any_gpe_status_set) + /******************************************************************************* * * FUNCTION: acpi_install_gpe_block diff --git a/drivers/acpi/acpica/hwgpe.c b/drivers/acpi/acpica/hwgpe.c index 1b4252bdcd0b1a6346a1dd1d375c3405ca7266e8..f4c285c2f5956da43d45a31daaa5bc2d3c4d74fe 100644 --- a/drivers/acpi/acpica/hwgpe.c +++ b/drivers/acpi/acpica/hwgpe.c @@ -444,6 +444,53 @@ acpi_hw_enable_wakeup_gpe_block(struct acpi_gpe_xrupt_info *gpe_xrupt_info, return (AE_OK); } +/****************************************************************************** + * + * FUNCTION: acpi_hw_get_gpe_block_status + * + * PARAMETERS: gpe_xrupt_info - GPE Interrupt info + * gpe_block - Gpe Block info + * + * RETURN: Success + * + * DESCRIPTION: Produce a combined GPE status bits mask for the given block. + * + ******************************************************************************/ + +static acpi_status +acpi_hw_get_gpe_block_status(struct acpi_gpe_xrupt_info *gpe_xrupt_info, + struct acpi_gpe_block_info *gpe_block, + void *ret_ptr) +{ + struct acpi_gpe_register_info *gpe_register_info; + u64 in_enable, in_status; + acpi_status status; + u8 *ret = ret_ptr; + u32 i; + + /* Examine each GPE Register within the block */ + + for (i = 0; i < gpe_block->register_count; i++) { + gpe_register_info = &gpe_block->register_info[i]; + + status = acpi_hw_read(&in_enable, + &gpe_register_info->enable_address); + if (ACPI_FAILURE(status)) { + continue; + } + + status = acpi_hw_read(&in_status, + &gpe_register_info->status_address); + if (ACPI_FAILURE(status)) { + continue; + } + + *ret |= in_enable & in_status; + } + + return (AE_OK); +} + /****************************************************************************** * * FUNCTION: acpi_hw_disable_all_gpes @@ -510,4 +557,28 @@ acpi_status acpi_hw_enable_all_wakeup_gpes(void) return_ACPI_STATUS(status); } +/****************************************************************************** + * + * FUNCTION: acpi_hw_check_all_gpes + * + * PARAMETERS: None + * + * RETURN: Combined status of all GPEs + * + * DESCRIPTION: Check all enabled GPEs in all GPE blocks and return TRUE if the + * status bit is set for at least one of them of FALSE otherwise. + * + ******************************************************************************/ + +u8 acpi_hw_check_all_gpes(void) +{ + u8 ret = 0; + + ACPI_FUNCTION_TRACE(acpi_hw_check_all_gpes); + + (void)acpi_ev_walk_gpe_list(acpi_hw_get_gpe_block_status, &ret); + + return (ret != 0); +} + #endif /* !ACPI_REDUCED_HARDWARE */ diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 103acbbfcf9a513ff219404e0fe8894df1f563db..24c9642e8fc70d272f71b083f703eb1a1095e564 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -171,7 +171,7 @@ int ghes_estatus_pool_init(int num_ghes) * New allocation must be visible in all pgd before it can be found by * an NMI allocating from the pool. */ - vmalloc_sync_all(); + vmalloc_sync_mappings(); rc = gen_pool_add(ghes_estatus_pool, addr, PAGE_ALIGN(len), -1); if (rc) diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 08bc9751fe6620f6e19f4356b7596c4a235feba6..d1f1cf5d4bf084e526ecb0f953f0097defd474d1 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -179,6 +179,7 @@ EXPORT_SYMBOL(first_ec); static struct acpi_ec *boot_ec; static bool boot_ec_is_ecdt = false; +static struct workqueue_struct *ec_wq; static struct workqueue_struct *ec_query_wq; static int EC_FLAGS_QUERY_HANDSHAKE; /* Needs QR_EC issued when SCI_EVT set */ @@ -469,7 +470,7 @@ static void acpi_ec_submit_query(struct acpi_ec *ec) ec_dbg_evt("Command(%s) submitted/blocked", acpi_ec_cmd_string(ACPI_EC_COMMAND_QUERY)); ec->nr_pending_queries++; - schedule_work(&ec->work); + queue_work(ec_wq, &ec->work); } } @@ -535,7 +536,7 @@ static void acpi_ec_enable_event(struct acpi_ec *ec) #ifdef CONFIG_PM_SLEEP static void __acpi_ec_flush_work(void) { - flush_scheduled_work(); /* flush ec->work */ + drain_workqueue(ec_wq); /* flush ec->work */ flush_workqueue(ec_query_wq); /* flush queries */ } @@ -556,8 +557,8 @@ static void acpi_ec_disable_event(struct acpi_ec *ec) void acpi_ec_flush_work(void) { - /* Without ec_query_wq there is nothing to flush. */ - if (!ec_query_wq) + /* Without ec_wq there is nothing to flush. */ + if (!ec_wq) return; __acpi_ec_flush_work(); @@ -2107,25 +2108,33 @@ static struct acpi_driver acpi_ec_driver = { .drv.pm = &acpi_ec_pm, }; -static inline int acpi_ec_query_init(void) +static void acpi_ec_destroy_workqueues(void) { - if (!ec_query_wq) { - ec_query_wq = alloc_workqueue("kec_query", 0, - ec_max_queries); - if (!ec_query_wq) - return -ENODEV; + if (ec_wq) { + destroy_workqueue(ec_wq); + ec_wq = NULL; } - return 0; -} - -static inline void acpi_ec_query_exit(void) -{ if (ec_query_wq) { destroy_workqueue(ec_query_wq); ec_query_wq = NULL; } } +static int acpi_ec_init_workqueues(void) +{ + if (!ec_wq) + ec_wq = alloc_ordered_workqueue("kec", 0); + + if (!ec_query_wq) + ec_query_wq = alloc_workqueue("kec_query", 0, ec_max_queries); + + if (!ec_wq || !ec_query_wq) { + acpi_ec_destroy_workqueues(); + return -ENODEV; + } + return 0; +} + static const struct dmi_system_id acpi_ec_no_wakeup[] = { { .ident = "Thinkpad X1 Carbon 6th", @@ -2156,8 +2165,7 @@ int __init acpi_ec_init(void) int result; int ecdt_fail, dsdt_fail; - /* register workqueue for _Qxx evaluations */ - result = acpi_ec_query_init(); + result = acpi_ec_init_workqueues(); if (result) return result; @@ -2188,6 +2196,6 @@ static void __exit acpi_ec_exit(void) { acpi_bus_unregister_driver(&acpi_ec_driver); - acpi_ec_query_exit(); + acpi_ec_destroy_workqueues(); } #endif /* 0 */ diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 4398806298398a78a3160ea13d212a2627a3f9c3..e5f95922bc217e42342cce186bf0968c7e7f31dd 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -990,21 +990,41 @@ static void acpi_s2idle_sync(void) acpi_os_wait_events_complete(); /* synchronize Notify handling */ } -static void acpi_s2idle_wake(void) +static bool acpi_s2idle_wake(void) { - /* - * If IRQD_WAKEUP_ARMED is set for the SCI at this point, the SCI has - * not triggered while suspended, so bail out. - */ - if (!acpi_sci_irq_valid() || - irqd_is_wakeup_armed(irq_get_irq_data(acpi_sci_irq))) - return; + if (!acpi_sci_irq_valid()) + return pm_wakeup_pending(); + + while (pm_wakeup_pending()) { + /* + * If IRQD_WAKEUP_ARMED is set for the SCI at this point, the + * SCI has not triggered while suspended, so bail out (the + * wakeup is pending anyway and the SCI is not the source of + * it). + */ + if (irqd_is_wakeup_armed(irq_get_irq_data(acpi_sci_irq))) + return true; + + /* + * If the status bit of any enabled fixed event is set, the + * wakeup is regarded as valid. + */ + if (acpi_any_fixed_event_status_set()) + return true; + + /* + * If there are no EC events to process and at least one of the + * other enabled GPEs is active, the wakeup is regarded as a + * genuine one. + * + * Note that the checks below must be carried out in this order + * to avoid returning prematurely due to a change of the EC GPE + * status bit from unset to set between the checks with the + * status bits of all the other GPEs unset. + */ + if (acpi_any_gpe_status_set() && !acpi_ec_dispatch_gpe()) + return true; - /* - * If there are EC events to process, the wakeup may be a spurious one - * coming from the EC. - */ - if (acpi_ec_dispatch_gpe()) { /* * Cancel the wakeup and process all pending events in case * there are any wakeup ones in there. @@ -1017,8 +1037,19 @@ static void acpi_s2idle_wake(void) acpi_s2idle_sync(); + /* + * The SCI is in the "suspended" state now and it cannot produce + * new wakeup events till the rearming below, so if any of them + * are pending here, they must be resulting from the processing + * of EC events above or coming from somewhere else. + */ + if (pm_wakeup_pending()) + return true; + rearm_wake_irq(acpi_sci_irq); } + + return false; } static void acpi_s2idle_restore_early(void) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index a6b2082c24f8f1031d906469793270db1eb833c7..e47c8a4c83db52ea97bf6a0b4283fa65de7ec8c8 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -5228,6 +5228,7 @@ static int binder_open(struct inode *nodp, struct file *filp) binder_dev = container_of(filp->private_data, struct binder_device, miscdev); } + refcount_inc(&binder_dev->ref); proc->context = &binder_dev->context; binder_alloc_init(&proc->alloc); @@ -5405,6 +5406,7 @@ static int binder_node_release(struct binder_node *node, int refs) static void binder_deferred_release(struct binder_proc *proc) { struct binder_context *context = proc->context; + struct binder_device *device; struct rb_node *n; int threads, nodes, incoming_refs, outgoing_refs, active_transactions; @@ -5421,6 +5423,12 @@ static void binder_deferred_release(struct binder_proc *proc) context->binder_context_mgr_node = NULL; } mutex_unlock(&context->context_mgr_node_lock); + device = container_of(proc->context, struct binder_device, context); + if (refcount_dec_and_test(&device->ref)) { + kfree(context->name); + kfree(device); + } + proc->context = NULL; binder_inner_proc_lock(proc); /* * Make sure proc stays alive after we @@ -6077,6 +6085,7 @@ static int __init init_binder_device(const char *name) binder_device->miscdev.minor = MISC_DYNAMIC_MINOR; binder_device->miscdev.name = name; + refcount_set(&binder_device->ref, 1); binder_device->context.binder_context_mgr_uid = INVALID_UID; binder_device->context.name = name; mutex_init(&binder_device->context.context_mgr_node_lock); diff --git a/drivers/android/binder_internal.h b/drivers/android/binder_internal.h index ae991097d14d17068f1512281704b0f04300c7d0..283d3cb9c16e5ffca25e171d7eb18b26e059f61f 100644 --- a/drivers/android/binder_internal.h +++ b/drivers/android/binder_internal.h @@ -8,6 +8,7 @@ #include #include #include +#include #include #include #include @@ -33,6 +34,7 @@ struct binder_device { struct miscdevice miscdev; struct binder_context context; struct inode *binderfs_inode; + refcount_t ref; }; /** diff --git a/drivers/android/binderfs.c b/drivers/android/binderfs.c index e2580e5316a2f5747f5db96d3cbbd907f7442822..f303106b3362b8621c026bad0d7ac517170e77cb 100644 --- a/drivers/android/binderfs.c +++ b/drivers/android/binderfs.c @@ -154,6 +154,7 @@ static int binderfs_binder_device_create(struct inode *ref_inode, if (!name) goto err; + refcount_set(&device->ref, 1); device->binderfs_inode = inode; device->context.binder_context_mgr_uid = INVALID_UID; device->context.name = name; @@ -257,8 +258,10 @@ static void binderfs_evict_inode(struct inode *inode) ida_free(&binderfs_minors, device->miscdev.minor); mutex_unlock(&binderfs_minors_mutex); - kfree(device->context.name); - kfree(device); + if (refcount_dec_and_test(&device->ref)) { + kfree(device->context.name); + kfree(device); + } } /** @@ -445,6 +448,7 @@ static int binderfs_binder_ctl_create(struct super_block *sb) inode->i_uid = info->root_uid; inode->i_gid = info->root_gid; + refcount_set(&device->ref, 1); device->binderfs_inode = inode; device->miscdev.minor = minor; diff --git a/drivers/atm/nicstar.c b/drivers/atm/nicstar.c index 8db8c0fb5e2dac6851893e62d25b682177539a7f..7af74fb450a0d01c5aaf90e9ba1a2859041b6250 100644 --- a/drivers/atm/nicstar.c +++ b/drivers/atm/nicstar.c @@ -91,7 +91,7 @@ #ifdef GENERAL_DEBUG #define PRINTK(args...) printk(args) #else -#define PRINTK(args...) +#define PRINTK(args...) do {} while (0) #endif /* GENERAL_DEBUG */ #ifdef EXTRA_DEBUG diff --git a/drivers/auxdisplay/Kconfig b/drivers/auxdisplay/Kconfig index b8313a04422db69495d547cd10a8ef39c88510a1..48efa7a047f3ec0e4149d24a836151928c717793 100644 --- a/drivers/auxdisplay/Kconfig +++ b/drivers/auxdisplay/Kconfig @@ -111,7 +111,7 @@ config CFAG12864B If unsure, say N. config CFAG12864B_RATE - int "Refresh rate (hertz)" + int "Refresh rate (hertz)" depends on CFAG12864B default "20" ---help--- @@ -329,7 +329,7 @@ config PANEL_LCD_PROTO config PANEL_LCD_PIN_E depends on PANEL_PROFILE="0" && PANEL_LCD="1" && PANEL_LCD_PROTO="0" - int "Parallel port pin number & polarity connected to the LCD E signal (-17...17) " + int "Parallel port pin number & polarity connected to the LCD E signal (-17...17) " range -17 17 default 14 ---help--- @@ -344,7 +344,7 @@ config PANEL_LCD_PIN_E config PANEL_LCD_PIN_RS depends on PANEL_PROFILE="0" && PANEL_LCD="1" && PANEL_LCD_PROTO="0" - int "Parallel port pin number & polarity connected to the LCD RS signal (-17...17) " + int "Parallel port pin number & polarity connected to the LCD RS signal (-17...17) " range -17 17 default 17 ---help--- @@ -359,7 +359,7 @@ config PANEL_LCD_PIN_RS config PANEL_LCD_PIN_RW depends on PANEL_PROFILE="0" && PANEL_LCD="1" && PANEL_LCD_PROTO="0" - int "Parallel port pin number & polarity connected to the LCD RW signal (-17...17) " + int "Parallel port pin number & polarity connected to the LCD RW signal (-17...17) " range -17 17 default 16 ---help--- @@ -374,7 +374,7 @@ config PANEL_LCD_PIN_RW config PANEL_LCD_PIN_SCL depends on PANEL_PROFILE="0" && PANEL_LCD="1" && PANEL_LCD_PROTO!="0" - int "Parallel port pin number & polarity connected to the LCD SCL signal (-17...17) " + int "Parallel port pin number & polarity connected to the LCD SCL signal (-17...17) " range -17 17 default 1 ---help--- @@ -389,7 +389,7 @@ config PANEL_LCD_PIN_SCL config PANEL_LCD_PIN_SDA depends on PANEL_PROFILE="0" && PANEL_LCD="1" && PANEL_LCD_PROTO!="0" - int "Parallel port pin number & polarity connected to the LCD SDA signal (-17...17) " + int "Parallel port pin number & polarity connected to the LCD SDA signal (-17...17) " range -17 17 default 2 ---help--- @@ -404,12 +404,12 @@ config PANEL_LCD_PIN_SDA config PANEL_LCD_PIN_BL depends on PANEL_PROFILE="0" && PANEL_LCD="1" - int "Parallel port pin number & polarity connected to the LCD backlight signal (-17...17) " + int "Parallel port pin number & polarity connected to the LCD backlight signal (-17...17) " range -17 17 default 0 ---help--- This describes the number of the parallel port pin to which the LCD 'BL' signal - has been connected. It can be : + has been connected. It can be : 0 : no connection (eg: connected to ground) 1..17 : directly connected to any of these pins on the DB25 plug diff --git a/drivers/auxdisplay/charlcd.c b/drivers/auxdisplay/charlcd.c index 874c259a88291880d368440437444dcf7e7b625d..c0da3820454b2ca944041d167e5f40857f0caeb9 100644 --- a/drivers/auxdisplay/charlcd.c +++ b/drivers/auxdisplay/charlcd.c @@ -88,7 +88,7 @@ struct charlcd_priv { int len; } esc_seq; - unsigned long long drvdata[0]; + unsigned long long drvdata[]; }; #define charlcd_to_priv(p) container_of(p, struct charlcd_priv, lcd) diff --git a/drivers/auxdisplay/img-ascii-lcd.c b/drivers/auxdisplay/img-ascii-lcd.c index efb928e25aef35cac24fa7f4f240391277bf9e0b..1cce409ce5cacbc8a9a7ae271233c981b0ef2dcd 100644 --- a/drivers/auxdisplay/img-ascii-lcd.c +++ b/drivers/auxdisplay/img-ascii-lcd.c @@ -356,7 +356,6 @@ static int img_ascii_lcd_probe(struct platform_device *pdev) const struct of_device_id *match; const struct img_ascii_lcd_config *cfg; struct img_ascii_lcd_ctx *ctx; - struct resource *res; int err; match = of_match_device(img_ascii_lcd_matches, &pdev->dev); @@ -378,8 +377,7 @@ static int img_ascii_lcd_probe(struct platform_device *pdev) &ctx->offset)) return -EINVAL; } else { - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - ctx->base = devm_ioremap_resource(&pdev->dev, res); + ctx->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(ctx->base)) return PTR_ERR(ctx->base); } diff --git a/drivers/base/core.c b/drivers/base/core.c index 42a67245643234a8fb23614feb1d7a5f60f7c0c9..dbb0f9130f42d386ad815d37377782fd2695bb8a 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -718,6 +718,8 @@ static void __device_links_queue_sync_state(struct device *dev, { struct device_link *link; + if (!dev_has_sync_state(dev)) + return; if (dev->state_synced) return; @@ -745,25 +747,31 @@ static void __device_links_queue_sync_state(struct device *dev, /** * device_links_flush_sync_list - Call sync_state() on a list of devices * @list: List of devices to call sync_state() on + * @dont_lock_dev: Device for which lock is already held by the caller * * Calls sync_state() on all the devices that have been queued for it. This - * function is used in conjunction with __device_links_queue_sync_state(). + * function is used in conjunction with __device_links_queue_sync_state(). The + * @dont_lock_dev parameter is useful when this function is called from a + * context where a device lock is already held. */ -static void device_links_flush_sync_list(struct list_head *list) +static void device_links_flush_sync_list(struct list_head *list, + struct device *dont_lock_dev) { struct device *dev, *tmp; list_for_each_entry_safe(dev, tmp, list, links.defer_sync) { list_del_init(&dev->links.defer_sync); - device_lock(dev); + if (dev != dont_lock_dev) + device_lock(dev); if (dev->bus->sync_state) dev->bus->sync_state(dev); else if (dev->driver && dev->driver->sync_state) dev->driver->sync_state(dev); - device_unlock(dev); + if (dev != dont_lock_dev) + device_unlock(dev); put_device(dev); } @@ -801,7 +809,7 @@ void device_links_supplier_sync_state_resume(void) out: device_links_write_unlock(); - device_links_flush_sync_list(&sync_list); + device_links_flush_sync_list(&sync_list, NULL); } static int sync_state_resume_initcall(void) @@ -813,7 +821,7 @@ late_initcall(sync_state_resume_initcall); static void __device_links_supplier_defer_sync(struct device *sup) { - if (list_empty(&sup->links.defer_sync)) + if (list_empty(&sup->links.defer_sync) && dev_has_sync_state(sup)) list_add_tail(&sup->links.defer_sync, &deferred_sync); } @@ -865,6 +873,11 @@ void device_links_driver_bound(struct device *dev) driver_deferred_probe_add(link->consumer); } + if (defer_sync_state_count) + __device_links_supplier_defer_sync(dev); + else + __device_links_queue_sync_state(dev, &sync_list); + list_for_each_entry(link, &dev->links.suppliers, c_node) { if (!(link->flags & DL_FLAG_MANAGED)) continue; @@ -883,7 +896,7 @@ void device_links_driver_bound(struct device *dev) device_links_write_unlock(); - device_links_flush_sync_list(&sync_list); + device_links_flush_sync_list(&sync_list, dev); } static void device_link_drop_managed(struct device_link *link) diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 7fa654f1288b80ffa73e11c49f7d340695d5de9e..b5ce7b0857953e32c90743c39b920a9f61a89f2a 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -363,10 +363,10 @@ static void setup_pdev_dma_masks(struct platform_device *pdev) { if (!pdev->dev.coherent_dma_mask) pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); - if (!pdev->dma_mask) - pdev->dma_mask = DMA_BIT_MASK(32); - if (!pdev->dev.dma_mask) - pdev->dev.dma_mask = &pdev->dma_mask; + if (!pdev->dev.dma_mask) { + pdev->platform_dma_mask = DMA_BIT_MASK(32); + pdev->dev.dma_mask = &pdev->platform_dma_mask; + } }; /** @@ -662,20 +662,8 @@ struct platform_device *platform_device_register_full( pdev->dev.of_node_reused = pdevinfo->of_node_reused; if (pdevinfo->dma_mask) { - /* - * This memory isn't freed when the device is put, - * I don't have a nice idea for that though. Conceptually - * dma_mask in struct device should not be a pointer. - * See http://thread.gmane.org/gmane.linux.kernel.pci/9081 - */ - pdev->dev.dma_mask = - kmalloc(sizeof(*pdev->dev.dma_mask), GFP_KERNEL); - if (!pdev->dev.dma_mask) - goto err; - - kmemleak_ignore(pdev->dev.dma_mask); - - *pdev->dev.dma_mask = pdevinfo->dma_mask; + pdev->platform_dma_mask = pdevinfo->dma_mask; + pdev->dev.dma_mask = &pdev->platform_dma_mask; pdev->dev.coherent_dma_mask = pdevinfo->dma_mask; } @@ -700,7 +688,6 @@ struct platform_device *platform_device_register_full( if (ret) { err: ACPI_COMPANION_SET(&pdev->dev, NULL); - kfree(pdev->dev.dma_mask); platform_device_put(pdev); return ERR_PTR(ret); } diff --git a/drivers/base/swnode.c b/drivers/base/swnode.c index 0b081dee1e95cce1b71b76131fce56d1d1b6f3b3..de8d3543e8fe347be2ffc2f3afdedd4ef84fd35c 100644 --- a/drivers/base/swnode.c +++ b/drivers/base/swnode.c @@ -608,6 +608,13 @@ static void software_node_release(struct kobject *kobj) { struct swnode *swnode = kobj_to_swnode(kobj); + if (swnode->parent) { + ida_simple_remove(&swnode->parent->child_ids, swnode->id); + list_del(&swnode->entry); + } else { + ida_simple_remove(&swnode_root_ids, swnode->id); + } + if (swnode->allocated) { property_entries_free(swnode->node->properties); kfree(swnode->node); @@ -773,13 +780,6 @@ void fwnode_remove_software_node(struct fwnode_handle *fwnode) if (!swnode) return; - if (swnode->parent) { - ida_simple_remove(&swnode->parent->child_ids, swnode->id); - list_del(&swnode->entry); - } else { - ida_simple_remove(&swnode_root_ids, swnode->id); - } - kobject_put(&swnode->kobj); } EXPORT_SYMBOL_GPL(fwnode_remove_software_node); diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index cd3612e4e2e14317ca506e24f00c4f9a6a2f9a73..8ef65c0856407cfbf780e370bf24a5141d8938f5 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -853,14 +853,17 @@ static void reset_fdc_info(int mode) /* selects the fdc and drive, and enables the fdc's input/dma. */ static void set_fdc(int drive) { + unsigned int new_fdc = fdc; + if (drive >= 0 && drive < N_DRIVE) { - fdc = FDC(drive); + new_fdc = FDC(drive); current_drive = drive; } - if (fdc != 1 && fdc != 0) { + if (new_fdc >= N_FDC) { pr_info("bad fdc value\n"); return; } + fdc = new_fdc; set_dor(fdc, ~0, 8); #if N_FDC > 1 set_dor(1 - fdc, ~8, 0); diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk.h index bc837862b7679ac88b0e8ef15d33e61f388114f5..62b660821dbcc19b390712b4088fc7141a4b27c2 100644 --- a/drivers/block/null_blk.h +++ b/drivers/block/null_blk.h @@ -14,9 +14,6 @@ #include struct nullb_cmd { - struct list_head list; - struct llist_node ll_list; - struct __call_single_data csd; struct request *rq; struct bio *bio; unsigned int tag; diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c index 16510795e37720de6b4c233bbd9c0f4bcf798e05..133060431dbdb2f2c058876c75072571c9141c41 100644 --- a/drivers/block/null_blk_main.c +++ b/drivers/block/null_blk_main.c @@ -1518,8 +1518,6 @@ static int setup_commands(struct nullb_queue *nq) for (i = 0; i < nq->queue_depth; i++) { cmd = &nq->cmds[i]; - INIT_LIST_HEAD(&cmd->list); - cmd->ll_list.next = NULL; cmd->tag = -1U; } diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c index 117cfc8cd05a4c509876d137bf7fb3e2bd272382..cda5cf917e9afaee700470b00e26d8aaeb7fffef 100644 --- a/drivers/block/paride/pcd.c +++ b/drivers/block/paride/pcd.c @@ -276,7 +276,7 @@ static const struct block_device_operations pcd_bdops = { .release = pcd_block_release, .ioctl = pcd_block_ioctl, #ifdef CONFIG_COMPAT - .ioctl = blkdev_compat_ptr_ioctl, + .compat_ioctl = blkdev_compat_ptr_ioctl, #endif .check_events = pcd_block_check_events, }; diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 54158766334b20cb7eeb0a5ead976843caa3df40..0736248999b0da7f81d81a1c9525483759444634 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -245,13 +245,20 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx, err = virtblk_add_req(vblk->vqs[qid].vq, vbr, vbr->sg, num); if (err) { virtqueue_kick(vblk->vqs[qid].vq); - blk_mq_stop_hw_queue(hctx); + /* Don't stop the queue if -ENOMEM: we may have failed to + * bounce the buffer due to global resource outage. + */ + if (err == -ENOSPC) + blk_mq_stop_hw_queue(hctx); spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags); - /* Out of mem doesn't actually happen, since we fall back - * to direct descriptors */ - if (err == -ENOMEM || err == -ENOSPC) + switch (err) { + case -ENOSPC: return BLK_STS_DEV_RESOURCE; - return BLK_STS_IOERR; + case -ENOMEM: + return BLK_STS_RESOURCE; + default: + return BLK_STS_IOERR; + } } if (bd->last && virtqueue_kick_prepare(vblk->vqs[qid].vq)) diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index e2ad6bba2281e79067066b5a5f05bc2f7818b3cc..9df516a56bb2f80ee38f2fefecf5aac599e4fa11 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -213,6 +213,7 @@ struct blkfront_info struct blk_mq_tag_set tag_set; struct blkfront_ring_info *rinfo; unsigned int nr_rings; + unsigned int rinfo_size; /* Save uncomplete reqs and bios for migration. */ struct list_head requests; struct bio_list bio_list; @@ -259,6 +260,18 @@ static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo); static void blkfront_gather_backend_features(struct blkfront_info *info); static int negotiate_mq(struct blkfront_info *info); +#define for_each_rinfo(info, ptr, idx) \ + for ((ptr) = (info)->rinfo, (idx) = 0; \ + (idx) < (info)->nr_rings; \ + (idx)++, (ptr) = (void *)(ptr) + (info)->rinfo_size) + +static inline struct blkfront_ring_info * +get_rinfo(const struct blkfront_info *info, unsigned int i) +{ + BUG_ON(i >= info->nr_rings); + return (void *)info->rinfo + i * info->rinfo_size; +} + static int get_id_from_freelist(struct blkfront_ring_info *rinfo) { unsigned long free = rinfo->shadow_free; @@ -883,8 +896,7 @@ static blk_status_t blkif_queue_rq(struct blk_mq_hw_ctx *hctx, struct blkfront_info *info = hctx->queue->queuedata; struct blkfront_ring_info *rinfo = NULL; - BUG_ON(info->nr_rings <= qid); - rinfo = &info->rinfo[qid]; + rinfo = get_rinfo(info, qid); blk_mq_start_request(qd->rq); spin_lock_irqsave(&rinfo->ring_lock, flags); if (RING_FULL(&rinfo->ring)) @@ -1181,6 +1193,7 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity, static void xlvbd_release_gendisk(struct blkfront_info *info) { unsigned int minor, nr_minors, i; + struct blkfront_ring_info *rinfo; if (info->rq == NULL) return; @@ -1188,9 +1201,7 @@ static void xlvbd_release_gendisk(struct blkfront_info *info) /* No more blkif_request(). */ blk_mq_stop_hw_queues(info->rq); - for (i = 0; i < info->nr_rings; i++) { - struct blkfront_ring_info *rinfo = &info->rinfo[i]; - + for_each_rinfo(info, rinfo, i) { /* No more gnttab callback work. */ gnttab_cancel_free_callback(&rinfo->callback); @@ -1339,6 +1350,7 @@ static void blkif_free_ring(struct blkfront_ring_info *rinfo) static void blkif_free(struct blkfront_info *info, int suspend) { unsigned int i; + struct blkfront_ring_info *rinfo; /* Prevent new requests being issued until we fix things up. */ info->connected = suspend ? @@ -1347,8 +1359,8 @@ static void blkif_free(struct blkfront_info *info, int suspend) if (info->rq) blk_mq_stop_hw_queues(info->rq); - for (i = 0; i < info->nr_rings; i++) - blkif_free_ring(&info->rinfo[i]); + for_each_rinfo(info, rinfo, i) + blkif_free_ring(rinfo); kvfree(info->rinfo); info->rinfo = NULL; @@ -1775,6 +1787,7 @@ static int talk_to_blkback(struct xenbus_device *dev, int err; unsigned int i, max_page_order; unsigned int ring_page_order; + struct blkfront_ring_info *rinfo; if (!info) return -ENODEV; @@ -1788,9 +1801,7 @@ static int talk_to_blkback(struct xenbus_device *dev, if (err) goto destroy_blkring; - for (i = 0; i < info->nr_rings; i++) { - struct blkfront_ring_info *rinfo = &info->rinfo[i]; - + for_each_rinfo(info, rinfo, i) { /* Create shared ring, alloc event channel. */ err = setup_blkring(dev, rinfo); if (err) @@ -1815,7 +1826,7 @@ static int talk_to_blkback(struct xenbus_device *dev, /* We already got the number of queues/rings in _probe */ if (info->nr_rings == 1) { - err = write_per_ring_nodes(xbt, &info->rinfo[0], dev->nodename); + err = write_per_ring_nodes(xbt, info->rinfo, dev->nodename); if (err) goto destroy_blkring; } else { @@ -1837,10 +1848,10 @@ static int talk_to_blkback(struct xenbus_device *dev, goto abort_transaction; } - for (i = 0; i < info->nr_rings; i++) { + for_each_rinfo(info, rinfo, i) { memset(path, 0, pathsize); snprintf(path, pathsize, "%s/queue-%u", dev->nodename, i); - err = write_per_ring_nodes(xbt, &info->rinfo[i], path); + err = write_per_ring_nodes(xbt, rinfo, path); if (err) { kfree(path); goto destroy_blkring; @@ -1868,9 +1879,8 @@ static int talk_to_blkback(struct xenbus_device *dev, goto destroy_blkring; } - for (i = 0; i < info->nr_rings; i++) { + for_each_rinfo(info, rinfo, i) { unsigned int j; - struct blkfront_ring_info *rinfo = &info->rinfo[i]; for (j = 0; j < BLK_RING_SIZE(info); j++) rinfo->shadow[j].req.u.rw.id = j + 1; @@ -1900,6 +1910,7 @@ static int negotiate_mq(struct blkfront_info *info) { unsigned int backend_max_queues; unsigned int i; + struct blkfront_ring_info *rinfo; BUG_ON(info->nr_rings); @@ -1911,20 +1922,16 @@ static int negotiate_mq(struct blkfront_info *info) if (!info->nr_rings) info->nr_rings = 1; - info->rinfo = kvcalloc(info->nr_rings, - struct_size(info->rinfo, shadow, - BLK_RING_SIZE(info)), - GFP_KERNEL); + info->rinfo_size = struct_size(info->rinfo, shadow, + BLK_RING_SIZE(info)); + info->rinfo = kvcalloc(info->nr_rings, info->rinfo_size, GFP_KERNEL); if (!info->rinfo) { xenbus_dev_fatal(info->xbdev, -ENOMEM, "allocating ring_info structure"); info->nr_rings = 0; return -ENOMEM; } - for (i = 0; i < info->nr_rings; i++) { - struct blkfront_ring_info *rinfo; - - rinfo = &info->rinfo[i]; + for_each_rinfo(info, rinfo, i) { INIT_LIST_HEAD(&rinfo->indirect_pages); INIT_LIST_HEAD(&rinfo->grants); rinfo->dev_info = info; @@ -2017,6 +2024,7 @@ static int blkif_recover(struct blkfront_info *info) int rc; struct bio *bio; unsigned int segs; + struct blkfront_ring_info *rinfo; blkfront_gather_backend_features(info); /* Reset limits changed by blk_mq_update_nr_hw_queues(). */ @@ -2024,9 +2032,7 @@ static int blkif_recover(struct blkfront_info *info) segs = info->max_indirect_segments ? : BLKIF_MAX_SEGMENTS_PER_REQUEST; blk_queue_max_segments(info->rq, segs / GRANTS_PER_PSEG); - for (r_index = 0; r_index < info->nr_rings; r_index++) { - struct blkfront_ring_info *rinfo = &info->rinfo[r_index]; - + for_each_rinfo(info, rinfo, r_index) { rc = blkfront_setup_indirect(rinfo); if (rc) return rc; @@ -2036,10 +2042,7 @@ static int blkif_recover(struct blkfront_info *info) /* Now safe for us to use the shared ring */ info->connected = BLKIF_STATE_CONNECTED; - for (r_index = 0; r_index < info->nr_rings; r_index++) { - struct blkfront_ring_info *rinfo; - - rinfo = &info->rinfo[r_index]; + for_each_rinfo(info, rinfo, r_index) { /* Kick any other new requests queued since we resumed */ kick_pending_request_queues(rinfo); } @@ -2072,13 +2075,13 @@ static int blkfront_resume(struct xenbus_device *dev) struct blkfront_info *info = dev_get_drvdata(&dev->dev); int err = 0; unsigned int i, j; + struct blkfront_ring_info *rinfo; dev_dbg(&dev->dev, "blkfront_resume: %s\n", dev->nodename); bio_list_init(&info->bio_list); INIT_LIST_HEAD(&info->requests); - for (i = 0; i < info->nr_rings; i++) { - struct blkfront_ring_info *rinfo = &info->rinfo[i]; + for_each_rinfo(info, rinfo, i) { struct bio_list merge_bio; struct blk_shadow *shadow = rinfo->shadow; @@ -2337,6 +2340,7 @@ static void blkfront_connect(struct blkfront_info *info) unsigned int binfo; char *envp[] = { "RESIZE=1", NULL }; int err, i; + struct blkfront_ring_info *rinfo; switch (info->connected) { case BLKIF_STATE_CONNECTED: @@ -2394,8 +2398,8 @@ static void blkfront_connect(struct blkfront_info *info) "physical-sector-size", sector_size); blkfront_gather_backend_features(info); - for (i = 0; i < info->nr_rings; i++) { - err = blkfront_setup_indirect(&info->rinfo[i]); + for_each_rinfo(info, rinfo, i) { + err = blkfront_setup_indirect(rinfo); if (err) { xenbus_dev_fatal(info->xbdev, err, "setup_indirect at %s", info->xbdev->otherend); @@ -2416,8 +2420,8 @@ static void blkfront_connect(struct blkfront_info *info) /* Kick pending requests. */ info->connected = BLKIF_STATE_CONNECTED; - for (i = 0; i < info->nr_rings; i++) - kick_pending_request_queues(&info->rinfo[i]); + for_each_rinfo(info, rinfo, i) + kick_pending_request_queues(rinfo); device_add_disk(&info->xbdev->dev, info->gd, NULL); @@ -2652,9 +2656,9 @@ static void purge_persistent_grants(struct blkfront_info *info) { unsigned int i; unsigned long flags; + struct blkfront_ring_info *rinfo; - for (i = 0; i < info->nr_rings; i++) { - struct blkfront_ring_info *rinfo = &info->rinfo[i]; + for_each_rinfo(info, rinfo, i) { struct grant *gnt_list_entry, *tmp; spin_lock_irqsave(&rinfo->ring_lock, flags); diff --git a/drivers/bus/moxtet.c b/drivers/bus/moxtet.c index 15fa293819a03124355d6163b7b393de75f553f8..b20fdcbd035b21cd4625ea5b401fe4cf9181c70b 100644 --- a/drivers/bus/moxtet.c +++ b/drivers/bus/moxtet.c @@ -465,7 +465,7 @@ static ssize_t input_read(struct file *file, char __user *buf, size_t len, { struct moxtet *moxtet = file->private_data; u8 bin[TURRIS_MOX_MAX_MODULES]; - u8 hex[sizeof(buf) * 2 + 1]; + u8 hex[sizeof(bin) * 2 + 1]; int ret, n; ret = moxtet_spi_read(moxtet, bin); diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index f702c85c81b657ec5e0dfe0712ab32e309028fa0..6113fc0a52aeba63be818aa356fd421d03d47443 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -1400,7 +1400,7 @@ static void sysc_init_revision_quirks(struct sysc *ddata) } /* 1-wire needs module's internal clocks enabled for reset */ -static void sysc_clk_enable_quirk_hdq1w(struct sysc *ddata) +static void sysc_pre_reset_quirk_hdq1w(struct sysc *ddata) { int offset = 0x0c; /* HDQ_CTRL_STATUS */ u16 val; @@ -1488,7 +1488,7 @@ static void sysc_init_module_quirks(struct sysc *ddata) return; if (ddata->cfg.quirks & SYSC_MODULE_QUIRK_HDQ1W) { - ddata->clk_enable_quirk = sysc_clk_enable_quirk_hdq1w; + ddata->clk_disable_quirk = sysc_pre_reset_quirk_hdq1w; return; } diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c index 886b2638c730308a6dce2061b18a06b04845fa18..c51292c2a131e0133872258e11470b6c5c58b73a 100644 --- a/drivers/cdrom/gdrom.c +++ b/drivers/cdrom/gdrom.c @@ -519,7 +519,7 @@ static const struct block_device_operations gdrom_bdops = { .check_events = gdrom_bdops_check_events, .ioctl = gdrom_bdops_ioctl, #ifdef CONFIG_COMPAT - .ioctl = blkdev_compat_ptr_ioctl, + .compat_ioctl = blkdev_compat_ptr_ioctl, #endif }; diff --git a/drivers/char/ipmi/ipmb_dev_int.c b/drivers/char/ipmi/ipmb_dev_int.c index 1ff4fb1def7ca7f412a68c25f224787e8f00855c..382b28f1cf2f6daf922236e827a2abce1bc73940 100644 --- a/drivers/char/ipmi/ipmb_dev_int.c +++ b/drivers/char/ipmi/ipmb_dev_int.c @@ -19,7 +19,7 @@ #include #include -#define MAX_MSG_LEN 128 +#define MAX_MSG_LEN 240 #define IPMB_REQUEST_LEN_MIN 7 #define NETFN_RSP_BIT_MASK 0x4 #define REQUEST_QUEUE_MAX_LEN 256 @@ -63,6 +63,7 @@ struct ipmb_dev { spinlock_t lock; wait_queue_head_t wait_queue; struct mutex file_mutex; + bool is_i2c_protocol; }; static inline struct ipmb_dev *to_ipmb_dev(struct file *file) @@ -112,6 +113,25 @@ static ssize_t ipmb_read(struct file *file, char __user *buf, size_t count, return ret < 0 ? ret : count; } +static int ipmb_i2c_write(struct i2c_client *client, u8 *msg, u8 addr) +{ + struct i2c_msg i2c_msg; + + /* + * subtract 1 byte (rq_sa) from the length of the msg passed to + * raw i2c_transfer + */ + i2c_msg.len = msg[IPMB_MSG_LEN_IDX] - 1; + + /* Assign message to buffer except first 2 bytes (length and address) */ + i2c_msg.buf = msg + 2; + + i2c_msg.addr = addr; + i2c_msg.flags = client->flags & I2C_CLIENT_PEC; + + return i2c_transfer(client->adapter, &i2c_msg, 1); +} + static ssize_t ipmb_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { @@ -133,6 +153,12 @@ static ssize_t ipmb_write(struct file *file, const char __user *buf, rq_sa = GET_7BIT_ADDR(msg[RQ_SA_8BIT_IDX]); netf_rq_lun = msg[NETFN_LUN_IDX]; + /* Check i2c block transfer vs smbus */ + if (ipmb_dev->is_i2c_protocol) { + ret = ipmb_i2c_write(ipmb_dev->client, msg, rq_sa); + return (ret == 1) ? count : ret; + } + /* * subtract rq_sa and netf_rq_lun from the length of the msg passed to * i2c_smbus_xfer @@ -253,7 +279,7 @@ static int ipmb_slave_cb(struct i2c_client *client, break; case I2C_SLAVE_WRITE_RECEIVED: - if (ipmb_dev->msg_idx >= sizeof(struct ipmb_msg)) + if (ipmb_dev->msg_idx >= sizeof(struct ipmb_msg) - 1) break; buf[++ipmb_dev->msg_idx] = *val; @@ -302,6 +328,9 @@ static int ipmb_probe(struct i2c_client *client, if (ret) return ret; + ipmb_dev->is_i2c_protocol + = device_property_read_bool(&client->dev, "i2c-protocol"); + ipmb_dev->client = client; i2c_set_clientdata(client, ipmb_dev); ret = i2c_slave_register(client, ipmb_slave_cb); diff --git a/drivers/char/ipmi/ipmi_si_platform.c b/drivers/char/ipmi/ipmi_si_platform.c index c78127ccbc0dd019b34ec784f439179c3d91d466..638c693e17adab63bc46a5b6979902865c34e8a2 100644 --- a/drivers/char/ipmi/ipmi_si_platform.c +++ b/drivers/char/ipmi/ipmi_si_platform.c @@ -194,7 +194,7 @@ static int platform_ipmi_probe(struct platform_device *pdev) else io.slave_addr = slave_addr; - io.irq = platform_get_irq(pdev, 0); + io.irq = platform_get_irq_optional(pdev, 0); if (io.irq > 0) io.irq_setup = ipmi_std_irq_setup; else @@ -378,7 +378,7 @@ static int acpi_ipmi_probe(struct platform_device *pdev) io.irq = tmp; io.irq_setup = acpi_gpe_irq_setup; } else { - int irq = platform_get_irq(pdev, 0); + int irq = platform_get_irq_optional(pdev, 0); if (irq > 0) { io.irq = irq; diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c index 22c6a2e612360aeae7a9d8fadbc2f43790903186..8ac390c2b51475b5dc79559c931dbd0b7f777571 100644 --- a/drivers/char/ipmi/ipmi_ssif.c +++ b/drivers/char/ipmi/ipmi_ssif.c @@ -775,10 +775,14 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result, flags = ipmi_ssif_lock_cond(ssif_info, &oflags); msg = ssif_info->curr_msg; if (msg) { + if (data) { + if (len > IPMI_MAX_MSG_LENGTH) + len = IPMI_MAX_MSG_LENGTH; + memcpy(msg->rsp, data, len); + } else { + len = 0; + } msg->rsp_size = len; - if (msg->rsp_size > IPMI_MAX_MSG_LENGTH) - msg->rsp_size = IPMI_MAX_MSG_LENGTH; - memcpy(msg->rsp, data, msg->rsp_size); ssif_info->curr_msg = NULL; } diff --git a/drivers/char/tpm/Makefile b/drivers/char/tpm/Makefile index 5a0d99d4fec0b1870e9f7b63e5e9e4444aa6950c..9567e5197f740f3c3b3ffeadc0495c928cd94399 100644 --- a/drivers/char/tpm/Makefile +++ b/drivers/char/tpm/Makefile @@ -21,9 +21,11 @@ tpm-$(CONFIG_EFI) += eventlog/efi.o tpm-$(CONFIG_OF) += eventlog/of.o obj-$(CONFIG_TCG_TIS_CORE) += tpm_tis_core.o obj-$(CONFIG_TCG_TIS) += tpm_tis.o -obj-$(CONFIG_TCG_TIS_SPI) += tpm_tis_spi_mod.o -tpm_tis_spi_mod-y := tpm_tis_spi.o -tpm_tis_spi_mod-$(CONFIG_TCG_TIS_SPI_CR50) += tpm_tis_spi_cr50.o + +obj-$(CONFIG_TCG_TIS_SPI) += tpm_tis_spi.o +tpm_tis_spi-y := tpm_tis_spi_main.o +tpm_tis_spi-$(CONFIG_TCG_TIS_SPI_CR50) += tpm_tis_spi_cr50.o + obj-$(CONFIG_TCG_TIS_I2C_ATMEL) += tpm_i2c_atmel.o obj-$(CONFIG_TCG_TIS_I2C_INFINEON) += tpm_i2c_infineon.o obj-$(CONFIG_TCG_TIS_I2C_NUVOTON) += tpm_i2c_nuvoton.o diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index 13696deceae8e7fb73862ea99d731a58fe647f67..760329598b9960855f42119ed01098acca312057 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -525,6 +525,8 @@ static int tpm2_init_bank_info(struct tpm_chip *chip, u32 bank_index) return 0; } + bank->crypto_id = HASH_ALGO__LAST; + return tpm2_pcr_read(chip, 0, &digest, &bank->digest_size); } diff --git a/drivers/char/tpm/tpm_tis_spi.c b/drivers/char/tpm/tpm_tis_spi_main.c similarity index 100% rename from drivers/char/tpm/tpm_tis_spi.c rename to drivers/char/tpm/tpm_tis_spi_main.c diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index f0f2b599fd7e90a5faacc1499f28aa058ef79d0d..95adf6c6db3db641d5be25d8573abd4232f309d4 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -4713,7 +4713,7 @@ EXPORT_SYMBOL(of_clk_get_by_name); * * Returns: The number of clocks that are possible parents of this node */ -unsigned int of_clk_get_parent_count(struct device_node *np) +unsigned int of_clk_get_parent_count(const struct device_node *np) { int count; @@ -4725,7 +4725,7 @@ unsigned int of_clk_get_parent_count(struct device_node *np) } EXPORT_SYMBOL_GPL(of_clk_get_parent_count); -const char *of_clk_get_parent_name(struct device_node *np, int index) +const char *of_clk_get_parent_name(const struct device_node *np, int index) { struct of_phandle_args clkspec; struct property *prop; diff --git a/drivers/clk/qcom/dispcc-sc7180.c b/drivers/clk/qcom/dispcc-sc7180.c index dd7af41e47eb96b7180410927852782e6873b850..0a5d395bce93584f85bca6a0fb390147eda26aee 100644 --- a/drivers/clk/qcom/dispcc-sc7180.c +++ b/drivers/clk/qcom/dispcc-sc7180.c @@ -592,24 +592,6 @@ static struct clk_branch disp_cc_mdss_rot_clk = { }, }; -static struct clk_branch disp_cc_mdss_rscc_ahb_clk = { - .halt_reg = 0x400c, - .halt_check = BRANCH_HALT, - .clkr = { - .enable_reg = 0x400c, - .enable_mask = BIT(0), - .hw.init = &(struct clk_init_data){ - .name = "disp_cc_mdss_rscc_ahb_clk", - .parent_data = &(const struct clk_parent_data){ - .hw = &disp_cc_mdss_ahb_clk_src.clkr.hw, - }, - .num_parents = 1, - .flags = CLK_IS_CRITICAL | CLK_SET_RATE_PARENT, - .ops = &clk_branch2_ops, - }, - }, -}; - static struct clk_branch disp_cc_mdss_rscc_vsync_clk = { .halt_reg = 0x4008, .halt_check = BRANCH_HALT, @@ -687,7 +669,6 @@ static struct clk_regmap *disp_cc_sc7180_clocks[] = { [DISP_CC_MDSS_PCLK0_CLK_SRC] = &disp_cc_mdss_pclk0_clk_src.clkr, [DISP_CC_MDSS_ROT_CLK] = &disp_cc_mdss_rot_clk.clkr, [DISP_CC_MDSS_ROT_CLK_SRC] = &disp_cc_mdss_rot_clk_src.clkr, - [DISP_CC_MDSS_RSCC_AHB_CLK] = &disp_cc_mdss_rscc_ahb_clk.clkr, [DISP_CC_MDSS_RSCC_VSYNC_CLK] = &disp_cc_mdss_rscc_vsync_clk.clkr, [DISP_CC_MDSS_VSYNC_CLK] = &disp_cc_mdss_vsync_clk.clkr, [DISP_CC_MDSS_VSYNC_CLK_SRC] = &disp_cc_mdss_vsync_clk_src.clkr, diff --git a/drivers/clk/qcom/videocc-sc7180.c b/drivers/clk/qcom/videocc-sc7180.c index c363c3cc544e2cd796d3678ad364b069b5368c81..276e5ecd48403f41914792981dd3c015e7a4c9fa 100644 --- a/drivers/clk/qcom/videocc-sc7180.c +++ b/drivers/clk/qcom/videocc-sc7180.c @@ -97,7 +97,7 @@ static struct clk_branch video_cc_vcodec0_axi_clk = { static struct clk_branch video_cc_vcodec0_core_clk = { .halt_reg = 0x890, - .halt_check = BRANCH_HALT, + .halt_check = BRANCH_HALT_VOTED, .clkr = { .enable_reg = 0x890, .enable_mask = BIT(0), diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 4adac3a8c2656b43d3a19d34e63bd486c885038c..808874bccf4ace34791e520b8d5bde8854d1dbb4 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -105,6 +105,8 @@ bool have_governor_per_policy(void) } EXPORT_SYMBOL_GPL(have_governor_per_policy); +static struct kobject *cpufreq_global_kobject; + struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy) { if (have_governor_per_policy()) @@ -1074,9 +1076,17 @@ static int cpufreq_init_policy(struct cpufreq_policy *policy) pol = policy->last_policy; } else if (def_gov) { pol = cpufreq_parse_policy(def_gov->name); - } else { - return -ENODATA; + /* + * In case the default governor is neiter "performance" + * nor "powersave", fall back to the initial policy + * value set by the driver. + */ + if (pol == CPUFREQ_POLICY_UNKNOWN) + pol = policy->policy; } + if (pol != CPUFREQ_POLICY_PERFORMANCE && + pol != CPUFREQ_POLICY_POWERSAVE) + return -ENODATA; } return cpufreq_set_policy(policy, gov, pol); @@ -2745,9 +2755,6 @@ int cpufreq_unregister_driver(struct cpufreq_driver *driver) } EXPORT_SYMBOL_GPL(cpufreq_unregister_driver); -struct kobject *cpufreq_global_kobject; -EXPORT_SYMBOL(cpufreq_global_kobject); - static int __init cpufreq_core_init(void) { if (cpufreq_disabled()) diff --git a/drivers/dax/super.c b/drivers/dax/super.c index 26a654dbc69a26d2b0dfb46ac0ba57cc0fb6c9a9..0aa4b6bc5101dcdcd2de08e4635c79a780335e9f 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -61,7 +61,7 @@ struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev) { if (!blk_queue_dax(bdev->bd_queue)) return NULL; - return fs_dax_get_by_host(bdev->bd_disk->disk_name); + return dax_get_by_host(bdev->bd_disk->disk_name); } EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev); #endif diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index cceee8bc3c2f745a02ab7b648d29458cbeaf2283..7dcf2093e5316a229dd9396feb73011a3f4f5fe3 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -738,7 +738,6 @@ struct devfreq *devfreq_add_device(struct device *dev, { struct devfreq *devfreq; struct devfreq_governor *governor; - static atomic_t devfreq_no = ATOMIC_INIT(-1); int err = 0; if (!dev || !profile || !governor_name) { @@ -800,8 +799,7 @@ struct devfreq *devfreq_add_device(struct device *dev, devfreq->suspend_freq = dev_pm_opp_get_suspend_opp_freq(dev); atomic_set(&devfreq->suspend_count, 0); - dev_set_name(&devfreq->dev, "devfreq%d", - atomic_inc_return(&devfreq_no)); + dev_set_name(&devfreq->dev, "%s", dev_name(dev)); err = device_register(&devfreq->dev); if (err) { mutex_unlock(&devfreq->lock); diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index d4097856c86b8b4a93242e09095f6006fbb0c2ea..c343c7c10b4cc21a53fde974dea5401c06a7855f 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -108,6 +108,7 @@ static int dma_buf_release(struct inode *inode, struct file *file) dma_resv_fini(dmabuf->resv); module_put(dmabuf->owner); + kfree(dmabuf->name); kfree(dmabuf); return 0; } diff --git a/drivers/dma/coh901318.c b/drivers/dma/coh901318.c index e51d836afcc7765d37ad5b084404aeebd13a8d69..1092d4ce723e436e7f3971bafcbeb084e505b12f 100644 --- a/drivers/dma/coh901318.c +++ b/drivers/dma/coh901318.c @@ -1947,8 +1947,6 @@ static void dma_tc_handle(struct coh901318_chan *cohc) return; } - spin_lock(&cohc->lock); - /* * When we reach this point, at least one queue item * should have been moved over from cohc->queue to @@ -1969,8 +1967,6 @@ static void dma_tc_handle(struct coh901318_chan *cohc) if (coh901318_queue_start(cohc) == NULL) cohc->busy = 0; - spin_unlock(&cohc->lock); - /* * This tasklet will remove items from cohc->active * and thus terminates them. diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c index 1d7347825b95a8a21d0fec1bda397a6093509ffc..df47be612ebb09f5b7c25fb1abb6767be190c093 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -204,6 +204,7 @@ static int idxd_wq_cdev_dev_setup(struct idxd_wq *wq) minor = ida_simple_get(&cdev_ctx->minor_ida, 0, MINORMASK, GFP_KERNEL); if (minor < 0) { rc = minor; + kfree(dev); goto ida_err; } @@ -212,7 +213,6 @@ static int idxd_wq_cdev_dev_setup(struct idxd_wq *wq) rc = device_register(dev); if (rc < 0) { dev_err(&idxd->pdev->dev, "device register failed\n"); - put_device(dev); goto dev_reg_err; } idxd_cdev->minor = minor; @@ -221,8 +221,8 @@ static int idxd_wq_cdev_dev_setup(struct idxd_wq *wq) dev_reg_err: ida_simple_remove(&cdev_ctx->minor_ida, MINOR(dev->devt)); + put_device(dev); ida_err: - kfree(dev); idxd_cdev->dev = NULL; return rc; } diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c index 6d907fe150aa4d508337b6f86d38da237f456318..6ca6e520a2fa4943e2b895f1816408de77d6c6e2 100644 --- a/drivers/dma/idxd/sysfs.c +++ b/drivers/dma/idxd/sysfs.c @@ -124,6 +124,7 @@ static int idxd_config_bus_probe(struct device *dev) rc = idxd_device_config(idxd); if (rc < 0) { spin_unlock_irqrestore(&idxd->dev_lock, flags); + module_put(THIS_MODULE); dev_warn(dev, "Device config failed: %d\n", rc); return rc; } @@ -132,6 +133,7 @@ static int idxd_config_bus_probe(struct device *dev) rc = idxd_device_enable(idxd); if (rc < 0) { spin_unlock_irqrestore(&idxd->dev_lock, flags); + module_put(THIS_MODULE); dev_warn(dev, "Device enable failed: %d\n", rc); return rc; } @@ -142,6 +144,7 @@ static int idxd_config_bus_probe(struct device *dev) rc = idxd_register_dma_device(idxd); if (rc < 0) { spin_unlock_irqrestore(&idxd->dev_lock, flags); + module_put(THIS_MODULE); dev_dbg(dev, "Failed to register dmaengine device\n"); return rc; } @@ -516,7 +519,7 @@ static ssize_t group_tokens_reserved_store(struct device *dev, if (val > idxd->max_tokens) return -EINVAL; - if (val > idxd->nr_tokens) + if (val > idxd->nr_tokens + group->tokens_reserved) return -EINVAL; group->tokens_reserved = val; @@ -901,6 +904,20 @@ static ssize_t wq_size_show(struct device *dev, struct device_attribute *attr, return sprintf(buf, "%u\n", wq->size); } +static int total_claimed_wq_size(struct idxd_device *idxd) +{ + int i; + int wq_size = 0; + + for (i = 0; i < idxd->max_wqs; i++) { + struct idxd_wq *wq = &idxd->wqs[i]; + + wq_size += wq->size; + } + + return wq_size; +} + static ssize_t wq_size_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) @@ -920,7 +937,7 @@ static ssize_t wq_size_store(struct device *dev, if (wq->state != IDXD_WQ_DISABLED) return -EPERM; - if (size > idxd->max_wq_size) + if (size + total_claimed_wq_size(idxd) - wq->size > idxd->max_wq_size) return -EINVAL; wq->size = size; @@ -999,12 +1016,14 @@ static ssize_t wq_type_store(struct device *dev, return -EPERM; old_type = wq->type; - if (sysfs_streq(buf, idxd_wq_type_names[IDXD_WQT_KERNEL])) + if (sysfs_streq(buf, idxd_wq_type_names[IDXD_WQT_NONE])) + wq->type = IDXD_WQT_NONE; + else if (sysfs_streq(buf, idxd_wq_type_names[IDXD_WQT_KERNEL])) wq->type = IDXD_WQT_KERNEL; else if (sysfs_streq(buf, idxd_wq_type_names[IDXD_WQT_USER])) wq->type = IDXD_WQT_USER; else - wq->type = IDXD_WQT_NONE; + return -EINVAL; /* If we are changing queue type, clear the name */ if (wq->type != old_type) diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c index 066b21a3223261f26a73a71266d3b0a3e67bb51d..4d4477df4ede751a9b4277833d851dc48fe8641f 100644 --- a/drivers/dma/imx-sdma.c +++ b/drivers/dma/imx-sdma.c @@ -1331,13 +1331,14 @@ static void sdma_free_chan_resources(struct dma_chan *chan) sdma_channel_synchronize(chan); - if (sdmac->event_id0) + if (sdmac->event_id0 >= 0) sdma_event_disable(sdmac, sdmac->event_id0); if (sdmac->event_id1) sdma_event_disable(sdmac, sdmac->event_id1); sdmac->event_id0 = 0; sdmac->event_id1 = 0; + sdmac->context_loaded = false; sdma_set_channel_priority(sdmac, 0); @@ -1631,7 +1632,7 @@ static int sdma_config(struct dma_chan *chan, memcpy(&sdmac->slave_config, dmaengine_cfg, sizeof(*dmaengine_cfg)); /* Set ENBLn earlier to make sure dma request triggered after that */ - if (sdmac->event_id0) { + if (sdmac->event_id0 >= 0) { if (sdmac->event_id0 >= sdmac->sdma->drvdata->num_events) return -EINVAL; sdma_event_enable(sdmac, sdmac->event_id0); diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c index 3a45079d11ecff40db8ea5b1824c55894a7429e7..4a750e29bfb533953584bc101f6e5eec99cc0239 100644 --- a/drivers/dma/tegra20-apb-dma.c +++ b/drivers/dma/tegra20-apb-dma.c @@ -281,7 +281,7 @@ static struct tegra_dma_desc *tegra_dma_desc_get( /* Do not allocate if desc are waiting for ack */ list_for_each_entry(dma_desc, &tdc->free_dma_desc, node) { - if (async_tx_test_ack(&dma_desc->txd)) { + if (async_tx_test_ack(&dma_desc->txd) && !dma_desc->cb_count) { list_del(&dma_desc->node); spin_unlock_irqrestore(&tdc->lock, flags); dma_desc->txd.flags = 0; @@ -756,10 +756,6 @@ static int tegra_dma_terminate_all(struct dma_chan *dc) bool was_busy; spin_lock_irqsave(&tdc->lock, flags); - if (list_empty(&tdc->pending_sg_req)) { - spin_unlock_irqrestore(&tdc->lock, flags); - return 0; - } if (!tdc->busy) goto skip_dma_stop; diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c index ea79c2df28e01b628a8ac08b5af33c7d50a931d1..0536866a58cee788374f63cad40259b122541474 100644 --- a/drivers/dma/ti/k3-udma.c +++ b/drivers/dma/ti/k3-udma.c @@ -5,6 +5,7 @@ */ #include +#include #include #include #include @@ -96,6 +97,24 @@ struct udma_match_data { u32 level_start_idx[]; }; +struct udma_hwdesc { + size_t cppi5_desc_size; + void *cppi5_desc_vaddr; + dma_addr_t cppi5_desc_paddr; + + /* TR descriptor internal pointers */ + void *tr_req_base; + struct cppi5_tr_resp_t *tr_resp_base; +}; + +struct udma_rx_flush { + struct udma_hwdesc hwdescs[2]; + + size_t buffer_size; + void *buffer_vaddr; + dma_addr_t buffer_paddr; +}; + struct udma_dev { struct dma_device ddev; struct device *dev; @@ -112,6 +131,8 @@ struct udma_dev { struct list_head desc_to_purge; spinlock_t lock; + struct udma_rx_flush rx_flush; + int tchan_cnt; int echan_cnt; int rchan_cnt; @@ -130,16 +151,6 @@ struct udma_dev { u32 psil_base; }; -struct udma_hwdesc { - size_t cppi5_desc_size; - void *cppi5_desc_vaddr; - dma_addr_t cppi5_desc_paddr; - - /* TR descriptor internal pointers */ - void *tr_req_base; - struct cppi5_tr_resp_t *tr_resp_base; -}; - struct udma_desc { struct virt_dma_desc vd; @@ -169,7 +180,7 @@ enum udma_chan_state { struct udma_tx_drain { struct delayed_work work; - unsigned long jiffie; + ktime_t tstamp; u32 residue; }; @@ -502,7 +513,7 @@ static bool udma_is_chan_paused(struct udma_chan *uc) { u32 val, pause_mask; - switch (uc->desc->dir) { + switch (uc->config.dir) { case DMA_DEV_TO_MEM: val = udma_rchanrt_read(uc->rchan, UDMA_RCHAN_RT_PEER_RT_EN_REG); @@ -551,12 +562,17 @@ static void udma_sync_for_device(struct udma_chan *uc, int idx) } } +static inline dma_addr_t udma_get_rx_flush_hwdesc_paddr(struct udma_chan *uc) +{ + return uc->ud->rx_flush.hwdescs[uc->config.pkt_mode].cppi5_desc_paddr; +} + static int udma_push_to_ring(struct udma_chan *uc, int idx) { struct udma_desc *d = uc->desc; - struct k3_ring *ring = NULL; - int ret = -EINVAL; + dma_addr_t paddr; + int ret; switch (uc->config.dir) { case DMA_DEV_TO_MEM: @@ -567,21 +583,37 @@ static int udma_push_to_ring(struct udma_chan *uc, int idx) ring = uc->tchan->t_ring; break; default: - break; + return -EINVAL; } - if (ring) { - dma_addr_t desc_addr = udma_curr_cppi5_desc_paddr(d, idx); + /* RX flush packet: idx == -1 is only passed in case of DEV_TO_MEM */ + if (idx == -1) { + paddr = udma_get_rx_flush_hwdesc_paddr(uc); + } else { + paddr = udma_curr_cppi5_desc_paddr(d, idx); wmb(); /* Ensure that writes are not moved over this point */ udma_sync_for_device(uc, idx); - ret = k3_ringacc_ring_push(ring, &desc_addr); - uc->in_ring_cnt++; } + ret = k3_ringacc_ring_push(ring, &paddr); + if (!ret) + uc->in_ring_cnt++; + return ret; } +static bool udma_desc_is_rx_flush(struct udma_chan *uc, dma_addr_t addr) +{ + if (uc->config.dir != DMA_DEV_TO_MEM) + return false; + + if (addr == udma_get_rx_flush_hwdesc_paddr(uc)) + return true; + + return false; +} + static int udma_pop_from_ring(struct udma_chan *uc, dma_addr_t *addr) { struct k3_ring *ring = NULL; @@ -610,6 +642,10 @@ static int udma_pop_from_ring(struct udma_chan *uc, dma_addr_t *addr) if (cppi5_desc_is_tdcm(*addr)) return ret; + /* Check for flush descriptor */ + if (udma_desc_is_rx_flush(uc, *addr)) + return -ENOENT; + d = udma_udma_desc_from_paddr(uc, *addr); if (d) @@ -890,6 +926,9 @@ static int udma_stop(struct udma_chan *uc) switch (uc->config.dir) { case DMA_DEV_TO_MEM: + if (!uc->cyclic && !uc->desc) + udma_push_to_ring(uc, -1); + udma_rchanrt_write(uc->rchan, UDMA_RCHAN_RT_PEER_RT_EN_REG, UDMA_PEER_RT_EN_ENABLE | UDMA_PEER_RT_EN_TEARDOWN); @@ -946,9 +985,10 @@ static bool udma_is_desc_really_done(struct udma_chan *uc, struct udma_desc *d) peer_bcnt = udma_tchanrt_read(uc->tchan, UDMA_TCHAN_RT_PEER_BCNT_REG); bcnt = udma_tchanrt_read(uc->tchan, UDMA_TCHAN_RT_BCNT_REG); + /* Transfer is incomplete, store current residue and time stamp */ if (peer_bcnt < bcnt) { uc->tx_drain.residue = bcnt - peer_bcnt; - uc->tx_drain.jiffie = jiffies; + uc->tx_drain.tstamp = ktime_get(); return false; } @@ -961,35 +1001,59 @@ static void udma_check_tx_completion(struct work_struct *work) tx_drain.work.work); bool desc_done = true; u32 residue_diff; - unsigned long jiffie_diff, delay; + ktime_t time_diff; + unsigned long delay; + + while (1) { + if (uc->desc) { + /* Get previous residue and time stamp */ + residue_diff = uc->tx_drain.residue; + time_diff = uc->tx_drain.tstamp; + /* + * Get current residue and time stamp or see if + * transfer is complete + */ + desc_done = udma_is_desc_really_done(uc, uc->desc); + } - if (uc->desc) { - residue_diff = uc->tx_drain.residue; - jiffie_diff = uc->tx_drain.jiffie; - desc_done = udma_is_desc_really_done(uc, uc->desc); - } - - if (!desc_done) { - jiffie_diff = uc->tx_drain.jiffie - jiffie_diff; - residue_diff -= uc->tx_drain.residue; - if (residue_diff) { - /* Try to guess when we should check next time */ - residue_diff /= jiffie_diff; - delay = uc->tx_drain.residue / residue_diff / 3; - if (jiffies_to_msecs(delay) < 5) - delay = 0; - } else { - /* No progress, check again in 1 second */ - delay = HZ; + if (!desc_done) { + /* + * Find the time delta and residue delta w.r.t + * previous poll + */ + time_diff = ktime_sub(uc->tx_drain.tstamp, + time_diff) + 1; + residue_diff -= uc->tx_drain.residue; + if (residue_diff) { + /* + * Try to guess when we should check + * next time by calculating rate at + * which data is being drained at the + * peer device + */ + delay = (time_diff / residue_diff) * + uc->tx_drain.residue; + } else { + /* No progress, check again in 1 second */ + schedule_delayed_work(&uc->tx_drain.work, HZ); + break; + } + + usleep_range(ktime_to_us(delay), + ktime_to_us(delay) + 10); + continue; } - schedule_delayed_work(&uc->tx_drain.work, delay); - } else if (uc->desc) { - struct udma_desc *d = uc->desc; + if (uc->desc) { + struct udma_desc *d = uc->desc; - uc->bcnt += d->residue; - udma_start(uc); - vchan_cookie_complete(&d->vd); + uc->bcnt += d->residue; + udma_start(uc); + vchan_cookie_complete(&d->vd); + break; + } + + break; } } @@ -1033,29 +1097,27 @@ static irqreturn_t udma_ring_irq_handler(int irq, void *data) goto out; } - if (uc->cyclic) { - /* push the descriptor back to the ring */ - if (d == uc->desc) { + if (d == uc->desc) { + /* active descriptor */ + if (uc->cyclic) { udma_cyclic_packet_elapsed(uc); vchan_cyclic_callback(&d->vd); - } - } else { - bool desc_done = false; - - if (d == uc->desc) { - desc_done = udma_is_desc_really_done(uc, d); - - if (desc_done) { + } else { + if (udma_is_desc_really_done(uc, d)) { uc->bcnt += d->residue; udma_start(uc); + vchan_cookie_complete(&d->vd); } else { schedule_delayed_work(&uc->tx_drain.work, 0); } } - - if (desc_done) - vchan_cookie_complete(&d->vd); + } else { + /* + * terminated descriptor, mark the descriptor as + * completed to update the channel's cookie marker + */ + dma_cookie_complete(&d->vd.tx); } } out: @@ -1965,36 +2027,81 @@ static struct udma_desc *udma_alloc_tr_desc(struct udma_chan *uc, return d; } +/** + * udma_get_tr_counters - calculate TR counters for a given length + * @len: Length of the trasnfer + * @align_to: Preferred alignment + * @tr0_cnt0: First TR icnt0 + * @tr0_cnt1: First TR icnt1 + * @tr1_cnt0: Second (if used) TR icnt0 + * + * For len < SZ_64K only one TR is enough, tr1_cnt0 is not updated + * For len >= SZ_64K two TRs are used in a simple way: + * First TR: SZ_64K-alignment blocks (tr0_cnt0, tr0_cnt1) + * Second TR: the remaining length (tr1_cnt0) + * + * Returns the number of TRs the length needs (1 or 2) + * -EINVAL if the length can not be supported + */ +static int udma_get_tr_counters(size_t len, unsigned long align_to, + u16 *tr0_cnt0, u16 *tr0_cnt1, u16 *tr1_cnt0) +{ + if (len < SZ_64K) { + *tr0_cnt0 = len; + *tr0_cnt1 = 1; + + return 1; + } + + if (align_to > 3) + align_to = 3; + +realign: + *tr0_cnt0 = SZ_64K - BIT(align_to); + if (len / *tr0_cnt0 >= SZ_64K) { + if (align_to) { + align_to--; + goto realign; + } + return -EINVAL; + } + + *tr0_cnt1 = len / *tr0_cnt0; + *tr1_cnt0 = len % *tr0_cnt0; + + return 2; +} + static struct udma_desc * udma_prep_slave_sg_tr(struct udma_chan *uc, struct scatterlist *sgl, unsigned int sglen, enum dma_transfer_direction dir, unsigned long tx_flags, void *context) { - enum dma_slave_buswidth dev_width; struct scatterlist *sgent; struct udma_desc *d; - size_t tr_size; struct cppi5_tr_type1_t *tr_req = NULL; + u16 tr0_cnt0, tr0_cnt1, tr1_cnt0; unsigned int i; - u32 burst; + size_t tr_size; + int num_tr = 0; + int tr_idx = 0; - if (dir == DMA_DEV_TO_MEM) { - dev_width = uc->cfg.src_addr_width; - burst = uc->cfg.src_maxburst; - } else if (dir == DMA_MEM_TO_DEV) { - dev_width = uc->cfg.dst_addr_width; - burst = uc->cfg.dst_maxburst; - } else { - dev_err(uc->ud->dev, "%s: bad direction?\n", __func__); + if (!is_slave_direction(dir)) { + dev_err(uc->ud->dev, "Only slave cyclic is supported\n"); return NULL; } - if (!burst) - burst = 1; + /* estimate the number of TRs we will need */ + for_each_sg(sgl, sgent, sglen, i) { + if (sg_dma_len(sgent) < SZ_64K) + num_tr++; + else + num_tr += 2; + } /* Now allocate and setup the descriptor. */ tr_size = sizeof(struct cppi5_tr_type1_t); - d = udma_alloc_tr_desc(uc, tr_size, sglen, dir); + d = udma_alloc_tr_desc(uc, tr_size, num_tr, dir); if (!d) return NULL; @@ -2002,19 +2109,46 @@ udma_prep_slave_sg_tr(struct udma_chan *uc, struct scatterlist *sgl, tr_req = d->hwdesc[0].tr_req_base; for_each_sg(sgl, sgent, sglen, i) { - d->residue += sg_dma_len(sgent); + dma_addr_t sg_addr = sg_dma_address(sgent); + + num_tr = udma_get_tr_counters(sg_dma_len(sgent), __ffs(sg_addr), + &tr0_cnt0, &tr0_cnt1, &tr1_cnt0); + if (num_tr < 0) { + dev_err(uc->ud->dev, "size %u is not supported\n", + sg_dma_len(sgent)); + udma_free_hwdesc(uc, d); + kfree(d); + return NULL; + } cppi5_tr_init(&tr_req[i].flags, CPPI5_TR_TYPE1, false, false, CPPI5_TR_EVENT_SIZE_COMPLETION, 0); cppi5_tr_csf_set(&tr_req[i].flags, CPPI5_TR_CSF_SUPR_EVT); - tr_req[i].addr = sg_dma_address(sgent); - tr_req[i].icnt0 = burst * dev_width; - tr_req[i].dim1 = burst * dev_width; - tr_req[i].icnt1 = sg_dma_len(sgent) / tr_req[i].icnt0; + tr_req[tr_idx].addr = sg_addr; + tr_req[tr_idx].icnt0 = tr0_cnt0; + tr_req[tr_idx].icnt1 = tr0_cnt1; + tr_req[tr_idx].dim1 = tr0_cnt0; + tr_idx++; + + if (num_tr == 2) { + cppi5_tr_init(&tr_req[tr_idx].flags, CPPI5_TR_TYPE1, + false, false, + CPPI5_TR_EVENT_SIZE_COMPLETION, 0); + cppi5_tr_csf_set(&tr_req[tr_idx].flags, + CPPI5_TR_CSF_SUPR_EVT); + + tr_req[tr_idx].addr = sg_addr + tr0_cnt1 * tr0_cnt0; + tr_req[tr_idx].icnt0 = tr1_cnt0; + tr_req[tr_idx].icnt1 = 1; + tr_req[tr_idx].dim1 = tr1_cnt0; + tr_idx++; + } + + d->residue += sg_dma_len(sgent); } - cppi5_tr_csf_set(&tr_req[i - 1].flags, CPPI5_TR_CSF_EOP); + cppi5_tr_csf_set(&tr_req[tr_idx - 1].flags, CPPI5_TR_CSF_EOP); return d; } @@ -2319,47 +2453,66 @@ udma_prep_dma_cyclic_tr(struct udma_chan *uc, dma_addr_t buf_addr, size_t buf_len, size_t period_len, enum dma_transfer_direction dir, unsigned long flags) { - enum dma_slave_buswidth dev_width; struct udma_desc *d; - size_t tr_size; + size_t tr_size, period_addr; struct cppi5_tr_type1_t *tr_req; - unsigned int i; unsigned int periods = buf_len / period_len; - u32 burst; + u16 tr0_cnt0, tr0_cnt1, tr1_cnt0; + unsigned int i; + int num_tr; - if (dir == DMA_DEV_TO_MEM) { - dev_width = uc->cfg.src_addr_width; - burst = uc->cfg.src_maxburst; - } else if (dir == DMA_MEM_TO_DEV) { - dev_width = uc->cfg.dst_addr_width; - burst = uc->cfg.dst_maxburst; - } else { - dev_err(uc->ud->dev, "%s: bad direction?\n", __func__); + if (!is_slave_direction(dir)) { + dev_err(uc->ud->dev, "Only slave cyclic is supported\n"); return NULL; } - if (!burst) - burst = 1; + num_tr = udma_get_tr_counters(period_len, __ffs(buf_addr), &tr0_cnt0, + &tr0_cnt1, &tr1_cnt0); + if (num_tr < 0) { + dev_err(uc->ud->dev, "size %zu is not supported\n", + period_len); + return NULL; + } /* Now allocate and setup the descriptor. */ tr_size = sizeof(struct cppi5_tr_type1_t); - d = udma_alloc_tr_desc(uc, tr_size, periods, dir); + d = udma_alloc_tr_desc(uc, tr_size, periods * num_tr, dir); if (!d) return NULL; tr_req = d->hwdesc[0].tr_req_base; + period_addr = buf_addr; for (i = 0; i < periods; i++) { - cppi5_tr_init(&tr_req[i].flags, CPPI5_TR_TYPE1, false, false, - CPPI5_TR_EVENT_SIZE_COMPLETION, 0); + int tr_idx = i * num_tr; - tr_req[i].addr = buf_addr + period_len * i; - tr_req[i].icnt0 = dev_width; - tr_req[i].icnt1 = period_len / dev_width; - tr_req[i].dim1 = dev_width; + cppi5_tr_init(&tr_req[tr_idx].flags, CPPI5_TR_TYPE1, false, + false, CPPI5_TR_EVENT_SIZE_COMPLETION, 0); + + tr_req[tr_idx].addr = period_addr; + tr_req[tr_idx].icnt0 = tr0_cnt0; + tr_req[tr_idx].icnt1 = tr0_cnt1; + tr_req[tr_idx].dim1 = tr0_cnt0; + + if (num_tr == 2) { + cppi5_tr_csf_set(&tr_req[tr_idx].flags, + CPPI5_TR_CSF_SUPR_EVT); + tr_idx++; + + cppi5_tr_init(&tr_req[tr_idx].flags, CPPI5_TR_TYPE1, + false, false, + CPPI5_TR_EVENT_SIZE_COMPLETION, 0); + + tr_req[tr_idx].addr = period_addr + tr0_cnt1 * tr0_cnt0; + tr_req[tr_idx].icnt0 = tr1_cnt0; + tr_req[tr_idx].icnt1 = 1; + tr_req[tr_idx].dim1 = tr1_cnt0; + } if (!(flags & DMA_PREP_INTERRUPT)) - cppi5_tr_csf_set(&tr_req[i].flags, + cppi5_tr_csf_set(&tr_req[tr_idx].flags, CPPI5_TR_CSF_SUPR_EVT); + + period_addr += period_len; } return d; @@ -2517,29 +2670,12 @@ udma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src, return NULL; } - if (len < SZ_64K) { - num_tr = 1; - tr0_cnt0 = len; - tr0_cnt1 = 1; - } else { - unsigned long align_to = __ffs(src | dest); - - if (align_to > 3) - align_to = 3; - /* - * Keep simple: tr0: SZ_64K-alignment blocks, - * tr1: the remaining - */ - num_tr = 2; - tr0_cnt0 = (SZ_64K - BIT(align_to)); - if (len / tr0_cnt0 >= SZ_64K) { - dev_err(uc->ud->dev, "size %zu is not supported\n", - len); - return NULL; - } - - tr0_cnt1 = len / tr0_cnt0; - tr1_cnt0 = len % tr0_cnt0; + num_tr = udma_get_tr_counters(len, __ffs(src | dest), &tr0_cnt0, + &tr0_cnt1, &tr1_cnt0); + if (num_tr < 0) { + dev_err(uc->ud->dev, "size %zu is not supported\n", + len); + return NULL; } d = udma_alloc_tr_desc(uc, tr_size, num_tr, DMA_MEM_TO_MEM); @@ -2631,6 +2767,9 @@ static enum dma_status udma_tx_status(struct dma_chan *chan, ret = dma_cookie_status(chan, cookie, txstate); + if (!udma_is_chan_running(uc)) + ret = DMA_COMPLETE; + if (ret == DMA_IN_PROGRESS && udma_is_chan_paused(uc)) ret = DMA_PAUSED; @@ -2697,11 +2836,8 @@ static int udma_pause(struct dma_chan *chan) { struct udma_chan *uc = to_udma_chan(chan); - if (!uc->desc) - return -EINVAL; - /* pause the channel */ - switch (uc->desc->dir) { + switch (uc->config.dir) { case DMA_DEV_TO_MEM: udma_rchanrt_update_bits(uc->rchan, UDMA_RCHAN_RT_PEER_RT_EN_REG, @@ -2730,11 +2866,8 @@ static int udma_resume(struct dma_chan *chan) { struct udma_chan *uc = to_udma_chan(chan); - if (!uc->desc) - return -EINVAL; - /* resume the channel */ - switch (uc->desc->dir) { + switch (uc->config.dir) { case DMA_DEV_TO_MEM: udma_rchanrt_update_bits(uc->rchan, UDMA_RCHAN_RT_PEER_RT_EN_REG, @@ -3248,6 +3381,98 @@ static int udma_setup_resources(struct udma_dev *ud) return ch_count; } +static int udma_setup_rx_flush(struct udma_dev *ud) +{ + struct udma_rx_flush *rx_flush = &ud->rx_flush; + struct cppi5_desc_hdr_t *tr_desc; + struct cppi5_tr_type1_t *tr_req; + struct cppi5_host_desc_t *desc; + struct device *dev = ud->dev; + struct udma_hwdesc *hwdesc; + size_t tr_size; + + /* Allocate 1K buffer for discarded data on RX channel teardown */ + rx_flush->buffer_size = SZ_1K; + rx_flush->buffer_vaddr = devm_kzalloc(dev, rx_flush->buffer_size, + GFP_KERNEL); + if (!rx_flush->buffer_vaddr) + return -ENOMEM; + + rx_flush->buffer_paddr = dma_map_single(dev, rx_flush->buffer_vaddr, + rx_flush->buffer_size, + DMA_TO_DEVICE); + if (dma_mapping_error(dev, rx_flush->buffer_paddr)) + return -ENOMEM; + + /* Set up descriptor to be used for TR mode */ + hwdesc = &rx_flush->hwdescs[0]; + tr_size = sizeof(struct cppi5_tr_type1_t); + hwdesc->cppi5_desc_size = cppi5_trdesc_calc_size(tr_size, 1); + hwdesc->cppi5_desc_size = ALIGN(hwdesc->cppi5_desc_size, + ud->desc_align); + + hwdesc->cppi5_desc_vaddr = devm_kzalloc(dev, hwdesc->cppi5_desc_size, + GFP_KERNEL); + if (!hwdesc->cppi5_desc_vaddr) + return -ENOMEM; + + hwdesc->cppi5_desc_paddr = dma_map_single(dev, hwdesc->cppi5_desc_vaddr, + hwdesc->cppi5_desc_size, + DMA_TO_DEVICE); + if (dma_mapping_error(dev, hwdesc->cppi5_desc_paddr)) + return -ENOMEM; + + /* Start of the TR req records */ + hwdesc->tr_req_base = hwdesc->cppi5_desc_vaddr + tr_size; + /* Start address of the TR response array */ + hwdesc->tr_resp_base = hwdesc->tr_req_base + tr_size; + + tr_desc = hwdesc->cppi5_desc_vaddr; + cppi5_trdesc_init(tr_desc, 1, tr_size, 0, 0); + cppi5_desc_set_pktids(tr_desc, 0, CPPI5_INFO1_DESC_FLOWID_DEFAULT); + cppi5_desc_set_retpolicy(tr_desc, 0, 0); + + tr_req = hwdesc->tr_req_base; + cppi5_tr_init(&tr_req->flags, CPPI5_TR_TYPE1, false, false, + CPPI5_TR_EVENT_SIZE_COMPLETION, 0); + cppi5_tr_csf_set(&tr_req->flags, CPPI5_TR_CSF_SUPR_EVT); + + tr_req->addr = rx_flush->buffer_paddr; + tr_req->icnt0 = rx_flush->buffer_size; + tr_req->icnt1 = 1; + + /* Set up descriptor to be used for packet mode */ + hwdesc = &rx_flush->hwdescs[1]; + hwdesc->cppi5_desc_size = ALIGN(sizeof(struct cppi5_host_desc_t) + + CPPI5_INFO0_HDESC_EPIB_SIZE + + CPPI5_INFO0_HDESC_PSDATA_MAX_SIZE, + ud->desc_align); + + hwdesc->cppi5_desc_vaddr = devm_kzalloc(dev, hwdesc->cppi5_desc_size, + GFP_KERNEL); + if (!hwdesc->cppi5_desc_vaddr) + return -ENOMEM; + + hwdesc->cppi5_desc_paddr = dma_map_single(dev, hwdesc->cppi5_desc_vaddr, + hwdesc->cppi5_desc_size, + DMA_TO_DEVICE); + if (dma_mapping_error(dev, hwdesc->cppi5_desc_paddr)) + return -ENOMEM; + + desc = hwdesc->cppi5_desc_vaddr; + cppi5_hdesc_init(desc, 0, 0); + cppi5_desc_set_pktids(&desc->hdr, 0, CPPI5_INFO1_DESC_FLOWID_DEFAULT); + cppi5_desc_set_retpolicy(&desc->hdr, 0, 0); + + cppi5_hdesc_attach_buf(desc, + rx_flush->buffer_paddr, rx_flush->buffer_size, + rx_flush->buffer_paddr, rx_flush->buffer_size); + + dma_sync_single_for_device(dev, hwdesc->cppi5_desc_paddr, + hwdesc->cppi5_desc_size, DMA_TO_DEVICE); + return 0; +} + #define TI_UDMAC_BUSWIDTHS (BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | \ BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \ BIT(DMA_SLAVE_BUSWIDTH_3_BYTES) | \ @@ -3361,6 +3586,10 @@ static int udma_probe(struct platform_device *pdev) if (ud->desc_align < dma_get_cache_alignment()) ud->desc_align = dma_get_cache_alignment(); + ret = udma_setup_rx_flush(ud); + if (ret) + return ret; + for (i = 0; i < ud->tchan_cnt; i++) { struct udma_tchan *tchan = &ud->tchans[i]; diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index 7243b88f81d889cd64b63d3ffc7991d05ab5e1a2..69e0d90460e6c4463046f29c76d1828d6dc3dde6 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -505,16 +505,10 @@ void edac_mc_free(struct mem_ctl_info *mci) { edac_dbg(1, "\n"); - /* If we're not yet registered with sysfs free only what was allocated - * in edac_mc_alloc(). - */ - if (!device_is_registered(&mci->dev)) { - _edac_mc_free(mci); - return; - } + if (device_is_registered(&mci->dev)) + edac_unregister_sysfs(mci); - /* the mci instance is freed here, when the sysfs object is dropped */ - edac_unregister_sysfs(mci); + _edac_mc_free(mci); } EXPORT_SYMBOL_GPL(edac_mc_free); diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c index 0367554e74374a4fbe11216985d1ec5733a04f32..c70ec0a306d8d47b312475894bc3b679780c3725 100644 --- a/drivers/edac/edac_mc_sysfs.c +++ b/drivers/edac/edac_mc_sysfs.c @@ -276,10 +276,7 @@ static const struct attribute_group *csrow_attr_groups[] = { static void csrow_attr_release(struct device *dev) { - struct csrow_info *csrow = container_of(dev, struct csrow_info, dev); - - edac_dbg(1, "device %s released\n", dev_name(dev)); - kfree(csrow); + /* release device with _edac_mc_free() */ } static const struct device_type csrow_attr_type = { @@ -447,8 +444,7 @@ static int edac_create_csrow_objects(struct mem_ctl_info *mci) csrow = mci->csrows[i]; if (!nr_pages_per_csrow(csrow)) continue; - - device_del(&mci->csrows[i]->dev); + device_unregister(&mci->csrows[i]->dev); } return err; @@ -608,10 +604,7 @@ static const struct attribute_group *dimm_attr_groups[] = { static void dimm_attr_release(struct device *dev) { - struct dimm_info *dimm = container_of(dev, struct dimm_info, dev); - - edac_dbg(1, "device %s released\n", dev_name(dev)); - kfree(dimm); + /* release device with _edac_mc_free() */ } static const struct device_type dimm_attr_type = { @@ -893,10 +886,7 @@ static const struct attribute_group *mci_attr_groups[] = { static void mci_attr_release(struct device *dev) { - struct mem_ctl_info *mci = container_of(dev, struct mem_ctl_info, dev); - - edac_dbg(1, "device %s released\n", dev_name(dev)); - kfree(mci); + /* release device with _edac_mc_free() */ } static const struct device_type mci_attr_type = { diff --git a/drivers/edac/synopsys_edac.c b/drivers/edac/synopsys_edac.c index 2d263382d797f0440d1e07408445ef4bf76c70fc..880ffd83371871032513e15a94bc5719d57ef1c8 100644 --- a/drivers/edac/synopsys_edac.c +++ b/drivers/edac/synopsys_edac.c @@ -479,20 +479,14 @@ static void handle_error(struct mem_ctl_info *mci, struct synps_ecc_status *p) pinf = &p->ceinfo; if (!priv->p_data->quirks) { snprintf(priv->message, SYNPS_EDAC_MSG_SIZE, - "DDR ECC error type:%s Row %d Bank %d Col %d ", - "CE", pinf->row, pinf->bank, pinf->col); - snprintf(priv->message, SYNPS_EDAC_MSG_SIZE, - "Bit Position: %d Data: 0x%08x\n", + "DDR ECC error type:%s Row %d Bank %d Col %d Bit Position: %d Data: 0x%08x", + "CE", pinf->row, pinf->bank, pinf->col, pinf->bitpos, pinf->data); } else { snprintf(priv->message, SYNPS_EDAC_MSG_SIZE, - "DDR ECC error type:%s Row %d Bank %d Col %d ", - "CE", pinf->row, pinf->bank, pinf->col); - snprintf(priv->message, SYNPS_EDAC_MSG_SIZE, - "BankGroup Number %d Block Number %d ", - pinf->bankgrpnr, pinf->blknr); - snprintf(priv->message, SYNPS_EDAC_MSG_SIZE, - "Bit Position: %d Data: 0x%08x\n", + "DDR ECC error type:%s Row %d Bank %d Col %d BankGroup Number %d Block Number %d Bit Position: %d Data: 0x%08x", + "CE", pinf->row, pinf->bank, pinf->col, + pinf->bankgrpnr, pinf->blknr, pinf->bitpos, pinf->data); } @@ -509,10 +503,8 @@ static void handle_error(struct mem_ctl_info *mci, struct synps_ecc_status *p) "UE", pinf->row, pinf->bank, pinf->col); } else { snprintf(priv->message, SYNPS_EDAC_MSG_SIZE, - "DDR ECC error type :%s Row %d Bank %d Col %d ", - "UE", pinf->row, pinf->bank, pinf->col); - snprintf(priv->message, SYNPS_EDAC_MSG_SIZE, - "BankGroup Number %d Block Number %d", + "DDR ECC error type :%s Row %d Bank %d Col %d BankGroup Number %d Block Number %d", + "UE", pinf->row, pinf->bank, pinf->col, pinf->bankgrpnr, pinf->blknr); } diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 621220ab3d0e348fdff0eda1af30f499ed37d1ce..21ea99f651134be47161831266f00cb43fb85f56 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -552,7 +552,7 @@ int __init efi_config_parse_tables(void *config_tables, int count, int sz, seed = early_memremap(efi.rng_seed, sizeof(*seed)); if (seed != NULL) { - size = seed->size; + size = READ_ONCE(seed->size); early_memunmap(seed, sizeof(*seed)); } else { pr_err("Could not map UEFI random seed!\n"); @@ -562,7 +562,7 @@ int __init efi_config_parse_tables(void *config_tables, int count, int sz, sizeof(*seed) + size); if (seed != NULL) { pr_notice("seeding entropy pool\n"); - add_bootloader_randomness(seed->bits, seed->size); + add_bootloader_randomness(seed->bits, size); early_memunmap(seed, sizeof(*seed) + size); } else { pr_err("Could not map UEFI random seed!\n"); diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c index 7576450c8254b8cc8c1cada05a1c9ac61922ea1f..aff3dfb4d7ba643219254820282a4f4d903edab7 100644 --- a/drivers/firmware/efi/efivars.c +++ b/drivers/firmware/efi/efivars.c @@ -83,13 +83,16 @@ static ssize_t efivar_attr_read(struct efivar_entry *entry, char *buf) { struct efi_variable *var = &entry->var; + unsigned long size = sizeof(var->Data); char *str = buf; + int ret; if (!entry || !buf) return -EINVAL; - var->DataSize = 1024; - if (efivar_entry_get(entry, &var->Attributes, &var->DataSize, var->Data)) + ret = efivar_entry_get(entry, &var->Attributes, &size, var->Data); + var->DataSize = size; + if (ret) return -EIO; if (var->Attributes & EFI_VARIABLE_NON_VOLATILE) @@ -116,13 +119,16 @@ static ssize_t efivar_size_read(struct efivar_entry *entry, char *buf) { struct efi_variable *var = &entry->var; + unsigned long size = sizeof(var->Data); char *str = buf; + int ret; if (!entry || !buf) return -EINVAL; - var->DataSize = 1024; - if (efivar_entry_get(entry, &var->Attributes, &var->DataSize, var->Data)) + ret = efivar_entry_get(entry, &var->Attributes, &size, var->Data); + var->DataSize = size; + if (ret) return -EIO; str += sprintf(str, "0x%lx\n", var->DataSize); @@ -133,12 +139,15 @@ static ssize_t efivar_data_read(struct efivar_entry *entry, char *buf) { struct efi_variable *var = &entry->var; + unsigned long size = sizeof(var->Data); + int ret; if (!entry || !buf) return -EINVAL; - var->DataSize = 1024; - if (efivar_entry_get(entry, &var->Attributes, &var->DataSize, var->Data)) + ret = efivar_entry_get(entry, &var->Attributes, &size, var->Data); + var->DataSize = size; + if (ret) return -EIO; memcpy(buf, var->Data, var->DataSize); @@ -199,6 +208,9 @@ efivar_store_raw(struct efivar_entry *entry, const char *buf, size_t count) u8 *data; int err; + if (!entry || !buf) + return -EINVAL; + if (in_compat_syscall()) { struct compat_efi_variable *compat; @@ -250,14 +262,16 @@ efivar_show_raw(struct efivar_entry *entry, char *buf) { struct efi_variable *var = &entry->var; struct compat_efi_variable *compat; + unsigned long datasize = sizeof(var->Data); size_t size; + int ret; if (!entry || !buf) return 0; - var->DataSize = 1024; - if (efivar_entry_get(entry, &entry->var.Attributes, - &entry->var.DataSize, entry->var.Data)) + ret = efivar_entry_get(entry, &var->Attributes, &datasize, var->Data); + var->DataSize = datasize; + if (ret) return -EIO; if (in_compat_syscall()) { diff --git a/drivers/firmware/imx/imx-scu.c b/drivers/firmware/imx/imx-scu.c index 03b43b7a6d1d573d9c9fc0f9421a53b6440baf8a..f71eaa5bf52d411c750aa359aa13f4a00d88130c 100644 --- a/drivers/firmware/imx/imx-scu.c +++ b/drivers/firmware/imx/imx-scu.c @@ -29,6 +29,7 @@ struct imx_sc_chan { struct mbox_client cl; struct mbox_chan *ch; int idx; + struct completion tx_done; }; struct imx_sc_ipc { @@ -100,6 +101,14 @@ int imx_scu_get_handle(struct imx_sc_ipc **ipc) } EXPORT_SYMBOL(imx_scu_get_handle); +/* Callback called when the word of a message is ack-ed, eg read by SCU */ +static void imx_scu_tx_done(struct mbox_client *cl, void *mssg, int r) +{ + struct imx_sc_chan *sc_chan = container_of(cl, struct imx_sc_chan, cl); + + complete(&sc_chan->tx_done); +} + static void imx_scu_rx_callback(struct mbox_client *c, void *msg) { struct imx_sc_chan *sc_chan = container_of(c, struct imx_sc_chan, cl); @@ -149,6 +158,19 @@ static int imx_scu_ipc_write(struct imx_sc_ipc *sc_ipc, void *msg) for (i = 0; i < hdr->size; i++) { sc_chan = &sc_ipc->chans[i % 4]; + + /* + * SCU requires that all messages words are written + * sequentially but linux MU driver implements multiple + * independent channels for each register so ordering between + * different channels must be ensured by SCU API interface. + * + * Wait for tx_done before every send to ensure that no + * queueing happens at the mailbox channel level. + */ + wait_for_completion(&sc_chan->tx_done); + reinit_completion(&sc_chan->tx_done); + ret = mbox_send_message(sc_chan->ch, &data[i]); if (ret < 0) return ret; @@ -247,6 +269,11 @@ static int imx_scu_probe(struct platform_device *pdev) cl->knows_txdone = true; cl->rx_callback = imx_scu_rx_callback; + /* Initial tx_done completion as "done" */ + cl->tx_done = imx_scu_tx_done; + init_completion(&sc_chan->tx_done); + complete(&sc_chan->tx_done); + sc_chan->sc_ipc = sc_ipc; sc_chan->idx = i % 4; sc_chan->ch = mbox_request_channel_byname(cl, chan_name); diff --git a/drivers/firmware/imx/misc.c b/drivers/firmware/imx/misc.c index 4b56a587dacd4b5b65d6d74e83eaec177ba0b7cb..d073cb3ce69937cc6073c936bfbd442172364866 100644 --- a/drivers/firmware/imx/misc.c +++ b/drivers/firmware/imx/misc.c @@ -16,7 +16,7 @@ struct imx_sc_msg_req_misc_set_ctrl { u32 ctrl; u32 val; u16 resource; -} __packed; +} __packed __aligned(4); struct imx_sc_msg_req_cpu_start { struct imx_sc_rpc_msg hdr; @@ -24,18 +24,18 @@ struct imx_sc_msg_req_cpu_start { u32 address_lo; u16 resource; u8 enable; -} __packed; +} __packed __aligned(4); struct imx_sc_msg_req_misc_get_ctrl { struct imx_sc_rpc_msg hdr; u32 ctrl; u16 resource; -} __packed; +} __packed __aligned(4); struct imx_sc_msg_resp_misc_get_ctrl { struct imx_sc_rpc_msg hdr; u32 val; -} __packed; +} __packed __aligned(4); /* * This function sets a miscellaneous control value. diff --git a/drivers/firmware/imx/scu-pd.c b/drivers/firmware/imx/scu-pd.c index b556612207e536a85dcdc8464b0256d3ff3f992a..af3ae0087de4e7ac8aa30e91dd00b6460aac265c 100644 --- a/drivers/firmware/imx/scu-pd.c +++ b/drivers/firmware/imx/scu-pd.c @@ -61,7 +61,7 @@ struct imx_sc_msg_req_set_resource_power_mode { struct imx_sc_rpc_msg hdr; u16 resource; u8 mode; -} __packed; +} __packed __aligned(4); #define IMX_SCU_PD_NAME_SIZE 20 struct imx_sc_pm_domain { diff --git a/drivers/fsi/Kconfig b/drivers/fsi/Kconfig index 92ce6d85802cc0602146bd23f6a276245f9d2db1..4cc0e630ab79b0be31ff97962a6a9c45507399f7 100644 --- a/drivers/fsi/Kconfig +++ b/drivers/fsi/Kconfig @@ -55,6 +55,7 @@ config FSI_MASTER_AST_CF config FSI_MASTER_ASPEED tristate "FSI ASPEED master" + depends on HAS_IOMEM help This option enables a FSI master that is present behind an OPB bridge in the AST2600. diff --git a/drivers/gpio/gpio-bd71828.c b/drivers/gpio/gpio-bd71828.c index 04aade9e0a4d4484f7b0218cea2df963abeb7dec..3dbbc638e9a911bfa8119e8b615736ef243d7d80 100644 --- a/drivers/gpio/gpio-bd71828.c +++ b/drivers/gpio/gpio-bd71828.c @@ -10,16 +10,6 @@ #define GPIO_OUT_REG(off) (BD71828_REG_GPIO_CTRL1 + (off)) #define HALL_GPIO_OFFSET 3 -/* - * These defines can be removed when - * "gpio: Add definition for GPIO direction" - * (9208b1e77d6e8e9776f34f46ef4079ecac9c3c25 in GPIO tree) gets merged, - */ -#ifndef GPIO_LINE_DIRECTION_IN - #define GPIO_LINE_DIRECTION_IN 1 - #define GPIO_LINE_DIRECTION_OUT 0 -#endif - struct bd71828_gpio { struct rohm_regmap_dev chip; struct gpio_chip gpio; diff --git a/drivers/gpio/gpio-sifive.c b/drivers/gpio/gpio-sifive.c index 147a1bd0451521bf5e9c78b6d7d4cdd968d6559c..c54dd08f2cbfd3c75d74ffec723f4e0e5f72e4f7 100644 --- a/drivers/gpio/gpio-sifive.c +++ b/drivers/gpio/gpio-sifive.c @@ -35,7 +35,7 @@ struct sifive_gpio { void __iomem *base; struct gpio_chip gc; struct regmap *regs; - u32 irq_state; + unsigned long irq_state; unsigned int trigger[SIFIVE_GPIO_MAX]; unsigned int irq_parent[SIFIVE_GPIO_MAX]; }; @@ -94,7 +94,7 @@ static void sifive_gpio_irq_enable(struct irq_data *d) spin_unlock_irqrestore(&gc->bgpio_lock, flags); /* Enable interrupts */ - assign_bit(offset, (unsigned long *)&chip->irq_state, 1); + assign_bit(offset, &chip->irq_state, 1); sifive_gpio_set_ie(chip, offset); } @@ -104,7 +104,7 @@ static void sifive_gpio_irq_disable(struct irq_data *d) struct sifive_gpio *chip = gpiochip_get_data(gc); int offset = irqd_to_hwirq(d) % SIFIVE_GPIO_MAX; - assign_bit(offset, (unsigned long *)&chip->irq_state, 0); + assign_bit(offset, &chip->irq_state, 0); sifive_gpio_set_ie(chip, offset); irq_chip_disable_parent(d); } diff --git a/drivers/gpio/gpio-xilinx.c b/drivers/gpio/gpio-xilinx.c index a9748b5198e634f6a0938cc8bdff61f14a120cbc..67f9f82e0db0ef49a59f073bdb52b982411f29ac 100644 --- a/drivers/gpio/gpio-xilinx.c +++ b/drivers/gpio/gpio-xilinx.c @@ -147,9 +147,10 @@ static void xgpio_set_multiple(struct gpio_chip *gc, unsigned long *mask, for (i = 0; i < gc->ngpio; i++) { if (*mask == 0) break; + /* Once finished with an index write it out to the register */ if (index != xgpio_index(chip, i)) { xgpio_writereg(chip->regs + XGPIO_DATA_OFFSET + - xgpio_regoffset(chip, i), + index * XGPIO_CHANNEL_OFFSET, chip->gpio_state[index]); spin_unlock_irqrestore(&chip->gpio_lock[index], flags); index = xgpio_index(chip, i); @@ -165,7 +166,7 @@ static void xgpio_set_multiple(struct gpio_chip *gc, unsigned long *mask, } xgpio_writereg(chip->regs + XGPIO_DATA_OFFSET + - xgpio_regoffset(chip, i), chip->gpio_state[index]); + index * XGPIO_CHANNEL_OFFSET, chip->gpio_state[index]); spin_unlock_irqrestore(&chip->gpio_lock[index], flags); } diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 44f2a449729f9cccccfe741dd07df478c395de08..e3616cc85d66b2d8deca800461f31393d4be7909 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -3187,13 +3187,33 @@ EXPORT_SYMBOL_GPL(gpiochip_free_own_desc); * rely on gpio_request() having been called beforehand. */ -static int gpio_set_config(struct gpio_chip *gc, unsigned int offset, - enum pin_config_param mode) +static int gpio_do_set_config(struct gpio_chip *gc, unsigned int offset, + unsigned long config) { if (!gc->set_config) return -ENOTSUPP; - return gc->set_config(gc, offset, mode); + return gc->set_config(gc, offset, config); +} + +static int gpio_set_config(struct gpio_chip *gc, unsigned int offset, + enum pin_config_param mode) +{ + unsigned long config; + unsigned arg; + + switch (mode) { + case PIN_CONFIG_BIAS_PULL_DOWN: + case PIN_CONFIG_BIAS_PULL_UP: + arg = 1; + break; + + default: + arg = 0; + } + + config = PIN_CONF_PACKED(mode, arg); + return gpio_do_set_config(gc, offset, config); } static int gpio_set_bias(struct gpio_chip *chip, struct gpio_desc *desc) @@ -3429,7 +3449,7 @@ int gpiod_set_debounce(struct gpio_desc *desc, unsigned debounce) chip = desc->gdev->chip; config = pinconf_to_config_packed(PIN_CONFIG_INPUT_DEBOUNCE, debounce); - return gpio_set_config(chip, gpio_chip_hwgpio(desc), config); + return gpio_do_set_config(chip, gpio_chip_hwgpio(desc), config); } EXPORT_SYMBOL_GPL(gpiod_set_debounce); @@ -3463,7 +3483,7 @@ int gpiod_set_transitory(struct gpio_desc *desc, bool transitory) packed = pinconf_to_config_packed(PIN_CONFIG_PERSIST_STATE, !transitory); gpio = gpio_chip_hwgpio(desc); - rc = gpio_set_config(chip, gpio, packed); + rc = gpio_do_set_config(chip, gpio, packed); if (rc == -ENOTSUPP) { dev_dbg(&desc->gdev->dev, "Persistence not supported for GPIO %d\n", gpio); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c index f24ed9a1a3e56a9513a70b054e6bd1746e2b2b1b..337d7cdce8e9ce34b232cae31c9ed79d28627675 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c @@ -781,11 +781,11 @@ static ssize_t amdgpu_debugfs_gpr_read(struct file *f, char __user *buf, ssize_t result = 0; uint32_t offset, se, sh, cu, wave, simd, thread, bank, *data; - if (size & 3 || *pos & 3) + if (size > 4096 || size & 3 || *pos & 3) return -EINVAL; /* decode offset */ - offset = *pos & GENMASK_ULL(11, 0); + offset = (*pos & GENMASK_ULL(11, 0)) >> 2; se = (*pos & GENMASK_ULL(19, 12)) >> 12; sh = (*pos & GENMASK_ULL(27, 20)) >> 20; cu = (*pos & GENMASK_ULL(35, 28)) >> 28; @@ -823,7 +823,7 @@ static ssize_t amdgpu_debugfs_gpr_read(struct file *f, char __user *buf, while (size) { uint32_t value; - value = data[offset++]; + value = data[result >> 2]; r = put_user(value, (uint32_t *)buf); if (r) { result = r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 39cd545976b7ea57314717a021951674eb9de48d..b8975857d60d68bb95f407668ded0e5dc60e8128 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3913,6 +3913,8 @@ static int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive, if (r) goto out; + amdgpu_fbdev_set_suspend(tmp_adev, 0); + /* must succeed. */ amdgpu_ras_resume(tmp_adev); @@ -4086,6 +4088,8 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, */ amdgpu_unregister_gpu_instance(tmp_adev); + amdgpu_fbdev_set_suspend(adev, 1); + /* disable ras on ALL IPs */ if (!(in_ras_intr && !use_baco) && amdgpu_device_ip_need_full_reset(tmp_adev)) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 94e2fd758e0130ab0185820e1905917e68c439d0..42f4febe24c6db0d5642b23acd9aa46dd9ab8db5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -1389,7 +1389,7 @@ amdgpu_get_crtc_scanout_position(struct drm_device *dev, unsigned int pipe, static struct drm_driver kms_driver = { .driver_features = - DRIVER_USE_AGP | DRIVER_ATOMIC | + DRIVER_ATOMIC | DRIVER_GEM | DRIVER_RENDER | DRIVER_MODESET | DRIVER_SYNCOBJ | DRIVER_SYNCOBJ_TIMELINE, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h index d3c27a3c43f68ad5ed11ff5b0379d8d06c648d13..7546da0cc70c7019c94f58fb0ee66debcdc93a22 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h @@ -195,6 +195,7 @@ struct amdgpu_gmc { uint32_t srbm_soft_reset; bool prt_warning; uint64_t stolen_size; + uint32_t sdpif_register; /* apertures */ u64 shared_aperture_start; u64 shared_aperture_end; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c index 07914e34bc2570b356c8b751fb29f8f120e04e69..1311d6aec5d4b3c17e5b391659c02f1fd762d41b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c @@ -52,7 +52,7 @@ static int amdgpu_perf_event_init(struct perf_event *event) return -ENOENT; /* update the hw_perf_event struct with config data */ - hwc->conf = event->attr.config; + hwc->config = event->attr.config; return 0; } @@ -74,9 +74,9 @@ static void amdgpu_perf_start(struct perf_event *event, int flags) switch (pe->pmu_perf_type) { case PERF_TYPE_AMDGPU_DF: if (!(flags & PERF_EF_RELOAD)) - pe->adev->df.funcs->pmc_start(pe->adev, hwc->conf, 1); + pe->adev->df.funcs->pmc_start(pe->adev, hwc->config, 1); - pe->adev->df.funcs->pmc_start(pe->adev, hwc->conf, 0); + pe->adev->df.funcs->pmc_start(pe->adev, hwc->config, 0); break; default: break; @@ -101,7 +101,7 @@ static void amdgpu_perf_read(struct perf_event *event) switch (pe->pmu_perf_type) { case PERF_TYPE_AMDGPU_DF: - pe->adev->df.funcs->pmc_get_count(pe->adev, hwc->conf, + pe->adev->df.funcs->pmc_get_count(pe->adev, hwc->config, &count); break; default: @@ -126,7 +126,7 @@ static void amdgpu_perf_stop(struct perf_event *event, int flags) switch (pe->pmu_perf_type) { case PERF_TYPE_AMDGPU_DF: - pe->adev->df.funcs->pmc_stop(pe->adev, hwc->conf, 0); + pe->adev->df.funcs->pmc_stop(pe->adev, hwc->config, 0); break; default: break; @@ -156,7 +156,8 @@ static int amdgpu_perf_add(struct perf_event *event, int flags) switch (pe->pmu_perf_type) { case PERF_TYPE_AMDGPU_DF: - retval = pe->adev->df.funcs->pmc_start(pe->adev, hwc->conf, 1); + retval = pe->adev->df.funcs->pmc_start(pe->adev, + hwc->config, 1); break; default: return 0; @@ -184,7 +185,7 @@ static void amdgpu_perf_del(struct perf_event *event, int flags) switch (pe->pmu_perf_type) { case PERF_TYPE_AMDGPU_DF: - pe->adev->df.funcs->pmc_stop(pe->adev, hwc->conf, 1); + pe->adev->df.funcs->pmc_stop(pe->adev, hwc->config, 1); break; default: break; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 3a1570dafe3482ac93992c0e76e1777d185721d6..146f96661b6b5c8945ba985bc047e1ccbd71fe38 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -1013,6 +1013,30 @@ static int psp_dtm_initialize(struct psp_context *psp) return 0; } +static int psp_dtm_unload(struct psp_context *psp) +{ + int ret; + struct psp_gfx_cmd_resp *cmd; + + /* + * TODO: bypass the unloading in sriov for now + */ + if (amdgpu_sriov_vf(psp->adev)) + return 0; + + cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL); + if (!cmd) + return -ENOMEM; + + psp_prep_ta_unload_cmd_buf(cmd, psp->dtm_context.session_id); + + ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr); + + kfree(cmd); + + return ret; +} + int psp_dtm_invoke(struct psp_context *psp, uint32_t ta_cmd_id) { /* @@ -1037,7 +1061,7 @@ static int psp_dtm_terminate(struct psp_context *psp) if (!psp->dtm_context.dtm_initialized) return 0; - ret = psp_hdcp_unload(psp); + ret = psp_dtm_unload(psp); if (ret) return ret; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h index d6deb0eb1e15a4a91f715b2cbeb20525894e3090..6fe057329de2b1237887dbbd3946cba653833806 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h @@ -179,6 +179,7 @@ struct amdgpu_vcn_inst { struct amdgpu_irq_src irq; struct amdgpu_vcn_reg external; struct amdgpu_bo *dpg_sram_bo; + struct dpg_pause_state pause_state; void *dpg_sram_cpu_addr; uint64_t dpg_sram_gpu_addr; uint32_t *dpg_sram_curr_addr; @@ -190,8 +191,6 @@ struct amdgpu_vcn { const struct firmware *fw; /* VCN firmware */ unsigned num_enc_rings; enum amd_powergating_state cur_state; - struct dpg_pause_state pause_state; - bool indirect_sram; uint8_t num_vcn_inst; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 1785fdad6ecbaa4631468e7202470708465c3d9c..02702597ddeb7048cb5eaeaf9d32718cded3222a 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -52,7 +52,7 @@ * 1. Primary ring * 2. Async ring */ -#define GFX10_NUM_GFX_RINGS 2 +#define GFX10_NUM_GFX_RINGS_NV1X 1 #define GFX10_MEC_HPD_SIZE 2048 #define F32_CE_PROGRAM_RAM_SIZE 65536 @@ -1304,7 +1304,7 @@ static int gfx_v10_0_sw_init(void *handle) case CHIP_NAVI14: case CHIP_NAVI12: adev->gfx.me.num_me = 1; - adev->gfx.me.num_pipe_per_me = 2; + adev->gfx.me.num_pipe_per_me = 1; adev->gfx.me.num_queue_per_pipe = 1; adev->gfx.mec.num_mec = 2; adev->gfx.mec.num_pipe_per_mec = 4; @@ -2710,18 +2710,20 @@ static int gfx_v10_0_cp_gfx_start(struct amdgpu_device *adev) amdgpu_ring_commit(ring); /* submit cs packet to copy state 0 to next available state */ - ring = &adev->gfx.gfx_ring[1]; - r = amdgpu_ring_alloc(ring, 2); - if (r) { - DRM_ERROR("amdgpu: cp failed to lock ring (%d).\n", r); - return r; - } - - amdgpu_ring_write(ring, PACKET3(PACKET3_CLEAR_STATE, 0)); - amdgpu_ring_write(ring, 0); + if (adev->gfx.num_gfx_rings > 1) { + /* maximum supported gfx ring is 2 */ + ring = &adev->gfx.gfx_ring[1]; + r = amdgpu_ring_alloc(ring, 2); + if (r) { + DRM_ERROR("amdgpu: cp failed to lock ring (%d).\n", r); + return r; + } - amdgpu_ring_commit(ring); + amdgpu_ring_write(ring, PACKET3(PACKET3_CLEAR_STATE, 0)); + amdgpu_ring_write(ring, 0); + amdgpu_ring_commit(ring); + } return 0; } @@ -2818,39 +2820,41 @@ static int gfx_v10_0_cp_gfx_resume(struct amdgpu_device *adev) mutex_unlock(&adev->srbm_mutex); /* Init gfx ring 1 for pipe 1 */ - mutex_lock(&adev->srbm_mutex); - gfx_v10_0_cp_gfx_switch_pipe(adev, PIPE_ID1); - ring = &adev->gfx.gfx_ring[1]; - rb_bufsz = order_base_2(ring->ring_size / 8); - tmp = REG_SET_FIELD(0, CP_RB1_CNTL, RB_BUFSZ, rb_bufsz); - tmp = REG_SET_FIELD(tmp, CP_RB1_CNTL, RB_BLKSZ, rb_bufsz - 2); - WREG32_SOC15(GC, 0, mmCP_RB1_CNTL, tmp); - /* Initialize the ring buffer's write pointers */ - ring->wptr = 0; - WREG32_SOC15(GC, 0, mmCP_RB1_WPTR, lower_32_bits(ring->wptr)); - WREG32_SOC15(GC, 0, mmCP_RB1_WPTR_HI, upper_32_bits(ring->wptr)); - /* Set the wb address wether it's enabled or not */ - rptr_addr = adev->wb.gpu_addr + (ring->rptr_offs * 4); - WREG32_SOC15(GC, 0, mmCP_RB1_RPTR_ADDR, lower_32_bits(rptr_addr)); - WREG32_SOC15(GC, 0, mmCP_RB1_RPTR_ADDR_HI, upper_32_bits(rptr_addr) & - CP_RB1_RPTR_ADDR_HI__RB_RPTR_ADDR_HI_MASK); - wptr_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4); - WREG32_SOC15(GC, 0, mmCP_RB_WPTR_POLL_ADDR_LO, - lower_32_bits(wptr_gpu_addr)); - WREG32_SOC15(GC, 0, mmCP_RB_WPTR_POLL_ADDR_HI, - upper_32_bits(wptr_gpu_addr)); - - mdelay(1); - WREG32_SOC15(GC, 0, mmCP_RB1_CNTL, tmp); - - rb_addr = ring->gpu_addr >> 8; - WREG32_SOC15(GC, 0, mmCP_RB1_BASE, rb_addr); - WREG32_SOC15(GC, 0, mmCP_RB1_BASE_HI, upper_32_bits(rb_addr)); - WREG32_SOC15(GC, 0, mmCP_RB1_ACTIVE, 1); - - gfx_v10_0_cp_gfx_set_doorbell(adev, ring); - mutex_unlock(&adev->srbm_mutex); - + if (adev->gfx.num_gfx_rings > 1) { + mutex_lock(&adev->srbm_mutex); + gfx_v10_0_cp_gfx_switch_pipe(adev, PIPE_ID1); + /* maximum supported gfx ring is 2 */ + ring = &adev->gfx.gfx_ring[1]; + rb_bufsz = order_base_2(ring->ring_size / 8); + tmp = REG_SET_FIELD(0, CP_RB1_CNTL, RB_BUFSZ, rb_bufsz); + tmp = REG_SET_FIELD(tmp, CP_RB1_CNTL, RB_BLKSZ, rb_bufsz - 2); + WREG32_SOC15(GC, 0, mmCP_RB1_CNTL, tmp); + /* Initialize the ring buffer's write pointers */ + ring->wptr = 0; + WREG32_SOC15(GC, 0, mmCP_RB1_WPTR, lower_32_bits(ring->wptr)); + WREG32_SOC15(GC, 0, mmCP_RB1_WPTR_HI, upper_32_bits(ring->wptr)); + /* Set the wb address wether it's enabled or not */ + rptr_addr = adev->wb.gpu_addr + (ring->rptr_offs * 4); + WREG32_SOC15(GC, 0, mmCP_RB1_RPTR_ADDR, lower_32_bits(rptr_addr)); + WREG32_SOC15(GC, 0, mmCP_RB1_RPTR_ADDR_HI, upper_32_bits(rptr_addr) & + CP_RB1_RPTR_ADDR_HI__RB_RPTR_ADDR_HI_MASK); + wptr_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4); + WREG32_SOC15(GC, 0, mmCP_RB_WPTR_POLL_ADDR_LO, + lower_32_bits(wptr_gpu_addr)); + WREG32_SOC15(GC, 0, mmCP_RB_WPTR_POLL_ADDR_HI, + upper_32_bits(wptr_gpu_addr)); + + mdelay(1); + WREG32_SOC15(GC, 0, mmCP_RB1_CNTL, tmp); + + rb_addr = ring->gpu_addr >> 8; + WREG32_SOC15(GC, 0, mmCP_RB1_BASE, rb_addr); + WREG32_SOC15(GC, 0, mmCP_RB1_BASE_HI, upper_32_bits(rb_addr)); + WREG32_SOC15(GC, 0, mmCP_RB1_ACTIVE, 1); + + gfx_v10_0_cp_gfx_set_doorbell(adev, ring); + mutex_unlock(&adev->srbm_mutex); + } /* Switch to pipe 0 */ mutex_lock(&adev->srbm_mutex); gfx_v10_0_cp_gfx_switch_pipe(adev, PIPE_ID0); @@ -3513,6 +3517,7 @@ static int gfx_v10_0_kcq_init_queue(struct amdgpu_ring *ring) /* reset ring buffer */ ring->wptr = 0; + atomic64_set((atomic64_t *)&adev->wb.wb[ring->wptr_offs], 0); amdgpu_ring_clear_ring(ring); } else { amdgpu_ring_clear_ring(ring); @@ -3923,11 +3928,13 @@ static uint64_t gfx_v10_0_get_gpu_clock_counter(struct amdgpu_device *adev) { uint64_t clock; + amdgpu_gfx_off_ctrl(adev, false); mutex_lock(&adev->gfx.gpu_clock_mutex); WREG32_SOC15(GC, 0, mmRLC_CAPTURE_GPU_CLOCK_COUNT, 1); clock = (uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_LSB) | ((uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_MSB) << 32ULL); mutex_unlock(&adev->gfx.gpu_clock_mutex); + amdgpu_gfx_off_ctrl(adev, true); return clock; } @@ -3964,7 +3971,8 @@ static int gfx_v10_0_early_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - adev->gfx.num_gfx_rings = GFX10_NUM_GFX_RINGS; + adev->gfx.num_gfx_rings = GFX10_NUM_GFX_RINGS_NV1X; + adev->gfx.num_compute_rings = AMDGPU_MAX_COMPUTE_RINGS; gfx_v10_0_set_kiq_pm4_funcs(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 90f64b8bc3586adc4f271876fb8428100818cc70..889154a78c4a8935764fa0e069613309c12e5840 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -1193,6 +1193,14 @@ static bool gfx_v9_0_should_disable_gfxoff(struct pci_dev *pdev) return false; } +static bool is_raven_kicker(struct amdgpu_device *adev) +{ + if (adev->pm.fw_version >= 0x41e2b) + return true; + else + return false; +} + static void gfx_v9_0_check_if_need_gfxoff(struct amdgpu_device *adev) { if (gfx_v9_0_should_disable_gfxoff(adev->pdev)) @@ -1205,9 +1213,8 @@ static void gfx_v9_0_check_if_need_gfxoff(struct amdgpu_device *adev) break; case CHIP_RAVEN: if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8) && - ((adev->gfx.rlc_fw_version != 106 && + ((!is_raven_kicker(adev) && adev->gfx.rlc_fw_version < 531) || - (adev->gfx.rlc_fw_version == 53815) || (adev->gfx.rlc_feature_version < 1) || !adev->gfx.rlc.is_rlc_v2_1)) adev->pm.pp_feature &= ~PP_GFXOFF_MASK; @@ -3656,6 +3663,7 @@ static int gfx_v9_0_kcq_init_queue(struct amdgpu_ring *ring) /* reset ring buffer */ ring->wptr = 0; + atomic64_set((atomic64_t *)&adev->wb.wb[ring->wptr_offs], 0); amdgpu_ring_clear_ring(ring); } else { amdgpu_ring_clear_ring(ring); @@ -3959,6 +3967,7 @@ static uint64_t gfx_v9_0_get_gpu_clock_counter(struct amdgpu_device *adev) { uint64_t clock; + amdgpu_gfx_off_ctrl(adev, false); mutex_lock(&adev->gfx.gpu_clock_mutex); if (adev->asic_type == CHIP_VEGA10 && amdgpu_sriov_runtime(adev)) { uint32_t tmp, lsb, msb, i = 0; @@ -3977,6 +3986,7 @@ static uint64_t gfx_v9_0_get_gpu_clock_counter(struct amdgpu_device *adev) ((uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_MSB) << 32ULL); } mutex_unlock(&adev->gfx.gpu_clock_mutex); + amdgpu_gfx_off_ctrl(adev, true); return clock; } @@ -4374,9 +4384,17 @@ static int gfx_v9_0_ecc_late_init(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; int r; - r = gfx_v9_0_do_edc_gds_workarounds(adev); - if (r) - return r; + /* + * Temp workaround to fix the issue that CP firmware fails to + * update read pointer when CPDMA is writing clearing operation + * to GDS in suspend/resume sequence on several cards. So just + * limit this operation in cold boot sequence. + */ + if (!adev->in_suspend) { + r = gfx_v9_0_do_edc_gds_workarounds(adev); + if (r) + return r; + } /* requires IBs so do in late init after IB pool is initialized */ r = gfx_v9_0_do_edc_gpr_workarounds(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 90216abf14a4c356732a7950284d835f19fbc9de..cc0c273a86f9298b19e60dbf4e401d9fe440017e 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1271,6 +1271,19 @@ static void gmc_v9_0_init_golden_registers(struct amdgpu_device *adev) } } +/** + * gmc_v9_0_restore_registers - restores regs + * + * @adev: amdgpu_device pointer + * + * This restores register values, saved at suspend. + */ +static void gmc_v9_0_restore_registers(struct amdgpu_device *adev) +{ + if (adev->asic_type == CHIP_RAVEN) + WREG32(mmDCHUBBUB_SDPIF_MMIO_CNTRL_0, adev->gmc.sdpif_register); +} + /** * gmc_v9_0_gart_enable - gart enable * @@ -1376,6 +1389,20 @@ static int gmc_v9_0_hw_init(void *handle) return r; } +/** + * gmc_v9_0_save_registers - saves regs + * + * @adev: amdgpu_device pointer + * + * This saves potential register values that should be + * restored upon resume + */ +static void gmc_v9_0_save_registers(struct amdgpu_device *adev) +{ + if (adev->asic_type == CHIP_RAVEN) + adev->gmc.sdpif_register = RREG32(mmDCHUBBUB_SDPIF_MMIO_CNTRL_0); +} + /** * gmc_v9_0_gart_disable - gart disable * @@ -1412,9 +1439,16 @@ static int gmc_v9_0_hw_fini(void *handle) static int gmc_v9_0_suspend(void *handle) { + int r; struct amdgpu_device *adev = (struct amdgpu_device *)handle; - return gmc_v9_0_hw_fini(adev); + r = gmc_v9_0_hw_fini(adev); + if (r) + return r; + + gmc_v9_0_save_registers(adev); + + return 0; } static int gmc_v9_0_resume(void *handle) @@ -1422,6 +1456,7 @@ static int gmc_v9_0_resume(void *handle) int r; struct amdgpu_device *adev = (struct amdgpu_device *)handle; + gmc_v9_0_restore_registers(adev); r = gmc_v9_0_hw_init(adev); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c index ff2e6e1ccde7ccee5008fe282a4e407a905b4b33..6173951db7b4527875a6cb53b043a124c1ae8227 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c @@ -693,7 +693,7 @@ static int jpeg_v2_0_set_clockgating_state(void *handle, bool enable = (state == AMD_CG_STATE_GATE); if (enable) { - if (jpeg_v2_0_is_idle(handle)) + if (!jpeg_v2_0_is_idle(handle)) return -EBUSY; jpeg_v2_0_enable_clock_gating(adev); } else { diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c index c6d046df4b706951455d2095c46f1eb08361f163..c04c2078a7c1f3655762e871c9147db0bafe8b64 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c @@ -477,7 +477,7 @@ static int jpeg_v2_5_set_clockgating_state(void *handle, continue; if (enable) { - if (jpeg_v2_5_is_idle(handle)) + if (!jpeg_v2_5_is_idle(handle)) return -EBUSY; jpeg_v2_5_enable_clock_gating(adev, i); } else { diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index 15f3424a1ff792b299f83c71c335461f08177d10..d8945c31b622c3a8ca5c628e2247e060acc60d2f 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -89,6 +89,13 @@ #define HDP_MEM_POWER_CTRL__RC_MEM_POWER_CTRL_EN_MASK 0x00010000L #define HDP_MEM_POWER_CTRL__RC_MEM_POWER_LS_EN_MASK 0x00020000L #define mmHDP_MEM_POWER_CTRL_BASE_IDX 0 + +/* for Vega20/arcturus regiter offset change */ +#define mmROM_INDEX_VG20 0x00e4 +#define mmROM_INDEX_VG20_BASE_IDX 0 +#define mmROM_DATA_VG20 0x00e5 +#define mmROM_DATA_VG20_BASE_IDX 0 + /* * Indirect registers accessor */ @@ -272,7 +279,12 @@ static u32 soc15_get_config_memsize(struct amdgpu_device *adev) static u32 soc15_get_xclk(struct amdgpu_device *adev) { - return adev->clock.spll.reference_freq; + u32 reference_clock = adev->clock.spll.reference_freq; + + if (adev->asic_type == CHIP_RAVEN) + return reference_clock / 4; + + return reference_clock; } @@ -304,6 +316,8 @@ static bool soc15_read_bios_from_rom(struct amdgpu_device *adev, { u32 *dw_ptr; u32 i, length_dw; + uint32_t rom_index_offset; + uint32_t rom_data_offset; if (bios == NULL) return false; @@ -316,11 +330,23 @@ static bool soc15_read_bios_from_rom(struct amdgpu_device *adev, dw_ptr = (u32 *)bios; length_dw = ALIGN(length_bytes, 4) / 4; + switch (adev->asic_type) { + case CHIP_VEGA20: + case CHIP_ARCTURUS: + rom_index_offset = SOC15_REG_OFFSET(SMUIO, 0, mmROM_INDEX_VG20); + rom_data_offset = SOC15_REG_OFFSET(SMUIO, 0, mmROM_DATA_VG20); + break; + default: + rom_index_offset = SOC15_REG_OFFSET(SMUIO, 0, mmROM_INDEX); + rom_data_offset = SOC15_REG_OFFSET(SMUIO, 0, mmROM_DATA); + break; + } + /* set rom index to 0 */ - WREG32(SOC15_REG_OFFSET(SMUIO, 0, mmROM_INDEX), 0); + WREG32(rom_index_offset, 0); /* read out the rom data */ for (i = 0; i < length_dw; i++) - dw_ptr[i] = RREG32(SOC15_REG_OFFSET(SMUIO, 0, mmROM_DATA)); + dw_ptr[i] = RREG32(rom_data_offset); return true; } diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c index 1a24fadd30e2da76d1c2a9cd3760f50edfdeb1ef..09b0572b838d29d6a758a570555722b03cbba341 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c @@ -1207,9 +1207,10 @@ static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev, struct amdgpu_ring *ring; /* pause/unpause if state is changed */ - if (adev->vcn.pause_state.fw_based != new_state->fw_based) { + if (adev->vcn.inst[inst_idx].pause_state.fw_based != new_state->fw_based) { DRM_DEBUG("dpg pause state changed %d:%d -> %d:%d", - adev->vcn.pause_state.fw_based, adev->vcn.pause_state.jpeg, + adev->vcn.inst[inst_idx].pause_state.fw_based, + adev->vcn.inst[inst_idx].pause_state.jpeg, new_state->fw_based, new_state->jpeg); reg_data = RREG32_SOC15(UVD, 0, mmUVD_DPG_PAUSE) & @@ -1258,13 +1259,14 @@ static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev, reg_data &= ~UVD_DPG_PAUSE__NJ_PAUSE_DPG_REQ_MASK; WREG32_SOC15(UVD, 0, mmUVD_DPG_PAUSE, reg_data); } - adev->vcn.pause_state.fw_based = new_state->fw_based; + adev->vcn.inst[inst_idx].pause_state.fw_based = new_state->fw_based; } /* pause/unpause if state is changed */ - if (adev->vcn.pause_state.jpeg != new_state->jpeg) { + if (adev->vcn.inst[inst_idx].pause_state.jpeg != new_state->jpeg) { DRM_DEBUG("dpg pause state changed %d:%d -> %d:%d", - adev->vcn.pause_state.fw_based, adev->vcn.pause_state.jpeg, + adev->vcn.inst[inst_idx].pause_state.fw_based, + adev->vcn.inst[inst_idx].pause_state.jpeg, new_state->fw_based, new_state->jpeg); reg_data = RREG32_SOC15(UVD, 0, mmUVD_DPG_PAUSE) & @@ -1318,7 +1320,7 @@ static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev, reg_data &= ~UVD_DPG_PAUSE__JPEG_PAUSE_DPG_REQ_MASK; WREG32_SOC15(UVD, 0, mmUVD_DPG_PAUSE, reg_data); } - adev->vcn.pause_state.jpeg = new_state->jpeg; + adev->vcn.inst[inst_idx].pause_state.jpeg = new_state->jpeg; } return 0; @@ -1350,7 +1352,7 @@ static int vcn_v1_0_set_clockgating_state(void *handle, if (enable) { /* wait for STATUS to clear */ - if (vcn_v1_0_is_idle(handle)) + if (!vcn_v1_0_is_idle(handle)) return -EBUSY; vcn_v1_0_enable_clock_gating(adev); } else { diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c index 4f7216788f11341860260374bb955b8c4933557f..b7f17342bbf082659838fdb43575e2a04b9ca930 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c @@ -1137,9 +1137,9 @@ static int vcn_v2_0_pause_dpg_mode(struct amdgpu_device *adev, int ret_code; /* pause/unpause if state is changed */ - if (adev->vcn.pause_state.fw_based != new_state->fw_based) { + if (adev->vcn.inst[inst_idx].pause_state.fw_based != new_state->fw_based) { DRM_DEBUG("dpg pause state changed %d -> %d", - adev->vcn.pause_state.fw_based, new_state->fw_based); + adev->vcn.inst[inst_idx].pause_state.fw_based, new_state->fw_based); reg_data = RREG32_SOC15(UVD, 0, mmUVD_DPG_PAUSE) & (~UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK); @@ -1185,7 +1185,7 @@ static int vcn_v2_0_pause_dpg_mode(struct amdgpu_device *adev, reg_data &= ~UVD_DPG_PAUSE__NJ_PAUSE_DPG_REQ_MASK; WREG32_SOC15(UVD, 0, mmUVD_DPG_PAUSE, reg_data); } - adev->vcn.pause_state.fw_based = new_state->fw_based; + adev->vcn.inst[inst_idx].pause_state.fw_based = new_state->fw_based; } return 0; @@ -1217,7 +1217,7 @@ static int vcn_v2_0_set_clockgating_state(void *handle, if (enable) { /* wait for STATUS to clear */ - if (vcn_v2_0_is_idle(handle)) + if (!vcn_v2_0_is_idle(handle)) return -EBUSY; vcn_v2_0_enable_clock_gating(adev); } else { diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c index 70fae7977f8f4695e4e7a3afc240402fc7569904..678253d81154fb3a719d7bd9ab1c75524c830b78 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c @@ -1367,9 +1367,9 @@ static int vcn_v2_5_pause_dpg_mode(struct amdgpu_device *adev, int ret_code; /* pause/unpause if state is changed */ - if (adev->vcn.pause_state.fw_based != new_state->fw_based) { + if (adev->vcn.inst[inst_idx].pause_state.fw_based != new_state->fw_based) { DRM_DEBUG("dpg pause state changed %d -> %d", - adev->vcn.pause_state.fw_based, new_state->fw_based); + adev->vcn.inst[inst_idx].pause_state.fw_based, new_state->fw_based); reg_data = RREG32_SOC15(UVD, inst_idx, mmUVD_DPG_PAUSE) & (~UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK); @@ -1407,14 +1407,14 @@ static int vcn_v2_5_pause_dpg_mode(struct amdgpu_device *adev, RREG32_SOC15(UVD, inst_idx, mmUVD_SCRATCH2) & 0x7FFFFFFF); SOC15_WAIT_ON_RREG(UVD, inst_idx, mmUVD_POWER_STATUS, - 0x0, UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ret_code); + UVD_PGFSM_CONFIG__UVDM_UVDU_PWR_ON, UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ret_code); } } else { /* unpause dpg, no need to wait */ reg_data &= ~UVD_DPG_PAUSE__NJ_PAUSE_DPG_REQ_MASK; WREG32_SOC15(UVD, inst_idx, mmUVD_DPG_PAUSE, reg_data); } - adev->vcn.pause_state.fw_based = new_state->fw_based; + adev->vcn.inst[inst_idx].pause_state.fw_based = new_state->fw_based; } return 0; @@ -1672,7 +1672,7 @@ static int vcn_v2_5_set_clockgating_state(void *handle, return 0; if (enable) { - if (vcn_v2_5_is_idle(handle)) + if (!vcn_v2_5_is_idle(handle)) return -EBUSY; vcn_v2_5_enable_clock_gating(adev); } else { 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 279541517a99a3a733722f72c9fff84fd8d13b2b..6240259b3a9379d4195078ff16aebab3fbbb8667 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -522,8 +522,9 @@ static void dm_dcn_crtc_high_irq(void *interrupt_params) acrtc_state = to_dm_crtc_state(acrtc->base.state); - DRM_DEBUG_DRIVER("crtc:%d, vupdate-vrr:%d\n", acrtc->crtc_id, - amdgpu_dm_vrr_active(acrtc_state)); + DRM_DEBUG_DRIVER("crtc:%d, vupdate-vrr:%d, planes:%d\n", acrtc->crtc_id, + amdgpu_dm_vrr_active(acrtc_state), + acrtc_state->active_planes); amdgpu_dm_crtc_handle_crc_irq(&acrtc->base); drm_crtc_handle_vblank(&acrtc->base); @@ -543,7 +544,18 @@ static void dm_dcn_crtc_high_irq(void *interrupt_params) &acrtc_state->vrr_params.adjust); } - if (acrtc->pflip_status == AMDGPU_FLIP_SUBMITTED) { + /* + * If there aren't any active_planes then DCH HUBP may be clock-gated. + * In that case, pageflip completion interrupts won't fire and pageflip + * completion events won't get delivered. Prevent this by sending + * pending pageflip events from here if a flip is still pending. + * + * If any planes are enabled, use dm_pflip_high_irq() instead, to + * avoid race conditions between flip programming and completion, + * which could cause too early flip completion events. + */ + if (acrtc->pflip_status == AMDGPU_FLIP_SUBMITTED && + acrtc_state->active_planes == 0) { if (acrtc->event) { drm_crtc_send_vblank_event(&acrtc->base, acrtc->event); acrtc->event = NULL; @@ -1422,6 +1434,73 @@ static void s3_handle_mst(struct drm_device *dev, bool suspend) drm_kms_helper_hotplug_event(dev); } +static int amdgpu_dm_smu_write_watermarks_table(struct amdgpu_device *adev) +{ + struct smu_context *smu = &adev->smu; + int ret = 0; + + if (!is_support_sw_smu(adev)) + return 0; + + /* This interface is for dGPU Navi1x.Linux dc-pplib interface depends + * on window driver dc implementation. + * For Navi1x, clock settings of dcn watermarks are fixed. the settings + * should be passed to smu during boot up and resume from s3. + * boot up: dc calculate dcn watermark clock settings within dc_create, + * dcn20_resource_construct + * then call pplib functions below to pass the settings to smu: + * smu_set_watermarks_for_clock_ranges + * smu_set_watermarks_table + * navi10_set_watermarks_table + * smu_write_watermarks_table + * + * For Renoir, clock settings of dcn watermark are also fixed values. + * dc has implemented different flow for window driver: + * dc_hardware_init / dc_set_power_state + * dcn10_init_hw + * notify_wm_ranges + * set_wm_ranges + * -- Linux + * smu_set_watermarks_for_clock_ranges + * renoir_set_watermarks_table + * smu_write_watermarks_table + * + * For Linux, + * dc_hardware_init -> amdgpu_dm_init + * dc_set_power_state --> dm_resume + * + * therefore, this function apply to navi10/12/14 but not Renoir + * * + */ + switch(adev->asic_type) { + case CHIP_NAVI10: + case CHIP_NAVI14: + case CHIP_NAVI12: + break; + default: + return 0; + } + + mutex_lock(&smu->mutex); + + /* pass data to smu controller */ + if ((smu->watermarks_bitmap & WATERMARKS_EXIST) && + !(smu->watermarks_bitmap & WATERMARKS_LOADED)) { + ret = smu_write_watermarks_table(smu); + + if (ret) { + mutex_unlock(&smu->mutex); + DRM_ERROR("Failed to update WMTABLE!\n"); + return ret; + } + smu->watermarks_bitmap |= WATERMARKS_LOADED; + } + + mutex_unlock(&smu->mutex); + + return 0; +} + /** * dm_hw_init() - Initialize DC device * @handle: The base driver device containing the amdgpu_dm device. @@ -1700,6 +1779,8 @@ static int dm_resume(void *handle) amdgpu_dm_irq_resume_late(adev); + amdgpu_dm_smu_write_watermarks_table(adev); + return 0; } @@ -1911,7 +1992,7 @@ static void handle_hpd_irq(void *param) mutex_lock(&aconnector->hpd_lock); #ifdef CONFIG_DRM_AMD_DC_HDCP - if (adev->asic_type >= CHIP_RAVEN) + if (adev->dm.hdcp_workqueue) hdcp_reset_display(adev->dm.hdcp_workqueue, aconnector->dc_link->link_index); #endif if (aconnector->fake_enable) @@ -2088,8 +2169,10 @@ static void handle_hpd_rx_irq(void *param) } } #ifdef CONFIG_DRM_AMD_DC_HDCP - if (hpd_irq_data.bytes.device_service_irq.bits.CP_IRQ) - hdcp_handle_cpirq(adev->dm.hdcp_workqueue, aconnector->base.index); + if (hpd_irq_data.bytes.device_service_irq.bits.CP_IRQ) { + if (adev->dm.hdcp_workqueue) + hdcp_handle_cpirq(adev->dm.hdcp_workqueue, aconnector->base.index); + } #endif if ((dc_link->cur_link_settings.lane_count != LANE_COUNT_UNKNOWN) || (dc_link->type == dc_connection_mst_branch)) @@ -5702,7 +5785,7 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm, drm_connector_attach_vrr_capable_property( &aconnector->base); #ifdef CONFIG_DRM_AMD_DC_HDCP - if (adev->asic_type >= CHIP_RAVEN) + if (adev->dm.hdcp_workqueue) drm_connector_attach_content_protection_property(&aconnector->base, true); #endif } @@ -8408,7 +8491,6 @@ bool amdgpu_dm_psr_enable(struct dc_stream_state *stream) /* Calculate number of static frames before generating interrupt to * enter PSR. */ - unsigned int frame_time_microsec = 1000000 / vsync_rate_hz; // Init fail safe of 2 frames static unsigned int num_frames_static = 2; @@ -8423,8 +8505,10 @@ bool amdgpu_dm_psr_enable(struct dc_stream_state *stream) * Calculate number of frames such that at least 30 ms of time has * passed. */ - if (vsync_rate_hz != 0) + if (vsync_rate_hz != 0) { + unsigned int frame_time_microsec = 1000000 / vsync_rate_hz; num_frames_static = (30000 / frame_time_microsec) + 1; + } params.triggers.cursor_update = true; params.triggers.overlay_update = true; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 5672f776591965f7f082ed389f4032b2262725cb..da73161043d5f0c0f46953f56dfcc0d271a468cd 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -451,6 +451,7 @@ static void dm_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr, aconnector->dc_sink); dc_sink_release(aconnector->dc_sink); aconnector->dc_sink = NULL; + aconnector->dc_link->cur_link_settings.lane_count = 0; } drm_connector_unregister(connector); diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c index 629a07a2719b2db7e3c657c0ed07aa669e0b2b28..c4ba6e84db6511a81eda89531c1de7d000aa1bd1 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c @@ -711,10 +711,6 @@ static void enable_disp_power_gating_dmcub( power_gating.header.sub_type = DMUB_CMD__VBIOS_ENABLE_DISP_POWER_GATING; power_gating.power_gating.pwr = *pwr; - /* ATOM_ENABLE is old API in DMUB */ - if (power_gating.power_gating.pwr.enable == ATOM_ENABLE) - power_gating.power_gating.pwr.enable = ATOM_INIT; - dc_dmub_srv_cmd_queue(dmcub, &power_gating.header); dc_dmub_srv_cmd_execute(dmcub); dc_dmub_srv_wait_idle(dmcub); diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile b/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile index 3cd2831950919e82bad51ad38797c3b7fa930c7e..c0f6a8c7de7de82c9d455474cd39da58937e112d 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile @@ -87,6 +87,12 @@ AMD_DISPLAY_FILES += $(AMD_DAL_CLK_MGR_DCN20) ############################################################################### CLK_MGR_DCN21 = rn_clk_mgr.o rn_clk_mgr_vbios_smu.o +# prevent build errors regarding soft-float vs hard-float FP ABI tags +# this code is currently unused on ppc64, as it applies to Renoir APUs only +ifdef CONFIG_PPC64 +CFLAGS_$(AMDDALPATH)/dc/clk_mgr/dcn21/rn_clk_mgr.o := $(call cc-option,-mno-gnu-attribute) +endif + AMD_DAL_CLK_MGR_DCN21 = $(addprefix $(AMDDALPATH)/dc/clk_mgr/dcn21/,$(CLK_MGR_DCN21)) AMD_DISPLAY_FILES += $(AMD_DAL_CLK_MGR_DCN21) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c index 495f01e9f2cac4f3da8e243f4ca0f79dadfac495..49ce46b543eaf5227d0a407504e7ed1872832484 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c @@ -117,7 +117,7 @@ void dcn20_update_clocks_update_dpp_dto(struct clk_mgr_internal *clk_mgr, prev_dppclk_khz = clk_mgr->base.ctx->dc->current_state->res_ctx.pipe_ctx[i].plane_res.bw.dppclk_khz; - if (safe_to_lower || prev_dppclk_khz < dppclk_khz) { + if ((prev_dppclk_khz > dppclk_khz && safe_to_lower) || prev_dppclk_khz < dppclk_khz) { clk_mgr->dccg->funcs->update_dpp_dto( clk_mgr->dccg, dpp_inst, dppclk_khz); } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c index 7ae4c06232dd2bf53fdb89a0c92f24e34d2fe9c2..9ef3f7b91a1d08aed184038dd6ff82e566bb6a6b 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c @@ -151,6 +151,12 @@ void rn_update_clocks(struct clk_mgr *clk_mgr_base, rn_vbios_smu_set_min_deep_sleep_dcfclk(clk_mgr, clk_mgr_base->clks.dcfclk_deep_sleep_khz); } + // workaround: Limit dppclk to 100Mhz to avoid lower eDP panel switch to plus 4K monitor underflow. + if (!IS_DIAG_DC(dc->ctx->dce_environment)) { + if (new_clocks->dppclk_khz < 100000) + new_clocks->dppclk_khz = 100000; + } + if (should_set_clock(safe_to_lower, new_clocks->dppclk_khz, clk_mgr->base.clks.dppclk_khz)) { if (clk_mgr->base.clks.dppclk_khz > new_clocks->dppclk_khz) dpp_clock_lowered = true; @@ -412,19 +418,19 @@ void build_watermark_ranges(struct clk_bw_params *bw_params, struct pp_smu_wm_ra ranges->reader_wm_sets[num_valid_sets].wm_inst = bw_params->wm_table.entries[i].wm_inst; ranges->reader_wm_sets[num_valid_sets].wm_type = bw_params->wm_table.entries[i].wm_type; - /* We will not select WM based on dcfclk, so leave it as unconstrained */ - ranges->reader_wm_sets[num_valid_sets].min_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN; - ranges->reader_wm_sets[num_valid_sets].max_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX; - /* fclk wil be used to select WM*/ + /* We will not select WM based on fclk, so leave it as unconstrained */ + ranges->reader_wm_sets[num_valid_sets].min_fill_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN; + ranges->reader_wm_sets[num_valid_sets].max_fill_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX; + /* dcfclk wil be used to select WM*/ if (ranges->reader_wm_sets[num_valid_sets].wm_type == WM_TYPE_PSTATE_CHG) { if (i == 0) - ranges->reader_wm_sets[num_valid_sets].min_fill_clk_mhz = 0; + ranges->reader_wm_sets[num_valid_sets].min_drain_clk_mhz = 0; else { /* add 1 to make it non-overlapping with next lvl */ - ranges->reader_wm_sets[num_valid_sets].min_fill_clk_mhz = bw_params->clk_table.entries[i - 1].fclk_mhz + 1; + ranges->reader_wm_sets[num_valid_sets].min_drain_clk_mhz = bw_params->clk_table.entries[i - 1].dcfclk_mhz + 1; } - ranges->reader_wm_sets[num_valid_sets].max_fill_clk_mhz = bw_params->clk_table.entries[i].fclk_mhz; + ranges->reader_wm_sets[num_valid_sets].max_drain_clk_mhz = bw_params->clk_table.entries[i].dcfclk_mhz; } else { /* unconstrained for memory retraining */ diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index cb731c1d30b1000b4624f12a7e495e2946aded47..fd9e69634c50abd555a59784754fe6e7fb53074c 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -3401,6 +3401,17 @@ static bool retrieve_link_cap(struct dc_link *link) sink_id.ieee_device_id, sizeof(sink_id.ieee_device_id)); + /* Quirk Apple MBP 2017 15" Retina panel: Wrong DP_MAX_LINK_RATE */ + { + uint8_t str_mbp_2017[] = { 101, 68, 21, 101, 98, 97 }; + + if ((link->dpcd_caps.sink_dev_id == 0x0010fa) && + !memcmp(link->dpcd_caps.sink_dev_id_str, str_mbp_2017, + sizeof(str_mbp_2017))) { + link->reported_link_cap.link_rate = 0x0c; + } + } + core_link_read_dpcd( link, DP_SINK_HW_REVISION_START, diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c index f1a5d2c6aa37874577fa6e804cad2c5a43b8c6b8..68c4049cbc2adaedd986f91e8951b8ad491208f3 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c @@ -400,7 +400,7 @@ static bool acquire( { enum gpio_result result; - if (!is_engine_available(engine)) + if ((engine == NULL) || !is_engine_available(engine)) return false; result = dal_ddc_open(ddc, GPIO_MODE_HARDWARE, diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c index f36a0d8cedfe1eec4b8db2766ca401991200ad41..446ba0a7a4b3d641474733fe2989b4d4c1a26226 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c @@ -840,8 +840,8 @@ static void hubbub1_det_request_size( hubbub1_get_blk256_size(&blk256_width, &blk256_height, bpe); - swath_bytes_horz_wc = height * blk256_height * bpe; - swath_bytes_vert_wc = width * blk256_width * bpe; + swath_bytes_horz_wc = width * blk256_height * bpe; + swath_bytes_vert_wc = height * blk256_width * bpe; *req128_horz_wc = (2 * swath_bytes_horz_wc <= detile_buf_size) ? false : /* full 256B request */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index cfbbaffa865475933d069f647be2df3bb02b322a..a444fed94184919c51bded44ebb4eaafd3db117b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -572,7 +572,6 @@ void dcn20_plane_atomic_disable(struct dc *dc, struct pipe_ctx *pipe_ctx) dpp->funcs->dpp_dppclk_control(dpp, false, false); hubp->power_gated = true; - dc->optimized_required = false; /* We're powering off, no need to optimize */ hws->funcs.plane_atomic_power_down(dc, pipe_ctx->plane_res.dpp, diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c index d51e02fdab4d3eb427e310dbde23122b5b162d86..5e640f17d3d482de8073efb5aa52e90c659ccf55 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c @@ -108,7 +108,6 @@ static const struct hwseq_private_funcs dcn20_private_funcs = { .enable_power_gating_plane = dcn20_enable_power_gating_plane, .dpp_pg_control = dcn20_dpp_pg_control, .hubp_pg_control = dcn20_hubp_pg_control, - .dsc_pg_control = NULL, .update_odm = dcn20_update_odm, .dsc_pg_control = dcn20_dsc_pg_control, .get_surface_visual_confirm_color = dcn10_get_surface_visual_confirm_color, diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index 85f90f3e24cb50a600a447db86dcfbc061397c52..e310d67c399a812b77c5d981858acdfc65678e78 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -335,6 +335,117 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_0_soc = { .use_urgent_burst_bw = 0 }; +struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv14_soc = { + .clock_limits = { + { + .state = 0, + .dcfclk_mhz = 560.0, + .fabricclk_mhz = 560.0, + .dispclk_mhz = 513.0, + .dppclk_mhz = 513.0, + .phyclk_mhz = 540.0, + .socclk_mhz = 560.0, + .dscclk_mhz = 171.0, + .dram_speed_mts = 8960.0, + }, + { + .state = 1, + .dcfclk_mhz = 694.0, + .fabricclk_mhz = 694.0, + .dispclk_mhz = 642.0, + .dppclk_mhz = 642.0, + .phyclk_mhz = 600.0, + .socclk_mhz = 694.0, + .dscclk_mhz = 214.0, + .dram_speed_mts = 11104.0, + }, + { + .state = 2, + .dcfclk_mhz = 875.0, + .fabricclk_mhz = 875.0, + .dispclk_mhz = 734.0, + .dppclk_mhz = 734.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 875.0, + .dscclk_mhz = 245.0, + .dram_speed_mts = 14000.0, + }, + { + .state = 3, + .dcfclk_mhz = 1000.0, + .fabricclk_mhz = 1000.0, + .dispclk_mhz = 1100.0, + .dppclk_mhz = 1100.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 1000.0, + .dscclk_mhz = 367.0, + .dram_speed_mts = 16000.0, + }, + { + .state = 4, + .dcfclk_mhz = 1200.0, + .fabricclk_mhz = 1200.0, + .dispclk_mhz = 1284.0, + .dppclk_mhz = 1284.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 1200.0, + .dscclk_mhz = 428.0, + .dram_speed_mts = 16000.0, + }, + /*Extra state, no dispclk ramping*/ + { + .state = 5, + .dcfclk_mhz = 1200.0, + .fabricclk_mhz = 1200.0, + .dispclk_mhz = 1284.0, + .dppclk_mhz = 1284.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 1200.0, + .dscclk_mhz = 428.0, + .dram_speed_mts = 16000.0, + }, + }, + .num_states = 5, + .sr_exit_time_us = 8.6, + .sr_enter_plus_exit_time_us = 10.9, + .urgent_latency_us = 4.0, + .urgent_latency_pixel_data_only_us = 4.0, + .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, + .urgent_latency_vm_data_only_us = 4.0, + .urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096, + .urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096, + .urgent_out_of_order_return_per_channel_vm_only_bytes = 4096, + .pct_ideal_dram_sdp_bw_after_urgent_pixel_only = 40.0, + .pct_ideal_dram_sdp_bw_after_urgent_pixel_and_vm = 40.0, + .pct_ideal_dram_sdp_bw_after_urgent_vm_only = 40.0, + .max_avg_sdp_bw_use_normal_percent = 40.0, + .max_avg_dram_bw_use_normal_percent = 40.0, + .writeback_latency_us = 12.0, + .ideal_dram_bw_after_urgent_percent = 40.0, + .max_request_size_bytes = 256, + .dram_channel_width_bytes = 2, + .fabric_datapath_to_dcn_data_return_bytes = 64, + .dcn_downspread_percent = 0.5, + .downspread_percent = 0.38, + .dram_page_open_time_ns = 50.0, + .dram_rw_turnaround_time_ns = 17.5, + .dram_return_buffer_per_channel_bytes = 8192, + .round_trip_ping_latency_dcfclk_cycles = 131, + .urgent_out_of_order_return_per_channel_bytes = 256, + .channel_interleave_bytes = 256, + .num_banks = 8, + .num_chans = 8, + .vmm_page_size_bytes = 4096, + .dram_clock_change_latency_us = 404.0, + .dummy_pstate_latency_us = 5.0, + .writeback_dram_clock_change_latency_us = 23.0, + .return_bus_width_bytes = 64, + .dispclk_dppclk_vco_speed_mhz = 3850, + .xfc_bus_transport_time_us = 20, + .xfc_xbuf_latency_tolerance_us = 4, + .use_urgent_burst_bw = 0 +}; + struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv12_soc = { 0 }; #ifndef mmDP0_DP_DPHY_INTERNAL_CTRL @@ -3291,6 +3402,9 @@ void dcn20_patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_st static struct _vcs_dpi_soc_bounding_box_st *get_asic_rev_soc_bb( uint32_t hw_internal_rev) { + if (ASICREV_IS_NAVI14_M(hw_internal_rev)) + return &dcn2_0_nv14_soc; + if (ASICREV_IS_NAVI12_P(hw_internal_rev)) return &dcn2_0_nv12_soc; diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c index 4861aa5c59aefd4ba3962d14b68d0bd0ff5c88b5..fddbd59bf4f980af5615642397e01620dff719ce 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c @@ -116,7 +116,6 @@ static const struct hwseq_private_funcs dcn21_private_funcs = { .enable_power_gating_plane = dcn20_enable_power_gating_plane, .dpp_pg_control = dcn20_dpp_pg_control, .hubp_pg_control = dcn20_hubp_pg_control, - .dsc_pg_control = NULL, .update_odm = dcn20_update_odm, .dsc_pg_control = dcn20_dsc_pg_control, .get_surface_visual_confirm_color = dcn10_get_surface_visual_confirm_color, diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index 0d506d30d6b6f455a197a053d693f38c060ec782..33d0a176841a57479db14b17c61d583c6e1161e5 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -60,6 +60,7 @@ #include "dcn20/dcn20_dccg.h" #include "dcn21_hubbub.h" #include "dcn10/dcn10_resource.h" +#include "dce110/dce110_resource.h" #include "dcn20/dcn20_dwb.h" #include "dcn20/dcn20_mmhubbub.h" @@ -856,6 +857,7 @@ static const struct dc_debug_options debug_defaults_diags = { enum dcn20_clk_src_array_id { DCN20_CLK_SRC_PLL0, DCN20_CLK_SRC_PLL1, + DCN20_CLK_SRC_PLL2, DCN20_CLK_SRC_TOTAL_DCN21 }; @@ -1718,6 +1720,10 @@ static bool dcn21_resource_construct( dcn21_clock_source_create(ctx, ctx->dc_bios, CLOCK_SOURCE_COMBO_PHY_PLL1, &clk_src_regs[1], false); + pool->base.clock_sources[DCN20_CLK_SRC_PLL2] = + dcn21_clock_source_create(ctx, ctx->dc_bios, + CLOCK_SOURCE_COMBO_PHY_PLL2, + &clk_src_regs[2], false); pool->base.clk_src_count = DCN20_CLK_SRC_TOTAL_DCN21; diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c index f730b94ac3c0633d584524296a1ca403028990b8..55246711700ba721f4ce02141fde6c1dae6cdefd 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c @@ -46,8 +46,8 @@ static inline enum mod_hdcp_status check_hdcp2_capable(struct mod_hdcp *hdcp) enum mod_hdcp_status status; if (is_dp_hdcp(hdcp)) - status = (hdcp->auth.msg.hdcp2.rxcaps_dp[2] & HDCP_2_2_RX_CAPS_VERSION_VAL) && - HDCP_2_2_DP_HDCP_CAPABLE(hdcp->auth.msg.hdcp2.rxcaps_dp[0]) ? + status = (hdcp->auth.msg.hdcp2.rxcaps_dp[0] == HDCP_2_2_RX_CAPS_VERSION_VAL) && + HDCP_2_2_DP_HDCP_CAPABLE(hdcp->auth.msg.hdcp2.rxcaps_dp[2]) ? MOD_HDCP_STATUS_SUCCESS : MOD_HDCP_STATUS_HDCP2_NOT_CAPABLE; else diff --git a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_offset.h index b6f74bf4af023fd53ee79ce44ecb29cf9f8cb43b..27bb8c1ab85876bed4ad23bfc6df7648eaa8a851 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_offset.h +++ b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_offset.h @@ -7376,6 +7376,8 @@ #define mmCRTC4_CRTC_DRR_CONTROL 0x0f3e #define mmCRTC4_CRTC_DRR_CONTROL_BASE_IDX 2 +#define mmDCHUBBUB_SDPIF_MMIO_CNTRL_0 0x395d +#define mmDCHUBBUB_SDPIF_MMIO_CNTRL_0_BASE_IDX 2 // addressBlock: dce_dc_fmt4_dispdec // base address: 0x2000 diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c index 99ad4ddbe12f01c89e36460eac27cc194f66bd72..96e81c7bc2669919917765f860ff54634da31b70 100644 --- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c @@ -222,7 +222,7 @@ int smu_set_soft_freq_range(struct smu_context *smu, enum smu_clk_type clk_type, { int ret = 0; - if (min <= 0 && max <= 0) + if (min < 0 && max < 0) return -EINVAL; if (!smu_clk_dpm_is_enabled(smu, clk_type)) @@ -2006,8 +2006,11 @@ int smu_set_watermarks_for_clock_ranges(struct smu_context *smu, smu_feature_is_enabled(smu, SMU_FEATURE_DPM_DCEFCLK_BIT) && smu_feature_is_enabled(smu, SMU_FEATURE_DPM_SOCCLK_BIT)) { smu_set_watermarks_table(smu, table, clock_ranges); - smu->watermarks_bitmap |= WATERMARKS_EXIST; - smu->watermarks_bitmap &= ~WATERMARKS_LOADED; + + if (!(smu->watermarks_bitmap & WATERMARKS_EXIST)) { + smu->watermarks_bitmap |= WATERMARKS_EXIST; + smu->watermarks_bitmap &= ~WATERMARKS_LOADED; + } } mutex_unlock(&smu->mutex); diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0_pptable.h b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0_pptable.h index b2f96a10112465f283add4d068ccab8fa630548a..7a63cf8e85ed9419fb96d10452a8280b164044d1 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0_pptable.h +++ b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0_pptable.h @@ -39,21 +39,39 @@ #define SMU_11_0_PP_OVERDRIVE_VERSION 0x0800 #define SMU_11_0_PP_POWERSAVINGCLOCK_VERSION 0x0100 +enum SMU_11_0_ODFEATURE_CAP { + SMU_11_0_ODCAP_GFXCLK_LIMITS = 0, + SMU_11_0_ODCAP_GFXCLK_CURVE, + SMU_11_0_ODCAP_UCLK_MAX, + SMU_11_0_ODCAP_POWER_LIMIT, + SMU_11_0_ODCAP_FAN_ACOUSTIC_LIMIT, + SMU_11_0_ODCAP_FAN_SPEED_MIN, + SMU_11_0_ODCAP_TEMPERATURE_FAN, + SMU_11_0_ODCAP_TEMPERATURE_SYSTEM, + SMU_11_0_ODCAP_MEMORY_TIMING_TUNE, + SMU_11_0_ODCAP_FAN_ZERO_RPM_CONTROL, + SMU_11_0_ODCAP_AUTO_UV_ENGINE, + SMU_11_0_ODCAP_AUTO_OC_ENGINE, + SMU_11_0_ODCAP_AUTO_OC_MEMORY, + SMU_11_0_ODCAP_FAN_CURVE, + SMU_11_0_ODCAP_COUNT, +}; + enum SMU_11_0_ODFEATURE_ID { - SMU_11_0_ODFEATURE_GFXCLK_LIMITS = 1 << 0, //GFXCLK Limit feature - SMU_11_0_ODFEATURE_GFXCLK_CURVE = 1 << 1, //GFXCLK Curve feature - SMU_11_0_ODFEATURE_UCLK_MAX = 1 << 2, //UCLK Limit feature - SMU_11_0_ODFEATURE_POWER_LIMIT = 1 << 3, //Power Limit feature - SMU_11_0_ODFEATURE_FAN_ACOUSTIC_LIMIT = 1 << 4, //Fan Acoustic RPM feature - SMU_11_0_ODFEATURE_FAN_SPEED_MIN = 1 << 5, //Minimum Fan Speed feature - SMU_11_0_ODFEATURE_TEMPERATURE_FAN = 1 << 6, //Fan Target Temperature Limit feature - SMU_11_0_ODFEATURE_TEMPERATURE_SYSTEM = 1 << 7, //Operating Temperature Limit feature - SMU_11_0_ODFEATURE_MEMORY_TIMING_TUNE = 1 << 8, //AC Timing Tuning feature - SMU_11_0_ODFEATURE_FAN_ZERO_RPM_CONTROL = 1 << 9, //Zero RPM feature - SMU_11_0_ODFEATURE_AUTO_UV_ENGINE = 1 << 10, //Auto Under Volt GFXCLK feature - SMU_11_0_ODFEATURE_AUTO_OC_ENGINE = 1 << 11, //Auto Over Clock GFXCLK feature - SMU_11_0_ODFEATURE_AUTO_OC_MEMORY = 1 << 12, //Auto Over Clock MCLK feature - SMU_11_0_ODFEATURE_FAN_CURVE = 1 << 13, //VICTOR TODO + SMU_11_0_ODFEATURE_GFXCLK_LIMITS = 1 << SMU_11_0_ODCAP_GFXCLK_LIMITS, //GFXCLK Limit feature + SMU_11_0_ODFEATURE_GFXCLK_CURVE = 1 << SMU_11_0_ODCAP_GFXCLK_CURVE, //GFXCLK Curve feature + SMU_11_0_ODFEATURE_UCLK_MAX = 1 << SMU_11_0_ODCAP_UCLK_MAX, //UCLK Limit feature + SMU_11_0_ODFEATURE_POWER_LIMIT = 1 << SMU_11_0_ODCAP_POWER_LIMIT, //Power Limit feature + SMU_11_0_ODFEATURE_FAN_ACOUSTIC_LIMIT = 1 << SMU_11_0_ODCAP_FAN_ACOUSTIC_LIMIT, //Fan Acoustic RPM feature + SMU_11_0_ODFEATURE_FAN_SPEED_MIN = 1 << SMU_11_0_ODCAP_FAN_SPEED_MIN, //Minimum Fan Speed feature + SMU_11_0_ODFEATURE_TEMPERATURE_FAN = 1 << SMU_11_0_ODCAP_TEMPERATURE_FAN, //Fan Target Temperature Limit feature + SMU_11_0_ODFEATURE_TEMPERATURE_SYSTEM = 1 << SMU_11_0_ODCAP_TEMPERATURE_SYSTEM, //Operating Temperature Limit feature + SMU_11_0_ODFEATURE_MEMORY_TIMING_TUNE = 1 << SMU_11_0_ODCAP_MEMORY_TIMING_TUNE, //AC Timing Tuning feature + SMU_11_0_ODFEATURE_FAN_ZERO_RPM_CONTROL = 1 << SMU_11_0_ODCAP_FAN_ZERO_RPM_CONTROL, //Zero RPM feature + SMU_11_0_ODFEATURE_AUTO_UV_ENGINE = 1 << SMU_11_0_ODCAP_AUTO_UV_ENGINE, //Auto Under Volt GFXCLK feature + SMU_11_0_ODFEATURE_AUTO_OC_ENGINE = 1 << SMU_11_0_ODCAP_AUTO_OC_ENGINE, //Auto Over Clock GFXCLK feature + SMU_11_0_ODFEATURE_AUTO_OC_MEMORY = 1 << SMU_11_0_ODCAP_AUTO_OC_MEMORY, //Auto Over Clock MCLK feature + SMU_11_0_ODFEATURE_FAN_CURVE = 1 << SMU_11_0_ODCAP_FAN_CURVE, //Fan Curve feature SMU_11_0_ODFEATURE_COUNT = 14, }; #define SMU_11_0_MAX_ODFEATURE 32 //Maximum Number of OD Features diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c index 19a9846b730e1b5e05769b2d4b3a3283620c0189..aed4d6e6090752d3aed67811147f9a16acf0ca4c 100644 --- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c @@ -736,9 +736,9 @@ static bool navi10_is_support_fine_grained_dpm(struct smu_context *smu, enum smu return dpm_desc->SnapToDiscrete == 0 ? true : false; } -static inline bool navi10_od_feature_is_supported(struct smu_11_0_overdrive_table *od_table, enum SMU_11_0_ODFEATURE_ID feature) +static inline bool navi10_od_feature_is_supported(struct smu_11_0_overdrive_table *od_table, enum SMU_11_0_ODFEATURE_CAP cap) { - return od_table->cap[feature]; + return od_table->cap[cap]; } static void navi10_od_setting_get_range(struct smu_11_0_overdrive_table *od_table, @@ -846,7 +846,7 @@ static int navi10_print_clk_levels(struct smu_context *smu, case SMU_OD_SCLK: if (!smu->od_enabled || !od_table || !od_settings) break; - if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODFEATURE_GFXCLK_LIMITS)) + if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_GFXCLK_LIMITS)) break; size += sprintf(buf + size, "OD_SCLK:\n"); size += sprintf(buf + size, "0: %uMhz\n1: %uMhz\n", od_table->GfxclkFmin, od_table->GfxclkFmax); @@ -854,7 +854,7 @@ static int navi10_print_clk_levels(struct smu_context *smu, case SMU_OD_MCLK: if (!smu->od_enabled || !od_table || !od_settings) break; - if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODFEATURE_UCLK_MAX)) + if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_UCLK_MAX)) break; size += sprintf(buf + size, "OD_MCLK:\n"); size += sprintf(buf + size, "1: %uMHz\n", od_table->UclkFmax); @@ -862,7 +862,7 @@ static int navi10_print_clk_levels(struct smu_context *smu, case SMU_OD_VDDC_CURVE: if (!smu->od_enabled || !od_table || !od_settings) break; - if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODFEATURE_GFXCLK_CURVE)) + if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_GFXCLK_CURVE)) break; size += sprintf(buf + size, "OD_VDDC_CURVE:\n"); for (i = 0; i < 3; i++) { @@ -887,7 +887,7 @@ static int navi10_print_clk_levels(struct smu_context *smu, break; size = sprintf(buf, "%s:\n", "OD_RANGE"); - if (navi10_od_feature_is_supported(od_settings, SMU_11_0_ODFEATURE_GFXCLK_LIMITS)) { + if (navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_GFXCLK_LIMITS)) { navi10_od_setting_get_range(od_settings, SMU_11_0_ODSETTING_GFXCLKFMIN, &min_value, NULL); navi10_od_setting_get_range(od_settings, SMU_11_0_ODSETTING_GFXCLKFMAX, @@ -896,14 +896,14 @@ static int navi10_print_clk_levels(struct smu_context *smu, min_value, max_value); } - if (navi10_od_feature_is_supported(od_settings, SMU_11_0_ODFEATURE_UCLK_MAX)) { + if (navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_UCLK_MAX)) { navi10_od_setting_get_range(od_settings, SMU_11_0_ODSETTING_UCLKFMAX, &min_value, &max_value); size += sprintf(buf + size, "MCLK: %7uMhz %10uMhz\n", min_value, max_value); } - if (navi10_od_feature_is_supported(od_settings, SMU_11_0_ODFEATURE_GFXCLK_CURVE)) { + if (navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_GFXCLK_CURVE)) { navi10_od_setting_get_range(od_settings, SMU_11_0_ODSETTING_VDDGFXCURVEFREQ_P1, &min_value, &max_value); size += sprintf(buf + size, "VDDC_CURVE_SCLK[0]: %7uMhz %10uMhz\n", @@ -1062,15 +1062,6 @@ static int navi10_display_config_changed(struct smu_context *smu) { int ret = 0; - if ((smu->watermarks_bitmap & WATERMARKS_EXIST) && - !(smu->watermarks_bitmap & WATERMARKS_LOADED)) { - ret = smu_write_watermarks_table(smu); - if (ret) - return ret; - - smu->watermarks_bitmap |= WATERMARKS_LOADED; - } - if ((smu->watermarks_bitmap & WATERMARKS_EXIST) && smu_feature_is_supported(smu, SMU_FEATURE_DPM_DCEFCLK_BIT) && smu_feature_is_supported(smu, SMU_FEATURE_DPM_SOCCLK_BIT)) { @@ -1493,6 +1484,7 @@ static int navi10_set_watermarks_table(struct smu_context *smu, *clock_ranges) { int i; + int ret = 0; Watermarks_t *table = watermarks; if (!table || !clock_ranges) @@ -1544,6 +1536,18 @@ static int navi10_set_watermarks_table(struct smu_context *smu, clock_ranges->wm_mcif_clocks_ranges[i].wm_set_id; } + smu->watermarks_bitmap |= WATERMARKS_EXIST; + + /* pass data to smu controller */ + if (!(smu->watermarks_bitmap & WATERMARKS_LOADED)) { + ret = smu_write_watermarks_table(smu); + if (ret) { + pr_err("Failed to update WMTABLE!"); + return ret; + } + smu->watermarks_bitmap |= WATERMARKS_LOADED; + } + return 0; } @@ -2056,7 +2060,7 @@ static int navi10_od_edit_dpm_table(struct smu_context *smu, enum PP_OD_DPM_TABL switch (type) { case PP_OD_EDIT_SCLK_VDDC_TABLE: - if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODFEATURE_GFXCLK_LIMITS)) { + if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_GFXCLK_LIMITS)) { pr_warn("GFXCLK_LIMITS not supported!\n"); return -ENOTSUPP; } @@ -2102,7 +2106,7 @@ static int navi10_od_edit_dpm_table(struct smu_context *smu, enum PP_OD_DPM_TABL } break; case PP_OD_EDIT_MCLK_VDDC_TABLE: - if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODFEATURE_UCLK_MAX)) { + if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_UCLK_MAX)) { pr_warn("UCLK_MAX not supported!\n"); return -ENOTSUPP; } @@ -2143,7 +2147,7 @@ static int navi10_od_edit_dpm_table(struct smu_context *smu, enum PP_OD_DPM_TABL } break; case PP_OD_EDIT_VDDC_CURVE: - if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODFEATURE_GFXCLK_CURVE)) { + if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_GFXCLK_CURVE)) { pr_warn("GFXCLK_CURVE not supported!\n"); return -ENOTSUPP; } diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c index 861e6410363bc764b68d6f62721854b78436f25f..3ad0f4aa3aa3f729e6aa06a4f4e2f87cebc4b63a 100644 --- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c @@ -111,8 +111,8 @@ static struct smu_12_0_cmn2aisc_mapping renoir_clk_map[SMU_CLK_COUNT] = { CLK_MAP(GFXCLK, CLOCK_GFXCLK), CLK_MAP(SCLK, CLOCK_GFXCLK), CLK_MAP(SOCCLK, CLOCK_SOCCLK), - CLK_MAP(UCLK, CLOCK_UMCCLK), - CLK_MAP(MCLK, CLOCK_UMCCLK), + CLK_MAP(UCLK, CLOCK_FCLK), + CLK_MAP(MCLK, CLOCK_FCLK), }; static struct smu_12_0_cmn2aisc_mapping renoir_table_map[SMU_TABLE_COUNT] = { @@ -280,7 +280,7 @@ static int renoir_print_clk_levels(struct smu_context *smu, break; case SMU_MCLK: count = NUM_MEMCLK_DPM_LEVELS; - cur_value = metrics.ClockFrequency[CLOCK_UMCCLK]; + cur_value = metrics.ClockFrequency[CLOCK_FCLK]; break; case SMU_DCEFCLK: count = NUM_DCFCLK_DPM_LEVELS; @@ -806,9 +806,10 @@ static int renoir_set_watermarks_table( clock_ranges->wm_mcif_clocks_ranges[i].wm_set_id; } + smu->watermarks_bitmap |= WATERMARKS_EXIST; + /* pass data to smu controller */ - if ((smu->watermarks_bitmap & WATERMARKS_EXIST) && - !(smu->watermarks_bitmap & WATERMARKS_LOADED)) { + if (!(smu->watermarks_bitmap & WATERMARKS_LOADED)) { ret = smu_write_watermarks_table(smu); if (ret) { pr_err("Failed to update WMTABLE!"); diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c index 0dc49479a7ebdabe0650d06b29db032c91843845..c9e5ce135fd42bd417fa64b1fe43bed8fee6cf45 100644 --- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c +++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c @@ -898,6 +898,9 @@ int smu_v11_0_system_features_control(struct smu_context *smu, if (ret) return ret; + bitmap_zero(feature->enabled, feature->feature_num); + bitmap_zero(feature->supported, feature->feature_num); + if (en) { ret = smu_feature_get_enabled_mask(smu, feature_mask, 2); if (ret) @@ -907,9 +910,6 @@ int smu_v11_0_system_features_control(struct smu_context *smu, feature->feature_num); bitmap_copy(feature->supported, (unsigned long *)&feature_mask, feature->feature_num); - } else { - bitmap_zero(feature->enabled, feature->feature_num); - bitmap_zero(feature->supported, feature->feature_num); } return ret; @@ -978,8 +978,12 @@ int smu_v11_0_init_max_sustainable_clocks(struct smu_context *smu) struct smu_11_0_max_sustainable_clocks *max_sustainable_clocks; int ret = 0; - max_sustainable_clocks = kzalloc(sizeof(struct smu_11_0_max_sustainable_clocks), + if (!smu->smu_table.max_sustainable_clocks) + max_sustainable_clocks = kzalloc(sizeof(struct smu_11_0_max_sustainable_clocks), GFP_KERNEL); + else + max_sustainable_clocks = smu->smu_table.max_sustainable_clocks; + smu->smu_table.max_sustainable_clocks = (void *)max_sustainable_clocks; max_sustainable_clocks->uclock = smu->smu_table.boot_values.uclk / 100; diff --git a/drivers/gpu/drm/amd/powerplay/smu_v12_0.c b/drivers/gpu/drm/amd/powerplay/smu_v12_0.c index 870e6db2907eb67e43d75ee26850c173d2985960..518e6597bf2d46153706958792d191cc23dc37c0 100644 --- a/drivers/gpu/drm/amd/powerplay/smu_v12_0.c +++ b/drivers/gpu/drm/amd/powerplay/smu_v12_0.c @@ -458,9 +458,6 @@ int smu_v12_0_set_soft_freq_limited_range(struct smu_context *smu, enum smu_clk_ { int ret = 0; - if (max < min) - return -EINVAL; - switch (clk_type) { case SMU_GFXCLK: case SMU_SCLK: diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_drv.c b/drivers/gpu/drm/arm/display/komeda/komeda_drv.c index ea5cd1e1730494e60bca57643f65dc23bcfb7f00..e7933930a65770c3d63d9d72e90b86798f25a8b0 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_drv.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_drv.c @@ -146,14 +146,14 @@ static const struct of_device_id komeda_of_match[] = { MODULE_DEVICE_TABLE(of, komeda_of_match); -static int komeda_rt_pm_suspend(struct device *dev) +static int __maybe_unused komeda_rt_pm_suspend(struct device *dev) { struct komeda_drv *mdrv = dev_get_drvdata(dev); return komeda_dev_suspend(mdrv->mdev); } -static int komeda_rt_pm_resume(struct device *dev) +static int __maybe_unused komeda_rt_pm_resume(struct device *dev) { struct komeda_drv *mdrv = dev_get_drvdata(dev); diff --git a/drivers/gpu/drm/bochs/bochs_hw.c b/drivers/gpu/drm/bochs/bochs_hw.c index b615b7dfdd9dab92d7149f5af7b671f774d9277e..a4fc4e6aee3927ce642b821b0dc3cf2e2c69eb92 100644 --- a/drivers/gpu/drm/bochs/bochs_hw.c +++ b/drivers/gpu/drm/bochs/bochs_hw.c @@ -156,10 +156,8 @@ int bochs_hw_init(struct drm_device *dev) size = min(size, mem); } - if (pci_request_region(pdev, 0, "bochs-drm") != 0) { - DRM_ERROR("Cannot request framebuffer\n"); - return -EBUSY; - } + if (pci_request_region(pdev, 0, "bochs-drm") != 0) + DRM_WARN("Cannot request framebuffer, boot fb still active?\n"); bochs->fb_map = ioremap(addr, size); if (bochs->fb_map == NULL) { diff --git a/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c b/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c index 56f55c53abfd8bfccdc6cf88e94ea211cf001f1f..2dfa2fd2a23b188fb2d2397a3e4c698a940c250e 100644 --- a/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c +++ b/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c @@ -210,8 +210,7 @@ static int anx6345_dp_link_training(struct anx6345 *anx6345) if (err) return err; - dpcd[0] = drm_dp_max_link_rate(anx6345->dpcd); - dpcd[0] = drm_dp_link_rate_to_bw_code(dpcd[0]); + dpcd[0] = dp_bw; err = regmap_write(anx6345->map[I2C_IDX_DPTX], SP_DP_MAIN_LINK_BW_SET_REG, dpcd[0]); if (err) diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c index 67fca439bbfb476f442262bd1094e7f59a27aad2..24965e53d351bf711906c5aa2950e612883cd61e 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c @@ -1624,28 +1624,34 @@ static void hdmi_config_AVI(struct dw_hdmi *hdmi, struct drm_display_mode *mode) frame.colorspace = HDMI_COLORSPACE_RGB; /* Set up colorimetry */ - switch (hdmi->hdmi_data.enc_out_encoding) { - case V4L2_YCBCR_ENC_601: - if (hdmi->hdmi_data.enc_in_encoding == V4L2_YCBCR_ENC_XV601) - frame.colorimetry = HDMI_COLORIMETRY_EXTENDED; - else + if (!hdmi_bus_fmt_is_rgb(hdmi->hdmi_data.enc_out_bus_format)) { + switch (hdmi->hdmi_data.enc_out_encoding) { + case V4L2_YCBCR_ENC_601: + if (hdmi->hdmi_data.enc_in_encoding == V4L2_YCBCR_ENC_XV601) + frame.colorimetry = HDMI_COLORIMETRY_EXTENDED; + else + frame.colorimetry = HDMI_COLORIMETRY_ITU_601; + frame.extended_colorimetry = + HDMI_EXTENDED_COLORIMETRY_XV_YCC_601; + break; + case V4L2_YCBCR_ENC_709: + if (hdmi->hdmi_data.enc_in_encoding == V4L2_YCBCR_ENC_XV709) + frame.colorimetry = HDMI_COLORIMETRY_EXTENDED; + else + frame.colorimetry = HDMI_COLORIMETRY_ITU_709; + frame.extended_colorimetry = + HDMI_EXTENDED_COLORIMETRY_XV_YCC_709; + break; + default: /* Carries no data */ frame.colorimetry = HDMI_COLORIMETRY_ITU_601; + frame.extended_colorimetry = + HDMI_EXTENDED_COLORIMETRY_XV_YCC_601; + break; + } + } else { + frame.colorimetry = HDMI_COLORIMETRY_NONE; frame.extended_colorimetry = - HDMI_EXTENDED_COLORIMETRY_XV_YCC_601; - break; - case V4L2_YCBCR_ENC_709: - if (hdmi->hdmi_data.enc_in_encoding == V4L2_YCBCR_ENC_XV709) - frame.colorimetry = HDMI_COLORIMETRY_EXTENDED; - else - frame.colorimetry = HDMI_COLORIMETRY_ITU_709; - frame.extended_colorimetry = - HDMI_EXTENDED_COLORIMETRY_XV_YCC_709; - break; - default: /* Carries no data */ - frame.colorimetry = HDMI_COLORIMETRY_ITU_601; - frame.extended_colorimetry = - HDMI_EXTENDED_COLORIMETRY_XV_YCC_601; - break; + HDMI_EXTENDED_COLORIMETRY_XV_YCC_601; } frame.scan_mode = HDMI_SCAN_MODE_NONE; diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c index 3709e5ace7246086b3b4d172bdd5a7218cbf6306..fbdb42d4e772ecf87666fe28191559f06afd8cf1 100644 --- a/drivers/gpu/drm/bridge/tc358767.c +++ b/drivers/gpu/drm/bridge/tc358767.c @@ -297,7 +297,7 @@ static inline int tc_poll_timeout(struct tc_data *tc, unsigned int addr, static int tc_aux_wait_busy(struct tc_data *tc) { - return tc_poll_timeout(tc, DP0_AUXSTATUS, AUX_BUSY, 0, 1000, 100000); + return tc_poll_timeout(tc, DP0_AUXSTATUS, AUX_BUSY, 0, 100, 100000); } static int tc_aux_write_data(struct tc_data *tc, const void *data, @@ -640,7 +640,7 @@ static int tc_aux_link_setup(struct tc_data *tc) if (ret) goto err; - ret = tc_poll_timeout(tc, DP_PHY_CTRL, PHY_RDY, PHY_RDY, 1, 1000); + ret = tc_poll_timeout(tc, DP_PHY_CTRL, PHY_RDY, PHY_RDY, 100, 100000); if (ret == -ETIMEDOUT) { dev_err(tc->dev, "Timeout waiting for PHY to become ready"); return ret; @@ -876,7 +876,7 @@ static int tc_wait_link_training(struct tc_data *tc) int ret; ret = tc_poll_timeout(tc, DP0_LTSTAT, LT_LOOPDONE, - LT_LOOPDONE, 1, 1000); + LT_LOOPDONE, 500, 100000); if (ret) { dev_err(tc->dev, "Link training timeout waiting for LT_LOOPDONE!\n"); return ret; @@ -949,7 +949,7 @@ static int tc_main_link_enable(struct tc_data *tc) dp_phy_ctrl &= ~(DP_PHY_RST | PHY_M1_RST | PHY_M0_RST); ret = regmap_write(tc->regmap, DP_PHY_CTRL, dp_phy_ctrl); - ret = tc_poll_timeout(tc, DP_PHY_CTRL, PHY_RDY, PHY_RDY, 1, 1000); + ret = tc_poll_timeout(tc, DP_PHY_CTRL, PHY_RDY, PHY_RDY, 500, 100000); if (ret) { dev_err(dev, "timeout waiting for phy become ready"); return ret; diff --git a/drivers/gpu/drm/bridge/ti-tfp410.c b/drivers/gpu/drm/bridge/ti-tfp410.c index 6f6d6d1e60ae9162d94c45e8e4e58cc6d389448b..f195a4732e0badac04f0864def9999bd1620b575 100644 --- a/drivers/gpu/drm/bridge/ti-tfp410.c +++ b/drivers/gpu/drm/bridge/ti-tfp410.c @@ -140,7 +140,8 @@ static int tfp410_attach(struct drm_bridge *bridge) dvi->connector_type, dvi->ddc); if (ret) { - dev_err(dvi->dev, "drm_connector_init() failed: %d\n", ret); + dev_err(dvi->dev, "drm_connector_init_with_ddc() failed: %d\n", + ret); return ret; } diff --git a/drivers/gpu/drm/drm_client_modeset.c b/drivers/gpu/drm/drm_client_modeset.c index 6d4a29e99ae264ea55985be4594a08319a53d6f1..3035584f6dc724ec81a5f7a7ffafc82745b043c6 100644 --- a/drivers/gpu/drm/drm_client_modeset.c +++ b/drivers/gpu/drm/drm_client_modeset.c @@ -951,7 +951,8 @@ bool drm_client_rotation(struct drm_mode_set *modeset, unsigned int *rotation) * depending on the hardware this may require the framebuffer * to be in a specific tiling format. */ - if ((*rotation & DRM_MODE_ROTATE_MASK) != DRM_MODE_ROTATE_180 || + if (((*rotation & DRM_MODE_ROTATE_MASK) != DRM_MODE_ROTATE_0 && + (*rotation & DRM_MODE_ROTATE_MASK) != DRM_MODE_ROTATE_180) || !plane->rotation_property) return false; diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 20cdaf3146b844b7fc2cd7ad3f752fda681b831d..ed0fea2ac3223f3c5641841b708fe44f46305cb7 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -1935,7 +1935,7 @@ static u8 drm_dp_calculate_rad(struct drm_dp_mst_port *port, return parent_lct + 1; } -static bool drm_dp_mst_is_dp_mst_end_device(u8 pdt, bool mcs) +static bool drm_dp_mst_is_end_device(u8 pdt, bool mcs) { switch (pdt) { case DP_PEER_DEVICE_DP_LEGACY_CONV: @@ -1965,13 +1965,13 @@ drm_dp_port_set_pdt(struct drm_dp_mst_port *port, u8 new_pdt, /* Teardown the old pdt, if there is one */ if (port->pdt != DP_PEER_DEVICE_NONE) { - if (drm_dp_mst_is_dp_mst_end_device(port->pdt, port->mcs)) { + if (drm_dp_mst_is_end_device(port->pdt, port->mcs)) { /* * If the new PDT would also have an i2c bus, * don't bother with reregistering it */ if (new_pdt != DP_PEER_DEVICE_NONE && - drm_dp_mst_is_dp_mst_end_device(new_pdt, new_mcs)) { + drm_dp_mst_is_end_device(new_pdt, new_mcs)) { port->pdt = new_pdt; port->mcs = new_mcs; return 0; @@ -1991,7 +1991,7 @@ drm_dp_port_set_pdt(struct drm_dp_mst_port *port, u8 new_pdt, port->mcs = new_mcs; if (port->pdt != DP_PEER_DEVICE_NONE) { - if (drm_dp_mst_is_dp_mst_end_device(port->pdt, port->mcs)) { + if (drm_dp_mst_is_end_device(port->pdt, port->mcs)) { /* add i2c over sideband */ ret = drm_dp_mst_register_i2c_bus(&port->aux); } else { @@ -2172,7 +2172,7 @@ drm_dp_mst_port_add_connector(struct drm_dp_mst_branch *mstb, } if (port->pdt != DP_PEER_DEVICE_NONE && - drm_dp_mst_is_dp_mst_end_device(port->pdt, port->mcs)) { + drm_dp_mst_is_end_device(port->pdt, port->mcs)) { port->cached_edid = drm_get_edid(port->connector, &port->aux.ddc); drm_connector_set_tile_property(port->connector); @@ -2302,14 +2302,18 @@ drm_dp_mst_handle_link_address_port(struct drm_dp_mst_branch *mstb, mutex_unlock(&mgr->lock); } - if (old_ddps != port->ddps) { - if (port->ddps) { - if (!port->input) { - drm_dp_send_enum_path_resources(mgr, mstb, - port); - } + /* + * Reprobe PBN caps on both hotplug, and when re-probing the link + * for our parent mstb + */ + if (old_ddps != port->ddps || !created) { + if (port->ddps && !port->input) { + ret = drm_dp_send_enum_path_resources(mgr, mstb, + port); + if (ret == 1) + changed = true; } else { - port->available_pbn = 0; + port->full_pbn = 0; } } @@ -2401,11 +2405,10 @@ drm_dp_mst_handle_conn_stat(struct drm_dp_mst_branch *mstb, port->ddps = conn_stat->displayport_device_plug_status; if (old_ddps != port->ddps) { - if (port->ddps) { - dowork = true; - } else { - port->available_pbn = 0; - } + if (port->ddps && !port->input) + drm_dp_send_enum_path_resources(mgr, mstb, port); + else + port->full_pbn = 0; } new_pdt = port->input ? DP_PEER_DEVICE_NONE : conn_stat->peer_device_type; @@ -2556,13 +2559,6 @@ static int drm_dp_check_and_send_link_address(struct drm_dp_mst_topology_mgr *mg if (port->input || !port->ddps) continue; - if (!port->available_pbn) { - drm_modeset_lock(&mgr->base.lock, NULL); - drm_dp_send_enum_path_resources(mgr, mstb, port); - drm_modeset_unlock(&mgr->base.lock); - changed = true; - } - if (port->mstb) mstb_child = drm_dp_mst_topology_get_mstb_validated( mgr, port->mstb); @@ -2990,6 +2986,7 @@ drm_dp_send_enum_path_resources(struct drm_dp_mst_topology_mgr *mgr, ret = drm_dp_mst_wait_tx_reply(mstb, txmsg); if (ret > 0) { + ret = 0; path_res = &txmsg->reply.u.path_resources; if (txmsg->reply.reply_type == DP_SIDEBAND_REPLY_NAK) { @@ -3002,14 +2999,22 @@ drm_dp_send_enum_path_resources(struct drm_dp_mst_topology_mgr *mgr, path_res->port_number, path_res->full_payload_bw_number, path_res->avail_payload_bw_number); - port->available_pbn = - path_res->avail_payload_bw_number; + + /* + * If something changed, make sure we send a + * hotplug + */ + if (port->full_pbn != path_res->full_payload_bw_number || + port->fec_capable != path_res->fec_capable) + ret = 1; + + port->full_pbn = path_res->full_payload_bw_number; port->fec_capable = path_res->fec_capable; } } kfree(txmsg); - return 0; + return ret; } static struct drm_dp_mst_port *drm_dp_get_last_connected_port_to_mstb(struct drm_dp_mst_branch *mstb) @@ -3596,13 +3601,9 @@ drm_dp_mst_topology_mgr_invalidate_mstb(struct drm_dp_mst_branch *mstb) /* The link address will need to be re-sent on resume */ mstb->link_address_sent = false; - list_for_each_entry(port, &mstb->ports, next) { - /* The PBN for each port will also need to be re-probed */ - port->available_pbn = 0; - + list_for_each_entry(port, &mstb->ports, next) if (port->mstb) drm_dp_mst_topology_mgr_invalidate_mstb(port->mstb); - } } /** @@ -3838,7 +3839,8 @@ drm_dp_mst_process_up_req(struct drm_dp_mst_topology_mgr *mgr, else if (msg->req_type == DP_RESOURCE_STATUS_NOTIFY) guid = msg->u.resource_stat.guid; - mstb = drm_dp_get_mst_branch_device_by_guid(mgr, guid); + if (guid) + mstb = drm_dp_get_mst_branch_device_by_guid(mgr, guid); } else { mstb = drm_dp_get_mst_branch_device(mgr, hdr->lct, hdr->rad); } @@ -4828,41 +4830,102 @@ static bool drm_dp_mst_port_downstream_of_branch(struct drm_dp_mst_port *port, return false; } -static inline -int drm_dp_mst_atomic_check_bw_limit(struct drm_dp_mst_branch *branch, - struct drm_dp_mst_topology_state *mst_state) +static int +drm_dp_mst_atomic_check_port_bw_limit(struct drm_dp_mst_port *port, + struct drm_dp_mst_topology_state *state); + +static int +drm_dp_mst_atomic_check_mstb_bw_limit(struct drm_dp_mst_branch *mstb, + struct drm_dp_mst_topology_state *state) { - struct drm_dp_mst_port *port; struct drm_dp_vcpi_allocation *vcpi; - int pbn_limit = 0, pbn_used = 0; + struct drm_dp_mst_port *port; + int pbn_used = 0, ret; + bool found = false; - list_for_each_entry(port, &branch->ports, next) { - if (port->mstb) - if (drm_dp_mst_atomic_check_bw_limit(port->mstb, mst_state)) - return -ENOSPC; + /* Check that we have at least one port in our state that's downstream + * of this branch, otherwise we can skip this branch + */ + list_for_each_entry(vcpi, &state->vcpis, next) { + if (!vcpi->pbn || + !drm_dp_mst_port_downstream_of_branch(vcpi->port, mstb)) + continue; - if (port->available_pbn > 0) - pbn_limit = port->available_pbn; + found = true; + break; } - DRM_DEBUG_ATOMIC("[MST BRANCH:%p] branch has %d PBN available\n", - branch, pbn_limit); + if (!found) + return 0; - list_for_each_entry(vcpi, &mst_state->vcpis, next) { - if (!vcpi->pbn) - continue; + if (mstb->port_parent) + DRM_DEBUG_ATOMIC("[MSTB:%p] [MST PORT:%p] Checking bandwidth limits on [MSTB:%p]\n", + mstb->port_parent->parent, mstb->port_parent, + mstb); + else + DRM_DEBUG_ATOMIC("[MSTB:%p] Checking bandwidth limits\n", + mstb); + + list_for_each_entry(port, &mstb->ports, next) { + ret = drm_dp_mst_atomic_check_port_bw_limit(port, state); + if (ret < 0) + return ret; - if (drm_dp_mst_port_downstream_of_branch(vcpi->port, branch)) - pbn_used += vcpi->pbn; + pbn_used += ret; } - DRM_DEBUG_ATOMIC("[MST BRANCH:%p] branch used %d PBN\n", - branch, pbn_used); - if (pbn_used > pbn_limit) { - DRM_DEBUG_ATOMIC("[MST BRANCH:%p] No available bandwidth\n", - branch); + return pbn_used; +} + +static int +drm_dp_mst_atomic_check_port_bw_limit(struct drm_dp_mst_port *port, + struct drm_dp_mst_topology_state *state) +{ + struct drm_dp_vcpi_allocation *vcpi; + int pbn_used = 0; + + if (port->pdt == DP_PEER_DEVICE_NONE) + return 0; + + if (drm_dp_mst_is_end_device(port->pdt, port->mcs)) { + bool found = false; + + list_for_each_entry(vcpi, &state->vcpis, next) { + if (vcpi->port != port) + continue; + if (!vcpi->pbn) + return 0; + + found = true; + break; + } + if (!found) + return 0; + + /* This should never happen, as it means we tried to + * set a mode before querying the full_pbn + */ + if (WARN_ON(!port->full_pbn)) + return -EINVAL; + + pbn_used = vcpi->pbn; + } else { + pbn_used = drm_dp_mst_atomic_check_mstb_bw_limit(port->mstb, + state); + if (pbn_used <= 0) + return pbn_used; + } + + if (pbn_used > port->full_pbn) { + DRM_DEBUG_ATOMIC("[MSTB:%p] [MST PORT:%p] required PBN of %d exceeds port limit of %d\n", + port->parent, port, pbn_used, + port->full_pbn); return -ENOSPC; } - return 0; + + DRM_DEBUG_ATOMIC("[MSTB:%p] [MST PORT:%p] uses %d out of %d PBN\n", + port->parent, port, pbn_used, port->full_pbn); + + return pbn_used; } static inline int @@ -5060,9 +5123,15 @@ int drm_dp_mst_atomic_check(struct drm_atomic_state *state) ret = drm_dp_mst_atomic_check_vcpi_alloc_limit(mgr, mst_state); if (ret) break; - ret = drm_dp_mst_atomic_check_bw_limit(mgr->mst_primary, mst_state); - if (ret) + + mutex_lock(&mgr->lock); + ret = drm_dp_mst_atomic_check_mstb_bw_limit(mgr->mst_primary, + mst_state); + mutex_unlock(&mgr->lock); + if (ret < 0) break; + else + ret = 0; } return ret; diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 99769d6c9f8462e25d189c78df3990b8519b7b79..805fb004c8eb922fca661d9dd1f56ded8115de1c 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -3211,7 +3211,7 @@ static u8 *drm_find_cea_extension(const struct edid *edid) return cea; } -static const struct drm_display_mode *cea_mode_for_vic(u8 vic) +static __always_inline const struct drm_display_mode *cea_mode_for_vic(u8 vic) { BUILD_BUG_ON(1 + ARRAY_SIZE(edid_cea_modes_1) - 1 != 127); BUILD_BUG_ON(193 + ARRAY_SIZE(edid_cea_modes_193) - 1 != 219); diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index a421a2eed48ad1b3bcf3cc4523280c49c98a5791..df31e5782eed1b372cc6076da54250c9eace0159 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -254,11 +254,16 @@ static void *drm_gem_shmem_vmap_locked(struct drm_gem_shmem_object *shmem) if (ret) goto err_zero_use; - if (obj->import_attach) + if (obj->import_attach) { shmem->vaddr = dma_buf_vmap(obj->import_attach->dmabuf); - else + } else { + pgprot_t prot = PAGE_KERNEL; + + if (!shmem->map_cached) + prot = pgprot_writecombine(prot); shmem->vaddr = vmap(shmem->pages, obj->size >> PAGE_SHIFT, - VM_MAP, pgprot_writecombine(PAGE_KERNEL)); + VM_MAP, prot); + } if (!shmem->vaddr) { DRM_DEBUG_KMS("Failed to vmap pages\n"); @@ -540,8 +545,9 @@ int drm_gem_shmem_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma) } vma->vm_flags |= VM_MIXEDMAP | VM_DONTEXPAND; - vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags)); - vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot); + vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); + if (!shmem->map_cached) + vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot); vma->vm_ops = &drm_gem_shmem_vm_ops; return 0; diff --git a/drivers/gpu/drm/drm_lease.c b/drivers/gpu/drm/drm_lease.c index b481cafdde280bbaddf0e9168c448fafba95d095..825abe38201acfe6aecd742f89b2b5b3e9165df0 100644 --- a/drivers/gpu/drm/drm_lease.c +++ b/drivers/gpu/drm/drm_lease.c @@ -542,10 +542,12 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev, } DRM_DEBUG_LEASE("Creating lease\n"); + /* lessee will take the ownership of leases */ lessee = drm_lease_create(lessor, &leases); if (IS_ERR(lessee)) { ret = PTR_ERR(lessee); + idr_destroy(&leases); goto out_leases; } @@ -580,7 +582,6 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev, out_leases: put_unused_fd(fd); - idr_destroy(&leases); DRM_DEBUG_LEASE("drm_mode_create_lease_ioctl failed: %d\n", ret); return ret; diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c index 10336b144c722b5aa03bca91d3d28685c009bf72..d4d64518e11b8fc06f45eddf2673a8c6ba0bfe34 100644 --- a/drivers/gpu/drm/drm_modes.c +++ b/drivers/gpu/drm/drm_modes.c @@ -1698,6 +1698,13 @@ static int drm_mode_parse_cmdline_options(const char *str, if (rotation && freestanding) return -EINVAL; + if (!(rotation & DRM_MODE_ROTATE_MASK)) + rotation |= DRM_MODE_ROTATE_0; + + /* Make sure there is exactly one rotation defined */ + if (!is_power_of_2(rotation & DRM_MODE_ROTATE_MASK)) + return -EINVAL; + mode->rotation_reflection = rotation; return 0; diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c index 8428ae12dfa5e8c4de938ac46c0689053d3609a5..1f79bc2a881e1f3889e5161ef14fbba33d1764be 100644 --- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c @@ -55,6 +55,7 @@ static const char * const decon_clks_name[] = { struct decon_context { struct device *dev; struct drm_device *drm_dev; + void *dma_priv; struct exynos_drm_crtc *crtc; struct exynos_drm_plane planes[WINDOWS_NR]; struct exynos_drm_plane_config configs[WINDOWS_NR]; @@ -644,7 +645,7 @@ static int decon_bind(struct device *dev, struct device *master, void *data) decon_clear_channels(ctx->crtc); - return exynos_drm_register_dma(drm_dev, dev); + return exynos_drm_register_dma(drm_dev, dev, &ctx->dma_priv); } static void decon_unbind(struct device *dev, struct device *master, void *data) @@ -654,7 +655,7 @@ static void decon_unbind(struct device *dev, struct device *master, void *data) decon_atomic_disable(ctx->crtc); /* detach this sub driver from iommu mapping if supported. */ - exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev); + exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev, &ctx->dma_priv); } static const struct component_ops decon_component_ops = { diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c index ff59c641fa809224b96972928c3b6ae6a5fb3c21..1eed3327999f36c5d30bce642c457d940006c10d 100644 --- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c @@ -40,6 +40,7 @@ struct decon_context { struct device *dev; struct drm_device *drm_dev; + void *dma_priv; struct exynos_drm_crtc *crtc; struct exynos_drm_plane planes[WINDOWS_NR]; struct exynos_drm_plane_config configs[WINDOWS_NR]; @@ -127,13 +128,13 @@ static int decon_ctx_initialize(struct decon_context *ctx, decon_clear_channels(ctx->crtc); - return exynos_drm_register_dma(drm_dev, ctx->dev); + return exynos_drm_register_dma(drm_dev, ctx->dev, &ctx->dma_priv); } static void decon_ctx_remove(struct decon_context *ctx) { /* detach this sub driver from iommu mapping if supported. */ - exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev); + exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev, &ctx->dma_priv); } static u32 decon_calc_clkdiv(struct decon_context *ctx, diff --git a/drivers/gpu/drm/exynos/exynos_drm_dma.c b/drivers/gpu/drm/exynos/exynos_drm_dma.c index 9ebc02768847eafaf73e58e1668f032bb693db45..619f81435c1b2273abe2d61e7ee6d58dc0ce73a5 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dma.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dma.c @@ -58,7 +58,7 @@ static inline void clear_dma_max_seg_size(struct device *dev) * mapping. */ static int drm_iommu_attach_device(struct drm_device *drm_dev, - struct device *subdrv_dev) + struct device *subdrv_dev, void **dma_priv) { struct exynos_drm_private *priv = drm_dev->dev_private; int ret; @@ -74,7 +74,14 @@ static int drm_iommu_attach_device(struct drm_device *drm_dev, return ret; if (IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)) { - if (to_dma_iommu_mapping(subdrv_dev)) + /* + * Keep the original DMA mapping of the sub-device and + * restore it on Exynos DRM detach, otherwise the DMA + * framework considers it as IOMMU-less during the next + * probe (in case of deferred probe or modular build) + */ + *dma_priv = to_dma_iommu_mapping(subdrv_dev); + if (*dma_priv) arm_iommu_detach_device(subdrv_dev); ret = arm_iommu_attach_device(subdrv_dev, priv->mapping); @@ -98,19 +105,21 @@ static int drm_iommu_attach_device(struct drm_device *drm_dev, * mapping */ static void drm_iommu_detach_device(struct drm_device *drm_dev, - struct device *subdrv_dev) + struct device *subdrv_dev, void **dma_priv) { struct exynos_drm_private *priv = drm_dev->dev_private; - if (IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)) + if (IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)) { arm_iommu_detach_device(subdrv_dev); - else if (IS_ENABLED(CONFIG_IOMMU_DMA)) + arm_iommu_attach_device(subdrv_dev, *dma_priv); + } else if (IS_ENABLED(CONFIG_IOMMU_DMA)) iommu_detach_device(priv->mapping, subdrv_dev); clear_dma_max_seg_size(subdrv_dev); } -int exynos_drm_register_dma(struct drm_device *drm, struct device *dev) +int exynos_drm_register_dma(struct drm_device *drm, struct device *dev, + void **dma_priv) { struct exynos_drm_private *priv = drm->dev_private; @@ -137,13 +146,14 @@ int exynos_drm_register_dma(struct drm_device *drm, struct device *dev) priv->mapping = mapping; } - return drm_iommu_attach_device(drm, dev); + return drm_iommu_attach_device(drm, dev, dma_priv); } -void exynos_drm_unregister_dma(struct drm_device *drm, struct device *dev) +void exynos_drm_unregister_dma(struct drm_device *drm, struct device *dev, + void **dma_priv) { if (IS_ENABLED(CONFIG_EXYNOS_IOMMU)) - drm_iommu_detach_device(drm, dev); + drm_iommu_detach_device(drm, dev, dma_priv); } void exynos_drm_cleanup_dma(struct drm_device *drm) diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h index d4d21d8cfb9060169ab86bda8ef49b879eaa5b4a..6ae9056e7a18f7a73a9d7096c98e6b61061534b6 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.h +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h @@ -223,8 +223,10 @@ static inline bool is_drm_iommu_supported(struct drm_device *drm_dev) return priv->mapping ? true : false; } -int exynos_drm_register_dma(struct drm_device *drm, struct device *dev); -void exynos_drm_unregister_dma(struct drm_device *drm, struct device *dev); +int exynos_drm_register_dma(struct drm_device *drm, struct device *dev, + void **dma_priv); +void exynos_drm_unregister_dma(struct drm_device *drm, struct device *dev, + void **dma_priv); void exynos_drm_cleanup_dma(struct drm_device *drm); #ifdef CONFIG_DRM_EXYNOS_DPI diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c index 33628d85edad9102cf2bf220b7b78fc645752882..a85365c56d4ddbedf576059273380f61d60c532f 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c @@ -1773,8 +1773,9 @@ static int exynos_dsi_probe(struct platform_device *pdev) ret = devm_regulator_bulk_get(dev, ARRAY_SIZE(dsi->supplies), dsi->supplies); if (ret) { - dev_info(dev, "failed to get regulators: %d\n", ret); - return -EPROBE_DEFER; + if (ret != -EPROBE_DEFER) + dev_info(dev, "failed to get regulators: %d\n", ret); + return ret; } dsi->clks = devm_kcalloc(dev, @@ -1787,9 +1788,10 @@ static int exynos_dsi_probe(struct platform_device *pdev) dsi->clks[i] = devm_clk_get(dev, clk_names[i]); if (IS_ERR(dsi->clks[i])) { if (strcmp(clk_names[i], "sclk_mipi") == 0) { - strcpy(clk_names[i], OLD_SCLK_MIPI_CLK_NAME); - i--; - continue; + dsi->clks[i] = devm_clk_get(dev, + OLD_SCLK_MIPI_CLK_NAME); + if (!IS_ERR(dsi->clks[i])) + continue; } dev_info(dev, "failed to get the clock: %s\n", diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c index 8ea2e1d77802a40670b23a9c5d300e6e75cac036..29ab8be8604c9ba0881d818eab5c055be699ecb2 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c @@ -97,6 +97,7 @@ struct fimc_scaler { struct fimc_context { struct exynos_drm_ipp ipp; struct drm_device *drm_dev; + void *dma_priv; struct device *dev; struct exynos_drm_ipp_task *task; struct exynos_drm_ipp_formats *formats; @@ -1133,7 +1134,7 @@ static int fimc_bind(struct device *dev, struct device *master, void *data) ctx->drm_dev = drm_dev; ipp->drm_dev = drm_dev; - exynos_drm_register_dma(drm_dev, dev); + exynos_drm_register_dma(drm_dev, dev, &ctx->dma_priv); exynos_drm_ipp_register(dev, ipp, &ipp_funcs, DRM_EXYNOS_IPP_CAP_CROP | DRM_EXYNOS_IPP_CAP_ROTATE | @@ -1153,7 +1154,7 @@ static void fimc_unbind(struct device *dev, struct device *master, struct exynos_drm_ipp *ipp = &ctx->ipp; exynos_drm_ipp_unregister(dev, ipp); - exynos_drm_unregister_dma(drm_dev, dev); + exynos_drm_unregister_dma(drm_dev, dev, &ctx->dma_priv); } static const struct component_ops fimc_component_ops = { diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c index 21aec38702fc2b731a1ae4a982ed15fced156175..bb67cad8371f03da95d878e334e32b1cff2b10e9 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c @@ -167,6 +167,7 @@ static struct fimd_driver_data exynos5420_fimd_driver_data = { struct fimd_context { struct device *dev; struct drm_device *drm_dev; + void *dma_priv; struct exynos_drm_crtc *crtc; struct exynos_drm_plane planes[WINDOWS_NR]; struct exynos_drm_plane_config configs[WINDOWS_NR]; @@ -1090,7 +1091,7 @@ static int fimd_bind(struct device *dev, struct device *master, void *data) if (is_drm_iommu_supported(drm_dev)) fimd_clear_channels(ctx->crtc); - return exynos_drm_register_dma(drm_dev, dev); + return exynos_drm_register_dma(drm_dev, dev, &ctx->dma_priv); } static void fimd_unbind(struct device *dev, struct device *master, @@ -1100,7 +1101,7 @@ static void fimd_unbind(struct device *dev, struct device *master, fimd_atomic_disable(ctx->crtc); - exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev); + exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev, &ctx->dma_priv); if (ctx->encoder) exynos_dpi_remove(ctx->encoder); diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c index 2a3382d43bc9020722617f421f9d3e7c6ae6bed1..fcee33a43aca3ee45a2c9d2584b551dd507c1cd1 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c +++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c @@ -232,6 +232,7 @@ struct g2d_runqueue_node { struct g2d_data { struct device *dev; + void *dma_priv; struct clk *gate_clk; void __iomem *regs; int irq; @@ -1409,7 +1410,7 @@ static int g2d_bind(struct device *dev, struct device *master, void *data) return ret; } - ret = exynos_drm_register_dma(drm_dev, dev); + ret = exynos_drm_register_dma(drm_dev, dev, &g2d->dma_priv); if (ret < 0) { dev_err(dev, "failed to enable iommu.\n"); g2d_fini_cmdlist(g2d); @@ -1434,7 +1435,7 @@ static void g2d_unbind(struct device *dev, struct device *master, void *data) priv->g2d_dev = NULL; cancel_work_sync(&g2d->runqueue_work); - exynos_drm_unregister_dma(g2d->drm_dev, dev); + exynos_drm_unregister_dma(g2d->drm_dev, dev, &g2d->dma_priv); } static const struct component_ops g2d_component_ops = { diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c index 88b6fcaa20be0976d4ff3f3009a75d548a6398f7..45e9aee8366a8f5bfc14fd60c6301424a5603f17 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c @@ -97,6 +97,7 @@ struct gsc_scaler { struct gsc_context { struct exynos_drm_ipp ipp; struct drm_device *drm_dev; + void *dma_priv; struct device *dev; struct exynos_drm_ipp_task *task; struct exynos_drm_ipp_formats *formats; @@ -1169,7 +1170,7 @@ static int gsc_bind(struct device *dev, struct device *master, void *data) ctx->drm_dev = drm_dev; ctx->drm_dev = drm_dev; - exynos_drm_register_dma(drm_dev, dev); + exynos_drm_register_dma(drm_dev, dev, &ctx->dma_priv); exynos_drm_ipp_register(dev, ipp, &ipp_funcs, DRM_EXYNOS_IPP_CAP_CROP | DRM_EXYNOS_IPP_CAP_ROTATE | @@ -1189,7 +1190,7 @@ static void gsc_unbind(struct device *dev, struct device *master, struct exynos_drm_ipp *ipp = &ctx->ipp; exynos_drm_ipp_unregister(dev, ipp); - exynos_drm_unregister_dma(drm_dev, dev); + exynos_drm_unregister_dma(drm_dev, dev, &ctx->dma_priv); } static const struct component_ops gsc_component_ops = { diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.c b/drivers/gpu/drm/exynos/exynos_drm_rotator.c index b98482990d1ade89faab2ec41a187ecc269264f8..dafa87b82052967ca27292c261008125a8e4d58d 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_rotator.c +++ b/drivers/gpu/drm/exynos/exynos_drm_rotator.c @@ -56,6 +56,7 @@ struct rot_variant { struct rot_context { struct exynos_drm_ipp ipp; struct drm_device *drm_dev; + void *dma_priv; struct device *dev; void __iomem *regs; struct clk *clock; @@ -243,7 +244,7 @@ static int rotator_bind(struct device *dev, struct device *master, void *data) rot->drm_dev = drm_dev; ipp->drm_dev = drm_dev; - exynos_drm_register_dma(drm_dev, dev); + exynos_drm_register_dma(drm_dev, dev, &rot->dma_priv); exynos_drm_ipp_register(dev, ipp, &ipp_funcs, DRM_EXYNOS_IPP_CAP_CROP | DRM_EXYNOS_IPP_CAP_ROTATE, @@ -261,7 +262,7 @@ static void rotator_unbind(struct device *dev, struct device *master, struct exynos_drm_ipp *ipp = &rot->ipp; exynos_drm_ipp_unregister(dev, ipp); - exynos_drm_unregister_dma(rot->drm_dev, rot->dev); + exynos_drm_unregister_dma(rot->drm_dev, rot->dev, &rot->dma_priv); } static const struct component_ops rotator_component_ops = { diff --git a/drivers/gpu/drm/exynos/exynos_drm_scaler.c b/drivers/gpu/drm/exynos/exynos_drm_scaler.c index 497973e9b2c55a7c827254ffe96f45041ba59e94..93c43c8d914ee78a1b275b700c6486026958ce84 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_scaler.c +++ b/drivers/gpu/drm/exynos/exynos_drm_scaler.c @@ -39,6 +39,7 @@ struct scaler_data { struct scaler_context { struct exynos_drm_ipp ipp; struct drm_device *drm_dev; + void *dma_priv; struct device *dev; void __iomem *regs; struct clk *clock[SCALER_MAX_CLK]; @@ -450,7 +451,7 @@ static int scaler_bind(struct device *dev, struct device *master, void *data) scaler->drm_dev = drm_dev; ipp->drm_dev = drm_dev; - exynos_drm_register_dma(drm_dev, dev); + exynos_drm_register_dma(drm_dev, dev, &scaler->dma_priv); exynos_drm_ipp_register(dev, ipp, &ipp_funcs, DRM_EXYNOS_IPP_CAP_CROP | DRM_EXYNOS_IPP_CAP_ROTATE | @@ -470,7 +471,8 @@ static void scaler_unbind(struct device *dev, struct device *master, struct exynos_drm_ipp *ipp = &scaler->ipp; exynos_drm_ipp_unregister(dev, ipp); - exynos_drm_unregister_dma(scaler->drm_dev, scaler->dev); + exynos_drm_unregister_dma(scaler->drm_dev, scaler->dev, + &scaler->dma_priv); } static const struct component_ops scaler_component_ops = { diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c index 9ff921f43a9391625ef84299f82d9c69db992add..f141916eade6998b85e4811d8d55758dcd8a2d1e 100644 --- a/drivers/gpu/drm/exynos/exynos_hdmi.c +++ b/drivers/gpu/drm/exynos/exynos_hdmi.c @@ -1805,18 +1805,10 @@ static int hdmi_resources_init(struct hdmi_context *hdata) hdata->reg_hdmi_en = devm_regulator_get_optional(dev, "hdmi-en"); - if (PTR_ERR(hdata->reg_hdmi_en) != -ENODEV) { + if (PTR_ERR(hdata->reg_hdmi_en) != -ENODEV) if (IS_ERR(hdata->reg_hdmi_en)) return PTR_ERR(hdata->reg_hdmi_en); - ret = regulator_enable(hdata->reg_hdmi_en); - if (ret) { - DRM_DEV_ERROR(dev, - "failed to enable hdmi-en regulator\n"); - return ret; - } - } - return hdmi_bridge_init(hdata); } @@ -2023,6 +2015,15 @@ static int hdmi_probe(struct platform_device *pdev) } } + if (!IS_ERR(hdata->reg_hdmi_en)) { + ret = regulator_enable(hdata->reg_hdmi_en); + if (ret) { + DRM_DEV_ERROR(dev, + "failed to enable hdmi-en regulator\n"); + goto err_hdmiphy; + } + } + pm_runtime_enable(dev); audio_infoframe = &hdata->audio.infoframe; @@ -2047,7 +2048,8 @@ static int hdmi_probe(struct platform_device *pdev) err_rpm_disable: pm_runtime_disable(dev); - + if (!IS_ERR(hdata->reg_hdmi_en)) + regulator_disable(hdata->reg_hdmi_en); err_hdmiphy: if (hdata->hdmiphy_port) put_device(&hdata->hdmiphy_port->dev); diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c index 38ae9c32feef594f398ab246582067604b9c29f7..21b726baedeaa625a975d45a37fe3ef834baa154 100644 --- a/drivers/gpu/drm/exynos/exynos_mixer.c +++ b/drivers/gpu/drm/exynos/exynos_mixer.c @@ -94,6 +94,7 @@ struct mixer_context { struct platform_device *pdev; struct device *dev; struct drm_device *drm_dev; + void *dma_priv; struct exynos_drm_crtc *crtc; struct exynos_drm_plane planes[MIXER_WIN_NR]; unsigned long flags; @@ -894,12 +895,14 @@ static int mixer_initialize(struct mixer_context *mixer_ctx, } } - return exynos_drm_register_dma(drm_dev, mixer_ctx->dev); + return exynos_drm_register_dma(drm_dev, mixer_ctx->dev, + &mixer_ctx->dma_priv); } static void mixer_ctx_remove(struct mixer_context *mixer_ctx) { - exynos_drm_unregister_dma(mixer_ctx->drm_dev, mixer_ctx->dev); + exynos_drm_unregister_dma(mixer_ctx->drm_dev, mixer_ctx->dev, + &mixer_ctx->dma_priv); } static int mixer_enable_vblank(struct exynos_drm_crtc *crtc) diff --git a/drivers/gpu/drm/hisilicon/kirin/kirin_ade_reg.h b/drivers/gpu/drm/hisilicon/kirin/kirin_ade_reg.h index 0da86020041094acd261e7949f68a7c9707909d0..e2ac09894a6d7c15be9730aa1ec481f895a07bbc 100644 --- a/drivers/gpu/drm/hisilicon/kirin/kirin_ade_reg.h +++ b/drivers/gpu/drm/hisilicon/kirin/kirin_ade_reg.h @@ -83,7 +83,6 @@ #define VSIZE_OFST 20 #define LDI_INT_EN 0x741C #define FRAME_END_INT_EN_OFST 1 -#define UNDERFLOW_INT_EN_OFST 2 #define LDI_CTRL 0x7420 #define BPP_OFST 3 #define DATA_GATE_EN BIT(2) diff --git a/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c b/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c index 73cd28a6ea078f95608bfb623bc5cd81a191946a..86000127d4eec54465ee2e4db8403c6f52cac117 100644 --- a/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c +++ b/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c @@ -46,7 +46,6 @@ struct ade_hw_ctx { struct clk *media_noc_clk; struct clk *ade_pix_clk; struct reset_control *reset; - struct work_struct display_reset_wq; bool power_on; int irq; @@ -136,7 +135,6 @@ static void ade_init(struct ade_hw_ctx *ctx) */ ade_update_bits(base + ADE_CTRL, FRM_END_START_OFST, FRM_END_START_MASK, REG_EFFECTIVE_IN_ADEEN_FRMEND); - ade_update_bits(base + LDI_INT_EN, UNDERFLOW_INT_EN_OFST, MASK(1), 1); } static bool ade_crtc_mode_fixup(struct drm_crtc *crtc, @@ -304,17 +302,6 @@ static void ade_crtc_disable_vblank(struct drm_crtc *crtc) MASK(1), 0); } -static void drm_underflow_wq(struct work_struct *work) -{ - struct ade_hw_ctx *ctx = container_of(work, struct ade_hw_ctx, - display_reset_wq); - struct drm_device *drm_dev = ctx->crtc->dev; - struct drm_atomic_state *state; - - state = drm_atomic_helper_suspend(drm_dev); - drm_atomic_helper_resume(drm_dev, state); -} - static irqreturn_t ade_irq_handler(int irq, void *data) { struct ade_hw_ctx *ctx = data; @@ -331,12 +318,6 @@ static irqreturn_t ade_irq_handler(int irq, void *data) MASK(1), 1); drm_crtc_handle_vblank(crtc); } - if (status & BIT(UNDERFLOW_INT_EN_OFST)) { - ade_update_bits(base + LDI_INT_CLR, UNDERFLOW_INT_EN_OFST, - MASK(1), 1); - DRM_ERROR("LDI underflow!"); - schedule_work(&ctx->display_reset_wq); - } return IRQ_HANDLED; } @@ -919,7 +900,6 @@ static void *ade_hw_ctx_alloc(struct platform_device *pdev, if (ret) return ERR_PTR(-EIO); - INIT_WORK(&ctx->display_reset_wq, drm_underflow_wq); ctx->crtc = crtc; return ctx; diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig index ba9595960bbebf290170a2bfb6247320a5fb8a21..907c4471f5916d742c4d65610374b80657fa74c9 100644 --- a/drivers/gpu/drm/i915/Kconfig +++ b/drivers/gpu/drm/i915/Kconfig @@ -75,9 +75,8 @@ config DRM_I915_CAPTURE_ERROR help This option enables capturing the GPU state when a hang is detected. This information is vital for triaging hangs and assists in debugging. - Please report any hang to - https://bugs.freedesktop.org/enter_bug.cgi?product=DRI - for triaging. + Please report any hang for triaging according to: + https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs If in doubt, say "Y". diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index b8c5f8934dbdf61792997b1cb6b03650a6dca6bf..a1f2411aa21b26a034b27312077d5f3764bb9083 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -294,7 +294,7 @@ extra-$(CONFIG_DRM_I915_WERROR) += \ $(shell cd $(srctree)/$(src) && find * -name '*.h'))) quiet_cmd_hdrtest = HDRTEST $(patsubst %.hdrtest,%.h,$@) - cmd_hdrtest = $(CC) $(c_flags) -S -o /dev/null -x c /dev/null -include $<; touch $@ + cmd_hdrtest = $(CC) $(filter-out $(CFLAGS_GCOV), $(c_flags)) -S -o /dev/null -x c /dev/null -include $<; touch $@ $(obj)/%.hdrtest: $(src)/%.h FORCE $(call if_changed_dep,hdrtest) diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c index 8beac06e3f10f213ae736f7fde35b309c51341c9..ef4017a1babaa10e17ae4271ffa8b94e00c158d6 100644 --- a/drivers/gpu/drm/i915/display/intel_bios.c +++ b/drivers/gpu/drm/i915/display/intel_bios.c @@ -357,14 +357,16 @@ parse_generic_dtd(struct drm_i915_private *dev_priv, panel_fixed_mode->hdisplay + dtd->hfront_porch; panel_fixed_mode->hsync_end = panel_fixed_mode->hsync_start + dtd->hsync; - panel_fixed_mode->htotal = panel_fixed_mode->hsync_end; + panel_fixed_mode->htotal = + panel_fixed_mode->hdisplay + dtd->hblank; panel_fixed_mode->vdisplay = dtd->vactive; panel_fixed_mode->vsync_start = panel_fixed_mode->vdisplay + dtd->vfront_porch; panel_fixed_mode->vsync_end = panel_fixed_mode->vsync_start + dtd->vsync; - panel_fixed_mode->vtotal = panel_fixed_mode->vsync_end; + panel_fixed_mode->vtotal = + panel_fixed_mode->vdisplay + dtd->vblank; panel_fixed_mode->clock = dtd->pixel_clock; panel_fixed_mode->width_mm = dtd->width_mm; diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index 33f1dc3d7c1a6d896054a83bc32a200689395527..d9a61f341070bd3df7fd1fddc0d68abf911fe526 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -4251,7 +4251,9 @@ static bool intel_ddi_is_audio_enabled(struct drm_i915_private *dev_priv, void intel_ddi_compute_min_voltage_level(struct drm_i915_private *dev_priv, struct intel_crtc_state *crtc_state) { - if (INTEL_GEN(dev_priv) >= 11 && crtc_state->port_clock > 594000) + if (IS_ELKHARTLAKE(dev_priv) && crtc_state->port_clock > 594000) + crtc_state->min_voltage_level = 3; + else if (INTEL_GEN(dev_priv) >= 11 && crtc_state->port_clock > 594000) crtc_state->min_voltage_level = 1; else if (IS_CANNONLAKE(dev_priv) && crtc_state->port_clock > 594000) crtc_state->min_voltage_level = 2; diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 19ea842cfd849fae402046ad0fa406096c0aad5a..aa453953908b54ff27fe2d2d60a12639b4d31fc0 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -11087,7 +11087,7 @@ static u32 intel_cursor_base(const struct intel_plane_state *plane_state) u32 base; if (INTEL_INFO(dev_priv)->display.cursor_needs_physical) - base = obj->phys_handle->busaddr; + base = sg_dma_address(obj->mm.pages->sgl); else base = intel_plane_ggtt_offset(plane_state); @@ -12366,6 +12366,7 @@ static int icl_check_nv12_planes(struct intel_crtc_state *crtc_state) /* Copy parameters to slave plane */ linked_state->ctl = plane_state->ctl | PLANE_CTL_YUV420_Y_PLANE; linked_state->color_ctl = plane_state->color_ctl; + linked_state->view = plane_state->view; memcpy(linked_state->color_plane, plane_state->color_plane, sizeof(linked_state->color_plane)); @@ -14476,37 +14477,23 @@ static int intel_atomic_check_crtcs(struct intel_atomic_state *state) return 0; } -static bool intel_cpu_transcoder_needs_modeset(struct intel_atomic_state *state, - enum transcoder transcoder) +static bool intel_cpu_transcoders_need_modeset(struct intel_atomic_state *state, + u8 transcoders) { - struct intel_crtc_state *new_crtc_state; + const struct intel_crtc_state *new_crtc_state; struct intel_crtc *crtc; int i; - for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) - if (new_crtc_state->cpu_transcoder == transcoder) - return needs_modeset(new_crtc_state); + for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) { + if (new_crtc_state->hw.enable && + transcoders & BIT(new_crtc_state->cpu_transcoder) && + needs_modeset(new_crtc_state)) + return true; + } return false; } -static void -intel_modeset_synced_crtcs(struct intel_atomic_state *state, - u8 transcoders) -{ - struct intel_crtc_state *new_crtc_state; - struct intel_crtc *crtc; - int i; - - for_each_new_intel_crtc_in_state(state, crtc, - new_crtc_state, i) { - if (transcoders & BIT(new_crtc_state->cpu_transcoder)) { - new_crtc_state->uapi.mode_changed = true; - new_crtc_state->update_pipe = false; - } - } -} - static int intel_modeset_all_tiles(struct intel_atomic_state *state, int tile_grp_id) { @@ -14662,15 +14649,20 @@ static int intel_atomic_check(struct drm_device *dev, if (intel_dp_mst_is_slave_trans(new_crtc_state)) { enum transcoder master = new_crtc_state->mst_master_transcoder; - if (intel_cpu_transcoder_needs_modeset(state, master)) { + if (intel_cpu_transcoders_need_modeset(state, BIT(master))) { new_crtc_state->uapi.mode_changed = true; new_crtc_state->update_pipe = false; } - } else if (is_trans_port_sync_mode(new_crtc_state)) { + } + + if (is_trans_port_sync_mode(new_crtc_state)) { u8 trans = new_crtc_state->sync_mode_slaves_mask | BIT(new_crtc_state->master_transcoder); - intel_modeset_synced_crtcs(state, trans); + if (intel_cpu_transcoders_need_modeset(state, trans)) { + new_crtc_state->uapi.mode_changed = true; + new_crtc_state->update_pipe = false; + } } } @@ -17441,6 +17433,24 @@ static int intel_initial_commit(struct drm_device *dev) * have readout for pipe gamma enable. */ crtc_state->uapi.color_mgmt_changed = true; + + /* + * FIXME hack to force full modeset when DSC is being + * used. + * + * As long as we do not have full state readout and + * config comparison of crtc_state->dsc, we have no way + * to ensure reliable fastset. Remove once we have + * readout for DSC. + */ + if (crtc_state->dsc.compression_enable) { + ret = drm_atomic_add_affected_connectors(state, + &crtc->base); + if (ret) + goto out; + crtc_state->uapi.mode_changed = true; + drm_dbg_kms(dev, "Force full modeset for DSC\n"); + } } } diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c index 21561acfa3ac43fdf6fd796168fb011b292fe46b..46c40db992dd70874d86d151a3bfdf785fe14610 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.c +++ b/drivers/gpu/drm/i915/display/intel_display_power.c @@ -4466,13 +4466,19 @@ static void icl_dbuf_disable(struct drm_i915_private *dev_priv) static void icl_mbus_init(struct drm_i915_private *dev_priv) { - u32 val; + u32 mask, val; - val = MBUS_ABOX_BT_CREDIT_POOL1(16) | - MBUS_ABOX_BT_CREDIT_POOL2(16) | - MBUS_ABOX_B_CREDIT(1) | - MBUS_ABOX_BW_CREDIT(1); + mask = MBUS_ABOX_BT_CREDIT_POOL1_MASK | + MBUS_ABOX_BT_CREDIT_POOL2_MASK | + MBUS_ABOX_B_CREDIT_MASK | + MBUS_ABOX_BW_CREDIT_MASK; + val = I915_READ(MBUS_ABOX_CTL); + val &= ~mask; + val |= MBUS_ABOX_BT_CREDIT_POOL1(16) | + MBUS_ABOX_BT_CREDIT_POOL2(16) | + MBUS_ABOX_B_CREDIT(1) | + MBUS_ABOX_BW_CREDIT(1); I915_WRITE(MBUS_ABOX_CTL, val); } @@ -4968,8 +4974,21 @@ static void tgl_bw_buddy_init(struct drm_i915_private *dev_priv) I915_WRITE(BW_BUDDY1_CTL, BW_BUDDY_DISABLE); I915_WRITE(BW_BUDDY2_CTL, BW_BUDDY_DISABLE); } else { + u32 val; + I915_WRITE(BW_BUDDY1_PAGE_MASK, table[i].page_mask); I915_WRITE(BW_BUDDY2_PAGE_MASK, table[i].page_mask); + + /* Wa_22010178259:tgl */ + val = I915_READ(BW_BUDDY1_CTL); + val &= ~BW_BUDDY_TLB_REQ_TIMER_MASK; + val |= REG_FIELD_PREP(BW_BUDDY_TLB_REQ_TIMER_MASK, 0x8); + I915_WRITE(BW_BUDDY1_CTL, val); + + val = I915_READ(BW_BUDDY2_CTL); + val &= ~BW_BUDDY_TLB_REQ_TIMER_MASK; + val |= REG_FIELD_PREP(BW_BUDDY_TLB_REQ_TIMER_MASK, 0x8); + I915_WRITE(BW_BUDDY2_CTL, val); } } diff --git a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c index 89fb0d90b694ab17e038afb9b0ee14681c327977..04f953ba8f0027fb143b9327912cea19e0002c2a 100644 --- a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c +++ b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c @@ -384,6 +384,7 @@ static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data) return data; } +#ifdef CONFIG_ACPI static int i2c_adapter_lookup(struct acpi_resource *ares, void *data) { struct i2c_adapter_lookup *lookup = data; @@ -393,8 +394,7 @@ static int i2c_adapter_lookup(struct acpi_resource *ares, void *data) acpi_handle adapter_handle; acpi_status status; - if (intel_dsi->i2c_bus_num >= 0 || - !i2c_acpi_get_i2c_resource(ares, &sb)) + if (!i2c_acpi_get_i2c_resource(ares, &sb)) return 1; if (lookup->slave_addr != sb->slave_address) @@ -413,14 +413,41 @@ static int i2c_adapter_lookup(struct acpi_resource *ares, void *data) return 1; } -static const u8 *mipi_exec_i2c(struct intel_dsi *intel_dsi, const u8 *data) +static void i2c_acpi_find_adapter(struct intel_dsi *intel_dsi, + const u16 slave_addr) { struct drm_device *drm_dev = intel_dsi->base.base.dev; struct device *dev = &drm_dev->pdev->dev; - struct i2c_adapter *adapter; struct acpi_device *acpi_dev; struct list_head resource_list; struct i2c_adapter_lookup lookup; + + acpi_dev = ACPI_COMPANION(dev); + if (acpi_dev) { + memset(&lookup, 0, sizeof(lookup)); + lookup.slave_addr = slave_addr; + lookup.intel_dsi = intel_dsi; + lookup.dev_handle = acpi_device_handle(acpi_dev); + + INIT_LIST_HEAD(&resource_list); + acpi_dev_get_resources(acpi_dev, &resource_list, + i2c_adapter_lookup, + &lookup); + acpi_dev_free_resource_list(&resource_list); + } +} +#else +static inline void i2c_acpi_find_adapter(struct intel_dsi *intel_dsi, + const u16 slave_addr) +{ +} +#endif + +static const u8 *mipi_exec_i2c(struct intel_dsi *intel_dsi, const u8 *data) +{ + struct drm_device *drm_dev = intel_dsi->base.base.dev; + struct device *dev = &drm_dev->pdev->dev; + struct i2c_adapter *adapter; struct i2c_msg msg; int ret; u8 vbt_i2c_bus_num = *(data + 2); @@ -431,20 +458,7 @@ static const u8 *mipi_exec_i2c(struct intel_dsi *intel_dsi, const u8 *data) if (intel_dsi->i2c_bus_num < 0) { intel_dsi->i2c_bus_num = vbt_i2c_bus_num; - - acpi_dev = ACPI_COMPANION(dev); - if (acpi_dev) { - memset(&lookup, 0, sizeof(lookup)); - lookup.slave_addr = slave_addr; - lookup.intel_dsi = intel_dsi; - lookup.dev_handle = acpi_device_handle(acpi_dev); - - INIT_LIST_HEAD(&resource_list); - acpi_dev_get_resources(acpi_dev, &resource_list, - i2c_adapter_lookup, - &lookup); - acpi_dev_free_resource_list(&resource_list); - } + i2c_acpi_find_adapter(intel_dsi, slave_addr); } adapter = i2c_get_adapter(intel_dsi->i2c_bus_num); diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index 89c9cf5f38d2d642009499c8e9de9c6268d78b8a..83025052c965586ada0b7ce4d9db85c53901f2d4 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -852,10 +852,12 @@ void intel_psr_enable(struct intel_dp *intel_dp, { struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); - if (!crtc_state->has_psr) + if (!CAN_PSR(dev_priv) || dev_priv->psr.dp != intel_dp) return; - if (WARN_ON(!CAN_PSR(dev_priv))) + dev_priv->psr.force_mode_changed = false; + + if (!crtc_state->has_psr) return; WARN_ON(dev_priv->drrs.dp); @@ -1009,6 +1011,8 @@ void intel_psr_update(struct intel_dp *intel_dp, if (!CAN_PSR(dev_priv) || READ_ONCE(psr->dp) != intel_dp) return; + dev_priv->psr.force_mode_changed = false; + mutex_lock(&dev_priv->psr.lock); enable = crtc_state->has_psr && psr_global_enabled(psr->debug); @@ -1534,7 +1538,7 @@ void intel_psr_atomic_check(struct drm_connector *connector, struct drm_crtc_state *crtc_state; if (!CAN_PSR(dev_priv) || !new_state->crtc || - dev_priv->psr.initially_probed) + !dev_priv->psr.force_mode_changed) return; intel_connector = to_intel_connector(connector); @@ -1545,5 +1549,18 @@ void intel_psr_atomic_check(struct drm_connector *connector, crtc_state = drm_atomic_get_new_crtc_state(new_state->state, new_state->crtc); crtc_state->mode_changed = true; - dev_priv->psr.initially_probed = true; +} + +void intel_psr_set_force_mode_changed(struct intel_dp *intel_dp) +{ + struct drm_i915_private *dev_priv; + + if (!intel_dp) + return; + + dev_priv = dp_to_i915(intel_dp); + if (!CAN_PSR(dev_priv) || intel_dp != dev_priv->psr.dp) + return; + + dev_priv->psr.force_mode_changed = true; } diff --git a/drivers/gpu/drm/i915/display/intel_psr.h b/drivers/gpu/drm/i915/display/intel_psr.h index c58a1d438808a7ca7869892be59de94da7bc853e..274fc6bb622122840de9eefe1e7c39d990253a6f 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.h +++ b/drivers/gpu/drm/i915/display/intel_psr.h @@ -40,5 +40,6 @@ bool intel_psr_enabled(struct intel_dp *intel_dp); void intel_psr_atomic_check(struct drm_connector *connector, struct drm_connector_state *old_state, struct drm_connector_state *new_state); +void intel_psr_set_force_mode_changed(struct intel_dp *intel_dp); #endif /* __INTEL_PSR_H__ */ diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index a2e57e62af30adc05e562ca734f3891ceda33fe2..151a1e8ae36abbc7cafea3c9aa9c4b7cb88014c4 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -565,6 +565,22 @@ static int __context_set_persistence(struct i915_gem_context *ctx, bool state) if (!(ctx->i915->caps.scheduler & I915_SCHEDULER_CAP_PREEMPTION)) return -ENODEV; + /* + * If the cancel fails, we then need to reset, cleanly! + * + * If the per-engine reset fails, all hope is lost! We resort + * to a full GPU reset in that unlikely case, but realistically + * if the engine could not reset, the full reset does not fare + * much better. The damage has been done. + * + * However, if we cannot reset an engine by itself, we cannot + * cleanup a hanging persistent context without causing + * colateral damage, and we should not pretend we can by + * exposing the interface. + */ + if (!intel_has_reset_engine(&ctx->i915->gt)) + return -ENODEV; + i915_gem_context_clear_persistence(ctx); } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index d5a0f5ae4a8ba3765ecdcdfd8933754696a2c16b..7643a30ba4cd03b512682d3efbf3838824ecea37 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -423,7 +423,8 @@ eb_validate_vma(struct i915_execbuffer *eb, if (unlikely(entry->flags & eb->invalid_flags)) return -EINVAL; - if (unlikely(entry->alignment && !is_power_of_2(entry->alignment))) + if (unlikely(entry->alignment && + !is_power_of_2_u64(entry->alignment))) return -EINVAL; /* @@ -1981,9 +1982,20 @@ static int __eb_parse(struct dma_fence_work *work) pw->trampoline); } +static void __eb_parse_release(struct dma_fence_work *work) +{ + struct eb_parse_work *pw = container_of(work, typeof(*pw), base); + + if (pw->trampoline) + i915_active_release(&pw->trampoline->active); + i915_active_release(&pw->shadow->active); + i915_active_release(&pw->batch->active); +} + static const struct dma_fence_work_ops eb_parse_ops = { .name = "eb_parse", .work = __eb_parse, + .release = __eb_parse_release, }; static int eb_parse_pipeline(struct i915_execbuffer *eb, @@ -1997,6 +2009,20 @@ static int eb_parse_pipeline(struct i915_execbuffer *eb, if (!pw) return -ENOMEM; + err = i915_active_acquire(&eb->batch->active); + if (err) + goto err_free; + + err = i915_active_acquire(&shadow->active); + if (err) + goto err_batch; + + if (trampoline) { + err = i915_active_acquire(&trampoline->active); + if (err) + goto err_shadow; + } + dma_fence_work_init(&pw->base, &eb_parse_ops); pw->engine = eb->engine; @@ -2006,7 +2032,9 @@ static int eb_parse_pipeline(struct i915_execbuffer *eb, pw->shadow = shadow; pw->trampoline = trampoline; - dma_resv_lock(pw->batch->resv, NULL); + err = dma_resv_lock_interruptible(pw->batch->resv, NULL); + if (err) + goto err_trampoline; err = dma_resv_reserve_shared(pw->batch->resv, 1); if (err) @@ -2034,6 +2062,14 @@ static int eb_parse_pipeline(struct i915_execbuffer *eb, err_batch_unlock: dma_resv_unlock(pw->batch->resv); +err_trampoline: + if (trampoline) + i915_active_release(&trampoline->active); +err_shadow: + i915_active_release(&shadow->active); +err_batch: + i915_active_release(&eb->batch->active); +err_free: kfree(pw); return err; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index b9fdac2f900364b70897eba0179b1a450f9bda82..0b6a442108de0ee14805438aacc59c919ce4e26e 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -455,10 +455,11 @@ static void i915_gem_object_release_mmap_gtt(struct drm_i915_gem_object *obj) void i915_gem_object_release_mmap_offset(struct drm_i915_gem_object *obj) { - struct i915_mmap_offset *mmo; + struct i915_mmap_offset *mmo, *mn; spin_lock(&obj->mmo.lock); - list_for_each_entry(mmo, &obj->mmo.offsets, offset) { + rbtree_postorder_for_each_entry_safe(mmo, mn, + &obj->mmo.offsets, offset) { /* * vma_node_unmap for GTT mmaps handled already in * __i915_gem_object_release_mmap_gtt @@ -487,6 +488,67 @@ void i915_gem_object_release_mmap(struct drm_i915_gem_object *obj) i915_gem_object_release_mmap_offset(obj); } +static struct i915_mmap_offset * +lookup_mmo(struct drm_i915_gem_object *obj, + enum i915_mmap_type mmap_type) +{ + struct rb_node *rb; + + spin_lock(&obj->mmo.lock); + rb = obj->mmo.offsets.rb_node; + while (rb) { + struct i915_mmap_offset *mmo = + rb_entry(rb, typeof(*mmo), offset); + + if (mmo->mmap_type == mmap_type) { + spin_unlock(&obj->mmo.lock); + return mmo; + } + + if (mmo->mmap_type < mmap_type) + rb = rb->rb_right; + else + rb = rb->rb_left; + } + spin_unlock(&obj->mmo.lock); + + return NULL; +} + +static struct i915_mmap_offset * +insert_mmo(struct drm_i915_gem_object *obj, struct i915_mmap_offset *mmo) +{ + struct rb_node *rb, **p; + + spin_lock(&obj->mmo.lock); + rb = NULL; + p = &obj->mmo.offsets.rb_node; + while (*p) { + struct i915_mmap_offset *pos; + + rb = *p; + pos = rb_entry(rb, typeof(*pos), offset); + + if (pos->mmap_type == mmo->mmap_type) { + spin_unlock(&obj->mmo.lock); + drm_vma_offset_remove(obj->base.dev->vma_offset_manager, + &mmo->vma_node); + kfree(mmo); + return pos; + } + + if (pos->mmap_type < mmo->mmap_type) + p = &rb->rb_right; + else + p = &rb->rb_left; + } + rb_link_node(&mmo->offset, rb, p); + rb_insert_color(&mmo->offset, &obj->mmo.offsets); + spin_unlock(&obj->mmo.lock); + + return mmo; +} + static struct i915_mmap_offset * mmap_offset_attach(struct drm_i915_gem_object *obj, enum i915_mmap_type mmap_type, @@ -496,20 +558,22 @@ mmap_offset_attach(struct drm_i915_gem_object *obj, struct i915_mmap_offset *mmo; int err; + mmo = lookup_mmo(obj, mmap_type); + if (mmo) + goto out; + mmo = kmalloc(sizeof(*mmo), GFP_KERNEL); if (!mmo) return ERR_PTR(-ENOMEM); mmo->obj = obj; - mmo->dev = obj->base.dev; - mmo->file = file; mmo->mmap_type = mmap_type; drm_vma_node_reset(&mmo->vma_node); - err = drm_vma_offset_add(mmo->dev->vma_offset_manager, &mmo->vma_node, - obj->base.size / PAGE_SIZE); + err = drm_vma_offset_add(obj->base.dev->vma_offset_manager, + &mmo->vma_node, obj->base.size / PAGE_SIZE); if (likely(!err)) - goto out; + goto insert; /* Attempt to reap some mmap space from dead objects */ err = intel_gt_retire_requests_timeout(&i915->gt, MAX_SCHEDULE_TIMEOUT); @@ -517,19 +581,17 @@ mmap_offset_attach(struct drm_i915_gem_object *obj, goto err; i915_gem_drain_freed_objects(i915); - err = drm_vma_offset_add(mmo->dev->vma_offset_manager, &mmo->vma_node, - obj->base.size / PAGE_SIZE); + err = drm_vma_offset_add(obj->base.dev->vma_offset_manager, + &mmo->vma_node, obj->base.size / PAGE_SIZE); if (err) goto err; +insert: + mmo = insert_mmo(obj, mmo); + GEM_BUG_ON(lookup_mmo(obj, mmap_type) != mmo); out: if (file) drm_vma_node_allow(&mmo->vma_node, file); - - spin_lock(&obj->mmo.lock); - list_add(&mmo->offset, &obj->mmo.offsets); - spin_unlock(&obj->mmo.lock); - return mmo; err: @@ -745,60 +807,43 @@ int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma) struct drm_vma_offset_node *node; struct drm_file *priv = filp->private_data; struct drm_device *dev = priv->minor->dev; + struct drm_i915_gem_object *obj = NULL; struct i915_mmap_offset *mmo = NULL; - struct drm_gem_object *obj = NULL; struct file *anon; if (drm_dev_is_unplugged(dev)) return -ENODEV; + rcu_read_lock(); drm_vma_offset_lock_lookup(dev->vma_offset_manager); node = drm_vma_offset_exact_lookup_locked(dev->vma_offset_manager, vma->vm_pgoff, vma_pages(vma)); - if (likely(node)) { - mmo = container_of(node, struct i915_mmap_offset, - vma_node); - /* - * In our dependency chain, the drm_vma_offset_node - * depends on the validity of the mmo, which depends on - * the gem object. However the only reference we have - * at this point is the mmo (as the parent of the node). - * Try to check if the gem object was at least cleared. - */ - if (!mmo || !mmo->obj) { - drm_vma_offset_unlock_lookup(dev->vma_offset_manager); - return -EINVAL; - } + if (node && drm_vma_node_is_allowed(node, priv)) { /* * Skip 0-refcnted objects as it is in the process of being * destroyed and will be invalid when the vma manager lock * is released. */ - obj = &mmo->obj->base; - if (!kref_get_unless_zero(&obj->refcount)) - obj = NULL; + mmo = container_of(node, struct i915_mmap_offset, vma_node); + obj = i915_gem_object_get_rcu(mmo->obj); } drm_vma_offset_unlock_lookup(dev->vma_offset_manager); + rcu_read_unlock(); if (!obj) - return -EINVAL; - - if (!drm_vma_node_is_allowed(node, priv)) { - drm_gem_object_put_unlocked(obj); - return -EACCES; - } + return node ? -EACCES : -EINVAL; - if (i915_gem_object_is_readonly(to_intel_bo(obj))) { + if (i915_gem_object_is_readonly(obj)) { if (vma->vm_flags & VM_WRITE) { - drm_gem_object_put_unlocked(obj); + i915_gem_object_put(obj); return -EINVAL; } vma->vm_flags &= ~VM_MAYWRITE; } - anon = mmap_singleton(to_i915(obj->dev)); + anon = mmap_singleton(to_i915(dev)); if (IS_ERR(anon)) { - drm_gem_object_put_unlocked(obj); + i915_gem_object_put(obj); return PTR_ERR(anon); } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c index 46bacc82ddc406b686d65bc8d7260988f0770b2a..5da9f9e534b94981c65e81ef6ba1f4eb5f634852 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c @@ -63,7 +63,7 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj, INIT_LIST_HEAD(&obj->lut_list); spin_lock_init(&obj->mmo.lock); - INIT_LIST_HEAD(&obj->mmo.offsets); + obj->mmo.offsets = RB_ROOT; init_rcu_head(&obj->rcu); @@ -100,8 +100,8 @@ void i915_gem_close_object(struct drm_gem_object *gem, struct drm_file *file) { struct drm_i915_gem_object *obj = to_intel_bo(gem); struct drm_i915_file_private *fpriv = file->driver_priv; + struct i915_mmap_offset *mmo, *mn; struct i915_lut_handle *lut, *ln; - struct i915_mmap_offset *mmo; LIST_HEAD(close); i915_gem_object_lock(obj); @@ -117,14 +117,8 @@ void i915_gem_close_object(struct drm_gem_object *gem, struct drm_file *file) i915_gem_object_unlock(obj); spin_lock(&obj->mmo.lock); - list_for_each_entry(mmo, &obj->mmo.offsets, offset) { - if (mmo->file != file) - continue; - - spin_unlock(&obj->mmo.lock); + rbtree_postorder_for_each_entry_safe(mmo, mn, &obj->mmo.offsets, offset) drm_vma_node_revoke(&mmo->vma_node, file); - spin_lock(&obj->mmo.lock); - } spin_unlock(&obj->mmo.lock); list_for_each_entry_safe(lut, ln, &close, obj_link) { @@ -203,12 +197,14 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915, i915_gem_object_release_mmap(obj); - list_for_each_entry_safe(mmo, mn, &obj->mmo.offsets, offset) { + rbtree_postorder_for_each_entry_safe(mmo, mn, + &obj->mmo.offsets, + offset) { drm_vma_offset_remove(obj->base.dev->vma_offset_manager, &mmo->vma_node); kfree(mmo); } - INIT_LIST_HEAD(&obj->mmo.offsets); + obj->mmo.offsets = RB_ROOT; GEM_BUG_ON(atomic_read(&obj->bind_count)); GEM_BUG_ON(obj->userfault_count); @@ -229,6 +225,7 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915, /* But keep the pointer alive for RCU-protected lookups */ call_rcu(&obj->rcu, __i915_gem_free_object_rcu); + cond_resched(); } intel_runtime_pm_put(&i915->runtime_pm, wakeref); } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h index db70a3306e5939e97907b3f2e3997fd82f760b14..9c86f2dea947b415de4524718c174adbc30f5e44 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h @@ -69,6 +69,15 @@ i915_gem_object_lookup_rcu(struct drm_file *file, u32 handle) return idr_find(&file->object_idr, handle); } +static inline struct drm_i915_gem_object * +i915_gem_object_get_rcu(struct drm_i915_gem_object *obj) +{ + if (obj && !kref_get_unless_zero(&obj->base.refcount)) + obj = NULL; + + return obj; +} + static inline struct drm_i915_gem_object * i915_gem_object_lookup(struct drm_file *file, u32 handle) { @@ -76,8 +85,7 @@ i915_gem_object_lookup(struct drm_file *file, u32 handle) rcu_read_lock(); obj = i915_gem_object_lookup_rcu(file, handle); - if (obj && !kref_get_unless_zero(&obj->base.refcount)) - obj = NULL; + obj = i915_gem_object_get_rcu(obj); rcu_read_unlock(); return obj; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h index 88e268633fdc742b559597073d954d89d33d2767..c2174da35bb0fdf3890af589440be127676df876 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -71,13 +71,11 @@ enum i915_mmap_type { }; struct i915_mmap_offset { - struct drm_device *dev; struct drm_vma_offset_node vma_node; struct drm_i915_gem_object *obj; - struct drm_file *file; enum i915_mmap_type mmap_type; - struct list_head offset; + struct rb_node offset; }; struct drm_i915_gem_object { @@ -137,7 +135,7 @@ struct drm_i915_gem_object { struct { spinlock_t lock; /* Protects access to mmo offsets */ - struct list_head offsets; + struct rb_root offsets; } mmo; I915_SELFTEST_DECLARE(struct list_head st_link); @@ -287,9 +285,6 @@ struct drm_i915_gem_object { void *gvt_info; }; - - /** for phys allocated objects */ - struct drm_dma_handle *phys_handle; }; static inline struct drm_i915_gem_object * diff --git a/drivers/gpu/drm/i915/gem/i915_gem_phys.c b/drivers/gpu/drm/i915/gem/i915_gem_phys.c index b1b7c1b3038aaa41b8bbdc1c5c7cdfef13d4e2d0..b07bb40edd5a3d8ad83fe9ed0d2b93b96f6c9ecd 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_phys.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_phys.c @@ -22,88 +22,87 @@ static int i915_gem_object_get_pages_phys(struct drm_i915_gem_object *obj) { struct address_space *mapping = obj->base.filp->f_mapping; - struct drm_dma_handle *phys; - struct sg_table *st; struct scatterlist *sg; - char *vaddr; + struct sg_table *st; + dma_addr_t dma; + void *vaddr; + void *dst; int i; - int err; if (WARN_ON(i915_gem_object_needs_bit17_swizzle(obj))) return -EINVAL; - /* Always aligning to the object size, allows a single allocation + /* + * Always aligning to the object size, allows a single allocation * to handle all possible callers, and given typical object sizes, * the alignment of the buddy allocation will naturally match. */ - phys = drm_pci_alloc(obj->base.dev, - roundup_pow_of_two(obj->base.size), - roundup_pow_of_two(obj->base.size)); - if (!phys) + vaddr = dma_alloc_coherent(&obj->base.dev->pdev->dev, + roundup_pow_of_two(obj->base.size), + &dma, GFP_KERNEL); + if (!vaddr) return -ENOMEM; - vaddr = phys->vaddr; + st = kmalloc(sizeof(*st), GFP_KERNEL); + if (!st) + goto err_pci; + + if (sg_alloc_table(st, 1, GFP_KERNEL)) + goto err_st; + + sg = st->sgl; + sg->offset = 0; + sg->length = obj->base.size; + + sg_assign_page(sg, (struct page *)vaddr); + sg_dma_address(sg) = dma; + sg_dma_len(sg) = obj->base.size; + + dst = vaddr; for (i = 0; i < obj->base.size / PAGE_SIZE; i++) { struct page *page; - char *src; + void *src; page = shmem_read_mapping_page(mapping, i); - if (IS_ERR(page)) { - err = PTR_ERR(page); - goto err_phys; - } + if (IS_ERR(page)) + goto err_st; src = kmap_atomic(page); - memcpy(vaddr, src, PAGE_SIZE); - drm_clflush_virt_range(vaddr, PAGE_SIZE); + memcpy(dst, src, PAGE_SIZE); + drm_clflush_virt_range(dst, PAGE_SIZE); kunmap_atomic(src); put_page(page); - vaddr += PAGE_SIZE; + dst += PAGE_SIZE; } intel_gt_chipset_flush(&to_i915(obj->base.dev)->gt); - st = kmalloc(sizeof(*st), GFP_KERNEL); - if (!st) { - err = -ENOMEM; - goto err_phys; - } - - if (sg_alloc_table(st, 1, GFP_KERNEL)) { - kfree(st); - err = -ENOMEM; - goto err_phys; - } - - sg = st->sgl; - sg->offset = 0; - sg->length = obj->base.size; - - sg_dma_address(sg) = phys->busaddr; - sg_dma_len(sg) = obj->base.size; - - obj->phys_handle = phys; - __i915_gem_object_set_pages(obj, st, sg->length); return 0; -err_phys: - drm_pci_free(obj->base.dev, phys); - - return err; +err_st: + kfree(st); +err_pci: + dma_free_coherent(&obj->base.dev->pdev->dev, + roundup_pow_of_two(obj->base.size), + vaddr, dma); + return -ENOMEM; } static void i915_gem_object_put_pages_phys(struct drm_i915_gem_object *obj, struct sg_table *pages) { + dma_addr_t dma = sg_dma_address(pages->sgl); + void *vaddr = sg_page(pages->sgl); + __i915_gem_object_release_shmem(obj, pages, false); if (obj->mm.dirty) { struct address_space *mapping = obj->base.filp->f_mapping; - char *vaddr = obj->phys_handle->vaddr; + void *src = vaddr; int i; for (i = 0; i < obj->base.size / PAGE_SIZE; i++) { @@ -115,15 +114,16 @@ i915_gem_object_put_pages_phys(struct drm_i915_gem_object *obj, continue; dst = kmap_atomic(page); - drm_clflush_virt_range(vaddr, PAGE_SIZE); - memcpy(dst, vaddr, PAGE_SIZE); + drm_clflush_virt_range(src, PAGE_SIZE); + memcpy(dst, src, PAGE_SIZE); kunmap_atomic(dst); set_page_dirty(page); if (obj->mm.madv == I915_MADV_WILLNEED) mark_page_accessed(page); put_page(page); - vaddr += PAGE_SIZE; + + src += PAGE_SIZE; } obj->mm.dirty = false; } @@ -131,7 +131,9 @@ i915_gem_object_put_pages_phys(struct drm_i915_gem_object *obj, sg_free_table(pages); kfree(pages); - drm_pci_free(obj->base.dev, obj->phys_handle); + dma_free_coherent(&obj->base.dev->pdev->dev, + roundup_pow_of_two(obj->base.size), + vaddr, dma); } static void phys_release(struct drm_i915_gem_object *obj) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c index f7e4b39c734f36e76d79d0ae2c250d709fb7ba8d..59b387ade49c079a1c605cb8754a617186ed3407 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c @@ -256,8 +256,7 @@ unsigned long i915_gem_shrink_all(struct drm_i915_private *i915) with_intel_runtime_pm(&i915->runtime_pm, wakeref) { freed = i915_gem_shrink(i915, -1UL, NULL, I915_SHRINK_BOUND | - I915_SHRINK_UNBOUND | - I915_SHRINK_ACTIVE); + I915_SHRINK_UNBOUND); } return freed; @@ -336,7 +335,6 @@ i915_gem_shrinker_oom(struct notifier_block *nb, unsigned long event, void *ptr) freed_pages = 0; with_intel_runtime_pm(&i915->runtime_pm, wakeref) freed_pages += i915_gem_shrink(i915, -1UL, NULL, - I915_SHRINK_ACTIVE | I915_SHRINK_BOUND | I915_SHRINK_UNBOUND | I915_SHRINK_WRITEBACK); diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c index ef7c74cff28a646ad0b71b6223f29fcbd62ad6bd..43912e9b683dccb1a43dae9f5a31890baedd831e 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c @@ -570,7 +570,7 @@ static bool assert_mmap_offset(struct drm_i915_private *i915, obj = i915_gem_object_create_internal(i915, size); if (IS_ERR(obj)) - return PTR_ERR(obj); + return false; mmo = mmap_offset_attach(obj, I915_MMAP_OFFSET_GTT, NULL); i915_gem_object_put(obj); diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c index 0ba524a414c68d66558afe24674613a2229451ee..cbad7fe722cebb840f50c46ad73f9f1c63c49c78 100644 --- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c @@ -136,6 +136,9 @@ static void add_retire(struct intel_breadcrumbs *b, struct intel_timeline *tl) struct intel_engine_cs *engine = container_of(b, struct intel_engine_cs, breadcrumbs); + if (unlikely(intel_engine_is_virtual(engine))) + engine = intel_virtual_engine_get_sibling(engine, 0); + intel_engine_add_retire(engine, tl); } diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index 23137b2a8689741e64276f3a88eeb4102d0693bd..57e8a051ddc2abbee284e3efd2f0c80f1e3e40ff 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -67,21 +67,18 @@ static int intel_context_active_acquire(struct intel_context *ce) { int err; - err = i915_active_acquire(&ce->active); - if (err) - return err; + __i915_active_acquire(&ce->active); + + if (intel_context_is_barrier(ce)) + return 0; /* Preallocate tracking nodes */ - if (!intel_context_is_barrier(ce)) { - err = i915_active_acquire_preallocate_barrier(&ce->active, - ce->engine); - if (err) { - i915_active_release(&ce->active); - return err; - } - } + err = i915_active_acquire_preallocate_barrier(&ce->active, + ce->engine); + if (err) + i915_active_release(&ce->active); - return 0; + return err; } static void intel_context_active_release(struct intel_context *ce) @@ -101,13 +98,19 @@ int __intel_context_do_pin(struct intel_context *ce) return err; } - if (mutex_lock_interruptible(&ce->pin_mutex)) - return -EINTR; + err = i915_active_acquire(&ce->active); + if (err) + return err; + + if (mutex_lock_interruptible(&ce->pin_mutex)) { + err = -EINTR; + goto out_release; + } - if (likely(!atomic_read(&ce->pin_count))) { + if (likely(!atomic_add_unless(&ce->pin_count, 1, 0))) { err = intel_context_active_acquire(ce); if (unlikely(err)) - goto err; + goto out_unlock; err = ce->ops->pin(ce); if (unlikely(err)) @@ -117,18 +120,19 @@ int __intel_context_do_pin(struct intel_context *ce) ce->ring->head, ce->ring->tail); smp_mb__before_atomic(); /* flush pin before it is visible */ + atomic_inc(&ce->pin_count); } - atomic_inc(&ce->pin_count); GEM_BUG_ON(!intel_context_is_pinned(ce)); /* no overflow! */ - - mutex_unlock(&ce->pin_mutex); - return 0; + GEM_BUG_ON(i915_active_is_idle(&ce->active)); + goto out_unlock; err_active: intel_context_active_release(ce); -err: +out_unlock: mutex_unlock(&ce->pin_mutex); +out_release: + i915_active_release(&ce->active); return err; } diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index f451ef376548e19207233333d4231fcab2364624..06ff7695fa290b8ad68c4a9a7f2667eb41aed8a5 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -671,6 +671,7 @@ void intel_engine_init_active(struct intel_engine_cs *engine, unsigned int subclass) { INIT_LIST_HEAD(&engine->active.requests); + INIT_LIST_HEAD(&engine->active.hold); spin_lock_init(&engine->active.lock); lockdep_set_subclass(&engine->active.lock, subclass); @@ -1422,6 +1423,17 @@ static void print_request_ring(struct drm_printer *m, struct i915_request *rq) } } +static unsigned long list_count(struct list_head *list) +{ + struct list_head *pos; + unsigned long count = 0; + + list_for_each(pos, list) + count++; + + return count; +} + void intel_engine_dump(struct intel_engine_cs *engine, struct drm_printer *m, const char *header, ...) @@ -1491,6 +1503,7 @@ void intel_engine_dump(struct intel_engine_cs *engine, hexdump(m, rq->context->lrc_reg_state, PAGE_SIZE); } } + drm_printf(m, "\tOn hold?: %lu\n", list_count(&engine->active.hold)); spin_unlock_irqrestore(&engine->active.lock, flags); drm_printf(m, "\tMMIO base: 0x%08x\n", engine->mmio_base); diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index 350da59e605b768978008d80187baeb09d8d0f2c..92be41a6903c0c6991c3e9d43ff61d5ca94f84e3 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -295,6 +295,7 @@ struct intel_engine_cs { struct { spinlock_t lock; struct list_head requests; + struct list_head hold; /* ready requests, but on hold */ } active; struct llist_head barrier_tasks; diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c index 7ef1d37970f6d4942d3ec2d1028f2e4d9467a8f1..24c99d0838af6e23e7eb6295139b852d02ec538c 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c @@ -99,6 +99,9 @@ static bool add_retire(struct intel_engine_cs *engine, void intel_engine_add_retire(struct intel_engine_cs *engine, struct intel_timeline *tl) { + /* We don't deal well with the engine disappearing beneath us */ + GEM_BUG_ON(intel_engine_is_virtual(engine)); + if (add_retire(engine, tl)) schedule_work(&engine->retire_work); } @@ -144,24 +147,32 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout) fence = i915_active_fence_get(&tl->last_request); if (fence) { + mutex_unlock(&tl->mutex); + timeout = dma_fence_wait_timeout(fence, interruptible, timeout); dma_fence_put(fence); + + /* Retirement is best effort */ + if (!mutex_trylock(&tl->mutex)) { + active_count++; + goto out_active; + } } } if (!retire_requests(tl) || flush_submission(gt)) active_count++; + mutex_unlock(&tl->mutex); - spin_lock(&timelines->lock); +out_active: spin_lock(&timelines->lock); - /* Resume iteration after dropping lock */ + /* Resume list iteration after reacquiring spinlock */ list_safe_reset_next(tl, tn, link); if (atomic_dec_and_test(&tl->active_count)) list_del(&tl->link); - mutex_unlock(&tl->mutex); /* Defer the final release to after the spinlock */ if (refcount_dec_and_test(&tl->kref.refcount)) { diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 0cf0f6fae675ab1975639a0774417a393dc9313b..31455eceeb0c6f7ece2b09f8188b1c2a7c3350eb 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -237,7 +237,8 @@ static void execlists_init_reg_state(u32 *reg_state, bool close); static void __execlists_update_reg_state(const struct intel_context *ce, - const struct intel_engine_cs *engine); + const struct intel_engine_cs *engine, + u32 head); static void mark_eio(struct i915_request *rq) { @@ -985,6 +986,8 @@ __unwind_incomplete_requests(struct intel_engine_cs *engine) GEM_BUG_ON(RB_EMPTY_ROOT(&engine->execlists.queue.rb_root)); list_move(&rq->sched.link, pl); + set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags); + active = rq; } else { struct intel_engine_cs *owner = rq->context->engine; @@ -1184,12 +1187,11 @@ static void reset_active(struct i915_request *rq, head = rq->tail; else head = active_request(ce->timeline, rq)->head; - ce->ring->head = intel_ring_wrap(ce->ring, head); - intel_ring_update_space(ce->ring); + head = intel_ring_wrap(ce->ring, head); /* Scrub the context image to prevent replaying the previous batch */ restore_default_state(ce, engine); - __execlists_update_reg_state(ce, engine); + __execlists_update_reg_state(ce, engine, head); /* We've switched away, so this should be a no-op, but intent matters */ ce->lrc_desc |= CTX_DESC_FORCE_RESTORE; @@ -1319,7 +1321,7 @@ static u64 execlists_update_context(struct i915_request *rq) { struct intel_context *ce = rq->context; u64 desc = ce->lrc_desc; - u32 tail; + u32 tail, prev; /* * WaIdleLiteRestore:bdw,skl @@ -1332,9 +1334,15 @@ static u64 execlists_update_context(struct i915_request *rq) * subsequent resubmissions (for lite restore). Should that fail us, * and we try and submit the same tail again, force the context * reload. + * + * If we need to return to a preempted context, we need to skip the + * lite-restore and force it to reload the RING_TAIL. Otherwise, the + * HW has a tendency to ignore us rewinding the TAIL to the end of + * an earlier request. */ tail = intel_ring_set_tail(rq->ring, rq->tail); - if (unlikely(ce->lrc_reg_state[CTX_RING_TAIL] == tail)) + prev = ce->lrc_reg_state[CTX_RING_TAIL]; + if (unlikely(intel_ring_direction(rq->ring, tail, prev) <= 0)) desc |= CTX_DESC_FORCE_RESTORE; ce->lrc_reg_state[CTX_RING_TAIL] = tail; rq->tail = rq->wa_tail; @@ -1535,7 +1543,8 @@ static bool can_merge_rq(const struct i915_request *prev, return true; if (unlikely((prev->fence.flags ^ next->fence.flags) & - (I915_FENCE_FLAG_NOPREEMPT | I915_FENCE_FLAG_SENTINEL))) + (BIT(I915_FENCE_FLAG_NOPREEMPT) | + BIT(I915_FENCE_FLAG_SENTINEL)))) return false; if (!can_merge_ctx(prev->context, next->context)) @@ -1591,16 +1600,10 @@ static void virtual_xfer_breadcrumbs(struct virtual_engine *ve, spin_unlock(&old->breadcrumbs.irq_lock); } -static struct i915_request * -last_active(const struct intel_engine_execlists *execlists) -{ - struct i915_request * const *last = READ_ONCE(execlists->active); - - while (*last && i915_request_completed(*last)) - last++; - - return *last; -} +#define for_each_waiter(p__, rq__) \ + list_for_each_entry_lockless(p__, \ + &(rq__)->sched.waiters_list, \ + wait_link) static void defer_request(struct i915_request *rq, struct list_head * const pl) { @@ -1619,7 +1622,7 @@ static void defer_request(struct i915_request *rq, struct list_head * const pl) GEM_BUG_ON(i915_request_is_active(rq)); list_move_tail(&rq->sched.link, pl); - list_for_each_entry(p, &rq->sched.waiters_list, wait_link) { + for_each_waiter(p, rq) { struct i915_request *w = container_of(p->waiter, typeof(*w), sched); @@ -1632,8 +1635,8 @@ static void defer_request(struct i915_request *rq, struct list_head * const pl) !i915_request_completed(rq)); GEM_BUG_ON(i915_request_is_active(w)); - if (list_empty(&w->sched.link)) - continue; /* Not yet submitted; unready */ + if (!i915_request_is_ready(w)) + continue; if (rq_prio(w) < rq_prio(rq)) continue; @@ -1665,11 +1668,9 @@ need_timeslice(struct intel_engine_cs *engine, const struct i915_request *rq) if (!intel_engine_has_timeslices(engine)) return false; - if (list_is_last(&rq->sched.link, &engine->active.requests)) - return false; - - hint = max(rq_prio(list_next_entry(rq, sched.link)), - engine->execlists.queue_priority_hint); + hint = engine->execlists.queue_priority_hint; + if (!list_is_last(&rq->sched.link, &engine->active.requests)) + hint = max(hint, rq_prio(list_next_entry(rq, sched.link))); return hint >= effective_prio(rq); } @@ -1711,16 +1712,26 @@ static void set_timeslice(struct intel_engine_cs *engine) set_timer_ms(&engine->execlists.timer, active_timeslice(engine)); } +static void start_timeslice(struct intel_engine_cs *engine) +{ + struct intel_engine_execlists *execlists = &engine->execlists; + + execlists->switch_priority_hint = execlists->queue_priority_hint; + + if (timer_pending(&execlists->timer)) + return; + + set_timer_ms(&execlists->timer, timeslice(engine)); +} + static void record_preemption(struct intel_engine_execlists *execlists) { (void)I915_SELFTEST_ONLY(execlists->preempt_hang.count++); } -static unsigned long active_preempt_timeout(struct intel_engine_cs *engine) +static unsigned long active_preempt_timeout(struct intel_engine_cs *engine, + const struct i915_request *rq) { - struct i915_request *rq; - - rq = last_active(&engine->execlists); if (!rq) return 0; @@ -1731,13 +1742,14 @@ static unsigned long active_preempt_timeout(struct intel_engine_cs *engine) return READ_ONCE(engine->props.preempt_timeout_ms); } -static void set_preempt_timeout(struct intel_engine_cs *engine) +static void set_preempt_timeout(struct intel_engine_cs *engine, + const struct i915_request *rq) { if (!intel_engine_has_preempt_reset(engine)) return; set_timer_ms(&engine->execlists.preempt, - active_preempt_timeout(engine)); + active_preempt_timeout(engine, rq)); } static inline void clear_ports(struct i915_request **ports, int count) @@ -1750,6 +1762,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine) struct intel_engine_execlists * const execlists = &engine->execlists; struct i915_request **port = execlists->pending; struct i915_request ** const last_port = port + execlists->port_mask; + struct i915_request * const *active; struct i915_request *last; struct rb_node *rb; bool submit = false; @@ -1804,7 +1817,10 @@ static void execlists_dequeue(struct intel_engine_cs *engine) * i.e. we will retrigger preemption following the ack in case * of trouble. */ - last = last_active(execlists); + active = READ_ONCE(execlists->active); + while ((last = *active) && i915_request_completed(last)) + active++; + if (last) { if (need_preempt(engine, last, rb)) { ENGINE_TRACE(engine, @@ -1831,14 +1847,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine) */ __unwind_incomplete_requests(engine); - /* - * If we need to return to the preempted context, we - * need to skip the lite-restore and force it to - * reload the RING_TAIL. Otherwise, the HW has a - * tendency to ignore us rewinding the TAIL to the - * end of an earlier request. - */ - last->context->lrc_desc |= CTX_DESC_FORCE_RESTORE; last = NULL; } else if (need_timeslice(engine, last) && timer_expired(&engine->execlists.timer)) { @@ -1882,11 +1890,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine) * Even if ELSP[1] is occupied and not worthy * of timeslices, our queue might be. */ - if (!execlists->timer.expires && - need_timeslice(engine, last)) - set_timer_ms(&execlists->timer, - timeslice(engine)); - + start_timeslice(engine); return; } } @@ -1921,7 +1925,8 @@ static void execlists_dequeue(struct intel_engine_cs *engine) if (last && !can_merge_rq(last, rq)) { spin_unlock(&ve->base.active.lock); - return; /* leave this for another */ + start_timeslice(engine); + return; /* leave this for another sibling */ } ENGINE_TRACE(engine, @@ -2097,7 +2102,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine) * Skip if we ended up with exactly the same set of requests, * e.g. trying to timeslice a pair of ordered contexts */ - if (!memcmp(execlists->active, execlists->pending, + if (!memcmp(active, execlists->pending, (port - execlists->pending + 1) * sizeof(*port))) { do execlists_schedule_out(fetch_and_zero(port)); @@ -2108,7 +2113,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine) clear_ports(port + 1, last_port - port); execlists_submit_ports(engine); - set_preempt_timeout(engine); + set_preempt_timeout(engine, *active); } else { skip_submit: ring_set_paused(engine, 0); @@ -2351,6 +2356,310 @@ static void __execlists_submission_tasklet(struct intel_engine_cs *const engine) } } +static void __execlists_hold(struct i915_request *rq) +{ + LIST_HEAD(list); + + do { + struct i915_dependency *p; + + if (i915_request_is_active(rq)) + __i915_request_unsubmit(rq); + + RQ_TRACE(rq, "on hold\n"); + clear_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags); + list_move_tail(&rq->sched.link, &rq->engine->active.hold); + i915_request_set_hold(rq); + + list_for_each_entry(p, &rq->sched.waiters_list, wait_link) { + struct i915_request *w = + container_of(p->waiter, typeof(*w), sched); + + /* Leave semaphores spinning on the other engines */ + if (w->engine != rq->engine) + continue; + + if (!i915_request_is_ready(w)) + continue; + + if (i915_request_completed(w)) + continue; + + if (i915_request_on_hold(rq)) + continue; + + list_move_tail(&w->sched.link, &list); + } + + rq = list_first_entry_or_null(&list, typeof(*rq), sched.link); + } while (rq); +} + +static bool execlists_hold(struct intel_engine_cs *engine, + struct i915_request *rq) +{ + spin_lock_irq(&engine->active.lock); + + if (i915_request_completed(rq)) { /* too late! */ + rq = NULL; + goto unlock; + } + + if (rq->engine != engine) { /* preempted virtual engine */ + struct virtual_engine *ve = to_virtual_engine(rq->engine); + + /* + * intel_context_inflight() is only protected by virtue + * of process_csb() being called only by the tasklet (or + * directly from inside reset while the tasklet is suspended). + * Assert that neither of those are allowed to run while we + * poke at the request queues. + */ + GEM_BUG_ON(!reset_in_progress(&engine->execlists)); + + /* + * An unsubmitted request along a virtual engine will + * remain on the active (this) engine until we are able + * to process the context switch away (and so mark the + * context as no longer in flight). That cannot have happened + * yet, otherwise we would not be hanging! + */ + spin_lock(&ve->base.active.lock); + GEM_BUG_ON(intel_context_inflight(rq->context) != engine); + GEM_BUG_ON(ve->request != rq); + ve->request = NULL; + spin_unlock(&ve->base.active.lock); + i915_request_put(rq); + + rq->engine = engine; + } + + /* + * Transfer this request onto the hold queue to prevent it + * being resumbitted to HW (and potentially completed) before we have + * released it. Since we may have already submitted following + * requests, we need to remove those as well. + */ + GEM_BUG_ON(i915_request_on_hold(rq)); + GEM_BUG_ON(rq->engine != engine); + __execlists_hold(rq); + +unlock: + spin_unlock_irq(&engine->active.lock); + return rq; +} + +static bool hold_request(const struct i915_request *rq) +{ + struct i915_dependency *p; + + /* + * If one of our ancestors is on hold, we must also be on hold, + * otherwise we will bypass it and execute before it. + */ + list_for_each_entry(p, &rq->sched.signalers_list, signal_link) { + const struct i915_request *s = + container_of(p->signaler, typeof(*s), sched); + + if (s->engine != rq->engine) + continue; + + if (i915_request_on_hold(s)) + return true; + } + + return false; +} + +static void __execlists_unhold(struct i915_request *rq) +{ + LIST_HEAD(list); + + do { + struct i915_dependency *p; + + GEM_BUG_ON(!i915_request_on_hold(rq)); + GEM_BUG_ON(!i915_sw_fence_signaled(&rq->submit)); + + i915_request_clear_hold(rq); + list_move_tail(&rq->sched.link, + i915_sched_lookup_priolist(rq->engine, + rq_prio(rq))); + set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags); + RQ_TRACE(rq, "hold release\n"); + + /* Also release any children on this engine that are ready */ + list_for_each_entry(p, &rq->sched.waiters_list, wait_link) { + struct i915_request *w = + container_of(p->waiter, typeof(*w), sched); + + if (w->engine != rq->engine) + continue; + + if (!i915_request_on_hold(rq)) + continue; + + /* Check that no other parents are also on hold */ + if (hold_request(rq)) + continue; + + list_move_tail(&w->sched.link, &list); + } + + rq = list_first_entry_or_null(&list, typeof(*rq), sched.link); + } while (rq); +} + +static void execlists_unhold(struct intel_engine_cs *engine, + struct i915_request *rq) +{ + spin_lock_irq(&engine->active.lock); + + /* + * Move this request back to the priority queue, and all of its + * children and grandchildren that were suspended along with it. + */ + __execlists_unhold(rq); + + if (rq_prio(rq) > engine->execlists.queue_priority_hint) { + engine->execlists.queue_priority_hint = rq_prio(rq); + tasklet_hi_schedule(&engine->execlists.tasklet); + } + + spin_unlock_irq(&engine->active.lock); +} + +struct execlists_capture { + struct work_struct work; + struct i915_request *rq; + struct i915_gpu_coredump *error; +}; + +static void execlists_capture_work(struct work_struct *work) +{ + struct execlists_capture *cap = container_of(work, typeof(*cap), work); + const gfp_t gfp = GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN; + struct intel_engine_cs *engine = cap->rq->engine; + struct intel_gt_coredump *gt = cap->error->gt; + struct intel_engine_capture_vma *vma; + + /* Compress all the objects attached to the request, slow! */ + vma = intel_engine_coredump_add_request(gt->engine, cap->rq, gfp); + if (vma) { + struct i915_vma_compress *compress = + i915_vma_capture_prepare(gt); + + intel_engine_coredump_add_vma(gt->engine, vma, compress); + i915_vma_capture_finish(gt, compress); + } + + gt->simulated = gt->engine->simulated; + cap->error->simulated = gt->simulated; + + /* Publish the error state, and announce it to the world */ + i915_error_state_store(cap->error); + i915_gpu_coredump_put(cap->error); + + /* Return this request and all that depend upon it for signaling */ + execlists_unhold(engine, cap->rq); + i915_request_put(cap->rq); + + kfree(cap); +} + +static struct execlists_capture *capture_regs(struct intel_engine_cs *engine) +{ + const gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN; + struct execlists_capture *cap; + + cap = kmalloc(sizeof(*cap), gfp); + if (!cap) + return NULL; + + cap->error = i915_gpu_coredump_alloc(engine->i915, gfp); + if (!cap->error) + goto err_cap; + + cap->error->gt = intel_gt_coredump_alloc(engine->gt, gfp); + if (!cap->error->gt) + goto err_gpu; + + cap->error->gt->engine = intel_engine_coredump_alloc(engine, gfp); + if (!cap->error->gt->engine) + goto err_gt; + + return cap; + +err_gt: + kfree(cap->error->gt); +err_gpu: + kfree(cap->error); +err_cap: + kfree(cap); + return NULL; +} + +static bool execlists_capture(struct intel_engine_cs *engine) +{ + struct execlists_capture *cap; + + if (!IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR)) + return true; + + /* + * We need to _quickly_ capture the engine state before we reset. + * We are inside an atomic section (softirq) here and we are delaying + * the forced preemption event. + */ + cap = capture_regs(engine); + if (!cap) + return true; + + cap->rq = execlists_active(&engine->execlists); + GEM_BUG_ON(!cap->rq); + + rcu_read_lock(); + cap->rq = active_request(cap->rq->context->timeline, cap->rq); + cap->rq = i915_request_get_rcu(cap->rq); + rcu_read_unlock(); + if (!cap->rq) + goto err_free; + + /* + * Remove the request from the execlists queue, and take ownership + * of the request. We pass it to our worker who will _slowly_ compress + * all the pages the _user_ requested for debugging their batch, after + * which we return it to the queue for signaling. + * + * By removing them from the execlists queue, we also remove the + * requests from being processed by __unwind_incomplete_requests() + * during the intel_engine_reset(), and so they will *not* be replayed + * afterwards. + * + * Note that because we have not yet reset the engine at this point, + * it is possible for the request that we have identified as being + * guilty, did in fact complete and we will then hit an arbitration + * point allowing the outstanding preemption to succeed. The likelihood + * of that is very low (as capturing of the engine registers should be + * fast enough to run inside an irq-off atomic section!), so we will + * simply hold that request accountable for being non-preemptible + * long enough to force the reset. + */ + if (!execlists_hold(engine, cap->rq)) + goto err_rq; + + INIT_WORK(&cap->work, execlists_capture_work); + schedule_work(&cap->work); + return true; + +err_rq: + i915_request_put(cap->rq); +err_free: + i915_gpu_coredump_put(cap->error); + kfree(cap); + return false; +} + static noinline void preempt_reset(struct intel_engine_cs *engine) { const unsigned int bit = I915_RESET_ENGINE + engine->id; @@ -2368,7 +2677,12 @@ static noinline void preempt_reset(struct intel_engine_cs *engine) ENGINE_TRACE(engine, "preempt timeout %lu+%ums\n", READ_ONCE(engine->props.preempt_timeout_ms), jiffies_to_msecs(jiffies - engine->execlists.preempt.expires)); - intel_engine_reset(engine, "preemption time out"); + + ring_set_paused(engine, 1); /* Freeze the current request in place */ + if (execlists_capture(engine)) + intel_engine_reset(engine, "preemption time out"); + else + ring_set_paused(engine, 0); tasklet_enable(&engine->execlists.tasklet); clear_and_wake_up_bit(bit, lock); @@ -2430,11 +2744,12 @@ static void execlists_preempt(struct timer_list *timer) } static void queue_request(struct intel_engine_cs *engine, - struct i915_sched_node *node, - int prio) + struct i915_request *rq) { - GEM_BUG_ON(!list_empty(&node->link)); - list_add_tail(&node->link, i915_sched_lookup_priolist(engine, prio)); + GEM_BUG_ON(!list_empty(&rq->sched.link)); + list_add_tail(&rq->sched.link, + i915_sched_lookup_priolist(engine, rq_prio(rq))); + set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags); } static void __submit_queue_imm(struct intel_engine_cs *engine) @@ -2462,6 +2777,13 @@ static void submit_queue(struct intel_engine_cs *engine, __submit_queue_imm(engine); } +static bool ancestor_on_hold(const struct intel_engine_cs *engine, + const struct i915_request *rq) +{ + GEM_BUG_ON(i915_request_on_hold(rq)); + return !list_empty(&engine->active.hold) && hold_request(rq); +} + static void execlists_submit_request(struct i915_request *request) { struct intel_engine_cs *engine = request->engine; @@ -2470,12 +2792,17 @@ static void execlists_submit_request(struct i915_request *request) /* Will be called from irq-context when using foreign fences. */ spin_lock_irqsave(&engine->active.lock, flags); - queue_request(engine, &request->sched, rq_prio(request)); + if (unlikely(ancestor_on_hold(engine, request))) { + list_add_tail(&request->sched.link, &engine->active.hold); + i915_request_set_hold(request); + } else { + queue_request(engine, request); - GEM_BUG_ON(RB_EMPTY_ROOT(&engine->execlists.queue.rb_root)); - GEM_BUG_ON(list_empty(&request->sched.link)); + GEM_BUG_ON(RB_EMPTY_ROOT(&engine->execlists.queue.rb_root)); + GEM_BUG_ON(list_empty(&request->sched.link)); - submit_queue(engine, request); + submit_queue(engine, request); + } spin_unlock_irqrestore(&engine->active.lock, flags); } @@ -2531,21 +2858,21 @@ static void execlists_context_unpin(struct intel_context *ce) ce->engine); i915_gem_object_unpin_map(ce->state->obj); - intel_ring_reset(ce->ring, ce->ring->tail); } static void __execlists_update_reg_state(const struct intel_context *ce, - const struct intel_engine_cs *engine) + const struct intel_engine_cs *engine, + u32 head) { struct intel_ring *ring = ce->ring; u32 *regs = ce->lrc_reg_state; - GEM_BUG_ON(!intel_ring_offset_valid(ring, ring->head)); + GEM_BUG_ON(!intel_ring_offset_valid(ring, head)); GEM_BUG_ON(!intel_ring_offset_valid(ring, ring->tail)); regs[CTX_RING_START] = i915_ggtt_offset(ring->vma); - regs[CTX_RING_HEAD] = ring->head; + regs[CTX_RING_HEAD] = head; regs[CTX_RING_TAIL] = ring->tail; /* RPCS */ @@ -2574,7 +2901,7 @@ __execlists_context_pin(struct intel_context *ce, ce->lrc_desc = lrc_descriptor(ce, engine) | CTX_DESC_FORCE_RESTORE; ce->lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE; - __execlists_update_reg_state(ce, engine); + __execlists_update_reg_state(ce, engine, ce->ring->tail); return 0; } @@ -2615,7 +2942,7 @@ static void execlists_context_reset(struct intel_context *ce) /* Scrub away the garbage */ execlists_init_reg_state(ce->lrc_reg_state, ce, ce->engine, ce->ring, true); - __execlists_update_reg_state(ce, ce->engine); + __execlists_update_reg_state(ce, ce->engine, ce->ring->tail); ce->lrc_desc |= CTX_DESC_FORCE_RESTORE; } @@ -3170,6 +3497,7 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled) struct intel_engine_execlists * const execlists = &engine->execlists; struct intel_context *ce; struct i915_request *rq; + u32 head; mb(); /* paranoia: read the CSB pointers from after the reset */ clflush(execlists->csb_write); @@ -3197,15 +3525,15 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled) if (i915_request_completed(rq)) { /* Idle context; tidy up the ring so we can restart afresh */ - ce->ring->head = intel_ring_wrap(ce->ring, rq->tail); + head = intel_ring_wrap(ce->ring, rq->tail); goto out_replay; } /* Context has requests still in-flight; it should not be idle! */ GEM_BUG_ON(i915_active_is_idle(&ce->active)); rq = active_request(ce->timeline, rq); - ce->ring->head = intel_ring_wrap(ce->ring, rq->head); - GEM_BUG_ON(ce->ring->head == ce->ring->tail); + head = intel_ring_wrap(ce->ring, rq->head); + GEM_BUG_ON(head == ce->ring->tail); /* * If this request hasn't started yet, e.g. it is waiting on a @@ -3250,10 +3578,9 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled) out_replay: ENGINE_TRACE(engine, "replay {head:%04x, tail:%04x}\n", - ce->ring->head, ce->ring->tail); - intel_ring_update_space(ce->ring); + head, ce->ring->tail); __execlists_reset_reg_state(ce, engine); - __execlists_update_reg_state(ce, engine); + __execlists_update_reg_state(ce, engine, head); ce->lrc_desc |= CTX_DESC_FORCE_RESTORE; /* paranoid: GPU was reset! */ unwind: @@ -3325,6 +3652,10 @@ static void execlists_reset_cancel(struct intel_engine_cs *engine) i915_priolist_free(p); } + /* On-hold requests will be flushed to timeline upon their release */ + list_for_each_entry(rq, &engine->active.hold, sched.link) + mark_eio(rq); + /* Cancel all attached virtual engines */ while ((rb = rb_first_cached(&execlists->virtual))) { struct virtual_engine *ve = @@ -3669,26 +4000,6 @@ static int gen12_emit_flush_render(struct i915_request *request, *cs++ = preparser_disable(false); intel_ring_advance(request, cs); - - /* - * Wa_1604544889:tgl - */ - if (IS_TGL_REVID(request->i915, TGL_REVID_A0, TGL_REVID_A0)) { - flags = 0; - flags |= PIPE_CONTROL_CS_STALL; - flags |= PIPE_CONTROL_HDC_PIPELINE_FLUSH; - - flags |= PIPE_CONTROL_STORE_DATA_INDEX; - flags |= PIPE_CONTROL_QW_WRITE; - - cs = intel_ring_begin(request, 6); - if (IS_ERR(cs)) - return PTR_ERR(cs); - - cs = gen8_emit_pipe_control(cs, flags, - LRC_PPHWSP_SCRATCH_ADDR); - intel_ring_advance(request, cs); - } } return 0; @@ -4892,10 +5203,7 @@ void intel_lr_context_reset(struct intel_engine_cs *engine, restore_default_state(ce, engine); /* Rerun the request; its payload has been neutered (if guilty). */ - ce->ring->head = head; - intel_ring_update_space(ce->ring); - - __execlists_update_reg_state(ce, engine); + __execlists_update_reg_state(ce, engine, head); } bool diff --git a/drivers/gpu/drm/i915/gt/intel_ring.c b/drivers/gpu/drm/i915/gt/intel_ring.c index 374b28f13ca0b4565adc32cd621ce0d69ad81d2c..6ff803f397c4d7015b6bfdb84785f5c6b355b0ea 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring.c +++ b/drivers/gpu/drm/i915/gt/intel_ring.c @@ -145,6 +145,7 @@ intel_engine_create_ring(struct intel_engine_cs *engine, int size) kref_init(&ring->ref); ring->size = size; + ring->wrap = BITS_PER_TYPE(ring->size) - ilog2(size); /* * Workaround an erratum on the i830 which causes a hang if diff --git a/drivers/gpu/drm/i915/gt/intel_ring.h b/drivers/gpu/drm/i915/gt/intel_ring.h index ea2839d9e044546957ea19133139c025375d9055..5bdce24994aa04ef80306a43e180c3599d81ee7c 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring.h +++ b/drivers/gpu/drm/i915/gt/intel_ring.h @@ -56,6 +56,14 @@ static inline u32 intel_ring_wrap(const struct intel_ring *ring, u32 pos) return pos & (ring->size - 1); } +static inline int intel_ring_direction(const struct intel_ring *ring, + u32 next, u32 prev) +{ + typecheck(typeof(ring->size), next); + typecheck(typeof(ring->size), prev); + return (next - prev) << ring->wrap; +} + static inline bool intel_ring_offset_valid(const struct intel_ring *ring, unsigned int pos) diff --git a/drivers/gpu/drm/i915/gt/intel_ring_types.h b/drivers/gpu/drm/i915/gt/intel_ring_types.h index d9f17f38e0cce9e2a05adf2fe7a1efc00b3c7709..1a189ea00fd8240bbdf4fcdd45822f7e6240d787 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring_types.h +++ b/drivers/gpu/drm/i915/gt/intel_ring_types.h @@ -39,12 +39,13 @@ struct intel_ring { */ atomic_t pin_count; - u32 head; - u32 tail; - u32 emit; + u32 head; /* updated during retire, loosely tracks RING_HEAD */ + u32 tail; /* updated on submission, used for RING_TAIL */ + u32 emit; /* updated during request construction */ u32 space; u32 size; + u32 wrap; u32 effective_size; }; diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c index 87716529cd2fe36999c0d933cac54ad3b0de8b73..d8d9f1179c2b048d10c963219ed729286b6080df 100644 --- a/drivers/gpu/drm/i915/gt/intel_timeline.c +++ b/drivers/gpu/drm/i915/gt/intel_timeline.c @@ -192,11 +192,15 @@ static void cacheline_release(struct intel_timeline_cacheline *cl) static void cacheline_free(struct intel_timeline_cacheline *cl) { + if (!i915_active_acquire_if_busy(&cl->active)) { + __idle_cacheline_free(cl); + return; + } + GEM_BUG_ON(ptr_test_bit(cl->vaddr, CACHELINE_FREE)); cl->vaddr = ptr_set_bit(cl->vaddr, CACHELINE_FREE); - if (i915_active_is_idle(&cl->active)) - __idle_cacheline_free(cl); + i915_active_release(&cl->active); } int intel_timeline_init(struct intel_timeline *timeline, diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index 4e292d4bf7b9d2aeaf79dccb8b99992b62a3c046..6c2f8462e0f38b2594b0470ff1d23488d8ab0394 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -575,24 +575,19 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine, static void tgl_ctx_workarounds_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) { - u32 val; - /* Wa_1409142259:tgl */ WA_SET_BIT_MASKED(GEN11_COMMON_SLICE_CHICKEN3, GEN12_DISABLE_CPS_AWARE_COLOR_PIPE); - /* Wa_1604555607:tgl */ - val = intel_uncore_read(engine->uncore, FF_MODE2); - val &= ~FF_MODE2_TDS_TIMER_MASK; - val |= FF_MODE2_TDS_TIMER_128; /* - * FIXME: FF_MODE2 register is not readable till TGL B0. We can - * enable verification of WA from the later steppings, which enables - * the read of FF_MODE2. + * Wa_1604555607:gen12 and Wa_1608008084:gen12 + * FF_MODE2 register will return the wrong value when read. The default + * value for this register is zero for all fields and there are no bit + * masks. So instead of doing a RMW we should just write the TDS timer + * value for Wa_1604555607. */ - wa_add(wal, FF_MODE2, FF_MODE2_TDS_TIMER_MASK, val, - IS_TGL_REVID(engine->i915, TGL_REVID_A0, TGL_REVID_A0) ? 0 : - FF_MODE2_TDS_TIMER_MASK); + wa_add(wal, FF_MODE2, FF_MODE2_TDS_TIMER_MASK, + FF_MODE2_TDS_TIMER_128, 0); } static void @@ -1534,15 +1529,34 @@ create_scratch(struct i915_address_space *vm, int count) return ERR_PTR(err); } +static const struct { + u32 start; + u32 end; +} mcr_ranges_gen8[] = { + { .start = 0x5500, .end = 0x55ff }, + { .start = 0x7000, .end = 0x7fff }, + { .start = 0x9400, .end = 0x97ff }, + { .start = 0xb000, .end = 0xb3ff }, + { .start = 0xe000, .end = 0xe7ff }, + {}, +}; + static bool mcr_range(struct drm_i915_private *i915, u32 offset) { + int i; + + if (INTEL_GEN(i915) < 8) + return false; + /* - * Registers in this range are affected by the MCR selector + * Registers in these ranges are affected by the MCR selector * which only controls CPU initiated MMIO. Routing does not * work for CS access so we cannot verify them on this path. */ - if (INTEL_GEN(i915) >= 8 && (offset >= 0xb000 && offset <= 0xb4ff)) - return true; + for (i = 0; mcr_ranges_gen8[i].start; i++) + if (offset >= mcr_ranges_gen8[i].start && + offset <= mcr_ranges_gen8[i].end) + return true; return false; } diff --git a/drivers/gpu/drm/i915/gt/mock_engine.c b/drivers/gpu/drm/i915/gt/mock_engine.c index a560b7eee2cd087b45e0e023f84eb971f594b902..f2806381733f55eacef5e5402711838c4682dfae 100644 --- a/drivers/gpu/drm/i915/gt/mock_engine.c +++ b/drivers/gpu/drm/i915/gt/mock_engine.c @@ -59,11 +59,26 @@ static struct intel_ring *mock_ring(struct intel_engine_cs *engine) ring->vaddr = (void *)(ring + 1); atomic_set(&ring->pin_count, 1); + ring->vma = i915_vma_alloc(); + if (!ring->vma) { + kfree(ring); + return NULL; + } + i915_active_init(&ring->vma->active, NULL, NULL); + intel_ring_update_space(ring); return ring; } +static void mock_ring_free(struct intel_ring *ring) +{ + i915_active_fini(&ring->vma->active); + i915_vma_free(ring->vma); + + kfree(ring); +} + static struct i915_request *first_request(struct mock_engine *engine) { return list_first_entry_or_null(&engine->hw_queue, @@ -121,7 +136,7 @@ static void mock_context_destroy(struct kref *ref) GEM_BUG_ON(intel_context_is_pinned(ce)); if (test_bit(CONTEXT_ALLOC_BIT, &ce->flags)) { - kfree(ce->ring); + mock_ring_free(ce->ring); mock_timeline_unpin(ce->timeline); } diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c index 15cda024e3e4577424a4c8580b03bfee2f3027d3..b292f8cbd0bf15eaa8a2f47b8b159069b852c40a 100644 --- a/drivers/gpu/drm/i915/gt/selftest_lrc.c +++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c @@ -186,7 +186,7 @@ static int live_unlite_restore(struct intel_gt *gt, int prio) } GEM_BUG_ON(!ce[1]->ring->size); intel_ring_reset(ce[1]->ring, ce[1]->ring->size / 2); - __execlists_update_reg_state(ce[1], engine); + __execlists_update_reg_state(ce[1], engine, ce[1]->ring->head); rq[0] = igt_spinner_create_request(&spin, ce[0], MI_ARB_CHECK); if (IS_ERR(rq[0])) { @@ -285,6 +285,107 @@ static int live_unlite_preempt(void *arg) return live_unlite_restore(arg, I915_USER_PRIORITY(I915_PRIORITY_MAX)); } +static int live_hold_reset(void *arg) +{ + struct intel_gt *gt = arg; + struct intel_engine_cs *engine; + enum intel_engine_id id; + struct igt_spinner spin; + int err = 0; + + /* + * In order to support offline error capture for fast preempt reset, + * we need to decouple the guilty request and ensure that it and its + * descendents are not executed while the capture is in progress. + */ + + if (!intel_has_reset_engine(gt)) + return 0; + + if (igt_spinner_init(&spin, gt)) + return -ENOMEM; + + for_each_engine(engine, gt, id) { + struct intel_context *ce; + unsigned long heartbeat; + struct i915_request *rq; + + ce = intel_context_create(engine); + if (IS_ERR(ce)) { + err = PTR_ERR(ce); + break; + } + + engine_heartbeat_disable(engine, &heartbeat); + + rq = igt_spinner_create_request(&spin, ce, MI_ARB_CHECK); + if (IS_ERR(rq)) { + err = PTR_ERR(rq); + goto out; + } + i915_request_add(rq); + + if (!igt_wait_for_spinner(&spin, rq)) { + intel_gt_set_wedged(gt); + err = -ETIME; + goto out; + } + + /* We have our request executing, now remove it and reset */ + + if (test_and_set_bit(I915_RESET_ENGINE + id, + >->reset.flags)) { + intel_gt_set_wedged(gt); + err = -EBUSY; + goto out; + } + tasklet_disable(&engine->execlists.tasklet); + + engine->execlists.tasklet.func(engine->execlists.tasklet.data); + GEM_BUG_ON(execlists_active(&engine->execlists) != rq); + + i915_request_get(rq); + execlists_hold(engine, rq); + GEM_BUG_ON(!i915_request_on_hold(rq)); + + intel_engine_reset(engine, NULL); + GEM_BUG_ON(rq->fence.error != -EIO); + + tasklet_enable(&engine->execlists.tasklet); + clear_and_wake_up_bit(I915_RESET_ENGINE + id, + >->reset.flags); + + /* Check that we do not resubmit the held request */ + if (!i915_request_wait(rq, 0, HZ / 5)) { + pr_err("%s: on hold request completed!\n", + engine->name); + i915_request_put(rq); + err = -EIO; + goto out; + } + GEM_BUG_ON(!i915_request_on_hold(rq)); + + /* But is resubmitted on release */ + execlists_unhold(engine, rq); + if (i915_request_wait(rq, 0, HZ / 5) < 0) { + pr_err("%s: held request did not complete!\n", + engine->name); + intel_gt_set_wedged(gt); + err = -ETIME; + } + i915_request_put(rq); + +out: + engine_heartbeat_enable(engine, heartbeat); + intel_context_put(ce); + if (err) + break; + } + + igt_spinner_fini(&spin); + return err; +} + static int emit_semaphore_chain(struct i915_request *rq, struct i915_vma *vma, int idx) { @@ -3309,12 +3410,168 @@ static int live_virtual_bond(void *arg) return 0; } +static int reset_virtual_engine(struct intel_gt *gt, + struct intel_engine_cs **siblings, + unsigned int nsibling) +{ + struct intel_engine_cs *engine; + struct intel_context *ve; + unsigned long *heartbeat; + struct igt_spinner spin; + struct i915_request *rq; + unsigned int n; + int err = 0; + + /* + * In order to support offline error capture for fast preempt reset, + * we need to decouple the guilty request and ensure that it and its + * descendents are not executed while the capture is in progress. + */ + + heartbeat = kmalloc_array(nsibling, sizeof(*heartbeat), GFP_KERNEL); + if (!heartbeat) + return -ENOMEM; + + if (igt_spinner_init(&spin, gt)) { + err = -ENOMEM; + goto out_free; + } + + ve = intel_execlists_create_virtual(siblings, nsibling); + if (IS_ERR(ve)) { + err = PTR_ERR(ve); + goto out_spin; + } + + for (n = 0; n < nsibling; n++) + engine_heartbeat_disable(siblings[n], &heartbeat[n]); + + rq = igt_spinner_create_request(&spin, ve, MI_ARB_CHECK); + if (IS_ERR(rq)) { + err = PTR_ERR(rq); + goto out_heartbeat; + } + i915_request_add(rq); + + if (!igt_wait_for_spinner(&spin, rq)) { + intel_gt_set_wedged(gt); + err = -ETIME; + goto out_heartbeat; + } + + engine = rq->engine; + GEM_BUG_ON(engine == ve->engine); + + /* Take ownership of the reset and tasklet */ + if (test_and_set_bit(I915_RESET_ENGINE + engine->id, + >->reset.flags)) { + intel_gt_set_wedged(gt); + err = -EBUSY; + goto out_heartbeat; + } + tasklet_disable(&engine->execlists.tasklet); + + engine->execlists.tasklet.func(engine->execlists.tasklet.data); + GEM_BUG_ON(execlists_active(&engine->execlists) != rq); + + /* Fake a preemption event; failed of course */ + spin_lock_irq(&engine->active.lock); + __unwind_incomplete_requests(engine); + spin_unlock_irq(&engine->active.lock); + GEM_BUG_ON(rq->engine != ve->engine); + + /* Reset the engine while keeping our active request on hold */ + execlists_hold(engine, rq); + GEM_BUG_ON(!i915_request_on_hold(rq)); + + intel_engine_reset(engine, NULL); + GEM_BUG_ON(rq->fence.error != -EIO); + + /* Release our grasp on the engine, letting CS flow again */ + tasklet_enable(&engine->execlists.tasklet); + clear_and_wake_up_bit(I915_RESET_ENGINE + engine->id, >->reset.flags); + + /* Check that we do not resubmit the held request */ + i915_request_get(rq); + if (!i915_request_wait(rq, 0, HZ / 5)) { + pr_err("%s: on hold request completed!\n", + engine->name); + intel_gt_set_wedged(gt); + err = -EIO; + goto out_rq; + } + GEM_BUG_ON(!i915_request_on_hold(rq)); + + /* But is resubmitted on release */ + execlists_unhold(engine, rq); + if (i915_request_wait(rq, 0, HZ / 5) < 0) { + pr_err("%s: held request did not complete!\n", + engine->name); + intel_gt_set_wedged(gt); + err = -ETIME; + } + +out_rq: + i915_request_put(rq); +out_heartbeat: + for (n = 0; n < nsibling; n++) + engine_heartbeat_enable(siblings[n], heartbeat[n]); + + intel_context_put(ve); +out_spin: + igt_spinner_fini(&spin); +out_free: + kfree(heartbeat); + return err; +} + +static int live_virtual_reset(void *arg) +{ + struct intel_gt *gt = arg; + struct intel_engine_cs *siblings[MAX_ENGINE_INSTANCE + 1]; + unsigned int class, inst; + + /* + * Check that we handle a reset event within a virtual engine. + * Only the physical engine is reset, but we have to check the flow + * of the virtual requests around the reset, and make sure it is not + * forgotten. + */ + + if (USES_GUC_SUBMISSION(gt->i915)) + return 0; + + if (!intel_has_reset_engine(gt)) + return 0; + + for (class = 0; class <= MAX_ENGINE_CLASS; class++) { + int nsibling, err; + + nsibling = 0; + for (inst = 0; inst <= MAX_ENGINE_INSTANCE; inst++) { + if (!gt->engine_class[class][inst]) + continue; + + siblings[nsibling++] = gt->engine_class[class][inst]; + } + if (nsibling < 2) + continue; + + err = reset_virtual_engine(gt, siblings, nsibling); + if (err) + return err; + } + + return 0; +} + int intel_execlists_live_selftests(struct drm_i915_private *i915) { static const struct i915_subtest tests[] = { SUBTEST(live_sanitycheck), SUBTEST(live_unlite_switch), SUBTEST(live_unlite_preempt), + SUBTEST(live_hold_reset), SUBTEST(live_timeslice_preempt), SUBTEST(live_timeslice_queue), SUBTEST(live_busywait_preempt), @@ -3333,6 +3590,7 @@ int intel_execlists_live_selftests(struct drm_i915_private *i915) SUBTEST(live_virtual_mask), SUBTEST(live_virtual_preserved), SUBTEST(live_virtual_bond), + SUBTEST(live_virtual_reset), }; if (!HAS_EXECLISTS(i915)) diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c index e1c313da6c00cfa7706d4fdd182f22cece527873..a62bdf9be68286da92ff8e994b36eeb50b9b5998 100644 --- a/drivers/gpu/drm/i915/gvt/display.c +++ b/drivers/gpu/drm/i915/gvt/display.c @@ -457,7 +457,8 @@ void intel_vgpu_emulate_hotplug(struct intel_vgpu *vgpu, bool connected) struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; /* TODO: add more platforms support */ - if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) { + if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv) || + IS_COFFEELAKE(dev_priv)) { if (connected) { vgpu_vreg_t(vgpu, SFUSE_STRAP) |= SFUSE_STRAP_DDID_DETECTED; diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c index 2477a1e5a1669cf220ccb85b062885714c100d3d..ae139f0877aeb72a098657ea296f876f6b8194a0 100644 --- a/drivers/gpu/drm/i915/gvt/dmabuf.c +++ b/drivers/gpu/drm/i915/gvt/dmabuf.c @@ -151,12 +151,12 @@ static void dmabuf_gem_object_free(struct kref *kref) dmabuf_obj = container_of(pos, struct intel_vgpu_dmabuf_obj, list); if (dmabuf_obj == obj) { + list_del(pos); intel_gvt_hypervisor_put_vfio_device(vgpu); idr_remove(&vgpu->object_idr, dmabuf_obj->dmabuf_id); kfree(dmabuf_obj->info); kfree(dmabuf_obj); - list_del(pos); break; } } diff --git a/drivers/gpu/drm/i915/gvt/firmware.c b/drivers/gpu/drm/i915/gvt/firmware.c index 049775e8e350eaf4179892bd8fe989dc790a79c0..b0c1fda32977ce26240954935767e4edfc51b7b9 100644 --- a/drivers/gpu/drm/i915/gvt/firmware.c +++ b/drivers/gpu/drm/i915/gvt/firmware.c @@ -146,7 +146,7 @@ void intel_gvt_free_firmware(struct intel_gvt *gvt) clean_firmware_sysfs(gvt); kfree(gvt->firmware.cfg_space); - kfree(gvt->firmware.mmio); + vfree(gvt->firmware.mmio); } static int verify_firmware(struct intel_gvt *gvt, @@ -229,7 +229,7 @@ int intel_gvt_load_firmware(struct intel_gvt *gvt) firmware->cfg_space = mem; - mem = kmalloc(info->mmio_size, GFP_KERNEL); + mem = vmalloc(info->mmio_size); if (!mem) { kfree(path); kfree(firmware->cfg_space); diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 34cb404ba4b789ca97c86794d90c24edf3cf95ef..4a4828074cb708b09b764f295f28f80fa137d14c 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -1956,7 +1956,11 @@ void _intel_vgpu_mm_release(struct kref *mm_ref) if (mm->type == INTEL_GVT_MM_PPGTT) { list_del(&mm->ppgtt_mm.list); + + mutex_lock(&mm->vgpu->gvt->gtt.ppgtt_mm_lock); list_del(&mm->ppgtt_mm.lru_list); + mutex_unlock(&mm->vgpu->gvt->gtt.ppgtt_mm_lock); + invalidate_ppgtt_mm(mm); } else { vfree(mm->ggtt_mm.virtual_ggtt); diff --git a/drivers/gpu/drm/i915/gvt/opregion.c b/drivers/gpu/drm/i915/gvt/opregion.c index 867e7629025be440cc903bd9d6b63a84608bac4b..33569b910ed5bf21c9d2f56645611047dfdafdb0 100644 --- a/drivers/gpu/drm/i915/gvt/opregion.c +++ b/drivers/gpu/drm/i915/gvt/opregion.c @@ -147,15 +147,14 @@ static void virt_vbt_generation(struct vbt *v) /* there's features depending on version! */ v->header.version = 155; v->header.header_size = sizeof(v->header); - v->header.vbt_size = sizeof(struct vbt) - sizeof(v->header); + v->header.vbt_size = sizeof(struct vbt); v->header.bdb_offset = offsetof(struct vbt, bdb_header); strcpy(&v->bdb_header.signature[0], "BIOS_DATA_BLOCK"); v->bdb_header.version = 186; /* child_dev_size = 33 */ v->bdb_header.header_size = sizeof(v->bdb_header); - v->bdb_header.bdb_size = sizeof(struct vbt) - sizeof(struct vbt_header) - - sizeof(struct bdb_header); + v->bdb_header.bdb_size = sizeof(struct vbt) - sizeof(struct vbt_header); /* general features */ v->general_features_header.id = BDB_GENERAL_FEATURES; diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index 85bd9bf4f6eee58b3c00e567a7c5286a017dccb9..345c2aa3b491e143fb00bb74dd9c86d29b95a4d3 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -272,10 +272,17 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu) { struct intel_gvt *gvt = vgpu->gvt; - mutex_lock(&vgpu->vgpu_lock); - WARN(vgpu->active, "vGPU is still active!\n"); + /* + * remove idr first so later clean can judge if need to stop + * service if no active vgpu. + */ + mutex_lock(&gvt->lock); + idr_remove(&gvt->vgpu_idr, vgpu->id); + mutex_unlock(&gvt->lock); + + mutex_lock(&vgpu->vgpu_lock); intel_gvt_debugfs_remove_vgpu(vgpu); intel_vgpu_clean_sched_policy(vgpu); intel_vgpu_clean_submission(vgpu); @@ -290,7 +297,6 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu) mutex_unlock(&vgpu->vgpu_lock); mutex_lock(&gvt->lock); - idr_remove(&gvt->vgpu_idr, vgpu->id); if (idr_is_empty(&gvt->vgpu_idr)) intel_gvt_clean_irq(gvt); intel_gvt_update_vgpu_types(gvt); @@ -560,9 +566,9 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr, intel_vgpu_reset_mmio(vgpu, dmlr); populate_pvinfo_page(vgpu); - intel_vgpu_reset_display(vgpu); if (dmlr) { + intel_vgpu_reset_display(vgpu); intel_vgpu_reset_cfg_space(vgpu); /* only reset the failsafe mode when dmlr reset */ vgpu->failsafe = false; diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c index f3da5c06f331a5cf7df35ac3c59a7a587ccbc81c..b0a499753526615c9175d6b276ecb7089df87c38 100644 --- a/drivers/gpu/drm/i915/i915_active.c +++ b/drivers/gpu/drm/i915/i915_active.c @@ -416,13 +416,15 @@ int i915_active_acquire(struct i915_active *ref) if (err) return err; - if (!atomic_read(&ref->count) && ref->active) - err = ref->active(ref); - if (!err) { - spin_lock_irq(&ref->tree_lock); /* vs __active_retire() */ - debug_active_activate(ref); - atomic_inc(&ref->count); - spin_unlock_irq(&ref->tree_lock); + if (likely(!i915_active_acquire_if_busy(ref))) { + if (ref->active) + err = ref->active(ref); + if (!err) { + spin_lock_irq(&ref->tree_lock); /* __active_retire() */ + debug_active_activate(ref); + atomic_inc(&ref->count); + spin_unlock_irq(&ref->tree_lock); + } } mutex_unlock(&ref->mutex); @@ -605,7 +607,7 @@ int i915_active_acquire_preallocate_barrier(struct i915_active *ref, struct intel_engine_cs *engine) { intel_engine_mask_t tmp, mask = engine->mask; - struct llist_node *pos = NULL, *next; + struct llist_node *first = NULL, *last = NULL; struct intel_gt *gt = engine->gt; int err; @@ -623,6 +625,7 @@ int i915_active_acquire_preallocate_barrier(struct i915_active *ref, */ for_each_engine_masked(engine, gt, mask, tmp) { u64 idx = engine->kernel_context->timeline->fence_context; + struct llist_node *prev = first; struct active_node *node; node = reuse_idle_barrier(ref, idx); @@ -656,23 +659,23 @@ int i915_active_acquire_preallocate_barrier(struct i915_active *ref, GEM_BUG_ON(rcu_access_pointer(node->base.fence) != ERR_PTR(-EAGAIN)); GEM_BUG_ON(barrier_to_engine(node) != engine); - next = barrier_to_ll(node); - next->next = pos; - if (!pos) - pos = next; + first = barrier_to_ll(node); + first->next = prev; + if (!last) + last = first; intel_engine_pm_get(engine); } GEM_BUG_ON(!llist_empty(&ref->preallocated_barriers)); - llist_add_batch(next, pos, &ref->preallocated_barriers); + llist_add_batch(first, last, &ref->preallocated_barriers); return 0; unwind: - while (pos) { - struct active_node *node = barrier_from_ll(pos); + while (first) { + struct active_node *node = barrier_from_ll(first); - pos = pos->next; + first = first->next; atomic_dec(&ref->count); intel_engine_pm_put(barrier_to_engine(node)); diff --git a/drivers/gpu/drm/i915/i915_active.h b/drivers/gpu/drm/i915/i915_active.h index b571f675c7956a2938bd16760fe9352fd4944024..51e1e854ca5575157d0b84fc6e9077642712a9e1 100644 --- a/drivers/gpu/drm/i915/i915_active.h +++ b/drivers/gpu/drm/i915/i915_active.h @@ -188,6 +188,12 @@ int i915_active_acquire(struct i915_active *ref); bool i915_active_acquire_if_busy(struct i915_active *ref); void i915_active_release(struct i915_active *ref); +static inline void __i915_active_acquire(struct i915_active *ref) +{ + GEM_BUG_ON(!atomic_read(&ref->count)); + atomic_inc(&ref->count); +} + static inline bool i915_active_is_idle(const struct i915_active *ref) { diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index f7385abdd74bc5540247c603300366e465ffa2bc..8410330ce4f04e505d14b03136b0ae96004948d5 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -56,6 +56,7 @@ #include "display/intel_hotplug.h" #include "display/intel_overlay.h" #include "display/intel_pipe_crc.h" +#include "display/intel_psr.h" #include "display/intel_sprite.h" #include "display/intel_vga.h" @@ -330,6 +331,8 @@ static int i915_driver_modeset_probe(struct drm_i915_private *i915) intel_init_ipc(i915); + intel_psr_set_force_mode_changed(i915->psr.dp); + return 0; cleanup_gem: diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 077af22b834063c04d44a8e181fae186fe984006..810e3ccd56ecb7ce1ccbe03cb726c150841abb27 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -505,7 +505,7 @@ struct i915_psr { bool dc3co_enabled; u32 dc3co_exit_delay; struct delayed_work idle_work; - bool initially_probed; + bool force_mode_changed; }; #define QUIRK_LVDS_SSC_DISABLE (1<<1) diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 94f993e4c12f5cb687513efee0a2822afd20d734..5f6e639528219378a7a1346c8b14ce7df9bf2da6 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -180,7 +180,7 @@ i915_gem_phys_pwrite(struct drm_i915_gem_object *obj, struct drm_i915_gem_pwrite *args, struct drm_file *file) { - void *vaddr = obj->phys_handle->vaddr + args->offset; + void *vaddr = sg_page(obj->mm.pages->sgl) + args->offset; char __user *user_data = u64_to_user_ptr(args->data_ptr); /* @@ -265,7 +265,10 @@ i915_gem_dumb_create(struct drm_file *file, DRM_FORMAT_MOD_LINEAR)) args->pitch = ALIGN(args->pitch, 4096); - args->size = args->pitch * args->height; + if (args->pitch < args->width) + return -EINVAL; + + args->size = mul_u32_u32(args->pitch, args->height); mem_type = INTEL_MEMORY_SYSTEM; if (HAS_LMEM(to_i915(dev))) @@ -841,10 +844,10 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data, ret = i915_gem_gtt_pwrite_fast(obj, args); if (ret == -EFAULT || ret == -ENOSPC) { - if (obj->phys_handle) - ret = i915_gem_phys_pwrite(obj, args, file); - else + if (i915_gem_object_has_struct_page(obj)) ret = i915_gem_shmem_pwrite(obj, args); + else + ret = i915_gem_phys_pwrite(obj, args, file); } i915_gem_object_unpin_pages(obj); diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 4c1836f0a9911bedb73ee91c583ddb2aaccea705..9e401a5fcae8c9e64f7c244d71df6a261de83e21 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -1681,7 +1681,7 @@ static const char *error_msg(struct i915_gpu_coredump *error) "GPU HANG: ecode %d:%x:%08x", INTEL_GEN(error->i915), engines, generate_ecode(first)); - if (first) { + if (first && first->context.pid) { /* Just show the first executing process, more is confusing */ len += scnprintf(error->error_msg + len, sizeof(error->error_msg) - len, @@ -1852,7 +1852,8 @@ void i915_error_state_store(struct i915_gpu_coredump *error) if (!xchg(&warned, true) && ktime_get_real_seconds() - DRIVER_TIMESTAMP < DAY_AS_SECONDS(180)) { pr_info("GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace.\n"); - pr_info("Please file a _new_ bug report on bugs.freedesktop.org against DRI -> DRM/Intel\n"); + pr_info("Please file a _new_ bug report at https://gitlab.freedesktop.org/drm/intel/issues/new.\n"); + pr_info("Please see https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs for details.\n"); pr_info("drm/i915 developers can then reassign to the right component if it's not a kernel issue.\n"); pr_info("The GPU crash dump is required to analyze GPU hangs, so please always attach it.\n"); pr_info("GPU crash dump saved to /sys/class/drm/card%d/error\n", diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h index 9109004956bd1e6b8c773e91f47cd4764bff47c3..e4a6afed3bbf6bd4fde09afd9bf5617101f9be6c 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.h +++ b/drivers/gpu/drm/i915/i915_gpu_error.h @@ -314,8 +314,11 @@ i915_vma_capture_finish(struct intel_gt_coredump *gt, } static inline void -i915_error_state_store(struct drm_i915_private *i915, - struct i915_gpu_coredump *error) +i915_error_state_store(struct i915_gpu_coredump *error) +{ +} + +static inline void i915_gpu_coredump_put(struct i915_gpu_coredump *gpu) { } diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index 83f01401b8b5c5758dea58f7c8ed5dcf6c22c21c..f631f6d2112746d408af0945e4eedad3e03a037b 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -437,7 +437,7 @@ static const struct intel_device_info snb_m_gt2_info = { .has_rc6 = 1, \ .has_rc6p = 1, \ .has_rps = true, \ - .ppgtt_type = INTEL_PPGTT_FULL, \ + .ppgtt_type = INTEL_PPGTT_ALIASING, \ .ppgtt_size = 31, \ IVB_PIPE_OFFSETS, \ IVB_CURSOR_OFFSETS, \ @@ -494,7 +494,7 @@ static const struct intel_device_info vlv_info = { .has_rps = true, .display.has_gmch = 1, .display.has_hotplug = 1, - .ppgtt_type = INTEL_PPGTT_FULL, + .ppgtt_type = INTEL_PPGTT_ALIASING, .ppgtt_size = 31, .has_snoop = true, .has_coherent_ggtt = false, diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 0f556d80ba36577c8c190066a3e18a9f99f670c0..3b6b913bd27a7dcf56b06d3aca12d589e48f5d62 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -1954,9 +1954,10 @@ get_oa_vma(struct i915_perf_stream *stream, struct i915_oa_config *oa_config) return i915_vma_get(oa_bo->vma); } -static int emit_oa_config(struct i915_perf_stream *stream, - struct i915_oa_config *oa_config, - struct intel_context *ce) +static struct i915_request * +emit_oa_config(struct i915_perf_stream *stream, + struct i915_oa_config *oa_config, + struct intel_context *ce) { struct i915_request *rq; struct i915_vma *vma; @@ -1964,7 +1965,7 @@ static int emit_oa_config(struct i915_perf_stream *stream, vma = get_oa_vma(stream, oa_config); if (IS_ERR(vma)) - return PTR_ERR(vma); + return ERR_CAST(vma); err = i915_vma_pin(vma, 0, 0, PIN_GLOBAL | PIN_HIGH); if (err) @@ -1989,13 +1990,17 @@ static int emit_oa_config(struct i915_perf_stream *stream, err = rq->engine->emit_bb_start(rq, vma->node.start, 0, I915_DISPATCH_SECURE); + if (err) + goto err_add_request; + + i915_request_get(rq); err_add_request: i915_request_add(rq); err_vma_unpin: i915_vma_unpin(vma); err_vma_put: i915_vma_put(vma); - return err; + return err ? ERR_PTR(err) : rq; } static struct intel_context *oa_context(struct i915_perf_stream *stream) @@ -2003,7 +2008,8 @@ static struct intel_context *oa_context(struct i915_perf_stream *stream) return stream->pinned_ctx ?: stream->engine->kernel_context; } -static int hsw_enable_metric_set(struct i915_perf_stream *stream) +static struct i915_request * +hsw_enable_metric_set(struct i915_perf_stream *stream) { struct intel_uncore *uncore = stream->uncore; @@ -2406,7 +2412,8 @@ static int lrc_configure_all_contexts(struct i915_perf_stream *stream, return oa_configure_all_contexts(stream, regs, ARRAY_SIZE(regs)); } -static int gen8_enable_metric_set(struct i915_perf_stream *stream) +static struct i915_request * +gen8_enable_metric_set(struct i915_perf_stream *stream) { struct intel_uncore *uncore = stream->uncore; struct i915_oa_config *oa_config = stream->oa_config; @@ -2448,7 +2455,7 @@ static int gen8_enable_metric_set(struct i915_perf_stream *stream) */ ret = lrc_configure_all_contexts(stream, oa_config); if (ret) - return ret; + return ERR_PTR(ret); return emit_oa_config(stream, oa_config, oa_context(stream)); } @@ -2460,7 +2467,8 @@ static u32 oag_report_ctx_switches(const struct i915_perf_stream *stream) 0 : GEN12_OAG_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS); } -static int gen12_enable_metric_set(struct i915_perf_stream *stream) +static struct i915_request * +gen12_enable_metric_set(struct i915_perf_stream *stream) { struct intel_uncore *uncore = stream->uncore; struct i915_oa_config *oa_config = stream->oa_config; @@ -2491,7 +2499,7 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream) */ ret = gen12_configure_all_contexts(stream, oa_config); if (ret) - return ret; + return ERR_PTR(ret); /* * For Gen12, performance counters are context @@ -2501,7 +2509,7 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream) if (stream->ctx) { ret = gen12_configure_oar_context(stream, true); if (ret) - return ret; + return ERR_PTR(ret); } return emit_oa_config(stream, oa_config, oa_context(stream)); @@ -2696,6 +2704,20 @@ static const struct i915_perf_stream_ops i915_oa_stream_ops = { .read = i915_oa_read, }; +static int i915_perf_stream_enable_sync(struct i915_perf_stream *stream) +{ + struct i915_request *rq; + + rq = stream->perf->ops.enable_metric_set(stream); + if (IS_ERR(rq)) + return PTR_ERR(rq); + + i915_request_wait(rq, 0, MAX_SCHEDULE_TIMEOUT); + i915_request_put(rq); + + return 0; +} + /** * i915_oa_stream_init - validate combined props for OA stream and init * @stream: An i915 perf stream @@ -2829,7 +2851,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, stream->ops = &i915_oa_stream_ops; perf->exclusive_stream = stream; - ret = perf->ops.enable_metric_set(stream); + ret = i915_perf_stream_enable_sync(stream); if (ret) { DRM_DEBUG("Unable to enable metric set\n"); goto err_enable; @@ -3147,7 +3169,7 @@ static long i915_perf_config_locked(struct i915_perf_stream *stream, return -EINVAL; if (config != stream->oa_config) { - int err; + struct i915_request *rq; /* * If OA is bound to a specific context, emit the @@ -3158,11 +3180,13 @@ static long i915_perf_config_locked(struct i915_perf_stream *stream, * When set globally, we use a low priority kernel context, * so it will effectively take effect when idle. */ - err = emit_oa_config(stream, config, oa_context(stream)); - if (err == 0) + rq = emit_oa_config(stream, config, oa_context(stream)); + if (!IS_ERR(rq)) { config = xchg(&stream->oa_config, config); - else - ret = err; + i915_request_put(rq); + } else { + ret = PTR_ERR(rq); + } } i915_oa_config_put(config); diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h index 45e581455f5d77ab19c58627716113a95439f0f7..a0e22f00f6cfbe84ad493596c56fdf98e19ffd99 100644 --- a/drivers/gpu/drm/i915/i915_perf_types.h +++ b/drivers/gpu/drm/i915/i915_perf_types.h @@ -339,7 +339,8 @@ struct i915_oa_ops { * counter reports being sampled. May apply system constraints such as * disabling EU clock gating as required. */ - int (*enable_metric_set)(struct i915_perf_stream *stream); + struct i915_request * + (*enable_metric_set)(struct i915_perf_stream *stream); /** * @disable_metric_set: Remove system constraints associated with using diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index 28a82c849bacbc2a43fc1fff4236b8981d349d1e..aa729d04abe2ecba8b74b10600a850d020dfbcd6 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -637,8 +637,10 @@ static void i915_pmu_enable(struct perf_event *event) container_of(event->pmu, typeof(*i915), pmu.base); unsigned int bit = event_enabled_bit(event); struct i915_pmu *pmu = &i915->pmu; + intel_wakeref_t wakeref; unsigned long flags; + wakeref = intel_runtime_pm_get(&i915->runtime_pm); spin_lock_irqsave(&pmu->lock, flags); /* @@ -648,6 +650,14 @@ static void i915_pmu_enable(struct perf_event *event) BUILD_BUG_ON(ARRAY_SIZE(pmu->enable_count) != I915_PMU_MASK_BITS); GEM_BUG_ON(bit >= ARRAY_SIZE(pmu->enable_count)); GEM_BUG_ON(pmu->enable_count[bit] == ~0); + + if (pmu->enable_count[bit] == 0 && + config_enabled_mask(I915_PMU_RC6_RESIDENCY) & BIT_ULL(bit)) { + pmu->sample[__I915_SAMPLE_RC6_LAST_REPORTED].cur = 0; + pmu->sample[__I915_SAMPLE_RC6].cur = __get_rc6(&i915->gt); + pmu->sleep_last = ktime_get(); + } + pmu->enable |= BIT_ULL(bit); pmu->enable_count[bit]++; @@ -688,6 +698,8 @@ static void i915_pmu_enable(struct perf_event *event) * an existing non-zero value. */ local64_set(&event->hw.prev_count, __i915_pmu_event_read(event)); + + intel_runtime_pm_put(&i915->runtime_pm, wakeref); } static void i915_pmu_disable(struct perf_event *event) @@ -810,11 +822,6 @@ static ssize_t i915_pmu_event_show(struct device *dev, return sprintf(buf, "config=0x%lx\n", eattr->val); } -static struct attribute_group i915_pmu_events_attr_group = { - .name = "events", - /* Patch in attrs at runtime. */ -}; - static ssize_t i915_pmu_get_attr_cpumask(struct device *dev, struct device_attribute *attr, @@ -834,13 +841,6 @@ static const struct attribute_group i915_pmu_cpumask_attr_group = { .attrs = i915_cpumask_attrs, }; -static const struct attribute_group *i915_pmu_attr_groups[] = { - &i915_pmu_format_attr_group, - &i915_pmu_events_attr_group, - &i915_pmu_cpumask_attr_group, - NULL -}; - #define __event(__config, __name, __unit) \ { \ .config = (__config), \ @@ -1014,23 +1014,23 @@ err:; static void free_event_attributes(struct i915_pmu *pmu) { - struct attribute **attr_iter = i915_pmu_events_attr_group.attrs; + struct attribute **attr_iter = pmu->events_attr_group.attrs; for (; *attr_iter; attr_iter++) kfree((*attr_iter)->name); - kfree(i915_pmu_events_attr_group.attrs); + kfree(pmu->events_attr_group.attrs); kfree(pmu->i915_attr); kfree(pmu->pmu_attr); - i915_pmu_events_attr_group.attrs = NULL; + pmu->events_attr_group.attrs = NULL; pmu->i915_attr = NULL; pmu->pmu_attr = NULL; } static int i915_pmu_cpu_online(unsigned int cpu, struct hlist_node *node) { - struct i915_pmu *pmu = hlist_entry_safe(node, typeof(*pmu), node); + struct i915_pmu *pmu = hlist_entry_safe(node, typeof(*pmu), cpuhp.node); GEM_BUG_ON(!pmu->base.event_init); @@ -1043,7 +1043,7 @@ static int i915_pmu_cpu_online(unsigned int cpu, struct hlist_node *node) static int i915_pmu_cpu_offline(unsigned int cpu, struct hlist_node *node) { - struct i915_pmu *pmu = hlist_entry_safe(node, typeof(*pmu), node); + struct i915_pmu *pmu = hlist_entry_safe(node, typeof(*pmu), cpuhp.node); unsigned int target; GEM_BUG_ON(!pmu->base.event_init); @@ -1060,8 +1060,6 @@ static int i915_pmu_cpu_offline(unsigned int cpu, struct hlist_node *node) return 0; } -static enum cpuhp_state cpuhp_slot = CPUHP_INVALID; - static int i915_pmu_register_cpuhp_state(struct i915_pmu *pmu) { enum cpuhp_state slot; @@ -1075,21 +1073,22 @@ static int i915_pmu_register_cpuhp_state(struct i915_pmu *pmu) return ret; slot = ret; - ret = cpuhp_state_add_instance(slot, &pmu->node); + ret = cpuhp_state_add_instance(slot, &pmu->cpuhp.node); if (ret) { cpuhp_remove_multi_state(slot); return ret; } - cpuhp_slot = slot; + pmu->cpuhp.slot = slot; return 0; } static void i915_pmu_unregister_cpuhp_state(struct i915_pmu *pmu) { - WARN_ON(cpuhp_slot == CPUHP_INVALID); - WARN_ON(cpuhp_state_remove_instance(cpuhp_slot, &pmu->node)); - cpuhp_remove_multi_state(cpuhp_slot); + WARN_ON(pmu->cpuhp.slot == CPUHP_INVALID); + WARN_ON(cpuhp_state_remove_instance(pmu->cpuhp.slot, &pmu->cpuhp.node)); + cpuhp_remove_multi_state(pmu->cpuhp.slot); + pmu->cpuhp.slot = CPUHP_INVALID; } static bool is_igp(struct drm_i915_private *i915) @@ -1106,6 +1105,13 @@ static bool is_igp(struct drm_i915_private *i915) void i915_pmu_register(struct drm_i915_private *i915) { struct i915_pmu *pmu = &i915->pmu; + const struct attribute_group *attr_groups[] = { + &i915_pmu_format_attr_group, + &pmu->events_attr_group, + &i915_pmu_cpumask_attr_group, + NULL + }; + int ret = -ENOMEM; if (INTEL_GEN(i915) <= 2) { @@ -1116,6 +1122,7 @@ void i915_pmu_register(struct drm_i915_private *i915) spin_lock_init(&pmu->lock); hrtimer_init(&pmu->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); pmu->timer.function = i915_sample; + pmu->cpuhp.slot = CPUHP_INVALID; if (!is_igp(i915)) { pmu->name = kasprintf(GFP_KERNEL, @@ -1131,11 +1138,16 @@ void i915_pmu_register(struct drm_i915_private *i915) if (!pmu->name) goto err; - i915_pmu_events_attr_group.attrs = create_event_attributes(pmu); - if (!i915_pmu_events_attr_group.attrs) + pmu->events_attr_group.name = "events"; + pmu->events_attr_group.attrs = create_event_attributes(pmu); + if (!pmu->events_attr_group.attrs) goto err_name; - pmu->base.attr_groups = i915_pmu_attr_groups; + pmu->base.attr_groups = kmemdup(attr_groups, sizeof(attr_groups), + GFP_KERNEL); + if (!pmu->base.attr_groups) + goto err_attr; + pmu->base.task_ctx_nr = perf_invalid_context; pmu->base.event_init = i915_pmu_event_init; pmu->base.add = i915_pmu_event_add; @@ -1147,7 +1159,7 @@ void i915_pmu_register(struct drm_i915_private *i915) ret = perf_pmu_register(&pmu->base, pmu->name, -1); if (ret) - goto err_attr; + goto err_groups; ret = i915_pmu_register_cpuhp_state(pmu); if (ret) @@ -1157,6 +1169,8 @@ void i915_pmu_register(struct drm_i915_private *i915) err_unreg: perf_pmu_unregister(&pmu->base); +err_groups: + kfree(pmu->base.attr_groups); err_attr: pmu->base.event_init = NULL; free_event_attributes(pmu); @@ -1182,6 +1196,7 @@ void i915_pmu_unregister(struct drm_i915_private *i915) perf_pmu_unregister(&pmu->base); pmu->base.event_init = NULL; + kfree(pmu->base.attr_groups); if (!is_igp(i915)) kfree(pmu->name); free_event_attributes(pmu); diff --git a/drivers/gpu/drm/i915/i915_pmu.h b/drivers/gpu/drm/i915/i915_pmu.h index 6c1647c5daf255ff4d27fb538dd2ec358ed782e2..f1d6cad0d7d576caa3999bf0b62fdfe9b9e656d2 100644 --- a/drivers/gpu/drm/i915/i915_pmu.h +++ b/drivers/gpu/drm/i915/i915_pmu.h @@ -39,9 +39,12 @@ struct i915_pmu_sample { struct i915_pmu { /** - * @node: List node for CPU hotplug handling. + * @cpuhp: Struct used for CPU hotplug handling. */ - struct hlist_node node; + struct { + struct hlist_node node; + enum cpuhp_state slot; + } cpuhp; /** * @base: PMU base. */ @@ -104,6 +107,10 @@ struct i915_pmu { * @sleep_last: Last time GT parked for RC6 estimation. */ ktime_t sleep_last; + /** + * @events_attr_group: Device events attribute group. + */ + struct attribute_group events_attr_group; /** * @i915_attr: Memory block holding device attributes. */ diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 6cc55c103f6742fe9b5dd027f49480a5faef9529..3575fd30756b5c46bebe8745a40fd9ccb807b2d2 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -7757,6 +7757,7 @@ enum { #define BW_BUDDY1_CTL _MMIO(0x45140) #define BW_BUDDY2_CTL _MMIO(0x45150) #define BW_BUDDY_DISABLE REG_BIT(31) +#define BW_BUDDY_TLB_REQ_TIMER_MASK REG_GENMASK(21, 16) #define BW_BUDDY1_PAGE_MASK _MMIO(0x45144) #define BW_BUDDY2_PAGE_MASK _MMIO(0x45154) diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index be185886e4fcc56dcc9b62f3ebe61e08ee543554..a18b2a2447066f1d529251303283409003acf35d 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -221,6 +221,8 @@ static void remove_from_engine(struct i915_request *rq) locked = engine; } list_del_init(&rq->sched.link); + clear_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags); + clear_bit(I915_FENCE_FLAG_HOLD, &rq->fence.flags); spin_unlock_irq(&locked->active.lock); } @@ -273,7 +275,7 @@ bool i915_request_retire(struct i915_request *rq) spin_unlock_irq(&rq->lock); remove_from_client(rq); - list_del(&rq->link); + list_del_rcu(&rq->link); intel_context_exit(rq->context); intel_context_unpin(rq->context); @@ -408,8 +410,10 @@ bool __i915_request_submit(struct i915_request *request) xfer: /* We may be recursing from the signal callback of another i915 fence */ spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING); - if (!test_and_set_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags)) + if (!test_and_set_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags)) { list_move_tail(&request->sched.link, &engine->active.requests); + clear_bit(I915_FENCE_FLAG_PQUEUE, &request->fence.flags); + } if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &request->fence.flags) && !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &request->fence.flags) && @@ -523,19 +527,31 @@ submit_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state) return NOTIFY_DONE; } +static void irq_semaphore_cb(struct irq_work *wrk) +{ + struct i915_request *rq = + container_of(wrk, typeof(*rq), semaphore_work); + + i915_schedule_bump_priority(rq, I915_PRIORITY_NOSEMAPHORE); + i915_request_put(rq); +} + static int __i915_sw_fence_call semaphore_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state) { - struct i915_request *request = - container_of(fence, typeof(*request), semaphore); + struct i915_request *rq = container_of(fence, typeof(*rq), semaphore); switch (state) { case FENCE_COMPLETE: - i915_schedule_bump_priority(request, I915_PRIORITY_NOSEMAPHORE); + if (!(READ_ONCE(rq->sched.attr.priority) & I915_PRIORITY_NOSEMAPHORE)) { + i915_request_get(rq); + init_irq_work(&rq->semaphore_work, irq_semaphore_cb); + irq_work_queue(&rq->semaphore_work); + } break; case FENCE_FREE: - i915_request_put(request); + i915_request_put(rq); break; } @@ -591,6 +607,8 @@ static void __i915_request_ctor(void *arg) i915_sw_fence_init(&rq->submit, submit_notify); i915_sw_fence_init(&rq->semaphore, semaphore_notify); + dma_fence_init(&rq->fence, &i915_fence_ops, &rq->lock, 0, 0); + rq->file_priv = NULL; rq->capture_list = NULL; @@ -649,25 +667,30 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp) } } - ret = intel_timeline_get_seqno(tl, rq, &seqno); - if (ret) - goto err_free; - rq->i915 = ce->engine->i915; rq->context = ce; rq->engine = ce->engine; rq->ring = ce->ring; rq->execution_mask = ce->engine->mask; + kref_init(&rq->fence.refcount); + rq->fence.flags = 0; + rq->fence.error = 0; + INIT_LIST_HEAD(&rq->fence.cb_list); + + ret = intel_timeline_get_seqno(tl, rq, &seqno); + if (ret) + goto err_free; + + rq->fence.context = tl->fence_context; + rq->fence.seqno = seqno; + RCU_INIT_POINTER(rq->timeline, tl); RCU_INIT_POINTER(rq->hwsp_cacheline, tl->hwsp_cacheline); rq->hwsp_seqno = tl->hwsp_seqno; rq->rcustate = get_state_synchronize_rcu(); /* acts as smp_mb() */ - dma_fence_init(&rq->fence, &i915_fence_ops, &rq->lock, - tl->fence_context, seqno); - /* We bump the ref for the fence chain */ i915_sw_fence_reinit(&i915_request_get(rq)->submit); i915_sw_fence_reinit(&i915_request_get(rq)->semaphore); @@ -710,6 +733,8 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp) rq->infix = rq->ring->emit; /* end of header; start of user payload */ intel_context_mark_active(ce); + list_add_tail_rcu(&rq->link, &tl->requests); + return rq; err_unwind: @@ -763,16 +788,26 @@ i915_request_await_start(struct i915_request *rq, struct i915_request *signal) struct dma_fence *fence; int err; - GEM_BUG_ON(i915_request_timeline(rq) == - rcu_access_pointer(signal->timeline)); + if (i915_request_timeline(rq) == rcu_access_pointer(signal->timeline)) + return 0; + + if (i915_request_started(signal)) + return 0; fence = NULL; rcu_read_lock(); spin_lock_irq(&signal->lock); - if (!i915_request_started(signal) && - !list_is_first(&signal->link, - &rcu_dereference(signal->timeline)->requests)) { - struct i915_request *prev = list_prev_entry(signal, link); + do { + struct list_head *pos = READ_ONCE(signal->link.prev); + struct i915_request *prev; + + /* Confirm signal has not been retired, the link is valid */ + if (unlikely(i915_request_started(signal))) + break; + + /* Is signal the earliest request on its timeline? */ + if (pos == &rcu_dereference(signal->timeline)->requests) + break; /* * Peek at the request before us in the timeline. That @@ -780,20 +815,25 @@ i915_request_await_start(struct i915_request *rq, struct i915_request *signal) * after acquiring a reference to it, confirm that it is * still part of the signaler's timeline. */ - if (i915_request_get_rcu(prev)) { - if (list_next_entry(prev, link) == signal) - fence = &prev->fence; - else - i915_request_put(prev); + prev = list_entry(pos, typeof(*prev), link); + if (!i915_request_get_rcu(prev)) + break; + + /* After the strong barrier, confirm prev is still attached */ + if (unlikely(READ_ONCE(prev->link.next) != &signal->link)) { + i915_request_put(prev); + break; } - } + + fence = &prev->fence; + } while (0); spin_unlock_irq(&signal->lock); rcu_read_unlock(); if (!fence) return 0; err = 0; - if (intel_timeline_sync_is_later(i915_request_timeline(rq), fence)) + if (!intel_timeline_sync_is_later(i915_request_timeline(rq), fence)) err = i915_sw_fence_await_dma_fence(&rq->submit, fence, 0, I915_FENCE_GFP); @@ -1231,8 +1271,6 @@ __i915_request_add_to_timeline(struct i915_request *rq) 0); } - list_add_tail(&rq->link, &timeline->requests); - /* * Make sure that no request gazumped us - if it was allocated after * our i915_request_alloc() and called __i915_request_add() before @@ -1292,9 +1330,9 @@ void __i915_request_queue(struct i915_request *rq, * decide whether to preempt the entire chain so that it is ready to * run at the earliest possible convenience. */ - i915_sw_fence_commit(&rq->semaphore); if (attr && rq->engine->schedule) rq->engine->schedule(rq, attr); + i915_sw_fence_commit(&rq->semaphore); i915_sw_fence_commit(&rq->submit); } diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h index 031433691a06f2b8b74ea286e1afd0a400b21d40..fccc339949ec114ccc6c0e36e2b0f6246aa76aee 100644 --- a/drivers/gpu/drm/i915/i915_request.h +++ b/drivers/gpu/drm/i915/i915_request.h @@ -26,6 +26,7 @@ #define I915_REQUEST_H #include +#include #include #include "gem/i915_gem_context_types.h" @@ -70,6 +71,18 @@ enum { */ I915_FENCE_FLAG_ACTIVE = DMA_FENCE_FLAG_USER_BITS, + /* + * I915_FENCE_FLAG_PQUEUE - this request is ready for execution + * + * Using the scheduler, when a request is ready for execution it is put + * into the priority queue, and removed from that queue when transferred + * to the HW runlists. We want to track its membership within the + * priority queue so that we can easily check before rescheduling. + * + * See i915_request_in_priority_queue() + */ + I915_FENCE_FLAG_PQUEUE, + /* * I915_FENCE_FLAG_SIGNAL - this request is currently on signal_list * @@ -78,6 +91,13 @@ enum { */ I915_FENCE_FLAG_SIGNAL, + /* + * I915_FENCE_FLAG_HOLD - this request is currently on hold + * + * This request has been suspended, pending an ongoing investigation. + */ + I915_FENCE_FLAG_HOLD, + /* * I915_FENCE_FLAG_NOPREEMPT - this request should not be preempted * @@ -189,6 +209,7 @@ struct i915_request { }; struct list_head execute_cb; struct i915_sw_fence semaphore; + struct irq_work semaphore_work; /* * A list of everyone we wait upon, and everyone who waits upon us. @@ -361,6 +382,11 @@ static inline bool i915_request_is_active(const struct i915_request *rq) return test_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags); } +static inline bool i915_request_in_priority_queue(const struct i915_request *rq) +{ + return test_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags); +} + /** * Returns true if seq1 is later than seq2. */ @@ -454,6 +480,27 @@ static inline bool i915_request_is_running(const struct i915_request *rq) return __i915_request_has_started(rq); } +/** + * i915_request_is_running - check if the request is ready for execution + * @rq: the request + * + * Upon construction, the request is instructed to wait upon various + * signals before it is ready to be executed by the HW. That is, we do + * not want to start execution and read data before it is written. In practice, + * this is controlled with a mixture of interrupts and semaphores. Once + * the submit fence is completed, the backend scheduler will place the + * request into its queue and from there submit it for execution. So we + * can detect when a request is eligible for execution (and is under control + * of the scheduler) by querying where it is in any of the scheduler's lists. + * + * Returns true if the request is ready for execution (it may be inflight), + * false otherwise. + */ +static inline bool i915_request_is_ready(const struct i915_request *rq) +{ + return !list_empty(&rq->sched.link); +} + static inline bool i915_request_completed(const struct i915_request *rq) { if (i915_request_signaled(rq)) @@ -483,6 +530,21 @@ static inline bool i915_request_has_sentinel(const struct i915_request *rq) return unlikely(test_bit(I915_FENCE_FLAG_SENTINEL, &rq->fence.flags)); } +static inline bool i915_request_on_hold(const struct i915_request *rq) +{ + return unlikely(test_bit(I915_FENCE_FLAG_HOLD, &rq->fence.flags)); +} + +static inline void i915_request_set_hold(struct i915_request *rq) +{ + set_bit(I915_FENCE_FLAG_HOLD, &rq->fence.flags); +} + +static inline void i915_request_clear_hold(struct i915_request *rq) +{ + clear_bit(I915_FENCE_FLAG_HOLD, &rq->fence.flags); +} + static inline struct intel_timeline * i915_request_timeline(struct i915_request *rq) { diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c index bf87c70bfdd9630b50af237503e5389c478e2715..34b654b4e58af2b7fb3eb22b4bcecd65c74c9e2f 100644 --- a/drivers/gpu/drm/i915/i915_scheduler.c +++ b/drivers/gpu/drm/i915/i915_scheduler.c @@ -326,20 +326,18 @@ static void __i915_schedule(struct i915_sched_node *node, node->attr.priority = prio; - if (list_empty(&node->link)) { - /* - * If the request is not in the priolist queue because - * it is not yet runnable, then it doesn't contribute - * to our preemption decisions. On the other hand, - * if the request is on the HW, it too is not in the - * queue; but in that case we may still need to reorder - * the inflight requests. - */ + /* + * Once the request is ready, it will be placed into the + * priority lists and then onto the HW runlist. Before the + * request is ready, it does not contribute to our preemption + * decisions and we can safely ignore it, as it will, and + * any preemption required, be dealt with upon submission. + * See engine->submit_request() + */ + if (list_empty(&node->link)) continue; - } - if (!intel_engine_is_virtual(engine) && - !i915_request_is_active(node_to_request(node))) { + if (i915_request_in_priority_queue(node_to_request(node))) { if (!cache.priolist) cache.priolist = i915_sched_lookup_priolist(engine, @@ -425,8 +423,6 @@ bool __i915_sched_node_add_dependency(struct i915_sched_node *node, if (!node_signaled(signal)) { INIT_LIST_HEAD(&dep->dfs_link); - list_add(&dep->wait_link, &signal->waiters_list); - list_add(&dep->signal_link, &node->signalers_list); dep->signaler = signal; dep->waiter = node; dep->flags = flags; @@ -436,6 +432,10 @@ bool __i915_sched_node_add_dependency(struct i915_sched_node *node, !node_started(signal)) node->flags |= I915_SCHED_HAS_SEMAPHORE_CHAIN; + /* All set, now publish. Beware the lockless walkers. */ + list_add(&dep->signal_link, &node->signalers_list); + list_add_rcu(&dep->wait_link, &signal->waiters_list); + /* * As we do not allow WAIT to preempt inflight requests, * once we have executed a request, along with triggering diff --git a/drivers/gpu/drm/i915/i915_utils.c b/drivers/gpu/drm/i915/i915_utils.c index c47261ae86eab09b1341059a3ec9cb36db6767a8..632d6953c78da92bfe4edbcf58407984a0c39c47 100644 --- a/drivers/gpu/drm/i915/i915_utils.c +++ b/drivers/gpu/drm/i915/i915_utils.c @@ -8,9 +8,8 @@ #include "i915_drv.h" #include "i915_utils.h" -#define FDO_BUG_URL "https://bugs.freedesktop.org/enter_bug.cgi?product=DRI" -#define FDO_BUG_MSG "Please file a bug at " FDO_BUG_URL " against DRM/Intel " \ - "providing the dmesg log by booting with drm.debug=0xf" +#define FDO_BUG_URL "https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs" +#define FDO_BUG_MSG "Please file a bug on drm/i915; see " FDO_BUG_URL " for details." void __i915_printk(struct drm_i915_private *dev_priv, const char *level, diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h index b0ade76bec90e282c52041b8f6b0bf7adb2594ff..d34141f7dcd8fcb7c211e0997b89caf21e1106e8 100644 --- a/drivers/gpu/drm/i915/i915_utils.h +++ b/drivers/gpu/drm/i915/i915_utils.h @@ -234,6 +234,11 @@ static inline u64 ptr_to_u64(const void *ptr) __idx; \ }) +static inline bool is_power_of_2_u64(u64 n) +{ + return (n != 0 && ((n & (n - 1)) == 0)); +} + static inline void __list_del_many(struct list_head *head, struct list_head *first) { diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 17d7c525ea5cdd104ec7364a7347f76abdbdd700..4ff380770b32936dea3c8eaf9c3e7f31cb342d35 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -1202,16 +1202,26 @@ int __i915_vma_unbind(struct i915_vma *vma) if (ret) return ret; - GEM_BUG_ON(i915_vma_is_active(vma)); if (i915_vma_is_pinned(vma)) { vma_print_allocator(vma, "is pinned"); return -EAGAIN; } - GEM_BUG_ON(i915_vma_is_active(vma)); + /* + * After confirming that no one else is pinning this vma, wait for + * any laggards who may have crept in during the wait (through + * a residual pin skipping the vm->mutex) to complete. + */ + ret = i915_vma_sync(vma); + if (ret) + return ret; + if (!drm_mm_node_allocated(&vma->node)) return 0; + GEM_BUG_ON(i915_vma_is_pinned(vma)); + GEM_BUG_ON(i915_vma_is_active(vma)); + if (i915_vma_is_map_and_fenceable(vma)) { /* * Check that we have flushed all writes through the GGTT diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c index 0dfcd1787e6519a3c6371938cb5ba8a761be1a9c..fe85e487e477d294db13876d918cf599364bdc55 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c @@ -486,6 +486,7 @@ static void mtk_drm_crtc_hw_config(struct mtk_drm_crtc *mtk_crtc) } #if IS_REACHABLE(CONFIG_MTK_CMDQ) if (mtk_crtc->cmdq_client) { + mbox_flush(mtk_crtc->cmdq_client->chan, 2000); cmdq_handle = cmdq_pkt_create(mtk_crtc->cmdq_client, PAGE_SIZE); cmdq_pkt_clear_event(cmdq_handle, mtk_crtc->cmdq_event); cmdq_pkt_wfe(cmdq_handle, mtk_crtc->cmdq_event); @@ -636,10 +637,18 @@ static const struct drm_crtc_helper_funcs mtk_crtc_helper_funcs = { static int mtk_drm_crtc_init(struct drm_device *drm, struct mtk_drm_crtc *mtk_crtc, - struct drm_plane *primary, - struct drm_plane *cursor, unsigned int pipe) + unsigned int pipe) { - int ret; + struct drm_plane *primary = NULL; + struct drm_plane *cursor = NULL; + int i, ret; + + for (i = 0; i < mtk_crtc->layer_nr; i++) { + if (mtk_crtc->planes[i].type == DRM_PLANE_TYPE_PRIMARY) + primary = &mtk_crtc->planes[i]; + else if (mtk_crtc->planes[i].type == DRM_PLANE_TYPE_CURSOR) + cursor = &mtk_crtc->planes[i]; + } ret = drm_crtc_init_with_planes(drm, &mtk_crtc->base, primary, cursor, &mtk_crtc_funcs, NULL); @@ -689,11 +698,12 @@ static int mtk_drm_crtc_num_comp_planes(struct mtk_drm_crtc *mtk_crtc, } static inline -enum drm_plane_type mtk_drm_crtc_plane_type(unsigned int plane_idx) +enum drm_plane_type mtk_drm_crtc_plane_type(unsigned int plane_idx, + unsigned int num_planes) { if (plane_idx == 0) return DRM_PLANE_TYPE_PRIMARY; - else if (plane_idx == 1) + else if (plane_idx == (num_planes - 1)) return DRM_PLANE_TYPE_CURSOR; else return DRM_PLANE_TYPE_OVERLAY; @@ -712,7 +722,8 @@ static int mtk_drm_crtc_init_comp_planes(struct drm_device *drm_dev, ret = mtk_plane_init(drm_dev, &mtk_crtc->planes[mtk_crtc->layer_nr], BIT(pipe), - mtk_drm_crtc_plane_type(mtk_crtc->layer_nr), + mtk_drm_crtc_plane_type(mtk_crtc->layer_nr, + num_planes), mtk_ddp_comp_supported_rotations(comp)); if (ret) return ret; @@ -807,9 +818,7 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev, return ret; } - ret = mtk_drm_crtc_init(drm_dev, mtk_crtc, &mtk_crtc->planes[0], - mtk_crtc->layer_nr > 1 ? &mtk_crtc->planes[1] : - NULL, pipe); + ret = mtk_drm_crtc_init(drm_dev, mtk_crtc, pipe); if (ret < 0) return ret; @@ -828,7 +837,8 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev, drm_crtc_index(&mtk_crtc->base)); mtk_crtc->cmdq_client = NULL; } - ret = of_property_read_u32_index(dev->of_node, "mediatek,gce-events", + ret = of_property_read_u32_index(priv->mutex_node, + "mediatek,gce-events", drm_crtc_index(&mtk_crtc->base), &mtk_crtc->cmdq_event); if (ret) diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c index 1f5a112bb034d76ed145f09863b003bd6cb31a4a..57c88de9a3293447e70965c6628258f7c9f31e05 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c @@ -471,6 +471,7 @@ int mtk_ddp_comp_init(struct device *dev, struct device_node *node, /* Only DMA capable components need the LARB property */ comp->larb_dev = NULL; if (type != MTK_DISP_OVL && + type != MTK_DISP_OVL_2L && type != MTK_DISP_RDMA && type != MTK_DISP_WDMA) return 0; diff --git a/drivers/gpu/drm/mediatek/mtk_drm_plane.c b/drivers/gpu/drm/mediatek/mtk_drm_plane.c index 914cc7619cd7747373577fd1ca67b6236000ec42..c2bd683a87c82857c74e508833d56256b731160b 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_plane.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_plane.c @@ -80,6 +80,7 @@ static int mtk_plane_atomic_async_check(struct drm_plane *plane, struct drm_plane_state *state) { struct drm_crtc_state *crtc_state; + int ret; if (plane != state->crtc->cursor) return -EINVAL; @@ -90,6 +91,11 @@ static int mtk_plane_atomic_async_check(struct drm_plane *plane, if (!plane->state->fb) return -EINVAL; + ret = mtk_drm_crtc_plane_check(state->crtc, plane, + to_mtk_plane_state(state)); + if (ret) + return ret; + if (state->state) crtc_state = drm_atomic_get_existing_crtc_state(state->state, state->crtc); @@ -115,6 +121,7 @@ static void mtk_plane_atomic_async_update(struct drm_plane *plane, plane->state->src_y = new_state->src_y; plane->state->src_h = new_state->src_h; plane->state->src_w = new_state->src_w; + swap(plane->state->fb, new_state->fb); state->pending.async_dirty = true; mtk_drm_crtc_async_update(new_state->crtc, plane, new_state); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index 983afeaee737ea27593f988ae5eb00a68e0a1c76..748cd379065f1103240ecf4dd4af72d635f63318 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -796,12 +796,41 @@ bool a6xx_gmu_isidle(struct a6xx_gmu *gmu) return true; } +#define GBIF_CLIENT_HALT_MASK BIT(0) +#define GBIF_ARB_HALT_MASK BIT(1) + +static void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu) +{ + struct msm_gpu *gpu = &adreno_gpu->base; + + if (!a6xx_has_gbif(adreno_gpu)) { + gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0xf); + spin_until((gpu_read(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL1) & + 0xf) == 0xf); + gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0); + + return; + } + + /* Halt new client requests on GBIF */ + gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_CLIENT_HALT_MASK); + spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) & + (GBIF_CLIENT_HALT_MASK)) == GBIF_CLIENT_HALT_MASK); + + /* Halt all AXI requests on GBIF */ + gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_ARB_HALT_MASK); + spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) & + (GBIF_ARB_HALT_MASK)) == GBIF_ARB_HALT_MASK); + + /* The GBIF halt needs to be explicitly cleared */ + gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0); +} + /* Gracefully try to shut down the GMU and by extension the GPU */ static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu) { struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; - struct msm_gpu *gpu = &adreno_gpu->base; u32 val; /* @@ -819,11 +848,7 @@ static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu) return; } - /* Clear the VBIF pipe before shutting down */ - gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0xf); - spin_until((gpu_read(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL1) & 0xf) - == 0xf); - gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0); + a6xx_bus_clear_pending_transactions(adreno_gpu); /* tell the GMU we want to slumber */ a6xx_gmu_notify_slumber(gmu); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index daf07800cde02a1ecc4797508dc1a631f38892da..68af24150de57c626f31231a06ab364b844da1b9 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -378,18 +378,6 @@ static int a6xx_hw_init(struct msm_gpu *gpu) struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); int ret; - /* - * During a previous slumber, GBIF halt is asserted to ensure - * no further transaction can go through GPU before GPU - * headswitch is turned off. - * - * This halt is deasserted once headswitch goes off but - * incase headswitch doesn't goes off clear GBIF halt - * here to ensure GPU wake-up doesn't fail because of - * halted GPU transactions. - */ - gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0); - /* Make sure the GMU keeps the GPU on while we set it up */ a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET); @@ -470,10 +458,12 @@ static int a6xx_hw_init(struct msm_gpu *gpu) /* Select CP0 to always count cycles */ gpu_write(gpu, REG_A6XX_CP_PERFCTR_CP_SEL_0, PERF_CP_ALWAYS_COUNT); - gpu_write(gpu, REG_A6XX_RB_NC_MODE_CNTL, 2 << 1); - gpu_write(gpu, REG_A6XX_TPL1_NC_MODE_CNTL, 2 << 1); - gpu_write(gpu, REG_A6XX_SP_NC_MODE_CNTL, 2 << 1); - gpu_write(gpu, REG_A6XX_UCHE_MODE_CNTL, 2 << 21); + if (adreno_is_a630(adreno_gpu)) { + gpu_write(gpu, REG_A6XX_RB_NC_MODE_CNTL, 2 << 1); + gpu_write(gpu, REG_A6XX_TPL1_NC_MODE_CNTL, 2 << 1); + gpu_write(gpu, REG_A6XX_SP_NC_MODE_CNTL, 2 << 1); + gpu_write(gpu, REG_A6XX_UCHE_MODE_CNTL, 2 << 21); + } /* Enable fault detection */ gpu_write(gpu, REG_A6XX_RBBM_INTERFACE_HANG_INT_CNTL, @@ -748,39 +738,6 @@ static const u32 a6xx_register_offsets[REG_ADRENO_REGISTER_MAX] = { REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_CNTL, REG_A6XX_CP_RB_CNTL), }; -#define GBIF_CLIENT_HALT_MASK BIT(0) -#define GBIF_ARB_HALT_MASK BIT(1) - -static void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu) -{ - struct msm_gpu *gpu = &adreno_gpu->base; - - if(!a6xx_has_gbif(adreno_gpu)){ - gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0xf); - spin_until((gpu_read(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL1) & - 0xf) == 0xf); - gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0); - - return; - } - - /* Halt new client requests on GBIF */ - gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_CLIENT_HALT_MASK); - spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) & - (GBIF_CLIENT_HALT_MASK)) == GBIF_CLIENT_HALT_MASK); - - /* Halt all AXI requests on GBIF */ - gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_ARB_HALT_MASK); - spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) & - (GBIF_ARB_HALT_MASK)) == GBIF_ARB_HALT_MASK); - - /* - * GMU needs DDR access in slumber path. Deassert GBIF halt now - * to allow for GMU to access system memory. - */ - gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0); -} - static int a6xx_pm_resume(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); @@ -805,16 +762,6 @@ static int a6xx_pm_suspend(struct msm_gpu *gpu) devfreq_suspend_device(gpu->devfreq.devfreq); - /* - * Make sure the GMU is idle before continuing (because some transitions - * may use VBIF - */ - a6xx_gmu_wait_for_idle(&a6xx_gpu->gmu); - - /* Clear the VBIF pipe before shutting down */ - /* FIXME: This accesses the GPU - do we need to make sure it is on? */ - a6xx_bus_clear_pending_transactions(adreno_gpu); - return a6xx_gmu_stop(a6xx_gpu); } diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c index eda11abc5f011f1a8ef8bab3feb19274d6c0277f..e450e0b97211533160878013cb72ac0a358d927b 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c @@ -7,6 +7,7 @@ #include "a6xx_gmu.h" #include "a6xx_gmu.xml.h" +#include "a6xx_gpu.h" #define HFI_MSG_ID(val) [val] = #val @@ -216,48 +217,82 @@ static int a6xx_hfi_send_perf_table(struct a6xx_gmu *gmu) NULL, 0); } -static int a6xx_hfi_send_bw_table(struct a6xx_gmu *gmu) +static void a618_build_bw_table(struct a6xx_hfi_msg_bw_table *msg) { - struct a6xx_hfi_msg_bw_table msg = { 0 }; + /* Send a single "off" entry since the 618 GMU doesn't do bus scaling */ + msg->bw_level_num = 1; + + msg->ddr_cmds_num = 3; + msg->ddr_wait_bitmask = 0x01; + + msg->ddr_cmds_addrs[0] = 0x50000; + msg->ddr_cmds_addrs[1] = 0x5003c; + msg->ddr_cmds_addrs[2] = 0x5000c; + + msg->ddr_cmds_data[0][0] = 0x40000000; + msg->ddr_cmds_data[0][1] = 0x40000000; + msg->ddr_cmds_data[0][2] = 0x40000000; /* - * The sdm845 GMU doesn't do bus frequency scaling on its own but it - * does need at least one entry in the list because it might be accessed - * when the GMU is shutting down. Send a single "off" entry. + * These are the CX (CNOC) votes - these are used by the GMU but the + * votes are known and fixed for the target */ + msg->cnoc_cmds_num = 1; + msg->cnoc_wait_bitmask = 0x01; + + msg->cnoc_cmds_addrs[0] = 0x5007c; + msg->cnoc_cmds_data[0][0] = 0x40000000; + msg->cnoc_cmds_data[1][0] = 0x60000001; +} - msg.bw_level_num = 1; +static void a6xx_build_bw_table(struct a6xx_hfi_msg_bw_table *msg) +{ + /* Send a single "off" entry since the 630 GMU doesn't do bus scaling */ + msg->bw_level_num = 1; - msg.ddr_cmds_num = 3; - msg.ddr_wait_bitmask = 0x07; + msg->ddr_cmds_num = 3; + msg->ddr_wait_bitmask = 0x07; - msg.ddr_cmds_addrs[0] = 0x50000; - msg.ddr_cmds_addrs[1] = 0x5005c; - msg.ddr_cmds_addrs[2] = 0x5000c; + msg->ddr_cmds_addrs[0] = 0x50000; + msg->ddr_cmds_addrs[1] = 0x5005c; + msg->ddr_cmds_addrs[2] = 0x5000c; - msg.ddr_cmds_data[0][0] = 0x40000000; - msg.ddr_cmds_data[0][1] = 0x40000000; - msg.ddr_cmds_data[0][2] = 0x40000000; + msg->ddr_cmds_data[0][0] = 0x40000000; + msg->ddr_cmds_data[0][1] = 0x40000000; + msg->ddr_cmds_data[0][2] = 0x40000000; /* * These are the CX (CNOC) votes. This is used but the values for the * sdm845 GMU are known and fixed so we can hard code them. */ - msg.cnoc_cmds_num = 3; - msg.cnoc_wait_bitmask = 0x05; + msg->cnoc_cmds_num = 3; + msg->cnoc_wait_bitmask = 0x05; - msg.cnoc_cmds_addrs[0] = 0x50034; - msg.cnoc_cmds_addrs[1] = 0x5007c; - msg.cnoc_cmds_addrs[2] = 0x5004c; + msg->cnoc_cmds_addrs[0] = 0x50034; + msg->cnoc_cmds_addrs[1] = 0x5007c; + msg->cnoc_cmds_addrs[2] = 0x5004c; - msg.cnoc_cmds_data[0][0] = 0x40000000; - msg.cnoc_cmds_data[0][1] = 0x00000000; - msg.cnoc_cmds_data[0][2] = 0x40000000; + msg->cnoc_cmds_data[0][0] = 0x40000000; + msg->cnoc_cmds_data[0][1] = 0x00000000; + msg->cnoc_cmds_data[0][2] = 0x40000000; + + msg->cnoc_cmds_data[1][0] = 0x60000001; + msg->cnoc_cmds_data[1][1] = 0x20000001; + msg->cnoc_cmds_data[1][2] = 0x60000001; +} + + +static int a6xx_hfi_send_bw_table(struct a6xx_gmu *gmu) +{ + struct a6xx_hfi_msg_bw_table msg = { 0 }; + struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); + struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; - msg.cnoc_cmds_data[1][0] = 0x60000001; - msg.cnoc_cmds_data[1][1] = 0x20000001; - msg.cnoc_cmds_data[1][2] = 0x60000001; + if (adreno_is_a618(adreno_gpu)) + a618_build_bw_table(&msg); + else + a6xx_build_bw_table(&msg); return a6xx_hfi_send_msg(gmu, HFI_H2F_MSG_BW_TABLE, &msg, sizeof(msg), NULL, 0); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c index 528632690f1ef4f6d0ab476f10d3c26e68540d1c..a05282dede91b6530d4a5d01a1df88dd90ee84a1 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c @@ -255,13 +255,13 @@ static const struct dpu_format dpu_format_map[] = { INTERLEAVED_RGB_FMT(RGB565, 0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT, - C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3, + C1_B_Cb, C0_G_Y, C2_R_Cr, 0, 3, false, 2, 0, DPU_FETCH_LINEAR, 1), INTERLEAVED_RGB_FMT(BGR565, 0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT, - C1_B_Cb, C0_G_Y, C2_R_Cr, 0, 3, + C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3, false, 2, 0, DPU_FETCH_LINEAR, 1), diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c index 29705e773a4b7035d6f9981a6a846deaf60231a8..80d3cfc140070d0cd3006981fb473a3cc453710e 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c @@ -12,6 +12,7 @@ #define to_dpu_mdss(x) container_of(x, struct dpu_mdss, base) +#define HW_REV 0x0 #define HW_INTR_STATUS 0x0010 /* Max BW defined in KBps */ @@ -22,6 +23,17 @@ struct dpu_irq_controller { struct irq_domain *domain; }; +struct dpu_hw_cfg { + u32 val; + u32 offset; +}; + +struct dpu_mdss_hw_init_handler { + u32 hw_rev; + u32 hw_reg_count; + struct dpu_hw_cfg* hw_cfg; +}; + struct dpu_mdss { struct msm_mdss base; void __iomem *mmio; @@ -32,6 +44,44 @@ struct dpu_mdss { u32 num_paths; }; +static struct dpu_hw_cfg hw_cfg[] = { + { + /* UBWC global settings */ + .val = 0x1E, + .offset = 0x144, + } +}; + +static struct dpu_mdss_hw_init_handler cfg_handler[] = { + { .hw_rev = DPU_HW_VER_620, + .hw_reg_count = ARRAY_SIZE(hw_cfg), + .hw_cfg = hw_cfg + }, +}; + +static void dpu_mdss_hw_init(struct dpu_mdss *dpu_mdss, u32 hw_rev) +{ + int i; + u32 count = 0; + struct dpu_hw_cfg *hw_cfg = NULL; + + for (i = 0; i < ARRAY_SIZE(cfg_handler); i++) { + if (cfg_handler[i].hw_rev == hw_rev) { + hw_cfg = cfg_handler[i].hw_cfg; + count = cfg_handler[i].hw_reg_count; + break; + } + } + + for (i = 0; i < count; i++ ) { + writel_relaxed(hw_cfg->val, + dpu_mdss->mmio + hw_cfg->offset); + hw_cfg++; + } + + return; +} + static int dpu_mdss_parse_data_bus_icc_path(struct drm_device *dev, struct dpu_mdss *dpu_mdss) { @@ -174,12 +224,18 @@ static int dpu_mdss_enable(struct msm_mdss *mdss) struct dpu_mdss *dpu_mdss = to_dpu_mdss(mdss); struct dss_module_power *mp = &dpu_mdss->mp; int ret; + u32 mdss_rev; dpu_mdss_icc_request_bw(mdss); ret = msm_dss_enable_clk(mp->clk_config, mp->num_clk, true); - if (ret) + if (ret) { DPU_ERROR("clock enable failed, ret:%d\n", ret); + return ret; + } + + mdss_rev = readl_relaxed(dpu_mdss->mmio + HW_REV); + dpu_mdss_hw_init(dpu_mdss, mdss_rev); return ret; } diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c index 05cc04f729d638963325b03a288ad502cccae822..e1cc541e0ef2e37a44d20378c1e3b37a493578d6 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c @@ -1109,8 +1109,8 @@ static void mdp5_crtc_wait_for_pp_done(struct drm_crtc *crtc) ret = wait_for_completion_timeout(&mdp5_crtc->pp_completion, msecs_to_jiffies(50)); if (ret == 0) - dev_warn(dev->dev, "pp done time out, lm=%d\n", - mdp5_cstate->pipeline.mixer->lm); + dev_warn_ratelimited(dev->dev, "pp done time out, lm=%d\n", + mdp5_cstate->pipeline.mixer->lm); } static void mdp5_crtc_wait_for_flush_done(struct drm_crtc *crtc) diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c index 104115d112eba6aebc87cb464c9b89a3c513b945..4864b9558f65ab6674a2df30444262afcca09405 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_manager.c +++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c @@ -336,7 +336,7 @@ static int dsi_mgr_connector_get_modes(struct drm_connector *connector) return num; } -static int dsi_mgr_connector_mode_valid(struct drm_connector *connector, +static enum drm_mode_status dsi_mgr_connector_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { int id = dsi_mgr_connector_get_id(connector); @@ -506,6 +506,7 @@ static void dsi_mgr_bridge_post_disable(struct drm_bridge *bridge) struct msm_dsi *msm_dsi1 = dsi_mgr_get_dsi(DSI_1); struct mipi_dsi_host *host = msm_dsi->host; struct drm_panel *panel = msm_dsi->panel; + struct msm_dsi_pll *src_pll; bool is_dual_dsi = IS_DUAL_DSI(); int ret; @@ -539,6 +540,10 @@ static void dsi_mgr_bridge_post_disable(struct drm_bridge *bridge) id, ret); } + /* Save PLL status if it is a clock source */ + src_pll = msm_dsi_phy_get_pll(msm_dsi->phy); + msm_dsi_pll_save_state(src_pll); + ret = msm_dsi_host_power_off(host); if (ret) pr_err("%s: host %d power off failed,%d\n", __func__, id, ret); diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c index b0cfa67d2a57806bc1e9cd7cb4846ebcfe8c08bd..f509ebd77500f43bbcd846de9c1ff44e5ec2eb2e 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c @@ -724,10 +724,6 @@ void msm_dsi_phy_disable(struct msm_dsi_phy *phy) if (!phy || !phy->cfg->ops.disable) return; - /* Save PLL status if it is a clock source */ - if (phy->usecase != MSM_DSI_PHY_SLAVE) - msm_dsi_pll_save_state(phy->pll); - phy->cfg->ops.disable(phy); dsi_phy_regulator_disable(phy); diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c index 1c894548dd725c8365bc4eae9b98446ea36739e1..6ac04fc303f5699ba29b356e714c35ea96b6f12e 100644 --- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c +++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c @@ -411,6 +411,12 @@ static int dsi_pll_10nm_vco_prepare(struct clk_hw *hw) if (pll_10nm->slave) dsi_pll_enable_pll_bias(pll_10nm->slave); + rc = dsi_pll_10nm_vco_set_rate(hw,pll_10nm->vco_current_rate, 0); + if (rc) { + pr_err("vco_set_rate failed, rc=%d\n", rc); + return rc; + } + /* Start PLL */ pll_write(pll_10nm->phy_cmn_mmio + REG_DSI_10nm_PHY_CMN_PLL_CNTRL, 0x01); diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index c26219c7a49fd18b29648a929a92453b4c894788..e4b750b0c2d3fcdad40761fe6cae1597b2844164 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -441,6 +441,14 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv) if (ret) goto err_msm_uninit; + if (!dev->dma_parms) { + dev->dma_parms = devm_kzalloc(dev, sizeof(*dev->dma_parms), + GFP_KERNEL); + if (!dev->dma_parms) + return -ENOMEM; + } + dma_set_max_seg_size(dev, DMA_BIT_MASK(32)); + msm_gem_shrinker_init(ddev); switch (get_mdp_ver(pdev)) { diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c index 890315291b01eff70a13ca6a3232517f970f4e65..bb737f9281e692f2adf4a3c8e93d7081b022b7ea 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c +++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c @@ -458,6 +458,8 @@ nv50_wndw_atomic_check(struct drm_plane *plane, struct drm_plane_state *state) asyw->clr.ntfy = armw->ntfy.handle != 0; asyw->clr.sema = armw->sema.handle != 0; asyw->clr.xlut = armw->xlut.handle != 0; + if (asyw->clr.xlut && asyw->visible) + asyw->set.xlut = asyw->xlut.handle != 0; asyw->clr.csc = armw->csc.valid; if (wndw->func->image_clr) asyw->clr.image = armw->image.handle[0] != 0; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c index c7d700916eae7356fa8f9e7e501c9a1efe255967..8ebbe16560083dc573b41dc0336d217264d0909d 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c @@ -2579,6 +2579,7 @@ nv166_chipset = { static const struct nvkm_device_chip nv167_chipset = { .name = "TU117", + .acr = tu102_acr_new, .bar = tu102_bar_new, .bios = nvkm_bios_new, .bus = gf100_bus_new, @@ -2607,6 +2608,7 @@ nv167_chipset = { .disp = tu102_disp_new, .dma = gv100_dma_new, .fifo = tu102_fifo_new, + .gr = tu102_gr_new, .nvdec[0] = gm107_nvdec_new, .nvenc[0] = gm107_nvenc_new, .sec2 = tu102_sec2_new, @@ -2615,6 +2617,7 @@ nv167_chipset = { static const struct nvkm_device_chip nv168_chipset = { .name = "TU116", + .acr = tu102_acr_new, .bar = tu102_bar_new, .bios = nvkm_bios_new, .bus = gf100_bus_new, @@ -2643,6 +2646,7 @@ nv168_chipset = { .disp = tu102_disp_new, .dma = gv100_dma_new, .fifo = tu102_fifo_new, + .gr = tu102_gr_new, .nvdec[0] = gm107_nvdec_new, .nvenc[0] = gm107_nvenc_new, .sec2 = tu102_sec2_new, diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/tu102.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/tu102.c index 454668b1cf54d5975f59a6694c5fd474845fb0f5..a9efa4d78be92a808f41e9a9b9329ec0d99cb5f6 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/tu102.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/tu102.c @@ -164,6 +164,32 @@ MODULE_FIRMWARE("nvidia/tu106/gr/sw_nonctx.bin"); MODULE_FIRMWARE("nvidia/tu106/gr/sw_bundle_init.bin"); MODULE_FIRMWARE("nvidia/tu106/gr/sw_method_init.bin"); +MODULE_FIRMWARE("nvidia/tu117/gr/fecs_bl.bin"); +MODULE_FIRMWARE("nvidia/tu117/gr/fecs_inst.bin"); +MODULE_FIRMWARE("nvidia/tu117/gr/fecs_data.bin"); +MODULE_FIRMWARE("nvidia/tu117/gr/fecs_sig.bin"); +MODULE_FIRMWARE("nvidia/tu117/gr/gpccs_bl.bin"); +MODULE_FIRMWARE("nvidia/tu117/gr/gpccs_inst.bin"); +MODULE_FIRMWARE("nvidia/tu117/gr/gpccs_data.bin"); +MODULE_FIRMWARE("nvidia/tu117/gr/gpccs_sig.bin"); +MODULE_FIRMWARE("nvidia/tu117/gr/sw_ctx.bin"); +MODULE_FIRMWARE("nvidia/tu117/gr/sw_nonctx.bin"); +MODULE_FIRMWARE("nvidia/tu117/gr/sw_bundle_init.bin"); +MODULE_FIRMWARE("nvidia/tu117/gr/sw_method_init.bin"); + +MODULE_FIRMWARE("nvidia/tu116/gr/fecs_bl.bin"); +MODULE_FIRMWARE("nvidia/tu116/gr/fecs_inst.bin"); +MODULE_FIRMWARE("nvidia/tu116/gr/fecs_data.bin"); +MODULE_FIRMWARE("nvidia/tu116/gr/fecs_sig.bin"); +MODULE_FIRMWARE("nvidia/tu116/gr/gpccs_bl.bin"); +MODULE_FIRMWARE("nvidia/tu116/gr/gpccs_inst.bin"); +MODULE_FIRMWARE("nvidia/tu116/gr/gpccs_data.bin"); +MODULE_FIRMWARE("nvidia/tu116/gr/gpccs_sig.bin"); +MODULE_FIRMWARE("nvidia/tu116/gr/sw_ctx.bin"); +MODULE_FIRMWARE("nvidia/tu116/gr/sw_nonctx.bin"); +MODULE_FIRMWARE("nvidia/tu116/gr/sw_bundle_init.bin"); +MODULE_FIRMWARE("nvidia/tu116/gr/sw_method_init.bin"); + static const struct gf100_gr_fwif tu102_gr_fwif[] = { { 0, gm200_gr_load, &tu102_gr, &gp108_gr_fecs_acr, &gp108_gr_gpccs_acr }, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/tu102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/tu102.c index 7f4b89d82d320a0b7ec6e0e2fe4b981b569ff2b0..d28d8f36ae2484ac4d237ad0fb3750b2d52b53b7 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/tu102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/tu102.c @@ -107,6 +107,12 @@ MODULE_FIRMWARE("nvidia/tu104/acr/ucode_unload.bin"); MODULE_FIRMWARE("nvidia/tu106/acr/unload_bl.bin"); MODULE_FIRMWARE("nvidia/tu106/acr/ucode_unload.bin"); +MODULE_FIRMWARE("nvidia/tu116/acr/unload_bl.bin"); +MODULE_FIRMWARE("nvidia/tu116/acr/ucode_unload.bin"); + +MODULE_FIRMWARE("nvidia/tu117/acr/unload_bl.bin"); +MODULE_FIRMWARE("nvidia/tu117/acr/ucode_unload.bin"); + static const struct nvkm_acr_hsf_fwif tu102_acr_unload_fwif[] = { { 0, nvkm_acr_hsfw_load, &gp108_acr_unload_0 }, @@ -130,6 +136,8 @@ tu102_acr_asb_0 = { MODULE_FIRMWARE("nvidia/tu102/acr/ucode_asb.bin"); MODULE_FIRMWARE("nvidia/tu104/acr/ucode_asb.bin"); MODULE_FIRMWARE("nvidia/tu106/acr/ucode_asb.bin"); +MODULE_FIRMWARE("nvidia/tu116/acr/ucode_asb.bin"); +MODULE_FIRMWARE("nvidia/tu117/acr/ucode_asb.bin"); static const struct nvkm_acr_hsf_fwif tu102_acr_asb_fwif[] = { @@ -154,6 +162,12 @@ MODULE_FIRMWARE("nvidia/tu104/acr/ucode_ahesasc.bin"); MODULE_FIRMWARE("nvidia/tu106/acr/bl.bin"); MODULE_FIRMWARE("nvidia/tu106/acr/ucode_ahesasc.bin"); +MODULE_FIRMWARE("nvidia/tu116/acr/bl.bin"); +MODULE_FIRMWARE("nvidia/tu116/acr/ucode_ahesasc.bin"); + +MODULE_FIRMWARE("nvidia/tu117/acr/bl.bin"); +MODULE_FIRMWARE("nvidia/tu117/acr/ucode_ahesasc.bin"); + static const struct nvkm_acr_hsf_fwif tu102_acr_ahesasc_fwif[] = { { 0, nvkm_acr_hsfw_load, &tu102_acr_ahesasc_0 }, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c index 389bad312bf279bd15102d121728e2a11607473e..10ff5d053f7ea4e0f0645028906da0d6acc2a031 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c @@ -51,3 +51,5 @@ MODULE_FIRMWARE("nvidia/gv100/nvdec/scrubber.bin"); MODULE_FIRMWARE("nvidia/tu102/nvdec/scrubber.bin"); MODULE_FIRMWARE("nvidia/tu104/nvdec/scrubber.bin"); MODULE_FIRMWARE("nvidia/tu106/nvdec/scrubber.bin"); +MODULE_FIRMWARE("nvidia/tu116/nvdec/scrubber.bin"); +MODULE_FIRMWARE("nvidia/tu117/nvdec/scrubber.bin"); diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c index 6da59f476aba6b793c238dc8ac65bd74e1647be7..b7a618db3ee223ec491ba66279b6c46e634146a1 100644 --- a/drivers/gpu/drm/panfrost/panfrost_drv.c +++ b/drivers/gpu/drm/panfrost/panfrost_drv.c @@ -166,6 +166,7 @@ panfrost_lookup_bos(struct drm_device *dev, break; } + atomic_inc(&bo->gpu_usecount); job->mappings[i] = mapping; } diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.h b/drivers/gpu/drm/panfrost/panfrost_gem.h index ca1bc9019600c839d384a6564a2dcf4d8e7be87a..b3517ff9630cb23a8753d066303fb5880adcf984 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gem.h +++ b/drivers/gpu/drm/panfrost/panfrost_gem.h @@ -30,6 +30,12 @@ struct panfrost_gem_object { struct mutex lock; } mappings; + /* + * Count the number of jobs referencing this BO so we don't let the + * shrinker reclaim this object prematurely. + */ + atomic_t gpu_usecount; + bool noexec :1; bool is_heap :1; }; diff --git a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c index f5dd7b29bc954909ad5d1508863c4b8a9e5db007..288e46c40673a9d102580030b8a107c2d2af3572 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c +++ b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c @@ -41,6 +41,9 @@ static bool panfrost_gem_purge(struct drm_gem_object *obj) struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj); struct panfrost_gem_object *bo = to_panfrost_bo(obj); + if (atomic_read(&bo->gpu_usecount)) + return false; + if (!mutex_trylock(&shmem->pages_lock)) return false; diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c index 7c36ec675b73dd464b554f177c22b996e131c930..9a1a72a748e724ca5bac36d4e05c82eb4ccd1f93 100644 --- a/drivers/gpu/drm/panfrost/panfrost_job.c +++ b/drivers/gpu/drm/panfrost/panfrost_job.c @@ -269,18 +269,19 @@ static void panfrost_job_cleanup(struct kref *ref) dma_fence_put(job->render_done_fence); if (job->mappings) { - for (i = 0; i < job->bo_count; i++) + for (i = 0; i < job->bo_count; i++) { + if (!job->mappings[i]) + break; + + atomic_dec(&job->mappings[i]->obj->gpu_usecount); panfrost_gem_mapping_put(job->mappings[i]); + } kvfree(job->mappings); } if (job->bos) { - struct panfrost_gem_object *bo; - - for (i = 0; i < job->bo_count; i++) { - bo = to_panfrost_bo(job->bos[i]); + for (i = 0; i < job->bo_count; i++) drm_gem_object_put_unlocked(job->bos[i]); - } kvfree(job->bos); } diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c index 763cfca886a73a7c90d8d6df9e0e4e36c7d2bf7d..5d75f8cf64776fab746fcb40a2527b62d50cfa5e 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c @@ -151,7 +151,12 @@ u32 panfrost_mmu_as_get(struct panfrost_device *pfdev, struct panfrost_mmu *mmu) as = mmu->as; if (as >= 0) { int en = atomic_inc_return(&mmu->as_count); - WARN_ON(en >= NUM_JOB_SLOTS); + + /* + * AS can be retained by active jobs or a perfcnt context, + * hence the '+ 1' here. + */ + WARN_ON(en >= (NUM_JOB_SLOTS + 1)); list_move(&mmu->list, &pfdev->as_lru_list); goto out; @@ -596,33 +601,27 @@ static irqreturn_t panfrost_mmu_irq_handler_thread(int irq, void *data) source_id = (fault_status >> 16); /* Page fault only */ - if ((status & mask) == BIT(i)) { - WARN_ON(exception_type < 0xC1 || exception_type > 0xC4); - + ret = -1; + if ((status & mask) == BIT(i) && (exception_type & 0xF8) == 0xC0) ret = panfrost_mmu_map_fault_addr(pfdev, i, addr); - if (!ret) { - mmu_write(pfdev, MMU_INT_CLEAR, BIT(i)); - status &= ~mask; - continue; - } - } - /* terminal fault, print info about the fault */ - dev_err(pfdev->dev, - "Unhandled Page fault in AS%d at VA 0x%016llX\n" - "Reason: %s\n" - "raw fault status: 0x%X\n" - "decoded fault status: %s\n" - "exception type 0x%X: %s\n" - "access type 0x%X: %s\n" - "source id 0x%X\n", - i, addr, - "TODO", - fault_status, - (fault_status & (1 << 10) ? "DECODER FAULT" : "SLAVE FAULT"), - exception_type, panfrost_exception_name(pfdev, exception_type), - access_type, access_type_name(pfdev, fault_status), - source_id); + if (ret) + /* terminal fault, print info about the fault */ + dev_err(pfdev->dev, + "Unhandled Page fault in AS%d at VA 0x%016llX\n" + "Reason: %s\n" + "raw fault status: 0x%X\n" + "decoded fault status: %s\n" + "exception type 0x%X: %s\n" + "access type 0x%X: %s\n" + "source id 0x%X\n", + i, addr, + "TODO", + fault_status, + (fault_status & (1 << 10) ? "DECODER FAULT" : "SLAVE FAULT"), + exception_type, panfrost_exception_name(pfdev, exception_type), + access_type, access_type_name(pfdev, fault_status), + source_id); mmu_write(pfdev, MMU_INT_CLEAR, mask); diff --git a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c index 684820448be31c7d459a1f139b5003b8cacd1968..6913578d5aa7211de705877f42d8eb210be5289c 100644 --- a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c +++ b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c @@ -73,7 +73,7 @@ static int panfrost_perfcnt_enable_locked(struct panfrost_device *pfdev, struct panfrost_file_priv *user = file_priv->driver_priv; struct panfrost_perfcnt *perfcnt = pfdev->perfcnt; struct drm_gem_shmem_object *bo; - u32 cfg; + u32 cfg, as; int ret; if (user == perfcnt->user) @@ -126,12 +126,8 @@ static int panfrost_perfcnt_enable_locked(struct panfrost_device *pfdev, perfcnt->user = user; - /* - * Always use address space 0 for now. - * FIXME: this needs to be updated when we start using different - * address space. - */ - cfg = GPU_PERFCNT_CFG_AS(0) | + as = panfrost_mmu_as_get(pfdev, perfcnt->mapping->mmu); + cfg = GPU_PERFCNT_CFG_AS(as) | GPU_PERFCNT_CFG_MODE(GPU_PERFCNT_CFG_MODE_MANUAL); /* @@ -195,6 +191,7 @@ static int panfrost_perfcnt_disable_locked(struct panfrost_device *pfdev, drm_gem_shmem_vunmap(&perfcnt->mapping->obj->base.base, perfcnt->buf); perfcnt->buf = NULL; panfrost_gem_close(&perfcnt->mapping->obj->base.base, file_priv); + panfrost_mmu_as_put(pfdev, perfcnt->mapping->mmu); panfrost_gem_mapping_put(perfcnt->mapping); perfcnt->mapping = NULL; pm_runtime_mark_last_busy(pfdev->dev); diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c index fd74e261118595e8fb4080764ee93eb961935319..8696af1ee14dc7705b9a98f6869d69526d6a1ddd 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -37,6 +37,7 @@ #include #include +#include #include #include #include @@ -325,6 +326,7 @@ static int radeon_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { unsigned long flags = 0; + struct drm_device *dev; int ret; if (!ent) @@ -365,7 +367,44 @@ static int radeon_pci_probe(struct pci_dev *pdev, if (ret) return ret; - return drm_get_pci_dev(pdev, ent, &kms_driver); + dev = drm_dev_alloc(&kms_driver, &pdev->dev); + if (IS_ERR(dev)) + return PTR_ERR(dev); + + ret = pci_enable_device(pdev); + if (ret) + goto err_free; + + dev->pdev = pdev; +#ifdef __alpha__ + dev->hose = pdev->sysdata; +#endif + + pci_set_drvdata(pdev, dev); + + if (pci_find_capability(dev->pdev, PCI_CAP_ID_AGP)) + dev->agp = drm_agp_init(dev); + if (dev->agp) { + dev->agp->agp_mtrr = arch_phys_wc_add( + dev->agp->agp_info.aper_base, + dev->agp->agp_info.aper_size * + 1024 * 1024); + } + + ret = drm_dev_register(dev, ent->driver_data); + if (ret) + goto err_agp; + + return 0; + +err_agp: + if (dev->agp) + arch_phys_wc_del(dev->agp->agp_mtrr); + kfree(dev->agp); + pci_disable_device(pdev); +err_free: + drm_dev_put(dev); + return ret; } static void @@ -575,7 +614,7 @@ radeon_get_crtc_scanout_position(struct drm_device *dev, unsigned int pipe, static struct drm_driver kms_driver = { .driver_features = - DRIVER_USE_AGP | DRIVER_GEM | DRIVER_RENDER, + DRIVER_GEM | DRIVER_RENDER, .load = radeon_driver_load_kms, .open = radeon_driver_open_kms, .postclose = radeon_driver_postclose_kms, diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c index d24f23a8165602a547608777a3cc004e7cc9cc22..dd2f19b8022bd2c215fed2a257e90307b666ea86 100644 --- a/drivers/gpu/drm/radeon/radeon_kms.c +++ b/drivers/gpu/drm/radeon/radeon_kms.c @@ -32,6 +32,7 @@ #include #include +#include #include #include #include @@ -77,6 +78,11 @@ void radeon_driver_unload_kms(struct drm_device *dev) radeon_modeset_fini(rdev); radeon_device_fini(rdev); + if (dev->agp) + arch_phys_wc_del(dev->agp->agp_mtrr); + kfree(dev->agp); + dev->agp = NULL; + done_free: kfree(rdev); dev->dev_private = NULL; diff --git a/drivers/gpu/drm/selftests/drm_cmdline_selftests.h b/drivers/gpu/drm/selftests/drm_cmdline_selftests.h index ceac7af9a172ddf4842e4f2f0500d2829427d488..29e367db6118ba125ec9ad23fc0cba393b2a7ca2 100644 --- a/drivers/gpu/drm/selftests/drm_cmdline_selftests.h +++ b/drivers/gpu/drm/selftests/drm_cmdline_selftests.h @@ -53,6 +53,7 @@ cmdline_test(drm_cmdline_test_rotate_0) cmdline_test(drm_cmdline_test_rotate_90) cmdline_test(drm_cmdline_test_rotate_180) cmdline_test(drm_cmdline_test_rotate_270) +cmdline_test(drm_cmdline_test_rotate_multiple) cmdline_test(drm_cmdline_test_rotate_invalid_val) cmdline_test(drm_cmdline_test_rotate_truncated) cmdline_test(drm_cmdline_test_hmirror) diff --git a/drivers/gpu/drm/selftests/test-drm_cmdline_parser.c b/drivers/gpu/drm/selftests/test-drm_cmdline_parser.c index 520f3e66a384a27f694a92f823a489ca439a88bf..d96cd890def6eafcd8773e9180928255072bdd62 100644 --- a/drivers/gpu/drm/selftests/test-drm_cmdline_parser.c +++ b/drivers/gpu/drm/selftests/test-drm_cmdline_parser.c @@ -856,6 +856,17 @@ static int drm_cmdline_test_rotate_270(void *ignored) return 0; } +static int drm_cmdline_test_rotate_multiple(void *ignored) +{ + struct drm_cmdline_mode mode = { }; + + FAIL_ON(drm_mode_parse_command_line_for_connector("720x480,rotate=0,rotate=90", + &no_connector, + &mode)); + + return 0; +} + static int drm_cmdline_test_rotate_invalid_val(void *ignored) { struct drm_cmdline_mode mode = { }; @@ -888,7 +899,7 @@ static int drm_cmdline_test_hmirror(void *ignored) FAIL_ON(!mode.specified); FAIL_ON(mode.xres != 720); FAIL_ON(mode.yres != 480); - FAIL_ON(mode.rotation_reflection != DRM_MODE_REFLECT_X); + FAIL_ON(mode.rotation_reflection != (DRM_MODE_ROTATE_0 | DRM_MODE_REFLECT_X)); FAIL_ON(mode.refresh_specified); @@ -913,7 +924,7 @@ static int drm_cmdline_test_vmirror(void *ignored) FAIL_ON(!mode.specified); FAIL_ON(mode.xres != 720); FAIL_ON(mode.yres != 480); - FAIL_ON(mode.rotation_reflection != DRM_MODE_REFLECT_Y); + FAIL_ON(mode.rotation_reflection != (DRM_MODE_ROTATE_0 | DRM_MODE_REFLECT_Y)); FAIL_ON(mode.refresh_specified); diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c index 5ae67d526b1de8b753eb724496c64d84706ed1b0..328272ff77d84d737c83327b8aa0ab30268190db 100644 --- a/drivers/gpu/drm/sun4i/sun4i_drv.c +++ b/drivers/gpu/drm/sun4i/sun4i_drv.c @@ -85,7 +85,6 @@ static int sun4i_drv_bind(struct device *dev) } drm_mode_config_init(drm); - drm->mode_config.allow_fb_modifiers = true; ret = component_bind_all(drm->dev, drm); if (ret) { diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.c b/drivers/gpu/drm/sun4i/sun8i_mixer.c index 7c24f8f832a53b36d77d66b2eabb772dc22acc3e..4a64f7ae437a8e13dc9510ae4e1264a87c4d9295 100644 --- a/drivers/gpu/drm/sun4i/sun8i_mixer.c +++ b/drivers/gpu/drm/sun4i/sun8i_mixer.c @@ -106,48 +106,128 @@ static const struct de2_fmt_info de2_formats[] = { .rgb = true, .csc = SUN8I_CSC_MODE_OFF, }, + { + /* for DE2 VI layer which ignores alpha */ + .drm_fmt = DRM_FORMAT_XRGB4444, + .de2_fmt = SUN8I_MIXER_FBFMT_ARGB4444, + .rgb = true, + .csc = SUN8I_CSC_MODE_OFF, + }, { .drm_fmt = DRM_FORMAT_ABGR4444, .de2_fmt = SUN8I_MIXER_FBFMT_ABGR4444, .rgb = true, .csc = SUN8I_CSC_MODE_OFF, }, + { + /* for DE2 VI layer which ignores alpha */ + .drm_fmt = DRM_FORMAT_XBGR4444, + .de2_fmt = SUN8I_MIXER_FBFMT_ABGR4444, + .rgb = true, + .csc = SUN8I_CSC_MODE_OFF, + }, { .drm_fmt = DRM_FORMAT_RGBA4444, .de2_fmt = SUN8I_MIXER_FBFMT_RGBA4444, .rgb = true, .csc = SUN8I_CSC_MODE_OFF, }, + { + /* for DE2 VI layer which ignores alpha */ + .drm_fmt = DRM_FORMAT_RGBX4444, + .de2_fmt = SUN8I_MIXER_FBFMT_RGBA4444, + .rgb = true, + .csc = SUN8I_CSC_MODE_OFF, + }, { .drm_fmt = DRM_FORMAT_BGRA4444, .de2_fmt = SUN8I_MIXER_FBFMT_BGRA4444, .rgb = true, .csc = SUN8I_CSC_MODE_OFF, }, + { + /* for DE2 VI layer which ignores alpha */ + .drm_fmt = DRM_FORMAT_BGRX4444, + .de2_fmt = SUN8I_MIXER_FBFMT_BGRA4444, + .rgb = true, + .csc = SUN8I_CSC_MODE_OFF, + }, { .drm_fmt = DRM_FORMAT_ARGB1555, .de2_fmt = SUN8I_MIXER_FBFMT_ARGB1555, .rgb = true, .csc = SUN8I_CSC_MODE_OFF, }, + { + /* for DE2 VI layer which ignores alpha */ + .drm_fmt = DRM_FORMAT_XRGB1555, + .de2_fmt = SUN8I_MIXER_FBFMT_ARGB1555, + .rgb = true, + .csc = SUN8I_CSC_MODE_OFF, + }, { .drm_fmt = DRM_FORMAT_ABGR1555, .de2_fmt = SUN8I_MIXER_FBFMT_ABGR1555, .rgb = true, .csc = SUN8I_CSC_MODE_OFF, }, + { + /* for DE2 VI layer which ignores alpha */ + .drm_fmt = DRM_FORMAT_XBGR1555, + .de2_fmt = SUN8I_MIXER_FBFMT_ABGR1555, + .rgb = true, + .csc = SUN8I_CSC_MODE_OFF, + }, { .drm_fmt = DRM_FORMAT_RGBA5551, .de2_fmt = SUN8I_MIXER_FBFMT_RGBA5551, .rgb = true, .csc = SUN8I_CSC_MODE_OFF, }, + { + /* for DE2 VI layer which ignores alpha */ + .drm_fmt = DRM_FORMAT_RGBX5551, + .de2_fmt = SUN8I_MIXER_FBFMT_RGBA5551, + .rgb = true, + .csc = SUN8I_CSC_MODE_OFF, + }, { .drm_fmt = DRM_FORMAT_BGRA5551, .de2_fmt = SUN8I_MIXER_FBFMT_BGRA5551, .rgb = true, .csc = SUN8I_CSC_MODE_OFF, }, + { + /* for DE2 VI layer which ignores alpha */ + .drm_fmt = DRM_FORMAT_BGRX5551, + .de2_fmt = SUN8I_MIXER_FBFMT_BGRA5551, + .rgb = true, + .csc = SUN8I_CSC_MODE_OFF, + }, + { + .drm_fmt = DRM_FORMAT_ARGB2101010, + .de2_fmt = SUN8I_MIXER_FBFMT_ARGB2101010, + .rgb = true, + .csc = SUN8I_CSC_MODE_OFF, + }, + { + .drm_fmt = DRM_FORMAT_ABGR2101010, + .de2_fmt = SUN8I_MIXER_FBFMT_ABGR2101010, + .rgb = true, + .csc = SUN8I_CSC_MODE_OFF, + }, + { + .drm_fmt = DRM_FORMAT_RGBA1010102, + .de2_fmt = SUN8I_MIXER_FBFMT_RGBA1010102, + .rgb = true, + .csc = SUN8I_CSC_MODE_OFF, + }, + { + .drm_fmt = DRM_FORMAT_BGRA1010102, + .de2_fmt = SUN8I_MIXER_FBFMT_BGRA1010102, + .rgb = true, + .csc = SUN8I_CSC_MODE_OFF, + }, { .drm_fmt = DRM_FORMAT_UYVY, .de2_fmt = SUN8I_MIXER_FBFMT_UYVY, @@ -196,12 +276,6 @@ static const struct de2_fmt_info de2_formats[] = { .rgb = false, .csc = SUN8I_CSC_MODE_YUV2RGB, }, - { - .drm_fmt = DRM_FORMAT_YUV444, - .de2_fmt = SUN8I_MIXER_FBFMT_RGB888, - .rgb = true, - .csc = SUN8I_CSC_MODE_YUV2RGB, - }, { .drm_fmt = DRM_FORMAT_YUV422, .de2_fmt = SUN8I_MIXER_FBFMT_YUV422, @@ -220,12 +294,6 @@ static const struct de2_fmt_info de2_formats[] = { .rgb = false, .csc = SUN8I_CSC_MODE_YUV2RGB, }, - { - .drm_fmt = DRM_FORMAT_YVU444, - .de2_fmt = SUN8I_MIXER_FBFMT_RGB888, - .rgb = true, - .csc = SUN8I_CSC_MODE_YVU2RGB, - }, { .drm_fmt = DRM_FORMAT_YVU422, .de2_fmt = SUN8I_MIXER_FBFMT_YUV422, @@ -244,6 +312,18 @@ static const struct de2_fmt_info de2_formats[] = { .rgb = false, .csc = SUN8I_CSC_MODE_YVU2RGB, }, + { + .drm_fmt = DRM_FORMAT_P010, + .de2_fmt = SUN8I_MIXER_FBFMT_P010_YUV, + .rgb = false, + .csc = SUN8I_CSC_MODE_YUV2RGB, + }, + { + .drm_fmt = DRM_FORMAT_P210, + .de2_fmt = SUN8I_MIXER_FBFMT_P210_YUV, + .rgb = false, + .csc = SUN8I_CSC_MODE_YUV2RGB, + }, }; const struct de2_fmt_info *sun8i_mixer_format_info(u32 format) diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.h b/drivers/gpu/drm/sun4i/sun8i_mixer.h index c6cc94057fafaa515d1bb29d932a724940855fde..345b28b0a80a1b8abe27870831d74b3e25f61256 100644 --- a/drivers/gpu/drm/sun4i/sun8i_mixer.h +++ b/drivers/gpu/drm/sun4i/sun8i_mixer.h @@ -93,6 +93,10 @@ #define SUN8I_MIXER_FBFMT_ABGR1555 17 #define SUN8I_MIXER_FBFMT_RGBA5551 18 #define SUN8I_MIXER_FBFMT_BGRA5551 19 +#define SUN8I_MIXER_FBFMT_ARGB2101010 20 +#define SUN8I_MIXER_FBFMT_ABGR2101010 21 +#define SUN8I_MIXER_FBFMT_RGBA1010102 22 +#define SUN8I_MIXER_FBFMT_BGRA1010102 23 #define SUN8I_MIXER_FBFMT_YUYV 0 #define SUN8I_MIXER_FBFMT_UYVY 1 @@ -109,6 +113,13 @@ /* format 12 is semi-planar YUV411 UVUV */ /* format 13 is semi-planar YUV411 VUVU */ #define SUN8I_MIXER_FBFMT_YUV411 14 +/* format 15 doesn't exist */ +/* format 16 is P010 YVU */ +#define SUN8I_MIXER_FBFMT_P010_YUV 17 +/* format 18 is P210 YVU */ +#define SUN8I_MIXER_FBFMT_P210_YUV 19 +/* format 20 is packed YVU444 10-bit */ +/* format 21 is packed YUV444 10-bit */ /* * Sub-engines listed bellow are unused for now. The EN registers are here only diff --git a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c index 42d445d2377353cc0a7e1e3613cdd7edef3d3f49..b8398ca18b0fd20027f136de12048cb7a094707d 100644 --- a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c +++ b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c @@ -398,24 +398,66 @@ static const struct drm_plane_funcs sun8i_vi_layer_funcs = { }; /* - * While all RGB formats are supported, VI planes don't support - * alpha blending, so there is no point having formats with alpha - * channel if their opaque analog exist. + * While DE2 VI layer supports same RGB formats as UI layer, alpha + * channel is ignored. This structure lists all unique variants + * where alpha channel is replaced with "don't care" (X) channel. */ static const u32 sun8i_vi_layer_formats[] = { + DRM_FORMAT_BGR565, + DRM_FORMAT_BGR888, + DRM_FORMAT_BGRX4444, + DRM_FORMAT_BGRX5551, + DRM_FORMAT_BGRX8888, + DRM_FORMAT_RGB565, + DRM_FORMAT_RGB888, + DRM_FORMAT_RGBX4444, + DRM_FORMAT_RGBX5551, + DRM_FORMAT_RGBX8888, + DRM_FORMAT_XBGR1555, + DRM_FORMAT_XBGR4444, + DRM_FORMAT_XBGR8888, + DRM_FORMAT_XRGB1555, + DRM_FORMAT_XRGB4444, + DRM_FORMAT_XRGB8888, + + DRM_FORMAT_NV16, + DRM_FORMAT_NV12, + DRM_FORMAT_NV21, + DRM_FORMAT_NV61, + DRM_FORMAT_UYVY, + DRM_FORMAT_VYUY, + DRM_FORMAT_YUYV, + DRM_FORMAT_YVYU, + DRM_FORMAT_YUV411, + DRM_FORMAT_YUV420, + DRM_FORMAT_YUV422, + DRM_FORMAT_YVU411, + DRM_FORMAT_YVU420, + DRM_FORMAT_YVU422, +}; + +static const u32 sun8i_vi_layer_de3_formats[] = { DRM_FORMAT_ABGR1555, + DRM_FORMAT_ABGR2101010, DRM_FORMAT_ABGR4444, + DRM_FORMAT_ABGR8888, DRM_FORMAT_ARGB1555, + DRM_FORMAT_ARGB2101010, DRM_FORMAT_ARGB4444, + DRM_FORMAT_ARGB8888, DRM_FORMAT_BGR565, DRM_FORMAT_BGR888, + DRM_FORMAT_BGRA1010102, DRM_FORMAT_BGRA5551, DRM_FORMAT_BGRA4444, + DRM_FORMAT_BGRA8888, DRM_FORMAT_BGRX8888, DRM_FORMAT_RGB565, DRM_FORMAT_RGB888, + DRM_FORMAT_RGBA1010102, DRM_FORMAT_RGBA4444, DRM_FORMAT_RGBA5551, + DRM_FORMAT_RGBA8888, DRM_FORMAT_RGBX8888, DRM_FORMAT_XBGR8888, DRM_FORMAT_XRGB8888, @@ -424,6 +466,8 @@ static const u32 sun8i_vi_layer_formats[] = { DRM_FORMAT_NV12, DRM_FORMAT_NV21, DRM_FORMAT_NV61, + DRM_FORMAT_P010, + DRM_FORMAT_P210, DRM_FORMAT_UYVY, DRM_FORMAT_VYUY, DRM_FORMAT_YUYV, @@ -431,11 +475,9 @@ static const u32 sun8i_vi_layer_formats[] = { DRM_FORMAT_YUV411, DRM_FORMAT_YUV420, DRM_FORMAT_YUV422, - DRM_FORMAT_YUV444, DRM_FORMAT_YVU411, DRM_FORMAT_YVU420, DRM_FORMAT_YVU422, - DRM_FORMAT_YVU444, }; struct sun8i_vi_layer *sun8i_vi_layer_init_one(struct drm_device *drm, @@ -443,19 +485,27 @@ struct sun8i_vi_layer *sun8i_vi_layer_init_one(struct drm_device *drm, int index) { u32 supported_encodings, supported_ranges; + unsigned int plane_cnt, format_count; struct sun8i_vi_layer *layer; - unsigned int plane_cnt; + const u32 *formats; int ret; layer = devm_kzalloc(drm->dev, sizeof(*layer), GFP_KERNEL); if (!layer) return ERR_PTR(-ENOMEM); + if (mixer->cfg->is_de3) { + formats = sun8i_vi_layer_de3_formats; + format_count = ARRAY_SIZE(sun8i_vi_layer_de3_formats); + } else { + formats = sun8i_vi_layer_formats; + format_count = ARRAY_SIZE(sun8i_vi_layer_formats); + } + /* possible crtcs are set later */ ret = drm_universal_plane_init(drm, &layer->plane, 0, &sun8i_vi_layer_funcs, - sun8i_vi_layer_formats, - ARRAY_SIZE(sun8i_vi_layer_formats), + formats, format_count, NULL, DRM_PLANE_TYPE_OVERLAY, NULL); if (ret) { dev_err(drm->dev, "Couldn't initialize layer\n"); diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index 49ed55779128e3cf5954041499fc534e20fa2dfd..953c82a4f5736afc22484a14296976319aa1a5e0 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -515,6 +515,7 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo, fbo->base.base.resv = &fbo->base.base._resv; dma_resv_init(&fbo->base.base._resv); + fbo->base.base.dev = NULL; ret = dma_resv_trylock(&fbo->base.base._resv); WARN_ON(!ret); diff --git a/drivers/gpu/drm/vgem/vgem_drv.c b/drivers/gpu/drm/vgem/vgem_drv.c index 5bd60ded3d8151d2e63b85d7c7afbb626a689665..909eba43664a28f857070ec7090482f53727416d 100644 --- a/drivers/gpu/drm/vgem/vgem_drv.c +++ b/drivers/gpu/drm/vgem/vgem_drv.c @@ -196,9 +196,10 @@ static struct drm_gem_object *vgem_gem_create(struct drm_device *dev, return ERR_CAST(obj); ret = drm_gem_handle_create(file, &obj->base, handle); - drm_gem_object_put_unlocked(&obj->base); - if (ret) + if (ret) { + drm_gem_object_put_unlocked(&obj->base); return ERR_PTR(ret); + } return &obj->base; } @@ -221,7 +222,9 @@ static int vgem_gem_dumb_create(struct drm_file *file, struct drm_device *dev, args->size = gem_object->size; args->pitch = pitch; - DRM_DEBUG("Created object of size %lld\n", size); + drm_gem_object_put_unlocked(gem_object); + + DRM_DEBUG("Created object of size %llu\n", args->size); return 0; } diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c index 017a9e0fc3bb80b5aa7ee92cd5c2a5946972607e..3af7ec80c7da7cc0c24173dcec8c9a88a300b616 100644 --- a/drivers/gpu/drm/virtio/virtgpu_object.c +++ b/drivers/gpu/drm/virtio/virtgpu_object.c @@ -42,8 +42,8 @@ static int virtio_gpu_resource_id_get(struct virtio_gpu_device *vgdev, * "f91a9dd35715 Fix unlinking resources from hash * table." (Feb 2019) fixes the bug. */ - static int handle; - handle++; + static atomic_t seqno = ATOMIC_INIT(0); + int handle = atomic_inc_return(&seqno); *resid = handle + 1; } else { int handle = ida_alloc(&vgdev->resource_ida, GFP_KERNEL); @@ -99,6 +99,7 @@ struct drm_gem_object *virtio_gpu_create_object(struct drm_device *dev, return NULL; bo->base.base.funcs = &virtio_gpu_gem_funcs; + bo->base.map_cached = true; return &bo->base.base; } diff --git a/drivers/hid/hid-alps.c b/drivers/hid/hid-alps.c index ae79a7c667372e6e54b8302565870c3f24b2ce85..fa704153cb00d5f7fa7d0185acd1f953fdd37754 100644 --- a/drivers/hid/hid-alps.c +++ b/drivers/hid/hid-alps.c @@ -730,7 +730,7 @@ static int alps_input_configured(struct hid_device *hdev, struct hid_input *hi) if (data->has_sp) { input2 = input_allocate_device(); if (!input2) { - input_free_device(input2); + ret = -ENOMEM; goto exit; } diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c index 6ac8becc2372efdd303ba29d14a246e9f5290239..d732d1d10cafb7bbafbf27ec59ff17bd5aae2c94 100644 --- a/drivers/hid/hid-apple.c +++ b/drivers/hid/hid-apple.c @@ -340,7 +340,8 @@ static int apple_input_mapping(struct hid_device *hdev, struct hid_input *hi, unsigned long **bit, int *max) { if (usage->hid == (HID_UP_CUSTOM | 0x0003) || - usage->hid == (HID_UP_MSVENDOR | 0x0003)) { + usage->hid == (HID_UP_MSVENDOR | 0x0003) || + usage->hid == (HID_UP_HPVENDOR2 | 0x0003)) { /* The fn key on Apple USB keyboards */ set_bit(EV_REP, hi->input->evbit); hid_map_usage_clear(hi, usage, bit, max, EV_KEY, KEY_FN); diff --git a/drivers/hid/hid-bigbenff.c b/drivers/hid/hid-bigbenff.c index 3f6abd190df43ef17cb6080505fe7761c38324fe..db6da21ade06315c457d087447cecf563eac8c55 100644 --- a/drivers/hid/hid-bigbenff.c +++ b/drivers/hid/hid-bigbenff.c @@ -174,6 +174,7 @@ static __u8 pid0902_rdesc_fixed[] = { struct bigben_device { struct hid_device *hid; struct hid_report *report; + bool removed; u8 led_state; /* LED1 = 1 .. LED4 = 8 */ u8 right_motor_on; /* right motor off/on 0/1 */ u8 left_motor_force; /* left motor force 0-255 */ @@ -190,6 +191,9 @@ static void bigben_worker(struct work_struct *work) struct bigben_device, worker); struct hid_field *report_field = bigben->report->field[0]; + if (bigben->removed) + return; + if (bigben->work_led) { bigben->work_led = false; report_field->value[0] = 0x01; /* 1 = led message */ @@ -220,10 +224,16 @@ static void bigben_worker(struct work_struct *work) static int hid_bigben_play_effect(struct input_dev *dev, void *data, struct ff_effect *effect) { - struct bigben_device *bigben = data; + struct hid_device *hid = input_get_drvdata(dev); + struct bigben_device *bigben = hid_get_drvdata(hid); u8 right_motor_on; u8 left_motor_force; + if (!bigben) { + hid_err(hid, "no device data\n"); + return 0; + } + if (effect->type != FF_RUMBLE) return 0; @@ -298,8 +308,8 @@ static void bigben_remove(struct hid_device *hid) { struct bigben_device *bigben = hid_get_drvdata(hid); + bigben->removed = true; cancel_work_sync(&bigben->worker); - hid_hw_close(hid); hid_hw_stop(hid); } @@ -319,6 +329,7 @@ static int bigben_probe(struct hid_device *hid, return -ENOMEM; hid_set_drvdata(hid, bigben); bigben->hid = hid; + bigben->removed = false; error = hid_parse(hid); if (error) { @@ -341,10 +352,10 @@ static int bigben_probe(struct hid_device *hid, INIT_WORK(&bigben->worker, bigben_worker); - error = input_ff_create_memless(hidinput->input, bigben, + error = input_ff_create_memless(hidinput->input, NULL, hid_bigben_play_effect); if (error) - return error; + goto error_hw_stop; name_sz = strlen(dev_name(&hid->dev)) + strlen(":red:bigben#") + 1; @@ -354,8 +365,10 @@ static int bigben_probe(struct hid_device *hid, sizeof(struct led_classdev) + name_sz, GFP_KERNEL ); - if (!led) - return -ENOMEM; + if (!led) { + error = -ENOMEM; + goto error_hw_stop; + } name = (void *)(&led[1]); snprintf(name, name_sz, "%s:red:bigben%d", @@ -369,7 +382,7 @@ static int bigben_probe(struct hid_device *hid, bigben->leds[n] = led; error = devm_led_classdev_register(&hid->dev, led); if (error) - return error; + goto error_hw_stop; } /* initial state: LED1 is on, no rumble effect */ @@ -383,6 +396,10 @@ static int bigben_probe(struct hid_device *hid, hid_info(hid, "LED and force feedback support for BigBen gamepad\n"); return 0; + +error_hw_stop: + hid_hw_stop(hid); + return error; } static __u8 *bigben_report_fixup(struct hid_device *hid, __u8 *rdesc, diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 851fe54ea59e7c2636ab204372c49b749a136014..359616e3efbbb244e633b4a37ae6361c30abf19f 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1741,7 +1741,9 @@ int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, u32 size, rsize = ((report->size - 1) >> 3) + 1; - if (rsize > HID_MAX_BUFFER_SIZE) + if (report_enum->numbered && rsize >= HID_MAX_BUFFER_SIZE) + rsize = HID_MAX_BUFFER_SIZE - 1; + else if (rsize > HID_MAX_BUFFER_SIZE) rsize = HID_MAX_BUFFER_SIZE; if (csize < rsize) { diff --git a/drivers/hid/hid-google-hammer.c b/drivers/hid/hid-google-hammer.c index 2aa4ed157aec875e0431420f55fdc5b7729bf8b0..85a054f1ce389520be52a6270968846383ecbebe 100644 --- a/drivers/hid/hid-google-hammer.c +++ b/drivers/hid/hid-google-hammer.c @@ -532,6 +532,8 @@ static const struct hid_device_id hammer_devices[] = { USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_MAGNEMITE) }, { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_MASTERBALL) }, + { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, + USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_MOONBALL) }, { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_STAFF) }, { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, diff --git a/drivers/hid/hid-hyperv.c b/drivers/hid/hid-hyperv.c index dddfca555df958306fd89dfcd41a14e03648e090..0b6ee1dee625a1f338f9449eac623e5862b9fc34 100644 --- a/drivers/hid/hid-hyperv.c +++ b/drivers/hid/hid-hyperv.c @@ -193,8 +193,7 @@ static void mousevsc_on_receive_device_info(struct mousevsc_dev *input_device, goto cleanup; /* The pointer is not NULL when we resume from hibernation */ - if (input_device->hid_desc != NULL) - kfree(input_device->hid_desc); + kfree(input_device->hid_desc); input_device->hid_desc = kmemdup(desc, desc->bLength, GFP_ATOMIC); if (!input_device->hid_desc) @@ -207,8 +206,7 @@ static void mousevsc_on_receive_device_info(struct mousevsc_dev *input_device, } /* The pointer is not NULL when we resume from hibernation */ - if (input_device->report_desc != NULL) - kfree(input_device->report_desc); + kfree(input_device->report_desc); input_device->report_desc = kzalloc(input_device->report_desc_size, GFP_ATOMIC); diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 3a400ce603c4f39cd3e21e8210f6f06a7d4366bd..9f2213426556544a3db34081d9871b5633147c4a 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -478,6 +478,7 @@ #define USB_DEVICE_ID_GOOGLE_WHISKERS 0x5030 #define USB_DEVICE_ID_GOOGLE_MASTERBALL 0x503c #define USB_DEVICE_ID_GOOGLE_MAGNEMITE 0x503d +#define USB_DEVICE_ID_GOOGLE_MOONBALL 0x5044 #define USB_VENDOR_ID_GOTOP 0x08f2 #define USB_DEVICE_ID_SUPER_Q2 0x007f @@ -726,6 +727,7 @@ #define USB_DEVICE_ID_LENOVO_X1_COVER 0x6085 #define USB_DEVICE_ID_LENOVO_X1_TAB 0x60a3 #define USB_DEVICE_ID_LENOVO_X1_TAB3 0x60b5 +#define USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_608D 0x608d #define USB_VENDOR_ID_LG 0x1fd2 #define USB_DEVICE_ID_LG_MULTITOUCH 0x0064 diff --git a/drivers/hid/hid-ite.c b/drivers/hid/hid-ite.c index c436e12feb23315f141362dccc38c2c549c8d9f9..6c55682c597409d1fcdbfbaad7a4974010b50857 100644 --- a/drivers/hid/hid-ite.c +++ b/drivers/hid/hid-ite.c @@ -41,8 +41,9 @@ static const struct hid_device_id ite_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_ITE, USB_DEVICE_ID_ITE8595) }, { HID_USB_DEVICE(USB_VENDOR_ID_258A, USB_DEVICE_ID_258A_6A88) }, /* ITE8595 USB kbd ctlr, with Synaptics touchpad connected to it. */ - { HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, - USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012) }, + { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, + USB_VENDOR_ID_SYNAPTICS, + USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012) }, { } }; MODULE_DEVICE_TABLE(hid, ite_devices); diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index 70e1cb928bf038876cd603e99302ea7e5687c426..094f4f1b6555b49315d44632a70cb8c6205f24db 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -1256,36 +1256,35 @@ static int hidpp20_battery_map_status_voltage(u8 data[3], int *voltage, { int status; - long charge_sts = (long)data[2]; + long flags = (long) data[2]; - *level = POWER_SUPPLY_CAPACITY_LEVEL_UNKNOWN; - switch (data[2] & 0xe0) { - case 0x00: - status = POWER_SUPPLY_STATUS_CHARGING; - break; - case 0x20: - status = POWER_SUPPLY_STATUS_FULL; - *level = POWER_SUPPLY_CAPACITY_LEVEL_FULL; - break; - case 0x40: + if (flags & 0x80) + switch (flags & 0x07) { + case 0: + status = POWER_SUPPLY_STATUS_CHARGING; + break; + case 1: + status = POWER_SUPPLY_STATUS_FULL; + *level = POWER_SUPPLY_CAPACITY_LEVEL_FULL; + break; + case 2: + status = POWER_SUPPLY_STATUS_NOT_CHARGING; + break; + default: + status = POWER_SUPPLY_STATUS_UNKNOWN; + break; + } + else status = POWER_SUPPLY_STATUS_DISCHARGING; - break; - case 0xe0: - status = POWER_SUPPLY_STATUS_NOT_CHARGING; - break; - default: - status = POWER_SUPPLY_STATUS_UNKNOWN; - } *charge_type = POWER_SUPPLY_CHARGE_TYPE_STANDARD; - if (test_bit(3, &charge_sts)) { + if (test_bit(3, &flags)) { *charge_type = POWER_SUPPLY_CHARGE_TYPE_FAST; } - if (test_bit(4, &charge_sts)) { + if (test_bit(4, &flags)) { *charge_type = POWER_SUPPLY_CHARGE_TYPE_TRICKLE; } - - if (test_bit(5, &charge_sts)) { + if (test_bit(5, &flags)) { *level = POWER_SUPPLY_CAPACITY_LEVEL_CRITICAL; } diff --git a/drivers/hid/hid-picolcd_fb.c b/drivers/hid/hid-picolcd_fb.c index a549c42e8c9025bc55f052260b4e62a3b262962b..33c102a609923eee955f7191b427310cb8607136 100644 --- a/drivers/hid/hid-picolcd_fb.c +++ b/drivers/hid/hid-picolcd_fb.c @@ -458,9 +458,9 @@ static ssize_t picolcd_fb_update_rate_show(struct device *dev, if (ret >= PAGE_SIZE) break; else if (i == fb_update_rate) - ret += snprintf(buf+ret, PAGE_SIZE-ret, "[%u] ", i); + ret += scnprintf(buf+ret, PAGE_SIZE-ret, "[%u] ", i); else - ret += snprintf(buf+ret, PAGE_SIZE-ret, "%u ", i); + ret += scnprintf(buf+ret, PAGE_SIZE-ret, "%u ", i); if (ret > 0) buf[min(ret, (size_t)PAGE_SIZE)-1] = '\n'; return ret; diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index 0e7b2d998395a91f5d5f9109443501707fe964fc..3735546bb524b1caef188b5a7abe37409f328f05 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -103,6 +103,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_PENSKETCH_M912), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M406XE), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_PIXART_USB_OPTICAL_MOUSE_ID2), HID_QUIRK_ALWAYS_POLL }, + { HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_608D), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_C007), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_C077), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_KEYBOARD_G710_PLUS), HID_QUIRK_NOGET }, diff --git a/drivers/hid/hid-sensor-custom.c b/drivers/hid/hid-sensor-custom.c index fb827c295842f0e4ebe9e81974c513bef9c6638e..4d25577a8573fe2edc2edc145748f454fd21d090 100644 --- a/drivers/hid/hid-sensor-custom.c +++ b/drivers/hid/hid-sensor-custom.c @@ -313,7 +313,7 @@ static ssize_t show_value(struct device *dev, struct device_attribute *attr, while (i < ret) { if (i + attribute->size > ret) { - len += snprintf(&buf[len], + len += scnprintf(&buf[len], PAGE_SIZE - len, "%d ", values[i]); break; @@ -336,10 +336,10 @@ static ssize_t show_value(struct device *dev, struct device_attribute *attr, ++i; break; } - len += snprintf(&buf[len], PAGE_SIZE - len, + len += scnprintf(&buf[len], PAGE_SIZE - len, "%lld ", value); } - len += snprintf(&buf[len], PAGE_SIZE - len, "\n"); + len += scnprintf(&buf[len], PAGE_SIZE - len, "\n"); return len; } else if (input) diff --git a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c index d31ea82b84c173033dd1a6582122ec9197671fbc..a66f08041a1aa105d1605210c3f70b71d4afbcc3 100644 --- a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c +++ b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c @@ -341,6 +341,14 @@ static const struct dmi_system_id i2c_hid_dmi_desc_override_table[] = { }, .driver_data = (void *)&sipodev_desc }, + { + .ident = "Trekstor SURFBOOK E11B", + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "TREKSTOR"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "SURFBOOK E11B"), + }, + .driver_data = (void *)&sipodev_desc + }, { .ident = "Direkt-Tek DTLAPY116-2", .matches = { diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c index a970b809d778c3c9a74702abe70c9f1f976a06d9..4140dea693e90988d80bac6129458499fb2d03af 100644 --- a/drivers/hid/usbhid/hiddev.c +++ b/drivers/hid/usbhid/hiddev.c @@ -932,9 +932,9 @@ void hiddev_disconnect(struct hid_device *hid) hiddev->exist = 0; if (hiddev->open) { - mutex_unlock(&hiddev->existancelock); hid_hw_close(hiddev->hid); wake_up_interruptible(&hiddev->wait); + mutex_unlock(&hiddev->existancelock); } else { mutex_unlock(&hiddev->existancelock); kfree(hiddev); diff --git a/drivers/hwmon/acpi_power_meter.c b/drivers/hwmon/acpi_power_meter.c index 4cf25458f0b9515e419a6f0b88047bf35809a2e5..0db8ef4fd6e18b7464f3c8e4b6c0de741f8e0998 100644 --- a/drivers/hwmon/acpi_power_meter.c +++ b/drivers/hwmon/acpi_power_meter.c @@ -355,7 +355,9 @@ static ssize_t show_str(struct device *dev, struct acpi_device *acpi_dev = to_acpi_device(dev); struct acpi_power_meter_resource *resource = acpi_dev->driver_data; acpi_string val; + int ret; + mutex_lock(&resource->lock); switch (attr->index) { case 0: val = resource->model_number; @@ -372,8 +374,9 @@ static ssize_t show_str(struct device *dev, val = ""; break; } - - return sprintf(buf, "%s\n", val); + ret = sprintf(buf, "%s\n", val); + mutex_unlock(&resource->lock); + return ret; } static ssize_t show_val(struct device *dev, @@ -817,11 +820,12 @@ static void acpi_power_meter_notify(struct acpi_device *device, u32 event) resource = acpi_driver_data(device); - mutex_lock(&resource->lock); switch (event) { case METER_NOTIFY_CONFIG: + mutex_lock(&resource->lock); free_capabilities(resource); res = read_capabilities(resource); + mutex_unlock(&resource->lock); if (res) break; @@ -830,15 +834,12 @@ static void acpi_power_meter_notify(struct acpi_device *device, u32 event) break; case METER_NOTIFY_TRIP: sysfs_notify(&device->dev.kobj, NULL, POWER_AVERAGE_NAME); - update_meter(resource); break; case METER_NOTIFY_CAP: sysfs_notify(&device->dev.kobj, NULL, POWER_CAP_NAME); - update_cap(resource); break; case METER_NOTIFY_INTERVAL: sysfs_notify(&device->dev.kobj, NULL, POWER_AVG_INTERVAL_NAME); - update_avg_interval(resource); break; case METER_NOTIFY_CAPPING: sysfs_notify(&device->dev.kobj, NULL, POWER_ALARM_NAME); @@ -848,7 +849,6 @@ static void acpi_power_meter_notify(struct acpi_device *device, u32 event) WARN(1, "Unexpected event %d\n", event); break; } - mutex_unlock(&resource->lock); acpi_bus_generate_netlink_event(ACPI_POWER_METER_CLASS, dev_name(&device->dev), event, 0); @@ -912,8 +912,8 @@ static int acpi_power_meter_remove(struct acpi_device *device) resource = acpi_driver_data(device); hwmon_device_unregister(resource->hwmon_dev); - free_capabilities(resource); remove_attrs(resource); + free_capabilities(resource); kfree(resource); return 0; diff --git a/drivers/hwmon/adt7462.c b/drivers/hwmon/adt7462.c index 9632e2e3c4bb4067cd58a1fb2f4252ab20e13c0a..319a0519ebdb0f44a675cd241a85a114b2b8dc7f 100644 --- a/drivers/hwmon/adt7462.c +++ b/drivers/hwmon/adt7462.c @@ -413,7 +413,7 @@ static int ADT7462_REG_VOLT(struct adt7462_data *data, int which) return 0x95; break; } - return -ENODEV; + return 0; } /* Provide labels for sysfs */ diff --git a/drivers/hwmon/pmbus/ltc2978.c b/drivers/hwmon/pmbus/ltc2978.c index f01f4887fb2e6b92d416d17a8ea75233bdd1ca91..a91ed01abb68050e4c6ffb231c21c5ab8b7585f1 100644 --- a/drivers/hwmon/pmbus/ltc2978.c +++ b/drivers/hwmon/pmbus/ltc2978.c @@ -82,8 +82,8 @@ enum chips { ltc2974, ltc2975, ltc2977, ltc2978, ltc2980, ltc3880, ltc3882, #define LTC_POLL_TIMEOUT 100 /* in milli-seconds */ -#define LTC_NOT_BUSY BIT(5) -#define LTC_NOT_PENDING BIT(4) +#define LTC_NOT_BUSY BIT(6) +#define LTC_NOT_PENDING BIT(5) /* * LTC2978 clears peak data whenever the CLEAR_FAULTS command is executed, which diff --git a/drivers/hwmon/pmbus/xdpe12284.c b/drivers/hwmon/pmbus/xdpe12284.c index 3d47806ff4d3f4704aeaf0e59099bec539b611e8..660556b89e9ff541069400861d8414d882906927 100644 --- a/drivers/hwmon/pmbus/xdpe12284.c +++ b/drivers/hwmon/pmbus/xdpe12284.c @@ -18,6 +18,59 @@ #define XDPE122_AMD_625MV 0x10 /* AMD mode 6.25mV */ #define XDPE122_PAGE_NUM 2 +static int xdpe122_read_word_data(struct i2c_client *client, int page, int reg) +{ + const struct pmbus_driver_info *info = pmbus_get_driver_info(client); + long val; + s16 exponent; + s32 mantissa; + int ret; + + switch (reg) { + case PMBUS_VOUT_OV_FAULT_LIMIT: + case PMBUS_VOUT_UV_FAULT_LIMIT: + ret = pmbus_read_word_data(client, page, reg); + if (ret < 0) + return ret; + + /* Convert register value to LINEAR11 data. */ + exponent = ((s16)ret) >> 11; + mantissa = ((s16)((ret & GENMASK(10, 0)) << 5)) >> 5; + val = mantissa * 1000L; + if (exponent >= 0) + val <<= exponent; + else + val >>= -exponent; + + /* Convert data to VID register. */ + switch (info->vrm_version[page]) { + case vr13: + if (val >= 500) + return 1 + DIV_ROUND_CLOSEST(val - 500, 10); + return 0; + case vr12: + if (val >= 250) + return 1 + DIV_ROUND_CLOSEST(val - 250, 5); + return 0; + case imvp9: + if (val >= 200) + return 1 + DIV_ROUND_CLOSEST(val - 200, 10); + return 0; + case amd625mv: + if (val >= 200 && val <= 1550) + return DIV_ROUND_CLOSEST((1550 - val) * 100, + 625); + return 0; + default: + return -EINVAL; + } + default: + return -ENODATA; + } + + return 0; +} + static int xdpe122_identify(struct i2c_client *client, struct pmbus_driver_info *info) { @@ -70,6 +123,7 @@ static struct pmbus_driver_info xdpe122_info = { PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP | PMBUS_HAVE_POUT | PMBUS_HAVE_PIN | PMBUS_HAVE_STATUS_INPUT, .identify = xdpe122_identify, + .read_word_data = xdpe122_read_word_data, }; static int xdpe122_probe(struct i2c_client *client, @@ -94,8 +148,8 @@ static const struct i2c_device_id xdpe122_id[] = { MODULE_DEVICE_TABLE(i2c, xdpe122_id); static const struct of_device_id __maybe_unused xdpe122_of_match[] = { - {.compatible = "infineon, xdpe12254"}, - {.compatible = "infineon, xdpe12284"}, + {.compatible = "infineon,xdpe12254"}, + {.compatible = "infineon,xdpe12284"}, {} }; MODULE_DEVICE_TABLE(of, xdpe122_of_match); diff --git a/drivers/hwmon/w83627ehf.c b/drivers/hwmon/w83627ehf.c index 7ffadc2da57b537d2638f0829fa778318546a1e3..5a5120121e50725c49a39356ab613b72beb58c97 100644 --- a/drivers/hwmon/w83627ehf.c +++ b/drivers/hwmon/w83627ehf.c @@ -1346,8 +1346,13 @@ w83627ehf_is_visible(const void *drvdata, enum hwmon_sensor_types type, /* channel 0.., name 1.. */ if (!(data->have_temp & (1 << channel))) return 0; - if (attr == hwmon_temp_input || attr == hwmon_temp_label) + if (attr == hwmon_temp_input) return 0444; + if (attr == hwmon_temp_label) { + if (data->temp_label) + return 0444; + return 0; + } if (channel == 2 && data->temp3_val_only) return 0; if (attr == hwmon_temp_max) { diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c index 8e48c7458aa35cbbf3963462d969d2b22614ce49..255f8f41c8ff7d2f71b8dfbbf1240be180420184 100644 --- a/drivers/hwtracing/intel_th/msu.c +++ b/drivers/hwtracing/intel_th/msu.c @@ -718,9 +718,6 @@ static int msc_win_set_lockout(struct msc_window *win, if (old != expect) { ret = -EINVAL; - dev_warn_ratelimited(msc_dev(win->msc), - "expected lockout state %d, got %d\n", - expect, old); goto unlock; } @@ -741,6 +738,10 @@ static int msc_win_set_lockout(struct msc_window *win, /* from intel_th_msc_window_unlock(), don't warn if not locked */ if (expect == WIN_LOCKED && old == new) return 0; + + dev_warn_ratelimited(msc_dev(win->msc), + "expected lockout state %d, got %d\n", + expect, old); } return ret; @@ -760,7 +761,7 @@ static int msc_configure(struct msc *msc) lockdep_assert_held(&msc->buf_mutex); if (msc->mode > MSC_MODE_MULTI) - return -ENOTSUPP; + return -EINVAL; if (msc->mode == MSC_MODE_MULTI) { if (msc_win_set_lockout(msc->cur_win, WIN_READY, WIN_INUSE)) @@ -1294,7 +1295,7 @@ static int msc_buffer_alloc(struct msc *msc, unsigned long *nr_pages, } else if (msc->mode == MSC_MODE_MULTI) { ret = msc_buffer_multi_alloc(msc, nr_pages, nr_wins); } else { - ret = -ENOTSUPP; + ret = -EINVAL; } if (!ret) { @@ -1530,7 +1531,7 @@ static ssize_t intel_th_msc_read(struct file *file, char __user *buf, if (ret >= 0) *ppos = iter->offset; } else { - ret = -ENOTSUPP; + ret = -EINVAL; } put_count: diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c index e9d90b53bbc46325f199a9d684cdf9f5e12430cc..86aa6a46bcba9f3b9a033f2d164e9eb3e0fc4db8 100644 --- a/drivers/hwtracing/intel_th/pci.c +++ b/drivers/hwtracing/intel_th/pci.c @@ -234,6 +234,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4da6), .driver_data = (kernel_ulong_t)&intel_th_2x, }, + { + /* Elkhart Lake CPU */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4529), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, { /* Elkhart Lake */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4b26), diff --git a/drivers/hwtracing/stm/p_sys-t.c b/drivers/hwtracing/stm/p_sys-t.c index b178a5495b6796e7687a82f422823545dc355b62..360b5c03df95b87e600843340ae24d6cfb9f0b99 100644 --- a/drivers/hwtracing/stm/p_sys-t.c +++ b/drivers/hwtracing/stm/p_sys-t.c @@ -238,7 +238,7 @@ static struct configfs_attribute *sys_t_policy_attrs[] = { static inline bool sys_t_need_ts(struct sys_t_output *op) { if (op->node.ts_interval && - time_after(op->ts_jiffies + op->node.ts_interval, jiffies)) { + time_after(jiffies, op->ts_jiffies + op->node.ts_interval)) { op->ts_jiffies = jiffies; return true; @@ -250,8 +250,8 @@ static inline bool sys_t_need_ts(struct sys_t_output *op) static bool sys_t_need_clock_sync(struct sys_t_output *op) { if (op->node.clocksync_interval && - time_after(op->clocksync_jiffies + op->node.clocksync_interval, - jiffies)) { + time_after(jiffies, + op->clocksync_jiffies + op->node.clocksync_interval)) { op->clocksync_jiffies = jiffies; return true; diff --git a/drivers/i2c/busses/i2c-altera.c b/drivers/i2c/busses/i2c-altera.c index 5255d3755411b29285b7170aca298b29e4f4a4e9..1de23b4f3809c507f8f23eac1b7e22641963f537 100644 --- a/drivers/i2c/busses/i2c-altera.c +++ b/drivers/i2c/busses/i2c-altera.c @@ -171,7 +171,7 @@ static void altr_i2c_init(struct altr_i2c_dev *idev) /* SCL Low Time */ writel(t_low, idev->base + ALTR_I2C_SCL_LOW); /* SDA Hold Time, 300ns */ - writel(div_u64(300 * clk_mhz, 1000), idev->base + ALTR_I2C_SDA_HOLD); + writel(3 * clk_mhz / 10, idev->base + ALTR_I2C_SDA_HOLD); /* Mask all master interrupt bits */ altr_i2c_int_enable(idev, ALTR_I2C_ALL_IRQ, false); diff --git a/drivers/i2c/busses/i2c-designware-pcidrv.c b/drivers/i2c/busses/i2c-designware-pcidrv.c index 050adda7c1bdf5d1ea511f0d2ada1e890a5919c7..05b35ac33ce33b4063b6993c6054b54be78aea88 100644 --- a/drivers/i2c/busses/i2c-designware-pcidrv.c +++ b/drivers/i2c/busses/i2c-designware-pcidrv.c @@ -313,6 +313,7 @@ static void i2c_dw_pci_remove(struct pci_dev *pdev) pm_runtime_get_noresume(&pdev->dev); i2c_del_adapter(&dev->adapter); + devm_free_irq(&pdev->dev, dev->irq, dev); pci_free_irq_vectors(pdev); } diff --git a/drivers/i2c/busses/i2c-gpio.c b/drivers/i2c/busses/i2c-gpio.c index 3a9e840a3546673b33dd7f4b9d1d3613632721da..a4a6825c87583f4d8b3d51800e753098597e3f1b 100644 --- a/drivers/i2c/busses/i2c-gpio.c +++ b/drivers/i2c/busses/i2c-gpio.c @@ -348,7 +348,7 @@ static struct gpio_desc *i2c_gpio_get_desc(struct device *dev, if (ret == -ENOENT) retdesc = ERR_PTR(-EPROBE_DEFER); - if (ret != -EPROBE_DEFER) + if (PTR_ERR(retdesc) != -EPROBE_DEFER) dev_err(dev, "error trying to get descriptor: %d\n", ret); return retdesc; diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index ca4f096fef74930254e772da8bd54dfbc2454716..a9c03f5c34825a95901ca420bc2164e74c0651f1 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -132,11 +132,6 @@ #define TCOBASE 0x050 #define TCOCTL 0x054 -#define ACPIBASE 0x040 -#define ACPIBASE_SMI_OFF 0x030 -#define ACPICTRL 0x044 -#define ACPICTRL_EN 0x080 - #define SBREG_BAR 0x10 #define SBREG_SMBCTRL 0xc6000c #define SBREG_SMBCTRL_DNV 0xcf000c @@ -1553,7 +1548,7 @@ i801_add_tco_spt(struct i801_priv *priv, struct pci_dev *pci_dev, pci_bus_write_config_byte(pci_dev->bus, devfn, 0xe1, hidden); spin_unlock(&p2sb_spinlock); - res = &tco_res[ICH_RES_MEM_OFF]; + res = &tco_res[1]; if (pci_dev->device == PCI_DEVICE_ID_INTEL_DNV_SMBUS) res->start = (resource_size_t)base64_addr + SBREG_SMBCTRL_DNV; else @@ -1563,7 +1558,7 @@ i801_add_tco_spt(struct i801_priv *priv, struct pci_dev *pci_dev, res->flags = IORESOURCE_MEM; return platform_device_register_resndata(&pci_dev->dev, "iTCO_wdt", -1, - tco_res, 3, &spt_tco_platform_data, + tco_res, 2, &spt_tco_platform_data, sizeof(spt_tco_platform_data)); } @@ -1576,17 +1571,16 @@ static struct platform_device * i801_add_tco_cnl(struct i801_priv *priv, struct pci_dev *pci_dev, struct resource *tco_res) { - return platform_device_register_resndata(&pci_dev->dev, "iTCO_wdt", -1, - tco_res, 2, &cnl_tco_platform_data, - sizeof(cnl_tco_platform_data)); + return platform_device_register_resndata(&pci_dev->dev, + "iTCO_wdt", -1, tco_res, 1, &cnl_tco_platform_data, + sizeof(cnl_tco_platform_data)); } static void i801_add_tco(struct i801_priv *priv) { - u32 base_addr, tco_base, tco_ctl, ctrl_val; struct pci_dev *pci_dev = priv->pci_dev; - struct resource tco_res[3], *res; - unsigned int devfn; + struct resource tco_res[2], *res; + u32 tco_base, tco_ctl; /* If we have ACPI based watchdog use that instead */ if (acpi_has_watchdog()) @@ -1601,30 +1595,15 @@ static void i801_add_tco(struct i801_priv *priv) return; memset(tco_res, 0, sizeof(tco_res)); - - res = &tco_res[ICH_RES_IO_TCO]; - res->start = tco_base & ~1; - res->end = res->start + 32 - 1; - res->flags = IORESOURCE_IO; - /* - * Power Management registers. + * Always populate the main iTCO IO resource here. The second entry + * for NO_REBOOT MMIO is filled by the SPT specific function. */ - devfn = PCI_DEVFN(PCI_SLOT(pci_dev->devfn), 2); - pci_bus_read_config_dword(pci_dev->bus, devfn, ACPIBASE, &base_addr); - - res = &tco_res[ICH_RES_IO_SMI]; - res->start = (base_addr & ~1) + ACPIBASE_SMI_OFF; - res->end = res->start + 3; + res = &tco_res[0]; + res->start = tco_base & ~1; + res->end = res->start + 32 - 1; res->flags = IORESOURCE_IO; - /* - * Enable the ACPI I/O space. - */ - pci_bus_read_config_dword(pci_dev->bus, devfn, ACPICTRL, &ctrl_val); - ctrl_val |= ACPICTRL_EN; - pci_bus_write_config_dword(pci_dev->bus, devfn, ACPICTRL, ctrl_val); - if (priv->features & FEATURE_TCO_CNL) priv->tco_pdev = i801_add_tco_cnl(priv, pci_dev, tco_res); else diff --git a/drivers/i2c/busses/i2c-jz4780.c b/drivers/i2c/busses/i2c-jz4780.c index 16a67a64284a04c2d58192e1e763a63f3d13f51f..b426fc9569387d431a955fe3f274f87f735c11f9 100644 --- a/drivers/i2c/busses/i2c-jz4780.c +++ b/drivers/i2c/busses/i2c-jz4780.c @@ -78,25 +78,6 @@ #define X1000_I2C_DC_STOP BIT(9) -static const char * const jz4780_i2c_abrt_src[] = { - "ABRT_7B_ADDR_NOACK", - "ABRT_10ADDR1_NOACK", - "ABRT_10ADDR2_NOACK", - "ABRT_XDATA_NOACK", - "ABRT_GCALL_NOACK", - "ABRT_GCALL_READ", - "ABRT_HS_ACKD", - "SBYTE_ACKDET", - "ABRT_HS_NORSTRT", - "SBYTE_NORSTRT", - "ABRT_10B_RD_NORSTRT", - "ABRT_MASTER_DIS", - "ARB_LOST", - "SLVFLUSH_TXFIFO", - "SLV_ARBLOST", - "SLVRD_INTX", -}; - #define JZ4780_I2C_INTST_IGC BIT(11) #define JZ4780_I2C_INTST_ISTT BIT(10) #define JZ4780_I2C_INTST_ISTP BIT(9) @@ -576,21 +557,8 @@ static irqreturn_t jz4780_i2c_irq(int irqno, void *dev_id) static void jz4780_i2c_txabrt(struct jz4780_i2c *i2c, int src) { - int i; - - dev_err(&i2c->adap.dev, "txabrt: 0x%08x\n", src); - dev_err(&i2c->adap.dev, "device addr=%x\n", - jz4780_i2c_readw(i2c, JZ4780_I2C_TAR)); - dev_err(&i2c->adap.dev, "send cmd count:%d %d\n", - i2c->cmd, i2c->cmd_buf[i2c->cmd]); - dev_err(&i2c->adap.dev, "receive data count:%d %d\n", - i2c->cmd, i2c->data_buf[i2c->cmd]); - - for (i = 0; i < 16; i++) { - if (src & BIT(i)) - dev_dbg(&i2c->adap.dev, "I2C TXABRT[%d]=%s\n", - i, jz4780_i2c_abrt_src[i]); - } + dev_dbg(&i2c->adap.dev, "txabrt: 0x%08x, cmd: %d, send: %d, recv: %d\n", + src, i2c->cmd, i2c->cmd_buf[i2c->cmd], i2c->data_buf[i2c->cmd]); } static inline int jz4780_i2c_xfer_read(struct jz4780_i2c *i2c, diff --git a/drivers/i2c/i2c-core-acpi.c b/drivers/i2c/i2c-core-acpi.c index 8f3dbc97a0571e3de740677e680ec25ef4348775..8b0ff780919b1d0436f1f93c6567e36561803d02 100644 --- a/drivers/i2c/i2c-core-acpi.c +++ b/drivers/i2c/i2c-core-acpi.c @@ -394,9 +394,17 @@ EXPORT_SYMBOL_GPL(i2c_acpi_find_adapter_by_handle); static struct i2c_client *i2c_acpi_find_client_by_adev(struct acpi_device *adev) { struct device *dev; + struct i2c_client *client; dev = bus_find_device_by_acpi_dev(&i2c_bus_type, adev); - return dev ? i2c_verify_client(dev) : NULL; + if (!dev) + return NULL; + + client = i2c_verify_client(dev); + if (!client) + put_device(dev); + + return client; } static int i2c_acpi_notify(struct notifier_block *nb, unsigned long value, diff --git a/drivers/ide/ide-gd.c b/drivers/ide/ide-gd.c index 1bb99b5563930c810855d2fe2f23e83e8d619147..05c26986637ba3ad8d29d46387d8cb9f45219402 100644 --- a/drivers/ide/ide-gd.c +++ b/drivers/ide/ide-gd.c @@ -361,7 +361,7 @@ static const struct block_device_operations ide_gd_ops = { .release = ide_gd_release, .ioctl = ide_gd_ioctl, #ifdef CONFIG_COMPAT - .ioctl = ide_gd_compat_ioctl, + .compat_ioctl = ide_gd_compat_ioctl, #endif .getgeo = ide_gd_getgeo, .check_events = ide_gd_check_events, diff --git a/drivers/iio/accel/adxl372.c b/drivers/iio/accel/adxl372.c index 67b8817995c047b791c638da6e1131f9f967f222..60daf04ce1889f01225d68eead697a8d9610ea90 100644 --- a/drivers/iio/accel/adxl372.c +++ b/drivers/iio/accel/adxl372.c @@ -237,6 +237,7 @@ static const struct adxl372_axis_lookup adxl372_axis_lookup_table[] = { .realbits = 12, \ .storagebits = 16, \ .shift = 4, \ + .endianness = IIO_BE, \ }, \ } diff --git a/drivers/iio/accel/st_accel_i2c.c b/drivers/iio/accel/st_accel_i2c.c index 633955d764cca7c5225f9c29a45b0b7fafca618b..849cf74153c496d0cc57c2d8160a77d71d7ee79e 100644 --- a/drivers/iio/accel/st_accel_i2c.c +++ b/drivers/iio/accel/st_accel_i2c.c @@ -110,7 +110,7 @@ MODULE_DEVICE_TABLE(of, st_accel_of_match); #ifdef CONFIG_ACPI static const struct acpi_device_id st_accel_acpi_match[] = { - {"SMO8840", (kernel_ulong_t)LNG2DM_ACCEL_DEV_NAME}, + {"SMO8840", (kernel_ulong_t)LIS2DH12_ACCEL_DEV_NAME}, {"SMO8A90", (kernel_ulong_t)LNG2DM_ACCEL_DEV_NAME}, { }, }; diff --git a/drivers/iio/adc/at91-sama5d2_adc.c b/drivers/iio/adc/at91-sama5d2_adc.c index a5c7771227d518e84270f7cd2113ca99f51284e3..9d96f7d08b9567f4ff4663020c4d224cea568756 100644 --- a/drivers/iio/adc/at91-sama5d2_adc.c +++ b/drivers/iio/adc/at91-sama5d2_adc.c @@ -723,6 +723,7 @@ static int at91_adc_configure_trigger(struct iio_trigger *trig, bool state) for_each_set_bit(bit, indio->active_scan_mask, indio->num_channels) { struct iio_chan_spec const *chan = at91_adc_chan_get(indio, bit); + u32 cor; if (!chan) continue; @@ -731,6 +732,20 @@ static int at91_adc_configure_trigger(struct iio_trigger *trig, bool state) chan->type == IIO_PRESSURE) continue; + if (state) { + cor = at91_adc_readl(st, AT91_SAMA5D2_COR); + + if (chan->differential) + cor |= (BIT(chan->channel) | + BIT(chan->channel2)) << + AT91_SAMA5D2_COR_DIFF_OFFSET; + else + cor &= ~(BIT(chan->channel) << + AT91_SAMA5D2_COR_DIFF_OFFSET); + + at91_adc_writel(st, AT91_SAMA5D2_COR, cor); + } + if (state) { at91_adc_writel(st, AT91_SAMA5D2_CHER, BIT(chan->channel)); diff --git a/drivers/iio/adc/stm32-dfsdm-adc.c b/drivers/iio/adc/stm32-dfsdm-adc.c index 2aad2cda6943e1bd1e17340b38c64ba20c1d195c..76a60d93fe23f148791adb6e78b663a8b7363156 100644 --- a/drivers/iio/adc/stm32-dfsdm-adc.c +++ b/drivers/iio/adc/stm32-dfsdm-adc.c @@ -842,31 +842,6 @@ static inline void stm32_dfsdm_process_data(struct stm32_dfsdm_adc *adc, } } -static irqreturn_t stm32_dfsdm_adc_trigger_handler(int irq, void *p) -{ - struct iio_poll_func *pf = p; - struct iio_dev *indio_dev = pf->indio_dev; - struct stm32_dfsdm_adc *adc = iio_priv(indio_dev); - int available = stm32_dfsdm_adc_dma_residue(adc); - - while (available >= indio_dev->scan_bytes) { - s32 *buffer = (s32 *)&adc->rx_buf[adc->bufi]; - - stm32_dfsdm_process_data(adc, buffer); - - iio_push_to_buffers_with_timestamp(indio_dev, buffer, - pf->timestamp); - available -= indio_dev->scan_bytes; - adc->bufi += indio_dev->scan_bytes; - if (adc->bufi >= adc->buf_sz) - adc->bufi = 0; - } - - iio_trigger_notify_done(indio_dev->trig); - - return IRQ_HANDLED; -} - static void stm32_dfsdm_dma_buffer_done(void *data) { struct iio_dev *indio_dev = data; @@ -874,11 +849,6 @@ static void stm32_dfsdm_dma_buffer_done(void *data) int available = stm32_dfsdm_adc_dma_residue(adc); size_t old_pos; - if (indio_dev->currentmode & INDIO_BUFFER_TRIGGERED) { - iio_trigger_poll_chained(indio_dev->trig); - return; - } - /* * FIXME: In Kernel interface does not support cyclic DMA buffer,and * offers only an interface to push data samples per samples. @@ -906,7 +876,15 @@ static void stm32_dfsdm_dma_buffer_done(void *data) adc->bufi = 0; old_pos = 0; } - /* regular iio buffer without trigger */ + /* + * In DMA mode the trigger services of IIO are not used + * (e.g. no call to iio_trigger_poll). + * Calling irq handler associated to the hardware trigger is not + * relevant as the conversions have already been done. Data + * transfers are performed directly in DMA callback instead. + * This implementation avoids to call trigger irq handler that + * may sleep, in an atomic context (DMA irq handler context). + */ if (adc->dev_data->type == DFSDM_IIO) iio_push_to_buffers(indio_dev, buffer); } @@ -1536,8 +1514,7 @@ static int stm32_dfsdm_adc_init(struct iio_dev *indio_dev) } ret = iio_triggered_buffer_setup(indio_dev, - &iio_pollfunc_store_time, - &stm32_dfsdm_adc_trigger_handler, + &iio_pollfunc_store_time, NULL, &stm32_dfsdm_buffer_setup_ops); if (ret) { stm32_dfsdm_dma_release(indio_dev); diff --git a/drivers/iio/chemical/Kconfig b/drivers/iio/chemical/Kconfig index 0b91de4df8f4609daf0ad14d80db9f3665d38d34..a7e65a59bf42996a1923c8db8dbbeba4252cab5b 100644 --- a/drivers/iio/chemical/Kconfig +++ b/drivers/iio/chemical/Kconfig @@ -91,6 +91,8 @@ config SPS30 tristate "SPS30 particulate matter sensor" depends on I2C select CRC8 + select IIO_BUFFER + select IIO_TRIGGERED_BUFFER help Say Y here to build support for the Sensirion SPS30 particulate matter sensor. diff --git a/drivers/iio/light/vcnl4000.c b/drivers/iio/light/vcnl4000.c index b0e241aaefb48863c28f06235bdab3b3ac221fa7..e5b00a6611acd28f9a6a34131e8d1f7da01be4a9 100644 --- a/drivers/iio/light/vcnl4000.c +++ b/drivers/iio/light/vcnl4000.c @@ -167,16 +167,17 @@ static int vcnl4200_init(struct vcnl4000_data *data) data->vcnl4200_ps.reg = VCNL4200_PS_DATA; switch (id) { case VCNL4200_PROD_ID: - /* Integration time is 50ms, but the experiments */ - /* show 54ms in total. */ - data->vcnl4200_al.sampling_rate = ktime_set(0, 54000 * 1000); - data->vcnl4200_ps.sampling_rate = ktime_set(0, 4200 * 1000); + /* Default wait time is 50ms, add 20% tolerance. */ + data->vcnl4200_al.sampling_rate = ktime_set(0, 60000 * 1000); + /* Default wait time is 4.8ms, add 20% tolerance. */ + data->vcnl4200_ps.sampling_rate = ktime_set(0, 5760 * 1000); data->al_scale = 24000; break; case VCNL4040_PROD_ID: - /* Integration time is 80ms, add 10ms. */ - data->vcnl4200_al.sampling_rate = ktime_set(0, 100000 * 1000); - data->vcnl4200_ps.sampling_rate = ktime_set(0, 100000 * 1000); + /* Default wait time is 80ms, add 20% tolerance. */ + data->vcnl4200_al.sampling_rate = ktime_set(0, 96000 * 1000); + /* Default wait time is 5ms, add 20% tolerance. */ + data->vcnl4200_ps.sampling_rate = ktime_set(0, 6000 * 1000); data->al_scale = 120000; break; } diff --git a/drivers/iio/magnetometer/ak8974.c b/drivers/iio/magnetometer/ak8974.c index fc7e910f8e8bfd1c7bf63664d20a6e7133e847f5..d3299670211035236a20cc0ee83130a9dbb4c904 100644 --- a/drivers/iio/magnetometer/ak8974.c +++ b/drivers/iio/magnetometer/ak8974.c @@ -564,7 +564,7 @@ static int ak8974_read_raw(struct iio_dev *indio_dev, * We read all axes and discard all but one, for optimized * reading, use the triggered buffer. */ - *val = le16_to_cpu(hw_values[chan->address]); + *val = (s16)le16_to_cpu(hw_values[chan->address]); ret = IIO_VAL_INT; } diff --git a/drivers/iio/proximity/ping.c b/drivers/iio/proximity/ping.c index 34aff108dff54dfed75e0821515f7370d5d81f0d..12b893c5b0eed33781634d9a4d039d7c7f8afc1a 100644 --- a/drivers/iio/proximity/ping.c +++ b/drivers/iio/proximity/ping.c @@ -269,7 +269,7 @@ static const struct iio_chan_spec ping_chan_spec[] = { static const struct of_device_id of_ping_match[] = { { .compatible = "parallax,ping", .data = &pa_ping_cfg}, - { .compatible = "parallax,laserping", .data = &pa_ping_cfg}, + { .compatible = "parallax,laserping", .data = &pa_laser_ping_cfg}, {}, }; diff --git a/drivers/iio/trigger/stm32-timer-trigger.c b/drivers/iio/trigger/stm32-timer-trigger.c index 2e0d32aa843665af68dcc0ffe1215444d02a7f06..2f82e8c32186fdd66fa5cfb1aa386f0f8813082d 100644 --- a/drivers/iio/trigger/stm32-timer-trigger.c +++ b/drivers/iio/trigger/stm32-timer-trigger.c @@ -161,7 +161,8 @@ static int stm32_timer_start(struct stm32_timer_trigger *priv, return 0; } -static void stm32_timer_stop(struct stm32_timer_trigger *priv) +static void stm32_timer_stop(struct stm32_timer_trigger *priv, + struct iio_trigger *trig) { u32 ccer, cr1; @@ -179,6 +180,12 @@ static void stm32_timer_stop(struct stm32_timer_trigger *priv) regmap_write(priv->regmap, TIM_PSC, 0); regmap_write(priv->regmap, TIM_ARR, 0); + /* Force disable master mode */ + if (stm32_timer_is_trgo2_name(trig->name)) + regmap_update_bits(priv->regmap, TIM_CR2, TIM_CR2_MMS2, 0); + else + regmap_update_bits(priv->regmap, TIM_CR2, TIM_CR2_MMS, 0); + /* Make sure that registers are updated */ regmap_update_bits(priv->regmap, TIM_EGR, TIM_EGR_UG, TIM_EGR_UG); } @@ -197,7 +204,7 @@ static ssize_t stm32_tt_store_frequency(struct device *dev, return ret; if (freq == 0) { - stm32_timer_stop(priv); + stm32_timer_stop(priv, trig); } else { ret = stm32_timer_start(priv, trig, freq); if (ret) diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 68cc1b2d68240dfb566f1552a4ff6081a52c192a..15e99a8884275fd921b4309212d57030f50f52d7 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -1191,6 +1191,7 @@ struct ib_cm_id *ib_cm_insert_listen(struct ib_device *device, /* Sharing an ib_cm_id with different handlers is not * supported */ spin_unlock_irqrestore(&cm.lock, flags); + ib_destroy_cm_id(cm_id); return ERR_PTR(-EINVAL); } refcount_inc(&cm_id_priv->refcount); diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 72f032160c4bd92ff54561463438d5b27dd4ee51..2dec3a02ab9fe7634cae6aba07532e3478737c73 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -3212,19 +3212,26 @@ int rdma_resolve_addr(struct rdma_cm_id *id, struct sockaddr *src_addr, int ret; id_priv = container_of(id, struct rdma_id_private, id); + memcpy(cma_dst_addr(id_priv), dst_addr, rdma_addr_size(dst_addr)); if (id_priv->state == RDMA_CM_IDLE) { ret = cma_bind_addr(id, src_addr, dst_addr); - if (ret) + if (ret) { + memset(cma_dst_addr(id_priv), 0, + rdma_addr_size(dst_addr)); return ret; + } } - if (cma_family(id_priv) != dst_addr->sa_family) + if (cma_family(id_priv) != dst_addr->sa_family) { + memset(cma_dst_addr(id_priv), 0, rdma_addr_size(dst_addr)); return -EINVAL; + } - if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_ADDR_QUERY)) + if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_ADDR_QUERY)) { + memset(cma_dst_addr(id_priv), 0, rdma_addr_size(dst_addr)); return -EINVAL; + } - memcpy(cma_dst_addr(id_priv), dst_addr, rdma_addr_size(dst_addr)); if (cma_any_addr(dst_addr)) { ret = cma_resolve_loopback(id_priv); } else { diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h index b1457b3464d34f0dd6489a7c7f6a02768ef6d2e6..cf42acca4a3a387a23b5a4dac6f8f190214175d4 100644 --- a/drivers/infiniband/core/core_priv.h +++ b/drivers/infiniband/core/core_priv.h @@ -338,6 +338,20 @@ static inline struct ib_qp *_ib_create_qp(struct ib_device *dev, qp->pd = pd; qp->uobject = uobj; qp->real_qp = qp; + + qp->qp_type = attr->qp_type; + qp->rwq_ind_tbl = attr->rwq_ind_tbl; + qp->send_cq = attr->send_cq; + qp->recv_cq = attr->recv_cq; + qp->srq = attr->srq; + qp->rwq_ind_tbl = attr->rwq_ind_tbl; + qp->event_handler = attr->event_handler; + + atomic_set(&qp->usecnt, 0); + spin_lock_init(&qp->mr_lock); + INIT_LIST_HEAD(&qp->rdma_mrs); + INIT_LIST_HEAD(&qp->sig_mrs); + /* * We don't track XRC QPs for now, because they don't have PD * and more importantly they are created internaly by driver, diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c index ade71823370f3335566079599a76dde871cc9333..da8adadf47559eb3144709d075264d1321d92dd5 100644 --- a/drivers/infiniband/core/iwcm.c +++ b/drivers/infiniband/core/iwcm.c @@ -159,8 +159,10 @@ static void dealloc_work_entries(struct iwcm_id_private *cm_id_priv) { struct list_head *e, *tmp; - list_for_each_safe(e, tmp, &cm_id_priv->work_free_list) + list_for_each_safe(e, tmp, &cm_id_priv->work_free_list) { + list_del(e); kfree(list_entry(e, struct iwcm_work, free_list)); + } } static int alloc_work_entries(struct iwcm_id_private *cm_id_priv, int count) diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c index 37b433aa730610e0f2d1806c37a5dbe31dae7d93..e0b0a91da696c5881306b9448f49aafcb33979de 100644 --- a/drivers/infiniband/core/nldev.c +++ b/drivers/infiniband/core/nldev.c @@ -1757,6 +1757,8 @@ static int nldev_stat_set_doit(struct sk_buff *skb, struct nlmsghdr *nlh, if (ret) goto err_msg; } else { + if (!tb[RDMA_NLDEV_ATTR_RES_LQPN]) + goto err_msg; qpn = nla_get_u32(tb[RDMA_NLDEV_ATTR_RES_LQPN]); if (tb[RDMA_NLDEV_ATTR_STAT_COUNTER_ID]) { cntn = nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_COUNTER_ID]); diff --git a/drivers/infiniband/core/rw.c b/drivers/infiniband/core/rw.c index 4fad732f9b3cc40041c7ba25139756ca425e7219..06e5b6787443ad2fc577cfbf630f72a6ce4d6773 100644 --- a/drivers/infiniband/core/rw.c +++ b/drivers/infiniband/core/rw.c @@ -273,6 +273,23 @@ static int rdma_rw_init_single_wr(struct rdma_rw_ctx *ctx, struct ib_qp *qp, return 1; } +static void rdma_rw_unmap_sg(struct ib_device *dev, struct scatterlist *sg, + u32 sg_cnt, enum dma_data_direction dir) +{ + if (is_pci_p2pdma_page(sg_page(sg))) + pci_p2pdma_unmap_sg(dev->dma_device, sg, sg_cnt, dir); + else + ib_dma_unmap_sg(dev, sg, sg_cnt, dir); +} + +static int rdma_rw_map_sg(struct ib_device *dev, struct scatterlist *sg, + u32 sg_cnt, enum dma_data_direction dir) +{ + if (is_pci_p2pdma_page(sg_page(sg))) + return pci_p2pdma_map_sg(dev->dma_device, sg, sg_cnt, dir); + return ib_dma_map_sg(dev, sg, sg_cnt, dir); +} + /** * rdma_rw_ctx_init - initialize a RDMA READ/WRITE context * @ctx: context to initialize @@ -295,11 +312,7 @@ int rdma_rw_ctx_init(struct rdma_rw_ctx *ctx, struct ib_qp *qp, u8 port_num, struct ib_device *dev = qp->pd->device; int ret; - if (is_pci_p2pdma_page(sg_page(sg))) - ret = pci_p2pdma_map_sg(dev->dma_device, sg, sg_cnt, dir); - else - ret = ib_dma_map_sg(dev, sg, sg_cnt, dir); - + ret = rdma_rw_map_sg(dev, sg, sg_cnt, dir); if (!ret) return -ENOMEM; sg_cnt = ret; @@ -338,7 +351,7 @@ int rdma_rw_ctx_init(struct rdma_rw_ctx *ctx, struct ib_qp *qp, u8 port_num, return ret; out_unmap_sg: - ib_dma_unmap_sg(dev, sg, sg_cnt, dir); + rdma_rw_unmap_sg(dev, sg, sg_cnt, dir); return ret; } EXPORT_SYMBOL(rdma_rw_ctx_init); @@ -588,11 +601,7 @@ void rdma_rw_ctx_destroy(struct rdma_rw_ctx *ctx, struct ib_qp *qp, u8 port_num, break; } - if (is_pci_p2pdma_page(sg_page(sg))) - pci_p2pdma_unmap_sg(qp->pd->device->dma_device, sg, - sg_cnt, dir); - else - ib_dma_unmap_sg(qp->pd->device, sg, sg_cnt, dir); + rdma_rw_unmap_sg(qp->pd->device, sg, sg_cnt, dir); } EXPORT_SYMBOL(rdma_rw_ctx_destroy); diff --git a/drivers/infiniband/core/security.c b/drivers/infiniband/core/security.c index 6eb6d2717ca5b2b392acc723d82ca5efcac1d5ce..2d5608315dc80139128e1673441bb008004d00e6 100644 --- a/drivers/infiniband/core/security.c +++ b/drivers/infiniband/core/security.c @@ -339,22 +339,20 @@ static struct ib_ports_pkeys *get_new_pps(const struct ib_qp *qp, if (!new_pps) return NULL; - if (qp_attr_mask & (IB_QP_PKEY_INDEX | IB_QP_PORT)) { - if (!qp_pps) { - new_pps->main.port_num = qp_attr->port_num; - new_pps->main.pkey_index = qp_attr->pkey_index; - } else { - new_pps->main.port_num = (qp_attr_mask & IB_QP_PORT) ? - qp_attr->port_num : - qp_pps->main.port_num; - - new_pps->main.pkey_index = - (qp_attr_mask & IB_QP_PKEY_INDEX) ? - qp_attr->pkey_index : - qp_pps->main.pkey_index; - } + if (qp_attr_mask & IB_QP_PORT) + new_pps->main.port_num = qp_attr->port_num; + else if (qp_pps) + new_pps->main.port_num = qp_pps->main.port_num; + + if (qp_attr_mask & IB_QP_PKEY_INDEX) + new_pps->main.pkey_index = qp_attr->pkey_index; + else if (qp_pps) + new_pps->main.pkey_index = qp_pps->main.pkey_index; + + if ((qp_attr_mask & IB_QP_PKEY_INDEX) && (qp_attr_mask & IB_QP_PORT)) new_pps->main.state = IB_PORT_PKEY_VALID; - } else if (qp_pps) { + + if (!(qp_attr_mask & (IB_QP_PKEY_INDEX | IB_QP_PORT)) && qp_pps) { new_pps->main.port_num = qp_pps->main.port_num; new_pps->main.pkey_index = qp_pps->main.pkey_index; if (qp_pps->main.state != IB_PORT_PKEY_NOT_VALID) diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c index b8c657b2838048b987d4429584dd9b743afd45db..cd656ad4953bfce4d8d3efabb34b6794662132c0 100644 --- a/drivers/infiniband/core/umem_odp.c +++ b/drivers/infiniband/core/umem_odp.c @@ -181,14 +181,28 @@ ib_umem_odp_alloc_child(struct ib_umem_odp *root, unsigned long addr, odp_data->page_shift = PAGE_SHIFT; odp_data->notifier.ops = ops; + /* + * A mmget must be held when registering a notifier, the owming_mm only + * has a mm_grab at this point. + */ + if (!mmget_not_zero(umem->owning_mm)) { + ret = -EFAULT; + goto out_free; + } + odp_data->tgid = get_pid(root->tgid); ret = ib_init_umem_odp(odp_data, ops); - if (ret) { - put_pid(odp_data->tgid); - kfree(odp_data); - return ERR_PTR(ret); - } + if (ret) + goto out_tgid; + mmput(umem->owning_mm); return odp_data; + +out_tgid: + put_pid(odp_data->tgid); + mmput(umem->owning_mm); +out_free: + kfree(odp_data); + return ERR_PTR(ret); } EXPORT_SYMBOL(ib_umem_odp_alloc_child); diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c index d1407fa378e832bdfe45ba4c4b35645bd59b3a89..1235ffb2389b1c00feed521311fb54d019337c4a 100644 --- a/drivers/infiniband/core/user_mad.c +++ b/drivers/infiniband/core/user_mad.c @@ -1312,6 +1312,9 @@ static void ib_umad_kill_port(struct ib_umad_port *port) struct ib_umad_file *file; int id; + cdev_device_del(&port->sm_cdev, &port->sm_dev); + cdev_device_del(&port->cdev, &port->dev); + mutex_lock(&port->file_mutex); /* Mark ib_dev NULL and block ioctl or other file ops to progress @@ -1331,8 +1334,6 @@ static void ib_umad_kill_port(struct ib_umad_port *port) mutex_unlock(&port->file_mutex); - cdev_device_del(&port->sm_cdev, &port->sm_dev); - cdev_device_del(&port->cdev, &port->dev); ida_free(&umad_ida, port->dev_num); /* balances device_initialize() */ diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index c8693f5231dd7dcfe678469662b628863df4a416..060b4ebbd2ba4d7b393f33c887d5ac80d8471502 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -1445,16 +1445,7 @@ static int create_qp(struct uverbs_attr_bundle *attrs, if (ret) goto err_cb; - qp->pd = pd; - qp->send_cq = attr.send_cq; - qp->recv_cq = attr.recv_cq; - qp->srq = attr.srq; - qp->rwq_ind_tbl = ind_tbl; - qp->event_handler = attr.event_handler; - qp->qp_type = attr.qp_type; - atomic_set(&qp->usecnt, 0); atomic_inc(&pd->usecnt); - qp->port = 0; if (attr.send_cq) atomic_inc(&attr.send_cq->usecnt); if (attr.recv_cq) @@ -2745,12 +2736,6 @@ static int kern_spec_to_ib_spec_action(struct uverbs_attr_bundle *attrs, return 0; } -static size_t kern_spec_filter_sz(const struct ib_uverbs_flow_spec_hdr *spec) -{ - /* Returns user space filter size, includes padding */ - return (spec->size - sizeof(struct ib_uverbs_flow_spec_hdr)) / 2; -} - static ssize_t spec_filter_size(const void *kern_spec_filter, u16 kern_filter_size, u16 ib_real_filter_sz) { @@ -2894,11 +2879,16 @@ int ib_uverbs_kern_spec_to_ib_spec_filter(enum ib_flow_spec_type type, static int kern_spec_to_ib_spec_filter(struct ib_uverbs_flow_spec *kern_spec, union ib_flow_spec *ib_spec) { - ssize_t kern_filter_sz; + size_t kern_filter_sz; void *kern_spec_mask; void *kern_spec_val; - kern_filter_sz = kern_spec_filter_sz(&kern_spec->hdr); + if (check_sub_overflow((size_t)kern_spec->hdr.size, + sizeof(struct ib_uverbs_flow_spec_hdr), + &kern_filter_sz)) + return -EINVAL; + + kern_filter_sz /= 2; kern_spec_val = (void *)kern_spec + sizeof(struct ib_uverbs_flow_spec_hdr); diff --git a/drivers/infiniband/core/uverbs_std_types.c b/drivers/infiniband/core/uverbs_std_types.c index 994d8744b246921ea1c3f0b89a159d621acebecf..3abfc63225cbfa24aea4c991d808b355a21eb0f9 100644 --- a/drivers/infiniband/core/uverbs_std_types.c +++ b/drivers/infiniband/core/uverbs_std_types.c @@ -220,6 +220,7 @@ void ib_uverbs_free_event_queue(struct ib_uverbs_event_queue *event_queue) list_for_each_entry_safe(entry, tmp, &event_queue->event_list, list) { if (entry->counter) list_del(&entry->obj_list); + list_del(&entry->list); kfree(entry); } spin_unlock_irq(&event_queue->lock); diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index 3ebae3b65c28210919fe3f4135d81b1d78faaccb..e62c9dfc7837a86b5a1fdfb7101e5ee0d54c79f7 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -1185,16 +1185,6 @@ struct ib_qp *ib_create_qp_user(struct ib_pd *pd, if (ret) goto err; - qp->qp_type = qp_init_attr->qp_type; - qp->rwq_ind_tbl = qp_init_attr->rwq_ind_tbl; - - atomic_set(&qp->usecnt, 0); - qp->mrs_used = 0; - spin_lock_init(&qp->mr_lock); - INIT_LIST_HEAD(&qp->rdma_mrs); - INIT_LIST_HEAD(&qp->sig_mrs); - qp->port = 0; - if (qp_init_attr->qp_type == IB_QPT_XRC_TGT) { struct ib_qp *xrc_qp = create_xrc_qp_user(qp, qp_init_attr, udata); diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index ee1182f9b627e5db1b6192c836e6cbe1a5bf9157..d69dece3b1d541ad3b834cc9ea128de7c9f20168 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -3036,6 +3036,10 @@ static int terminate(struct c4iw_dev *dev, struct sk_buff *skb) C4IW_QP_ATTR_NEXT_STATE, &attrs, 1); } + /* As per draft-hilland-iwarp-verbs-v1.0, sec 6.2.3, + * when entering the TERM state the RNIC MUST initiate a CLOSE. + */ + c4iw_ep_disconnect(ep, 1, GFP_KERNEL); c4iw_put_ep(&ep->com); } else pr_warn("TERM received tid %u no ep/qp\n", tid); diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c index bbcac539777a2f62281963bf988465c6add06d58..89ac2f9ae6dd8219cf24d70b5f046c9ff9d255a5 100644 --- a/drivers/infiniband/hw/cxgb4/qp.c +++ b/drivers/infiniband/hw/cxgb4/qp.c @@ -1948,10 +1948,10 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp, qhp->attr.layer_etype = attrs->layer_etype; qhp->attr.ecode = attrs->ecode; ep = qhp->ep; - c4iw_get_ep(&ep->com); - disconnect = 1; if (!internal) { + c4iw_get_ep(&ep->com); terminate = 1; + disconnect = 1; } else { terminate = qhp->attr.send_term; ret = rdma_fini(rhp, qhp, ep); diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c index c142b23bb40183d61bc009a1904b65768bac711c..1aeea5d65c0159756605dbfbc660dce7e1c4bd13 100644 --- a/drivers/infiniband/hw/hfi1/affinity.c +++ b/drivers/infiniband/hw/hfi1/affinity.c @@ -479,6 +479,8 @@ static int _dev_comp_vect_mappings_create(struct hfi1_devdata *dd, rvt_get_ibdev_name(&(dd)->verbs_dev.rdi), i, cpu); } + free_cpumask_var(available_cpus); + free_cpumask_var(non_intr_cpus); return 0; fail: diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c index bef6946861b24432c99fc4cd06621f9c4ce72d53..259115886d35145a8ffbde8a804b93b7c96dec4a 100644 --- a/drivers/infiniband/hw/hfi1/file_ops.c +++ b/drivers/infiniband/hw/hfi1/file_ops.c @@ -200,23 +200,24 @@ static int hfi1_file_open(struct inode *inode, struct file *fp) fd = kzalloc(sizeof(*fd), GFP_KERNEL); - if (fd) { - fd->rec_cpu_num = -1; /* no cpu affinity by default */ - fd->mm = current->mm; - mmgrab(fd->mm); - fd->dd = dd; - kobject_get(&fd->dd->kobj); - fp->private_data = fd; - } else { - fp->private_data = NULL; - - if (atomic_dec_and_test(&dd->user_refcount)) - complete(&dd->user_comp); - - return -ENOMEM; - } - + if (!fd || init_srcu_struct(&fd->pq_srcu)) + goto nomem; + spin_lock_init(&fd->pq_rcu_lock); + spin_lock_init(&fd->tid_lock); + spin_lock_init(&fd->invalid_lock); + fd->rec_cpu_num = -1; /* no cpu affinity by default */ + fd->mm = current->mm; + mmgrab(fd->mm); + fd->dd = dd; + kobject_get(&fd->dd->kobj); + fp->private_data = fd; return 0; +nomem: + kfree(fd); + fp->private_data = NULL; + if (atomic_dec_and_test(&dd->user_refcount)) + complete(&dd->user_comp); + return -ENOMEM; } static long hfi1_file_ioctl(struct file *fp, unsigned int cmd, @@ -301,21 +302,30 @@ static long hfi1_file_ioctl(struct file *fp, unsigned int cmd, static ssize_t hfi1_write_iter(struct kiocb *kiocb, struct iov_iter *from) { struct hfi1_filedata *fd = kiocb->ki_filp->private_data; - struct hfi1_user_sdma_pkt_q *pq = fd->pq; + struct hfi1_user_sdma_pkt_q *pq; struct hfi1_user_sdma_comp_q *cq = fd->cq; int done = 0, reqs = 0; unsigned long dim = from->nr_segs; + int idx; - if (!cq || !pq) + idx = srcu_read_lock(&fd->pq_srcu); + pq = srcu_dereference(fd->pq, &fd->pq_srcu); + if (!cq || !pq) { + srcu_read_unlock(&fd->pq_srcu, idx); return -EIO; + } - if (!iter_is_iovec(from) || !dim) + if (!iter_is_iovec(from) || !dim) { + srcu_read_unlock(&fd->pq_srcu, idx); return -EINVAL; + } trace_hfi1_sdma_request(fd->dd, fd->uctxt->ctxt, fd->subctxt, dim); - if (atomic_read(&pq->n_reqs) == pq->n_max_reqs) + if (atomic_read(&pq->n_reqs) == pq->n_max_reqs) { + srcu_read_unlock(&fd->pq_srcu, idx); return -ENOSPC; + } while (dim) { int ret; @@ -333,6 +343,7 @@ static ssize_t hfi1_write_iter(struct kiocb *kiocb, struct iov_iter *from) reqs++; } + srcu_read_unlock(&fd->pq_srcu, idx); return reqs; } @@ -707,6 +718,7 @@ static int hfi1_file_close(struct inode *inode, struct file *fp) if (atomic_dec_and_test(&dd->user_refcount)) complete(&dd->user_comp); + cleanup_srcu_struct(&fdata->pq_srcu); kfree(fdata); return 0; } diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h index 6365e8ffed9d4c0f47e3e813977fb379d1e3e982..cae12f416ca0e4e8ac9e29fb0da486cf0c225db6 100644 --- a/drivers/infiniband/hw/hfi1/hfi.h +++ b/drivers/infiniband/hw/hfi1/hfi.h @@ -1444,10 +1444,13 @@ struct mmu_rb_handler; /* Private data for file operations */ struct hfi1_filedata { + struct srcu_struct pq_srcu; struct hfi1_devdata *dd; struct hfi1_ctxtdata *uctxt; struct hfi1_user_sdma_comp_q *cq; - struct hfi1_user_sdma_pkt_q *pq; + /* update side lock for SRCU */ + spinlock_t pq_rcu_lock; + struct hfi1_user_sdma_pkt_q __rcu *pq; u16 subctxt; /* for cpu affinity; -1 if none */ int rec_cpu_num; diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.c b/drivers/infiniband/hw/hfi1/user_exp_rcv.c index f05742ac0949712e2480948449bc2a3b74b3445c..4da03f82347492001c5e0fb49af5393087be9b4b 100644 --- a/drivers/infiniband/hw/hfi1/user_exp_rcv.c +++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.c @@ -87,9 +87,6 @@ int hfi1_user_exp_rcv_init(struct hfi1_filedata *fd, { int ret = 0; - spin_lock_init(&fd->tid_lock); - spin_lock_init(&fd->invalid_lock); - fd->entry_to_rb = kcalloc(uctxt->expected_count, sizeof(struct rb_node *), GFP_KERNEL); @@ -142,10 +139,12 @@ void hfi1_user_exp_rcv_free(struct hfi1_filedata *fd) { struct hfi1_ctxtdata *uctxt = fd->uctxt; + mutex_lock(&uctxt->exp_mutex); if (!EXP_TID_SET_EMPTY(uctxt->tid_full_list)) unlock_exp_tids(uctxt, &uctxt->tid_full_list, fd); if (!EXP_TID_SET_EMPTY(uctxt->tid_used_list)) unlock_exp_tids(uctxt, &uctxt->tid_used_list, fd); + mutex_unlock(&uctxt->exp_mutex); kfree(fd->invalid_tids); fd->invalid_tids = NULL; diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c index fd754a16475a540de927aa938445856ffc5314b9..c2f0d9ba93de17dc3e5bd7d78f45d5e8a1d36b68 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.c +++ b/drivers/infiniband/hw/hfi1/user_sdma.c @@ -179,7 +179,6 @@ int hfi1_user_sdma_alloc_queues(struct hfi1_ctxtdata *uctxt, pq = kzalloc(sizeof(*pq), GFP_KERNEL); if (!pq) return -ENOMEM; - pq->dd = dd; pq->ctxt = uctxt->ctxt; pq->subctxt = fd->subctxt; @@ -236,7 +235,7 @@ int hfi1_user_sdma_alloc_queues(struct hfi1_ctxtdata *uctxt, goto pq_mmu_fail; } - fd->pq = pq; + rcu_assign_pointer(fd->pq, pq); fd->cq = cq; return 0; @@ -264,8 +263,14 @@ int hfi1_user_sdma_free_queues(struct hfi1_filedata *fd, trace_hfi1_sdma_user_free_queues(uctxt->dd, uctxt->ctxt, fd->subctxt); - pq = fd->pq; + spin_lock(&fd->pq_rcu_lock); + pq = srcu_dereference_check(fd->pq, &fd->pq_srcu, + lockdep_is_held(&fd->pq_rcu_lock)); if (pq) { + rcu_assign_pointer(fd->pq, NULL); + spin_unlock(&fd->pq_rcu_lock); + synchronize_srcu(&fd->pq_srcu); + /* at this point there can be no more new requests */ if (pq->handler) hfi1_mmu_rb_unregister(pq->handler); iowait_sdma_drain(&pq->busy); @@ -277,7 +282,8 @@ int hfi1_user_sdma_free_queues(struct hfi1_filedata *fd, kfree(pq->req_in_use); kmem_cache_destroy(pq->txreq_cache); kfree(pq); - fd->pq = NULL; + } else { + spin_unlock(&fd->pq_rcu_lock); } if (fd->cq) { vfree(fd->cq->comps); @@ -321,7 +327,8 @@ int hfi1_user_sdma_process_request(struct hfi1_filedata *fd, { int ret = 0, i; struct hfi1_ctxtdata *uctxt = fd->uctxt; - struct hfi1_user_sdma_pkt_q *pq = fd->pq; + struct hfi1_user_sdma_pkt_q *pq = + srcu_dereference(fd->pq, &fd->pq_srcu); struct hfi1_user_sdma_comp_q *cq = fd->cq; struct hfi1_devdata *dd = pq->dd; unsigned long idx = 0; diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c index 089e201d75500072f527410a6ea8b1499fef19b1..2f6323ad9c598561585ff1a00323c39265f92ac6 100644 --- a/drivers/infiniband/hw/hfi1/verbs.c +++ b/drivers/infiniband/hw/hfi1/verbs.c @@ -515,10 +515,11 @@ static inline void hfi1_handle_packet(struct hfi1_packet *packet, opa_get_lid(packet->dlid, 9B)); if (!mcast) goto drop; + rcu_read_lock(); list_for_each_entry_rcu(p, &mcast->qp_list, list) { packet->qp = p->qp; if (hfi1_do_pkey_check(packet)) - goto drop; + goto unlock_drop; spin_lock_irqsave(&packet->qp->r_lock, flags); packet_handler = qp_ok(packet); if (likely(packet_handler)) @@ -527,6 +528,7 @@ static inline void hfi1_handle_packet(struct hfi1_packet *packet, ibp->rvp.n_pkt_drops++; spin_unlock_irqrestore(&packet->qp->r_lock, flags); } + rcu_read_unlock(); /* * Notify rvt_multicast_detach() if it is waiting for us * to finish. diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index d7efc9f6daf09d13499735a527822c1faedd92ca..46e1ab771f106065d7998eaf14cdba29faa851f6 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -2319,14 +2319,12 @@ static int deliver_event(struct devx_event_subscription *event_sub, if (ev_file->omit_data) { spin_lock_irqsave(&ev_file->lock, flags); - if (!list_empty(&event_sub->event_list)) { + if (!list_empty(&event_sub->event_list) || + ev_file->is_destroyed) { spin_unlock_irqrestore(&ev_file->lock, flags); return 0; } - /* is_destroyed is ignored here because we don't have any memory - * allocation to clean up for the omit_data case - */ list_add_tail(&event_sub->event_list, &ev_file->event_list); spin_unlock_irqrestore(&ev_file->lock, flags); wake_up_interruptible(&ev_file->poll_wait); @@ -2473,11 +2471,11 @@ static ssize_t devx_async_cmd_event_read(struct file *filp, char __user *buf, return -ERESTARTSYS; } - if (list_empty(&ev_queue->event_list) && - ev_queue->is_destroyed) - return -EIO; - spin_lock_irq(&ev_queue->lock); + if (ev_queue->is_destroyed) { + spin_unlock_irq(&ev_queue->lock); + return -EIO; + } } event = list_entry(ev_queue->event_list.next, @@ -2551,10 +2549,6 @@ static ssize_t devx_async_event_read(struct file *filp, char __user *buf, return -EOVERFLOW; } - if (ev_file->is_destroyed) { - spin_unlock_irq(&ev_file->lock); - return -EIO; - } while (list_empty(&ev_file->event_list)) { spin_unlock_irq(&ev_file->lock); @@ -2667,8 +2661,10 @@ static int devx_async_cmd_event_destroy_uobj(struct ib_uobject *uobj, spin_lock_irq(&comp_ev_file->ev_queue.lock); list_for_each_entry_safe(entry, tmp, - &comp_ev_file->ev_queue.event_list, list) + &comp_ev_file->ev_queue.event_list, list) { + list_del(&entry->list); kvfree(entry); + } spin_unlock_irq(&comp_ev_file->ev_queue.lock); return 0; }; @@ -2680,11 +2676,29 @@ static int devx_async_event_destroy_uobj(struct ib_uobject *uobj, container_of(uobj, struct devx_async_event_file, uobj); struct devx_event_subscription *event_sub, *event_sub_tmp; - struct devx_async_event_data *entry, *tmp; struct mlx5_ib_dev *dev = ev_file->dev; spin_lock_irq(&ev_file->lock); ev_file->is_destroyed = 1; + + /* free the pending events allocation */ + if (ev_file->omit_data) { + struct devx_event_subscription *event_sub, *tmp; + + list_for_each_entry_safe(event_sub, tmp, &ev_file->event_list, + event_list) + list_del_init(&event_sub->event_list); + + } else { + struct devx_async_event_data *entry, *tmp; + + list_for_each_entry_safe(entry, tmp, &ev_file->event_list, + list) { + list_del(&entry->list); + kfree(entry); + } + } + spin_unlock_irq(&ev_file->lock); wake_up_interruptible(&ev_file->poll_wait); @@ -2699,15 +2713,6 @@ static int devx_async_event_destroy_uobj(struct ib_uobject *uobj, } mutex_unlock(&dev->devx_event_table.event_xa_lock); - /* free the pending events allocation */ - if (!ev_file->omit_data) { - spin_lock_irq(&ev_file->lock); - list_for_each_entry_safe(entry, tmp, - &ev_file->event_list, list) - kfree(entry); /* read can't come any more */ - spin_unlock_irq(&ev_file->lock); - } - put_device(&dev->ib_dev.dev); return 0; }; diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index e874d688d040d69eac94c1d680d3f8eb81d422f1..e4bcfa81b70a3eedb003dceeb9634b0fbbf2bd6a 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -2283,8 +2283,8 @@ static int mlx5_ib_mmap_offset(struct mlx5_ib_dev *dev, static u64 mlx5_entry_to_mmap_offset(struct mlx5_user_mmap_entry *entry) { - u16 cmd = entry->rdma_entry.start_pgoff >> 16; - u16 index = entry->rdma_entry.start_pgoff & 0xFFFF; + u64 cmd = (entry->rdma_entry.start_pgoff >> 16) & 0xFFFF; + u64 index = entry->rdma_entry.start_pgoff & 0xFFFF; return (((index >> 8) << 16) | (cmd << MLX5_IB_MMAP_CMD_SHIFT) | (index & 0xFF)) << PAGE_SHIFT; @@ -6545,7 +6545,7 @@ static int mlx5_ib_init_var_table(struct mlx5_ib_dev *dev) doorbell_bar_offset); bar_size = (1ULL << log_doorbell_bar_size) * 4096; var_table->stride_size = 1ULL << log_doorbell_stride; - var_table->num_var_hw_entries = bar_size / var_table->stride_size; + var_table->num_var_hw_entries = div64_u64(bar_size, var_table->stride_size); mutex_init(&var_table->bitmap_lock); var_table->bitmap = bitmap_zalloc(var_table->num_var_hw_entries, GFP_KERNEL); diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index d9bffcc935875b00c5e1bebf51bac72a16a16845..bb78142bca5eaf8a137785d144520ed391a3bbf4 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -636,6 +636,7 @@ struct mlx5_ib_mr { /* For ODP and implicit */ atomic_t num_deferred_work; + wait_queue_head_t q_deferred_work; struct xarray implicit_children; union { struct rcu_head rcu; diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index 4216814ba871d2c20f8e634caf3ae99482e10fe9..bf50cd91f472586dfa711e0fa22fa5e5f80fe8cb 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -235,7 +235,8 @@ static void free_implicit_child_mr(struct mlx5_ib_mr *mr, bool need_imr_xlt) mr->parent = NULL; mlx5_mr_cache_free(mr->dev, mr); ib_umem_odp_release(odp); - atomic_dec(&imr->num_deferred_work); + if (atomic_dec_and_test(&imr->num_deferred_work)) + wake_up(&imr->q_deferred_work); } static void free_implicit_child_mr_work(struct work_struct *work) @@ -554,6 +555,7 @@ struct mlx5_ib_mr *mlx5_ib_alloc_implicit_mr(struct mlx5_ib_pd *pd, imr->umem = &umem_odp->umem; imr->is_odp_implicit = true; atomic_set(&imr->num_deferred_work, 0); + init_waitqueue_head(&imr->q_deferred_work); xa_init(&imr->implicit_children); err = mlx5_ib_update_xlt(imr, 0, @@ -611,10 +613,7 @@ void mlx5_ib_free_implicit_mr(struct mlx5_ib_mr *imr) * under xa_lock while the child is in the xarray. Thus at this point * it is only decreasing, and all work holding it is now on the wq. */ - if (atomic_read(&imr->num_deferred_work)) { - flush_workqueue(system_unbound_wq); - WARN_ON(atomic_read(&imr->num_deferred_work)); - } + wait_event(imr->q_deferred_work, !atomic_read(&imr->num_deferred_work)); /* * Fence the imr before we destroy the children. This allows us to @@ -645,10 +644,7 @@ void mlx5_ib_fence_odp_mr(struct mlx5_ib_mr *mr) /* Wait for all running page-fault handlers to finish. */ synchronize_srcu(&mr->dev->odp_srcu); - if (atomic_read(&mr->num_deferred_work)) { - flush_workqueue(system_unbound_wq); - WARN_ON(atomic_read(&mr->num_deferred_work)); - } + wait_event(mr->q_deferred_work, !atomic_read(&mr->num_deferred_work)); dma_fence_odp_mr(mr); } @@ -1720,7 +1716,8 @@ static void destroy_prefetch_work(struct prefetch_mr_work *work) u32 i; for (i = 0; i < work->num_sge; ++i) - atomic_dec(&work->frags[i].mr->num_deferred_work); + if (atomic_dec_and_test(&work->frags[i].mr->num_deferred_work)) + wake_up(&work->frags[i].mr->q_deferred_work); kvfree(work); } diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index a4f8e7030787184761ad57fa26452dbb69ee4b3f..957f3a52589bef9026fadcee8c5601fc6aa0c2d8 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -3441,9 +3441,6 @@ static int __mlx5_ib_qp_set_counter(struct ib_qp *qp, struct mlx5_ib_qp_base *base; u32 set_id; - if (!MLX5_CAP_GEN(dev->mdev, rts2rts_qp_counters_set_id)) - return 0; - if (counter) set_id = counter->id; else @@ -6576,6 +6573,7 @@ void mlx5_ib_drain_rq(struct ib_qp *qp) */ int mlx5_ib_qp_set_counter(struct ib_qp *qp, struct rdma_counter *counter) { + struct mlx5_ib_dev *dev = to_mdev(qp->device); struct mlx5_ib_qp *mqp = to_mqp(qp); int err = 0; @@ -6585,6 +6583,11 @@ int mlx5_ib_qp_set_counter(struct ib_qp *qp, struct rdma_counter *counter) goto out; } + if (!MLX5_CAP_GEN(dev->mdev, rts2rts_qp_counters_set_id)) { + err = -EOPNOTSUPP; + goto out; + } + if (mqp->state == IB_QPS_RTS) { err = __mlx5_ib_qp_set_counter(qp, counter); if (!err) diff --git a/drivers/infiniband/hw/qib/qib_verbs.c b/drivers/infiniband/hw/qib/qib_verbs.c index 33778d451b827f3b91a9025875f365e41587f499..5ef93f8f17a192733fdf0751e01cfb9fb7732387 100644 --- a/drivers/infiniband/hw/qib/qib_verbs.c +++ b/drivers/infiniband/hw/qib/qib_verbs.c @@ -329,8 +329,10 @@ void qib_ib_rcv(struct qib_ctxtdata *rcd, void *rhdr, void *data, u32 tlen) if (mcast == NULL) goto drop; this_cpu_inc(ibp->pmastats->n_multicast_rcv); + rcu_read_lock(); list_for_each_entry_rcu(p, &mcast->qp_list, list) qib_qp_rcv(rcd, hdr, 1, data, tlen, p->qp); + rcu_read_unlock(); /* * Notify rvt_multicast_detach() if it is waiting for us * to finish. diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index 3cdf75d0c7a4cf9a0a965087794dff4485373046..7858d499db03390cb73069b0e795b58478c12004 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -61,6 +61,8 @@ #define RVT_RWQ_COUNT_THRESHOLD 16 static void rvt_rc_timeout(struct timer_list *t); +static void rvt_reset_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp, + enum ib_qp_type type); /* * Convert the AETH RNR timeout code into the number of microseconds. @@ -452,40 +454,41 @@ int rvt_driver_qp_init(struct rvt_dev_info *rdi) } /** - * free_all_qps - check for QPs still in use + * rvt_free_qp_cb - callback function to reset a qp + * @qp: the qp to reset + * @v: a 64-bit value + * + * This function resets the qp and removes it from the + * qp hash table. + */ +static void rvt_free_qp_cb(struct rvt_qp *qp, u64 v) +{ + unsigned int *qp_inuse = (unsigned int *)v; + struct rvt_dev_info *rdi = ib_to_rvt(qp->ibqp.device); + + /* Reset the qp and remove it from the qp hash list */ + rvt_reset_qp(rdi, qp, qp->ibqp.qp_type); + + /* Increment the qp_inuse count */ + (*qp_inuse)++; +} + +/** + * rvt_free_all_qps - check for QPs still in use * @rdi: rvt device info structure * * There should not be any QPs still in use. * Free memory for table. + * Return the number of QPs still in use. */ static unsigned rvt_free_all_qps(struct rvt_dev_info *rdi) { - unsigned long flags; - struct rvt_qp *qp; - unsigned n, qp_inuse = 0; - spinlock_t *ql; /* work around too long line below */ - - if (rdi->driver_f.free_all_qps) - qp_inuse = rdi->driver_f.free_all_qps(rdi); + unsigned int qp_inuse = 0; qp_inuse += rvt_mcast_tree_empty(rdi); - if (!rdi->qp_dev) - return qp_inuse; - - ql = &rdi->qp_dev->qpt_lock; - spin_lock_irqsave(ql, flags); - for (n = 0; n < rdi->qp_dev->qp_table_size; n++) { - qp = rcu_dereference_protected(rdi->qp_dev->qp_table[n], - lockdep_is_held(ql)); - RCU_INIT_POINTER(rdi->qp_dev->qp_table[n], NULL); + rvt_qp_iter(rdi, (u64)&qp_inuse, rvt_free_qp_cb); - for (; qp; qp = rcu_dereference_protected(qp->next, - lockdep_is_held(ql))) - qp_inuse++; - } - spin_unlock_irqrestore(ql, flags); - synchronize_rcu(); return qp_inuse; } @@ -902,14 +905,14 @@ static void rvt_init_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp, } /** - * rvt_reset_qp - initialize the QP state to the reset state + * _rvt_reset_qp - initialize the QP state to the reset state * @qp: the QP to reset * @type: the QP type * * r_lock, s_hlock, and s_lock are required to be held by the caller */ -static void rvt_reset_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp, - enum ib_qp_type type) +static void _rvt_reset_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp, + enum ib_qp_type type) __must_hold(&qp->s_lock) __must_hold(&qp->s_hlock) __must_hold(&qp->r_lock) @@ -955,6 +958,27 @@ static void rvt_reset_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp, lockdep_assert_held(&qp->s_lock); } +/** + * rvt_reset_qp - initialize the QP state to the reset state + * @rdi: the device info + * @qp: the QP to reset + * @type: the QP type + * + * This is the wrapper function to acquire the r_lock, s_hlock, and s_lock + * before calling _rvt_reset_qp(). + */ +static void rvt_reset_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp, + enum ib_qp_type type) +{ + spin_lock_irq(&qp->r_lock); + spin_lock(&qp->s_hlock); + spin_lock(&qp->s_lock); + _rvt_reset_qp(rdi, qp, type); + spin_unlock(&qp->s_lock); + spin_unlock(&qp->s_hlock); + spin_unlock_irq(&qp->r_lock); +} + /** rvt_free_qpn - Free a qpn from the bit map * @qpt: QP table * @qpn: queue pair number to free @@ -1546,7 +1570,7 @@ int rvt_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, switch (new_state) { case IB_QPS_RESET: if (qp->state != IB_QPS_RESET) - rvt_reset_qp(rdi, qp, ibqp->qp_type); + _rvt_reset_qp(rdi, qp, ibqp->qp_type); break; case IB_QPS_RTR: @@ -1695,13 +1719,7 @@ int rvt_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) struct rvt_qp *qp = ibqp_to_rvtqp(ibqp); struct rvt_dev_info *rdi = ib_to_rvt(ibqp->device); - spin_lock_irq(&qp->r_lock); - spin_lock(&qp->s_hlock); - spin_lock(&qp->s_lock); rvt_reset_qp(rdi, qp, ibqp->qp_type); - spin_unlock(&qp->s_lock); - spin_unlock(&qp->s_hlock); - spin_unlock_irq(&qp->r_lock); wait_event(qp->wait, !atomic_read(&qp->refcount)); /* qpn is now available for use again */ diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c index 116cafc9afcf601a2a040831668947be785c49ed..4bc88708b355885b3f429e75af0dc3cb1975cd90 100644 --- a/drivers/infiniband/sw/rxe/rxe_comp.c +++ b/drivers/infiniband/sw/rxe/rxe_comp.c @@ -329,7 +329,7 @@ static inline enum comp_state check_ack(struct rxe_qp *qp, qp->comp.psn = pkt->psn; if (qp->req.wait_psn) { qp->req.wait_psn = 0; - rxe_run_task(&qp->req.task, 1); + rxe_run_task(&qp->req.task, 0); } } return COMPST_ERROR_RETRY; @@ -463,7 +463,7 @@ static void do_complete(struct rxe_qp *qp, struct rxe_send_wqe *wqe) */ if (qp->req.wait_fence) { qp->req.wait_fence = 0; - rxe_run_task(&qp->req.task, 1); + rxe_run_task(&qp->req.task, 0); } } @@ -479,7 +479,7 @@ static inline enum comp_state complete_ack(struct rxe_qp *qp, if (qp->req.need_rd_atomic) { qp->comp.timeout_retry = 0; qp->req.need_rd_atomic = 0; - rxe_run_task(&qp->req.task, 1); + rxe_run_task(&qp->req.task, 0); } } @@ -725,7 +725,7 @@ int rxe_completer(void *arg) RXE_CNT_COMP_RETRY); qp->req.need_retry = 1; qp->comp.started_retry = 1; - rxe_run_task(&qp->req.task, 1); + rxe_run_task(&qp->req.task, 0); } if (pkt) { diff --git a/drivers/infiniband/sw/siw/siw_cm.c b/drivers/infiniband/sw/siw/siw_cm.c index 0c3f0588346efa317e152c9496796fe999b552db..c5651a96b196480a4537cb81f46bf88a0664ddd0 100644 --- a/drivers/infiniband/sw/siw/siw_cm.c +++ b/drivers/infiniband/sw/siw/siw_cm.c @@ -1225,10 +1225,9 @@ static void siw_cm_llp_data_ready(struct sock *sk) read_lock(&sk->sk_callback_lock); cep = sk_to_cep(sk); - if (!cep) { - WARN_ON(1); + if (!cep) goto out; - } + siw_dbg_cep(cep, "state: %d\n", cep->state); switch (cep->state) { diff --git a/drivers/infiniband/sw/siw/siw_main.c b/drivers/infiniband/sw/siw/siw_main.c index 96ed349c093923060b3b348cb6ec08e9f34c43f7..5cd40fb9e20ce5eb0a667c9882928e58f4a1269a 100644 --- a/drivers/infiniband/sw/siw/siw_main.c +++ b/drivers/infiniband/sw/siw/siw_main.c @@ -388,6 +388,9 @@ static struct siw_device *siw_device_create(struct net_device *netdev) { .max_segment_size = SZ_2G }; base_dev->num_comp_vectors = num_possible_cpus(); + xa_init_flags(&sdev->qp_xa, XA_FLAGS_ALLOC1); + xa_init_flags(&sdev->mem_xa, XA_FLAGS_ALLOC1); + ib_set_device_ops(base_dev, &siw_device_ops); rv = ib_device_set_netdev(base_dev, netdev, 1); if (rv) @@ -415,9 +418,6 @@ static struct siw_device *siw_device_create(struct net_device *netdev) sdev->attrs.max_srq_wr = SIW_MAX_SRQ_WR; sdev->attrs.max_srq_sge = SIW_MAX_SGE; - xa_init_flags(&sdev->qp_xa, XA_FLAGS_ALLOC1); - xa_init_flags(&sdev->mem_xa, XA_FLAGS_ALLOC1); - INIT_LIST_HEAD(&sdev->cep_list); INIT_LIST_HEAD(&sdev->qp_list); diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index b273e421e9103f9a4aa7652bda41f6c08a9dc7b6..a1a035270cabf0b0dac14542b5f879514c7ce2e1 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -2575,6 +2575,17 @@ isert_wait4logout(struct isert_conn *isert_conn) } } +static void +isert_wait4cmds(struct iscsi_conn *conn) +{ + isert_info("iscsi_conn %p\n", conn); + + if (conn->sess) { + target_sess_cmd_list_set_waiting(conn->sess->se_sess); + target_wait_for_sess_cmds(conn->sess->se_sess); + } +} + /** * isert_put_unsol_pending_cmds() - Drop commands waiting for * unsolicitate dataout @@ -2622,6 +2633,7 @@ static void isert_wait_conn(struct iscsi_conn *conn) ib_drain_qp(isert_conn->qp); isert_put_unsol_pending_cmds(conn); + isert_wait4cmds(conn); isert_wait4logout(isert_conn); queue_work(isert_release_wq, &isert_conn->release_work); diff --git a/drivers/input/keyboard/goldfish_events.c b/drivers/input/keyboard/goldfish_events.c index bc8c85a52a10ce82f8be1695886af013013203ab..57d435fc5c73da8bfbf0db2773b8b0fe6a54fc3c 100644 --- a/drivers/input/keyboard/goldfish_events.c +++ b/drivers/input/keyboard/goldfish_events.c @@ -30,7 +30,7 @@ struct event_dev { struct input_dev *input; int irq; void __iomem *addr; - char name[0]; + char name[]; }; static irqreturn_t events_interrupt(int irq, void *dev_id) diff --git a/drivers/input/keyboard/gpio_keys.c b/drivers/input/keyboard/gpio_keys.c index 1f56d53454b22c0a6590b28cb89d47ab48d38a60..53c9ff338dea405076283bc6238109a76c0e618e 100644 --- a/drivers/input/keyboard/gpio_keys.c +++ b/drivers/input/keyboard/gpio_keys.c @@ -55,7 +55,7 @@ struct gpio_keys_drvdata { struct input_dev *input; struct mutex disable_lock; unsigned short *keymap; - struct gpio_button_data data[0]; + struct gpio_button_data data[]; }; /* diff --git a/drivers/input/keyboard/gpio_keys_polled.c b/drivers/input/keyboard/gpio_keys_polled.c index 6eb0a2f3f9de7954c33a89477537fd5b7281ce85..c3937d2fc7446e8b68e517cb4e5491809407fb06 100644 --- a/drivers/input/keyboard/gpio_keys_polled.c +++ b/drivers/input/keyboard/gpio_keys_polled.c @@ -38,7 +38,7 @@ struct gpio_keys_polled_dev { const struct gpio_keys_platform_data *pdata; unsigned long rel_axis_seen[BITS_TO_LONGS(REL_CNT)]; unsigned long abs_axis_seen[BITS_TO_LONGS(ABS_CNT)]; - struct gpio_keys_button_data data[0]; + struct gpio_keys_button_data data[]; }; static void gpio_keys_button_event(struct input_dev *input, diff --git a/drivers/input/keyboard/tca6416-keypad.c b/drivers/input/keyboard/tca6416-keypad.c index 2a14769de63705e4a01f36716061fe8eb320e144..21758767ccf063613a755f8f430f0f62c01acc88 100644 --- a/drivers/input/keyboard/tca6416-keypad.c +++ b/drivers/input/keyboard/tca6416-keypad.c @@ -33,7 +33,7 @@ MODULE_DEVICE_TABLE(i2c, tca6416_id); struct tca6416_drv_data { struct input_dev *input; - struct tca6416_button data[0]; + struct tca6416_button data[]; }; struct tca6416_keypad_chip { @@ -48,7 +48,7 @@ struct tca6416_keypad_chip { int irqnum; u16 pinmask; bool use_polling; - struct tca6416_button buttons[0]; + struct tca6416_button buttons[]; }; static int tca6416_write_reg(struct tca6416_keypad_chip *chip, int reg, u16 val) diff --git a/drivers/input/mouse/cyapa_gen5.c b/drivers/input/mouse/cyapa_gen5.c index 14239fbd72cf2032e193558dca87833ce4df4afd..7f012bfa26583d5133c59b76b788b62b30f69172 100644 --- a/drivers/input/mouse/cyapa_gen5.c +++ b/drivers/input/mouse/cyapa_gen5.c @@ -250,7 +250,7 @@ struct cyapa_tsg_bin_image_data_record { struct cyapa_tsg_bin_image { struct cyapa_tsg_bin_image_head image_head; - struct cyapa_tsg_bin_image_data_record records[0]; + struct cyapa_tsg_bin_image_data_record records[]; } __packed; struct pip_bl_packet_start { @@ -271,7 +271,7 @@ struct pip_bl_cmd_head { u8 report_id; /* Bootloader output report id, must be 40h */ u8 rsvd; /* Reserved, must be 0 */ struct pip_bl_packet_start packet_start; - u8 data[0]; /* Command data variable based on commands */ + u8 data[]; /* Command data variable based on commands */ } __packed; /* Initiate bootload command data structure. */ @@ -300,7 +300,7 @@ struct tsg_bl_metadata_row_params { struct tsg_bl_flash_row_head { u8 flash_array_id; __le16 flash_row_id; - u8 flash_data[0]; + u8 flash_data[]; } __packed; struct pip_app_cmd_head { @@ -314,7 +314,7 @@ struct pip_app_cmd_head { * Bit 6-0: command code. */ u8 cmd_code; - u8 parameter_data[0]; /* Parameter data variable based on cmd_code */ + u8 parameter_data[]; /* Parameter data variable based on cmd_code */ } __packed; /* Application get/set parameter command data structure */ diff --git a/drivers/input/mouse/psmouse-smbus.c b/drivers/input/mouse/psmouse-smbus.c index 027efdd2b2adfbcffce91f071744ddd990853eba..a472489ccbad6895524ecf5b701f47c819f9e20e 100644 --- a/drivers/input/mouse/psmouse-smbus.c +++ b/drivers/input/mouse/psmouse-smbus.c @@ -190,6 +190,7 @@ static int psmouse_smbus_create_companion(struct device *dev, void *data) struct psmouse_smbus_dev *smbdev = data; unsigned short addr_list[] = { smbdev->board.addr, I2C_CLIENT_END }; struct i2c_adapter *adapter; + struct i2c_client *client; adapter = i2c_verify_adapter(dev); if (!adapter) @@ -198,12 +199,13 @@ static int psmouse_smbus_create_companion(struct device *dev, void *data) if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_HOST_NOTIFY)) return 0; - smbdev->client = i2c_new_probed_device(adapter, &smbdev->board, - addr_list, NULL); - if (!smbdev->client) + client = i2c_new_scanned_device(adapter, &smbdev->board, + addr_list, NULL); + if (IS_ERR(client)) return 0; /* We have our(?) device, stop iterating i2c bus. */ + smbdev->client = client; return 1; } diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index 1ae6f8bba9ae15acc09f175ffb682a38a1ba19ba..2c666fb34625ad0df43a4b166e3e1b44e0fbe5d7 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -146,7 +146,6 @@ static const char * const topbuttonpad_pnp_ids[] = { "LEN0042", /* Yoga */ "LEN0045", "LEN0047", - "LEN0049", "LEN2000", /* S540 */ "LEN2001", /* Edge E431 */ "LEN2002", /* Edge E531 */ @@ -166,9 +165,11 @@ static const char * const smbus_pnp_ids[] = { /* all of the topbuttonpad_pnp_ids are valid, we just add some extras */ "LEN0048", /* X1 Carbon 3 */ "LEN0046", /* X250 */ + "LEN0049", /* Yoga 11e */ "LEN004a", /* W541 */ "LEN005b", /* P50 */ "LEN005e", /* T560 */ + "LEN006c", /* T470s */ "LEN0071", /* T480 */ "LEN0072", /* X1 Carbon Gen 5 (2017) - Elan/ALPS trackpoint */ "LEN0073", /* X1 Carbon G5 (Elantech) */ @@ -179,6 +180,7 @@ static const char * const smbus_pnp_ids[] = { "LEN0097", /* X280 -> ALPS trackpoint */ "LEN009b", /* T580 */ "LEN200f", /* T450s */ + "LEN2044", /* L470 */ "LEN2054", /* E480 */ "LEN2055", /* E580 */ "SYN3052", /* HP EliteBook 840 G4 */ diff --git a/drivers/input/touchscreen/ili210x.c b/drivers/input/touchscreen/ili210x.c index 4a17096e83e11679a26579148daba4cc17330d6b..199cf3daec10661d13e248cec654b3fddd3b4ae6 100644 --- a/drivers/input/touchscreen/ili210x.c +++ b/drivers/input/touchscreen/ili210x.c @@ -167,6 +167,36 @@ static const struct ili2xxx_chip ili211x_chip = { .resolution = 2048, }; +static bool ili212x_touchdata_to_coords(const u8 *touchdata, + unsigned int finger, + unsigned int *x, unsigned int *y) +{ + u16 val; + + val = get_unaligned_be16(touchdata + 3 + (finger * 5) + 0); + if (!(val & BIT(15))) /* Touch indication */ + return false; + + *x = val & 0x3fff; + *y = get_unaligned_be16(touchdata + 3 + (finger * 5) + 2); + + return true; +} + +static bool ili212x_check_continue_polling(const u8 *data, bool touch) +{ + return touch; +} + +static const struct ili2xxx_chip ili212x_chip = { + .read_reg = ili210x_read_reg, + .get_touch_data = ili210x_read_touch_data, + .parse_touch_data = ili212x_touchdata_to_coords, + .continue_polling = ili212x_check_continue_polling, + .max_touches = 10, + .has_calibrate_reg = true, +}; + static int ili251x_read_reg(struct i2c_client *client, u8 reg, void *buf, size_t len) { @@ -321,7 +351,7 @@ static umode_t ili210x_calibrate_visible(struct kobject *kobj, struct i2c_client *client = to_i2c_client(dev); struct ili210x *priv = i2c_get_clientdata(client); - return priv->chip->has_calibrate_reg; + return priv->chip->has_calibrate_reg ? attr->mode : 0; } static const struct attribute_group ili210x_attr_group = { @@ -447,6 +477,7 @@ static int ili210x_i2c_probe(struct i2c_client *client, static const struct i2c_device_id ili210x_i2c_id[] = { { "ili210x", (long)&ili210x_chip }, { "ili2117", (long)&ili211x_chip }, + { "ili2120", (long)&ili212x_chip }, { "ili251x", (long)&ili251x_chip }, { } }; @@ -455,6 +486,7 @@ MODULE_DEVICE_TABLE(i2c, ili210x_i2c_id); static const struct of_device_id ili210x_dt_ids[] = { { .compatible = "ilitek,ili210x", .data = &ili210x_chip }, { .compatible = "ilitek,ili2117", .data = &ili211x_chip }, + { .compatible = "ilitek,ili2120", .data = &ili212x_chip }, { .compatible = "ilitek,ili251x", .data = &ili251x_chip }, { } }; diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index f277e467156f759de71af874557be07dfaa3e25b..2c6515e3ecf13ee9dfad6af55037bbb9f4e9bd97 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -445,6 +445,11 @@ struct icc_path *of_icc_get(struct device *dev, const char *name) path->name = kasprintf(GFP_KERNEL, "%s-%s", src_node->name, dst_node->name); + if (!path->name) { + kfree(path); + return ERR_PTR(-ENOMEM); + } + return path; } EXPORT_SYMBOL_GPL(of_icc_get); @@ -579,6 +584,10 @@ struct icc_path *icc_get(struct device *dev, const int src_id, const int dst_id) } path->name = kasprintf(GFP_KERNEL, "%s-%s", src->name, dst->name); + if (!path->name) { + kfree(path); + path = ERR_PTR(-ENOMEM); + } out: mutex_unlock(&icc_lock); return path; diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile index 2104fb8afc0660c2516df9dd5a5d4b6c31d21b8b..9f33fdb3bb0516feb086741a2b4ac89a9e6331dc 100644 --- a/drivers/iommu/Makefile +++ b/drivers/iommu/Makefile @@ -14,8 +14,8 @@ obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o amd_iommu_quirks.o obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += amd_iommu_debugfs.o obj-$(CONFIG_AMD_IOMMU_V2) += amd_iommu_v2.o -obj-$(CONFIG_ARM_SMMU) += arm-smmu-mod.o -arm-smmu-mod-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-qcom.o +obj-$(CONFIG_ARM_SMMU) += arm_smmu.o +arm_smmu-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-qcom.o obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o obj-$(CONFIG_DMAR_TABLE) += dmar.o obj-$(CONFIG_INTEL_IOMMU) += intel-iommu.o intel-pasid.o diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index aac132bd1ef00101c385441ceca43115176d8bdd..20cce366e951813908aa2e7cb3cc8bcd474cf6c3 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -3826,7 +3826,7 @@ int amd_iommu_activate_guest_mode(void *data) entry->lo.fields_vapic.ga_tag = ir_data->ga_tag; return modify_irte_ga(ir_data->irq_2_irte.devid, - ir_data->irq_2_irte.index, entry, NULL); + ir_data->irq_2_irte.index, entry, ir_data); } EXPORT_SYMBOL(amd_iommu_activate_guest_mode); @@ -3852,7 +3852,7 @@ int amd_iommu_deactivate_guest_mode(void *data) APICID_TO_IRTE_DEST_HI(cfg->dest_apicid); return modify_irte_ga(ir_data->irq_2_irte.devid, - ir_data->irq_2_irte.index, entry, NULL); + ir_data->irq_2_irte.index, entry, ir_data); } EXPORT_SYMBOL(amd_iommu_deactivate_guest_mode); diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index 2759a8d57b7f91be441012c23c01bb6d6b408907..6be3853a5d978e09b8aeebb02daaec01e3a80cc9 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -2523,6 +2523,7 @@ static int __init early_amd_iommu_init(void) struct acpi_table_header *ivrs_base; acpi_status status; int i, remap_cache_sz, ret = 0; + u32 pci_id; if (!amd_iommu_detected) return -ENODEV; @@ -2610,6 +2611,16 @@ static int __init early_amd_iommu_init(void) if (ret) goto out; + /* Disable IOMMU if there's Stoney Ridge graphics */ + for (i = 0; i < 32; i++) { + pci_id = read_pci_config(0, i, 0, 0); + if ((pci_id & 0xffff) == 0x1002 && (pci_id >> 16) == 0x98e4) { + pr_info("Disable IOMMU on Stoney Ridge\n"); + amd_iommu_disabled = true; + break; + } + } + /* Disable any previously enabled IOMMUs */ if (!is_kdump_kernel() || amd_iommu_disabled) disable_iommus(); @@ -2718,7 +2729,7 @@ static int __init state_next(void) ret = early_amd_iommu_init(); init_state = ret ? IOMMU_INIT_ERROR : IOMMU_ACPI_FINISHED; if (init_state == IOMMU_ACPI_FINISHED && amd_iommu_disabled) { - pr_info("AMD IOMMU disabled on kernel command-line\n"); + pr_info("AMD IOMMU disabled\n"); init_state = IOMMU_CMDLINE_DISABLED; ret = -EINVAL; } diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index a2e96a5fd9a7b3a6d9e2bf35ea1a8d7bdc78f1f2..ba128d1cdaeeb15a5fcfae09e8c41544b2990883 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -177,15 +177,15 @@ static int cookie_init_hw_msi_region(struct iommu_dma_cookie *cookie, start -= iova_offset(iovad, start); num_pages = iova_align(iovad, end - start) >> iova_shift(iovad); - msi_page = kcalloc(num_pages, sizeof(*msi_page), GFP_KERNEL); - if (!msi_page) - return -ENOMEM; - for (i = 0; i < num_pages; i++) { - msi_page[i].phys = start; - msi_page[i].iova = start; - INIT_LIST_HEAD(&msi_page[i].list); - list_add(&msi_page[i].list, &cookie->msi_page_list); + msi_page = kmalloc(sizeof(*msi_page), GFP_KERNEL); + if (!msi_page) + return -ENOMEM; + + msi_page->phys = start; + msi_page->iova = start; + INIT_LIST_HEAD(&msi_page->list); + list_add(&msi_page->list, &cookie->msi_page_list); start += iovad->granule; } diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index 071bb42bbbc5bef6eba8584ec50ce24eeea06993..f77dae7ba7d4089f9fbf441b70a3e121f1dd7deb 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include @@ -128,6 +129,13 @@ dmar_alloc_pci_notify_info(struct pci_dev *dev, unsigned long event) BUG_ON(dev->is_virtfn); + /* + * Ignore devices that have a domain number higher than what can + * be looked up in DMAR, e.g. VMD subdevices with domain 0x10000 + */ + if (pci_domain_nr(dev->bus) > U16_MAX) + return NULL; + /* Only generate path[] for device addition event */ if (event == BUS_NOTIFY_ADD_DEVICE) for (tmp = dev; tmp; tmp = tmp->bus->self) @@ -363,7 +371,8 @@ dmar_find_dmaru(struct acpi_dmar_hardware_unit *drhd) { struct dmar_drhd_unit *dmaru; - list_for_each_entry_rcu(dmaru, &dmar_drhd_units, list) + list_for_each_entry_rcu(dmaru, &dmar_drhd_units, list, + dmar_rcu_check()) if (dmaru->segment == drhd->segment && dmaru->reg_base_addr == drhd->address) return dmaru; @@ -440,12 +449,13 @@ static int __init dmar_parse_one_andd(struct acpi_dmar_header *header, /* Check for NUL termination within the designated length */ if (strnlen(andd->device_name, header->length - 8) == header->length - 8) { - WARN_TAINT(1, TAINT_FIRMWARE_WORKAROUND, + pr_warn(FW_BUG "Your BIOS is broken; ANDD object name is not NUL-terminated\n" "BIOS vendor: %s; Ver: %s; Product Version: %s\n", dmi_get_system_info(DMI_BIOS_VENDOR), dmi_get_system_info(DMI_BIOS_VERSION), dmi_get_system_info(DMI_PRODUCT_VERSION)); + add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); return -EINVAL; } pr_info("ANDD device: %x name: %s\n", andd->device_number, @@ -471,14 +481,14 @@ static int dmar_parse_one_rhsa(struct acpi_dmar_header *header, void *arg) return 0; } } - WARN_TAINT( - 1, TAINT_FIRMWARE_WORKAROUND, + pr_warn(FW_BUG "Your BIOS is broken; RHSA refers to non-existent DMAR unit at %llx\n" "BIOS vendor: %s; Ver: %s; Product Version: %s\n", - drhd->reg_base_addr, + rhsa->base_address, dmi_get_system_info(DMI_BIOS_VENDOR), dmi_get_system_info(DMI_BIOS_VERSION), dmi_get_system_info(DMI_PRODUCT_VERSION)); + add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); return 0; } @@ -827,14 +837,14 @@ int __init dmar_table_init(void) static void warn_invalid_dmar(u64 addr, const char *message) { - WARN_TAINT_ONCE( - 1, TAINT_FIRMWARE_WORKAROUND, + pr_warn_once(FW_BUG "Your BIOS is broken; DMAR reported at address %llx%s!\n" "BIOS vendor: %s; Ver: %s; Product Version: %s\n", addr, message, dmi_get_system_info(DMI_BIOS_VENDOR), dmi_get_system_info(DMI_BIOS_VERSION), dmi_get_system_info(DMI_PRODUCT_VERSION)); + add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); } static int __ref diff --git a/drivers/iommu/intel-iommu-debugfs.c b/drivers/iommu/intel-iommu-debugfs.c index c1257bef553cef77881a54dd0372babe03b1544b..3eb1fe240fb00981471c3bc2b40a87d9ca81e4bc 100644 --- a/drivers/iommu/intel-iommu-debugfs.c +++ b/drivers/iommu/intel-iommu-debugfs.c @@ -33,38 +33,42 @@ struct iommu_regset { #define IOMMU_REGSET_ENTRY(_reg_) \ { DMAR_##_reg_##_REG, __stringify(_reg_) } -static const struct iommu_regset iommu_regs[] = { + +static const struct iommu_regset iommu_regs_32[] = { IOMMU_REGSET_ENTRY(VER), - IOMMU_REGSET_ENTRY(CAP), - IOMMU_REGSET_ENTRY(ECAP), IOMMU_REGSET_ENTRY(GCMD), IOMMU_REGSET_ENTRY(GSTS), - IOMMU_REGSET_ENTRY(RTADDR), - IOMMU_REGSET_ENTRY(CCMD), IOMMU_REGSET_ENTRY(FSTS), IOMMU_REGSET_ENTRY(FECTL), IOMMU_REGSET_ENTRY(FEDATA), IOMMU_REGSET_ENTRY(FEADDR), IOMMU_REGSET_ENTRY(FEUADDR), - IOMMU_REGSET_ENTRY(AFLOG), IOMMU_REGSET_ENTRY(PMEN), IOMMU_REGSET_ENTRY(PLMBASE), IOMMU_REGSET_ENTRY(PLMLIMIT), + IOMMU_REGSET_ENTRY(ICS), + IOMMU_REGSET_ENTRY(PRS), + IOMMU_REGSET_ENTRY(PECTL), + IOMMU_REGSET_ENTRY(PEDATA), + IOMMU_REGSET_ENTRY(PEADDR), + IOMMU_REGSET_ENTRY(PEUADDR), +}; + +static const struct iommu_regset iommu_regs_64[] = { + IOMMU_REGSET_ENTRY(CAP), + IOMMU_REGSET_ENTRY(ECAP), + IOMMU_REGSET_ENTRY(RTADDR), + IOMMU_REGSET_ENTRY(CCMD), + IOMMU_REGSET_ENTRY(AFLOG), IOMMU_REGSET_ENTRY(PHMBASE), IOMMU_REGSET_ENTRY(PHMLIMIT), IOMMU_REGSET_ENTRY(IQH), IOMMU_REGSET_ENTRY(IQT), IOMMU_REGSET_ENTRY(IQA), - IOMMU_REGSET_ENTRY(ICS), IOMMU_REGSET_ENTRY(IRTA), IOMMU_REGSET_ENTRY(PQH), IOMMU_REGSET_ENTRY(PQT), IOMMU_REGSET_ENTRY(PQA), - IOMMU_REGSET_ENTRY(PRS), - IOMMU_REGSET_ENTRY(PECTL), - IOMMU_REGSET_ENTRY(PEDATA), - IOMMU_REGSET_ENTRY(PEADDR), - IOMMU_REGSET_ENTRY(PEUADDR), IOMMU_REGSET_ENTRY(MTRRCAP), IOMMU_REGSET_ENTRY(MTRRDEF), IOMMU_REGSET_ENTRY(MTRR_FIX64K_00000), @@ -127,10 +131,16 @@ static int iommu_regset_show(struct seq_file *m, void *unused) * by adding the offset to the pointer (virtual address). */ raw_spin_lock_irqsave(&iommu->register_lock, flag); - for (i = 0 ; i < ARRAY_SIZE(iommu_regs); i++) { - value = dmar_readq(iommu->reg + iommu_regs[i].offset); + for (i = 0 ; i < ARRAY_SIZE(iommu_regs_32); i++) { + value = dmar_readl(iommu->reg + iommu_regs_32[i].offset); + seq_printf(m, "%-16s\t0x%02x\t\t0x%016llx\n", + iommu_regs_32[i].regs, iommu_regs_32[i].offset, + value); + } + for (i = 0 ; i < ARRAY_SIZE(iommu_regs_64); i++) { + value = dmar_readq(iommu->reg + iommu_regs_64[i].offset); seq_printf(m, "%-16s\t0x%02x\t\t0x%016llx\n", - iommu_regs[i].regs, iommu_regs[i].offset, + iommu_regs_64[i].regs, iommu_regs_64[i].offset, value); } raw_spin_unlock_irqrestore(&iommu->register_lock, flag); @@ -272,9 +282,16 @@ static int dmar_translation_struct_show(struct seq_file *m, void *unused) { struct dmar_drhd_unit *drhd; struct intel_iommu *iommu; + u32 sts; rcu_read_lock(); for_each_active_iommu(iommu, drhd) { + sts = dmar_readl(iommu->reg + DMAR_GSTS_REG); + if (!(sts & DMA_GSTS_TES)) { + seq_printf(m, "DMA Remapping is not enabled on %s\n", + iommu->name); + continue; + } root_tbl_walk(m, iommu); seq_putc(m, '\n'); } @@ -415,6 +432,7 @@ static int ir_translation_struct_show(struct seq_file *m, void *unused) struct dmar_drhd_unit *drhd; struct intel_iommu *iommu; u64 irta; + u32 sts; rcu_read_lock(); for_each_active_iommu(iommu, drhd) { @@ -424,7 +442,8 @@ static int ir_translation_struct_show(struct seq_file *m, void *unused) seq_printf(m, "Remapped Interrupt supported on IOMMU: %s\n", iommu->name); - if (iommu->ir_table) { + sts = dmar_readl(iommu->reg + DMAR_GSTS_REG); + if (iommu->ir_table && (sts & DMA_GSTS_IRES)) { irta = virt_to_phys(iommu->ir_table->base); seq_printf(m, " IR table address:%llx\n", irta); ir_tbl_remap_entry_show(m, iommu); diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 9dc37672bf893bb70808a9fdef0a850eba685f01..4be549478691884f75e148ed5e1bd23b84a23ac9 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -762,6 +762,11 @@ static int iommu_dummy(struct device *dev) return dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO; } +static bool attach_deferred(struct device *dev) +{ + return dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO; +} + /** * is_downstream_to_pci_bridge - test if a device belongs to the PCI * sub-hierarchy of a candidate PCI-PCI bridge @@ -2510,8 +2515,7 @@ struct dmar_domain *find_domain(struct device *dev) { struct device_domain_info *info; - if (unlikely(dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO || - dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO)) + if (unlikely(attach_deferred(dev) || iommu_dummy(dev))) return NULL; if (dev_is_pci(dev)) @@ -2525,18 +2529,14 @@ struct dmar_domain *find_domain(struct device *dev) return NULL; } -static struct dmar_domain *deferred_attach_domain(struct device *dev) +static void do_deferred_attach(struct device *dev) { - if (unlikely(dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO)) { - struct iommu_domain *domain; - - dev->archdata.iommu = NULL; - domain = iommu_get_domain_for_dev(dev); - if (domain) - intel_iommu_attach_device(domain, dev); - } + struct iommu_domain *domain; - return find_domain(dev); + dev->archdata.iommu = NULL; + domain = iommu_get_domain_for_dev(dev); + if (domain) + intel_iommu_attach_device(domain, dev); } static inline struct device_domain_info * @@ -2916,7 +2916,7 @@ static int identity_mapping(struct device *dev) struct device_domain_info *info; info = dev->archdata.iommu; - if (info && info != DUMMY_DEVICE_DOMAIN_INFO && info != DEFER_DEVICE_DOMAIN_INFO) + if (info) return (info->domain == si_domain); return 0; @@ -3587,6 +3587,9 @@ static bool iommu_need_mapping(struct device *dev) if (iommu_dummy(dev)) return false; + if (unlikely(attach_deferred(dev))) + do_deferred_attach(dev); + ret = identity_mapping(dev); if (ret) { u64 dma_mask = *dev->dma_mask; @@ -3635,7 +3638,7 @@ static dma_addr_t __intel_map_single(struct device *dev, phys_addr_t paddr, BUG_ON(dir == DMA_NONE); - domain = deferred_attach_domain(dev); + domain = find_domain(dev); if (!domain) return DMA_MAPPING_ERROR; @@ -3855,7 +3858,7 @@ static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nele if (!iommu_need_mapping(dev)) return dma_direct_map_sg(dev, sglist, nelems, dir, attrs); - domain = deferred_attach_domain(dev); + domain = find_domain(dev); if (!domain) return 0; @@ -3950,7 +3953,11 @@ bounce_map_single(struct device *dev, phys_addr_t paddr, size_t size, int prot = 0; int ret; - domain = deferred_attach_domain(dev); + if (unlikely(attach_deferred(dev))) + do_deferred_attach(dev); + + domain = find_domain(dev); + if (WARN_ON(dir == DMA_NONE || !domain)) return DMA_MAPPING_ERROR; @@ -4254,10 +4261,11 @@ static void quirk_ioat_snb_local_iommu(struct pci_dev *pdev) /* we know that the this iommu should be at offset 0xa000 from vtbar */ drhd = dmar_find_matched_drhd_unit(pdev); - if (WARN_TAINT_ONCE(!drhd || drhd->reg_base_addr - vtbar != 0xa000, - TAINT_FIRMWARE_WORKAROUND, - "BIOS assigned incorrect VT-d unit for Intel(R) QuickData Technology device\n")) + if (!drhd || drhd->reg_base_addr - vtbar != 0xa000) { + pr_warn_once(FW_BUG "BIOS assigned incorrect VT-d unit for Intel(R) QuickData Technology device\n"); + add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); pdev->dev.archdata.iommu = DUMMY_DEVICE_DOMAIN_INFO; + } } DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB, quirk_ioat_snb_local_iommu); @@ -4453,14 +4461,16 @@ int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg) struct dmar_rmrr_unit *rmrru; rmrr = (struct acpi_dmar_reserved_memory *)header; - if (rmrr_sanity_check(rmrr)) - WARN_TAINT(1, TAINT_FIRMWARE_WORKAROUND, + if (rmrr_sanity_check(rmrr)) { + pr_warn(FW_BUG "Your BIOS is broken; bad RMRR [%#018Lx-%#018Lx]\n" "BIOS vendor: %s; Ver: %s; Product Version: %s\n", rmrr->base_address, rmrr->end_address, dmi_get_system_info(DMI_BIOS_VENDOR), dmi_get_system_info(DMI_BIOS_VERSION), dmi_get_system_info(DMI_PRODUCT_VERSION)); + add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); + } rmrru = kzalloc(sizeof(*rmrru), GFP_KERNEL); if (!rmrru) @@ -5123,6 +5133,9 @@ int __init intel_iommu_init(void) down_write(&dmar_global_lock); + if (!no_iommu) + intel_iommu_debugfs_init(); + if (no_iommu || dmar_disabled) { /* * We exit the function here to ensure IOMMU's remapping and @@ -5186,6 +5199,7 @@ int __init intel_iommu_init(void) init_iommu_pm_ops(); + down_read(&dmar_global_lock); for_each_active_iommu(iommu, drhd) { iommu_device_sysfs_add(&iommu->iommu, NULL, intel_iommu_groups, @@ -5193,6 +5207,7 @@ int __init intel_iommu_init(void) iommu_device_set_ops(&iommu->iommu, &intel_iommu_ops); iommu_device_register(&iommu->iommu); } + up_read(&dmar_global_lock); bus_set_iommu(&pci_bus_type, &intel_iommu_ops); if (si_domain && !hw_pass_through) @@ -5203,7 +5218,6 @@ int __init intel_iommu_init(void) down_read(&dmar_global_lock); if (probe_acpi_namespace_devices()) pr_warn("ACPI name space devices didn't probe correctly\n"); - up_read(&dmar_global_lock); /* Finally, we enable the DMA remapping hardware. */ for_each_iommu(iommu, drhd) { @@ -5212,10 +5226,11 @@ int __init intel_iommu_init(void) iommu_disable_protect_mem_regions(iommu); } + up_read(&dmar_global_lock); + pr_info("Intel(R) Virtualization Technology for Directed I/O\n"); intel_iommu_enabled = 1; - intel_iommu_debugfs_init(); return 0; @@ -5693,8 +5708,10 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain, u64 phys = 0; pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level); - if (pte) - phys = dma_pte_addr(pte); + if (pte && dma_pte_present(pte)) + phys = dma_pte_addr(pte) + + (iova & (BIT_MASK(level_to_offset_bits(level) + + VTD_PAGE_SHIFT) - 1)); return phys; } @@ -6133,7 +6150,7 @@ intel_iommu_aux_get_pasid(struct iommu_domain *domain, struct device *dev) static bool intel_iommu_is_attach_deferred(struct iommu_domain *domain, struct device *dev) { - return dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO; + return attach_deferred(dev); } static int diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 983b08477e645902a6e477fa9adc3226b9143e13..04fbd4bf0ff9fd2140ff01a0063352eef047fb7f 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -468,7 +468,7 @@ static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova, arm_lpae_iopte *ptep = data->pgd; int ret, lvl = data->start_level; arm_lpae_iopte prot; - long iaext = (long)iova >> cfg->ias; + long iaext = (s64)iova >> cfg->ias; /* If no access, then nothing to do */ if (!(iommu_prot & (IOMMU_READ | IOMMU_WRITE))) @@ -645,7 +645,7 @@ static size_t arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova, struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops); struct io_pgtable_cfg *cfg = &data->iop.cfg; arm_lpae_iopte *ptep = data->pgd; - long iaext = (long)iova >> cfg->ias; + long iaext = (s64)iova >> cfg->ias; if (WARN_ON(!size || (size & cfg->pgsize_bitmap) != size)) return 0; diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c index 39759db4f0038c0ec7dd49928b75e6d89e5cae86..4328da0b0a9fdfa35b1d7f951b72e3599d195a31 100644 --- a/drivers/iommu/qcom_iommu.c +++ b/drivers/iommu/qcom_iommu.c @@ -344,21 +344,19 @@ static void qcom_iommu_domain_free(struct iommu_domain *domain) { struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain); - if (WARN_ON(qcom_domain->iommu)) /* forgot to detach? */ - return; - iommu_put_dma_cookie(domain); - /* NOTE: unmap can be called after client device is powered off, - * for example, with GPUs or anything involving dma-buf. So we - * cannot rely on the device_link. Make sure the IOMMU is on to - * avoid unclocked accesses in the TLB inv path: - */ - pm_runtime_get_sync(qcom_domain->iommu->dev); - - free_io_pgtable_ops(qcom_domain->pgtbl_ops); - - pm_runtime_put_sync(qcom_domain->iommu->dev); + if (qcom_domain->iommu) { + /* + * NOTE: unmap can be called after client device is powered + * off, for example, with GPUs or anything involving dma-buf. + * So we cannot rely on the device_link. Make sure the IOMMU + * is on to avoid unclocked accesses in the TLB inv path: + */ + pm_runtime_get_sync(qcom_domain->iommu->dev); + free_io_pgtable_ops(qcom_domain->pgtbl_ops); + pm_runtime_put_sync(qcom_domain->iommu->dev); + } kfree(qcom_domain); } @@ -404,7 +402,7 @@ static void qcom_iommu_detach_dev(struct iommu_domain *domain, struct device *de struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain); unsigned i; - if (!qcom_domain->iommu) + if (WARN_ON(!qcom_domain->iommu)) return; pm_runtime_get_sync(qcom_iommu->dev); @@ -417,8 +415,6 @@ static void qcom_iommu_detach_dev(struct iommu_domain *domain, struct device *de ctx->domain = NULL; } pm_runtime_put_sync(qcom_iommu->dev); - - qcom_domain->iommu = NULL; } static int qcom_iommu_map(struct iommu_domain *domain, unsigned long iova, diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index c1f7af9d9ae719a8b01cf7c84760ce6cd9781070..1eec9d4649d51ac5ae835cc8ae75377c6ca5db04 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -34,6 +34,7 @@ #define GICD_INT_NMI_PRI (GICD_INT_DEF_PRI & ~0x80) #define FLAGS_WORKAROUND_GICR_WAKER_MSM8996 (1ULL << 0) +#define FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539 (1ULL << 1) struct redist_region { void __iomem *redist_base; @@ -1464,6 +1465,15 @@ static bool gic_enable_quirk_msm8996(void *data) return true; } +static bool gic_enable_quirk_cavium_38539(void *data) +{ + struct gic_chip_data *d = data; + + d->flags |= FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539; + + return true; +} + static bool gic_enable_quirk_hip06_07(void *data) { struct gic_chip_data *d = data; @@ -1502,6 +1512,19 @@ static const struct gic_quirk gic_quirks[] = { .mask = 0xffffffff, .init = gic_enable_quirk_hip06_07, }, + { + /* + * Reserved register accesses generate a Synchronous + * External Abort. This erratum applies to: + * - ThunderX: CN88xx + * - OCTEON TX: CN83xx, CN81xx + * - OCTEON TX2: CN93xx, CN96xx, CN98xx, CNF95xx* + */ + .desc = "GICv3: Cavium erratum 38539", + .iidr = 0xa000034c, + .mask = 0xe8f00fff, + .init = gic_enable_quirk_cavium_38539, + }, { } }; @@ -1577,7 +1600,12 @@ static int __init gic_init_bases(void __iomem *dist_base, pr_info("%d SPIs implemented\n", GIC_LINE_NR - 32); pr_info("%d Extended SPIs implemented\n", GIC_ESPI_NR); - gic_data.rdists.gicd_typer2 = readl_relaxed(gic_data.dist_base + GICD_TYPER2); + /* + * ThunderX1 explodes on reading GICD_TYPER2, in violation of the + * architecture spec (which says that reserved registers are RES0). + */ + if (!(gic_data.flags & FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539)) + gic_data.rdists.gicd_typer2 = readl_relaxed(gic_data.dist_base + GICD_TYPER2); gic_data.domain = irq_domain_create_tree(handle, &gic_irq_domain_ops, &gic_data); diff --git a/drivers/macintosh/therm_windtunnel.c b/drivers/macintosh/therm_windtunnel.c index 8c744578122a3e229079571b7bce093380c90662..a0d87ed9da69612224903eb192da987e3d5f5504 100644 --- a/drivers/macintosh/therm_windtunnel.c +++ b/drivers/macintosh/therm_windtunnel.c @@ -300,9 +300,11 @@ static int control_loop(void *dummy) /* i2c probing and setup */ /************************************************************************/ -static int -do_attach( struct i2c_adapter *adapter ) +static void do_attach(struct i2c_adapter *adapter) { + struct i2c_board_info info = { }; + struct device_node *np; + /* scan 0x48-0x4f (DS1775) and 0x2c-2x2f (ADM1030) */ static const unsigned short scan_ds1775[] = { 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, @@ -313,25 +315,24 @@ do_attach( struct i2c_adapter *adapter ) I2C_CLIENT_END }; - if( strncmp(adapter->name, "uni-n", 5) ) - return 0; - - if( !x.running ) { - struct i2c_board_info info; + if (x.running || strncmp(adapter->name, "uni-n", 5)) + return; - memset(&info, 0, sizeof(struct i2c_board_info)); - strlcpy(info.type, "therm_ds1775", I2C_NAME_SIZE); + np = of_find_compatible_node(adapter->dev.of_node, NULL, "MAC,ds1775"); + if (np) { + of_node_put(np); + } else { + strlcpy(info.type, "MAC,ds1775", I2C_NAME_SIZE); i2c_new_probed_device(adapter, &info, scan_ds1775, NULL); + } - strlcpy(info.type, "therm_adm1030", I2C_NAME_SIZE); + np = of_find_compatible_node(adapter->dev.of_node, NULL, "MAC,adm1030"); + if (np) { + of_node_put(np); + } else { + strlcpy(info.type, "MAC,adm1030", I2C_NAME_SIZE); i2c_new_probed_device(adapter, &info, scan_adm1030, NULL); - - if( x.thermostat && x.fan ) { - x.running = 1; - x.poll_task = kthread_run(control_loop, NULL, "g4fand"); - } } - return 0; } static int @@ -404,8 +405,8 @@ attach_thermostat( struct i2c_client *cl ) enum chip { ds1775, adm1030 }; static const struct i2c_device_id therm_windtunnel_id[] = { - { "therm_ds1775", ds1775 }, - { "therm_adm1030", adm1030 }, + { "MAC,ds1775", ds1775 }, + { "MAC,adm1030", adm1030 }, { } }; MODULE_DEVICE_TABLE(i2c, therm_windtunnel_id); @@ -414,6 +415,7 @@ static int do_probe(struct i2c_client *cl, const struct i2c_device_id *id) { struct i2c_adapter *adapter = cl->adapter; + int ret = 0; if( !i2c_check_functionality(adapter, I2C_FUNC_SMBUS_WORD_DATA | I2C_FUNC_SMBUS_WRITE_BYTE) ) @@ -421,11 +423,19 @@ do_probe(struct i2c_client *cl, const struct i2c_device_id *id) switch (id->driver_data) { case adm1030: - return attach_fan( cl ); + ret = attach_fan(cl); + break; case ds1775: - return attach_thermostat(cl); + ret = attach_thermostat(cl); + break; } - return 0; + + if (!x.running && x.thermostat && x.fan) { + x.running = 1; + x.poll_task = kthread_run(control_loop, NULL, "g4fand"); + } + + return ret; } static struct i2c_driver g4fan_driver = { diff --git a/drivers/macintosh/windfarm_ad7417_sensor.c b/drivers/macintosh/windfarm_ad7417_sensor.c index 125605987b443b6f123070de71d4b72679f298c3..e7dec328c7cfdffeede1bf04b701ac9bca899301 100644 --- a/drivers/macintosh/windfarm_ad7417_sensor.c +++ b/drivers/macintosh/windfarm_ad7417_sensor.c @@ -312,9 +312,16 @@ static const struct i2c_device_id wf_ad7417_id[] = { }; MODULE_DEVICE_TABLE(i2c, wf_ad7417_id); +static const struct of_device_id wf_ad7417_of_id[] = { + { .compatible = "ad7417", }, + { } +}; +MODULE_DEVICE_TABLE(of, wf_ad7417_of_id); + static struct i2c_driver wf_ad7417_driver = { .driver = { .name = "wf_ad7417", + .of_match_table = wf_ad7417_of_id, }, .probe = wf_ad7417_probe, .remove = wf_ad7417_remove, diff --git a/drivers/macintosh/windfarm_fcu_controls.c b/drivers/macintosh/windfarm_fcu_controls.c index 67daeec94b44a06eca49905c7ed86c979c779e52..2470e5a725c812f5342cdf40fd88aab61a5ca414 100644 --- a/drivers/macintosh/windfarm_fcu_controls.c +++ b/drivers/macintosh/windfarm_fcu_controls.c @@ -580,9 +580,16 @@ static const struct i2c_device_id wf_fcu_id[] = { }; MODULE_DEVICE_TABLE(i2c, wf_fcu_id); +static const struct of_device_id wf_fcu_of_id[] = { + { .compatible = "fcu", }, + { } +}; +MODULE_DEVICE_TABLE(of, wf_fcu_of_id); + static struct i2c_driver wf_fcu_driver = { .driver = { .name = "wf_fcu", + .of_match_table = wf_fcu_of_id, }, .probe = wf_fcu_probe, .remove = wf_fcu_remove, diff --git a/drivers/macintosh/windfarm_lm75_sensor.c b/drivers/macintosh/windfarm_lm75_sensor.c index 282c28a17ea1ae936dd7b9bdafd61f344fa3ef7c..1e5fa09845e77be5efb2f06ca8836fb7214cf032 100644 --- a/drivers/macintosh/windfarm_lm75_sensor.c +++ b/drivers/macintosh/windfarm_lm75_sensor.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -91,9 +92,14 @@ static int wf_lm75_probe(struct i2c_client *client, const struct i2c_device_id *id) { struct wf_lm75_sensor *lm; - int rc, ds1775 = id->driver_data; + int rc, ds1775; const char *name, *loc; + if (id) + ds1775 = id->driver_data; + else + ds1775 = !!of_device_get_match_data(&client->dev); + DBG("wf_lm75: creating %s device at address 0x%02x\n", ds1775 ? "ds1775" : "lm75", client->addr); @@ -164,9 +170,17 @@ static const struct i2c_device_id wf_lm75_id[] = { }; MODULE_DEVICE_TABLE(i2c, wf_lm75_id); +static const struct of_device_id wf_lm75_of_id[] = { + { .compatible = "lm75", .data = (void *)0}, + { .compatible = "ds1775", .data = (void *)1 }, + { } +}; +MODULE_DEVICE_TABLE(of, wf_lm75_of_id); + static struct i2c_driver wf_lm75_driver = { .driver = { .name = "wf_lm75", + .of_match_table = wf_lm75_of_id, }, .probe = wf_lm75_probe, .remove = wf_lm75_remove, diff --git a/drivers/macintosh/windfarm_lm87_sensor.c b/drivers/macintosh/windfarm_lm87_sensor.c index b03a33b803b793c110a911c11610d8b98c0e4880..d011899c0a8a1fb14f51b211407a75963bcd1d68 100644 --- a/drivers/macintosh/windfarm_lm87_sensor.c +++ b/drivers/macintosh/windfarm_lm87_sensor.c @@ -166,9 +166,16 @@ static const struct i2c_device_id wf_lm87_id[] = { }; MODULE_DEVICE_TABLE(i2c, wf_lm87_id); +static const struct of_device_id wf_lm87_of_id[] = { + { .compatible = "lm87cimt", }, + { } +}; +MODULE_DEVICE_TABLE(of, wf_lm87_of_id); + static struct i2c_driver wf_lm87_driver = { .driver = { .name = "wf_lm87", + .of_match_table = wf_lm87_of_id, }, .probe = wf_lm87_probe, .remove = wf_lm87_remove, diff --git a/drivers/macintosh/windfarm_max6690_sensor.c b/drivers/macintosh/windfarm_max6690_sensor.c index e666cc02068387723c86f237cf60939ba8ac71f7..1e7b03d44ad975413a8086f12a5ff0b95d339d90 100644 --- a/drivers/macintosh/windfarm_max6690_sensor.c +++ b/drivers/macintosh/windfarm_max6690_sensor.c @@ -120,9 +120,16 @@ static const struct i2c_device_id wf_max6690_id[] = { }; MODULE_DEVICE_TABLE(i2c, wf_max6690_id); +static const struct of_device_id wf_max6690_of_id[] = { + { .compatible = "max6690", }, + { } +}; +MODULE_DEVICE_TABLE(of, wf_max6690_of_id); + static struct i2c_driver wf_max6690_driver = { .driver = { .name = "wf_max6690", + .of_match_table = wf_max6690_of_id, }, .probe = wf_max6690_probe, .remove = wf_max6690_remove, diff --git a/drivers/macintosh/windfarm_smu_sat.c b/drivers/macintosh/windfarm_smu_sat.c index c84ec49c37415c90366de89b70633e079f5e30ac..cb75dc03561670c2864ca4054355f5db1e0043ec 100644 --- a/drivers/macintosh/windfarm_smu_sat.c +++ b/drivers/macintosh/windfarm_smu_sat.c @@ -341,9 +341,16 @@ static const struct i2c_device_id wf_sat_id[] = { }; MODULE_DEVICE_TABLE(i2c, wf_sat_id); +static const struct of_device_id wf_sat_of_id[] = { + { .compatible = "smu-sat", }, + { } +}; +MODULE_DEVICE_TABLE(of, wf_sat_of_id); + static struct i2c_driver wf_sat_driver = { .driver = { .name = "wf_smu_sat", + .of_match_table = wf_sat_of_id, }, .probe = wf_sat_probe, .remove = wf_sat_remove, diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c index 6730820780b067c918e15e63ee9086c3c8cbd008..0e3ff9745ac742d5fb72bdcda46ae227dd37ee62 100644 --- a/drivers/md/bcache/journal.c +++ b/drivers/md/bcache/journal.c @@ -417,8 +417,6 @@ int bch_journal_replay(struct cache_set *s, struct list_head *list) /* Journalling */ -#define nr_to_fifo_front(p, front_p, mask) (((p) - (front_p)) & (mask)) - static void btree_flush_write(struct cache_set *c) { struct btree *b, *t, *btree_nodes[BTREE_FLUSH_NR]; @@ -510,9 +508,8 @@ static void btree_flush_write(struct cache_set *c) * journal entry can be reclaimed). These selected nodes * will be ignored and skipped in the folowing for-loop. */ - if (nr_to_fifo_front(btree_current_write(b)->journal, - fifo_front_p, - mask) != 0) { + if (((btree_current_write(b)->journal - fifo_front_p) & + mask) != 0) { mutex_unlock(&b->write_lock); continue; } diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 2749daf0972425b0186d05ebae5239641feed3d8..0c3c5419c52b67a0fafd743ed4e509a330a2dabb 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1917,23 +1917,6 @@ static int run_cache_set(struct cache_set *c) if (bch_btree_check(c)) goto err; - /* - * bch_btree_check() may occupy too much system memory which - * has negative effects to user space application (e.g. data - * base) performance. Shrink the mca cache memory proactively - * here to avoid competing memory with user space workloads.. - */ - if (!c->shrinker_disabled) { - struct shrink_control sc; - - sc.gfp_mask = GFP_KERNEL; - sc.nr_to_scan = c->btree_cache_used * c->btree_pages; - /* first run to clear b->accessed tag */ - c->shrink.scan_objects(&c->shrink, &sc); - /* second run to reap non-accessed nodes */ - c->shrink.scan_objects(&c->shrink, &sc); - } - bch_journal_mark(c, &journal); bch_initial_gc_finish(c); pr_debug("btree_check() done"); diff --git a/drivers/md/dm-bio-record.h b/drivers/md/dm-bio-record.h index c82578af56a5bbff035a272f258327a7fce6ecfd..2ea0360108e1d41b57a39b5c5df715c52a641442 100644 --- a/drivers/md/dm-bio-record.h +++ b/drivers/md/dm-bio-record.h @@ -20,8 +20,13 @@ struct dm_bio_details { struct gendisk *bi_disk; u8 bi_partno; + int __bi_remaining; unsigned long bi_flags; struct bvec_iter bi_iter; + bio_end_io_t *bi_end_io; +#if defined(CONFIG_BLK_DEV_INTEGRITY) + struct bio_integrity_payload *bi_integrity; +#endif }; static inline void dm_bio_record(struct dm_bio_details *bd, struct bio *bio) @@ -30,6 +35,11 @@ static inline void dm_bio_record(struct dm_bio_details *bd, struct bio *bio) bd->bi_partno = bio->bi_partno; bd->bi_flags = bio->bi_flags; bd->bi_iter = bio->bi_iter; + bd->__bi_remaining = atomic_read(&bio->__bi_remaining); + bd->bi_end_io = bio->bi_end_io; +#if defined(CONFIG_BLK_DEV_INTEGRITY) + bd->bi_integrity = bio_integrity(bio); +#endif } static inline void dm_bio_restore(struct dm_bio_details *bd, struct bio *bio) @@ -38,6 +48,11 @@ static inline void dm_bio_restore(struct dm_bio_details *bd, struct bio *bio) bio->bi_partno = bd->bi_partno; bio->bi_flags = bd->bi_flags; bio->bi_iter = bd->bi_iter; + atomic_set(&bio->__bi_remaining, bd->__bi_remaining); + bio->bi_end_io = bd->bi_end_io; +#if defined(CONFIG_BLK_DEV_INTEGRITY) + bio->bi_integrity = bd->bi_integrity; +#endif } #endif diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 2d32821b3a5b8fdac87c54a7778b635fd62f8c7d..d3bb355819a421fbdda41cb5880321d248d29699 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -2846,8 +2846,8 @@ static void cache_postsuspend(struct dm_target *ti) prevent_background_work(cache); BUG_ON(atomic_read(&cache->nr_io_migrations)); - cancel_delayed_work(&cache->waker); - flush_workqueue(cache->wq); + cancel_delayed_work_sync(&cache->waker); + drain_workqueue(cache->wq); WARN_ON(cache->tracker.in_flight); /* @@ -3492,7 +3492,7 @@ static void cache_io_hints(struct dm_target *ti, struct queue_limits *limits) static struct target_type cache_target = { .name = "cache", - .version = {2, 1, 0}, + .version = {2, 2, 0}, .module = THIS_MODULE, .ctr = cache_ctr, .dtr = cache_dtr, diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index b225b3e445fa43aa57c51828f7f6bea09351fb0c..2f03fecd312d8b4c8995c7fe275a6d5fac76045b 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -6,6 +6,8 @@ * This file is released under the GPL. */ +#include "dm-bio-record.h" + #include #include #include @@ -201,17 +203,19 @@ struct dm_integrity_c { __u8 log2_blocks_per_bitmap_bit; unsigned char mode; - int suspending; int failed; struct crypto_shash *internal_hash; + struct dm_target *ti; + /* these variables are locked with endio_wait.lock */ struct rb_root in_progress; struct list_head wait_list; wait_queue_head_t endio_wait; struct workqueue_struct *wait_wq; + struct workqueue_struct *offload_wq; unsigned char commit_seq; commit_id_t commit_ids[N_COMMIT_IDS]; @@ -293,11 +297,7 @@ struct dm_integrity_io { struct completion *completion; - struct gendisk *orig_bi_disk; - u8 orig_bi_partno; - bio_end_io_t *orig_bi_end_io; - struct bio_integrity_payload *orig_bi_integrity; - struct bvec_iter orig_bi_iter; + struct dm_bio_details bio_details; }; struct journal_completion { @@ -1439,7 +1439,7 @@ static void dec_in_flight(struct dm_integrity_io *dio) dio->range.logical_sector += dio->range.n_sectors; bio_advance(bio, dio->range.n_sectors << SECTOR_SHIFT); INIT_WORK(&dio->work, integrity_bio_wait); - queue_work(ic->wait_wq, &dio->work); + queue_work(ic->offload_wq, &dio->work); return; } do_endio_flush(ic, dio); @@ -1450,14 +1450,9 @@ static void integrity_end_io(struct bio *bio) { struct dm_integrity_io *dio = dm_per_bio_data(bio, sizeof(struct dm_integrity_io)); - bio->bi_iter = dio->orig_bi_iter; - bio->bi_disk = dio->orig_bi_disk; - bio->bi_partno = dio->orig_bi_partno; - if (dio->orig_bi_integrity) { - bio->bi_integrity = dio->orig_bi_integrity; + dm_bio_restore(&dio->bio_details, bio); + if (bio->bi_integrity) bio->bi_opf |= REQ_INTEGRITY; - } - bio->bi_end_io = dio->orig_bi_end_io; if (dio->completion) complete(dio->completion); @@ -1542,7 +1537,7 @@ static void integrity_metadata(struct work_struct *w) } } - __bio_for_each_segment(bv, bio, iter, dio->orig_bi_iter) { + __bio_for_each_segment(bv, bio, iter, dio->bio_details.bi_iter) { unsigned pos; char *mem, *checksums_ptr; @@ -1586,7 +1581,7 @@ static void integrity_metadata(struct work_struct *w) if (likely(checksums != checksums_onstack)) kfree(checksums); } else { - struct bio_integrity_payload *bip = dio->orig_bi_integrity; + struct bio_integrity_payload *bip = dio->bio_details.bi_integrity; if (bip) { struct bio_vec biv; @@ -1865,7 +1860,7 @@ static void dm_integrity_map_continue(struct dm_integrity_io *dio, bool from_map if (need_sync_io && from_map) { INIT_WORK(&dio->work, integrity_bio_wait); - queue_work(ic->metadata_wq, &dio->work); + queue_work(ic->offload_wq, &dio->work); return; } @@ -2005,20 +2000,13 @@ static void dm_integrity_map_continue(struct dm_integrity_io *dio, bool from_map } else dio->completion = NULL; - dio->orig_bi_iter = bio->bi_iter; - - dio->orig_bi_disk = bio->bi_disk; - dio->orig_bi_partno = bio->bi_partno; + dm_bio_record(&dio->bio_details, bio); bio_set_dev(bio, ic->dev->bdev); - - dio->orig_bi_integrity = bio_integrity(bio); bio->bi_integrity = NULL; bio->bi_opf &= ~REQ_INTEGRITY; - - dio->orig_bi_end_io = bio->bi_end_io; bio->bi_end_io = integrity_end_io; - bio->bi_iter.bi_size = dio->range.n_sectors << SECTOR_SHIFT; + generic_make_request(bio); if (need_sync_io) { @@ -2315,7 +2303,7 @@ static void integrity_writer(struct work_struct *w) unsigned prev_free_sectors; /* the following test is not needed, but it tests the replay code */ - if (READ_ONCE(ic->suspending) && !ic->meta_dev) + if (unlikely(dm_suspended(ic->ti)) && !ic->meta_dev) return; spin_lock_irq(&ic->endio_wait.lock); @@ -2376,7 +2364,7 @@ static void integrity_recalc(struct work_struct *w) next_chunk: - if (unlikely(READ_ONCE(ic->suspending))) + if (unlikely(dm_suspended(ic->ti))) goto unlock_ret; range.logical_sector = le64_to_cpu(ic->sb->recalc_sector); @@ -2501,7 +2489,7 @@ static void bitmap_block_work(struct work_struct *w) dio->range.n_sectors, BITMAP_OP_TEST_ALL_SET)) { remove_range(ic, &dio->range); INIT_WORK(&dio->work, integrity_bio_wait); - queue_work(ic->wait_wq, &dio->work); + queue_work(ic->offload_wq, &dio->work); } else { block_bitmap_op(ic, ic->journal, dio->range.logical_sector, dio->range.n_sectors, BITMAP_OP_SET); @@ -2524,7 +2512,7 @@ static void bitmap_block_work(struct work_struct *w) remove_range(ic, &dio->range); INIT_WORK(&dio->work, integrity_bio_wait); - queue_work(ic->wait_wq, &dio->work); + queue_work(ic->offload_wq, &dio->work); } queue_delayed_work(ic->commit_wq, &ic->bitmap_flush_work, ic->bitmap_flush_interval); @@ -2804,8 +2792,6 @@ static void dm_integrity_postsuspend(struct dm_target *ti) del_timer_sync(&ic->autocommit_timer); - WRITE_ONCE(ic->suspending, 1); - if (ic->recalc_wq) drain_workqueue(ic->recalc_wq); @@ -2834,8 +2820,6 @@ static void dm_integrity_postsuspend(struct dm_target *ti) #endif } - WRITE_ONCE(ic->suspending, 0); - BUG_ON(!RB_EMPTY_ROOT(&ic->in_progress)); ic->journal_uptodate = true; @@ -2888,17 +2872,24 @@ static void dm_integrity_resume(struct dm_target *ti) } else { replay_journal(ic); if (ic->mode == 'B') { - int mode; ic->sb->flags |= cpu_to_le32(SB_FLAG_DIRTY_BITMAP); ic->sb->log2_blocks_per_bitmap_bit = ic->log2_blocks_per_bitmap_bit; r = sync_rw_sb(ic, REQ_OP_WRITE, REQ_FUA); if (unlikely(r)) dm_integrity_io_error(ic, "writing superblock", r); - mode = ic->recalculate_flag ? BITMAP_OP_SET : BITMAP_OP_CLEAR; - block_bitmap_op(ic, ic->journal, 0, ic->provided_data_sectors, mode); - block_bitmap_op(ic, ic->recalc_bitmap, 0, ic->provided_data_sectors, mode); - block_bitmap_op(ic, ic->may_write_bitmap, 0, ic->provided_data_sectors, mode); + block_bitmap_op(ic, ic->journal, 0, ic->provided_data_sectors, BITMAP_OP_CLEAR); + block_bitmap_op(ic, ic->recalc_bitmap, 0, ic->provided_data_sectors, BITMAP_OP_CLEAR); + block_bitmap_op(ic, ic->may_write_bitmap, 0, ic->provided_data_sectors, BITMAP_OP_CLEAR); + if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING) && + le64_to_cpu(ic->sb->recalc_sector) < ic->provided_data_sectors) { + block_bitmap_op(ic, ic->journal, le64_to_cpu(ic->sb->recalc_sector), + ic->provided_data_sectors - le64_to_cpu(ic->sb->recalc_sector), BITMAP_OP_SET); + block_bitmap_op(ic, ic->recalc_bitmap, le64_to_cpu(ic->sb->recalc_sector), + ic->provided_data_sectors - le64_to_cpu(ic->sb->recalc_sector), BITMAP_OP_SET); + block_bitmap_op(ic, ic->may_write_bitmap, le64_to_cpu(ic->sb->recalc_sector), + ic->provided_data_sectors - le64_to_cpu(ic->sb->recalc_sector), BITMAP_OP_SET); + } rw_journal_sectors(ic, REQ_OP_WRITE, REQ_FUA | REQ_SYNC, 0, ic->n_bitmap_blocks * (BITMAP_BLOCK_SIZE >> SECTOR_SHIFT), NULL); } @@ -2967,7 +2958,7 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type, DMEMIT(" meta_device:%s", ic->meta_dev->name); if (ic->sectors_per_block != 1) DMEMIT(" block_size:%u", ic->sectors_per_block << SECTOR_SHIFT); - if (ic->recalculate_flag) + if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING)) DMEMIT(" recalculate"); DMEMIT(" journal_sectors:%u", ic->initial_sectors - SB_SECTORS); DMEMIT(" interleave_sectors:%u", 1U << ic->sb->log2_interleave_sectors); @@ -3623,6 +3614,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv) } ti->private = ic; ti->per_io_data_size = sizeof(struct dm_integrity_io); + ic->ti = ti; ic->in_progress = RB_ROOT; INIT_LIST_HEAD(&ic->wait_list); @@ -3836,6 +3828,14 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv) goto bad; } + ic->offload_wq = alloc_workqueue("dm-integrity-offload", WQ_MEM_RECLAIM, + METADATA_WORKQUEUE_MAX_ACTIVE); + if (!ic->offload_wq) { + ti->error = "Cannot allocate workqueue"; + r = -ENOMEM; + goto bad; + } + ic->commit_wq = alloc_workqueue("dm-integrity-commit", WQ_MEM_RECLAIM, 1); if (!ic->commit_wq) { ti->error = "Cannot allocate workqueue"; @@ -4140,6 +4140,8 @@ static void dm_integrity_dtr(struct dm_target *ti) destroy_workqueue(ic->metadata_wq); if (ic->wait_wq) destroy_workqueue(ic->wait_wq); + if (ic->offload_wq) + destroy_workqueue(ic->offload_wq); if (ic->commit_wq) destroy_workqueue(ic->commit_wq); if (ic->writer_wq) @@ -4200,7 +4202,7 @@ static void dm_integrity_dtr(struct dm_target *ti) static struct target_type integrity_target = { .name = "integrity", - .version = {1, 4, 0}, + .version = {1, 5, 0}, .module = THIS_MODULE, .features = DM_TARGET_SINGLETON | DM_TARGET_INTEGRITY, .ctr = dm_integrity_ctr, diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 2bc18c9c3abcfc60e0763976704c878aea7fd13f..58fd137b6ae1a041c8503a62bef175a27a70ff16 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -2053,7 +2053,7 @@ static int multipath_busy(struct dm_target *ti) *---------------------------------------------------------------*/ static struct target_type multipath_target = { .name = "multipath", - .version = {1, 13, 0}, + .version = {1, 14, 0}, .features = DM_TARGET_SINGLETON | DM_TARGET_IMMUTABLE | DM_TARGET_PASSES_INTEGRITY, .module = THIS_MODULE, diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index fc9947d6210c202273d2c44a3198e88429530e76..76b6b323bf4bd560f1b83eead235ffcaf373ad86 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -960,9 +960,9 @@ int dm_pool_metadata_close(struct dm_pool_metadata *pmd) DMWARN("%s: __commit_transaction() failed, error = %d", __func__, r); } + pmd_write_unlock(pmd); if (!pmd->fail_io) __destroy_persistent_data_objects(pmd); - pmd_write_unlock(pmd); kfree(pmd); return 0; diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 0d61e9c6798650bc46bc34aa98b29564fe21d9c9..eec9f252e9354bd8746e3f647ff1b1e8eb610aef 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -1221,7 +1221,7 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) static struct target_type verity_target = { .name = "verity", - .version = {1, 5, 0}, + .version = {1, 6, 0}, .module = THIS_MODULE, .ctr = verity_ctr, .dtr = verity_dtr, diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index b9e27e37a94373c1cbc8ca52f3b64c0d72d46228..a09bdc000e6462738be71b70686d2a0d67ab3009 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -625,6 +625,12 @@ static void writecache_add_to_freelist(struct dm_writecache *wc, struct wc_entry wc->freelist_size++; } +static inline void writecache_verify_watermark(struct dm_writecache *wc) +{ + if (unlikely(wc->freelist_size + wc->writeback_size <= wc->freelist_high_watermark)) + queue_work(wc->writeback_wq, &wc->writeback_work); +} + static struct wc_entry *writecache_pop_from_freelist(struct dm_writecache *wc, sector_t expected_sector) { struct wc_entry *e; @@ -650,8 +656,8 @@ static struct wc_entry *writecache_pop_from_freelist(struct dm_writecache *wc, s list_del(&e->lru); } wc->freelist_size--; - if (unlikely(wc->freelist_size + wc->writeback_size <= wc->freelist_high_watermark)) - queue_work(wc->writeback_wq, &wc->writeback_work); + + writecache_verify_watermark(wc); return e; } @@ -842,7 +848,7 @@ static void writecache_suspend(struct dm_target *ti) } wc_unlock(wc); - flush_workqueue(wc->writeback_wq); + drain_workqueue(wc->writeback_wq); wc_lock(wc); if (flush_on_suspend) @@ -965,6 +971,8 @@ static void writecache_resume(struct dm_target *ti) writecache_commit_flushed(wc, false); } + writecache_verify_watermark(wc); + wc_unlock(wc); } @@ -2312,7 +2320,7 @@ static void writecache_status(struct dm_target *ti, status_type_t type, static struct target_type writecache_target = { .name = "writecache", - .version = {1, 1, 1}, + .version = {1, 2, 0}, .module = THIS_MODULE, .ctr = writecache_ctr, .dtr = writecache_dtr, diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index 70a1063161c04aef304eb3e008c0842f0ccf5e62..f4f83d39b3dcf03d2736fa762ded17160e0e56a2 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -533,8 +533,9 @@ static int dmz_queue_chunk_work(struct dmz_target *dmz, struct bio *bio) /* Get the BIO chunk work. If one is not active yet, create one */ cw = radix_tree_lookup(&dmz->chunk_rxtree, chunk); - if (!cw) { - + if (cw) { + dmz_get_chunk_work(cw); + } else { /* Create a new chunk work */ cw = kmalloc(sizeof(struct dm_chunk_work), GFP_NOIO); if (unlikely(!cw)) { @@ -543,7 +544,7 @@ static int dmz_queue_chunk_work(struct dmz_target *dmz, struct bio *bio) } INIT_WORK(&cw->work, dmz_chunk_work); - refcount_set(&cw->refcount, 0); + refcount_set(&cw->refcount, 1); cw->target = dmz; cw->chunk = chunk; bio_list_init(&cw->bio_list); @@ -556,7 +557,6 @@ static int dmz_queue_chunk_work(struct dmz_target *dmz, struct bio *bio) } bio_list_add(&cw->bio_list, bio); - dmz_get_chunk_work(cw); dmz_reclaim_bio_acc(dmz->reclaim); if (queue_work(dmz->chunk_wq, &cw->work)) @@ -967,7 +967,7 @@ static int dmz_iterate_devices(struct dm_target *ti, static struct target_type dmz_type = { .name = "zoned", - .version = {1, 0, 0}, + .version = {1, 1, 0}, .features = DM_TARGET_SINGLETON | DM_TARGET_ZONED_HM, .module = THIS_MODULE, .ctr = dmz_ctr, diff --git a/drivers/md/dm.c b/drivers/md/dm.c index b89f07ee2efff2c19207f2b820011af901e3a3cb..0413018c83058f0907795484064e4373d8775215 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1788,7 +1788,8 @@ static int dm_any_congested(void *congested_data, int bdi_bits) * With request-based DM we only need to check the * top-level queue for congestion. */ - r = md->queue->backing_dev_info->wb.state & bdi_bits; + struct backing_dev_info *bdi = md->queue->backing_dev_info; + r = bdi->wb.congested->state & bdi_bits; } else { map = dm_get_live_table_fast(md); if (map) @@ -1854,15 +1855,6 @@ static const struct dax_operations dm_dax_ops; static void dm_wq_work(struct work_struct *work); -static void dm_init_normal_md_queue(struct mapped_device *md) -{ - /* - * Initialize aspects of queue that aren't relevant for blk-mq - */ - md->queue->backing_dev_info->congested_data = md; - md->queue->backing_dev_info->congested_fn = dm_any_congested; -} - static void cleanup_mapped_device(struct mapped_device *md) { if (md->wq) @@ -2249,6 +2241,12 @@ struct queue_limits *dm_get_queue_limits(struct mapped_device *md) } EXPORT_SYMBOL_GPL(dm_get_queue_limits); +static void dm_init_congested_fn(struct mapped_device *md) +{ + md->queue->backing_dev_info->congested_data = md; + md->queue->backing_dev_info->congested_fn = dm_any_congested; +} + /* * Setup the DM device's queue based on md's type */ @@ -2265,11 +2263,12 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t) DMERR("Cannot initialize queue for request-based dm-mq mapped device"); return r; } + dm_init_congested_fn(md); break; case DM_TYPE_BIO_BASED: case DM_TYPE_DAX_BIO_BASED: case DM_TYPE_NVME_BIO_BASED: - dm_init_normal_md_queue(md); + dm_init_congested_fn(md); break; case DM_TYPE_NONE: WARN_ON_ONCE(true); @@ -2368,6 +2367,7 @@ static void __dm_destroy(struct mapped_device *md, bool wait) map = dm_get_live_table(md, &srcu_idx); if (!dm_suspended_md(md)) { dm_table_presuspend_targets(map); + set_bit(DMF_SUSPENDED, &md->flags); dm_table_postsuspend_targets(map); } /* dm_put_live_table must be before msleep, otherwise deadlock is possible */ diff --git a/drivers/media/mc/mc-entity.c b/drivers/media/mc/mc-entity.c index 7c429ce98bae66424c7e70a36e3c29166fa17fba..668770e9f609000ffb15c834a059a14ea1750d51 100644 --- a/drivers/media/mc/mc-entity.c +++ b/drivers/media/mc/mc-entity.c @@ -639,9 +639,9 @@ int media_get_pad_index(struct media_entity *entity, bool is_sink, return -EINVAL; for (i = 0; i < entity->num_pads; i++) { - if (entity->pads[i].flags == MEDIA_PAD_FL_SINK) + if (entity->pads[i].flags & MEDIA_PAD_FL_SINK) pad_is_sink = true; - else if (entity->pads[i].flags == MEDIA_PAD_FL_SOURCE) + else if (entity->pads[i].flags & MEDIA_PAD_FL_SOURCE) pad_is_sink = false; else continue; /* This is an error! */ diff --git a/drivers/media/platform/vicodec/codec-v4l2-fwht.c b/drivers/media/platform/vicodec/codec-v4l2-fwht.c index 3c93d9232c3cf55e3bc52ae5284b8abd79fd4baa..b6e39fbd8ad5dd081381e481a9ab054e0e7da441 100644 --- a/drivers/media/platform/vicodec/codec-v4l2-fwht.c +++ b/drivers/media/platform/vicodec/codec-v4l2-fwht.c @@ -27,17 +27,17 @@ static const struct v4l2_fwht_pixfmt_info v4l2_fwht_pixfmts[] = { { V4L2_PIX_FMT_BGR24, 3, 3, 1, 3, 3, 1, 1, 3, 1, FWHT_FL_PIXENC_RGB}, { V4L2_PIX_FMT_RGB24, 3, 3, 1, 3, 3, 1, 1, 3, 1, FWHT_FL_PIXENC_RGB}, { V4L2_PIX_FMT_HSV24, 3, 3, 1, 3, 3, 1, 1, 3, 1, FWHT_FL_PIXENC_HSV}, - { V4L2_PIX_FMT_BGR32, 4, 4, 1, 4, 4, 1, 1, 3, 1, FWHT_FL_PIXENC_RGB}, - { V4L2_PIX_FMT_XBGR32, 4, 4, 1, 4, 4, 1, 1, 3, 1, FWHT_FL_PIXENC_RGB}, + { V4L2_PIX_FMT_BGR32, 4, 4, 1, 4, 4, 1, 1, 4, 1, FWHT_FL_PIXENC_RGB}, + { V4L2_PIX_FMT_XBGR32, 4, 4, 1, 4, 4, 1, 1, 4, 1, FWHT_FL_PIXENC_RGB}, { V4L2_PIX_FMT_ABGR32, 4, 4, 1, 4, 4, 1, 1, 4, 1, FWHT_FL_PIXENC_RGB}, - { V4L2_PIX_FMT_RGB32, 4, 4, 1, 4, 4, 1, 1, 3, 1, FWHT_FL_PIXENC_RGB}, - { V4L2_PIX_FMT_XRGB32, 4, 4, 1, 4, 4, 1, 1, 3, 1, FWHT_FL_PIXENC_RGB}, + { V4L2_PIX_FMT_RGB32, 4, 4, 1, 4, 4, 1, 1, 4, 1, FWHT_FL_PIXENC_RGB}, + { V4L2_PIX_FMT_XRGB32, 4, 4, 1, 4, 4, 1, 1, 4, 1, FWHT_FL_PIXENC_RGB}, { V4L2_PIX_FMT_ARGB32, 4, 4, 1, 4, 4, 1, 1, 4, 1, FWHT_FL_PIXENC_RGB}, - { V4L2_PIX_FMT_BGRX32, 4, 4, 1, 4, 4, 1, 1, 3, 1, FWHT_FL_PIXENC_RGB}, + { V4L2_PIX_FMT_BGRX32, 4, 4, 1, 4, 4, 1, 1, 4, 1, FWHT_FL_PIXENC_RGB}, { V4L2_PIX_FMT_BGRA32, 4, 4, 1, 4, 4, 1, 1, 4, 1, FWHT_FL_PIXENC_RGB}, - { V4L2_PIX_FMT_RGBX32, 4, 4, 1, 4, 4, 1, 1, 3, 1, FWHT_FL_PIXENC_RGB}, + { V4L2_PIX_FMT_RGBX32, 4, 4, 1, 4, 4, 1, 1, 4, 1, FWHT_FL_PIXENC_RGB}, { V4L2_PIX_FMT_RGBA32, 4, 4, 1, 4, 4, 1, 1, 4, 1, FWHT_FL_PIXENC_RGB}, - { V4L2_PIX_FMT_HSV32, 4, 4, 1, 4, 4, 1, 1, 3, 1, FWHT_FL_PIXENC_HSV}, + { V4L2_PIX_FMT_HSV32, 4, 4, 1, 4, 4, 1, 1, 4, 1, FWHT_FL_PIXENC_HSV}, { V4L2_PIX_FMT_GREY, 1, 1, 1, 1, 0, 1, 1, 1, 1, FWHT_FL_PIXENC_RGB}, }; @@ -175,22 +175,14 @@ static int prepare_raw_frame(struct fwht_raw_frame *rf, case V4L2_PIX_FMT_RGB32: case V4L2_PIX_FMT_XRGB32: case V4L2_PIX_FMT_HSV32: - rf->cr = rf->luma + 1; - rf->cb = rf->cr + 2; - rf->luma += 2; - break; - case V4L2_PIX_FMT_BGR32: - case V4L2_PIX_FMT_XBGR32: - rf->cb = rf->luma; - rf->cr = rf->cb + 2; - rf->luma++; - break; case V4L2_PIX_FMT_ARGB32: rf->alpha = rf->luma; rf->cr = rf->luma + 1; rf->cb = rf->cr + 2; rf->luma += 2; break; + case V4L2_PIX_FMT_BGR32: + case V4L2_PIX_FMT_XBGR32: case V4L2_PIX_FMT_ABGR32: rf->cb = rf->luma; rf->cr = rf->cb + 2; @@ -198,10 +190,6 @@ static int prepare_raw_frame(struct fwht_raw_frame *rf, rf->alpha = rf->cr + 1; break; case V4L2_PIX_FMT_BGRX32: - rf->cb = rf->luma + 1; - rf->cr = rf->cb + 2; - rf->luma += 2; - break; case V4L2_PIX_FMT_BGRA32: rf->alpha = rf->luma; rf->cb = rf->luma + 1; @@ -209,10 +197,6 @@ static int prepare_raw_frame(struct fwht_raw_frame *rf, rf->luma += 2; break; case V4L2_PIX_FMT_RGBX32: - rf->cr = rf->luma; - rf->cb = rf->cr + 2; - rf->luma++; - break; case V4L2_PIX_FMT_RGBA32: rf->alpha = rf->luma + 3; rf->cr = rf->luma; diff --git a/drivers/media/usb/pulse8-cec/pulse8-cec.c b/drivers/media/usb/pulse8-cec/pulse8-cec.c index afda438d4e0ac5c81e66ebc5626960538918d53f..0655aa9ecf283a6a73231d12413300a4f7a4c3fa 100644 --- a/drivers/media/usb/pulse8-cec/pulse8-cec.c +++ b/drivers/media/usb/pulse8-cec/pulse8-cec.c @@ -635,8 +635,6 @@ static void pulse8_cec_adap_free(struct cec_adapter *adap) cancel_delayed_work_sync(&pulse8->ping_eeprom_work); cancel_work_sync(&pulse8->irq_work); cancel_work_sync(&pulse8->tx_work); - serio_close(pulse8->serio); - serio_set_drvdata(pulse8->serio, NULL); kfree(pulse8); } @@ -652,6 +650,9 @@ static void pulse8_disconnect(struct serio *serio) struct pulse8 *pulse8 = serio_get_drvdata(serio); cec_unregister_adapter(pulse8->adap); + pulse8->serio = NULL; + serio_set_drvdata(serio, NULL); + serio_close(serio); } static int pulse8_setup(struct pulse8 *pulse8, struct serio *serio, @@ -840,6 +841,8 @@ static int pulse8_connect(struct serio *serio, struct serio_driver *drv) serio_set_drvdata(serio, pulse8); INIT_WORK(&pulse8->irq_work, pulse8_irq_work_handler); INIT_WORK(&pulse8->tx_work, pulse8_tx_work_handler); + INIT_DELAYED_WORK(&pulse8->ping_eeprom_work, + pulse8_ping_eeprom_work_handler); mutex_init(&pulse8->lock); spin_lock_init(&pulse8->msg_lock); pulse8->config_pending = false; @@ -865,17 +868,16 @@ static int pulse8_connect(struct serio *serio, struct serio_driver *drv) pulse8->restoring_config = true; } - INIT_DELAYED_WORK(&pulse8->ping_eeprom_work, - pulse8_ping_eeprom_work_handler); schedule_delayed_work(&pulse8->ping_eeprom_work, PING_PERIOD); return 0; close_serio: + pulse8->serio = NULL; + serio_set_drvdata(serio, NULL); serio_close(serio); delete_adap: cec_delete_adapter(pulse8->adap); - serio_set_drvdata(serio, NULL); free_device: kfree(pulse8); return err; diff --git a/drivers/media/v4l2-core/v4l2-mem2mem.c b/drivers/media/v4l2-core/v4l2-mem2mem.c index 1afd9c6ad90848d78c3969f9ce1ad0063858062e..cc34c5ab70099b13968d9c1806fcc29c26ca4993 100644 --- a/drivers/media/v4l2-core/v4l2-mem2mem.c +++ b/drivers/media/v4l2-core/v4l2-mem2mem.c @@ -880,12 +880,12 @@ int v4l2_m2m_register_media_controller(struct v4l2_m2m_dev *m2m_dev, goto err_rel_entity1; /* Connect the three entities */ - ret = media_create_pad_link(m2m_dev->source, 0, &m2m_dev->proc, 1, + ret = media_create_pad_link(m2m_dev->source, 0, &m2m_dev->proc, 0, MEDIA_LNK_FL_IMMUTABLE | MEDIA_LNK_FL_ENABLED); if (ret) goto err_rel_entity2; - ret = media_create_pad_link(&m2m_dev->proc, 0, &m2m_dev->sink, 0, + ret = media_create_pad_link(&m2m_dev->proc, 1, &m2m_dev->sink, 0, MEDIA_LNK_FL_IMMUTABLE | MEDIA_LNK_FL_ENABLED); if (ret) goto err_rm_links0; diff --git a/drivers/misc/altera-stapl/altera.c b/drivers/misc/altera-stapl/altera.c index 25e5f24b3fecd9ee227cec50ae8029716fc80398..5bdf574723144c8952e6b2cd0e83207e8b5ac45e 100644 --- a/drivers/misc/altera-stapl/altera.c +++ b/drivers/misc/altera-stapl/altera.c @@ -2112,8 +2112,8 @@ static int altera_execute(struct altera_state *astate, return status; } -static int altera_get_note(u8 *p, s32 program_size, - s32 *offset, char *key, char *value, int length) +static int altera_get_note(u8 *p, s32 program_size, s32 *offset, + char *key, char *value, int keylen, int vallen) /* * Gets key and value of NOTE fields in the JBC file. * Can be called in two modes: if offset pointer is NULL, @@ -2170,7 +2170,7 @@ static int altera_get_note(u8 *p, s32 program_size, &p[note_table + (8 * i) + 4])]; if (value != NULL) - strlcpy(value, value_ptr, length); + strlcpy(value, value_ptr, vallen); } } @@ -2189,13 +2189,13 @@ static int altera_get_note(u8 *p, s32 program_size, strlcpy(key, &p[note_strings + get_unaligned_be32( &p[note_table + (8 * i)])], - length); + keylen); if (value != NULL) strlcpy(value, &p[note_strings + get_unaligned_be32( &p[note_table + (8 * i) + 4])], - length); + vallen); *offset = i + 1; } @@ -2449,7 +2449,7 @@ int altera_init(struct altera_config *config, const struct firmware *fw) __func__, (format_version == 2) ? "Jam STAPL" : "pre-standardized Jam 1.1"); while (altera_get_note((u8 *)fw->data, fw->size, - &offset, key, value, 256) == 0) + &offset, key, value, 32, 256) == 0) printk(KERN_INFO "%s: NOTE \"%s\" = \"%s\"\n", __func__, key, value); } diff --git a/drivers/misc/cardreader/rts5227.c b/drivers/misc/cardreader/rts5227.c index 4feed296a32767abee716e8f520af073cd67e59b..423fecc19fc4a65a83ac844cfc9bcbfa419b613e 100644 --- a/drivers/misc/cardreader/rts5227.c +++ b/drivers/misc/cardreader/rts5227.c @@ -394,7 +394,7 @@ static const struct pcr_ops rts522a_pcr_ops = { void rts522a_init_params(struct rtsx_pcr *pcr) { rts5227_init_params(pcr); - + pcr->tx_initial_phase = SET_CLOCK_PHASE(20, 20, 11); pcr->reg_pm_ctrl3 = RTS522A_PM_CTRL3; pcr->option.ocp_en = 1; diff --git a/drivers/misc/cardreader/rts5249.c b/drivers/misc/cardreader/rts5249.c index db936e4d6e5638d5c6fd016d2e05da07261e367b..1a81cda948c1e39c106ab6f6b44a24bfd784fd57 100644 --- a/drivers/misc/cardreader/rts5249.c +++ b/drivers/misc/cardreader/rts5249.c @@ -618,6 +618,7 @@ static const struct pcr_ops rts524a_pcr_ops = { void rts524a_init_params(struct rtsx_pcr *pcr) { rts5249_init_params(pcr); + pcr->tx_initial_phase = SET_CLOCK_PHASE(27, 29, 11); pcr->option.ltr_l1off_sspwrgate = LTR_L1OFF_SSPWRGATE_5250_DEF; pcr->option.ltr_l1off_snooze_sspwrgate = LTR_L1OFF_SNOOZE_SSPWRGATE_5250_DEF; @@ -733,6 +734,7 @@ static const struct pcr_ops rts525a_pcr_ops = { void rts525a_init_params(struct rtsx_pcr *pcr) { rts5249_init_params(pcr); + pcr->tx_initial_phase = SET_CLOCK_PHASE(25, 29, 11); pcr->option.ltr_l1off_sspwrgate = LTR_L1OFF_SSPWRGATE_5250_DEF; pcr->option.ltr_l1off_snooze_sspwrgate = LTR_L1OFF_SNOOZE_SSPWRGATE_5250_DEF; diff --git a/drivers/misc/cardreader/rts5260.c b/drivers/misc/cardreader/rts5260.c index 4214f02a17fdc53314b402e35730a3e7102eeb97..711054ebad74e7078b952b90e40000f7e7250125 100644 --- a/drivers/misc/cardreader/rts5260.c +++ b/drivers/misc/cardreader/rts5260.c @@ -662,7 +662,7 @@ void rts5260_init_params(struct rtsx_pcr *pcr) pcr->sd30_drive_sel_1v8 = CFG_DRIVER_TYPE_B; pcr->sd30_drive_sel_3v3 = CFG_DRIVER_TYPE_B; pcr->aspm_en = ASPM_L1_EN; - pcr->tx_initial_phase = SET_CLOCK_PHASE(1, 29, 16); + pcr->tx_initial_phase = SET_CLOCK_PHASE(27, 29, 11); pcr->rx_initial_phase = SET_CLOCK_PHASE(24, 6, 5); pcr->ic_version = rts5260_get_ic_version(pcr); diff --git a/drivers/misc/cardreader/rts5261.c b/drivers/misc/cardreader/rts5261.c index bc4967a6efa1fed7561d25071c2f7691e92d1ea4..78c3b1d424c3c16fbdd9d3c59a7b1fb80a6e6d08 100644 --- a/drivers/misc/cardreader/rts5261.c +++ b/drivers/misc/cardreader/rts5261.c @@ -764,7 +764,7 @@ void rts5261_init_params(struct rtsx_pcr *pcr) pcr->sd30_drive_sel_1v8 = CFG_DRIVER_TYPE_B; pcr->sd30_drive_sel_3v3 = CFG_DRIVER_TYPE_B; pcr->aspm_en = ASPM_L1_EN; - pcr->tx_initial_phase = SET_CLOCK_PHASE(20, 27, 16); + pcr->tx_initial_phase = SET_CLOCK_PHASE(27, 27, 11); pcr->rx_initial_phase = SET_CLOCK_PHASE(24, 6, 5); pcr->ic_version = rts5261_get_ic_version(pcr); diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c index 031eb64549af51018eefda562f43a67a0d07e85d..282c9ef68ed22dfe73c58f11916fff9c44582228 100644 --- a/drivers/misc/eeprom/at24.c +++ b/drivers/misc/eeprom/at24.c @@ -712,13 +712,14 @@ static int at24_probe(struct i2c_client *client) * chip is functional. */ err = at24_read(at24, 0, &test_byte, 1); - pm_runtime_idle(dev); if (err) { pm_runtime_disable(dev); regulator_disable(at24->vcc_reg); return -ENODEV; } + pm_runtime_idle(dev); + if (writable) dev_info(dev, "%u byte %s EEPROM, writable, %u bytes/write\n", byte_len, client->name, at24->write_max); diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c index b155e95490761271262d46c4c46adface12c561a..b680b0caa69be91ab423391ea58e47724351e561 100644 --- a/drivers/misc/habanalabs/device.c +++ b/drivers/misc/habanalabs/device.c @@ -598,7 +598,9 @@ int hl_device_set_debug_mode(struct hl_device *hdev, bool enable) goto out; } - hdev->asic_funcs->halt_coresight(hdev); + if (!hdev->hard_reset_pending) + hdev->asic_funcs->halt_coresight(hdev); + hdev->in_debug = 0; goto out; @@ -1189,6 +1191,7 @@ int hl_device_init(struct hl_device *hdev, struct class *hclass) if (hdev->asic_funcs->get_hw_state(hdev) == HL_DEVICE_HW_STATE_DIRTY) { dev_info(hdev->dev, "H/W state is dirty, must reset before initializing\n"); + hdev->asic_funcs->halt_engines(hdev, true); hdev->asic_funcs->hw_fini(hdev, true); } diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 7344e8a222ae567fd3f525c242ce49a1750fe3ff..b8a8de24aaf722a3c2f4abee4f4720b616c9761b 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -895,6 +895,11 @@ void goya_init_dma_qmans(struct hl_device *hdev) */ static void goya_disable_external_queues(struct hl_device *hdev) { + struct goya_device *goya = hdev->asic_specific; + + if (!(goya->hw_cap_initialized & HW_CAP_DMA)) + return; + WREG32(mmDMA_QM_0_GLBL_CFG0, 0); WREG32(mmDMA_QM_1_GLBL_CFG0, 0); WREG32(mmDMA_QM_2_GLBL_CFG0, 0); @@ -956,6 +961,11 @@ static int goya_stop_external_queues(struct hl_device *hdev) { int rc, retval = 0; + struct goya_device *goya = hdev->asic_specific; + + if (!(goya->hw_cap_initialized & HW_CAP_DMA)) + return retval; + rc = goya_stop_queue(hdev, mmDMA_QM_0_GLBL_CFG1, mmDMA_QM_0_CP_STS, @@ -1744,9 +1754,18 @@ void goya_init_tpc_qmans(struct hl_device *hdev) */ static void goya_disable_internal_queues(struct hl_device *hdev) { + struct goya_device *goya = hdev->asic_specific; + + if (!(goya->hw_cap_initialized & HW_CAP_MME)) + goto disable_tpc; + WREG32(mmMME_QM_GLBL_CFG0, 0); WREG32(mmMME_CMDQ_GLBL_CFG0, 0); +disable_tpc: + if (!(goya->hw_cap_initialized & HW_CAP_TPC)) + return; + WREG32(mmTPC0_QM_GLBL_CFG0, 0); WREG32(mmTPC0_CMDQ_GLBL_CFG0, 0); @@ -1782,8 +1801,12 @@ static void goya_disable_internal_queues(struct hl_device *hdev) */ static int goya_stop_internal_queues(struct hl_device *hdev) { + struct goya_device *goya = hdev->asic_specific; int rc, retval = 0; + if (!(goya->hw_cap_initialized & HW_CAP_MME)) + goto stop_tpc; + /* * Each queue (QMAN) is a separate H/W logic. That means that each * QMAN can be stopped independently and failure to stop one does NOT @@ -1810,6 +1833,10 @@ static int goya_stop_internal_queues(struct hl_device *hdev) retval = -EIO; } +stop_tpc: + if (!(goya->hw_cap_initialized & HW_CAP_TPC)) + return retval; + rc = goya_stop_queue(hdev, mmTPC0_QM_GLBL_CFG1, mmTPC0_QM_CP_STS, @@ -1975,6 +2002,11 @@ static int goya_stop_internal_queues(struct hl_device *hdev) static void goya_dma_stall(struct hl_device *hdev) { + struct goya_device *goya = hdev->asic_specific; + + if (!(goya->hw_cap_initialized & HW_CAP_DMA)) + return; + WREG32(mmDMA_QM_0_GLBL_CFG1, 1 << DMA_QM_0_GLBL_CFG1_DMA_STOP_SHIFT); WREG32(mmDMA_QM_1_GLBL_CFG1, 1 << DMA_QM_1_GLBL_CFG1_DMA_STOP_SHIFT); WREG32(mmDMA_QM_2_GLBL_CFG1, 1 << DMA_QM_2_GLBL_CFG1_DMA_STOP_SHIFT); @@ -1984,6 +2016,11 @@ static void goya_dma_stall(struct hl_device *hdev) static void goya_tpc_stall(struct hl_device *hdev) { + struct goya_device *goya = hdev->asic_specific; + + if (!(goya->hw_cap_initialized & HW_CAP_TPC)) + return; + WREG32(mmTPC0_CFG_TPC_STALL, 1 << TPC0_CFG_TPC_STALL_V_SHIFT); WREG32(mmTPC1_CFG_TPC_STALL, 1 << TPC1_CFG_TPC_STALL_V_SHIFT); WREG32(mmTPC2_CFG_TPC_STALL, 1 << TPC2_CFG_TPC_STALL_V_SHIFT); @@ -1996,6 +2033,11 @@ static void goya_tpc_stall(struct hl_device *hdev) static void goya_mme_stall(struct hl_device *hdev) { + struct goya_device *goya = hdev->asic_specific; + + if (!(goya->hw_cap_initialized & HW_CAP_MME)) + return; + WREG32(mmMME_STALL, 0xFFFFFFFF); } @@ -4648,8 +4690,6 @@ static int goya_memset_device_memory(struct hl_device *hdev, u64 addr, u64 size, rc = goya_send_job_on_qman0(hdev, job); - hl_cb_put(job->patched_cb); - hl_debugfs_remove_job(hdev, job); kfree(job); cb->cs_cnt--; diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index aa54d359dab74beb7ea27850b5ac144511df3fdc..a971c4bcc442b11ab76c5425bbab46c89bf32dfd 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -1732,8 +1732,11 @@ static int mmc_do_erase(struct mmc_card *card, unsigned int from, * the erase operation does not exceed the max_busy_timeout, we should * use R1B response. Or we need to prevent the host from doing hw busy * detection, which is done by converting to a R1 response instead. + * Note, some hosts requires R1B, which also means they are on their own + * when it comes to deal with the busy timeout. */ - if (card->host->max_busy_timeout && + if (!(card->host->caps & MMC_CAP_NEED_RSP_BUSY) && + card->host->max_busy_timeout && busy_timeout > card->host->max_busy_timeout) { cmd.flags = MMC_RSP_SPI_R1 | MMC_RSP_R1 | MMC_CMD_AC; } else { diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index f6912ded652dcd3e60081e0f9504fd8ed105d163..de14b5845f525e0e8279465695eae885f7bd3ff9 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -1910,9 +1910,12 @@ static int mmc_sleep(struct mmc_host *host) * If the max_busy_timeout of the host is specified, validate it against * the sleep cmd timeout. A failure means we need to prevent the host * from doing hw busy detection, which is done by converting to a R1 - * response instead of a R1B. + * response instead of a R1B. Note, some hosts requires R1B, which also + * means they are on their own when it comes to deal with the busy + * timeout. */ - if (host->max_busy_timeout && (timeout_ms > host->max_busy_timeout)) { + if (!(host->caps & MMC_CAP_NEED_RSP_BUSY) && host->max_busy_timeout && + (timeout_ms > host->max_busy_timeout)) { cmd.flags = MMC_RSP_R1 | MMC_CMD_AC; } else { cmd.flags = MMC_RSP_R1B | MMC_CMD_AC; diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c index da425ee2d9bf50da3cee4962dcdb5b6fe341ab6e..e025604e17d45aeafdb5e30488c3380bb3f2dc63 100644 --- a/drivers/mmc/core/mmc_ops.c +++ b/drivers/mmc/core/mmc_ops.c @@ -542,9 +542,11 @@ int __mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value, * If the max_busy_timeout of the host is specified, make sure it's * enough to fit the used timeout_ms. In case it's not, let's instruct * the host to avoid HW busy detection, by converting to a R1 response - * instead of a R1B. + * instead of a R1B. Note, some hosts requires R1B, which also means + * they are on their own when it comes to deal with the busy timeout. */ - if (host->max_busy_timeout && (timeout_ms > host->max_busy_timeout)) + if (!(host->caps & MMC_CAP_NEED_RSP_BUSY) && host->max_busy_timeout && + (timeout_ms > host->max_busy_timeout)) use_r1b_resp = false; cmd.opcode = MMC_SWITCH; diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c index bd50935dc37db857d26ee0b5aaf427de208f1860..11087976ab19cf296053fc35205bfb3e69cece2a 100644 --- a/drivers/mmc/host/rtsx_pci_sdmmc.c +++ b/drivers/mmc/host/rtsx_pci_sdmmc.c @@ -606,19 +606,22 @@ static int sd_change_phase(struct realtek_pci_sdmmc *host, u8 sample_point, bool rx) { struct rtsx_pcr *pcr = host->pcr; - + u16 SD_VP_CTL = 0; dev_dbg(sdmmc_dev(host), "%s(%s): sample_point = %d\n", __func__, rx ? "RX" : "TX", sample_point); rtsx_pci_write_register(pcr, CLK_CTL, CHANGE_CLK, CHANGE_CLK); - if (rx) + if (rx) { + SD_VP_CTL = SD_VPRX_CTL; rtsx_pci_write_register(pcr, SD_VPRX_CTL, PHASE_SELECT_MASK, sample_point); - else + } else { + SD_VP_CTL = SD_VPTX_CTL; rtsx_pci_write_register(pcr, SD_VPTX_CTL, PHASE_SELECT_MASK, sample_point); - rtsx_pci_write_register(pcr, SD_VPCLK0_CTL, PHASE_NOT_RESET, 0); - rtsx_pci_write_register(pcr, SD_VPCLK0_CTL, PHASE_NOT_RESET, + } + rtsx_pci_write_register(pcr, SD_VP_CTL, PHASE_NOT_RESET, 0); + rtsx_pci_write_register(pcr, SD_VP_CTL, PHASE_NOT_RESET, PHASE_NOT_RESET); rtsx_pci_write_register(pcr, CLK_CTL, CHANGE_CLK, 0); rtsx_pci_write_register(pcr, SD_CFG1, SD_ASYNC_FIFO_NOT_RST, 0); diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c index 9651dca6863ec299df9062879015a83aadc25a78..2a2173d953f584d283eecc7845147e88d152435e 100644 --- a/drivers/mmc/host/sdhci-acpi.c +++ b/drivers/mmc/host/sdhci-acpi.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include @@ -72,9 +73,16 @@ struct sdhci_acpi_host { const struct sdhci_acpi_slot *slot; struct platform_device *pdev; bool use_runtime_pm; + bool is_intel; + bool reset_signal_volt_on_suspend; unsigned long private[0] ____cacheline_aligned; }; +enum { + DMI_QUIRK_RESET_SD_SIGNAL_VOLT_ON_SUSP = BIT(0), + DMI_QUIRK_SD_NO_WRITE_PROTECT = BIT(1), +}; + static inline void *sdhci_acpi_priv(struct sdhci_acpi_host *c) { return (void *)c->private; @@ -391,6 +399,8 @@ static int intel_probe_slot(struct platform_device *pdev, struct acpi_device *ad host->mmc_host_ops.start_signal_voltage_switch = intel_start_signal_voltage_switch; + c->is_intel = true; + return 0; } @@ -647,6 +657,36 @@ static const struct acpi_device_id sdhci_acpi_ids[] = { }; MODULE_DEVICE_TABLE(acpi, sdhci_acpi_ids); +static const struct dmi_system_id sdhci_acpi_quirks[] = { + { + /* + * The Lenovo Miix 320-10ICR has a bug in the _PS0 method of + * the SHC1 ACPI device, this bug causes it to reprogram the + * wrong LDO (DLDO3) to 1.8V if 1.8V modes are used and the + * card is (runtime) suspended + resumed. DLDO3 is used for + * the LCD and setting it to 1.8V causes the LCD to go black. + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo MIIX 320-10ICR"), + }, + .driver_data = (void *)DMI_QUIRK_RESET_SD_SIGNAL_VOLT_ON_SUSP, + }, + { + /* + * The Acer Aspire Switch 10 (SW5-012) microSD slot always + * reports the card being write-protected even though microSD + * cards do not have a write-protect switch at all. + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire SW5-012"), + }, + .driver_data = (void *)DMI_QUIRK_SD_NO_WRITE_PROTECT, + }, + {} /* Terminating entry */ +}; + static const struct sdhci_acpi_slot *sdhci_acpi_get_slot(struct acpi_device *adev) { const struct sdhci_acpi_uid_slot *u; @@ -663,17 +703,23 @@ static int sdhci_acpi_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; const struct sdhci_acpi_slot *slot; struct acpi_device *device, *child; + const struct dmi_system_id *id; struct sdhci_acpi_host *c; struct sdhci_host *host; struct resource *iomem; resource_size_t len; size_t priv_size; + int quirks = 0; int err; device = ACPI_COMPANION(dev); if (!device) return -ENODEV; + id = dmi_first_match(sdhci_acpi_quirks); + if (id) + quirks = (long)id->driver_data; + slot = sdhci_acpi_get_slot(device); /* Power on the SDHCI controller and its children */ @@ -759,6 +805,12 @@ static int sdhci_acpi_probe(struct platform_device *pdev) dev_warn(dev, "failed to setup card detect gpio\n"); c->use_runtime_pm = false; } + + if (quirks & DMI_QUIRK_RESET_SD_SIGNAL_VOLT_ON_SUSP) + c->reset_signal_volt_on_suspend = true; + + if (quirks & DMI_QUIRK_SD_NO_WRITE_PROTECT) + host->mmc->caps2 |= MMC_CAP2_NO_WRITE_PROTECT; } err = sdhci_setup_host(host); @@ -823,17 +875,39 @@ static int sdhci_acpi_remove(struct platform_device *pdev) return 0; } +static void __maybe_unused sdhci_acpi_reset_signal_voltage_if_needed( + struct device *dev) +{ + struct sdhci_acpi_host *c = dev_get_drvdata(dev); + struct sdhci_host *host = c->host; + + if (c->is_intel && c->reset_signal_volt_on_suspend && + host->mmc->ios.signal_voltage != MMC_SIGNAL_VOLTAGE_330) { + struct intel_host *intel_host = sdhci_acpi_priv(c); + unsigned int fn = INTEL_DSM_V33_SWITCH; + u32 result = 0; + + intel_dsm(intel_host, dev, fn, &result); + } +} + #ifdef CONFIG_PM_SLEEP static int sdhci_acpi_suspend(struct device *dev) { struct sdhci_acpi_host *c = dev_get_drvdata(dev); struct sdhci_host *host = c->host; + int ret; if (host->tuning_mode != SDHCI_TUNING_MODE_3) mmc_retune_needed(host->mmc); - return sdhci_suspend_host(host); + ret = sdhci_suspend_host(host); + if (ret) + return ret; + + sdhci_acpi_reset_signal_voltage_if_needed(dev); + return 0; } static int sdhci_acpi_resume(struct device *dev) @@ -853,11 +927,17 @@ static int sdhci_acpi_runtime_suspend(struct device *dev) { struct sdhci_acpi_host *c = dev_get_drvdata(dev); struct sdhci_host *host = c->host; + int ret; if (host->tuning_mode != SDHCI_TUNING_MODE_3) mmc_retune_needed(host->mmc); - return sdhci_runtime_suspend_host(host); + ret = sdhci_runtime_suspend_host(host); + if (ret) + return ret; + + sdhci_acpi_reset_signal_voltage_if_needed(dev); + return 0; } static int sdhci_acpi_runtime_resume(struct device *dev) diff --git a/drivers/mmc/host/sdhci-cadence.c b/drivers/mmc/host/sdhci-cadence.c index 5827d3751b813176a6446463678a7448c1b389ab..e573495f872660597b0e96414d0cf501cd8551d3 100644 --- a/drivers/mmc/host/sdhci-cadence.c +++ b/drivers/mmc/host/sdhci-cadence.c @@ -11,6 +11,7 @@ #include #include #include +#include #include "sdhci-pltfm.h" @@ -235,6 +236,11 @@ static const struct sdhci_ops sdhci_cdns_ops = { .set_uhs_signaling = sdhci_cdns_set_uhs_signaling, }; +static const struct sdhci_pltfm_data sdhci_cdns_uniphier_pltfm_data = { + .ops = &sdhci_cdns_ops, + .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN, +}; + static const struct sdhci_pltfm_data sdhci_cdns_pltfm_data = { .ops = &sdhci_cdns_ops, }; @@ -334,6 +340,7 @@ static void sdhci_cdns_hs400_enhanced_strobe(struct mmc_host *mmc, static int sdhci_cdns_probe(struct platform_device *pdev) { struct sdhci_host *host; + const struct sdhci_pltfm_data *data; struct sdhci_pltfm_host *pltfm_host; struct sdhci_cdns_priv *priv; struct clk *clk; @@ -350,8 +357,12 @@ static int sdhci_cdns_probe(struct platform_device *pdev) if (ret) return ret; + data = of_device_get_match_data(dev); + if (!data) + data = &sdhci_cdns_pltfm_data; + nr_phy_params = sdhci_cdns_phy_param_count(dev->of_node); - host = sdhci_pltfm_init(pdev, &sdhci_cdns_pltfm_data, + host = sdhci_pltfm_init(pdev, data, struct_size(priv, phy_params, nr_phy_params)); if (IS_ERR(host)) { ret = PTR_ERR(host); @@ -431,7 +442,10 @@ static const struct dev_pm_ops sdhci_cdns_pm_ops = { }; static const struct of_device_id sdhci_cdns_match[] = { - { .compatible = "socionext,uniphier-sd4hc" }, + { + .compatible = "socionext,uniphier-sd4hc", + .data = &sdhci_cdns_uniphier_pltfm_data, + }, { .compatible = "cdns,sd4hc" }, { /* sentinel */ } }; diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c index c3a160c1804772963840deab9b593caa4c1640e0..3955fa5db43c69f60b50a8abbcfcb90e43313f7e 100644 --- a/drivers/mmc/host/sdhci-msm.c +++ b/drivers/mmc/host/sdhci-msm.c @@ -1590,7 +1590,7 @@ static u32 sdhci_msm_cqe_irq(struct sdhci_host *host, u32 intmask) return 0; } -void sdhci_msm_cqe_disable(struct mmc_host *mmc, bool recovery) +static void sdhci_msm_cqe_disable(struct mmc_host *mmc, bool recovery) { struct sdhci_host *host = mmc_priv(mmc); unsigned long flags; diff --git a/drivers/mmc/host/sdhci-of-at91.c b/drivers/mmc/host/sdhci-of-at91.c index ab2bd314a390799b3f8e1f071b0f6c2c164ec80c..fcef5c0d0908f7473c529a338a72600cc605f769 100644 --- a/drivers/mmc/host/sdhci-of-at91.c +++ b/drivers/mmc/host/sdhci-of-at91.c @@ -132,7 +132,8 @@ static void sdhci_at91_reset(struct sdhci_host *host, u8 mask) sdhci_reset(host, mask); - if (host->mmc->caps & MMC_CAP_NONREMOVABLE) + if ((host->mmc->caps & MMC_CAP_NONREMOVABLE) + || mmc_gpio_get_cd(host->mmc) >= 0) sdhci_at91_set_force_card_detect(host); if (priv->cal_always_on && (mask & SDHCI_RESET_ALL)) @@ -427,8 +428,11 @@ static int sdhci_at91_probe(struct platform_device *pdev) * detection procedure using the SDMCC_CD signal is bypassed. * This bit is reset when a software reset for all command is performed * so we need to implement our own reset function to set back this bit. + * + * WA: SAMA5D2 doesn't drive CMD if using CD GPIO line. */ - if (host->mmc->caps & MMC_CAP_NONREMOVABLE) + if ((host->mmc->caps & MMC_CAP_NONREMOVABLE) + || mmc_gpio_get_cd(host->mmc) >= 0) sdhci_at91_set_force_card_detect(host); pm_runtime_put_autosuspend(&pdev->dev); diff --git a/drivers/mmc/host/sdhci-omap.c b/drivers/mmc/host/sdhci-omap.c index 882053151a4741098684898e70bf5f1e03ea45ad..c4978177ef88c2b03e68dc40010adca958ade70d 100644 --- a/drivers/mmc/host/sdhci-omap.c +++ b/drivers/mmc/host/sdhci-omap.c @@ -1192,6 +1192,9 @@ static int sdhci_omap_probe(struct platform_device *pdev) if (of_find_property(dev->of_node, "dmas", NULL)) sdhci_switch_external_dma(host, true); + /* R1B responses is required to properly manage HW busy detection. */ + mmc->caps |= MMC_CAP_NEED_RSP_BUSY; + ret = sdhci_setup_host(host); if (ret) goto err_put_sync; diff --git a/drivers/mmc/host/sdhci-pci-gli.c b/drivers/mmc/host/sdhci-pci-gli.c index 5eea8d70a85d7ba9ecf2a9b3217581e59f552f08..ce15a05f23d41988dcbb36f2d08dc8cd6733cc4f 100644 --- a/drivers/mmc/host/sdhci-pci-gli.c +++ b/drivers/mmc/host/sdhci-pci-gli.c @@ -262,10 +262,26 @@ static int gl9750_execute_tuning(struct sdhci_host *host, u32 opcode) return 0; } +static void gli_pcie_enable_msi(struct sdhci_pci_slot *slot) +{ + int ret; + + ret = pci_alloc_irq_vectors(slot->chip->pdev, 1, 1, + PCI_IRQ_MSI | PCI_IRQ_MSIX); + if (ret < 0) { + pr_warn("%s: enable PCI MSI failed, error=%d\n", + mmc_hostname(slot->host->mmc), ret); + return; + } + + slot->host->irq = pci_irq_vector(slot->chip->pdev, 0); +} + static int gli_probe_slot_gl9750(struct sdhci_pci_slot *slot) { struct sdhci_host *host = slot->host; + gli_pcie_enable_msi(slot); slot->host->mmc->caps2 |= MMC_CAP2_NO_SDIO; sdhci_enable_v4_mode(host); @@ -276,6 +292,7 @@ static int gli_probe_slot_gl9755(struct sdhci_pci_slot *slot) { struct sdhci_host *host = slot->host; + gli_pcie_enable_msi(slot); slot->host->mmc->caps2 |= MMC_CAP2_NO_SDIO; sdhci_enable_v4_mode(host); diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c index 403ac44a737822cbd754021ad644164ea6e0dc79..a25c3a4d3f6cbb9dfd1d9d65607e31f102011fdb 100644 --- a/drivers/mmc/host/sdhci-tegra.c +++ b/drivers/mmc/host/sdhci-tegra.c @@ -1552,6 +1552,9 @@ static int sdhci_tegra_probe(struct platform_device *pdev) if (tegra_host->soc_data->nvquirks & NVQUIRK_ENABLE_DDR50) host->mmc->caps |= MMC_CAP_1_8V_DDR; + /* R1B responses is required to properly manage HW busy detection. */ + host->mmc->caps |= MMC_CAP_NEED_RSP_BUSY; + tegra_sdhci_parse_dt(host); tegra_host->power_gpio = devm_gpiod_get_optional(&pdev->dev, "power", diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 1cc2cd894f877c0f6d9117ce008b7ef3fdfbcbcc..c81698550e5a78b091a761638ee35f887aacba1d 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -50,11 +50,6 @@ struct arp_pkt { }; #pragma pack() -static inline struct arp_pkt *arp_pkt(const struct sk_buff *skb) -{ - return (struct arp_pkt *)skb_network_header(skb); -} - /* Forward declaration */ static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[], bool strict_match); @@ -553,10 +548,11 @@ static void rlb_req_update_subnet_clients(struct bonding *bond, __be32 src_ip) spin_unlock(&bond->mode_lock); } -static struct slave *rlb_choose_channel(struct sk_buff *skb, struct bonding *bond) +static struct slave *rlb_choose_channel(struct sk_buff *skb, + struct bonding *bond, + const struct arp_pkt *arp) { struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); - struct arp_pkt *arp = arp_pkt(skb); struct slave *assigned_slave, *curr_active_slave; struct rlb_client_info *client_info; u32 hash_index = 0; @@ -653,8 +649,12 @@ static struct slave *rlb_choose_channel(struct sk_buff *skb, struct bonding *bon */ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond) { - struct arp_pkt *arp = arp_pkt(skb); struct slave *tx_slave = NULL; + struct arp_pkt *arp; + + if (!pskb_network_may_pull(skb, sizeof(*arp))) + return NULL; + arp = (struct arp_pkt *)skb_network_header(skb); /* Don't modify or load balance ARPs that do not originate locally * (e.g.,arrive via a bridge). @@ -664,7 +664,7 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond) if (arp->op_code == htons(ARPOP_REPLY)) { /* the arp must be sent on the selected rx channel */ - tx_slave = rlb_choose_channel(skb, bond); + tx_slave = rlb_choose_channel(skb, bond, arp); if (tx_slave) bond_hw_addr_copy(arp->mac_src, tx_slave->dev->dev_addr, tx_slave->dev->addr_len); @@ -676,7 +676,7 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond) * When the arp reply is received the entry will be updated * with the correct unicast address of the client. */ - tx_slave = rlb_choose_channel(skb, bond); + tx_slave = rlb_choose_channel(skb, bond, arp); /* The ARP reply packets must be delayed so that * they can cancel out the influence of the ARP request. diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 48d5ec770b94242fddb71a02effab6fc1ee988e8..d10805e5e6232b91bf8e125e2734da4629712b1b 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3526,6 +3526,47 @@ static void bond_fold_stats(struct rtnl_link_stats64 *_res, } } +#ifdef CONFIG_LOCKDEP +static int bond_get_lowest_level_rcu(struct net_device *dev) +{ + struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; + struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; + int cur = 0, max = 0; + + now = dev; + iter = &dev->adj_list.lower; + + while (1) { + next = NULL; + while (1) { + ldev = netdev_next_lower_dev_rcu(now, &iter); + if (!ldev) + break; + + next = ldev; + niter = &ldev->adj_list.lower; + dev_stack[cur] = now; + iter_stack[cur++] = iter; + if (max <= cur) + max = cur; + break; + } + + if (!next) { + if (!cur) + return max; + next = dev_stack[--cur]; + niter = iter_stack[cur]; + } + + now = next; + iter = niter; + } + + return max; +} +#endif + static void bond_get_stats(struct net_device *bond_dev, struct rtnl_link_stats64 *stats) { @@ -3533,11 +3574,17 @@ static void bond_get_stats(struct net_device *bond_dev, struct rtnl_link_stats64 temp; struct list_head *iter; struct slave *slave; + int nest_level = 0; - spin_lock(&bond->stats_lock); - memcpy(stats, &bond->bond_stats, sizeof(*stats)); rcu_read_lock(); +#ifdef CONFIG_LOCKDEP + nest_level = bond_get_lowest_level_rcu(bond_dev); +#endif + + spin_lock_nested(&bond->stats_lock, nest_level); + memcpy(stats, &bond->bond_stats, sizeof(*stats)); + bond_for_each_slave_rcu(bond, slave, iter) { const struct rtnl_link_stats64 *new = dev_get_stats(slave->dev, &temp); @@ -3547,10 +3594,10 @@ static void bond_get_stats(struct net_device *bond_dev, /* save off the slave stats for the next run */ memcpy(&slave->slave_stats, new, sizeof(*new)); } - rcu_read_unlock(); memcpy(&bond->bond_stats, stats, sizeof(*stats)); spin_unlock(&bond->stats_lock); + rcu_read_unlock(); } static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd) @@ -3640,6 +3687,8 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd case BOND_RELEASE_OLD: case SIOCBONDRELEASE: res = bond_release(bond_dev, slave_dev); + if (!res) + netdev_update_lockdep_key(slave_dev); break; case BOND_SETHWADDR_OLD: case SIOCBONDSETHWADDR: diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index ddb3916d3506bec2fe317973054a32ea5c4255ad..215c1092328937a01531840ea9222fc5fe0e13a2 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -1398,6 +1398,8 @@ static int bond_option_slaves_set(struct bonding *bond, case '-': slave_dbg(bond->dev, dev, "Releasing interface\n"); ret = bond_release(bond->dev, dev); + if (!ret) + netdev_update_lockdep_key(dev); break; default: diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index 6ee06a49fb4cdc4d8ffcb029918590539d192ee0..68834a2853c9d86a290a2f7cf2de86578f4ad44a 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -883,6 +883,7 @@ static const struct nla_policy can_policy[IFLA_CAN_MAX + 1] = { = { .len = sizeof(struct can_bittiming) }, [IFLA_CAN_DATA_BITTIMING_CONST] = { .len = sizeof(struct can_bittiming_const) }, + [IFLA_CAN_TERMINATION] = { .type = NLA_U16 }, }; static int can_validate(struct nlattr *tb[], struct nlattr *data[], diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 449a22172e079649940a1c3ba76cd30fb6e46ccb..1a69286daa8d8adcc2b2e535c1bd4a02b380a1c0 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1366,6 +1366,9 @@ void b53_vlan_add(struct dsa_switch *ds, int port, b53_get_vlan_entry(dev, vid, vl); + if (vid == 0 && vid == b53_default_pvid(dev)) + untagged = true; + vl->members |= BIT(port); if (untagged && !dsa_is_cpu_port(ds, port)) vl->untag |= BIT(port); diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index d1955543acd1d1d151d8292c9638c25de2267ae0..b0f5280a83cb612a1a5cfd62060b189b98a967e3 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -69,8 +69,7 @@ static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port) /* Force link status for IMP port */ reg = core_readl(priv, offset); reg |= (MII_SW_OR | LINK_STS); - if (priv->type == BCM7278_DEVICE_ID) - reg |= GMII_SPEED_UP_2G; + reg &= ~GMII_SPEED_UP_2G; core_writel(priv, reg, offset); /* Enable Broadcast, Multicast, Unicast forwarding to IMP port */ diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 8c92895496881cb9d11adf4ee459bd549b247fe3..2f993e673ec7476261a900f76588970ff4532f49 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2769,6 +2769,8 @@ static u64 mv88e6xxx_devlink_atu_bin_get(struct mv88e6xxx_chip *chip, goto unlock; } + occupancy &= MV88E6XXX_G2_ATU_STATS_MASK; + unlock: mv88e6xxx_reg_unlock(chip); diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h index f332cb4b2fbf370a8cb0cead4df2892aca1a343d..79cad5e751c6cd4784d0bf67aa3045336da400ad 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.h +++ b/drivers/net/dsa/mv88e6xxx/chip.h @@ -236,7 +236,7 @@ struct mv88e6xxx_port { bool mirror_ingress; bool mirror_egress; unsigned int serdes_irq; - char serdes_irq_name[32]; + char serdes_irq_name[64]; }; struct mv88e6xxx_chip { @@ -293,16 +293,16 @@ struct mv88e6xxx_chip { struct mv88e6xxx_irq g1_irq; struct mv88e6xxx_irq g2_irq; int irq; - char irq_name[32]; + char irq_name[64]; int device_irq; - char device_irq_name[32]; + char device_irq_name[64]; int watchdog_irq; - char watchdog_irq_name[32]; + char watchdog_irq_name[64]; int atu_prob_irq; - char atu_prob_irq_name[32]; + char atu_prob_irq_name[64]; int vtu_prob_irq; - char vtu_prob_irq_name[32]; + char vtu_prob_irq_name[64]; struct kthread_worker *kworker; struct kthread_delayed_work irq_poll_work; diff --git a/drivers/net/dsa/mv88e6xxx/global1.c b/drivers/net/dsa/mv88e6xxx/global1.c index b016cc205f81f02c1c27a43a5f7618770c7a15ae..ca3a7a7a73c32700bde1206c3122f967edc58842 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.c +++ b/drivers/net/dsa/mv88e6xxx/global1.c @@ -278,13 +278,13 @@ int mv88e6095_g1_set_egress_port(struct mv88e6xxx_chip *chip, switch (direction) { case MV88E6XXX_EGRESS_DIR_INGRESS: dest_port_chip = &chip->ingress_dest_port; - reg &= MV88E6185_G1_MONITOR_CTL_INGRESS_DEST_MASK; + reg &= ~MV88E6185_G1_MONITOR_CTL_INGRESS_DEST_MASK; reg |= port << __bf_shf(MV88E6185_G1_MONITOR_CTL_INGRESS_DEST_MASK); break; case MV88E6XXX_EGRESS_DIR_EGRESS: dest_port_chip = &chip->egress_dest_port; - reg &= MV88E6185_G1_MONITOR_CTL_EGRESS_DEST_MASK; + reg &= ~MV88E6185_G1_MONITOR_CTL_EGRESS_DEST_MASK; reg |= port << __bf_shf(MV88E6185_G1_MONITOR_CTL_EGRESS_DEST_MASK); break; diff --git a/drivers/net/dsa/mv88e6xxx/global2.c b/drivers/net/dsa/mv88e6xxx/global2.c index 01503014b1ee761571497c5da84758b80a0cce8b..8fd483020c5b91685731cbac02cfe3b4328ead42 100644 --- a/drivers/net/dsa/mv88e6xxx/global2.c +++ b/drivers/net/dsa/mv88e6xxx/global2.c @@ -1099,6 +1099,13 @@ int mv88e6xxx_g2_irq_setup(struct mv88e6xxx_chip *chip) { int err, irq, virq; + chip->g2_irq.masked = ~0; + mv88e6xxx_reg_lock(chip); + err = mv88e6xxx_g2_int_mask(chip, ~chip->g2_irq.masked); + mv88e6xxx_reg_unlock(chip); + if (err) + return err; + chip->g2_irq.domain = irq_domain_add_simple( chip->dev->of_node, 16, 0, &mv88e6xxx_g2_irq_domain_ops, chip); if (!chip->g2_irq.domain) @@ -1108,7 +1115,6 @@ int mv88e6xxx_g2_irq_setup(struct mv88e6xxx_chip *chip) irq_create_mapping(chip->g2_irq.domain, irq); chip->g2_irq.chip = mv88e6xxx_g2_irq_chip; - chip->g2_irq.masked = ~0; chip->device_irq = irq_find_mapping(chip->g1_irq.domain, MV88E6XXX_G1_STS_IRQ_DEVICE); diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 03ba6d25f7fefb9b8b2d1dae8ea401ee23df13e5..7edea5741a5fdfb2baf2ba4b8aee098562f74bda 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -1741,7 +1741,8 @@ static void sja1105_teardown(struct dsa_switch *ds) if (!dsa_is_user_port(ds, port)) continue; - kthread_destroy_worker(sp->xmit_worker); + if (sp->xmit_worker) + kthread_destroy_worker(sp->xmit_worker); } sja1105_tas_teardown(ds); diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index ea62604fdf8ca7b0dc647b986ac5ea998f7bc414..1fb58f9ad80b83243455e5a8d80501a692c80ff6 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -200,6 +200,11 @@ static void comp_ctxt_release(struct ena_com_admin_queue *queue, static struct ena_comp_ctx *get_comp_ctxt(struct ena_com_admin_queue *queue, u16 command_id, bool capture) { + if (unlikely(!queue->comp_ctx)) { + pr_err("Completion context is NULL\n"); + return NULL; + } + if (unlikely(command_id >= queue->q_depth)) { pr_err("command id is larger than the queue size. cmd_id: %u queue size %d\n", command_id, queue->q_depth); @@ -1041,9 +1046,41 @@ static int ena_com_get_feature(struct ena_com_dev *ena_dev, feature_ver); } +int ena_com_get_current_hash_function(struct ena_com_dev *ena_dev) +{ + return ena_dev->rss.hash_func; +} + +static void ena_com_hash_key_fill_default_key(struct ena_com_dev *ena_dev) +{ + struct ena_admin_feature_rss_flow_hash_control *hash_key = + (ena_dev->rss).hash_key; + + netdev_rss_key_fill(&hash_key->key, sizeof(hash_key->key)); + /* The key is stored in the device in u32 array + * as well as the API requires the key to be passed in this + * format. Thus the size of our array should be divided by 4 + */ + hash_key->keys_num = sizeof(hash_key->key) / sizeof(u32); +} + static int ena_com_hash_key_allocate(struct ena_com_dev *ena_dev) { struct ena_rss *rss = &ena_dev->rss; + struct ena_admin_feature_rss_flow_hash_control *hash_key; + struct ena_admin_get_feat_resp get_resp; + int rc; + + hash_key = (ena_dev->rss).hash_key; + + rc = ena_com_get_feature_ex(ena_dev, &get_resp, + ENA_ADMIN_RSS_HASH_FUNCTION, + ena_dev->rss.hash_key_dma_addr, + sizeof(ena_dev->rss.hash_key), 0); + if (unlikely(rc)) { + hash_key = NULL; + return -EOPNOTSUPP; + } rss->hash_key = dma_alloc_coherent(ena_dev->dmadev, sizeof(*rss->hash_key), @@ -1254,30 +1291,6 @@ static int ena_com_ind_tbl_convert_to_device(struct ena_com_dev *ena_dev) return 0; } -static int ena_com_ind_tbl_convert_from_device(struct ena_com_dev *ena_dev) -{ - u16 dev_idx_to_host_tbl[ENA_TOTAL_NUM_QUEUES] = { (u16)-1 }; - struct ena_rss *rss = &ena_dev->rss; - u8 idx; - u16 i; - - for (i = 0; i < ENA_TOTAL_NUM_QUEUES; i++) - dev_idx_to_host_tbl[ena_dev->io_sq_queues[i].idx] = i; - - for (i = 0; i < 1 << rss->tbl_log_size; i++) { - if (rss->rss_ind_tbl[i].cq_idx > ENA_TOTAL_NUM_QUEUES) - return -EINVAL; - idx = (u8)rss->rss_ind_tbl[i].cq_idx; - - if (dev_idx_to_host_tbl[idx] > ENA_TOTAL_NUM_QUEUES) - return -EINVAL; - - rss->host_rss_ind_tbl[i] = dev_idx_to_host_tbl[idx]; - } - - return 0; -} - static void ena_com_update_intr_delay_resolution(struct ena_com_dev *ena_dev, u16 intr_delay_resolution) { @@ -2297,15 +2310,16 @@ int ena_com_fill_hash_function(struct ena_com_dev *ena_dev, switch (func) { case ENA_ADMIN_TOEPLITZ: - if (key_len > sizeof(hash_key->key)) { - pr_err("key len (%hu) is bigger than the max supported (%zu)\n", - key_len, sizeof(hash_key->key)); - return -EINVAL; + if (key) { + if (key_len != sizeof(hash_key->key)) { + pr_err("key len (%hu) doesn't equal the supported size (%zu)\n", + key_len, sizeof(hash_key->key)); + return -EINVAL; + } + memcpy(hash_key->key, key, key_len); + rss->hash_init_val = init_val; + hash_key->keys_num = key_len >> 2; } - - memcpy(hash_key->key, key, key_len); - rss->hash_init_val = init_val; - hash_key->keys_num = key_len >> 2; break; case ENA_ADMIN_CRC32: rss->hash_init_val = init_val; @@ -2342,7 +2356,11 @@ int ena_com_get_hash_function(struct ena_com_dev *ena_dev, if (unlikely(rc)) return rc; - rss->hash_func = get_resp.u.flow_hash_func.selected_func; + /* ffs() returns 1 in case the lsb is set */ + rss->hash_func = ffs(get_resp.u.flow_hash_func.selected_func); + if (rss->hash_func) + rss->hash_func--; + if (func) *func = rss->hash_func; @@ -2606,10 +2624,6 @@ int ena_com_indirect_table_get(struct ena_com_dev *ena_dev, u32 *ind_tbl) if (!ind_tbl) return 0; - rc = ena_com_ind_tbl_convert_from_device(ena_dev); - if (unlikely(rc)) - return rc; - for (i = 0; i < (1 << rss->tbl_log_size); i++) ind_tbl[i] = rss->host_rss_ind_tbl[i]; @@ -2626,9 +2640,15 @@ int ena_com_rss_init(struct ena_com_dev *ena_dev, u16 indr_tbl_log_size) if (unlikely(rc)) goto err_indr_tbl; + /* The following function might return unsupported in case the + * device doesn't support setting the key / hash function. We can safely + * ignore this error and have indirection table support only. + */ rc = ena_com_hash_key_allocate(ena_dev); - if (unlikely(rc)) + if (unlikely(rc) && rc != -EOPNOTSUPP) goto err_hash_key; + else if (rc != -EOPNOTSUPP) + ena_com_hash_key_fill_default_key(ena_dev); rc = ena_com_hash_ctrl_init(ena_dev); if (unlikely(rc)) diff --git a/drivers/net/ethernet/amazon/ena/ena_com.h b/drivers/net/ethernet/amazon/ena/ena_com.h index 0ce37d54ed108f0a34167306247ba94eb9833050..469f298199a7b9a7c67ed4934ad6a503c40a1803 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.h +++ b/drivers/net/ethernet/amazon/ena/ena_com.h @@ -44,6 +44,7 @@ #include #include #include +#include #include "ena_common_defs.h" #include "ena_admin_defs.h" @@ -655,6 +656,14 @@ int ena_com_rss_init(struct ena_com_dev *ena_dev, u16 log_size); */ void ena_com_rss_destroy(struct ena_com_dev *ena_dev); +/* ena_com_get_current_hash_function - Get RSS hash function + * @ena_dev: ENA communication layer struct + * + * Return the current hash function. + * @return: 0 or one of the ena_admin_hash_functions values. + */ +int ena_com_get_current_hash_function(struct ena_com_dev *ena_dev); + /* ena_com_fill_hash_function - Fill RSS hash function * @ena_dev: ENA communication layer struct * @func: The hash function (Toeplitz or crc) diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c index b4e891d49a941cc3a36d0a42ac60f694ba9b2794..ced1d577b62a97c0dd3e23bbedea0994e8d4b93c 100644 --- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c +++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c @@ -636,6 +636,28 @@ static u32 ena_get_rxfh_key_size(struct net_device *netdev) return ENA_HASH_KEY_SIZE; } +static int ena_indirection_table_get(struct ena_adapter *adapter, u32 *indir) +{ + struct ena_com_dev *ena_dev = adapter->ena_dev; + int i, rc; + + if (!indir) + return 0; + + rc = ena_com_indirect_table_get(ena_dev, indir); + if (rc) + return rc; + + /* Our internal representation of the indices is: even indices + * for Tx and uneven indices for Rx. We need to convert the Rx + * indices to be consecutive + */ + for (i = 0; i < ENA_RX_RSS_TABLE_SIZE; i++) + indir[i] = ENA_IO_RXQ_IDX_TO_COMBINED_IDX(indir[i]); + + return rc; +} + static int ena_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, u8 *hfunc) { @@ -644,11 +666,25 @@ static int ena_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, u8 func; int rc; - rc = ena_com_indirect_table_get(adapter->ena_dev, indir); + rc = ena_indirection_table_get(adapter, indir); if (rc) return rc; + /* We call this function in order to check if the device + * supports getting/setting the hash function. + */ rc = ena_com_get_hash_function(adapter->ena_dev, &ena_func, key); + + if (rc) { + if (rc == -EOPNOTSUPP) { + key = NULL; + hfunc = NULL; + rc = 0; + } + + return rc; + } + if (rc) return rc; @@ -657,7 +693,7 @@ static int ena_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, func = ETH_RSS_HASH_TOP; break; case ENA_ADMIN_CRC32: - func = ETH_RSS_HASH_XOR; + func = ETH_RSS_HASH_CRC32; break; default: netif_err(adapter, drv, netdev, @@ -700,10 +736,13 @@ static int ena_set_rxfh(struct net_device *netdev, const u32 *indir, } switch (hfunc) { + case ETH_RSS_HASH_NO_CHANGE: + func = ena_com_get_current_hash_function(ena_dev); + break; case ETH_RSS_HASH_TOP: func = ENA_ADMIN_TOEPLITZ; break; - case ETH_RSS_HASH_XOR: + case ETH_RSS_HASH_CRC32: func = ENA_ADMIN_CRC32; break; default: @@ -814,6 +853,7 @@ static const struct ethtool_ops ena_ethtool_ops = { .set_channels = ena_set_channels, .get_tunable = ena_get_tunable, .set_tunable = ena_set_tunable, + .get_ts_info = ethtool_op_get_ts_info, }; void ena_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 894e8c1a8cf15f7ab33eb3d2cb326507255ce5a6..0b2fd96b93d7f23e71d8fe599d2bb4503f01cd73 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -3706,8 +3706,8 @@ static void check_for_missing_keep_alive(struct ena_adapter *adapter) if (adapter->keep_alive_timeout == ENA_HW_HINTS_NO_TIMEOUT) return; - keep_alive_expired = round_jiffies(adapter->last_keep_alive_jiffies + - adapter->keep_alive_timeout); + keep_alive_expired = adapter->last_keep_alive_jiffies + + adapter->keep_alive_timeout; if (unlikely(time_is_before_jiffies(keep_alive_expired))) { netif_err(adapter, drv, adapter->netdev, "Keep alive watchdog timeout.\n"); @@ -3809,7 +3809,7 @@ static void ena_timer_service(struct timer_list *t) } /* Reset the timer */ - mod_timer(&adapter->timer_service, jiffies + HZ); + mod_timer(&adapter->timer_service, round_jiffies(jiffies + HZ)); } static int ena_calc_max_io_queue_num(struct pci_dev *pdev, diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h index 094324fd0edc194909c7afe65f128ffabf3fe7a5..8795e0b1dc3c0522c67c3978125be788d60b852e 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.h +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h @@ -130,6 +130,8 @@ #define ENA_IO_TXQ_IDX(q) (2 * (q)) #define ENA_IO_RXQ_IDX(q) (2 * (q) + 1) +#define ENA_IO_TXQ_IDX_TO_COMBINED_IDX(q) ((q) / 2) +#define ENA_IO_RXQ_IDX_TO_COMBINED_IDX(q) (((q) - 1) / 2) #define ENA_MGMNT_IRQ_IDX 0 #define ENA_IO_IRQ_FIRST_IDX 1 diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c index a1f99bef4a683286bda9c141f9fed6e7953b68b0..7b55633d2cb939d23f08cb442e380cc215464115 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c @@ -722,6 +722,11 @@ static int aq_ethtool_set_priv_flags(struct net_device *ndev, u32 flags) if (flags & ~AQ_PRIV_FLAGS_MASK) return -EOPNOTSUPP; + if (hweight32((flags | priv_flags) & AQ_HW_LOOPBACK_MASK) > 1) { + netdev_info(ndev, "Can't enable more than one loopback simultaneously\n"); + return -EINVAL; + } + cfg->priv_flags = flags; if ((priv_flags ^ flags) & BIT(AQ_HW_LOOPBACK_DMA_NET)) { diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c index 6102251bb909b02c3736b9e0f6f204b40eeba286..03ff92bc4a7fb11c97e4e128609ada081b0dfb44 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c @@ -163,7 +163,7 @@ aq_check_approve_fvlan(struct aq_nic_s *aq_nic, } if ((aq_nic->ndev->features & NETIF_F_HW_VLAN_CTAG_FILTER) && - (!test_bit(be16_to_cpu(fsp->h_ext.vlan_tci), + (!test_bit(be16_to_cpu(fsp->h_ext.vlan_tci) & VLAN_VID_MASK, aq_nic->active_vlans))) { netdev_err(aq_nic->ndev, "ethtool: unknown vlan-id specified"); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h index cc70c606b6ef292fa61cd915942ee88f9ac40091..251767c31f7e59e47250ea96a5a1d1d4cfa1f056 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h @@ -337,6 +337,8 @@ struct aq_fw_ops { void (*enable_ptp)(struct aq_hw_s *self, int enable); + void (*adjust_ptp)(struct aq_hw_s *self, uint64_t adj); + int (*set_eee_rate)(struct aq_hw_s *self, u32 speed); int (*get_eee_rate)(struct aq_hw_s *self, u32 *rate, diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index c85e3e29012c0be813dde299aa8731653362a791..e95f6a6bef733d1f944af19b852e18971795c21c 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -533,8 +533,10 @@ unsigned int aq_nic_map_skb(struct aq_nic_s *self, struct sk_buff *skb, dx_buff->len, DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(aq_nic_get_dev(self), dx_buff->pa))) + if (unlikely(dma_mapping_error(aq_nic_get_dev(self), dx_buff->pa))) { + ret = 0; goto exit; + } first = dx_buff; dx_buff->len_pkt = skb->len; @@ -655,10 +657,6 @@ int aq_nic_xmit(struct aq_nic_s *self, struct sk_buff *skb) if (likely(frags)) { err = self->aq_hw_ops->hw_ring_tx_xmit(self->aq_hw, ring, frags); - if (err >= 0) { - ++ring->stats.tx.packets; - ring->stats.tx.bytes += skb->len; - } } else { err = NETDEV_TX_BUSY; } diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c index 6b27af0db4992888ec1d2648ef6b51f5c89aabc3..78b6f32487565f30069c12565d92dd73c182c9de 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c @@ -359,7 +359,8 @@ static int aq_suspend_common(struct device *dev, bool deep) netif_device_detach(nic->ndev); netif_tx_stop_all_queues(nic->ndev); - aq_nic_stop(nic); + if (netif_running(nic->ndev)) + aq_nic_stop(nic); if (deep) { aq_nic_deinit(nic, !nic->aq_hw->aq_nic_cfg->wol); @@ -375,7 +376,7 @@ static int atl_resume_common(struct device *dev, bool deep) { struct pci_dev *pdev = to_pci_dev(dev); struct aq_nic_s *nic; - int ret; + int ret = 0; nic = pci_get_drvdata(pdev); @@ -390,9 +391,11 @@ static int atl_resume_common(struct device *dev, bool deep) goto err_exit; } - ret = aq_nic_start(nic); - if (ret) - goto err_exit; + if (netif_running(nic->ndev)) { + ret = aq_nic_start(nic); + if (ret) + goto err_exit; + } netif_device_attach(nic->ndev); netif_tx_start_all_queues(nic->ndev); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 951d86f8b66e8c9114510d41436c030cf7bffeb8..bae95a61856081afc83e36c43fd1b1bc59634d7a 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -272,9 +272,12 @@ bool aq_ring_tx_clean(struct aq_ring_s *self) } } - if (unlikely(buff->is_eop)) - dev_kfree_skb_any(buff->skb); + if (unlikely(buff->is_eop)) { + ++self->stats.rx.packets; + self->stats.tx.bytes += buff->skb->len; + dev_kfree_skb_any(buff->skb); + } buff->pa = 0U; buff->eop_index = 0xffffU; self->sw_head = aq_ring_next_dx(self, self->sw_head); @@ -351,7 +354,8 @@ int aq_ring_rx_clean(struct aq_ring_s *self, err = 0; goto err_exit; } - if (buff->is_error || buff->is_cso_err) { + if (buff->is_error || + (buff->is_lro && buff->is_cso_err)) { buff_ = buff; do { next_ = buff_->next, diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h index 991e4d31b0948e86e21299c069d3bc70a738b3b0..2c96f20f62891dbec2184039cce3a7de952a6b14 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h @@ -78,7 +78,8 @@ struct __packed aq_ring_buff_s { u32 is_cleaned:1; u32 is_error:1; u32 is_vlan:1; - u32 rsvd3:4; + u32 is_lro:1; + u32 rsvd3:3; u16 eop_index; u16 rsvd4; }; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index ec041f78d0634426d76e23a23678c6be8321a69b..d20d91cdece861adeb0b45c44a69a8140cb048e4 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -823,6 +823,8 @@ static int hw_atl_b0_hw_ring_rx_receive(struct aq_hw_s *self, } } + buff->is_lro = !!(HW_ATL_B0_RXD_WB_STAT2_RSCCNT & + rxd_wb->status); if (HW_ATL_B0_RXD_WB_STAT2_EOP & rxd_wb->status) { buff->len = rxd_wb->pkt_len % AQ_CFG_RX_FRAME_MAX; @@ -835,8 +837,7 @@ static int hw_atl_b0_hw_ring_rx_receive(struct aq_hw_s *self, rxd_wb->pkt_len > AQ_CFG_RX_FRAME_MAX ? AQ_CFG_RX_FRAME_MAX : rxd_wb->pkt_len; - if (HW_ATL_B0_RXD_WB_STAT2_RSCCNT & - rxd_wb->status) { + if (buff->is_lro) { /* LRO */ buff->next = rxd_wb->next_desc_ptr; ++ring->stats.rx.lro_packets; @@ -884,13 +885,16 @@ static int hw_atl_b0_hw_packet_filter_set(struct aq_hw_s *self, { struct aq_nic_cfg_s *cfg = self->aq_nic_cfg; unsigned int i = 0U; + u32 vlan_promisc; + u32 l2_promisc; - hw_atl_rpfl2promiscuous_mode_en_set(self, - IS_FILTER_ENABLED(IFF_PROMISC)); + l2_promisc = IS_FILTER_ENABLED(IFF_PROMISC) || + !!(cfg->priv_flags & BIT(AQ_HW_LOOPBACK_DMA_NET)); + vlan_promisc = l2_promisc || cfg->is_vlan_force_promisc; - hw_atl_rpf_vlan_prom_mode_en_set(self, - IS_FILTER_ENABLED(IFF_PROMISC) || - cfg->is_vlan_force_promisc); + hw_atl_rpfl2promiscuous_mode_en_set(self, l2_promisc); + + hw_atl_rpf_vlan_prom_mode_en_set(self, vlan_promisc); hw_atl_rpfl2multicast_flr_en_set(self, IS_FILTER_ENABLED(IFF_ALLMULTI) && @@ -1161,6 +1165,8 @@ static int hw_atl_b0_adj_sys_clock(struct aq_hw_s *self, s64 delta) { self->ptp_clk_offset += delta; + self->aq_fw_ops->adjust_ptp(self, self->ptp_clk_offset); + return 0; } @@ -1211,7 +1217,7 @@ static int hw_atl_b0_gpio_pulse(struct aq_hw_s *self, u32 index, fwreq.ptp_gpio_ctrl.index = index; fwreq.ptp_gpio_ctrl.period = period; /* Apply time offset */ - fwreq.ptp_gpio_ctrl.start = start - self->ptp_clk_offset; + fwreq.ptp_gpio_ctrl.start = start; size = sizeof(fwreq.msg_id) + sizeof(fwreq.ptp_gpio_ctrl); return self->aq_fw_ops->send_fw_request(self, &fwreq, size); diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c index f547baa6c95499e5f16313ea47b2c04f18f105ca..354705f9bc493afcbe9c63f28cc36f779eea4be5 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c @@ -22,6 +22,7 @@ #define HW_ATL_MIF_ADDR 0x0208U #define HW_ATL_MIF_VAL 0x020CU +#define HW_ATL_MPI_RPC_ADDR 0x0334U #define HW_ATL_RPC_CONTROL_ADR 0x0338U #define HW_ATL_RPC_STATE_ADR 0x033CU @@ -53,15 +54,14 @@ enum mcp_area { }; static int hw_atl_utils_ver_match(u32 ver_expected, u32 ver_actual); - static int hw_atl_utils_mpi_set_state(struct aq_hw_s *self, enum hal_atl_utils_fw_state_e state); - static u32 hw_atl_utils_get_mpi_mbox_tid(struct aq_hw_s *self); static u32 hw_atl_utils_mpi_get_state(struct aq_hw_s *self); static u32 hw_atl_utils_mif_cmd_get(struct aq_hw_s *self); static u32 hw_atl_utils_mif_addr_get(struct aq_hw_s *self); static u32 hw_atl_utils_rpc_state_get(struct aq_hw_s *self); +static u32 aq_fw1x_rpc_get(struct aq_hw_s *self); int hw_atl_utils_initfw(struct aq_hw_s *self, const struct aq_fw_ops **fw_ops) { @@ -476,6 +476,10 @@ static int hw_atl_utils_init_ucp(struct aq_hw_s *self, self, self->mbox_addr, self->mbox_addr != 0U, 1000U, 10000U); + err = readx_poll_timeout_atomic(aq_fw1x_rpc_get, self, + self->rpc_addr, + self->rpc_addr != 0U, + 1000U, 100000U); return err; } @@ -531,6 +535,12 @@ int hw_atl_utils_fw_rpc_wait(struct aq_hw_s *self, self, fw.val, sw.tid == fw.tid, 1000U, 100000U); + if (err < 0) + goto err_exit; + + err = aq_hw_err_from_flags(self); + if (err < 0) + goto err_exit; if (fw.len == 0xFFFFU) { err = hw_atl_utils_fw_rpc_call(self, sw.len); @@ -1025,6 +1035,11 @@ static u32 hw_atl_utils_rpc_state_get(struct aq_hw_s *self) return aq_hw_read_reg(self, HW_ATL_RPC_STATE_ADR); } +static u32 aq_fw1x_rpc_get(struct aq_hw_s *self) +{ + return aq_hw_read_reg(self, HW_ATL_MPI_RPC_ADDR); +} + const struct aq_fw_ops aq_fw_1x_ops = { .init = hw_atl_utils_mpi_create, .deinit = hw_atl_fw1x_deinit, diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c index 97ebf849695fdb0b9cc386c535b3ff34e7fba3c4..77a4ed64830fd1e1c04814f1b18aecf99f0f0dd3 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c @@ -30,6 +30,9 @@ #define HW_ATL_FW3X_EXT_CONTROL_ADDR 0x378 #define HW_ATL_FW3X_EXT_STATE_ADDR 0x37c +#define HW_ATL_FW3X_PTP_ADJ_LSW_ADDR 0x50a0 +#define HW_ATL_FW3X_PTP_ADJ_MSW_ADDR 0x50a4 + #define HW_ATL_FW2X_CAP_PAUSE BIT(CAPS_HI_PAUSE) #define HW_ATL_FW2X_CAP_ASYM_PAUSE BIT(CAPS_HI_ASYMMETRIC_PAUSE) #define HW_ATL_FW2X_CAP_SLEEP_PROXY BIT(CAPS_HI_SLEEP_PROXY) @@ -475,6 +478,14 @@ static void aq_fw3x_enable_ptp(struct aq_hw_s *self, int enable) aq_hw_write_reg(self, HW_ATL_FW3X_EXT_CONTROL_ADDR, ptp_opts); } +static void aq_fw3x_adjust_ptp(struct aq_hw_s *self, uint64_t adj) +{ + aq_hw_write_reg(self, HW_ATL_FW3X_PTP_ADJ_LSW_ADDR, + (adj >> 0) & 0xffffffff); + aq_hw_write_reg(self, HW_ATL_FW3X_PTP_ADJ_MSW_ADDR, + (adj >> 32) & 0xffffffff); +} + static int aq_fw2x_led_control(struct aq_hw_s *self, u32 mode) { if (self->fw_ver_actual < HW_ATL_FW_VER_LED) @@ -633,4 +644,5 @@ const struct aq_fw_ops aq_fw_2x_ops = { .enable_ptp = aq_fw3x_enable_ptp, .led_control = aq_fw2x_led_control, .set_phyloopback = aq_fw2x_set_phyloopback, + .adjust_ptp = aq_fw3x_adjust_ptp, }; diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index e0611cba87f9586f23d85d8617c010f66e9230f6..15b31cddc054b754ce495569d560d232df84a073 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -2135,7 +2135,7 @@ static int bcm_sysport_rule_set(struct bcm_sysport_priv *priv, return -ENOSPC; index = find_first_zero_bit(priv->filters, RXCHK_BRCM_TAG_MAX); - if (index > RXCHK_BRCM_TAG_MAX) + if (index >= RXCHK_BRCM_TAG_MAX) return -ENOSPC; /* Location is the classification ID, and index is the position diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 597e6fd5bfea8344d21efc5da7918b3291ba3601..c5c8effc013970faab50b985215763b7d5fc451d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -10982,13 +10982,13 @@ static int bnxt_change_mtu(struct net_device *dev, int new_mtu) struct bnxt *bp = netdev_priv(dev); if (netif_running(dev)) - bnxt_close_nic(bp, false, false); + bnxt_close_nic(bp, true, false); dev->mtu = new_mtu; bnxt_set_ring_params(bp); if (netif_running(dev)) - return bnxt_open_nic(bp, false, false); + return bnxt_open_nic(bp, true, false); return 0; } @@ -11252,7 +11252,7 @@ static void bnxt_cfg_ntp_filters(struct bnxt *bp) } } if (test_and_clear_bit(BNXT_HWRM_PF_UNLOAD_SP_EVENT, &bp->sp_event)) - netdev_info(bp->dev, "Receive PF driver unload event!"); + netdev_info(bp->dev, "Receive PF driver unload event!\n"); } #else @@ -11759,7 +11759,7 @@ static int bnxt_pcie_dsn_get(struct bnxt *bp, u8 dsn[]) u32 dw; if (!pos) { - netdev_info(bp->dev, "Unable do read adapter's DSN"); + netdev_info(bp->dev, "Unable do read adapter's DSN\n"); return -EOPNOTSUPP; } @@ -11786,6 +11786,14 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (version_printed++ == 0) pr_info("%s", version); + /* Clear any pending DMA transactions from crash kernel + * while loading driver in capture kernel. + */ + if (is_kdump_kernel()) { + pci_clear_master(pdev); + pcie_flr(pdev); + } + max_irqs = bnxt_get_max_irq(pdev); dev = alloc_etherdev_mq(sizeof(*bp), max_irqs); if (!dev) @@ -11983,10 +11991,10 @@ static void bnxt_shutdown(struct pci_dev *pdev) dev_close(dev); bnxt_ulp_shutdown(bp); + bnxt_clear_int_mode(bp); + pci_disable_device(pdev); if (system_state == SYSTEM_POWER_OFF) { - bnxt_clear_int_mode(bp); - pci_disable_device(pdev); pci_wake_from_d3(pdev, bp->wol); pci_set_power_state(pdev, PCI_D3hot); } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index eec0168330b757af7e598f1608342c2161bfbc2e..d3c93ccee86ad9570cbfbdc3762b47a7ff903a26 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -641,14 +641,14 @@ static int bnxt_dl_params_register(struct bnxt *bp) rc = devlink_params_register(bp->dl, bnxt_dl_params, ARRAY_SIZE(bnxt_dl_params)); if (rc) { - netdev_warn(bp->dev, "devlink_params_register failed. rc=%d", + netdev_warn(bp->dev, "devlink_params_register failed. rc=%d\n", rc); return rc; } rc = devlink_port_params_register(&bp->dl_port, bnxt_dl_port_params, ARRAY_SIZE(bnxt_dl_port_params)); if (rc) { - netdev_err(bp->dev, "devlink_port_params_register failed"); + netdev_err(bp->dev, "devlink_port_params_register failed\n"); devlink_params_unregister(bp->dl, bnxt_dl_params, ARRAY_SIZE(bnxt_dl_params)); return rc; @@ -679,7 +679,7 @@ int bnxt_dl_register(struct bnxt *bp) else dl = devlink_alloc(&bnxt_vf_dl_ops, sizeof(struct bnxt_dl)); if (!dl) { - netdev_warn(bp->dev, "devlink_alloc failed"); + netdev_warn(bp->dev, "devlink_alloc failed\n"); return -ENOMEM; } @@ -692,7 +692,7 @@ int bnxt_dl_register(struct bnxt *bp) rc = devlink_register(dl, &bp->pdev->dev); if (rc) { - netdev_warn(bp->dev, "devlink_register failed. rc=%d", rc); + netdev_warn(bp->dev, "devlink_register failed. rc=%d\n", rc); goto err_dl_free; } @@ -704,7 +704,7 @@ int bnxt_dl_register(struct bnxt *bp) sizeof(bp->dsn)); rc = devlink_port_register(dl, &bp->dl_port, bp->pf.port_id); if (rc) { - netdev_err(bp->dev, "devlink_port_register failed"); + netdev_err(bp->dev, "devlink_port_register failed\n"); goto err_dl_unreg; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 6171fa8b3677b4097d3a10278dced2693b5a340b..1f67e6729a2c7ea58a448c778ad4944f926405f9 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -2007,8 +2007,8 @@ int bnxt_flash_package_from_file(struct net_device *dev, const char *filename, struct hwrm_nvm_install_update_output *resp = bp->hwrm_cmd_resp_addr; struct hwrm_nvm_install_update_input install = {0}; const struct firmware *fw; - int rc, hwrm_err = 0; u32 item_len; + int rc = 0; u16 index; bnxt_hwrm_fw_set_time(bp); @@ -2028,7 +2028,7 @@ int bnxt_flash_package_from_file(struct net_device *dev, const char *filename, } if (fw->size > item_len) { - netdev_err(dev, "PKG insufficient update area in nvram: %lu", + netdev_err(dev, "PKG insufficient update area in nvram: %lu\n", (unsigned long)fw->size); rc = -EFBIG; } else { @@ -2052,15 +2052,14 @@ int bnxt_flash_package_from_file(struct net_device *dev, const char *filename, memcpy(kmem, fw->data, fw->size); modify.host_src_addr = cpu_to_le64(dma_handle); - hwrm_err = hwrm_send_message(bp, &modify, - sizeof(modify), - FLASH_PACKAGE_TIMEOUT); + rc = hwrm_send_message(bp, &modify, sizeof(modify), + FLASH_PACKAGE_TIMEOUT); dma_free_coherent(&bp->pdev->dev, fw->size, kmem, dma_handle); } } release_firmware(fw); - if (rc || hwrm_err) + if (rc) goto err_exit; if ((install_type & 0xffff) == 0) @@ -2069,20 +2068,19 @@ int bnxt_flash_package_from_file(struct net_device *dev, const char *filename, install.install_type = cpu_to_le32(install_type); mutex_lock(&bp->hwrm_cmd_lock); - hwrm_err = _hwrm_send_message(bp, &install, sizeof(install), - INSTALL_PACKAGE_TIMEOUT); - if (hwrm_err) { + rc = _hwrm_send_message(bp, &install, sizeof(install), + INSTALL_PACKAGE_TIMEOUT); + if (rc) { u8 error_code = ((struct hwrm_err_output *)resp)->cmd_err; if (resp->error_code && error_code == NVM_INSTALL_UPDATE_CMD_ERR_CODE_FRAG_ERR) { install.flags |= cpu_to_le16( NVM_INSTALL_UPDATE_REQ_FLAGS_ALLOWED_TO_DEFRAG); - hwrm_err = _hwrm_send_message(bp, &install, - sizeof(install), - INSTALL_PACKAGE_TIMEOUT); + rc = _hwrm_send_message(bp, &install, sizeof(install), + INSTALL_PACKAGE_TIMEOUT); } - if (hwrm_err) + if (rc) goto flash_pkg_exit; } @@ -2094,7 +2092,7 @@ int bnxt_flash_package_from_file(struct net_device *dev, const char *filename, flash_pkg_exit: mutex_unlock(&bp->hwrm_cmd_lock); err_exit: - if (hwrm_err == -EACCES) + if (rc == -EACCES) bnxt_print_admin_err(bp); return rc; } @@ -3338,7 +3336,7 @@ static int bnxt_get_coredump(struct bnxt *bp, void *buf, u32 *dump_len) kfree(coredump.data); *dump_len += sizeof(struct bnxt_coredump_record); if (rc == -ENOBUFS) - netdev_err(bp->dev, "Firmware returned large coredump buffer"); + netdev_err(bp->dev, "Firmware returned large coredump buffer\n"); return rc; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index 0cc6ec51f45fe2ab028bb3c0299dbef0fd3bf088..9bec256b0934afd7285a45432d3fc461246216cb 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -50,7 +50,7 @@ static u16 bnxt_flow_get_dst_fid(struct bnxt *pf_bp, struct net_device *dev) /* check if dev belongs to the same switch */ if (!netdev_port_same_parent_id(pf_bp->dev, dev)) { - netdev_info(pf_bp->dev, "dev(ifindex=%d) not on same switch", + netdev_info(pf_bp->dev, "dev(ifindex=%d) not on same switch\n", dev->ifindex); return BNXT_FID_INVALID; } @@ -70,7 +70,7 @@ static int bnxt_tc_parse_redir(struct bnxt *bp, struct net_device *dev = act->dev; if (!dev) { - netdev_info(bp->dev, "no dev in mirred action"); + netdev_info(bp->dev, "no dev in mirred action\n"); return -EINVAL; } @@ -106,7 +106,7 @@ static int bnxt_tc_parse_tunnel_set(struct bnxt *bp, const struct ip_tunnel_key *tun_key = &tun_info->key; if (ip_tunnel_info_af(tun_info) != AF_INET) { - netdev_info(bp->dev, "only IPv4 tunnel-encap is supported"); + netdev_info(bp->dev, "only IPv4 tunnel-encap is supported\n"); return -EOPNOTSUPP; } @@ -295,7 +295,7 @@ static int bnxt_tc_parse_actions(struct bnxt *bp, int i, rc; if (!flow_action_has_entries(flow_action)) { - netdev_info(bp->dev, "no actions"); + netdev_info(bp->dev, "no actions\n"); return -EINVAL; } @@ -370,7 +370,7 @@ static int bnxt_tc_parse_flow(struct bnxt *bp, /* KEY_CONTROL and KEY_BASIC are needed for forming a meaningful key */ if ((dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL)) == 0 || (dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_BASIC)) == 0) { - netdev_info(bp->dev, "cannot form TC key: used_keys = 0x%x", + netdev_info(bp->dev, "cannot form TC key: used_keys = 0x%x\n", dissector->used_keys); return -EOPNOTSUPP; } @@ -508,7 +508,7 @@ static int bnxt_hwrm_cfa_flow_free(struct bnxt *bp, rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (rc) - netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc); + netdev_info(bp->dev, "%s: Error rc=%d\n", __func__, rc); return rc; } @@ -841,7 +841,7 @@ static int hwrm_cfa_decap_filter_alloc(struct bnxt *bp, resp = bnxt_get_hwrm_resp_addr(bp, &req); *decap_filter_handle = resp->decap_filter_id; } else { - netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc); + netdev_info(bp->dev, "%s: Error rc=%d\n", __func__, rc); } mutex_unlock(&bp->hwrm_cmd_lock); @@ -859,7 +859,7 @@ static int hwrm_cfa_decap_filter_free(struct bnxt *bp, rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (rc) - netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc); + netdev_info(bp->dev, "%s: Error rc=%d\n", __func__, rc); return rc; } @@ -906,7 +906,7 @@ static int hwrm_cfa_encap_record_alloc(struct bnxt *bp, resp = bnxt_get_hwrm_resp_addr(bp, &req); *encap_record_handle = resp->encap_record_id; } else { - netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc); + netdev_info(bp->dev, "%s: Error rc=%d\n", __func__, rc); } mutex_unlock(&bp->hwrm_cmd_lock); @@ -924,7 +924,7 @@ static int hwrm_cfa_encap_record_free(struct bnxt *bp, rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (rc) - netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc); + netdev_info(bp->dev, "%s: Error rc=%d\n", __func__, rc); return rc; } @@ -943,7 +943,7 @@ static int bnxt_tc_put_l2_node(struct bnxt *bp, tc_info->l2_ht_params); if (rc) netdev_err(bp->dev, - "Error: %s: rhashtable_remove_fast: %d", + "Error: %s: rhashtable_remove_fast: %d\n", __func__, rc); kfree_rcu(l2_node, rcu); } @@ -972,7 +972,7 @@ bnxt_tc_get_l2_node(struct bnxt *bp, struct rhashtable *l2_table, if (rc) { kfree_rcu(l2_node, rcu); netdev_err(bp->dev, - "Error: %s: rhashtable_insert_fast: %d", + "Error: %s: rhashtable_insert_fast: %d\n", __func__, rc); return NULL; } @@ -1031,7 +1031,7 @@ static bool bnxt_tc_can_offload(struct bnxt *bp, struct bnxt_tc_flow *flow) if ((flow->flags & BNXT_TC_FLOW_FLAGS_PORTS) && (flow->l4_key.ip_proto != IPPROTO_TCP && flow->l4_key.ip_proto != IPPROTO_UDP)) { - netdev_info(bp->dev, "Cannot offload non-TCP/UDP (%d) ports", + netdev_info(bp->dev, "Cannot offload non-TCP/UDP (%d) ports\n", flow->l4_key.ip_proto); return false; } @@ -1088,7 +1088,7 @@ static int bnxt_tc_put_tunnel_node(struct bnxt *bp, rc = rhashtable_remove_fast(tunnel_table, &tunnel_node->node, *ht_params); if (rc) { - netdev_err(bp->dev, "rhashtable_remove_fast rc=%d", rc); + netdev_err(bp->dev, "rhashtable_remove_fast rc=%d\n", rc); rc = -1; } kfree_rcu(tunnel_node, rcu); @@ -1129,7 +1129,7 @@ bnxt_tc_get_tunnel_node(struct bnxt *bp, struct rhashtable *tunnel_table, tunnel_node->refcount++; return tunnel_node; err: - netdev_info(bp->dev, "error rc=%d", rc); + netdev_info(bp->dev, "error rc=%d\n", rc); return NULL; } @@ -1187,7 +1187,7 @@ static void bnxt_tc_put_decap_l2_node(struct bnxt *bp, &decap_l2_node->node, tc_info->decap_l2_ht_params); if (rc) - netdev_err(bp->dev, "rhashtable_remove_fast rc=%d", rc); + netdev_err(bp->dev, "rhashtable_remove_fast rc=%d\n", rc); kfree_rcu(decap_l2_node, rcu); } } @@ -1227,7 +1227,7 @@ static int bnxt_tc_resolve_tunnel_hdrs(struct bnxt *bp, rt = ip_route_output_key(dev_net(real_dst_dev), &flow); if (IS_ERR(rt)) { - netdev_info(bp->dev, "no route to %pI4b", &flow.daddr); + netdev_info(bp->dev, "no route to %pI4b\n", &flow.daddr); return -EOPNOTSUPP; } @@ -1241,7 +1241,7 @@ static int bnxt_tc_resolve_tunnel_hdrs(struct bnxt *bp, if (vlan->real_dev != real_dst_dev) { netdev_info(bp->dev, - "dst_dev(%s) doesn't use PF-if(%s)", + "dst_dev(%s) doesn't use PF-if(%s)\n", netdev_name(dst_dev), netdev_name(real_dst_dev)); rc = -EOPNOTSUPP; @@ -1253,7 +1253,7 @@ static int bnxt_tc_resolve_tunnel_hdrs(struct bnxt *bp, #endif } else if (dst_dev != real_dst_dev) { netdev_info(bp->dev, - "dst_dev(%s) for %pI4b is not PF-if(%s)", + "dst_dev(%s) for %pI4b is not PF-if(%s)\n", netdev_name(dst_dev), &flow.daddr, netdev_name(real_dst_dev)); rc = -EOPNOTSUPP; @@ -1262,7 +1262,7 @@ static int bnxt_tc_resolve_tunnel_hdrs(struct bnxt *bp, nbr = dst_neigh_lookup(&rt->dst, &flow.daddr); if (!nbr) { - netdev_info(bp->dev, "can't lookup neighbor for %pI4b", + netdev_info(bp->dev, "can't lookup neighbor for %pI4b\n", &flow.daddr); rc = -EOPNOTSUPP; goto put_rt; @@ -1472,7 +1472,7 @@ static int __bnxt_tc_del_flow(struct bnxt *bp, rc = rhashtable_remove_fast(&tc_info->flow_table, &flow_node->node, tc_info->flow_ht_params); if (rc) - netdev_err(bp->dev, "Error: %s: rhashtable_remove_fast rc=%d", + netdev_err(bp->dev, "Error: %s: rhashtable_remove_fast rc=%d\n", __func__, rc); kfree_rcu(flow_node, rcu); @@ -1587,7 +1587,7 @@ static int bnxt_tc_add_flow(struct bnxt *bp, u16 src_fid, free_node: kfree_rcu(new_node, rcu); done: - netdev_err(bp->dev, "Error: %s: cookie=0x%lx error=%d", + netdev_err(bp->dev, "Error: %s: cookie=0x%lx error=%d\n", __func__, tc_flow_cmd->cookie, rc); return rc; } @@ -1700,7 +1700,7 @@ bnxt_hwrm_cfa_flow_stats_get(struct bnxt *bp, int num_flows, le64_to_cpu(resp_bytes[i]); } } else { - netdev_info(bp->dev, "error rc=%d", rc); + netdev_info(bp->dev, "error rc=%d\n", rc); } mutex_unlock(&bp->hwrm_cmd_lock); @@ -1970,7 +1970,7 @@ static int bnxt_tc_indr_block_event(struct notifier_block *nb, bp); if (rc) netdev_info(bp->dev, - "Failed to register indirect blk: dev: %s", + "Failed to register indirect blk: dev: %s\n", netdev->name); break; case NETDEV_UNREGISTER: diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c index b010b34cdaf835fdf23eea5ffceaddce4386ec98..6f2faf81c1aead78822e81207c1213639971c248 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c @@ -43,7 +43,7 @@ static int hwrm_cfa_vfr_alloc(struct bnxt *bp, u16 vf_idx, netdev_dbg(bp->dev, "tx_cfa_action=0x%x, rx_cfa_code=0x%x", *tx_cfa_action, *rx_cfa_code); } else { - netdev_info(bp->dev, "%s error rc=%d", __func__, rc); + netdev_info(bp->dev, "%s error rc=%d\n", __func__, rc); } mutex_unlock(&bp->hwrm_cmd_lock); @@ -60,7 +60,7 @@ static int hwrm_cfa_vfr_free(struct bnxt *bp, u16 vf_idx) rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (rc) - netdev_info(bp->dev, "%s error rc=%d", __func__, rc); + netdev_info(bp->dev, "%s error rc=%d\n", __func__, rc); return rc; } @@ -465,7 +465,7 @@ static int bnxt_vf_reps_create(struct bnxt *bp) return 0; err: - netdev_info(bp->dev, "%s error=%d", __func__, rc); + netdev_info(bp->dev, "%s error=%d\n", __func__, rc); kfree(cfa_code_map); __bnxt_vf_reps_destroy(bp); return rc; @@ -488,7 +488,7 @@ int bnxt_dl_eswitch_mode_set(struct devlink *devlink, u16 mode, mutex_lock(&bp->sriov_lock); if (bp->eswitch_mode == mode) { - netdev_info(bp->dev, "already in %s eswitch mode", + netdev_info(bp->dev, "already in %s eswitch mode\n", mode == DEVLINK_ESWITCH_MODE_LEGACY ? "legacy" : "switchdev"); rc = -EINVAL; @@ -508,7 +508,7 @@ int bnxt_dl_eswitch_mode_set(struct devlink *devlink, u16 mode, } if (pci_num_vf(bp->pdev) == 0) { - netdev_info(bp->dev, "Enable VFs before setting switchdev mode"); + netdev_info(bp->dev, "Enable VFs before setting switchdev mode\n"); rc = -EPERM; goto done; } diff --git a/drivers/net/ethernet/broadcom/cnic_defs.h b/drivers/net/ethernet/broadcom/cnic_defs.h index b384997740717996485ed2ab6f8c882bba438d8d..99e2c6d4d8c3ad1cdd3f956851a99944789cb84c 100644 --- a/drivers/net/ethernet/broadcom/cnic_defs.h +++ b/drivers/net/ethernet/broadcom/cnic_defs.h @@ -543,13 +543,13 @@ struct l4_kwq_update_pg { #define L4_KWQ_UPDATE_PG_RESERVERD2_SHIFT 2 #endif #if defined(__BIG_ENDIAN) - u16 reserverd3; + u16 reserved3; u8 da0; u8 da1; #elif defined(__LITTLE_ENDIAN) u8 da1; u8 da0; - u16 reserverd3; + u16 reserved3; #endif #if defined(__BIG_ENDIAN) u8 da2; diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 6392a25301838f849241dc53448db5b476b224f8..10244941a7a604fc51f2d3182034b4a93e681ee2 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -294,6 +294,7 @@ int bcmgenet_mii_config(struct net_device *dev, bool init) */ if (priv->ext_phy) { reg = bcmgenet_ext_readl(priv, EXT_RGMII_OOB_CTRL); + reg &= ~ID_MODE_DIS; reg |= id_mode_dis; if (GENET_IS_V1(priv) || GENET_IS_V2(priv) || GENET_IS_V3(priv)) reg |= RGMII_MODE_EN_V123; diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index dbf7070fcdba26b66c54608d0e7f1bd673a3deae..a3f0f27fc79a1c3ebd6664afced137221eb257c0 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -652,6 +652,7 @@ #define MACB_CAPS_GEM_HAS_PTP 0x00000040 #define MACB_CAPS_BD_RD_PREFETCH 0x00000080 #define MACB_CAPS_NEEDS_RSTONUBR 0x00000100 +#define MACB_CAPS_MACB_IS_EMAC 0x08000000 #define MACB_CAPS_FIFO_MODE 0x10000000 #define MACB_CAPS_GIGABIT_MODE_AVAILABLE 0x20000000 #define MACB_CAPS_SG_DISABLED 0x40000000 diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 4508f0d150da95d8e838d0ead806e8ef74794cc5..2c28da1737fe4ec2c0d1579d71bb454a3cabe289 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -572,8 +572,21 @@ static void macb_mac_config(struct phylink_config *config, unsigned int mode, old_ctrl = ctrl = macb_or_gem_readl(bp, NCFGR); /* Clear all the bits we might set later */ - ctrl &= ~(GEM_BIT(GBE) | MACB_BIT(SPD) | MACB_BIT(FD) | MACB_BIT(PAE) | - GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL)); + ctrl &= ~(MACB_BIT(SPD) | MACB_BIT(FD) | MACB_BIT(PAE)); + + if (bp->caps & MACB_CAPS_MACB_IS_EMAC) { + if (state->interface == PHY_INTERFACE_MODE_RMII) + ctrl |= MACB_BIT(RM9200_RMII); + } else { + ctrl &= ~(GEM_BIT(GBE) | GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL)); + + /* We do not support MLO_PAUSE_RX yet */ + if (state->pause & MLO_PAUSE_TX) + ctrl |= MACB_BIT(PAE); + + if (state->interface == PHY_INTERFACE_MODE_SGMII) + ctrl |= GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL); + } if (state->speed == SPEED_1000) ctrl |= GEM_BIT(GBE); @@ -583,13 +596,6 @@ static void macb_mac_config(struct phylink_config *config, unsigned int mode, if (state->duplex) ctrl |= MACB_BIT(FD); - /* We do not support MLO_PAUSE_RX yet */ - if (state->pause & MLO_PAUSE_TX) - ctrl |= MACB_BIT(PAE); - - if (state->interface == PHY_INTERFACE_MODE_SGMII) - ctrl |= GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL); - /* Apply the new configuration, if any */ if (old_ctrl ^ ctrl) macb_or_gem_writel(bp, NCFGR, ctrl); @@ -608,9 +614,10 @@ static void macb_mac_link_down(struct phylink_config *config, unsigned int mode, unsigned int q; u32 ctrl; - for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) - queue_writel(queue, IDR, - bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP)); + if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC)) + for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) + queue_writel(queue, IDR, + bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP)); /* Disable Rx and Tx */ ctrl = macb_readl(bp, NCR) & ~(MACB_BIT(RE) | MACB_BIT(TE)); @@ -627,17 +634,19 @@ static void macb_mac_link_up(struct phylink_config *config, unsigned int mode, struct macb_queue *queue; unsigned int q; - macb_set_tx_clk(bp->tx_clk, bp->speed, ndev); + if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC)) { + macb_set_tx_clk(bp->tx_clk, bp->speed, ndev); - /* Initialize rings & buffers as clearing MACB_BIT(TE) in link down - * cleared the pipeline and control registers. - */ - bp->macbgem_ops.mog_init_rings(bp); - macb_init_buffers(bp); + /* Initialize rings & buffers as clearing MACB_BIT(TE) in link down + * cleared the pipeline and control registers. + */ + bp->macbgem_ops.mog_init_rings(bp); + macb_init_buffers(bp); - for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) - queue_writel(queue, IER, - bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP)); + for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) + queue_writel(queue, IER, + bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP)); + } /* Enable Rx and Tx */ macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(RE) | MACB_BIT(TE)); @@ -3790,6 +3799,10 @@ static int at91ether_open(struct net_device *dev) u32 ctl; int ret; + ret = pm_runtime_get_sync(&lp->pdev->dev); + if (ret < 0) + return ret; + /* Clear internal statistics */ ctl = macb_readl(lp, NCR); macb_writel(lp, NCR, ctl | MACB_BIT(CLRSTAT)); @@ -3854,7 +3867,7 @@ static int at91ether_close(struct net_device *dev) q->rx_buffers, q->rx_buffers_dma); q->rx_buffers = NULL; - return 0; + return pm_runtime_put(&lp->pdev->dev); } /* Transmit packet */ @@ -4037,7 +4050,6 @@ static int at91ether_init(struct platform_device *pdev) struct net_device *dev = platform_get_drvdata(pdev); struct macb *bp = netdev_priv(dev); int err; - u32 reg; bp->queues[0].bp = bp; @@ -4051,11 +4063,7 @@ static int at91ether_init(struct platform_device *pdev) macb_writel(bp, NCR, 0); - reg = MACB_BF(CLK, MACB_CLK_DIV32) | MACB_BIT(BIG); - if (bp->phy_interface == PHY_INTERFACE_MODE_RMII) - reg |= MACB_BIT(RM9200_RMII); - - macb_writel(bp, NCFGR, reg); + macb_writel(bp, NCFGR, MACB_BF(CLK, MACB_CLK_DIV32) | MACB_BIT(BIG)); return 0; } @@ -4214,7 +4222,7 @@ static const struct macb_config sama5d4_config = { }; static const struct macb_config emac_config = { - .caps = MACB_CAPS_NEEDS_RSTONUBR, + .caps = MACB_CAPS_NEEDS_RSTONUBR | MACB_CAPS_MACB_IS_EMAC, .clk_init = at91ether_clk_init, .init = at91ether_init, }; diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index 17a4110c2e4935d74e8f677ab0405fd73cec0593..8ff28ed04b7fcd0616760f91d727898d98f01f3e 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -410,10 +410,19 @@ void bgx_lmac_rx_tx_enable(int node, int bgx_idx, int lmacid, bool enable) lmac = &bgx->lmac[lmacid]; cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG); - if (enable) + if (enable) { cfg |= CMR_PKT_RX_EN | CMR_PKT_TX_EN; - else + + /* enable TX FIFO Underflow interrupt */ + bgx_reg_modify(bgx, lmacid, BGX_GMP_GMI_TXX_INT_ENA_W1S, + GMI_TXX_INT_UNDFLW); + } else { cfg &= ~(CMR_PKT_RX_EN | CMR_PKT_TX_EN); + + /* Disable TX FIFO Underflow interrupt */ + bgx_reg_modify(bgx, lmacid, BGX_GMP_GMI_TXX_INT_ENA_W1C, + GMI_TXX_INT_UNDFLW); + } bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg); if (bgx->is_rgx) @@ -1535,6 +1544,48 @@ static int bgx_init_phy(struct bgx *bgx) return bgx_init_of_phy(bgx); } +static irqreturn_t bgx_intr_handler(int irq, void *data) +{ + struct bgx *bgx = (struct bgx *)data; + u64 status, val; + int lmac; + + for (lmac = 0; lmac < bgx->lmac_count; lmac++) { + status = bgx_reg_read(bgx, lmac, BGX_GMP_GMI_TXX_INT); + if (status & GMI_TXX_INT_UNDFLW) { + pci_err(bgx->pdev, "BGX%d lmac%d UNDFLW\n", + bgx->bgx_id, lmac); + val = bgx_reg_read(bgx, lmac, BGX_CMRX_CFG); + val &= ~CMR_EN; + bgx_reg_write(bgx, lmac, BGX_CMRX_CFG, val); + val |= CMR_EN; + bgx_reg_write(bgx, lmac, BGX_CMRX_CFG, val); + } + /* clear interrupts */ + bgx_reg_write(bgx, lmac, BGX_GMP_GMI_TXX_INT, status); + } + + return IRQ_HANDLED; +} + +static void bgx_register_intr(struct pci_dev *pdev) +{ + struct bgx *bgx = pci_get_drvdata(pdev); + int ret; + + ret = pci_alloc_irq_vectors(pdev, BGX_LMAC_VEC_OFFSET, + BGX_LMAC_VEC_OFFSET, PCI_IRQ_ALL_TYPES); + if (ret < 0) { + pci_err(pdev, "Req for #%d msix vectors failed\n", + BGX_LMAC_VEC_OFFSET); + return; + } + ret = pci_request_irq(pdev, GMPX_GMI_TX_INT, bgx_intr_handler, NULL, + bgx, "BGX%d", bgx->bgx_id); + if (ret) + pci_free_irq(pdev, GMPX_GMI_TX_INT, bgx); +} + static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { int err; @@ -1550,7 +1601,7 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_drvdata(pdev, bgx); - err = pci_enable_device(pdev); + err = pcim_enable_device(pdev); if (err) { dev_err(dev, "Failed to enable PCI device\n"); pci_set_drvdata(pdev, NULL); @@ -1604,6 +1655,8 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) bgx_init_hw(bgx); + bgx_register_intr(pdev); + /* Enable all LMACs */ for (lmac = 0; lmac < bgx->lmac_count; lmac++) { err = bgx_lmac_enable(bgx, lmac); @@ -1620,6 +1673,7 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err_enable: bgx_vnic[bgx->bgx_id] = NULL; + pci_free_irq(pdev, GMPX_GMI_TX_INT, bgx); err_release_regions: pci_release_regions(pdev); err_disable_device: @@ -1637,6 +1691,8 @@ static void bgx_remove(struct pci_dev *pdev) for (lmac = 0; lmac < bgx->lmac_count; lmac++) bgx_lmac_disable(bgx, lmac); + pci_free_irq(pdev, GMPX_GMI_TX_INT, bgx); + bgx_vnic[bgx->bgx_id] = NULL; pci_release_regions(pdev); pci_disable_device(pdev); diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h index 25888706bdcd1115e2824c88df23aff273b62171..cdea4939218578cd8424ad632702ce4e00104130 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h @@ -180,6 +180,15 @@ #define BGX_GMP_GMI_TXX_BURST 0x38228 #define BGX_GMP_GMI_TXX_MIN_PKT 0x38240 #define BGX_GMP_GMI_TXX_SGMII_CTL 0x38300 +#define BGX_GMP_GMI_TXX_INT 0x38500 +#define BGX_GMP_GMI_TXX_INT_W1S 0x38508 +#define BGX_GMP_GMI_TXX_INT_ENA_W1C 0x38510 +#define BGX_GMP_GMI_TXX_INT_ENA_W1S 0x38518 +#define GMI_TXX_INT_PTP_LOST BIT_ULL(4) +#define GMI_TXX_INT_LATE_COL BIT_ULL(3) +#define GMI_TXX_INT_XSDEF BIT_ULL(2) +#define GMI_TXX_INT_XSCOL BIT_ULL(1) +#define GMI_TXX_INT_UNDFLW BIT_ULL(0) #define BGX_MSIX_VEC_0_29_ADDR 0x400000 /* +(0..29) << 4 */ #define BGX_MSIX_VEC_0_29_CTL 0x400008 diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 649842a8aa285e45eb929493fee2e40603339258..97f90edbc06831303813eb1a70db61e8c620fc34 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -5381,12 +5381,11 @@ static inline bool is_x_10g_port(const struct link_config *lc) static int cfg_queues(struct adapter *adap) { u32 avail_qsets, avail_eth_qsets, avail_uld_qsets; + u32 i, n10g = 0, qidx = 0, n1g = 0; + u32 ncpus = num_online_cpus(); u32 niqflint, neq, num_ulds; struct sge *s = &adap->sge; - u32 i, n10g = 0, qidx = 0; -#ifndef CONFIG_CHELSIO_T4_DCB - int q10g = 0; -#endif + u32 q10g = 0, q1g; /* Reduce memory usage in kdump environment, disable all offload. */ if (is_kdump_kernel() || (is_uld(adap) && t4_uld_mem_alloc(adap))) { @@ -5424,44 +5423,50 @@ static int cfg_queues(struct adapter *adap) n10g += is_x_10g_port(&adap2pinfo(adap, i)->link_cfg); avail_eth_qsets = min_t(u32, avail_qsets, MAX_ETH_QSETS); + + /* We default to 1 queue per non-10G port and up to # of cores queues + * per 10G port. + */ + if (n10g) + q10g = (avail_eth_qsets - (adap->params.nports - n10g)) / n10g; + + n1g = adap->params.nports - n10g; #ifdef CONFIG_CHELSIO_T4_DCB /* For Data Center Bridging support we need to be able to support up * to 8 Traffic Priorities; each of which will be assigned to its * own TX Queue in order to prevent Head-Of-Line Blocking. */ + q1g = 8; if (adap->params.nports * 8 > avail_eth_qsets) { dev_err(adap->pdev_dev, "DCB avail_eth_qsets=%d < %d!\n", avail_eth_qsets, adap->params.nports * 8); return -ENOMEM; } - for_each_port(adap, i) { - struct port_info *pi = adap2pinfo(adap, i); + if (adap->params.nports * ncpus < avail_eth_qsets) + q10g = max(8U, ncpus); + else + q10g = max(8U, q10g); - pi->first_qset = qidx; - pi->nqsets = is_kdump_kernel() ? 1 : 8; - qidx += pi->nqsets; - } -#else /* !CONFIG_CHELSIO_T4_DCB */ - /* We default to 1 queue per non-10G port and up to # of cores queues - * per 10G port. - */ - if (n10g) - q10g = (avail_eth_qsets - (adap->params.nports - n10g)) / n10g; - if (q10g > netif_get_num_default_rss_queues()) - q10g = netif_get_num_default_rss_queues(); + while ((q10g * n10g) > (avail_eth_qsets - n1g * q1g)) + q10g--; - if (is_kdump_kernel()) +#else /* !CONFIG_CHELSIO_T4_DCB */ + q1g = 1; + q10g = min(q10g, ncpus); +#endif /* !CONFIG_CHELSIO_T4_DCB */ + if (is_kdump_kernel()) { q10g = 1; + q1g = 1; + } for_each_port(adap, i) { struct port_info *pi = adap2pinfo(adap, i); pi->first_qset = qidx; - pi->nqsets = is_x_10g_port(&pi->link_cfg) ? q10g : 1; + pi->nqsets = is_x_10g_port(&pi->link_cfg) ? q10g : q1g; qidx += pi->nqsets; } -#endif /* !CONFIG_CHELSIO_T4_DCB */ s->ethqsets = qidx; s->max_ethqsets = qidx; /* MSI-X may lower it later */ @@ -5473,7 +5478,7 @@ static int cfg_queues(struct adapter *adap) * capped by the number of available cores. */ num_ulds = adap->num_uld + adap->num_ofld_uld; - i = min_t(u32, MAX_OFLD_QSETS, num_online_cpus()); + i = min_t(u32, MAX_OFLD_QSETS, ncpus); avail_uld_qsets = roundup(i, adap->params.nports); if (avail_qsets < num_ulds * adap->params.nports) { adap->params.offload = 0; diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index bbd7b3175f09ed35094487c3b055f3c38e08a1ce..ddf60dc9ad167d913f9d2c454aacc2da1779e947 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -2013,10 +2013,10 @@ static int enic_stop(struct net_device *netdev) napi_disable(&enic->napi[i]); netif_carrier_off(netdev); - netif_tx_disable(netdev); if (vnic_dev_get_intr_mode(enic->vdev) == VNIC_DEV_INTR_MODE_MSIX) for (i = 0; i < enic->wq_count; i++) napi_disable(&enic->napi[enic_cq_wq(enic, i)]); + netif_tx_disable(netdev); if (!enic_is_dynamic(enic) && !enic_is_sriov_vf(enic)) enic_dev_del_station_addr(enic); diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c index 1ea3372775e6daa39c300e2624f921742cb5f29e..e94ae9b94dbfceea2c44065ad58d624676b5dd8f 100644 --- a/drivers/net/ethernet/davicom/dm9000.c +++ b/drivers/net/ethernet/davicom/dm9000.c @@ -1405,6 +1405,8 @@ static struct dm9000_plat_data *dm9000_parse_dt(struct device *dev) mac_addr = of_get_mac_address(np); if (!IS_ERR(mac_addr)) ether_addr_copy(pdata->dev_addr, mac_addr); + else if (PTR_ERR(mac_addr) == -EPROBE_DEFER) + return ERR_CAST(mac_addr); return pdata; } diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index fd93d542f497b8535cba6ac7c5859a3d12e7e867..ca74a684a9040e054b03784cac603077b33bf277 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -1,4 +1,5 @@ /* Copyright 2008 - 2016 Freescale Semiconductor Inc. + * Copyright 2020 NXP * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -123,7 +124,22 @@ MODULE_PARM_DESC(tx_timeout, "The Tx timeout in ms"); #define FSL_QMAN_MAX_OAL 127 /* Default alignment for start of data in an Rx FD */ +#ifdef CONFIG_DPAA_ERRATUM_A050385 +/* aligning data start to 64 avoids DMA transaction splits, unless the buffer + * is crossing a 4k page boundary + */ +#define DPAA_FD_DATA_ALIGNMENT (fman_has_errata_a050385() ? 64 : 16) +/* aligning to 256 avoids DMA transaction splits caused by 4k page boundary + * crossings; also, all SG fragments except the last must have a size multiple + * of 256 to avoid DMA transaction splits + */ +#define DPAA_A050385_ALIGN 256 +#define DPAA_FD_RX_DATA_ALIGNMENT (fman_has_errata_a050385() ? \ + DPAA_A050385_ALIGN : 16) +#else #define DPAA_FD_DATA_ALIGNMENT 16 +#define DPAA_FD_RX_DATA_ALIGNMENT DPAA_FD_DATA_ALIGNMENT +#endif /* The DPAA requires 256 bytes reserved and mapped for the SGT */ #define DPAA_SGT_SIZE 256 @@ -158,8 +174,13 @@ MODULE_PARM_DESC(tx_timeout, "The Tx timeout in ms"); #define DPAA_PARSE_RESULTS_SIZE sizeof(struct fman_prs_result) #define DPAA_TIME_STAMP_SIZE 8 #define DPAA_HASH_RESULTS_SIZE 8 +#ifdef CONFIG_DPAA_ERRATUM_A050385 +#define DPAA_RX_PRIV_DATA_SIZE (DPAA_A050385_ALIGN - (DPAA_PARSE_RESULTS_SIZE\ + + DPAA_TIME_STAMP_SIZE + DPAA_HASH_RESULTS_SIZE)) +#else #define DPAA_RX_PRIV_DATA_SIZE (u16)(DPAA_TX_PRIV_DATA_SIZE + \ dpaa_rx_extra_headroom) +#endif #define DPAA_ETH_PCD_RXQ_NUM 128 @@ -180,7 +201,12 @@ static struct dpaa_bp *dpaa_bp_array[BM_MAX_NUM_OF_POOLS]; #define DPAA_BP_RAW_SIZE 4096 +#ifdef CONFIG_DPAA_ERRATUM_A050385 +#define dpaa_bp_size(raw_size) (SKB_WITH_OVERHEAD(raw_size) & \ + ~(DPAA_A050385_ALIGN - 1)) +#else #define dpaa_bp_size(raw_size) SKB_WITH_OVERHEAD(raw_size) +#endif static int dpaa_max_frm; @@ -1192,7 +1218,7 @@ static int dpaa_eth_init_rx_port(struct fman_port *port, struct dpaa_bp *bp, buf_prefix_content.pass_prs_result = true; buf_prefix_content.pass_hash_result = true; buf_prefix_content.pass_time_stamp = true; - buf_prefix_content.data_align = DPAA_FD_DATA_ALIGNMENT; + buf_prefix_content.data_align = DPAA_FD_RX_DATA_ALIGNMENT; rx_p = ¶ms.specific_params.rx_params; rx_p->err_fqid = errq->fqid; @@ -1662,6 +1688,8 @@ static u8 rx_csum_offload(const struct dpaa_priv *priv, const struct qm_fd *fd) return CHECKSUM_NONE; } +#define PTR_IS_ALIGNED(x, a) (IS_ALIGNED((unsigned long)(x), (a))) + /* Build a linear skb around the received buffer. * We are guaranteed there is enough room at the end of the data buffer to * accommodate the shared info area of the skb. @@ -1733,8 +1761,7 @@ static struct sk_buff *sg_fd_to_skb(const struct dpaa_priv *priv, sg_addr = qm_sg_addr(&sgt[i]); sg_vaddr = phys_to_virt(sg_addr); - WARN_ON(!IS_ALIGNED((unsigned long)sg_vaddr, - SMP_CACHE_BYTES)); + WARN_ON(!PTR_IS_ALIGNED(sg_vaddr, SMP_CACHE_BYTES)); dma_unmap_page(priv->rx_dma_dev, sg_addr, DPAA_BP_RAW_SIZE, DMA_FROM_DEVICE); @@ -2022,6 +2049,75 @@ static inline int dpaa_xmit(struct dpaa_priv *priv, return 0; } +#ifdef CONFIG_DPAA_ERRATUM_A050385 +int dpaa_a050385_wa(struct net_device *net_dev, struct sk_buff **s) +{ + struct dpaa_priv *priv = netdev_priv(net_dev); + struct sk_buff *new_skb, *skb = *s; + unsigned char *start, i; + + /* check linear buffer alignment */ + if (!PTR_IS_ALIGNED(skb->data, DPAA_A050385_ALIGN)) + goto workaround; + + /* linear buffers just need to have an aligned start */ + if (!skb_is_nonlinear(skb)) + return 0; + + /* linear data size for nonlinear skbs needs to be aligned */ + if (!IS_ALIGNED(skb_headlen(skb), DPAA_A050385_ALIGN)) + goto workaround; + + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + + /* all fragments need to have aligned start addresses */ + if (!IS_ALIGNED(skb_frag_off(frag), DPAA_A050385_ALIGN)) + goto workaround; + + /* all but last fragment need to have aligned sizes */ + if (!IS_ALIGNED(skb_frag_size(frag), DPAA_A050385_ALIGN) && + (i < skb_shinfo(skb)->nr_frags - 1)) + goto workaround; + } + + return 0; + +workaround: + /* copy all the skb content into a new linear buffer */ + new_skb = netdev_alloc_skb(net_dev, skb->len + DPAA_A050385_ALIGN - 1 + + priv->tx_headroom); + if (!new_skb) + return -ENOMEM; + + /* NET_SKB_PAD bytes already reserved, adding up to tx_headroom */ + skb_reserve(new_skb, priv->tx_headroom - NET_SKB_PAD); + + /* Workaround for DPAA_A050385 requires data start to be aligned */ + start = PTR_ALIGN(new_skb->data, DPAA_A050385_ALIGN); + if (start - new_skb->data != 0) + skb_reserve(new_skb, start - new_skb->data); + + skb_put(new_skb, skb->len); + skb_copy_bits(skb, 0, new_skb->data, skb->len); + skb_copy_header(new_skb, skb); + new_skb->dev = skb->dev; + + /* We move the headroom when we align it so we have to reset the + * network and transport header offsets relative to the new data + * pointer. The checksum offload relies on these offsets. + */ + skb_set_network_header(new_skb, skb_network_offset(skb)); + skb_set_transport_header(new_skb, skb_transport_offset(skb)); + + /* TODO: does timestamping need the result in the old skb? */ + dev_kfree_skb(skb); + *s = new_skb; + + return 0; +} +#endif + static netdev_tx_t dpaa_start_xmit(struct sk_buff *skb, struct net_device *net_dev) { @@ -2068,6 +2164,14 @@ dpaa_start_xmit(struct sk_buff *skb, struct net_device *net_dev) nonlinear = skb_is_nonlinear(skb); } +#ifdef CONFIG_DPAA_ERRATUM_A050385 + if (unlikely(fman_has_errata_a050385())) { + if (dpaa_a050385_wa(net_dev, &skb)) + goto enomem; + nonlinear = skb_is_nonlinear(skb); + } +#endif + if (nonlinear) { /* Just create a S/G fd based on the skb */ err = skb_to_sg_fd(priv, skb, &fd); @@ -2741,9 +2845,7 @@ static inline u16 dpaa_get_headroom(struct dpaa_buffer_layout *bl) headroom = (u16)(bl->priv_data_size + DPAA_PARSE_RESULTS_SIZE + DPAA_TIME_STAMP_SIZE + DPAA_HASH_RESULTS_SIZE); - return DPAA_FD_DATA_ALIGNMENT ? ALIGN(headroom, - DPAA_FD_DATA_ALIGNMENT) : - headroom; + return ALIGN(headroom, DPAA_FD_DATA_ALIGNMENT); } static int dpaa_eth_probe(struct platform_device *pdev) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 4432a59904c77772f4ca1521fc8a4904485e87d2..23c5fef2f1ad1f274fe66db138e9cb662493f4c0 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -2529,15 +2529,15 @@ fec_enet_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *ec) return -EINVAL; } - cycle = fec_enet_us_to_itr_clock(ndev, fep->rx_time_itr); + cycle = fec_enet_us_to_itr_clock(ndev, ec->rx_coalesce_usecs); if (cycle > 0xFFFF) { dev_err(dev, "Rx coalesced usec exceed hardware limitation\n"); return -EINVAL; } - cycle = fec_enet_us_to_itr_clock(ndev, fep->tx_time_itr); + cycle = fec_enet_us_to_itr_clock(ndev, ec->tx_coalesce_usecs); if (cycle > 0xFFFF) { - dev_err(dev, "Rx coalesced usec exceed hardware limitation\n"); + dev_err(dev, "Tx coalesced usec exceed hardware limitation\n"); return -EINVAL; } diff --git a/drivers/net/ethernet/freescale/fman/Kconfig b/drivers/net/ethernet/freescale/fman/Kconfig index 0139cb9042ec74cf8da79845b823f6cd96eea8eb..34150182cc35c06c65141b7104d910e6e4465ac7 100644 --- a/drivers/net/ethernet/freescale/fman/Kconfig +++ b/drivers/net/ethernet/freescale/fman/Kconfig @@ -8,3 +8,31 @@ config FSL_FMAN help Freescale Data-Path Acceleration Architecture Frame Manager (FMan) support + +config DPAA_ERRATUM_A050385 + bool + depends on ARM64 && FSL_DPAA + default y + help + DPAA FMan erratum A050385 software workaround implementation: + align buffers, data start, SG fragment length to avoid FMan DMA + splits. + FMAN DMA read or writes under heavy traffic load may cause FMAN + internal resource leak thus stopping further packet processing. + The FMAN internal queue can overflow when FMAN splits single + read or write transactions into multiple smaller transactions + such that more than 17 AXI transactions are in flight from FMAN + to interconnect. When the FMAN internal queue overflows, it can + stall further packet processing. The issue can occur with any + one of the following three conditions: + 1. FMAN AXI transaction crosses 4K address boundary (Errata + A010022) + 2. FMAN DMA address for an AXI transaction is not 16 byte + aligned, i.e. the last 4 bits of an address are non-zero + 3. Scatter Gather (SG) frames have more than one SG buffer in + the SG list and any one of the buffers, except the last + buffer in the SG list has data size that is not a multiple + of 16 bytes, i.e., other than 16, 32, 48, 64, etc. + With any one of the above three conditions present, there is + likelihood of stalled FMAN packet processing, especially under + stress with multiple ports injecting line-rate traffic. diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c index 934111def0becb5664e119b4d32bb672496c66e7..f151d6e111dd9a6dd24ab2456a3957846c449174 100644 --- a/drivers/net/ethernet/freescale/fman/fman.c +++ b/drivers/net/ethernet/freescale/fman/fman.c @@ -1,5 +1,6 @@ /* * Copyright 2008-2015 Freescale Semiconductor Inc. + * Copyright 2020 NXP * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -566,6 +567,10 @@ struct fman_cfg { u32 qmi_def_tnums_thresh; }; +#ifdef CONFIG_DPAA_ERRATUM_A050385 +static bool fman_has_err_a050385; +#endif + static irqreturn_t fman_exceptions(struct fman *fman, enum fman_exceptions exception) { @@ -2518,6 +2523,14 @@ struct fman *fman_bind(struct device *fm_dev) } EXPORT_SYMBOL(fman_bind); +#ifdef CONFIG_DPAA_ERRATUM_A050385 +bool fman_has_errata_a050385(void) +{ + return fman_has_err_a050385; +} +EXPORT_SYMBOL(fman_has_errata_a050385); +#endif + static irqreturn_t fman_err_irq(int irq, void *handle) { struct fman *fman = (struct fman *)handle; @@ -2845,6 +2858,11 @@ static struct fman *read_dts_node(struct platform_device *of_dev) goto fman_free; } +#ifdef CONFIG_DPAA_ERRATUM_A050385 + fman_has_err_a050385 = + of_property_read_bool(fm_node, "fsl,erratum-a050385"); +#endif + return fman; fman_node_put: diff --git a/drivers/net/ethernet/freescale/fman/fman.h b/drivers/net/ethernet/freescale/fman/fman.h index 935c317fa69642c9707fc583d1f34a12061b390e..f2ede1360f03a9cc1f312d84c87df854dc5f4847 100644 --- a/drivers/net/ethernet/freescale/fman/fman.h +++ b/drivers/net/ethernet/freescale/fman/fman.h @@ -1,5 +1,6 @@ /* * Copyright 2008-2015 Freescale Semiconductor Inc. + * Copyright 2020 NXP * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -398,6 +399,10 @@ u16 fman_get_max_frm(void); int fman_get_rx_extra_headroom(void); +#ifdef CONFIG_DPAA_ERRATUM_A050385 +bool fman_has_errata_a050385(void); +#endif + struct fman *fman_bind(struct device *dev); #endif /* __FM_H */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h index 1b0313900f98565b046a28610fad8cce16260ea6..d87158acdf6fd6563829ac239847544d14cc4c17 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h +++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h @@ -46,6 +46,7 @@ enum HCLGE_MBX_OPCODE { HCLGE_MBX_PUSH_VLAN_INFO, /* (PF -> VF) push port base vlan */ HCLGE_MBX_GET_MEDIA_TYPE, /* (VF -> PF) get media type */ HCLGE_MBX_PUSH_PROMISC_INFO, /* (PF -> VF) push vf promisc info */ + HCLGE_MBX_VF_UNINIT, /* (VF -> PF) vf is unintializing */ HCLGE_MBX_GET_VF_FLR_STATUS = 200, /* (M7 -> PF) get vf flr status */ HCLGE_MBX_PUSH_LINK_STATUS, /* (M7 -> PF) get port link status */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index acb796cc10d0bbe2ee701db1fabeba198a527dd6..a7f40aa1a0ea6d51b456cf4d81a6484b5a09c239 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -1711,7 +1711,7 @@ static int hns3_setup_tc(struct net_device *netdev, void *type_data) netif_dbg(h, drv, netdev, "setup tc: num_tc=%u\n", tc); return (kinfo->dcb_ops && kinfo->dcb_ops->setup_tc) ? - kinfo->dcb_ops->setup_tc(h, tc, prio_tc) : -EOPNOTSUPP; + kinfo->dcb_ops->setup_tc(h, tc ? tc : 1, prio_tc) : -EOPNOTSUPP; } static int hns3_nic_setup_tc(struct net_device *dev, enum tc_setup_type type, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index ec5f6eeb639b68b0b94020be857647701ce02ea8..d3b0cd74ecd231bd43e774a785c41363b8c6d963 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -2446,10 +2446,12 @@ static int hclge_cfg_mac_speed_dup_hw(struct hclge_dev *hdev, int speed, int hclge_cfg_mac_speed_dup(struct hclge_dev *hdev, int speed, u8 duplex) { + struct hclge_mac *mac = &hdev->hw.mac; int ret; duplex = hclge_check_speed_dup(duplex, speed); - if (hdev->hw.mac.speed == speed && hdev->hw.mac.duplex == duplex) + if (!mac->support_autoneg && mac->speed == speed && + mac->duplex == duplex) return 0; ret = hclge_cfg_mac_speed_dup_hw(hdev, speed, duplex); @@ -6113,6 +6115,9 @@ static int hclge_get_all_rules(struct hnae3_handle *handle, static void hclge_fd_get_flow_tuples(const struct flow_keys *fkeys, struct hclge_fd_rule_tuples *tuples) { +#define flow_ip6_src fkeys->addrs.v6addrs.src.in6_u.u6_addr32 +#define flow_ip6_dst fkeys->addrs.v6addrs.dst.in6_u.u6_addr32 + tuples->ether_proto = be16_to_cpu(fkeys->basic.n_proto); tuples->ip_proto = fkeys->basic.ip_proto; tuples->dst_port = be16_to_cpu(fkeys->ports.dst); @@ -6121,12 +6126,12 @@ static void hclge_fd_get_flow_tuples(const struct flow_keys *fkeys, tuples->src_ip[3] = be32_to_cpu(fkeys->addrs.v4addrs.src); tuples->dst_ip[3] = be32_to_cpu(fkeys->addrs.v4addrs.dst); } else { - memcpy(tuples->src_ip, - fkeys->addrs.v6addrs.src.in6_u.u6_addr32, - sizeof(tuples->src_ip)); - memcpy(tuples->dst_ip, - fkeys->addrs.v6addrs.dst.in6_u.u6_addr32, - sizeof(tuples->dst_ip)); + int i; + + for (i = 0; i < IPV6_SIZE; i++) { + tuples->src_ip[i] = be32_to_cpu(flow_ip6_src[i]); + tuples->dst_ip[i] = be32_to_cpu(flow_ip6_dst[i]); + } } } @@ -7740,16 +7745,27 @@ static int hclge_set_vlan_filter_ctrl(struct hclge_dev *hdev, u8 vlan_type, struct hclge_desc desc; int ret; - hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_VLAN_FILTER_CTRL, false); - + /* read current vlan filter parameter */ + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_VLAN_FILTER_CTRL, true); req = (struct hclge_vlan_filter_ctrl_cmd *)desc.data; req->vlan_type = vlan_type; - req->vlan_fe = filter_en ? fe_type : 0; req->vf_id = vf_id; + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to get vlan filter config, ret = %d.\n", ret); + return ret; + } + + /* modify and write new config parameter */ + hclge_cmd_reuse_desc(&desc, false); + req->vlan_fe = filter_en ? + (req->vlan_fe | fe_type) : (req->vlan_fe & ~fe_type); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) - dev_err(&hdev->pdev->dev, "set vlan filter fail, ret =%d.\n", + dev_err(&hdev->pdev->dev, "failed to set vlan filter, ret = %d.\n", ret); return ret; @@ -8267,6 +8283,7 @@ void hclge_rm_vport_all_vlan_table(struct hclge_vport *vport, bool is_del_list) kfree(vlan); } } + clear_bit(vport->vport_id, hdev->vf_vlan_full); } void hclge_uninit_vport_vlan_table(struct hclge_dev *hdev) @@ -8483,6 +8500,28 @@ static int hclge_set_vf_vlan_filter(struct hnae3_handle *handle, int vfid, } } +static void hclge_clear_vf_vlan(struct hclge_dev *hdev) +{ + struct hclge_vlan_info *vlan_info; + struct hclge_vport *vport; + int ret; + int vf; + + /* clear port base vlan for all vf */ + for (vf = HCLGE_VF_VPORT_START_NUM; vf < hdev->num_alloc_vport; vf++) { + vport = &hdev->vport[vf]; + vlan_info = &vport->port_base_vlan_cfg.vlan_info; + + ret = hclge_set_vlan_filter_hw(hdev, htons(ETH_P_8021Q), + vport->vport_id, + vlan_info->vlan_tag, true); + if (ret) + dev_err(&hdev->pdev->dev, + "failed to clear vf vlan for vf%d, ret = %d\n", + vf - HCLGE_VF_VPORT_START_NUM, ret); + } +} + int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto, u16 vlan_id, bool is_kill) { @@ -9834,6 +9873,13 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev) return ret; } + ret = init_mgr_tbl(hdev); + if (ret) { + dev_err(&pdev->dev, + "failed to reinit manager table, ret = %d\n", ret); + return ret; + } + ret = hclge_init_fd_config(hdev); if (ret) { dev_err(&pdev->dev, "fd table init fail, ret=%d\n", ret); @@ -9885,6 +9931,7 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev) struct hclge_mac *mac = &hdev->hw.mac; hclge_reset_vf_rate(hdev); + hclge_clear_vf_vlan(hdev); hclge_misc_affinity_teardown(hdev); hclge_state_uninit(hdev); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index a3c0822191a957fffb7d08b62432e3bbdf5e2ba3..3d850f6b1e373685dceb27dd9593b5fd488fb12f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -799,6 +799,7 @@ void hclge_mbx_handler(struct hclge_dev *hdev) hclge_get_link_mode(vport, req); break; case HCLGE_MBX_GET_VF_FLR_STATUS: + case HCLGE_MBX_VF_UNINIT: hclge_rm_vport_all_mac_table(vport, true, HCLGE_MAC_ADDR_UC); hclge_rm_vport_all_mac_table(vport, true, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index 180224eab1ca4a46c34e9c62061c7087cd22bfb4..28db13253a5e762ae373cfeaf4cb9c5412dd4c2f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -566,7 +566,7 @@ static void hclge_tm_vport_tc_info_update(struct hclge_vport *vport) */ kinfo->num_tc = vport->vport_id ? 1 : min_t(u16, vport->alloc_tqps, hdev->tm_info.num_tc); - vport->qs_offset = (vport->vport_id ? hdev->tm_info.num_tc : 0) + + vport->qs_offset = (vport->vport_id ? HNAE3_MAX_TC : 0) + (vport->vport_id ? (vport->vport_id - 1) : 0); max_rss_size = min_t(u16, hdev->rss_size_max, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index d6597206e692e2737912e40de5f2685f2d665d5f..0510d85a7f6ae6d9bce3680a98a7b194b8417163 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -2803,6 +2803,9 @@ static void hclgevf_uninit_hdev(struct hclgevf_dev *hdev) { hclgevf_state_uninit(hdev); + hclgevf_send_mbx_msg(hdev, HCLGE_MBX_VF_UNINIT, 0, NULL, 0, + false, NULL, 0); + if (test_bit(HCLGEVF_STATE_IRQ_INITED, &hdev->state)) { hclgevf_misc_irq_uninit(hdev); hclgevf_uninit_msi(hdev); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c index 6f2cf569a283cb8f53ce653d7ab2c72fb2ca0799..79b3d53f2fbfa73d89ecd1f5490072da9503c0e9 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c @@ -297,6 +297,7 @@ static int set_hw_ioctxt(struct hinic_hwdev *hwdev, unsigned int rq_depth, } hw_ioctxt.func_idx = HINIC_HWIF_FUNC_IDX(hwif); + hw_ioctxt.ppf_idx = HINIC_HWIF_PPF_IDX(hwif); hw_ioctxt.set_cmdq_depth = HW_IOCTXT_SET_CMDQ_DEPTH_DEFAULT; hw_ioctxt.cmdq_depth = 0; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h index b069045de416c582660e06b5f98db3869e09478b..66fd2340d44795bc3bc56071f801e50c26d7e1ea 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h @@ -151,8 +151,8 @@ struct hinic_cmd_hw_ioctxt { u8 lro_en; u8 rsvd3; + u8 ppf_idx; u8 rsvd4; - u8 rsvd5; u16 rq_depth; u16 rx_buf_sz_idx; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h index 517794509eb295cb0217e2df4ba43c1767ccaa9a..c7bb9ceca72cac90d85a6a11966c5771e7eee486 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h @@ -137,6 +137,7 @@ #define HINIC_HWIF_FUNC_IDX(hwif) ((hwif)->attr.func_idx) #define HINIC_HWIF_PCI_INTF(hwif) ((hwif)->attr.pci_intf_idx) #define HINIC_HWIF_PF_IDX(hwif) ((hwif)->attr.pf_idx) +#define HINIC_HWIF_PPF_IDX(hwif) ((hwif)->attr.ppf_idx) #define HINIC_FUNC_TYPE(hwif) ((hwif)->attr.func_type) #define HINIC_IS_PF(hwif) (HINIC_FUNC_TYPE(hwif) == HINIC_PF) diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h index f4a339b10b10b55c86da6080adf12b3248b58534..79091e1314181e3493c9e54760ca4671936337e1 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h @@ -94,6 +94,7 @@ struct hinic_rq { struct hinic_wq *wq; + struct cpumask affinity_mask; u32 irq; u16 msix_entry; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index 02a14f5e7fe31ddc28fe5a3720e081d5346db653..13560975c103a29438b4e00542561a4b796abb1f 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -356,7 +356,8 @@ static void hinic_enable_rss(struct hinic_dev *nic_dev) if (!num_cpus) num_cpus = num_online_cpus(); - nic_dev->num_qps = min_t(u16, nic_dev->max_qps, num_cpus); + nic_dev->num_qps = hinic_hwdev_num_qps(hwdev); + nic_dev->num_qps = min_t(u16, nic_dev->num_qps, num_cpus); nic_dev->rss_limit = nic_dev->num_qps; nic_dev->num_rss = nic_dev->num_qps; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c index 56ea6d692f1c3dda7fd329c555d1a70696c0dd1a..2695ad69fca600c469762643ebd804f6bdfade1d 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c @@ -475,7 +475,6 @@ static int rx_request_irq(struct hinic_rxq *rxq) struct hinic_hwdev *hwdev = nic_dev->hwdev; struct hinic_rq *rq = rxq->rq; struct hinic_qp *qp; - struct cpumask mask; int err; rx_add_napi(rxq); @@ -492,8 +491,8 @@ static int rx_request_irq(struct hinic_rxq *rxq) } qp = container_of(rq, struct hinic_qp, rq); - cpumask_set_cpu(qp->q_id % num_online_cpus(), &mask); - return irq_set_affinity_hint(rq->irq, &mask); + cpumask_set_cpu(qp->q_id % num_online_cpus(), &rq->affinity_mask); + return irq_set_affinity_hint(rq->irq, &rq->affinity_mask); } static void rx_free_irq(struct hinic_rxq *rxq) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index c75239d8820f9519089d2caa74fcea6ab2c02cc1..4bd33245bad625d7bffb7a7002dc776effd3e956 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2142,6 +2142,8 @@ static void __ibmvnic_reset(struct work_struct *work) { struct ibmvnic_rwi *rwi; struct ibmvnic_adapter *adapter; + bool saved_state = false; + unsigned long flags; u32 reset_state; int rc = 0; @@ -2153,17 +2155,25 @@ static void __ibmvnic_reset(struct work_struct *work) return; } - reset_state = adapter->state; - rwi = get_next_rwi(adapter); while (rwi) { + spin_lock_irqsave(&adapter->state_lock, flags); + if (adapter->state == VNIC_REMOVING || adapter->state == VNIC_REMOVED) { + spin_unlock_irqrestore(&adapter->state_lock, flags); kfree(rwi); rc = EBUSY; break; } + if (!saved_state) { + reset_state = adapter->state; + adapter->state = VNIC_RESETTING; + saved_state = true; + } + spin_unlock_irqrestore(&adapter->state_lock, flags); + if (rwi->reset_reason == VNIC_RESET_CHANGE_PARAM) { /* CHANGE_PARAM requestor holds rtnl_lock */ rc = do_change_param_reset(adapter, rwi, reset_state); @@ -5091,6 +5101,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) __ibmvnic_delayed_reset); INIT_LIST_HEAD(&adapter->rwi_list); spin_lock_init(&adapter->rwi_lock); + spin_lock_init(&adapter->state_lock); mutex_init(&adapter->fw_lock); init_completion(&adapter->init_done); init_completion(&adapter->fw_done); @@ -5163,8 +5174,17 @@ static int ibmvnic_remove(struct vio_dev *dev) { struct net_device *netdev = dev_get_drvdata(&dev->dev); struct ibmvnic_adapter *adapter = netdev_priv(netdev); + unsigned long flags; + + spin_lock_irqsave(&adapter->state_lock, flags); + if (adapter->state == VNIC_RESETTING) { + spin_unlock_irqrestore(&adapter->state_lock, flags); + return -EBUSY; + } adapter->state = VNIC_REMOVING; + spin_unlock_irqrestore(&adapter->state_lock, flags); + rtnl_lock(); unregister_netdevice(netdev); diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index 60eccaf91b122e8946595ffb807fbe977e139961..f8416e1d4cf0942fd013faa6cefa85e552fb0849 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -941,7 +941,8 @@ enum vnic_state {VNIC_PROBING = 1, VNIC_CLOSING, VNIC_CLOSED, VNIC_REMOVING, - VNIC_REMOVED}; + VNIC_REMOVED, + VNIC_RESETTING}; enum ibmvnic_reset_reason {VNIC_RESET_FAILOVER = 1, VNIC_RESET_MOBILITY, @@ -1090,4 +1091,7 @@ struct ibmvnic_adapter { struct ibmvnic_tunables desired; struct ibmvnic_tunables fallback; + + /* Used for serializatin of state field */ + spinlock_t state_lock; }; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 69523ac85639ef2204223352e86c5bedb62a9fbb..56b9e445732ba500a88edcca938a1e658104a6fe 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -2362,7 +2362,7 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg) goto error_param; } - if (i40e_vc_validate_vqs_bitmaps(vqs)) { + if (!i40e_vc_validate_vqs_bitmaps(vqs)) { aq_ret = I40E_ERR_PARAM; goto error_param; } @@ -2424,7 +2424,7 @@ static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg) goto error_param; } - if (i40e_vc_validate_vqs_bitmaps(vqs)) { + if (!i40e_vc_validate_vqs_bitmaps(vqs)) { aq_ret = I40E_ERR_PARAM; goto error_param; } diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 4459bc564b11f2bfd59831c6c881b417150cd6fe..6873998cf14547b44ef54aa926227d8f2ba7002c 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -1660,6 +1660,7 @@ struct ice_aqc_get_pkg_info_resp { __le32 count; struct ice_aqc_get_pkg_info pkg_info[1]; }; + /** * struct ice_aq_desc - Admin Queue (AQ) descriptor * @flags: ICE_AQ_FLAG_* flags diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index d8e975cceb211322dc71f7a419245a2707f0e877..81885efadc7a6472b82da6c42f1602de76526acb 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -324,7 +324,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring) if (err) return err; - dev_info(&vsi->back->pdev->dev, "Registered XDP mem model MEM_TYPE_ZERO_COPY on Rx ring %d\n", + dev_info(ice_pf_to_dev(vsi->back), "Registered XDP mem model MEM_TYPE_ZERO_COPY on Rx ring %d\n", ring->q_index); } else { ring->zca.free = NULL; @@ -405,8 +405,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring) /* Absolute queue number out of 2K needs to be passed */ err = ice_write_rxq_ctx(hw, &rlan_ctx, pf_q); if (err) { - dev_err(&vsi->back->pdev->dev, - "Failed to set LAN Rx queue context for absolute Rx queue %d error: %d\n", + dev_err(ice_pf_to_dev(vsi->back), "Failed to set LAN Rx queue context for absolute Rx queue %d error: %d\n", pf_q, err); return -EIO; } @@ -428,8 +427,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring) ice_alloc_rx_bufs_slow_zc(ring, ICE_DESC_UNUSED(ring)) : ice_alloc_rx_bufs(ring, ICE_DESC_UNUSED(ring)); if (err) - dev_info(&vsi->back->pdev->dev, - "Failed allocate some buffers on %sRx ring %d (pf_q %d)\n", + dev_info(ice_pf_to_dev(vsi->back), "Failed allocate some buffers on %sRx ring %d (pf_q %d)\n", ring->xsk_umem ? "UMEM enabled " : "", ring->q_index, pf_q); @@ -490,8 +488,7 @@ int ice_vsi_ctrl_rx_ring(struct ice_vsi *vsi, bool ena, u16 rxq_idx) /* wait for the change to finish */ ret = ice_pf_rxq_wait(pf, pf_q, ena); if (ret) - dev_err(ice_pf_to_dev(pf), - "VSI idx %d Rx ring %d %sable timeout\n", + dev_err(ice_pf_to_dev(pf), "VSI idx %d Rx ring %d %sable timeout\n", vsi->idx, pf_q, (ena ? "en" : "dis")); return ret; @@ -506,20 +503,15 @@ int ice_vsi_ctrl_rx_ring(struct ice_vsi *vsi, bool ena, u16 rxq_idx) */ int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi) { - struct ice_pf *pf = vsi->back; - int v_idx = 0, num_q_vectors; - struct device *dev; - int err; + struct device *dev = ice_pf_to_dev(vsi->back); + int v_idx, err; - dev = ice_pf_to_dev(pf); if (vsi->q_vectors[0]) { dev_dbg(dev, "VSI %d has existing q_vectors\n", vsi->vsi_num); return -EEXIST; } - num_q_vectors = vsi->num_q_vectors; - - for (v_idx = 0; v_idx < num_q_vectors; v_idx++) { + for (v_idx = 0; v_idx < vsi->num_q_vectors; v_idx++) { err = ice_vsi_alloc_q_vector(vsi, v_idx); if (err) goto err_out; @@ -648,8 +640,7 @@ ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_ring *ring, status = ice_ena_vsi_txq(vsi->port_info, vsi->idx, tc, ring->q_handle, 1, qg_buf, buf_len, NULL); if (status) { - dev_err(ice_pf_to_dev(pf), - "Failed to set LAN Tx queue context, error: %d\n", + dev_err(ice_pf_to_dev(pf), "Failed to set LAN Tx queue context, error: %d\n", status); return -ENODEV; } @@ -815,14 +806,12 @@ ice_vsi_stop_tx_ring(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, * queues at the hardware level anyway. */ if (status == ICE_ERR_RESET_ONGOING) { - dev_dbg(&vsi->back->pdev->dev, - "Reset in progress. LAN Tx queues already disabled\n"); + dev_dbg(ice_pf_to_dev(vsi->back), "Reset in progress. LAN Tx queues already disabled\n"); } else if (status == ICE_ERR_DOES_NOT_EXIST) { - dev_dbg(&vsi->back->pdev->dev, - "LAN Tx queues do not exist, nothing to disable\n"); + dev_dbg(ice_pf_to_dev(vsi->back), "LAN Tx queues do not exist, nothing to disable\n"); } else if (status) { - dev_err(&vsi->back->pdev->dev, - "Failed to disable LAN Tx queues, error: %d\n", status); + dev_err(ice_pf_to_dev(vsi->back), "Failed to disable LAN Tx queues, error: %d\n", + status); return -ENODEV; } diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 0207e28c26827c0b10f4fe3c290898cccc895286..04d5db0a25bfb521cabc435fcd489e1d8fce4d33 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -24,20 +24,6 @@ static enum ice_status ice_set_mac_type(struct ice_hw *hw) return 0; } -/** - * ice_dev_onetime_setup - Temporary HW/FW workarounds - * @hw: pointer to the HW structure - * - * This function provides temporary workarounds for certain issues - * that are expected to be fixed in the HW/FW. - */ -void ice_dev_onetime_setup(struct ice_hw *hw) -{ -#define MBX_PF_VT_PFALLOC 0x00231E80 - /* set VFs per PF */ - wr32(hw, MBX_PF_VT_PFALLOC, rd32(hw, PF_VT_PFALLOC_HIF)); -} - /** * ice_clear_pf_cfg - Clear PF configuration * @hw: pointer to the hardware structure @@ -602,10 +588,10 @@ void ice_output_fw_log(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf) } /** - * ice_get_itr_intrl_gran - determine int/intrl granularity + * ice_get_itr_intrl_gran * @hw: pointer to the HW struct * - * Determines the ITR/intrl granularities based on the maximum aggregate + * Determines the ITR/INTRL granularities based on the maximum aggregate * bandwidth according to the device's configuration during power-on. */ static void ice_get_itr_intrl_gran(struct ice_hw *hw) @@ -763,8 +749,6 @@ enum ice_status ice_init_hw(struct ice_hw *hw) if (status) goto err_unroll_sched; - ice_dev_onetime_setup(hw); - /* Get MAC information */ /* A single port can report up to two (LAN and WoL) addresses */ mac_buf = devm_kcalloc(ice_hw_to_dev(hw), 2, @@ -834,7 +818,7 @@ void ice_deinit_hw(struct ice_hw *hw) */ enum ice_status ice_check_reset(struct ice_hw *hw) { - u32 cnt, reg = 0, grst_delay; + u32 cnt, reg = 0, grst_delay, uld_mask; /* Poll for Device Active state in case a recent CORER, GLOBR, * or EMPR has occurred. The grst delay value is in 100ms units. @@ -856,13 +840,20 @@ enum ice_status ice_check_reset(struct ice_hw *hw) return ICE_ERR_RESET_FAILED; } -#define ICE_RESET_DONE_MASK (GLNVM_ULD_CORER_DONE_M | \ - GLNVM_ULD_GLOBR_DONE_M) +#define ICE_RESET_DONE_MASK (GLNVM_ULD_PCIER_DONE_M |\ + GLNVM_ULD_PCIER_DONE_1_M |\ + GLNVM_ULD_CORER_DONE_M |\ + GLNVM_ULD_GLOBR_DONE_M |\ + GLNVM_ULD_POR_DONE_M |\ + GLNVM_ULD_POR_DONE_1_M |\ + GLNVM_ULD_PCIER_DONE_2_M) + + uld_mask = ICE_RESET_DONE_MASK; /* Device is Active; check Global Reset processes are done */ for (cnt = 0; cnt < ICE_PF_RESET_WAIT_COUNT; cnt++) { - reg = rd32(hw, GLNVM_ULD) & ICE_RESET_DONE_MASK; - if (reg == ICE_RESET_DONE_MASK) { + reg = rd32(hw, GLNVM_ULD) & uld_mask; + if (reg == uld_mask) { ice_debug(hw, ICE_DBG_INIT, "Global reset processes done. %d\n", cnt); break; diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index b5c013fdaaf972ac0de3264de38fbe01e0a96c22..f9fc005d35a78dfc58b284b1be4c9a45367a2a54 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -54,8 +54,6 @@ enum ice_status ice_get_caps(struct ice_hw *hw); void ice_set_safe_mode_caps(struct ice_hw *hw); -void ice_dev_onetime_setup(struct ice_hw *hw); - enum ice_status ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx, u32 rxq_index); diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.c b/drivers/net/ethernet/intel/ice/ice_dcb.c index 713e8a892e149ec6578a889655ca71a61101fb3e..adb8dab765c8fae0a39f8c4360eedbadfb0e6715 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb.c @@ -1323,13 +1323,13 @@ enum ice_status ice_set_dcb_cfg(struct ice_port_info *pi) } /** - * ice_aq_query_port_ets - query port ets configuration + * ice_aq_query_port_ets - query port ETS configuration * @pi: port information structure * @buf: pointer to buffer * @buf_size: buffer size in bytes * @cd: pointer to command details structure or NULL * - * query current port ets configuration + * query current port ETS configuration */ static enum ice_status ice_aq_query_port_ets(struct ice_port_info *pi, @@ -1416,13 +1416,13 @@ ice_update_port_tc_tree_cfg(struct ice_port_info *pi, } /** - * ice_query_port_ets - query port ets configuration + * ice_query_port_ets - query port ETS configuration * @pi: port information structure * @buf: pointer to buffer * @buf_size: buffer size in bytes * @cd: pointer to command details structure or NULL * - * query current port ets configuration and update the + * query current port ETS configuration and update the * SW DB with the TC changes */ enum ice_status diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c index 0664e5b8d130a1c2c51b12accd7f129a0e26971c..7108fb41b604296b24d7314467ff9147122324be 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -315,9 +315,9 @@ ice_dcb_need_recfg(struct ice_pf *pf, struct ice_dcbx_cfg *old_cfg, */ void ice_dcb_rebuild(struct ice_pf *pf) { - struct ice_dcbx_cfg *local_dcbx_cfg, *desired_dcbx_cfg, *prev_cfg; struct ice_aqc_port_ets_elem buf = { 0 }; struct device *dev = ice_pf_to_dev(pf); + struct ice_dcbx_cfg *err_cfg; enum ice_status ret; ret = ice_query_port_ets(pf->hw.port_info, &buf, sizeof(buf), NULL); @@ -330,53 +330,25 @@ void ice_dcb_rebuild(struct ice_pf *pf) if (!test_bit(ICE_FLAG_DCB_ENA, pf->flags)) return; - local_dcbx_cfg = &pf->hw.port_info->local_dcbx_cfg; - desired_dcbx_cfg = &pf->hw.port_info->desired_dcbx_cfg; + mutex_lock(&pf->tc_mutex); - /* Save current willing state and force FW to unwilling */ - local_dcbx_cfg->etscfg.willing = 0x0; - local_dcbx_cfg->pfc.willing = 0x0; - local_dcbx_cfg->app_mode = ICE_DCBX_APPS_NON_WILLING; + if (!pf->hw.port_info->is_sw_lldp) + ice_cfg_etsrec_defaults(pf->hw.port_info); - ice_cfg_etsrec_defaults(pf->hw.port_info); ret = ice_set_dcb_cfg(pf->hw.port_info); if (ret) { - dev_err(dev, "Failed to set DCB to unwilling\n"); + dev_err(dev, "Failed to set DCB config in rebuild\n"); goto dcb_error; } - /* Retrieve DCB config and ensure same as current in SW */ - prev_cfg = kmemdup(local_dcbx_cfg, sizeof(*prev_cfg), GFP_KERNEL); - if (!prev_cfg) - goto dcb_error; - - ice_init_dcb(&pf->hw, true); - if (pf->hw.port_info->dcbx_status == ICE_DCBX_STATUS_DIS) - pf->hw.port_info->is_sw_lldp = true; - else - pf->hw.port_info->is_sw_lldp = false; - - if (ice_dcb_need_recfg(pf, prev_cfg, local_dcbx_cfg)) { - /* difference in cfg detected - disable DCB till next MIB */ - dev_err(dev, "Set local MIB not accurate\n"); - kfree(prev_cfg); - goto dcb_error; + if (!pf->hw.port_info->is_sw_lldp) { + ret = ice_cfg_lldp_mib_change(&pf->hw, true); + if (ret && !pf->hw.port_info->is_sw_lldp) { + dev_err(dev, "Failed to register for MIB changes\n"); + goto dcb_error; + } } - /* fetched config congruent to previous configuration */ - kfree(prev_cfg); - - /* Set the local desired config */ - if (local_dcbx_cfg->dcbx_mode == ICE_DCBX_MODE_CEE) - memcpy(local_dcbx_cfg, desired_dcbx_cfg, - sizeof(*local_dcbx_cfg)); - - ice_cfg_etsrec_defaults(pf->hw.port_info); - ret = ice_set_dcb_cfg(pf->hw.port_info); - if (ret) { - dev_err(dev, "Failed to set desired config\n"); - goto dcb_error; - } dev_info(dev, "DCB restored after reset\n"); ret = ice_query_port_ets(pf->hw.port_info, &buf, sizeof(buf), NULL); if (ret) { @@ -384,26 +356,32 @@ void ice_dcb_rebuild(struct ice_pf *pf) goto dcb_error; } + mutex_unlock(&pf->tc_mutex); + return; dcb_error: dev_err(dev, "Disabling DCB until new settings occur\n"); - prev_cfg = kzalloc(sizeof(*prev_cfg), GFP_KERNEL); - if (!prev_cfg) + err_cfg = kzalloc(sizeof(*err_cfg), GFP_KERNEL); + if (!err_cfg) { + mutex_unlock(&pf->tc_mutex); return; + } - prev_cfg->etscfg.willing = true; - prev_cfg->etscfg.tcbwtable[0] = ICE_TC_MAX_BW; - prev_cfg->etscfg.tsatable[0] = ICE_IEEE_TSA_ETS; - memcpy(&prev_cfg->etsrec, &prev_cfg->etscfg, sizeof(prev_cfg->etsrec)); + err_cfg->etscfg.willing = true; + err_cfg->etscfg.tcbwtable[0] = ICE_TC_MAX_BW; + err_cfg->etscfg.tsatable[0] = ICE_IEEE_TSA_ETS; + memcpy(&err_cfg->etsrec, &err_cfg->etscfg, sizeof(err_cfg->etsrec)); /* Coverity warns the return code of ice_pf_dcb_cfg() is not checked * here as is done for other calls to that function. That check is * not necessary since this is in this function's error cleanup path. * Suppress the Coverity warning with the following comment... */ /* coverity[check_return] */ - ice_pf_dcb_cfg(pf, prev_cfg, false); - kfree(prev_cfg); + ice_pf_dcb_cfg(pf, err_cfg, false); + kfree(err_cfg); + + mutex_unlock(&pf->tc_mutex); } /** @@ -434,9 +412,9 @@ static int ice_dcb_init_cfg(struct ice_pf *pf, bool locked) } /** - * ice_dcb_sw_default_config - Apply a default DCB config + * ice_dcb_sw_dflt_cfg - Apply a default DCB config * @pf: PF to apply config to - * @ets_willing: configure ets willing + * @ets_willing: configure ETS willing * @locked: was this function called with RTNL held */ static int ice_dcb_sw_dflt_cfg(struct ice_pf *pf, bool ets_willing, bool locked) @@ -599,8 +577,7 @@ int ice_init_pf_dcb(struct ice_pf *pf, bool locked) goto dcb_init_err; } - dev_info(dev, - "DCB is enabled in the hardware, max number of TCs supported on this port are %d\n", + dev_info(dev, "DCB is enabled in the hardware, max number of TCs supported on this port are %d\n", pf->hw.func_caps.common_cap.maxtc); if (err) { struct ice_vsi *pf_vsi; @@ -610,8 +587,8 @@ int ice_init_pf_dcb(struct ice_pf *pf, bool locked) clear_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags); err = ice_dcb_sw_dflt_cfg(pf, true, locked); if (err) { - dev_err(dev, - "Failed to set local DCB config %d\n", err); + dev_err(dev, "Failed to set local DCB config %d\n", + err); err = -EIO; goto dcb_init_err; } @@ -777,6 +754,8 @@ ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf, } } + mutex_lock(&pf->tc_mutex); + /* store the old configuration */ tmp_dcbx_cfg = pf->hw.port_info->local_dcbx_cfg; @@ -787,20 +766,20 @@ ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf, ret = ice_get_dcb_cfg(pf->hw.port_info); if (ret) { dev_err(dev, "Failed to get DCB config\n"); - return; + goto out; } /* No change detected in DCBX configs */ if (!memcmp(&tmp_dcbx_cfg, &pi->local_dcbx_cfg, sizeof(tmp_dcbx_cfg))) { dev_dbg(dev, "No change detected in DCBX configuration.\n"); - return; + goto out; } need_reconfig = ice_dcb_need_recfg(pf, &tmp_dcbx_cfg, &pi->local_dcbx_cfg); ice_dcbnl_flush_apps(pf, &tmp_dcbx_cfg, &pi->local_dcbx_cfg); if (!need_reconfig) - return; + goto out; /* Enable DCB tagging only when more than one TC */ if (ice_dcb_get_num_tc(&pi->local_dcbx_cfg) > 1) { @@ -814,7 +793,7 @@ ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf, pf_vsi = ice_get_main_vsi(pf); if (!pf_vsi) { dev_dbg(dev, "PF VSI doesn't exist\n"); - return; + goto out; } rtnl_lock(); @@ -823,13 +802,15 @@ ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf, ret = ice_query_port_ets(pf->hw.port_info, &buf, sizeof(buf), NULL); if (ret) { dev_err(dev, "Query Port ETS failed\n"); - rtnl_unlock(); - return; + goto unlock_rtnl; } /* changes in configuration update VSI */ ice_pf_dcb_recfg(pf); ice_ena_vsi(pf_vsi, true); +unlock_rtnl: rtnl_unlock(); +out: + mutex_unlock(&pf->tc_mutex); } diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c index d870c1aedc1709b79ba75a6183c80fed65a53222..b61aba428adbfa44ed2fc53f445da2a2bf4355fa 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c @@ -297,8 +297,7 @@ ice_dcbnl_get_pfc_cfg(struct net_device *netdev, int prio, u8 *setting) return; *setting = (pi->local_dcbx_cfg.pfc.pfcena >> prio) & 0x1; - dev_dbg(ice_pf_to_dev(pf), - "Get PFC Config up=%d, setting=%d, pfcenable=0x%x\n", + dev_dbg(ice_pf_to_dev(pf), "Get PFC Config up=%d, setting=%d, pfcenable=0x%x\n", prio, *setting, pi->local_dcbx_cfg.pfc.pfcena); } @@ -418,8 +417,8 @@ ice_dcbnl_get_pg_tc_cfg_tx(struct net_device *netdev, int prio, return; *pgid = pi->local_dcbx_cfg.etscfg.prio_table[prio]; - dev_dbg(ice_pf_to_dev(pf), - "Get PG config prio=%d tc=%d\n", prio, *pgid); + dev_dbg(ice_pf_to_dev(pf), "Get PG config prio=%d tc=%d\n", prio, + *pgid); } /** @@ -713,13 +712,13 @@ static int ice_dcbnl_delapp(struct net_device *netdev, struct dcb_app *app) return -EINVAL; mutex_lock(&pf->tc_mutex); - ret = dcb_ieee_delapp(netdev, app); - if (ret) - goto delapp_out; - old_cfg = &pf->hw.port_info->local_dcbx_cfg; - if (old_cfg->numapps == 1) + if (old_cfg->numapps <= 1) + goto delapp_out; + + ret = dcb_ieee_delapp(netdev, app); + if (ret) goto delapp_out; new_cfg = &pf->hw.port_info->desired_dcbx_cfg; @@ -882,8 +881,7 @@ ice_dcbnl_vsi_del_app(struct ice_vsi *vsi, sapp.protocol = app->prot_id; sapp.priority = app->priority; err = ice_dcbnl_delapp(vsi->netdev, &sapp); - dev_dbg(&vsi->back->pdev->dev, - "Deleting app for VSI idx=%d err=%d sel=%d proto=0x%x, prio=%d\n", + dev_dbg(ice_pf_to_dev(vsi->back), "Deleting app for VSI idx=%d err=%d sel=%d proto=0x%x, prio=%d\n", vsi->idx, err, app->selector, app->prot_id, app->priority); } diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 90c6a3ca20c99beb67024e9473773000b43132c5..77c412a7e7a47f4842dfd3c0ec96c3415aa39178 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -166,13 +166,24 @@ static void ice_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) { struct ice_netdev_priv *np = netdev_priv(netdev); + u8 oem_ver, oem_patch, nvm_ver_hi, nvm_ver_lo; struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; + struct ice_hw *hw = &pf->hw; + u16 oem_build; strlcpy(drvinfo->driver, KBUILD_MODNAME, sizeof(drvinfo->driver)); strlcpy(drvinfo->version, ice_drv_ver, sizeof(drvinfo->version)); - strlcpy(drvinfo->fw_version, ice_nvm_version_str(&pf->hw), - sizeof(drvinfo->fw_version)); + + /* Display NVM version (from which the firmware version can be + * determined) which contains more pertinent information. + */ + ice_get_nvm_version(hw, &oem_ver, &oem_build, &oem_patch, + &nvm_ver_hi, &nvm_ver_lo); + snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), + "%x.%02x 0x%x %d.%d.%d", nvm_ver_hi, nvm_ver_lo, + hw->nvm.eetrack, oem_ver, oem_build, oem_patch); + strlcpy(drvinfo->bus_info, pci_name(pf->pdev), sizeof(drvinfo->bus_info)); drvinfo->n_priv_flags = ICE_PRIV_FLAG_ARRAY_SIZE; @@ -363,8 +374,7 @@ static int ice_reg_pattern_test(struct ice_hw *hw, u32 reg, u32 mask) val = rd32(hw, reg); if (val == pattern) continue; - dev_err(dev, - "%s: reg pattern test failed - reg 0x%08x pat 0x%08x val 0x%08x\n" + dev_err(dev, "%s: reg pattern test failed - reg 0x%08x pat 0x%08x val 0x%08x\n" , __func__, reg, pattern, val); return 1; } @@ -372,8 +382,7 @@ static int ice_reg_pattern_test(struct ice_hw *hw, u32 reg, u32 mask) wr32(hw, reg, orig_val); val = rd32(hw, reg); if (val != orig_val) { - dev_err(dev, - "%s: reg restore test failed - reg 0x%08x orig 0x%08x val 0x%08x\n" + dev_err(dev, "%s: reg restore test failed - reg 0x%08x orig 0x%08x val 0x%08x\n" , __func__, reg, orig_val, val); return 1; } @@ -791,8 +800,7 @@ ice_self_test(struct net_device *netdev, struct ethtool_test *eth_test, set_bit(__ICE_TESTING, pf->state); if (ice_active_vfs(pf)) { - dev_warn(dev, - "Please take active VFs and Netqueues offline and restart the adapter before running NIC diagnostics\n"); + dev_warn(dev, "Please take active VFs and Netqueues offline and restart the adapter before running NIC diagnostics\n"); data[ICE_ETH_TEST_REG] = 1; data[ICE_ETH_TEST_EEPROM] = 1; data[ICE_ETH_TEST_INTR] = 1; @@ -1047,7 +1055,7 @@ ice_set_fecparam(struct net_device *netdev, struct ethtool_fecparam *fecparam) fec = ICE_FEC_NONE; break; default: - dev_warn(&vsi->back->pdev->dev, "Unsupported FEC mode: %d\n", + dev_warn(ice_pf_to_dev(vsi->back), "Unsupported FEC mode: %d\n", fecparam->fec); return -EINVAL; } @@ -1200,8 +1208,7 @@ static int ice_set_priv_flags(struct net_device *netdev, u32 flags) * events to respond to. */ if (status) - dev_info(dev, - "Failed to unreg for LLDP events\n"); + dev_info(dev, "Failed to unreg for LLDP events\n"); /* The AQ call to stop the FW LLDP agent will generate * an error if the agent is already stopped. @@ -1256,8 +1263,7 @@ static int ice_set_priv_flags(struct net_device *netdev, u32 flags) /* Register for MIB change events */ status = ice_cfg_lldp_mib_change(&pf->hw, true); if (status) - dev_dbg(dev, - "Fail to enable MIB change events\n"); + dev_dbg(dev, "Fail to enable MIB change events\n"); } } if (test_bit(ICE_FLAG_LEGACY_RX, change_flags)) { @@ -1710,291 +1716,13 @@ ice_get_settings_link_up(struct ethtool_link_ksettings *ks, { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_port_info *pi = np->vsi->port_info; - struct ethtool_link_ksettings cap_ksettings; struct ice_link_status *link_info; struct ice_vsi *vsi = np->vsi; - bool unrecog_phy_high = false; - bool unrecog_phy_low = false; link_info = &vsi->port_info->phy.link_info; - /* Initialize supported and advertised settings based on PHY settings */ - switch (link_info->phy_type_low) { - case ICE_PHY_TYPE_LOW_100BASE_TX: - ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, supported, - 100baseT_Full); - ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, advertising, - 100baseT_Full); - break; - case ICE_PHY_TYPE_LOW_100M_SGMII: - ethtool_link_ksettings_add_link_mode(ks, supported, - 100baseT_Full); - break; - case ICE_PHY_TYPE_LOW_1000BASE_T: - ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, supported, - 1000baseT_Full); - ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, advertising, - 1000baseT_Full); - break; - case ICE_PHY_TYPE_LOW_1G_SGMII: - ethtool_link_ksettings_add_link_mode(ks, supported, - 1000baseT_Full); - break; - case ICE_PHY_TYPE_LOW_1000BASE_SX: - case ICE_PHY_TYPE_LOW_1000BASE_LX: - ethtool_link_ksettings_add_link_mode(ks, supported, - 1000baseX_Full); - break; - case ICE_PHY_TYPE_LOW_1000BASE_KX: - ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, supported, - 1000baseKX_Full); - ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, advertising, - 1000baseKX_Full); - break; - case ICE_PHY_TYPE_LOW_2500BASE_T: - ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, supported, - 2500baseT_Full); - ethtool_link_ksettings_add_link_mode(ks, advertising, - 2500baseT_Full); - break; - case ICE_PHY_TYPE_LOW_2500BASE_X: - ethtool_link_ksettings_add_link_mode(ks, supported, - 2500baseX_Full); - break; - case ICE_PHY_TYPE_LOW_2500BASE_KX: - ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, supported, - 2500baseX_Full); - ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, advertising, - 2500baseX_Full); - break; - case ICE_PHY_TYPE_LOW_5GBASE_T: - case ICE_PHY_TYPE_LOW_5GBASE_KR: - ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, supported, - 5000baseT_Full); - ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, advertising, - 5000baseT_Full); - break; - case ICE_PHY_TYPE_LOW_10GBASE_T: - ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, supported, - 10000baseT_Full); - ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, advertising, - 10000baseT_Full); - break; - case ICE_PHY_TYPE_LOW_10G_SFI_DA: - case ICE_PHY_TYPE_LOW_10G_SFI_AOC_ACC: - case ICE_PHY_TYPE_LOW_10G_SFI_C2C: - ethtool_link_ksettings_add_link_mode(ks, supported, - 10000baseT_Full); - break; - case ICE_PHY_TYPE_LOW_10GBASE_SR: - ethtool_link_ksettings_add_link_mode(ks, supported, - 10000baseSR_Full); - break; - case ICE_PHY_TYPE_LOW_10GBASE_LR: - ethtool_link_ksettings_add_link_mode(ks, supported, - 10000baseLR_Full); - break; - case ICE_PHY_TYPE_LOW_10GBASE_KR_CR1: - ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, supported, - 10000baseKR_Full); - ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, advertising, - 10000baseKR_Full); - break; - case ICE_PHY_TYPE_LOW_25GBASE_T: - case ICE_PHY_TYPE_LOW_25GBASE_CR: - case ICE_PHY_TYPE_LOW_25GBASE_CR_S: - case ICE_PHY_TYPE_LOW_25GBASE_CR1: - ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, supported, - 25000baseCR_Full); - ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, advertising, - 25000baseCR_Full); - break; - case ICE_PHY_TYPE_LOW_25G_AUI_AOC_ACC: - case ICE_PHY_TYPE_LOW_25G_AUI_C2C: - ethtool_link_ksettings_add_link_mode(ks, supported, - 25000baseCR_Full); - break; - case ICE_PHY_TYPE_LOW_25GBASE_SR: - case ICE_PHY_TYPE_LOW_25GBASE_LR: - ethtool_link_ksettings_add_link_mode(ks, supported, - 25000baseSR_Full); - break; - case ICE_PHY_TYPE_LOW_25GBASE_KR: - case ICE_PHY_TYPE_LOW_25GBASE_KR1: - case ICE_PHY_TYPE_LOW_25GBASE_KR_S: - ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, supported, - 25000baseKR_Full); - ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, advertising, - 25000baseKR_Full); - break; - case ICE_PHY_TYPE_LOW_40GBASE_CR4: - ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, supported, - 40000baseCR4_Full); - ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, advertising, - 40000baseCR4_Full); - break; - case ICE_PHY_TYPE_LOW_40G_XLAUI_AOC_ACC: - case ICE_PHY_TYPE_LOW_40G_XLAUI: - ethtool_link_ksettings_add_link_mode(ks, supported, - 40000baseCR4_Full); - break; - case ICE_PHY_TYPE_LOW_40GBASE_SR4: - ethtool_link_ksettings_add_link_mode(ks, supported, - 40000baseSR4_Full); - break; - case ICE_PHY_TYPE_LOW_40GBASE_LR4: - ethtool_link_ksettings_add_link_mode(ks, supported, - 40000baseLR4_Full); - break; - case ICE_PHY_TYPE_LOW_40GBASE_KR4: - ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, supported, - 40000baseKR4_Full); - ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, advertising, - 40000baseKR4_Full); - break; - case ICE_PHY_TYPE_LOW_50GBASE_CR2: - case ICE_PHY_TYPE_LOW_50GBASE_CP: - ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, supported, - 50000baseCR2_Full); - ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, advertising, - 50000baseCR2_Full); - break; - case ICE_PHY_TYPE_LOW_50G_LAUI2_AOC_ACC: - case ICE_PHY_TYPE_LOW_50G_LAUI2: - case ICE_PHY_TYPE_LOW_50G_AUI2_AOC_ACC: - case ICE_PHY_TYPE_LOW_50G_AUI2: - case ICE_PHY_TYPE_LOW_50GBASE_SR: - case ICE_PHY_TYPE_LOW_50G_AUI1_AOC_ACC: - case ICE_PHY_TYPE_LOW_50G_AUI1: - ethtool_link_ksettings_add_link_mode(ks, supported, - 50000baseCR2_Full); - break; - case ICE_PHY_TYPE_LOW_50GBASE_KR2: - case ICE_PHY_TYPE_LOW_50GBASE_KR_PAM4: - ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, supported, - 50000baseKR2_Full); - ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, advertising, - 50000baseKR2_Full); - break; - case ICE_PHY_TYPE_LOW_50GBASE_SR2: - case ICE_PHY_TYPE_LOW_50GBASE_LR2: - case ICE_PHY_TYPE_LOW_50GBASE_FR: - case ICE_PHY_TYPE_LOW_50GBASE_LR: - ethtool_link_ksettings_add_link_mode(ks, supported, - 50000baseSR2_Full); - break; - case ICE_PHY_TYPE_LOW_100GBASE_CR4: - ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, supported, - 100000baseCR4_Full); - ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, advertising, - 100000baseCR4_Full); - break; - case ICE_PHY_TYPE_LOW_100G_CAUI4_AOC_ACC: - case ICE_PHY_TYPE_LOW_100G_CAUI4: - case ICE_PHY_TYPE_LOW_100G_AUI4_AOC_ACC: - case ICE_PHY_TYPE_LOW_100G_AUI4: - case ICE_PHY_TYPE_LOW_100GBASE_CR_PAM4: - ethtool_link_ksettings_add_link_mode(ks, supported, - 100000baseCR4_Full); - break; - case ICE_PHY_TYPE_LOW_100GBASE_CP2: - ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, supported, - 100000baseCR4_Full); - ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, advertising, - 100000baseCR4_Full); - break; - case ICE_PHY_TYPE_LOW_100GBASE_SR4: - case ICE_PHY_TYPE_LOW_100GBASE_SR2: - ethtool_link_ksettings_add_link_mode(ks, supported, - 100000baseSR4_Full); - break; - case ICE_PHY_TYPE_LOW_100GBASE_LR4: - case ICE_PHY_TYPE_LOW_100GBASE_DR: - ethtool_link_ksettings_add_link_mode(ks, supported, - 100000baseLR4_ER4_Full); - break; - case ICE_PHY_TYPE_LOW_100GBASE_KR4: - case ICE_PHY_TYPE_LOW_100GBASE_KR_PAM4: - ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, supported, - 100000baseKR4_Full); - ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, advertising, - 100000baseKR4_Full); - break; - default: - unrecog_phy_low = true; - } - - switch (link_info->phy_type_high) { - case ICE_PHY_TYPE_HIGH_100GBASE_KR2_PAM4: - ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, supported, - 100000baseKR4_Full); - ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); - ethtool_link_ksettings_add_link_mode(ks, advertising, - 100000baseKR4_Full); - break; - case ICE_PHY_TYPE_HIGH_100G_CAUI2_AOC_ACC: - case ICE_PHY_TYPE_HIGH_100G_CAUI2: - case ICE_PHY_TYPE_HIGH_100G_AUI2_AOC_ACC: - case ICE_PHY_TYPE_HIGH_100G_AUI2: - ethtool_link_ksettings_add_link_mode(ks, supported, - 100000baseCR4_Full); - break; - default: - unrecog_phy_high = true; - } - - if (unrecog_phy_low && unrecog_phy_high) { - /* if we got here and link is up something bad is afoot */ - netdev_info(netdev, - "WARNING: Unrecognized PHY_Low (0x%llx).\n", - (u64)link_info->phy_type_low); - netdev_info(netdev, - "WARNING: Unrecognized PHY_High (0x%llx).\n", - (u64)link_info->phy_type_high); - } - - /* Now that we've worked out everything that could be supported by the - * current PHY type, get what is supported by the NVM and intersect - * them to get what is truly supported - */ - memset(&cap_ksettings, 0, sizeof(cap_ksettings)); - ice_phy_type_to_ethtool(netdev, &cap_ksettings); - ethtool_intersect_link_masks(ks, &cap_ksettings); + /* Get supported and advertised settings from PHY ability with media */ + ice_phy_type_to_ethtool(netdev, ks); switch (link_info->link_speed) { case ICE_AQ_LINK_SPEED_100GB: @@ -2028,8 +1756,7 @@ ice_get_settings_link_up(struct ethtool_link_ksettings *ks, ks->base.speed = SPEED_100; break; default: - netdev_info(netdev, - "WARNING: Unrecognized link_speed (0x%x).\n", + netdev_info(netdev, "WARNING: Unrecognized link_speed (0x%x).\n", link_info->link_speed); break; } @@ -2845,13 +2572,11 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) new_tx_cnt = ALIGN(ring->tx_pending, ICE_REQ_DESC_MULTIPLE); if (new_tx_cnt != ring->tx_pending) - netdev_info(netdev, - "Requested Tx descriptor count rounded up to %d\n", + netdev_info(netdev, "Requested Tx descriptor count rounded up to %d\n", new_tx_cnt); new_rx_cnt = ALIGN(ring->rx_pending, ICE_REQ_DESC_MULTIPLE); if (new_rx_cnt != ring->rx_pending) - netdev_info(netdev, - "Requested Rx descriptor count rounded up to %d\n", + netdev_info(netdev, "Requested Rx descriptor count rounded up to %d\n", new_rx_cnt); /* if nothing to do return success */ @@ -3211,13 +2936,6 @@ ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) else return -EINVAL; - /* Tell the OS link is going down, the link will go back up when fw - * says it is ready asynchronously - */ - ice_print_link_msg(vsi, false); - netif_carrier_off(netdev); - netif_tx_stop_all_queues(netdev); - /* Set the FC mode and only restart AN if link is up */ status = ice_set_fc(pi, &aq_failures, link_up); @@ -3718,8 +3436,7 @@ ice_set_rc_coalesce(enum ice_container_type c_type, struct ethtool_coalesce *ec, if (ec->rx_coalesce_usecs_high > ICE_MAX_INTRL || (ec->rx_coalesce_usecs_high && ec->rx_coalesce_usecs_high < pf->hw.intrl_gran)) { - netdev_info(vsi->netdev, - "Invalid value, %s-usecs-high valid values are 0 (disabled), %d-%d\n", + netdev_info(vsi->netdev, "Invalid value, %s-usecs-high valid values are 0 (disabled), %d-%d\n", c_type_str, pf->hw.intrl_gran, ICE_MAX_INTRL); return -EINVAL; @@ -3737,8 +3454,7 @@ ice_set_rc_coalesce(enum ice_container_type c_type, struct ethtool_coalesce *ec, break; case ICE_TX_CONTAINER: if (ec->tx_coalesce_usecs_high) { - netdev_info(vsi->netdev, - "setting %s-usecs-high is not supported\n", + netdev_info(vsi->netdev, "setting %s-usecs-high is not supported\n", c_type_str); return -EINVAL; } @@ -3755,35 +3471,24 @@ ice_set_rc_coalesce(enum ice_container_type c_type, struct ethtool_coalesce *ec, itr_setting = rc->itr_setting & ~ICE_ITR_DYNAMIC; if (coalesce_usecs != itr_setting && use_adaptive_coalesce) { - netdev_info(vsi->netdev, - "%s interrupt throttling cannot be changed if adaptive-%s is enabled\n", + netdev_info(vsi->netdev, "%s interrupt throttling cannot be changed if adaptive-%s is enabled\n", c_type_str, c_type_str); return -EINVAL; } if (coalesce_usecs > ICE_ITR_MAX) { - netdev_info(vsi->netdev, - "Invalid value, %s-usecs range is 0-%d\n", + netdev_info(vsi->netdev, "Invalid value, %s-usecs range is 0-%d\n", c_type_str, ICE_ITR_MAX); return -EINVAL; } - /* hardware only supports an ITR granularity of 2us */ - if (coalesce_usecs % 2 != 0) { - netdev_info(vsi->netdev, - "Invalid value, %s-usecs must be even\n", - c_type_str); - return -EINVAL; - } - if (use_adaptive_coalesce) { rc->itr_setting |= ICE_ITR_DYNAMIC; } else { - /* store user facing value how it was set */ + /* save the user set usecs */ rc->itr_setting = coalesce_usecs; - /* set to static and convert to value HW understands */ - rc->target_itr = - ITR_TO_REG(ITR_REG_ALIGN(rc->itr_setting)); + /* device ITR granularity is in 2 usec increments */ + rc->target_itr = ITR_REG_ALIGN(rc->itr_setting); } return 0; @@ -3876,6 +3581,30 @@ ice_is_coalesce_param_invalid(struct net_device *netdev, return 0; } +/** + * ice_print_if_odd_usecs - print message if user tries to set odd [tx|rx]-usecs + * @netdev: netdev used for print + * @itr_setting: previous user setting + * @use_adaptive_coalesce: if adaptive coalesce is enabled or being enabled + * @coalesce_usecs: requested value of [tx|rx]-usecs + * @c_type_str: either "rx" or "tx" to match user set field of [tx|rx]-usecs + */ +static void +ice_print_if_odd_usecs(struct net_device *netdev, u16 itr_setting, + u32 use_adaptive_coalesce, u32 coalesce_usecs, + const char *c_type_str) +{ + if (use_adaptive_coalesce) + return; + + itr_setting = ITR_TO_REG(itr_setting); + + if (itr_setting != coalesce_usecs && (coalesce_usecs % 2)) + netdev_info(netdev, "User set %s-usecs to %d, device only supports even values. Rounding down and attempting to set %s-usecs to %d\n", + c_type_str, coalesce_usecs, c_type_str, + ITR_REG_ALIGN(coalesce_usecs)); +} + /** * __ice_set_coalesce - set ITR/INTRL values for the device * @netdev: pointer to the netdev associated with this query @@ -3896,8 +3625,19 @@ __ice_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec, return -EINVAL; if (q_num < 0) { + struct ice_q_vector *q_vector = vsi->q_vectors[0]; int v_idx; + if (q_vector) { + ice_print_if_odd_usecs(netdev, q_vector->rx.itr_setting, + ec->use_adaptive_rx_coalesce, + ec->rx_coalesce_usecs, "rx"); + + ice_print_if_odd_usecs(netdev, q_vector->tx.itr_setting, + ec->use_adaptive_tx_coalesce, + ec->tx_coalesce_usecs, "tx"); + } + ice_for_each_q_vector(vsi, v_idx) { /* In some cases if DCB is configured the num_[rx|tx]q * can be less than vsi->num_q_vectors. This check @@ -4012,8 +3752,7 @@ ice_get_module_info(struct net_device *netdev, } break; default: - netdev_warn(netdev, - "SFF Module Type not recognized.\n"); + netdev_warn(netdev, "SFF Module Type not recognized.\n"); return -EINVAL; } return 0; @@ -4081,11 +3820,11 @@ ice_get_module_eeprom(struct net_device *netdev, static const struct ethtool_ops ice_ethtool_ops = { .get_link_ksettings = ice_get_link_ksettings, .set_link_ksettings = ice_set_link_ksettings, - .get_drvinfo = ice_get_drvinfo, - .get_regs_len = ice_get_regs_len, - .get_regs = ice_get_regs, - .get_msglevel = ice_get_msglevel, - .set_msglevel = ice_set_msglevel, + .get_drvinfo = ice_get_drvinfo, + .get_regs_len = ice_get_regs_len, + .get_regs = ice_get_regs, + .get_msglevel = ice_get_msglevel, + .set_msglevel = ice_set_msglevel, .self_test = ice_self_test, .get_link = ethtool_op_get_link, .get_eeprom_len = ice_get_eeprom_len, @@ -4112,8 +3851,8 @@ static const struct ethtool_ops ice_ethtool_ops = { .get_channels = ice_get_channels, .set_channels = ice_set_channels, .get_ts_info = ethtool_op_get_ts_info, - .get_per_queue_coalesce = ice_get_per_q_coalesce, - .set_per_queue_coalesce = ice_set_per_q_coalesce, + .get_per_queue_coalesce = ice_get_per_q_coalesce, + .set_per_queue_coalesce = ice_set_per_q_coalesce, .get_fecparam = ice_get_fecparam, .set_fecparam = ice_set_fecparam, .get_module_info = ice_get_module_info, diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index f2cababf256130a1de99d6f5900ba830426fbf75..6db3d0494127638098a7a4a2c02b8f15939d31a8 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -267,8 +267,14 @@ #define GLNVM_GENS_SR_SIZE_S 5 #define GLNVM_GENS_SR_SIZE_M ICE_M(0x7, 5) #define GLNVM_ULD 0x000B6008 +#define GLNVM_ULD_PCIER_DONE_M BIT(0) +#define GLNVM_ULD_PCIER_DONE_1_M BIT(1) #define GLNVM_ULD_CORER_DONE_M BIT(3) #define GLNVM_ULD_GLOBR_DONE_M BIT(4) +#define GLNVM_ULD_POR_DONE_M BIT(5) +#define GLNVM_ULD_POR_DONE_1_M BIT(8) +#define GLNVM_ULD_PCIER_DONE_2_M BIT(9) +#define GLNVM_ULD_PE_DONE_M BIT(10) #define GLPCI_CNF2 0x000BE004 #define GLPCI_CNF2_CACHELINE_SIZE_M BIT(1) #define PF_FUNC_RID 0x0009E880 @@ -331,7 +337,6 @@ #define GLV_TEPC(_VSI) (0x00312000 + ((_VSI) * 4)) #define GLV_UPRCL(_i) (0x003B2000 + ((_i) * 8)) #define GLV_UPTCL(_i) (0x0030A000 + ((_i) * 8)) -#define PF_VT_PFALLOC_HIF 0x0009DD80 #define VSIQF_HKEY_MAX_INDEX 12 #define VSIQF_HLUT_MAX_INDEX 15 #define VFINT_DYN_CTLN(_i) (0x00003800 + ((_i) * 4)) diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 1874c9f51a3223a6c2585b333f59528b38672c43..d974e2fa3e63816a3e35030fb2618abaea434294 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -117,8 +117,7 @@ static void ice_vsi_set_num_desc(struct ice_vsi *vsi) vsi->num_tx_desc = ICE_DFLT_NUM_TX_DESC; break; default: - dev_dbg(&vsi->back->pdev->dev, - "Not setting number of Tx/Rx descriptors for VSI type %d\n", + dev_dbg(ice_pf_to_dev(vsi->back), "Not setting number of Tx/Rx descriptors for VSI type %d\n", vsi->type); break; } @@ -724,7 +723,7 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) vsi->num_txq = tx_count; if (vsi->type == ICE_VSI_VF && vsi->num_txq != vsi->num_rxq) { - dev_dbg(&vsi->back->pdev->dev, "VF VSI should have same number of Tx and Rx queues. Hence making them equal\n"); + dev_dbg(ice_pf_to_dev(vsi->back), "VF VSI should have same number of Tx and Rx queues. Hence making them equal\n"); /* since there is a chance that num_rxq could have been changed * in the above for loop, make num_txq equal to num_rxq. */ @@ -929,8 +928,7 @@ static int ice_vsi_setup_vector_base(struct ice_vsi *vsi) vsi->base_vector = ice_get_res(pf, pf->irq_tracker, num_q_vectors, vsi->idx); if (vsi->base_vector < 0) { - dev_err(dev, - "Failed to get tracking for %d vectors for VSI %d, err=%d\n", + dev_err(dev, "Failed to get tracking for %d vectors for VSI %d, err=%d\n", num_q_vectors, vsi->vsi_num, vsi->base_vector); return -ENOENT; } @@ -1232,8 +1230,9 @@ static void ice_vsi_set_rss_flow_fld(struct ice_vsi *vsi) * * Returns 0 on success or ENOMEM on failure. */ -int ice_add_mac_to_list(struct ice_vsi *vsi, struct list_head *add_list, - const u8 *macaddr) +int +ice_add_mac_to_list(struct ice_vsi *vsi, struct list_head *add_list, + const u8 *macaddr) { struct ice_fltr_list_entry *tmp; struct ice_pf *pf = vsi->back; @@ -1392,12 +1391,10 @@ int ice_vsi_kill_vlan(struct ice_vsi *vsi, u16 vid) status = ice_remove_vlan(&pf->hw, &tmp_add_list); if (status == ICE_ERR_DOES_NOT_EXIST) { - dev_dbg(dev, - "Failed to remove VLAN %d on VSI %i, it does not exist, status: %d\n", + dev_dbg(dev, "Failed to remove VLAN %d on VSI %i, it does not exist, status: %d\n", vid, vsi->vsi_num, status); } else if (status) { - dev_err(dev, - "Error removing VLAN %d on vsi %i error: %d\n", + dev_err(dev, "Error removing VLAN %d on vsi %i error: %d\n", vid, vsi->vsi_num, status); err = -EIO; } @@ -1453,8 +1450,7 @@ int ice_vsi_cfg_rxqs(struct ice_vsi *vsi) err = ice_setup_rx_ctx(vsi->rx_rings[i]); if (err) { - dev_err(&vsi->back->pdev->dev, - "ice_setup_rx_ctx failed for RxQ %d, err %d\n", + dev_err(ice_pf_to_dev(vsi->back), "ice_setup_rx_ctx failed for RxQ %d, err %d\n", i, err); return err; } @@ -1623,7 +1619,7 @@ int ice_vsi_manage_vlan_insertion(struct ice_vsi *vsi) status = ice_update_vsi(hw, vsi->idx, ctxt, NULL); if (status) { - dev_err(&vsi->back->pdev->dev, "update VSI for VLAN insert failed, err %d aq_err %d\n", + dev_err(ice_pf_to_dev(vsi->back), "update VSI for VLAN insert failed, err %d aq_err %d\n", status, hw->adminq.sq_last_status); ret = -EIO; goto out; @@ -1669,7 +1665,7 @@ int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena) status = ice_update_vsi(hw, vsi->idx, ctxt, NULL); if (status) { - dev_err(&vsi->back->pdev->dev, "update VSI for VLAN strip failed, ena = %d err %d aq_err %d\n", + dev_err(ice_pf_to_dev(vsi->back), "update VSI for VLAN strip failed, ena = %d err %d aq_err %d\n", ena, status, hw->adminq.sq_last_status); ret = -EIO; goto out; @@ -1834,8 +1830,7 @@ ice_vsi_set_q_vectors_reg_idx(struct ice_vsi *vsi) struct ice_q_vector *q_vector = vsi->q_vectors[i]; if (!q_vector) { - dev_err(&vsi->back->pdev->dev, - "Failed to set reg_idx on q_vector %d VSI %d\n", + dev_err(ice_pf_to_dev(vsi->back), "Failed to set reg_idx on q_vector %d VSI %d\n", i, vsi->vsi_num); goto clear_reg_idx; } @@ -1898,8 +1893,7 @@ ice_vsi_add_rem_eth_mac(struct ice_vsi *vsi, bool add_rule) status = ice_remove_eth_mac(&pf->hw, &tmp_add_list); if (status) - dev_err(dev, - "Failure Adding or Removing Ethertype on VSI %i error: %d\n", + dev_err(dev, "Failure Adding or Removing Ethertype on VSI %i error: %d\n", vsi->vsi_num, status); ice_free_fltr_list(dev, &tmp_add_list); @@ -2384,8 +2378,7 @@ ice_get_res(struct ice_pf *pf, struct ice_res_tracker *res, u16 needed, u16 id) return -EINVAL; if (!needed || needed > res->num_entries || id >= ICE_RES_VALID_BIT) { - dev_err(ice_pf_to_dev(pf), - "param err: needed=%d, num_entries = %d id=0x%04x\n", + dev_err(ice_pf_to_dev(pf), "param err: needed=%d, num_entries = %d id=0x%04x\n", needed, res->num_entries, id); return -EINVAL; } @@ -2686,7 +2679,6 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) ice_vsi_put_qs(vsi); ice_vsi_clear_rings(vsi); ice_vsi_free_arrays(vsi); - ice_dev_onetime_setup(&pf->hw); if (vsi->type == ICE_VSI_VF) ice_vsi_set_num_qs(vsi, vf->vf_id); else @@ -2765,8 +2757,7 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) status = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc, max_txqs); if (status) { - dev_err(ice_pf_to_dev(pf), - "VSI %d failed lan queue config, error %d\n", + dev_err(ice_pf_to_dev(pf), "VSI %d failed lan queue config, error %d\n", vsi->vsi_num, status); if (init_vsi) { ret = -EIO; @@ -2834,8 +2825,8 @@ static void ice_vsi_update_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctx) int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc) { u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; - struct ice_vsi_ctx *ctx; struct ice_pf *pf = vsi->back; + struct ice_vsi_ctx *ctx; enum ice_status status; struct device *dev; int i, ret = 0; @@ -2891,25 +2882,6 @@ int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc) } #endif /* CONFIG_DCB */ -/** - * ice_nvm_version_str - format the NVM version strings - * @hw: ptr to the hardware info - */ -char *ice_nvm_version_str(struct ice_hw *hw) -{ - u8 oem_ver, oem_patch, ver_hi, ver_lo; - static char buf[ICE_NVM_VER_LEN]; - u16 oem_build; - - ice_get_nvm_version(hw, &oem_ver, &oem_build, &oem_patch, &ver_hi, - &ver_lo); - - snprintf(buf, sizeof(buf), "%x.%02x 0x%x %d.%d.%d", ver_hi, ver_lo, - hw->nvm.eetrack, oem_ver, oem_build, oem_patch); - - return buf; -} - /** * ice_update_ring_stats - Update ring statistics * @ring: ring to update @@ -2981,7 +2953,7 @@ ice_vsi_cfg_mac_fltr(struct ice_vsi *vsi, const u8 *macaddr, bool set) status = ice_remove_mac(&vsi->back->hw, &tmp_add_list); cfg_mac_fltr_exit: - ice_free_fltr_list(&vsi->back->pdev->dev, &tmp_add_list); + ice_free_fltr_list(ice_pf_to_dev(vsi->back), &tmp_add_list); return status; } @@ -3043,16 +3015,14 @@ int ice_set_dflt_vsi(struct ice_sw *sw, struct ice_vsi *vsi) /* another VSI is already the default VSI for this switch */ if (ice_is_dflt_vsi_in_use(sw)) { - dev_err(dev, - "Default forwarding VSI %d already in use, disable it and try again\n", + dev_err(dev, "Default forwarding VSI %d already in use, disable it and try again\n", sw->dflt_vsi->vsi_num); return -EEXIST; } status = ice_cfg_dflt_vsi(&vsi->back->hw, vsi->idx, true, ICE_FLTR_RX); if (status) { - dev_err(dev, - "Failed to set VSI %d as the default forwarding VSI, error %d\n", + dev_err(dev, "Failed to set VSI %d as the default forwarding VSI, error %d\n", vsi->vsi_num, status); return -EIO; } @@ -3091,8 +3061,7 @@ int ice_clear_dflt_vsi(struct ice_sw *sw) status = ice_cfg_dflt_vsi(&dflt_vsi->back->hw, dflt_vsi->idx, false, ICE_FLTR_RX); if (status) { - dev_err(dev, - "Failed to clear the default forwarding VSI %d, error %d\n", + dev_err(dev, "Failed to clear the default forwarding VSI %d, error %d\n", dflt_vsi->vsi_num, status); return -EIO; } diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index 68fd0d4505c26c6b200e1cb6ed3ac8625028611d..e2c0dadce9204d8310128198c0d41f461a10a159 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -97,8 +97,6 @@ void ice_vsi_cfg_frame_size(struct ice_vsi *vsi); u32 ice_intrl_usec_to_reg(u8 intrl, u8 gran); -char *ice_nvm_version_str(struct ice_hw *hw); - enum ice_status ice_vsi_cfg_mac_fltr(struct ice_vsi *vsi, const u8 *macaddr, bool set); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 5ae671609f98a0ac532ef5f967d7ab0b0ca8a203..5ef28052c0f8be19636a93b4a7ba7b0fca2bdb65 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -162,8 +162,7 @@ static int ice_init_mac_fltr(struct ice_pf *pf) * had an error */ if (status && vsi->netdev->reg_state == NETREG_REGISTERED) { - dev_err(ice_pf_to_dev(pf), - "Could not add MAC filters error %d. Unregistering device\n", + dev_err(ice_pf_to_dev(pf), "Could not add MAC filters error %d. Unregistering device\n", status); unregister_netdev(vsi->netdev); free_netdev(vsi->netdev); @@ -269,7 +268,7 @@ static int ice_cfg_promisc(struct ice_vsi *vsi, u8 promisc_m, bool set_promisc) */ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) { - struct device *dev = &vsi->back->pdev->dev; + struct device *dev = ice_pf_to_dev(vsi->back); struct net_device *netdev = vsi->netdev; bool promisc_forced_on = false; struct ice_pf *pf = vsi->back; @@ -335,8 +334,7 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) !test_and_set_bit(__ICE_FLTR_OVERFLOW_PROMISC, vsi->state)) { promisc_forced_on = true; - netdev_warn(netdev, - "Reached MAC filter limit, forcing promisc mode on VSI %d\n", + netdev_warn(netdev, "Reached MAC filter limit, forcing promisc mode on VSI %d\n", vsi->vsi_num); } else { err = -EIO; @@ -382,8 +380,7 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) if (!ice_is_dflt_vsi_in_use(pf->first_sw)) { err = ice_set_dflt_vsi(pf->first_sw, vsi); if (err && err != -EEXIST) { - netdev_err(netdev, - "Error %d setting default VSI %i Rx rule\n", + netdev_err(netdev, "Error %d setting default VSI %i Rx rule\n", err, vsi->vsi_num); vsi->current_netdev_flags &= ~IFF_PROMISC; @@ -395,8 +392,7 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) if (ice_is_vsi_dflt_vsi(pf->first_sw, vsi)) { err = ice_clear_dflt_vsi(pf->first_sw); if (err) { - netdev_err(netdev, - "Error %d clearing default VSI %i Rx rule\n", + netdev_err(netdev, "Error %d clearing default VSI %i Rx rule\n", err, vsi->vsi_num); vsi->current_netdev_flags |= IFF_PROMISC; @@ -752,7 +748,7 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup) kfree(caps); done: - netdev_info(vsi->netdev, "NIC Link is up %sbps, Requested FEC: %s, FEC: %s, Autoneg: %s, Flow Control: %s\n", + netdev_info(vsi->netdev, "NIC Link is up %sbps Full Duplex, Requested FEC: %s, Negotiated FEC: %s, Autoneg: %s, Flow Control: %s\n", speed, fec_req, fec, an, fc); ice_print_topo_conflict(vsi); } @@ -815,8 +811,7 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up, */ result = ice_update_link_info(pi); if (result) - dev_dbg(dev, - "Failed to update link status and re-enable link events for port %d\n", + dev_dbg(dev, "Failed to update link status and re-enable link events for port %d\n", pi->lport); /* if the old link up/down and speed is the same as the new */ @@ -834,13 +829,13 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up, result = ice_aq_set_link_restart_an(pi, false, NULL); if (result) { - dev_dbg(dev, - "Failed to set link down, VSI %d error %d\n", + dev_dbg(dev, "Failed to set link down, VSI %d error %d\n", vsi->vsi_num, result); return result; } } + ice_dcb_rebuild(pf); ice_vsi_link_event(vsi, link_up); ice_print_link_msg(vsi, link_up); @@ -892,15 +887,13 @@ static int ice_init_link_events(struct ice_port_info *pi) ICE_AQ_LINK_EVENT_MODULE_QUAL_FAIL)); if (ice_aq_set_event_mask(pi->hw, pi->lport, mask, NULL)) { - dev_dbg(ice_hw_to_dev(pi->hw), - "Failed to set link event mask for port %d\n", + dev_dbg(ice_hw_to_dev(pi->hw), "Failed to set link event mask for port %d\n", pi->lport); return -EIO; } if (ice_aq_get_link_info(pi, true, NULL, NULL)) { - dev_dbg(ice_hw_to_dev(pi->hw), - "Failed to enable link events for port %d\n", + dev_dbg(ice_hw_to_dev(pi->hw), "Failed to enable link events for port %d\n", pi->lport); return -EIO; } @@ -929,8 +922,8 @@ ice_handle_link_event(struct ice_pf *pf, struct ice_rq_event_info *event) !!(link_data->link_info & ICE_AQ_LINK_UP), le16_to_cpu(link_data->link_speed)); if (status) - dev_dbg(ice_pf_to_dev(pf), - "Could not process link event, error %d\n", status); + dev_dbg(ice_pf_to_dev(pf), "Could not process link event, error %d\n", + status); return status; } @@ -979,13 +972,11 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type) dev_dbg(dev, "%s Receive Queue VF Error detected\n", qtype); if (val & PF_FW_ARQLEN_ARQOVFL_M) { - dev_dbg(dev, - "%s Receive Queue Overflow Error detected\n", + dev_dbg(dev, "%s Receive Queue Overflow Error detected\n", qtype); } if (val & PF_FW_ARQLEN_ARQCRIT_M) - dev_dbg(dev, - "%s Receive Queue Critical Error detected\n", + dev_dbg(dev, "%s Receive Queue Critical Error detected\n", qtype); val &= ~(PF_FW_ARQLEN_ARQVFE_M | PF_FW_ARQLEN_ARQOVFL_M | PF_FW_ARQLEN_ARQCRIT_M); @@ -998,8 +989,8 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type) PF_FW_ATQLEN_ATQCRIT_M)) { oldval = val; if (val & PF_FW_ATQLEN_ATQVFE_M) - dev_dbg(dev, - "%s Send Queue VF Error detected\n", qtype); + dev_dbg(dev, "%s Send Queue VF Error detected\n", + qtype); if (val & PF_FW_ATQLEN_ATQOVFL_M) { dev_dbg(dev, "%s Send Queue Overflow Error detected\n", qtype); @@ -1048,8 +1039,7 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type) ice_dcb_process_lldp_set_mib_change(pf, &event); break; default: - dev_dbg(dev, - "%s Receive Queue unknown event 0x%04x ignored\n", + dev_dbg(dev, "%s Receive Queue unknown event 0x%04x ignored\n", qtype, opcode); break; } @@ -1238,7 +1228,7 @@ static void ice_handle_mdd_event(struct ice_pf *pf) u16 queue = ((reg & GL_MDET_TX_TCLAN_QNUM_M) >> GL_MDET_TX_TCLAN_QNUM_S); - if (netif_msg_rx_err(pf)) + if (netif_msg_tx_err(pf)) dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n", event, queue, pf_num, vf_num); wr32(hw, GL_MDET_TX_TCLAN, 0xffffffff); @@ -1335,8 +1325,7 @@ static void ice_handle_mdd_event(struct ice_pf *pf) vf->num_mdd_events++; if (vf->num_mdd_events && vf->num_mdd_events <= ICE_MDD_EVENTS_THRESHOLD) - dev_info(dev, - "VF %d has had %llu MDD events since last boot, Admin might need to reload AVF driver with this number of events\n", + dev_info(dev, "VF %d has had %llu MDD events since last boot, Admin might need to reload AVF driver with this number of events\n", i, vf->num_mdd_events); } } @@ -1367,7 +1356,7 @@ static int ice_force_phys_link_state(struct ice_vsi *vsi, bool link_up) if (vsi->type != ICE_VSI_PF) return 0; - dev = &vsi->back->pdev->dev; + dev = ice_pf_to_dev(vsi->back); pi = vsi->port_info; @@ -1378,8 +1367,7 @@ static int ice_force_phys_link_state(struct ice_vsi *vsi, bool link_up) retcode = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_SW_CFG, pcaps, NULL); if (retcode) { - dev_err(dev, - "Failed to get phy capabilities, VSI %d error %d\n", + dev_err(dev, "Failed to get phy capabilities, VSI %d error %d\n", vsi->vsi_num, retcode); retcode = -EIO; goto out; @@ -1649,8 +1637,8 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename) err = devm_request_irq(dev, irq_num, vsi->irq_handler, 0, q_vector->name, q_vector); if (err) { - netdev_err(vsi->netdev, - "MSIX request_irq failed, error: %d\n", err); + netdev_err(vsi->netdev, "MSIX request_irq failed, error: %d\n", + err); goto free_q_irqs; } @@ -1685,7 +1673,7 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename) */ static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi) { - struct device *dev = &vsi->back->pdev->dev; + struct device *dev = ice_pf_to_dev(vsi->back); int i; for (i = 0; i < vsi->num_xdp_txq; i++) { @@ -2664,14 +2652,12 @@ static void ice_set_pf_caps(struct ice_pf *pf) clear_bit(ICE_FLAG_DCB_CAPABLE, pf->flags); if (func_caps->common_cap.dcb) set_bit(ICE_FLAG_DCB_CAPABLE, pf->flags); -#ifdef CONFIG_PCI_IOV clear_bit(ICE_FLAG_SRIOV_CAPABLE, pf->flags); if (func_caps->common_cap.sr_iov_1_1) { set_bit(ICE_FLAG_SRIOV_CAPABLE, pf->flags); pf->num_vfs_supported = min_t(int, func_caps->num_allocd_vfs, ICE_MAX_VF_COUNT); } -#endif /* CONFIG_PCI_IOV */ clear_bit(ICE_FLAG_RSS_ENA, pf->flags); if (func_caps->common_cap.rss_table_size) set_bit(ICE_FLAG_RSS_ENA, pf->flags); @@ -2764,8 +2750,7 @@ static int ice_ena_msix_range(struct ice_pf *pf) } if (v_actual < v_budget) { - dev_warn(dev, - "not enough OS MSI-X vectors. requested = %d, obtained = %d\n", + dev_warn(dev, "not enough OS MSI-X vectors. requested = %d, obtained = %d\n", v_budget, v_actual); /* 2 vectors for LAN (traffic + OICR) */ #define ICE_MIN_LAN_VECS 2 @@ -2787,8 +2772,7 @@ static int ice_ena_msix_range(struct ice_pf *pf) goto exit_err; no_hw_vecs_left_err: - dev_err(dev, - "not enough device MSI-X vectors. requested = %d, available = %d\n", + dev_err(dev, "not enough device MSI-X vectors. requested = %d, available = %d\n", needed, v_left); err = -ERANGE; exit_err: @@ -2921,16 +2905,14 @@ ice_log_pkg_init(struct ice_hw *hw, enum ice_status *status) !memcmp(hw->pkg_name, hw->active_pkg_name, sizeof(hw->pkg_name))) { if (hw->pkg_dwnld_status == ICE_AQ_RC_EEXIST) - dev_info(dev, - "DDP package already present on device: %s version %d.%d.%d.%d\n", + dev_info(dev, "DDP package already present on device: %s version %d.%d.%d.%d\n", hw->active_pkg_name, hw->active_pkg_ver.major, hw->active_pkg_ver.minor, hw->active_pkg_ver.update, hw->active_pkg_ver.draft); else - dev_info(dev, - "The DDP package was successfully loaded: %s version %d.%d.%d.%d\n", + dev_info(dev, "The DDP package was successfully loaded: %s version %d.%d.%d.%d\n", hw->active_pkg_name, hw->active_pkg_ver.major, hw->active_pkg_ver.minor, @@ -2938,8 +2920,7 @@ ice_log_pkg_init(struct ice_hw *hw, enum ice_status *status) hw->active_pkg_ver.draft); } else if (hw->active_pkg_ver.major != ICE_PKG_SUPP_VER_MAJ || hw->active_pkg_ver.minor != ICE_PKG_SUPP_VER_MNR) { - dev_err(dev, - "The device has a DDP package that is not supported by the driver. The device has package '%s' version %d.%d.x.x. The driver requires version %d.%d.x.x. Entering Safe Mode.\n", + dev_err(dev, "The device has a DDP package that is not supported by the driver. The device has package '%s' version %d.%d.x.x. The driver requires version %d.%d.x.x. Entering Safe Mode.\n", hw->active_pkg_name, hw->active_pkg_ver.major, hw->active_pkg_ver.minor, @@ -2947,8 +2928,7 @@ ice_log_pkg_init(struct ice_hw *hw, enum ice_status *status) *status = ICE_ERR_NOT_SUPPORTED; } else if (hw->active_pkg_ver.major == ICE_PKG_SUPP_VER_MAJ && hw->active_pkg_ver.minor == ICE_PKG_SUPP_VER_MNR) { - dev_info(dev, - "The driver could not load the DDP package file because a compatible DDP package is already present on the device. The device has package '%s' version %d.%d.%d.%d. The package file found by the driver: '%s' version %d.%d.%d.%d.\n", + dev_info(dev, "The driver could not load the DDP package file because a compatible DDP package is already present on the device. The device has package '%s' version %d.%d.%d.%d. The package file found by the driver: '%s' version %d.%d.%d.%d.\n", hw->active_pkg_name, hw->active_pkg_ver.major, hw->active_pkg_ver.minor, @@ -2960,54 +2940,46 @@ ice_log_pkg_init(struct ice_hw *hw, enum ice_status *status) hw->pkg_ver.update, hw->pkg_ver.draft); } else { - dev_err(dev, - "An unknown error occurred when loading the DDP package, please reboot the system. If the problem persists, update the NVM. Entering Safe Mode.\n"); + dev_err(dev, "An unknown error occurred when loading the DDP package, please reboot the system. If the problem persists, update the NVM. Entering Safe Mode.\n"); *status = ICE_ERR_NOT_SUPPORTED; } break; case ICE_ERR_BUF_TOO_SHORT: /* fall-through */ case ICE_ERR_CFG: - dev_err(dev, - "The DDP package file is invalid. Entering Safe Mode.\n"); + dev_err(dev, "The DDP package file is invalid. Entering Safe Mode.\n"); break; case ICE_ERR_NOT_SUPPORTED: /* Package File version not supported */ if (hw->pkg_ver.major > ICE_PKG_SUPP_VER_MAJ || (hw->pkg_ver.major == ICE_PKG_SUPP_VER_MAJ && hw->pkg_ver.minor > ICE_PKG_SUPP_VER_MNR)) - dev_err(dev, - "The DDP package file version is higher than the driver supports. Please use an updated driver. Entering Safe Mode.\n"); + dev_err(dev, "The DDP package file version is higher than the driver supports. Please use an updated driver. Entering Safe Mode.\n"); else if (hw->pkg_ver.major < ICE_PKG_SUPP_VER_MAJ || (hw->pkg_ver.major == ICE_PKG_SUPP_VER_MAJ && hw->pkg_ver.minor < ICE_PKG_SUPP_VER_MNR)) - dev_err(dev, - "The DDP package file version is lower than the driver supports. The driver requires version %d.%d.x.x. Please use an updated DDP Package file. Entering Safe Mode.\n", + dev_err(dev, "The DDP package file version is lower than the driver supports. The driver requires version %d.%d.x.x. Please use an updated DDP Package file. Entering Safe Mode.\n", ICE_PKG_SUPP_VER_MAJ, ICE_PKG_SUPP_VER_MNR); break; case ICE_ERR_AQ_ERROR: switch (hw->pkg_dwnld_status) { case ICE_AQ_RC_ENOSEC: case ICE_AQ_RC_EBADSIG: - dev_err(dev, - "The DDP package could not be loaded because its signature is not valid. Please use a valid DDP Package. Entering Safe Mode.\n"); + dev_err(dev, "The DDP package could not be loaded because its signature is not valid. Please use a valid DDP Package. Entering Safe Mode.\n"); return; case ICE_AQ_RC_ESVN: - dev_err(dev, - "The DDP Package could not be loaded because its security revision is too low. Please use an updated DDP Package. Entering Safe Mode.\n"); + dev_err(dev, "The DDP Package could not be loaded because its security revision is too low. Please use an updated DDP Package. Entering Safe Mode.\n"); return; case ICE_AQ_RC_EBADMAN: case ICE_AQ_RC_EBADBUF: - dev_err(dev, - "An error occurred on the device while loading the DDP package. The device will be reset.\n"); + dev_err(dev, "An error occurred on the device while loading the DDP package. The device will be reset.\n"); return; default: break; } /* fall-through */ default: - dev_err(dev, - "An unknown error (%d) occurred when loading the DDP package. Entering Safe Mode.\n", + dev_err(dev, "An unknown error (%d) occurred when loading the DDP package. Entering Safe Mode.\n", *status); break; } @@ -3038,8 +3010,7 @@ ice_load_pkg(const struct firmware *firmware, struct ice_pf *pf) status = ice_init_pkg(hw, hw->pkg_copy, hw->pkg_size); ice_log_pkg_init(hw, &status); } else { - dev_err(dev, - "The DDP package file failed to load. Entering Safe Mode.\n"); + dev_err(dev, "The DDP package file failed to load. Entering Safe Mode.\n"); } if (status) { @@ -3065,8 +3036,7 @@ ice_load_pkg(const struct firmware *firmware, struct ice_pf *pf) static void ice_verify_cacheline_size(struct ice_pf *pf) { if (rd32(&pf->hw, GLPCI_CNF2) & GLPCI_CNF2_CACHELINE_SIZE_M) - dev_warn(ice_pf_to_dev(pf), - "%d Byte cache line assumption is invalid, driver may have Tx timeouts!\n", + dev_warn(ice_pf_to_dev(pf), "%d Byte cache line assumption is invalid, driver may have Tx timeouts!\n", ICE_CACHE_LINE_BYTES); } @@ -3159,8 +3129,7 @@ static void ice_request_fw(struct ice_pf *pf) dflt_pkg_load: err = request_firmware(&firmware, ICE_DDP_PKG_FILE, dev); if (err) { - dev_err(dev, - "The DDP package file was not found or could not be read. Entering Safe Mode\n"); + dev_err(dev, "The DDP package file was not found or could not be read. Entering Safe Mode\n"); return; } @@ -3184,7 +3153,9 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) struct ice_hw *hw; int err; - /* this driver uses devres, see Documentation/driver-api/driver-model/devres.rst */ + /* this driver uses devres, see + * Documentation/driver-api/driver-model/devres.rst + */ err = pcim_enable_device(pdev); if (err) return err; @@ -3245,11 +3216,6 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) goto err_exit_unroll; } - dev_info(dev, "firmware %d.%d.%d api %d.%d.%d nvm %s build 0x%08x\n", - hw->fw_maj_ver, hw->fw_min_ver, hw->fw_patch, - hw->api_maj_ver, hw->api_min_ver, hw->api_patch, - ice_nvm_version_str(hw), hw->fw_build); - ice_request_fw(pf); /* if ice_request_fw fails, ICE_FLAG_ADV_FEATURES bit won't be @@ -3257,8 +3223,7 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) * true */ if (ice_is_safe_mode(pf)) { - dev_err(dev, - "Package download failed. Advanced features disabled - Device now in Safe Mode\n"); + dev_err(dev, "Package download failed. Advanced features disabled - Device now in Safe Mode\n"); /* we already got function/device capabilities but these don't * reflect what the driver needs to do in safe mode. Instead of * adding conditional logic everywhere to ignore these @@ -3335,8 +3300,7 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) /* tell the firmware we are up */ err = ice_send_version(pf); if (err) { - dev_err(dev, - "probe failed sending driver version %s. error: %d\n", + dev_err(dev, "probe failed sending driver version %s. error: %d\n", ice_drv_ver, err); goto err_alloc_sw_unroll; } @@ -3477,8 +3441,7 @@ static pci_ers_result_t ice_pci_err_slot_reset(struct pci_dev *pdev) err = pci_enable_device_mem(pdev); if (err) { - dev_err(&pdev->dev, - "Cannot re-enable PCI device after reset, error %d\n", + dev_err(&pdev->dev, "Cannot re-enable PCI device after reset, error %d\n", err); result = PCI_ERS_RESULT_DISCONNECT; } else { @@ -3497,8 +3460,7 @@ static pci_ers_result_t ice_pci_err_slot_reset(struct pci_dev *pdev) err = pci_cleanup_aer_uncorrect_error_status(pdev); if (err) - dev_dbg(&pdev->dev, - "pci_cleanup_aer_uncorrect_error_status failed, error %d\n", + dev_dbg(&pdev->dev, "pci_cleanup_aer_uncorrect_error_status failed, error %d\n", err); /* non-fatal, continue */ @@ -3517,8 +3479,8 @@ static void ice_pci_err_resume(struct pci_dev *pdev) struct ice_pf *pf = pci_get_drvdata(pdev); if (!pf) { - dev_err(&pdev->dev, - "%s failed, device is unrecoverable\n", __func__); + dev_err(&pdev->dev, "%s failed, device is unrecoverable\n", + __func__); return; } @@ -3766,8 +3728,7 @@ ice_set_tx_maxrate(struct net_device *netdev, int queue_index, u32 maxrate) /* Validate maxrate requested is within permitted range */ if (maxrate && (maxrate > (ICE_SCHED_MAX_BW / 1000))) { - netdev_err(netdev, - "Invalid max rate %d specified for the queue %d\n", + netdev_err(netdev, "Invalid max rate %d specified for the queue %d\n", maxrate, queue_index); return -EINVAL; } @@ -3783,8 +3744,8 @@ ice_set_tx_maxrate(struct net_device *netdev, int queue_index, u32 maxrate) status = ice_cfg_q_bw_lmt(vsi->port_info, vsi->idx, tc, q_handle, ICE_MAX_BW, maxrate * 1000); if (status) { - netdev_err(netdev, - "Unable to set Tx max rate, error %d\n", status); + netdev_err(netdev, "Unable to set Tx max rate, error %d\n", + status); return -EIO; } @@ -3876,15 +3837,13 @@ ice_set_features(struct net_device *netdev, netdev_features_t features) /* Don't set any netdev advanced features with device in Safe Mode */ if (ice_is_safe_mode(vsi->back)) { - dev_err(&vsi->back->pdev->dev, - "Device is in Safe Mode - not enabling advanced netdev features\n"); + dev_err(ice_pf_to_dev(vsi->back), "Device is in Safe Mode - not enabling advanced netdev features\n"); return ret; } /* Do not change setting during reset */ if (ice_is_reset_in_progress(pf->state)) { - dev_err(&vsi->back->pdev->dev, - "Device is resetting, changing advanced netdev features temporarily unavailable.\n"); + dev_err(ice_pf_to_dev(vsi->back), "Device is resetting, changing advanced netdev features temporarily unavailable.\n"); return -EBUSY; } @@ -4372,21 +4331,18 @@ int ice_down(struct ice_vsi *vsi) tx_err = ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, 0); if (tx_err) - netdev_err(vsi->netdev, - "Failed stop Tx rings, VSI %d error %d\n", + netdev_err(vsi->netdev, "Failed stop Tx rings, VSI %d error %d\n", vsi->vsi_num, tx_err); if (!tx_err && ice_is_xdp_ena_vsi(vsi)) { tx_err = ice_vsi_stop_xdp_tx_rings(vsi); if (tx_err) - netdev_err(vsi->netdev, - "Failed stop XDP rings, VSI %d error %d\n", + netdev_err(vsi->netdev, "Failed stop XDP rings, VSI %d error %d\n", vsi->vsi_num, tx_err); } rx_err = ice_vsi_stop_rx_rings(vsi); if (rx_err) - netdev_err(vsi->netdev, - "Failed stop Rx rings, VSI %d error %d\n", + netdev_err(vsi->netdev, "Failed stop Rx rings, VSI %d error %d\n", vsi->vsi_num, rx_err); ice_napi_disable_all(vsi); @@ -4394,8 +4350,7 @@ int ice_down(struct ice_vsi *vsi) if (test_bit(ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA, vsi->back->flags)) { link_err = ice_force_phys_link_state(vsi, false); if (link_err) - netdev_err(vsi->netdev, - "Failed to set physical link down, VSI %d error %d\n", + netdev_err(vsi->netdev, "Failed to set physical link down, VSI %d error %d\n", vsi->vsi_num, link_err); } @@ -4406,8 +4361,7 @@ int ice_down(struct ice_vsi *vsi) ice_clean_rx_ring(vsi->rx_rings[i]); if (tx_err || rx_err || link_err) { - netdev_err(vsi->netdev, - "Failed to close VSI 0x%04X on switch 0x%04X\n", + netdev_err(vsi->netdev, "Failed to close VSI 0x%04X on switch 0x%04X\n", vsi->vsi_num, vsi->vsw->sw_id); return -EIO; } @@ -4426,7 +4380,7 @@ int ice_vsi_setup_tx_rings(struct ice_vsi *vsi) int i, err = 0; if (!vsi->num_txq) { - dev_err(&vsi->back->pdev->dev, "VSI %d has 0 Tx queues\n", + dev_err(ice_pf_to_dev(vsi->back), "VSI %d has 0 Tx queues\n", vsi->vsi_num); return -EINVAL; } @@ -4457,7 +4411,7 @@ int ice_vsi_setup_rx_rings(struct ice_vsi *vsi) int i, err = 0; if (!vsi->num_rxq) { - dev_err(&vsi->back->pdev->dev, "VSI %d has 0 Rx queues\n", + dev_err(ice_pf_to_dev(vsi->back), "VSI %d has 0 Rx queues\n", vsi->vsi_num); return -EINVAL; } @@ -4554,8 +4508,7 @@ static void ice_vsi_release_all(struct ice_pf *pf) err = ice_vsi_release(pf->vsi[i]); if (err) - dev_dbg(ice_pf_to_dev(pf), - "Failed to release pf->vsi[%d], err %d, vsi_num = %d\n", + dev_dbg(ice_pf_to_dev(pf), "Failed to release pf->vsi[%d], err %d, vsi_num = %d\n", i, err, pf->vsi[i]->vsi_num); } } @@ -4582,8 +4535,7 @@ static int ice_vsi_rebuild_by_type(struct ice_pf *pf, enum ice_vsi_type type) /* rebuild the VSI */ err = ice_vsi_rebuild(vsi, true); if (err) { - dev_err(dev, - "rebuild VSI failed, err %d, VSI index %d, type %s\n", + dev_err(dev, "rebuild VSI failed, err %d, VSI index %d, type %s\n", err, vsi->idx, ice_vsi_type_str(type)); return err; } @@ -4591,8 +4543,7 @@ static int ice_vsi_rebuild_by_type(struct ice_pf *pf, enum ice_vsi_type type) /* replay filters for the VSI */ status = ice_replay_vsi(&pf->hw, vsi->idx); if (status) { - dev_err(dev, - "replay VSI failed, status %d, VSI index %d, type %s\n", + dev_err(dev, "replay VSI failed, status %d, VSI index %d, type %s\n", status, vsi->idx, ice_vsi_type_str(type)); return -EIO; } @@ -4605,8 +4556,7 @@ static int ice_vsi_rebuild_by_type(struct ice_pf *pf, enum ice_vsi_type type) /* enable the VSI */ err = ice_ena_vsi(vsi, false); if (err) { - dev_err(dev, - "enable VSI failed, err %d, VSI index %d, type %s\n", + dev_err(dev, "enable VSI failed, err %d, VSI index %d, type %s\n", err, vsi->idx, ice_vsi_type_str(type)); return err; } @@ -4684,8 +4634,7 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) } if (pf->first_sw->dflt_vsi_ena) - dev_info(dev, - "Clearing default VSI, re-enable after reset completes\n"); + dev_info(dev, "Clearing default VSI, re-enable after reset completes\n"); /* clear the default VSI configuration if it exists */ pf->first_sw->dflt_vsi = NULL; pf->first_sw->dflt_vsi_ena = false; @@ -4736,8 +4685,7 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) /* tell the firmware we are up */ ret = ice_send_version(pf); if (ret) { - dev_err(dev, - "Rebuild failed due to error sending driver version: %d\n", + dev_err(dev, "Rebuild failed due to error sending driver version: %d\n", ret); goto err_vsi_rebuild; } @@ -4993,7 +4941,7 @@ static int ice_vsi_update_bridge_mode(struct ice_vsi *vsi, u16 bmode) status = ice_update_vsi(hw, vsi->idx, ctxt, NULL); if (status) { - dev_err(&vsi->back->pdev->dev, "update VSI for bridge mode failed, bmode = %d err %d aq_err %d\n", + dev_err(ice_pf_to_dev(vsi->back), "update VSI for bridge mode failed, bmode = %d err %d aq_err %d\n", bmode, status, hw->adminq.sq_last_status); ret = -EIO; goto out; @@ -5185,8 +5133,7 @@ int ice_open(struct net_device *netdev) if (pi->phy.link_info.link_info & ICE_AQ_MEDIA_AVAILABLE) { err = ice_force_phys_link_state(vsi, true); if (err) { - netdev_err(netdev, - "Failed to set physical link up, error %d\n", + netdev_err(netdev, "Failed to set physical link up, error %d\n", err); return err; } diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index fd17ace6b226edb2b2523ba398b5d2c38371dc04..4de61dbedd36d97fac722d62374287da5651fd03 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -644,7 +644,7 @@ static bool ice_page_is_reserved(struct page *page) * Update the offset within page so that Rx buf will be ready to be reused. * For systems with PAGE_SIZE < 8192 this function will flip the page offset * so the second half of page assigned to Rx buffer will be used, otherwise - * the offset is moved by the @size bytes + * the offset is moved by "size" bytes */ static void ice_rx_buf_adjust_pg_offset(struct ice_rx_buf *rx_buf, unsigned int size) @@ -1078,8 +1078,6 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) skb = ice_build_skb(rx_ring, rx_buf, &xdp); else skb = ice_construct_skb(rx_ring, rx_buf, &xdp); - } else { - skb = ice_construct_skb(rx_ring, rx_buf, &xdp); } /* exit if we failed to retrieve a buffer */ if (!skb) { @@ -1621,11 +1619,11 @@ ice_tx_map(struct ice_ring *tx_ring, struct ice_tx_buf *first, { u64 td_offset, td_tag, td_cmd; u16 i = tx_ring->next_to_use; - skb_frag_t *frag; unsigned int data_len, size; struct ice_tx_desc *tx_desc; struct ice_tx_buf *tx_buf; struct sk_buff *skb; + skb_frag_t *frag; dma_addr_t dma; td_tag = off->td_l2tag1; @@ -1738,9 +1736,8 @@ ice_tx_map(struct ice_ring *tx_ring, struct ice_tx_buf *first, ice_maybe_stop_tx(tx_ring, DESC_NEEDED); /* notify HW of packet */ - if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) { + if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) writel(i, tx_ring->tail); - } return; @@ -2078,7 +2075,7 @@ static bool __ice_chk_linearize(struct sk_buff *skb) frag = &skb_shinfo(skb)->frags[0]; /* Initialize size to the negative value of gso_size minus 1. We - * use this as the worst case scenerio in which the frag ahead + * use this as the worst case scenario in which the frag ahead * of us only provides one byte which is why we are limited to 6 * descriptors for a single transmit as the header and previous * fragment are already consuming 2 descriptors. diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index a86270696df1c027d9070f620e741829bace25d9..7ee00a1286634a5eed591f5d22c5a29ebbc79cf3 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -33,8 +33,8 @@ * frame. * * Note: For cache line sizes 256 or larger this value is going to end - * up negative. In these cases we should fall back to the legacy - * receive path. + * up negative. In these cases we should fall back to the legacy + * receive path. */ #if (PAGE_SIZE < 8192) #define ICE_2K_TOO_SMALL_WITH_PADDING \ @@ -222,7 +222,7 @@ enum ice_rx_dtype { #define ICE_ITR_GRAN_S 1 /* ITR granularity is always 2us */ #define ICE_ITR_GRAN_US BIT(ICE_ITR_GRAN_S) #define ICE_ITR_MASK 0x1FFE /* ITR register value alignment mask */ -#define ITR_REG_ALIGN(setting) __ALIGN_MASK(setting, ~ICE_ITR_MASK) +#define ITR_REG_ALIGN(setting) ((setting) & ICE_ITR_MASK) #define ICE_ITR_ADAPTIVE_MIN_INC 0x0002 #define ICE_ITR_ADAPTIVE_MIN_USECS 0x0002 diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c index 35bbc4ff603cddc4a3f2c5e951d414ff60d41c4a..6da048a6ca7c1b302ae281694807e126cfb85537 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c @@ -10,7 +10,7 @@ */ void ice_release_rx_desc(struct ice_ring *rx_ring, u32 val) { - u16 prev_ntu = rx_ring->next_to_use; + u16 prev_ntu = rx_ring->next_to_use & ~0x7; rx_ring->next_to_use = val; diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index b361ffabb0ca5ea409b3d214449e594dbd3c2854..db0ef6ba907f4930a70280c6a68a388e51e4907e 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -517,7 +517,7 @@ struct ice_hw { struct ice_fw_log_cfg fw_log; /* Device max aggregate bandwidths corresponding to the GL_PWR_MODE_CTL - * register. Used for determining the ITR/intrl granularity during + * register. Used for determining the ITR/INTRL granularity during * initialization. */ #define ICE_MAX_AGG_BW_200G 0x0 diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index 82b1e7a4cb920e1a4ee59bb1724f9f5007ee4da5..75c70d432c7245e1c76f1b0a39cdfa4be5d62dc9 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -199,8 +199,7 @@ static void ice_dis_vf_mappings(struct ice_vf *vf) if (vsi->rx_mapping_mode == ICE_VSI_MAP_CONTIG) wr32(hw, VPLAN_RX_QBASE(vf->vf_id), 0); else - dev_err(dev, - "Scattered mode for VF Rx queues is not yet implemented\n"); + dev_err(dev, "Scattered mode for VF Rx queues is not yet implemented\n"); } /** @@ -402,8 +401,7 @@ static void ice_trigger_vf_reset(struct ice_vf *vf, bool is_vflr, bool is_pfr) if ((reg & VF_TRANS_PENDING_M) == 0) break; - dev_err(dev, - "VF %d PCI transactions stuck\n", vf->vf_id); + dev_err(dev, "VF %d PCI transactions stuck\n", vf->vf_id); udelay(ICE_PCI_CIAD_WAIT_DELAY_US); } } @@ -462,7 +460,7 @@ static int ice_vsi_manage_pvid(struct ice_vsi *vsi, u16 vid, bool enable) status = ice_update_vsi(hw, vsi->idx, ctxt, NULL); if (status) { - dev_info(&vsi->back->pdev->dev, "update VSI for port VLAN failed, err %d aq_err %d\n", + dev_info(ice_pf_to_dev(vsi->back), "update VSI for port VLAN failed, err %d aq_err %d\n", status, hw->adminq.sq_last_status); ret = -EIO; goto out; @@ -1095,7 +1093,6 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr) * finished resetting. */ for (i = 0, v = 0; i < 10 && v < pf->num_alloc_vfs; i++) { - /* Check each VF in sequence */ while (v < pf->num_alloc_vfs) { u32 reg; @@ -1553,8 +1550,7 @@ ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode, dev_info(dev, "VF %d failed opcode %d, retval: %d\n", vf->vf_id, v_opcode, v_retval); if (vf->num_inval_msgs > ICE_DFLT_NUM_INVAL_MSGS_ALLOWED) { - dev_err(dev, - "Number of invalid messages exceeded for VF %d\n", + dev_err(dev, "Number of invalid messages exceeded for VF %d\n", vf->vf_id); dev_err(dev, "Use PF Control I/F to enable the VF\n"); set_bit(ICE_VF_STATE_DIS, vf->vf_states); @@ -1569,8 +1565,7 @@ ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode, aq_ret = ice_aq_send_msg_to_vf(&pf->hw, vf->vf_id, v_opcode, v_retval, msg, msglen, NULL); if (aq_ret && pf->hw.mailboxq.sq_last_status != ICE_AQ_RC_ENOSYS) { - dev_info(dev, - "Unable to send the message to VF %d ret %d aq_err %d\n", + dev_info(dev, "Unable to send the message to VF %d ret %d aq_err %d\n", vf->vf_id, aq_ret, pf->hw.mailboxq.sq_last_status); return -EIO; } @@ -1878,6 +1873,48 @@ static int ice_vc_config_rss_lut(struct ice_vf *vf, u8 *msg) NULL, 0); } +/** + * ice_wait_on_vf_reset - poll to make sure a given VF is ready after reset + * @vf: The VF being resseting + * + * The max poll time is about ~800ms, which is about the maximum time it takes + * for a VF to be reset and/or a VF driver to be removed. + */ +static void ice_wait_on_vf_reset(struct ice_vf *vf) +{ + int i; + + for (i = 0; i < ICE_MAX_VF_RESET_TRIES; i++) { + if (test_bit(ICE_VF_STATE_INIT, vf->vf_states)) + break; + msleep(ICE_MAX_VF_RESET_SLEEP_MS); + } +} + +/** + * ice_check_vf_ready_for_cfg - check if VF is ready to be configured/queried + * @vf: VF to check if it's ready to be configured/queried + * + * The purpose of this function is to make sure the VF is not in reset, not + * disabled, and initialized so it can be configured and/or queried by a host + * administrator. + */ +static int ice_check_vf_ready_for_cfg(struct ice_vf *vf) +{ + struct ice_pf *pf; + + ice_wait_on_vf_reset(vf); + + if (ice_is_vf_disabled(vf)) + return -EINVAL; + + pf = vf->pf; + if (ice_check_vf_init(pf, vf)) + return -EBUSY; + + return 0; +} + /** * ice_set_vf_spoofchk * @netdev: network interface device structure @@ -1895,16 +1932,16 @@ int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena) enum ice_status status; struct device *dev; struct ice_vf *vf; - int ret = 0; + int ret; dev = ice_pf_to_dev(pf); if (ice_validate_vf_id(pf, vf_id)) return -EINVAL; vf = &pf->vf[vf_id]; - - if (ice_check_vf_init(pf, vf)) - return -EBUSY; + ret = ice_check_vf_ready_for_cfg(vf); + if (ret) + return ret; vf_vsi = pf->vsi[vf->lan_vsi_idx]; if (!vf_vsi) { @@ -1914,8 +1951,7 @@ int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena) } if (vf_vsi->type != ICE_VSI_VF) { - netdev_err(netdev, - "Type %d of VSI %d for VF %d is no ICE_VSI_VF\n", + netdev_err(netdev, "Type %d of VSI %d for VF %d is no ICE_VSI_VF\n", vf_vsi->type, vf_vsi->vsi_num, vf->vf_id); return -ENODEV; } @@ -1945,8 +1981,7 @@ int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena) status = ice_update_vsi(&pf->hw, vf_vsi->idx, ctx, NULL); if (status) { - dev_err(dev, - "Failed to %sable spoofchk on VF %d VSI %d\n error %d", + dev_err(dev, "Failed to %sable spoofchk on VF %d VSI %d\n error %d", ena ? "en" : "dis", vf->vf_id, vf_vsi->vsi_num, status); ret = -EIO; goto out; @@ -2063,8 +2098,7 @@ static int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg) continue; if (ice_vsi_ctrl_rx_ring(vsi, true, vf_q_id)) { - dev_err(&vsi->back->pdev->dev, - "Failed to enable Rx ring %d on VSI %d\n", + dev_err(ice_pf_to_dev(vsi->back), "Failed to enable Rx ring %d on VSI %d\n", vf_q_id, vsi->vsi_num); v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; @@ -2166,8 +2200,7 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) if (ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, vf->vf_id, ring, &txq_meta)) { - dev_err(&vsi->back->pdev->dev, - "Failed to stop Tx ring %d on VSI %d\n", + dev_err(ice_pf_to_dev(vsi->back), "Failed to stop Tx ring %d on VSI %d\n", vf_q_id, vsi->vsi_num); v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; @@ -2193,8 +2226,7 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) continue; if (ice_vsi_ctrl_rx_ring(vsi, false, vf_q_id)) { - dev_err(&vsi->back->pdev->dev, - "Failed to stop Rx ring %d on VSI %d\n", + dev_err(ice_pf_to_dev(vsi->back), "Failed to stop Rx ring %d on VSI %d\n", vf_q_id, vsi->vsi_num); v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; @@ -2357,8 +2389,7 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) if (qci->num_queue_pairs > ICE_MAX_BASE_QS_PER_VF || qci->num_queue_pairs > min_t(u16, vsi->alloc_txq, vsi->alloc_rxq)) { - dev_err(ice_pf_to_dev(pf), - "VF-%d requesting more than supported number of queues: %d\n", + dev_err(ice_pf_to_dev(pf), "VF-%d requesting more than supported number of queues: %d\n", vf->vf_id, min_t(u16, vsi->alloc_txq, vsi->alloc_rxq)); v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; @@ -2570,8 +2601,7 @@ ice_vc_handle_mac_addr_msg(struct ice_vf *vf, u8 *msg, bool set) */ if (set && !ice_is_vf_trusted(vf) && (vf->num_mac + al->num_elements) > ICE_MAX_MACADDR_PER_VF) { - dev_err(ice_pf_to_dev(pf), - "Can't add more MAC addresses, because VF-%d is not trusted, switch the VF to trusted mode in order to add more functionalities\n", + dev_err(ice_pf_to_dev(pf), "Can't add more MAC addresses, because VF-%d is not trusted, switch the VF to trusted mode in order to add more functionalities\n", vf->vf_id); v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto handle_mac_exit; @@ -2648,8 +2678,8 @@ static int ice_vc_request_qs_msg(struct ice_vf *vf, u8 *msg) struct ice_pf *pf = vf->pf; u16 max_allowed_vf_queues; u16 tx_rx_queue_left; - u16 cur_queues; struct device *dev; + u16 cur_queues; dev = ice_pf_to_dev(pf); if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { @@ -2670,8 +2700,7 @@ static int ice_vc_request_qs_msg(struct ice_vf *vf, u8 *msg) vfres->num_queue_pairs = ICE_MAX_BASE_QS_PER_VF; } else if (req_queues > cur_queues && req_queues - cur_queues > tx_rx_queue_left) { - dev_warn(dev, - "VF %d requested %u more queues, but only %u left.\n", + dev_warn(dev, "VF %d requested %u more queues, but only %u left.\n", vf->vf_id, req_queues - cur_queues, tx_rx_queue_left); vfres->num_queue_pairs = min_t(u16, max_allowed_vf_queues, ICE_MAX_BASE_QS_PER_VF); @@ -2709,7 +2738,7 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, struct ice_vsi *vsi; struct device *dev; struct ice_vf *vf; - int ret = 0; + int ret; dev = ice_pf_to_dev(pf); if (ice_validate_vf_id(pf, vf_id)) @@ -2727,13 +2756,15 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, vf = &pf->vf[vf_id]; vsi = pf->vsi[vf->lan_vsi_idx]; - if (ice_check_vf_init(pf, vf)) - return -EBUSY; + + ret = ice_check_vf_ready_for_cfg(vf); + if (ret) + return ret; if (le16_to_cpu(vsi->info.pvid) == vlanprio) { /* duplicate request, so just return success */ dev_dbg(dev, "Duplicate pvid %d request\n", vlanprio); - return ret; + return 0; } /* If PVID, then remove all filters on the old VLAN */ @@ -2744,7 +2775,7 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, if (vlan_id || qos) { ret = ice_vsi_manage_pvid(vsi, vlanprio, true); if (ret) - goto error_set_pvid; + return ret; } else { ice_vsi_manage_pvid(vsi, 0, false); vsi->info.pvid = 0; @@ -2757,7 +2788,7 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, /* add new VLAN filter for each MAC */ ret = ice_vsi_add_vlan(vsi, vlan_id); if (ret) - goto error_set_pvid; + return ret; } /* The Port VLAN needs to be saved across resets the same as the @@ -2765,8 +2796,7 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, */ vf->port_vlan_id = le16_to_cpu(vsi->info.pvid); -error_set_pvid: - return ret; + return 0; } /** @@ -2821,8 +2851,8 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) for (i = 0; i < vfl->num_elements; i++) { if (vfl->vlan_id[i] > ICE_MAX_VLANID) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; - dev_err(dev, - "invalid VF VLAN id %d\n", vfl->vlan_id[i]); + dev_err(dev, "invalid VF VLAN id %d\n", + vfl->vlan_id[i]); goto error_param; } } @@ -2836,8 +2866,7 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) if (add_v && !ice_is_vf_trusted(vf) && vsi->num_vlan >= ICE_MAX_VLAN_PER_VF) { - dev_info(dev, - "VF-%d is not trusted, switch the VF to trusted mode, in order to add more VLAN addresses\n", + dev_info(dev, "VF-%d is not trusted, switch the VF to trusted mode, in order to add more VLAN addresses\n", vf->vf_id); /* There is no need to let VF know about being not trusted, * so we can just return success message here @@ -2860,8 +2889,7 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) if (!ice_is_vf_trusted(vf) && vsi->num_vlan >= ICE_MAX_VLAN_PER_VF) { - dev_info(dev, - "VF-%d is not trusted, switch the VF to trusted mode, in order to add more VLAN addresses\n", + dev_info(dev, "VF-%d is not trusted, switch the VF to trusted mode, in order to add more VLAN addresses\n", vf->vf_id); /* There is no need to let VF know about being * not trusted, so we can just return success @@ -2889,8 +2917,7 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) status = ice_cfg_vlan_pruning(vsi, true, false); if (status) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; - dev_err(dev, - "Enable VLAN pruning on VLAN ID: %d failed error-%d\n", + dev_err(dev, "Enable VLAN pruning on VLAN ID: %d failed error-%d\n", vid, status); goto error_param; } @@ -2903,8 +2930,7 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) promisc_m, vid); if (status) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; - dev_err(dev, - "Enable Unicast/multicast promiscuous mode on VLAN ID:%d failed error-%d\n", + dev_err(dev, "Enable Unicast/multicast promiscuous mode on VLAN ID:%d failed error-%d\n", vid, status); } } @@ -3140,8 +3166,7 @@ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) case VIRTCHNL_OP_GET_VF_RESOURCES: err = ice_vc_get_vf_res_msg(vf, msg); if (ice_vf_init_vlan_stripping(vf)) - dev_err(dev, - "Failed to initialize VLAN stripping for VF %d\n", + dev_err(dev, "Failed to initialize VLAN stripping for VF %d\n", vf->vf_id); ice_vc_notify_vf_link_state(vf); break; @@ -3254,23 +3279,6 @@ ice_get_vf_cfg(struct net_device *netdev, int vf_id, struct ifla_vf_info *ivi) return 0; } -/** - * ice_wait_on_vf_reset - * @vf: The VF being resseting - * - * Poll to make sure a given VF is ready after reset - */ -static void ice_wait_on_vf_reset(struct ice_vf *vf) -{ - int i; - - for (i = 0; i < ICE_MAX_VF_RESET_WAIT; i++) { - if (test_bit(ICE_VF_STATE_INIT, vf->vf_states)) - break; - msleep(20); - } -} - /** * ice_set_vf_mac * @netdev: network interface device structure @@ -3283,29 +3291,21 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) { struct ice_pf *pf = ice_netdev_to_pf(netdev); struct ice_vf *vf; - int ret = 0; + int ret; if (ice_validate_vf_id(pf, vf_id)) return -EINVAL; - vf = &pf->vf[vf_id]; - /* Don't set MAC on disabled VF */ - if (ice_is_vf_disabled(vf)) - return -EINVAL; - - /* In case VF is in reset mode, wait until it is completed. Depending - * on factors like queue disabling routine, this could take ~250ms - */ - ice_wait_on_vf_reset(vf); - - if (ice_check_vf_init(pf, vf)) - return -EBUSY; - if (is_zero_ether_addr(mac) || is_multicast_ether_addr(mac)) { netdev_err(netdev, "%pM not a valid unicast address\n", mac); return -EINVAL; } + vf = &pf->vf[vf_id]; + ret = ice_check_vf_ready_for_cfg(vf); + if (ret) + return ret; + /* copy MAC into dflt_lan_addr and trigger a VF reset. The reset * flow will use the updated dflt_lan_addr and add a MAC filter * using ice_add_mac. Also set pf_set_mac to indicate that the PF has @@ -3313,12 +3313,11 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) */ ether_addr_copy(vf->dflt_lan_addr.addr, mac); vf->pf_set_mac = true; - netdev_info(netdev, - "MAC on VF %d set to %pM. VF driver will be reinitialized\n", + netdev_info(netdev, "MAC on VF %d set to %pM. VF driver will be reinitialized\n", vf_id, mac); ice_vc_reset_vf(vf); - return ret; + return 0; } /** @@ -3332,25 +3331,16 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted) { struct ice_pf *pf = ice_netdev_to_pf(netdev); - struct device *dev; struct ice_vf *vf; + int ret; - dev = ice_pf_to_dev(pf); if (ice_validate_vf_id(pf, vf_id)) return -EINVAL; vf = &pf->vf[vf_id]; - /* Don't set Trusted Mode on disabled VF */ - if (ice_is_vf_disabled(vf)) - return -EINVAL; - - /* In case VF is in reset mode, wait until it is completed. Depending - * on factors like queue disabling routine, this could take ~250ms - */ - ice_wait_on_vf_reset(vf); - - if (ice_check_vf_init(pf, vf)) - return -EBUSY; + ret = ice_check_vf_ready_for_cfg(vf); + if (ret) + return ret; /* Check if already trusted */ if (trusted == vf->trusted) @@ -3358,7 +3348,7 @@ int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted) vf->trusted = trusted; ice_vc_reset_vf(vf); - dev_info(dev, "VF %u is now %strusted\n", + dev_info(ice_pf_to_dev(pf), "VF %u is now %strusted\n", vf_id, trusted ? "" : "un"); return 0; @@ -3376,13 +3366,15 @@ int ice_set_vf_link_state(struct net_device *netdev, int vf_id, int link_state) { struct ice_pf *pf = ice_netdev_to_pf(netdev); struct ice_vf *vf; + int ret; if (ice_validate_vf_id(pf, vf_id)) return -EINVAL; vf = &pf->vf[vf_id]; - if (ice_check_vf_init(pf, vf)) - return -EBUSY; + ret = ice_check_vf_ready_for_cfg(vf); + if (ret) + return ret; switch (link_state) { case IFLA_VF_LINK_STATE_AUTO: @@ -3418,14 +3410,15 @@ int ice_get_vf_stats(struct net_device *netdev, int vf_id, struct ice_eth_stats *stats; struct ice_vsi *vsi; struct ice_vf *vf; + int ret; if (ice_validate_vf_id(pf, vf_id)) return -EINVAL; vf = &pf->vf[vf_id]; - - if (ice_check_vf_init(pf, vf)) - return -EBUSY; + ret = ice_check_vf_ready_for_cfg(vf); + if (ret) + return ret; vsi = pf->vsi[vf->lan_vsi_idx]; if (!vsi) diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h index 4647d636ed36e07c921f5e4c903f43effde7bc93..ac67982751dfb517dc050331b44a4c580de96de2 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h @@ -38,7 +38,8 @@ #define ICE_MAX_POLICY_INTR_PER_VF 33 #define ICE_MIN_INTR_PER_VF (ICE_MIN_QS_PER_VF + 1) #define ICE_DFLT_INTR_PER_VF (ICE_DFLT_QS_PER_VF + 1) -#define ICE_MAX_VF_RESET_WAIT 15 +#define ICE_MAX_VF_RESET_TRIES 40 +#define ICE_MAX_VF_RESET_SLEEP_MS 20 #define ice_for_each_vf(pf, i) \ for ((i) = 0; (i) < (pf)->num_alloc_vfs; (i)++) diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 149dca0012bae3ab1097128c414ab79260d0009d..4d3407bbd4c48ded8c956168e794039dd71d6ebe 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -338,8 +338,8 @@ static int ice_xsk_umem_dma_map(struct ice_vsi *vsi, struct xdp_umem *umem) DMA_BIDIRECTIONAL, ICE_RX_DMA_ATTR); if (dma_mapping_error(dev, dma)) { - dev_dbg(dev, - "XSK UMEM DMA mapping error on page num %d", i); + dev_dbg(dev, "XSK UMEM DMA mapping error on page num %d\n", + i); goto out_unmap; } diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c index 0b9e851f3da4fb1a37989e1aed311a5ad282353f..d2e2dc5384287c55447e32c5e547df65de0a6894 100644 --- a/drivers/net/ethernet/marvell/mvmdio.c +++ b/drivers/net/ethernet/marvell/mvmdio.c @@ -347,7 +347,7 @@ static int orion_mdio_probe(struct platform_device *pdev) } - dev->err_interrupt = platform_get_irq(pdev, 0); + dev->err_interrupt = platform_get_irq_optional(pdev, 0); if (dev->err_interrupt > 0 && resource_size(r) < MVMDIO_ERR_INT_MASK + 4) { dev_err(&pdev->dev, @@ -364,8 +364,8 @@ static int orion_mdio_probe(struct platform_device *pdev) writel(MVMDIO_ERR_INT_SMI_DONE, dev->regs + MVMDIO_ERR_INT_MASK); - } else if (dev->err_interrupt == -EPROBE_DEFER) { - ret = -EPROBE_DEFER; + } else if (dev->err_interrupt < 0) { + ret = dev->err_interrupt; goto out_mdio; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c index 3a975641f902adbb5da9286e39dbe3bb84c71b61..20b907dc1e297ff697cae883f5c8e6978b1e576c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c @@ -200,7 +200,7 @@ int mlx5e_health_report(struct mlx5e_priv *priv, netdev_err(priv->netdev, err_str); if (!reporter) - return err_ctx->recover(&err_ctx->ctx); + return err_ctx->recover(err_ctx->ctx); return devlink_health_report(reporter, err_str, err_ctx); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index 7c8796d9743fa5a6c66f4aa3e0017b800a121a9b..a226277b09805a75a107e069db46801ffa1c454c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -179,6 +179,14 @@ mlx5e_tx_dma_unmap(struct device *pdev, struct mlx5e_sq_dma *dma) } } +static inline void mlx5e_rqwq_reset(struct mlx5e_rq *rq) +{ + if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) + mlx5_wq_ll_reset(&rq->mpwqe.wq); + else + mlx5_wq_cyc_reset(&rq->wqe.wq); +} + /* SW parser related functions */ struct mlx5e_swp_spec { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 454d3459bd8b9639f2207dd2b5b0aef08e296aa5..21de4764d4c09b933a39b476b2509c5e3896204b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -712,6 +712,9 @@ int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state, int next_state) if (!in) return -ENOMEM; + if (curr_state == MLX5_RQC_STATE_RST && next_state == MLX5_RQC_STATE_RDY) + mlx5e_rqwq_reset(rq); + rqc = MLX5_ADDR_OF(modify_rq_in, in, ctx); MLX5_SET(modify_rq_in, in, rq_state, curr_state); @@ -5144,7 +5147,6 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv) static void mlx5e_nic_disable(struct mlx5e_priv *priv) { - struct net_device *netdev = priv->netdev; struct mlx5_core_dev *mdev = priv->mdev; #ifdef CONFIG_MLX5_CORE_EN_DCB @@ -5165,7 +5167,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv) mlx5e_monitor_counter_cleanup(priv); mlx5e_disable_async_events(priv); - mlx5_lag_remove(mdev, netdev); + mlx5_lag_remove(mdev); } int mlx5e_update_nic_rx(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 7b48ccacebe29bdaf7a46f610869bec31e469b34..6ed307d7f191499af3f80d2f4a5a0cdb48878eb6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1861,7 +1861,6 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv) static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv) { - struct net_device *netdev = priv->netdev; struct mlx5_core_dev *mdev = priv->mdev; struct mlx5e_rep_priv *rpriv = priv->ppriv; @@ -1870,7 +1869,7 @@ static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv) #endif mlx5_notifier_unregister(mdev, &priv->events_nb); cancel_work_sync(&rpriv->uplink_priv.reoffload_flows_work); - mlx5_lag_remove(mdev, netdev); + mlx5_lag_remove(mdev); } static MLX5E_DEFINE_STATS_GRP(sw_rep, 0); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 5acf60b1bbfed5ba230fb57ec28c418f16ccab44..e49acd0c5da5cf27ffe78b386da4535f4a36091a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -459,12 +459,16 @@ static void esw_destroy_legacy_table(struct mlx5_eswitch *esw) static int esw_legacy_enable(struct mlx5_eswitch *esw) { - int ret; + struct mlx5_vport *vport; + int ret, i; ret = esw_create_legacy_table(esw); if (ret) return ret; + mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs) + vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO; + ret = mlx5_eswitch_enable_pf_vf_vports(esw, MLX5_LEGACY_SRIOV_VPORT_EVENTS); if (ret) esw_destroy_legacy_table(esw); @@ -2452,25 +2456,17 @@ int mlx5_eswitch_set_vepa(struct mlx5_eswitch *esw, u8 setting) int mlx5_eswitch_get_vepa(struct mlx5_eswitch *esw, u8 *setting) { - int err = 0; - if (!esw) return -EOPNOTSUPP; if (!ESW_ALLOWED(esw)) return -EPERM; - mutex_lock(&esw->state_lock); - if (esw->mode != MLX5_ESWITCH_LEGACY) { - err = -EOPNOTSUPP; - goto out; - } + if (esw->mode != MLX5_ESWITCH_LEGACY) + return -EOPNOTSUPP; *setting = esw->fdb_table.legacy.vepa_uplink_rule ? 1 : 0; - -out: - mutex_unlock(&esw->state_lock); - return err; + return 0; } int mlx5_eswitch_set_vport_trust(struct mlx5_eswitch *esw, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 979f13bdc203a48c2b7c53a454d9e41f1389a790..1a57b2bd74b8650c070f1c0ad80b4c7069ad502b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1172,7 +1172,7 @@ static int esw_offloads_start(struct mlx5_eswitch *esw, return -EINVAL; } - mlx5_eswitch_disable(esw, true); + mlx5_eswitch_disable(esw, false); mlx5_eswitch_update_num_of_vfs(esw, esw->dev->priv.sriov.num_vfs); err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_OFFLOADS); if (err) { @@ -2065,7 +2065,7 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw, { int err, err1; - mlx5_eswitch_disable(esw, true); + mlx5_eswitch_disable(esw, false); err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_LEGACY); if (err) { NL_SET_ERR_MSG_MOD(extack, "Failed setting eswitch to legacy"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_chains.c index c5a446e295aa7d9b522cb0a145edd199bd120c2e..4276194b633fd1ef25a00982c9bb5f2ea51b18a5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_chains.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_chains.c @@ -35,7 +35,7 @@ static const unsigned int ESW_POOLS[] = { 4 * 1024 * 1024, 1 * 1024 * 1024, 64 * 1024, - 4 * 1024, }; + 128 }; struct mlx5_esw_chains_priv { struct rhashtable chains_ht; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c index b91eabc09fbc187460750f6bc10465ae1b3be944..8e19f6ab8393202c6c15791d9daa220c8536b512 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c @@ -464,9 +464,6 @@ static int mlx5_lag_netdev_event(struct notifier_block *this, struct mlx5_lag *ldev; int changed = 0; - if (!net_eq(dev_net(ndev), &init_net)) - return NOTIFY_DONE; - if ((event != NETDEV_CHANGEUPPER) && (event != NETDEV_CHANGELOWERSTATE)) return NOTIFY_DONE; @@ -586,8 +583,7 @@ void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev) if (!ldev->nb.notifier_call) { ldev->nb.notifier_call = mlx5_lag_netdev_event; - if (register_netdevice_notifier_dev_net(netdev, &ldev->nb, - &ldev->nn)) { + if (register_netdevice_notifier_net(&init_net, &ldev->nb)) { ldev->nb.notifier_call = NULL; mlx5_core_err(dev, "Failed to register LAG netdev notifier\n"); } @@ -600,7 +596,7 @@ void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev) } /* Must be called with intf_mutex held */ -void mlx5_lag_remove(struct mlx5_core_dev *dev, struct net_device *netdev) +void mlx5_lag_remove(struct mlx5_core_dev *dev) { struct mlx5_lag *ldev; int i; @@ -620,8 +616,7 @@ void mlx5_lag_remove(struct mlx5_core_dev *dev, struct net_device *netdev) if (i == MLX5_MAX_PORTS) { if (ldev->nb.notifier_call) - unregister_netdevice_notifier_dev_net(netdev, &ldev->nb, - &ldev->nn); + unregister_netdevice_notifier_net(&init_net, &ldev->nb); mlx5_lag_mp_cleanup(ldev); cancel_delayed_work_sync(&ldev->bond_work); mlx5_lag_dev_free(ldev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag.h index 316ab09e26645a59b34a60e61a33db3185d3c2fb..f1068aac64067080234ddb89fdaf68631698f7fa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.h @@ -44,7 +44,6 @@ struct mlx5_lag { struct workqueue_struct *wq; struct delayed_work bond_work; struct notifier_block nb; - struct netdev_net_notifier nn; struct lag_mp lag_mp; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index fcce9e0fc82c8e3f2d240cfbaa1cfdd6f0a51f3f..da67b28d6e23e621bac2c014b26cf811274ed10f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -157,7 +157,7 @@ int mlx5_query_qcam_reg(struct mlx5_core_dev *mdev, u32 *qcam, u8 feature_group, u8 access_reg_group); void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev); -void mlx5_lag_remove(struct mlx5_core_dev *dev, struct net_device *netdev); +void mlx5_lag_remove(struct mlx5_core_dev *dev); int mlx5_irq_table_init(struct mlx5_core_dev *dev); void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c index c6c7d1defbd788ee657f45c8e3914c6e8393243e..aade62a9ee5ce93e59c9ffb139665d9eaf277b5b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c @@ -2307,7 +2307,9 @@ static int dr_ste_build_src_gvmi_qpn_tag(struct mlx5dr_match_param *value, struct mlx5dr_cmd_vport_cap *vport_cap; struct mlx5dr_domain *dmn = sb->dmn; struct mlx5dr_cmd_caps *caps; + u8 *bit_mask = sb->bit_mask; u8 *tag = hw_ste->tag; + bool source_gvmi_set; DR_STE_SET_TAG(src_gvmi_qp, tag, source_qp, misc, source_sqn); @@ -2328,7 +2330,8 @@ static int dr_ste_build_src_gvmi_qpn_tag(struct mlx5dr_match_param *value, if (!vport_cap) return -EINVAL; - if (vport_cap->vport_gvmi) + source_gvmi_set = MLX5_GET(ste_src_gvmi_qp, bit_mask, source_gvmi); + if (vport_cap->vport_gvmi && source_gvmi_set) MLX5_SET(ste_src_gvmi_qp, tag, source_gvmi, vport_cap->vport_gvmi); misc->source_eswitch_owner_vhca_id = 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c index 3abfc81259262d94a327b24b34d00b89d5409288..c2027192e21e8c8a298e915e161ea592d17b83f6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c @@ -66,15 +66,20 @@ static int mlx5_cmd_dr_create_flow_table(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_table *next_ft) { struct mlx5dr_table *tbl; + u32 flags; int err; if (mlx5_dr_is_fw_table(ft->flags)) return mlx5_fs_cmd_get_fw_cmds()->create_flow_table(ns, ft, log_size, next_ft); + flags = ft->flags; + /* turn off encap/decap if not supported for sw-str by fw */ + if (!MLX5_CAP_FLOWTABLE(ns->dev, sw_owner_reformat_supported)) + flags = ft->flags & ~(MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT | + MLX5_FLOW_TABLE_TUNNEL_EN_DECAP); - tbl = mlx5dr_table_create(ns->fs_dr_domain.dr_domain, - ft->level, ft->flags); + tbl = mlx5dr_table_create(ns->fs_dr_domain.dr_domain, ft->level, flags); if (!tbl) { mlx5_core_err(ns->dev, "Failed creating dr flow_table\n"); return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c index 02f7e4a39578a33f04e030c32e1da47a322d09aa..01f075fac2765d2ad85651fbca2bf59195dcbfe1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c @@ -94,6 +94,13 @@ void mlx5_wq_cyc_wqe_dump(struct mlx5_wq_cyc *wq, u16 ix, u8 nstrides) print_hex_dump(KERN_WARNING, "", DUMP_PREFIX_OFFSET, 16, 1, wqe, len, false); } +void mlx5_wq_cyc_reset(struct mlx5_wq_cyc *wq) +{ + wq->wqe_ctr = 0; + wq->cur_sz = 0; + mlx5_wq_cyc_update_db_record(wq); +} + int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *qpc, struct mlx5_wq_qp *wq, struct mlx5_wq_ctrl *wq_ctrl) @@ -192,6 +199,19 @@ int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, return err; } +static void mlx5_wq_ll_init_list(struct mlx5_wq_ll *wq) +{ + struct mlx5_wqe_srq_next_seg *next_seg; + int i; + + for (i = 0; i < wq->fbc.sz_m1; i++) { + next_seg = mlx5_wq_ll_get_wqe(wq, i); + next_seg->next_wqe_index = cpu_to_be16(i + 1); + } + next_seg = mlx5_wq_ll_get_wqe(wq, i); + wq->tail_next = &next_seg->next_wqe_index; +} + int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *wqc, struct mlx5_wq_ll *wq, struct mlx5_wq_ctrl *wq_ctrl) @@ -199,9 +219,7 @@ int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, u8 log_wq_stride = MLX5_GET(wq, wqc, log_wq_stride); u8 log_wq_sz = MLX5_GET(wq, wqc, log_wq_sz); struct mlx5_frag_buf_ctrl *fbc = &wq->fbc; - struct mlx5_wqe_srq_next_seg *next_seg; int err; - int i; err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node); if (err) { @@ -220,13 +238,7 @@ int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, mlx5_init_fbc(wq_ctrl->buf.frags, log_wq_stride, log_wq_sz, fbc); - for (i = 0; i < fbc->sz_m1; i++) { - next_seg = mlx5_wq_ll_get_wqe(wq, i); - next_seg->next_wqe_index = cpu_to_be16(i + 1); - } - next_seg = mlx5_wq_ll_get_wqe(wq, i); - wq->tail_next = &next_seg->next_wqe_index; - + mlx5_wq_ll_init_list(wq); wq_ctrl->mdev = mdev; return 0; @@ -237,6 +249,15 @@ int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, return err; } +void mlx5_wq_ll_reset(struct mlx5_wq_ll *wq) +{ + wq->head = 0; + wq->wqe_ctr = 0; + wq->cur_sz = 0; + mlx5_wq_ll_init_list(wq); + mlx5_wq_ll_update_db_record(wq); +} + void mlx5_wq_destroy(struct mlx5_wq_ctrl *wq_ctrl) { mlx5_frag_buf_free(wq_ctrl->mdev, &wq_ctrl->buf); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h index d9a94bc223c05d470ba1cc58a1bf2a04086e1e27..4cadc336593f1cf76321ff6f85e940ea35297a10 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h @@ -80,6 +80,7 @@ int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *wqc, struct mlx5_wq_cyc *wq, struct mlx5_wq_ctrl *wq_ctrl); void mlx5_wq_cyc_wqe_dump(struct mlx5_wq_cyc *wq, u16 ix, u8 nstrides); +void mlx5_wq_cyc_reset(struct mlx5_wq_cyc *wq); int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *qpc, struct mlx5_wq_qp *wq, @@ -92,6 +93,7 @@ int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *wqc, struct mlx5_wq_ll *wq, struct mlx5_wq_ctrl *wq_ctrl); +void mlx5_wq_ll_reset(struct mlx5_wq_ll *wq); void mlx5_wq_destroy(struct mlx5_wq_ctrl *wq_ctrl); diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h index e0d7d2d9a0c81c8df137a6b01ea17c0f9066e169..43fa8c85b5d9f85d0892adbfdf28d482bb4c7e39 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h +++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h @@ -28,7 +28,7 @@ #define MLXSW_PCI_SW_RESET 0xF0010 #define MLXSW_PCI_SW_RESET_RST_BIT BIT(0) #define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS 900000 -#define MLXSW_PCI_SW_RESET_WAIT_MSECS 100 +#define MLXSW_PCI_SW_RESET_WAIT_MSECS 200 #define MLXSW_PCI_FW_READY 0xA1844 #define MLXSW_PCI_FW_READY_MASK 0xFFFF #define MLXSW_PCI_FW_READY_MAGIC 0x5E diff --git a/drivers/net/ethernet/micrel/ks8851_mll.c b/drivers/net/ethernet/micrel/ks8851_mll.c index a41a90c589db2d2e85863e6da3850307d5e2a488..58579baf3f7a007f65910938b7e3a7f3ddaed718 100644 --- a/drivers/net/ethernet/micrel/ks8851_mll.c +++ b/drivers/net/ethernet/micrel/ks8851_mll.c @@ -156,24 +156,6 @@ static int msg_enable; * chip is busy transferring packet data (RX/TX FIFO accesses). */ -/** - * ks_rdreg8 - read 8 bit register from device - * @ks : The chip information - * @offset: The register address - * - * Read a 8bit register from the chip, returning the result - */ -static u8 ks_rdreg8(struct ks_net *ks, int offset) -{ - u16 data; - u8 shift_bit = offset & 0x03; - u8 shift_data = (offset & 1) << 3; - ks->cmd_reg_cache = (u16) offset | (u16)(BE0 << shift_bit); - iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd); - data = ioread16(ks->hw_addr); - return (u8)(data >> shift_data); -} - /** * ks_rdreg16 - read 16 bit register from device * @ks : The chip information @@ -184,27 +166,11 @@ static u8 ks_rdreg8(struct ks_net *ks, int offset) static u16 ks_rdreg16(struct ks_net *ks, int offset) { - ks->cmd_reg_cache = (u16)offset | ((BE1 | BE0) << (offset & 0x02)); + ks->cmd_reg_cache = (u16)offset | ((BE3 | BE2) >> (offset & 0x02)); iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd); return ioread16(ks->hw_addr); } -/** - * ks_wrreg8 - write 8bit register value to chip - * @ks: The chip information - * @offset: The register address - * @value: The value to write - * - */ -static void ks_wrreg8(struct ks_net *ks, int offset, u8 value) -{ - u8 shift_bit = (offset & 0x03); - u16 value_write = (u16)(value << ((offset & 1) << 3)); - ks->cmd_reg_cache = (u16)offset | (BE0 << shift_bit); - iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd); - iowrite16(value_write, ks->hw_addr); -} - /** * ks_wrreg16 - write 16bit register value to chip * @ks: The chip information @@ -215,7 +181,7 @@ static void ks_wrreg8(struct ks_net *ks, int offset, u8 value) static void ks_wrreg16(struct ks_net *ks, int offset, u16 value) { - ks->cmd_reg_cache = (u16)offset | ((BE1 | BE0) << (offset & 0x02)); + ks->cmd_reg_cache = (u16)offset | ((BE3 | BE2) >> (offset & 0x02)); iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd); iowrite16(value, ks->hw_addr); } @@ -231,7 +197,7 @@ static inline void ks_inblk(struct ks_net *ks, u16 *wptr, u32 len) { len >>= 1; while (len--) - *wptr++ = (u16)ioread16(ks->hw_addr); + *wptr++ = be16_to_cpu(ioread16(ks->hw_addr)); } /** @@ -245,7 +211,7 @@ static inline void ks_outblk(struct ks_net *ks, u16 *wptr, u32 len) { len >>= 1; while (len--) - iowrite16(*wptr++, ks->hw_addr); + iowrite16(cpu_to_be16(*wptr++), ks->hw_addr); } static void ks_disable_int(struct ks_net *ks) @@ -324,8 +290,7 @@ static void ks_read_config(struct ks_net *ks) u16 reg_data = 0; /* Regardless of bus width, 8 bit read should always work.*/ - reg_data = ks_rdreg8(ks, KS_CCR) & 0x00FF; - reg_data |= ks_rdreg8(ks, KS_CCR+1) << 8; + reg_data = ks_rdreg16(ks, KS_CCR); /* addr/data bus are multiplexed */ ks->sharedbus = (reg_data & CCR_SHARED) == CCR_SHARED; @@ -429,7 +394,7 @@ static inline void ks_read_qmu(struct ks_net *ks, u16 *buf, u32 len) /* 1. set sudo DMA mode */ ks_wrreg16(ks, KS_RXFDPR, RXFDPR_RXFPAI); - ks_wrreg8(ks, KS_RXQCR, (ks->rc_rxqcr | RXQCR_SDA) & 0xff); + ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA); /* 2. read prepend data */ /** @@ -446,7 +411,7 @@ static inline void ks_read_qmu(struct ks_net *ks, u16 *buf, u32 len) ks_inblk(ks, buf, ALIGN(len, 4)); /* 4. reset sudo DMA Mode */ - ks_wrreg8(ks, KS_RXQCR, ks->rc_rxqcr); + ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr); } /** @@ -548,14 +513,17 @@ static irqreturn_t ks_irq(int irq, void *pw) { struct net_device *netdev = pw; struct ks_net *ks = netdev_priv(netdev); + unsigned long flags; u16 status; + spin_lock_irqsave(&ks->statelock, flags); /*this should be the first in IRQ handler */ ks_save_cmd_reg(ks); status = ks_rdreg16(ks, KS_ISR); if (unlikely(!status)) { ks_restore_cmd_reg(ks); + spin_unlock_irqrestore(&ks->statelock, flags); return IRQ_NONE; } @@ -581,6 +549,7 @@ static irqreturn_t ks_irq(int irq, void *pw) ks->netdev->stats.rx_over_errors++; /* this should be the last in IRQ handler*/ ks_restore_cmd_reg(ks); + spin_unlock_irqrestore(&ks->statelock, flags); return IRQ_HANDLED; } @@ -650,6 +619,7 @@ static int ks_net_stop(struct net_device *netdev) /* shutdown RX/TX QMU */ ks_disable_qmu(ks); + ks_disable_int(ks); /* set powermode to soft power down to save power */ ks_set_powermode(ks, PMECR_PM_SOFTDOWN); @@ -679,13 +649,13 @@ static void ks_write_qmu(struct ks_net *ks, u8 *pdata, u16 len) ks->txh.txw[1] = cpu_to_le16(len); /* 1. set sudo-DMA mode */ - ks_wrreg8(ks, KS_RXQCR, (ks->rc_rxqcr | RXQCR_SDA) & 0xff); + ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA); /* 2. write status/lenth info */ ks_outblk(ks, ks->txh.txw, 4); /* 3. write pkt data */ ks_outblk(ks, (u16 *)pdata, ALIGN(len, 4)); /* 4. reset sudo-DMA mode */ - ks_wrreg8(ks, KS_RXQCR, ks->rc_rxqcr); + ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr); /* 5. Enqueue Tx(move the pkt from TX buffer into TXQ) */ ks_wrreg16(ks, KS_TXQCR, TXQCR_METFE); /* 6. wait until TXQCR_METFE is auto-cleared */ @@ -706,10 +676,9 @@ static netdev_tx_t ks_start_xmit(struct sk_buff *skb, struct net_device *netdev) { netdev_tx_t retv = NETDEV_TX_OK; struct ks_net *ks = netdev_priv(netdev); + unsigned long flags; - disable_irq(netdev->irq); - ks_disable_int(ks); - spin_lock(&ks->statelock); + spin_lock_irqsave(&ks->statelock, flags); /* Extra space are required: * 4 byte for alignment, 4 for status/length, 4 for CRC @@ -723,9 +692,7 @@ static netdev_tx_t ks_start_xmit(struct sk_buff *skb, struct net_device *netdev) dev_kfree_skb(skb); } else retv = NETDEV_TX_BUSY; - spin_unlock(&ks->statelock); - ks_enable_int(ks); - enable_irq(netdev->irq); + spin_unlock_irqrestore(&ks->statelock, flags); return retv; } diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 86d543ab1ab9307c2ac790bd6368cedd67d0386c..d3b7373c59617b64bea82dd32a91ad4179c1c404 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -2176,24 +2176,29 @@ static int ocelot_init_timestamp(struct ocelot *ocelot) return 0; } -static void ocelot_port_set_mtu(struct ocelot *ocelot, int port, size_t mtu) +/* Configure the maximum SDU (L2 payload) on RX to the value specified in @sdu. + * The length of VLAN tags is accounted for automatically via DEV_MAC_TAGS_CFG. + */ +static void ocelot_port_set_maxlen(struct ocelot *ocelot, int port, size_t sdu) { struct ocelot_port *ocelot_port = ocelot->ports[port]; + int maxlen = sdu + ETH_HLEN + ETH_FCS_LEN; int atop_wm; - ocelot_port_writel(ocelot_port, mtu, DEV_MAC_MAXLEN_CFG); + ocelot_port_writel(ocelot_port, maxlen, DEV_MAC_MAXLEN_CFG); /* Set Pause WM hysteresis - * 152 = 6 * mtu / OCELOT_BUFFER_CELL_SZ - * 101 = 4 * mtu / OCELOT_BUFFER_CELL_SZ + * 152 = 6 * maxlen / OCELOT_BUFFER_CELL_SZ + * 101 = 4 * maxlen / OCELOT_BUFFER_CELL_SZ */ ocelot_write_rix(ocelot, SYS_PAUSE_CFG_PAUSE_ENA | SYS_PAUSE_CFG_PAUSE_STOP(101) | SYS_PAUSE_CFG_PAUSE_START(152), SYS_PAUSE_CFG, port); /* Tail dropping watermark */ - atop_wm = (ocelot->shared_queue_sz - 9 * mtu) / OCELOT_BUFFER_CELL_SZ; - ocelot_write_rix(ocelot, ocelot_wm_enc(9 * mtu), + atop_wm = (ocelot->shared_queue_sz - 9 * maxlen) / + OCELOT_BUFFER_CELL_SZ; + ocelot_write_rix(ocelot, ocelot_wm_enc(9 * maxlen), SYS_ATOP, port); ocelot_write(ocelot, ocelot_wm_enc(atop_wm), SYS_ATOP_TOT_CFG); } @@ -2222,9 +2227,10 @@ void ocelot_init_port(struct ocelot *ocelot, int port) DEV_MAC_HDX_CFG); /* Set Max Length and maximum tags allowed */ - ocelot_port_set_mtu(ocelot, port, VLAN_ETH_FRAME_LEN); + ocelot_port_set_maxlen(ocelot, port, ETH_DATA_LEN); ocelot_port_writel(ocelot_port, DEV_MAC_TAGS_CFG_TAG_ID(ETH_P_8021AD) | DEV_MAC_TAGS_CFG_VLAN_AWR_ENA | + DEV_MAC_TAGS_CFG_VLAN_DBL_AWR_ENA | DEV_MAC_TAGS_CFG_VLAN_LEN_AWR_ENA, DEV_MAC_TAGS_CFG); @@ -2310,18 +2316,18 @@ void ocelot_set_cpu_port(struct ocelot *ocelot, int cpu, * Only one port can be an NPI at the same time. */ if (cpu < ocelot->num_phys_ports) { - int mtu = VLAN_ETH_FRAME_LEN + OCELOT_TAG_LEN; + int sdu = ETH_DATA_LEN + OCELOT_TAG_LEN; ocelot_write(ocelot, QSYS_EXT_CPU_CFG_EXT_CPUQ_MSK_M | QSYS_EXT_CPU_CFG_EXT_CPU_PORT(cpu), QSYS_EXT_CPU_CFG); if (injection == OCELOT_TAG_PREFIX_SHORT) - mtu += OCELOT_SHORT_PREFIX_LEN; + sdu += OCELOT_SHORT_PREFIX_LEN; else if (injection == OCELOT_TAG_PREFIX_LONG) - mtu += OCELOT_LONG_PREFIX_LEN; + sdu += OCELOT_LONG_PREFIX_LEN; - ocelot_port_set_mtu(ocelot, cpu, mtu); + ocelot_port_set_maxlen(ocelot, cpu, sdu); } /* CPU port Injection/Extraction configuration */ diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c index b38820849faab9d23bcd7f06e2a0637819c96647..1135a18019c77faf4ff7c42a90de630644d8364a 100644 --- a/drivers/net/ethernet/mscc/ocelot_board.c +++ b/drivers/net/ethernet/mscc/ocelot_board.c @@ -114,6 +114,14 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg) if (err != 4) break; + /* At this point the IFH was read correctly, so it is safe to + * presume that there is no error. The err needs to be reset + * otherwise a frame could come in CPU queue between the while + * condition and the check for error later on. And in that case + * the new frame is just removed and not processed. + */ + err = 0; + ocelot_parse_ifh(ifh, &info); ocelot_port = ocelot->ports[info.port]; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c index 87f82f36812ffaa52d5dae0d191581b61c4fda15..46107de5e6c3bfb0fcc526ef46f642595c0b7304 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c @@ -103,7 +103,7 @@ int ionic_heartbeat_check(struct ionic *ionic) { struct ionic_dev *idev = &ionic->idev; unsigned long hb_time; - u32 fw_status; + u8 fw_status; u32 hb; /* wait a little more than one second before testing again */ @@ -111,9 +111,12 @@ int ionic_heartbeat_check(struct ionic *ionic) if (time_before(hb_time, (idev->last_hb_time + ionic->watchdog_period))) return 0; - /* firmware is useful only if fw_status is non-zero */ - fw_status = ioread32(&idev->dev_info_regs->fw_status); - if (!fw_status) + /* firmware is useful only if the running bit is set and + * fw_status != 0xff (bad PCI read) + */ + fw_status = ioread8(&idev->dev_info_regs->fw_status); + if (fw_status == 0xff || + !(fw_status & IONIC_FW_STS_F_RUNNING)) return -ENXIO; /* early FW has no heartbeat, else FW will return non-zero */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_if.h b/drivers/net/ethernet/pensando/ionic/ionic_if.h index ce07c2931a727a4e2571803f9d986dafe6c2e0b2..54547d53b0f22c62feda507af8a0fb1a14664f85 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_if.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_if.h @@ -2445,6 +2445,7 @@ union ionic_dev_info_regs { u8 version; u8 asic_type; u8 asic_rev; +#define IONIC_FW_STS_F_RUNNING 0x1 u8 fw_status; u32 fw_heartbeat; char fw_version[IONIC_DEVINFO_FWVERS_BUFLEN]; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 191271f6260d2923d577d81fbc53b4d4242af0d5..c2f5b691e0fa09092dc82b6361f6b2ba64a8fc70 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -1688,7 +1688,7 @@ static int ionic_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) if (!(is_zero_ether_addr(mac) || is_valid_ether_addr(mac))) return -EINVAL; - down_read(&ionic->vf_op_lock); + down_write(&ionic->vf_op_lock); if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) { ret = -EINVAL; @@ -1698,7 +1698,7 @@ static int ionic_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) ether_addr_copy(ionic->vfs[vf].macaddr, mac); } - up_read(&ionic->vf_op_lock); + up_write(&ionic->vf_op_lock); return ret; } @@ -1719,7 +1719,7 @@ static int ionic_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, if (proto != htons(ETH_P_8021Q)) return -EPROTONOSUPPORT; - down_read(&ionic->vf_op_lock); + down_write(&ionic->vf_op_lock); if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) { ret = -EINVAL; @@ -1730,7 +1730,7 @@ static int ionic_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, ionic->vfs[vf].vlanid = vlan; } - up_read(&ionic->vf_op_lock); + up_write(&ionic->vf_op_lock); return ret; } diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index e8a1b27db84debab0aad020a869660bc310b2b80..234c6f30effb7ff12ab6d0ea2cbd3e08b4610dec 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -163,6 +163,8 @@ struct qede_rdma_dev { struct list_head entry; struct list_head rdma_event_list; struct workqueue_struct *rdma_wq; + struct kref refcnt; + struct completion event_comp; bool exp_recovery; }; diff --git a/drivers/net/ethernet/qlogic/qede/qede_rdma.c b/drivers/net/ethernet/qlogic/qede/qede_rdma.c index ffabc2d2f082444e85a546db4a5b10a460a59c16..2d873ae8a234d2520a79febe99d740e3e4b95913 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_rdma.c +++ b/drivers/net/ethernet/qlogic/qede/qede_rdma.c @@ -59,6 +59,9 @@ static void _qede_rdma_dev_add(struct qede_dev *edev) static int qede_rdma_create_wq(struct qede_dev *edev) { INIT_LIST_HEAD(&edev->rdma_info.rdma_event_list); + kref_init(&edev->rdma_info.refcnt); + init_completion(&edev->rdma_info.event_comp); + edev->rdma_info.rdma_wq = create_singlethread_workqueue("rdma_wq"); if (!edev->rdma_info.rdma_wq) { DP_NOTICE(edev, "qedr: Could not create workqueue\n"); @@ -83,8 +86,23 @@ static void qede_rdma_cleanup_event(struct qede_dev *edev) } } +static void qede_rdma_complete_event(struct kref *ref) +{ + struct qede_rdma_dev *rdma_dev = + container_of(ref, struct qede_rdma_dev, refcnt); + + /* no more events will be added after this */ + complete(&rdma_dev->event_comp); +} + static void qede_rdma_destroy_wq(struct qede_dev *edev) { + /* Avoid race with add_event flow, make sure it finishes before + * we start accessing the list and cleaning up the work + */ + kref_put(&edev->rdma_info.refcnt, qede_rdma_complete_event); + wait_for_completion(&edev->rdma_info.event_comp); + qede_rdma_cleanup_event(edev); destroy_workqueue(edev->rdma_info.rdma_wq); } @@ -310,15 +328,24 @@ static void qede_rdma_add_event(struct qede_dev *edev, if (!edev->rdma_info.qedr_dev) return; + /* We don't want the cleanup flow to start while we're allocating and + * scheduling the work + */ + if (!kref_get_unless_zero(&edev->rdma_info.refcnt)) + return; /* already being destroyed */ + event_node = qede_rdma_get_free_event_node(edev); if (!event_node) - return; + goto out; event_node->event = event; event_node->ptr = edev; INIT_WORK(&event_node->work, qede_rdma_handle_event); queue_work(edev->rdma_info.rdma_wq, &event_node->work); + +out: + kref_put(&edev->rdma_info.refcnt, qede_rdma_complete_event); } void qede_rdma_dev_event_open(struct qede_dev *edev) diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c index 06de59521fc4a5e0d8861672525ab39406f98f18..fbf4cbcf1a6544b7fca722721bb94f1579493447 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c @@ -13,25 +13,6 @@ #include "rmnet_vnd.h" #include "rmnet_private.h" -/* Locking scheme - - * The shared resource which needs to be protected is realdev->rx_handler_data. - * For the writer path, this is using rtnl_lock(). The writer paths are - * rmnet_newlink(), rmnet_dellink() and rmnet_force_unassociate_device(). These - * paths are already called with rtnl_lock() acquired in. There is also an - * ASSERT_RTNL() to ensure that we are calling with rtnl acquired. For - * dereference here, we will need to use rtnl_dereference(). Dev list writing - * needs to happen with rtnl_lock() acquired for netdev_master_upper_dev_link(). - * For the reader path, the real_dev->rx_handler_data is called in the TX / RX - * path. We only need rcu_read_lock() for these scenarios. In these cases, - * the rcu_read_lock() is held in __dev_queue_xmit() and - * netif_receive_skb_internal(), so readers need to use rcu_dereference_rtnl() - * to get the relevant information. For dev list reading, we again acquire - * rcu_read_lock() in rmnet_dellink() for netdev_master_upper_dev_get_rcu(). - * We also use unregister_netdevice_many() to free all rmnet devices in - * rmnet_force_unassociate_device() so we dont lose the rtnl_lock() and free in - * same context. - */ - /* Local Definitions and Declarations */ static const struct nla_policy rmnet_policy[IFLA_RMNET_MAX + 1] = { @@ -51,9 +32,10 @@ rmnet_get_port_rtnl(const struct net_device *real_dev) return rtnl_dereference(real_dev->rx_handler_data); } -static int rmnet_unregister_real_device(struct net_device *real_dev, - struct rmnet_port *port) +static int rmnet_unregister_real_device(struct net_device *real_dev) { + struct rmnet_port *port = rmnet_get_port_rtnl(real_dev); + if (port->nr_rmnet_devs) return -EINVAL; @@ -61,9 +43,6 @@ static int rmnet_unregister_real_device(struct net_device *real_dev, kfree(port); - /* release reference on real_dev */ - dev_put(real_dev); - netdev_dbg(real_dev, "Removed from rmnet\n"); return 0; } @@ -89,9 +68,6 @@ static int rmnet_register_real_device(struct net_device *real_dev) return -EBUSY; } - /* hold on to real dev for MAP data */ - dev_hold(real_dev); - for (entry = 0; entry < RMNET_MAX_LOGICAL_EP; entry++) INIT_HLIST_HEAD(&port->muxed_ep[entry]); @@ -99,28 +75,33 @@ static int rmnet_register_real_device(struct net_device *real_dev) return 0; } -static void rmnet_unregister_bridge(struct net_device *dev, - struct rmnet_port *port) +static void rmnet_unregister_bridge(struct rmnet_port *port) { - struct rmnet_port *bridge_port; - struct net_device *bridge_dev; + struct net_device *bridge_dev, *real_dev, *rmnet_dev; + struct rmnet_port *real_port; if (port->rmnet_mode != RMNET_EPMODE_BRIDGE) return; - /* bridge slave handling */ + rmnet_dev = port->rmnet_dev; if (!port->nr_rmnet_devs) { - bridge_dev = port->bridge_ep; + /* bridge device */ + real_dev = port->bridge_ep; + bridge_dev = port->dev; - bridge_port = rmnet_get_port_rtnl(bridge_dev); - bridge_port->bridge_ep = NULL; - bridge_port->rmnet_mode = RMNET_EPMODE_VND; + real_port = rmnet_get_port_rtnl(real_dev); + real_port->bridge_ep = NULL; + real_port->rmnet_mode = RMNET_EPMODE_VND; } else { + /* real device */ bridge_dev = port->bridge_ep; - bridge_port = rmnet_get_port_rtnl(bridge_dev); - rmnet_unregister_real_device(bridge_dev, bridge_port); + port->bridge_ep = NULL; + port->rmnet_mode = RMNET_EPMODE_VND; } + + netdev_upper_dev_unlink(bridge_dev, rmnet_dev); + rmnet_unregister_real_device(bridge_dev); } static int rmnet_newlink(struct net *src_net, struct net_device *dev, @@ -135,6 +116,11 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev, int err = 0; u16 mux_id; + if (!tb[IFLA_LINK]) { + NL_SET_ERR_MSG_MOD(extack, "link not specified"); + return -EINVAL; + } + real_dev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK])); if (!real_dev || !dev) return -ENODEV; @@ -157,7 +143,12 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev, if (err) goto err1; + err = netdev_upper_dev_link(real_dev, dev, extack); + if (err < 0) + goto err2; + port->rmnet_mode = mode; + port->rmnet_dev = dev; hlist_add_head_rcu(&ep->hlnode, &port->muxed_ep[mux_id]); @@ -173,8 +164,11 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev, return 0; +err2: + unregister_netdevice(dev); + rmnet_vnd_dellink(mux_id, port, ep); err1: - rmnet_unregister_real_device(real_dev, port); + rmnet_unregister_real_device(real_dev); err0: kfree(ep); return err; @@ -183,77 +177,74 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev, static void rmnet_dellink(struct net_device *dev, struct list_head *head) { struct rmnet_priv *priv = netdev_priv(dev); - struct net_device *real_dev; + struct net_device *real_dev, *bridge_dev; + struct rmnet_port *real_port, *bridge_port; struct rmnet_endpoint *ep; - struct rmnet_port *port; - u8 mux_id; + u8 mux_id = priv->mux_id; real_dev = priv->real_dev; - if (!real_dev || !rmnet_is_real_dev_registered(real_dev)) + if (!rmnet_is_real_dev_registered(real_dev)) return; - port = rmnet_get_port_rtnl(real_dev); - - mux_id = rmnet_vnd_get_mux(dev); + real_port = rmnet_get_port_rtnl(real_dev); + bridge_dev = real_port->bridge_ep; + if (bridge_dev) { + bridge_port = rmnet_get_port_rtnl(bridge_dev); + rmnet_unregister_bridge(bridge_port); + } - ep = rmnet_get_endpoint(port, mux_id); + ep = rmnet_get_endpoint(real_port, mux_id); if (ep) { hlist_del_init_rcu(&ep->hlnode); - rmnet_unregister_bridge(dev, port); - rmnet_vnd_dellink(mux_id, port, ep); + rmnet_vnd_dellink(mux_id, real_port, ep); kfree(ep); } - rmnet_unregister_real_device(real_dev, port); + netdev_upper_dev_unlink(real_dev, dev); + rmnet_unregister_real_device(real_dev); unregister_netdevice_queue(dev, head); } -static void rmnet_force_unassociate_device(struct net_device *dev) +static void rmnet_force_unassociate_device(struct net_device *real_dev) { - struct net_device *real_dev = dev; struct hlist_node *tmp_ep; struct rmnet_endpoint *ep; struct rmnet_port *port; unsigned long bkt_ep; LIST_HEAD(list); - if (!rmnet_is_real_dev_registered(real_dev)) - return; - - ASSERT_RTNL(); - - port = rmnet_get_port_rtnl(dev); - - rcu_read_lock(); - rmnet_unregister_bridge(dev, port); - - hash_for_each_safe(port->muxed_ep, bkt_ep, tmp_ep, ep, hlnode) { - unregister_netdevice_queue(ep->egress_dev, &list); - rmnet_vnd_dellink(ep->mux_id, port, ep); + port = rmnet_get_port_rtnl(real_dev); - hlist_del_init_rcu(&ep->hlnode); - kfree(ep); + if (port->nr_rmnet_devs) { + /* real device */ + rmnet_unregister_bridge(port); + hash_for_each_safe(port->muxed_ep, bkt_ep, tmp_ep, ep, hlnode) { + unregister_netdevice_queue(ep->egress_dev, &list); + netdev_upper_dev_unlink(real_dev, ep->egress_dev); + rmnet_vnd_dellink(ep->mux_id, port, ep); + hlist_del_init_rcu(&ep->hlnode); + kfree(ep); + } + rmnet_unregister_real_device(real_dev); + unregister_netdevice_many(&list); + } else { + rmnet_unregister_bridge(port); } - - rcu_read_unlock(); - unregister_netdevice_many(&list); - - rmnet_unregister_real_device(real_dev, port); } static int rmnet_config_notify_cb(struct notifier_block *nb, unsigned long event, void *data) { - struct net_device *dev = netdev_notifier_info_to_dev(data); + struct net_device *real_dev = netdev_notifier_info_to_dev(data); - if (!dev) + if (!rmnet_is_real_dev_registered(real_dev)) return NOTIFY_DONE; switch (event) { case NETDEV_UNREGISTER: - netdev_dbg(dev, "Kernel unregister\n"); - rmnet_force_unassociate_device(dev); + netdev_dbg(real_dev, "Kernel unregister\n"); + rmnet_force_unassociate_device(real_dev); break; default: @@ -295,16 +286,18 @@ static int rmnet_changelink(struct net_device *dev, struct nlattr *tb[], if (!dev) return -ENODEV; - real_dev = __dev_get_by_index(dev_net(dev), - nla_get_u32(tb[IFLA_LINK])); - - if (!real_dev || !rmnet_is_real_dev_registered(real_dev)) + real_dev = priv->real_dev; + if (!rmnet_is_real_dev_registered(real_dev)) return -ENODEV; port = rmnet_get_port_rtnl(real_dev); if (data[IFLA_RMNET_MUX_ID]) { mux_id = nla_get_u16(data[IFLA_RMNET_MUX_ID]); + if (rmnet_get_endpoint(port, mux_id)) { + NL_SET_ERR_MSG_MOD(extack, "MUX ID already exists"); + return -EINVAL; + } ep = rmnet_get_endpoint(port, priv->mux_id); if (!ep) return -ENODEV; @@ -379,11 +372,10 @@ struct rtnl_link_ops rmnet_link_ops __read_mostly = { .fill_info = rmnet_fill_info, }; -/* Needs either rcu_read_lock() or rtnl lock */ -struct rmnet_port *rmnet_get_port(struct net_device *real_dev) +struct rmnet_port *rmnet_get_port_rcu(struct net_device *real_dev) { if (rmnet_is_real_dev_registered(real_dev)) - return rcu_dereference_rtnl(real_dev->rx_handler_data); + return rcu_dereference_bh(real_dev->rx_handler_data); else return NULL; } @@ -409,7 +401,7 @@ int rmnet_add_bridge(struct net_device *rmnet_dev, struct rmnet_port *port, *slave_port; int err; - port = rmnet_get_port(real_dev); + port = rmnet_get_port_rtnl(real_dev); /* If there is more than one rmnet dev attached, its probably being * used for muxing. Skip the briding in that case @@ -417,6 +409,9 @@ int rmnet_add_bridge(struct net_device *rmnet_dev, if (port->nr_rmnet_devs > 1) return -EINVAL; + if (port->rmnet_mode != RMNET_EPMODE_VND) + return -EINVAL; + if (rmnet_is_real_dev_registered(slave_dev)) return -EBUSY; @@ -424,9 +419,17 @@ int rmnet_add_bridge(struct net_device *rmnet_dev, if (err) return -EBUSY; - slave_port = rmnet_get_port(slave_dev); + err = netdev_master_upper_dev_link(slave_dev, rmnet_dev, NULL, NULL, + extack); + if (err) { + rmnet_unregister_real_device(slave_dev); + return err; + } + + slave_port = rmnet_get_port_rtnl(slave_dev); slave_port->rmnet_mode = RMNET_EPMODE_BRIDGE; slave_port->bridge_ep = real_dev; + slave_port->rmnet_dev = rmnet_dev; port->rmnet_mode = RMNET_EPMODE_BRIDGE; port->bridge_ep = slave_dev; @@ -438,16 +441,9 @@ int rmnet_add_bridge(struct net_device *rmnet_dev, int rmnet_del_bridge(struct net_device *rmnet_dev, struct net_device *slave_dev) { - struct rmnet_priv *priv = netdev_priv(rmnet_dev); - struct net_device *real_dev = priv->real_dev; - struct rmnet_port *port, *slave_port; + struct rmnet_port *port = rmnet_get_port_rtnl(slave_dev); - port = rmnet_get_port(real_dev); - port->rmnet_mode = RMNET_EPMODE_VND; - port->bridge_ep = NULL; - - slave_port = rmnet_get_port(slave_dev); - rmnet_unregister_real_device(slave_dev, slave_port); + rmnet_unregister_bridge(port); netdev_dbg(slave_dev, "removed from rmnet as slave\n"); return 0; @@ -473,8 +469,8 @@ static int __init rmnet_init(void) static void __exit rmnet_exit(void) { - unregister_netdevice_notifier(&rmnet_dev_notifier); rtnl_link_unregister(&rmnet_link_ops); + unregister_netdevice_notifier(&rmnet_dev_notifier); } module_init(rmnet_init) diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h index cd0a6bcbe74ade8247a428345615240faa6d9169..be515982d6286e8d9ca676e8a316b1f8e4606765 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h @@ -28,6 +28,7 @@ struct rmnet_port { u8 rmnet_mode; struct hlist_head muxed_ep[RMNET_MAX_LOGICAL_EP]; struct net_device *bridge_ep; + struct net_device *rmnet_dev; }; extern struct rtnl_link_ops rmnet_link_ops; @@ -65,7 +66,7 @@ struct rmnet_priv { struct rmnet_priv_stats stats; }; -struct rmnet_port *rmnet_get_port(struct net_device *real_dev); +struct rmnet_port *rmnet_get_port_rcu(struct net_device *real_dev); struct rmnet_endpoint *rmnet_get_endpoint(struct rmnet_port *port, u8 mux_id); int rmnet_add_bridge(struct net_device *rmnet_dev, struct net_device *slave_dev, diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c index 1b74bc16040274f21432aba798898e688e716eb5..29a7bfa2584dc95b05fbcc7de61a5c912739b435 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c @@ -159,6 +159,9 @@ static int rmnet_map_egress_handler(struct sk_buff *skb, static void rmnet_bridge_handler(struct sk_buff *skb, struct net_device *bridge_dev) { + if (skb_mac_header_was_set(skb)) + skb_push(skb, skb->mac_len); + if (bridge_dev) { skb->dev = bridge_dev; dev_queue_xmit(skb); @@ -184,7 +187,7 @@ rx_handler_result_t rmnet_rx_handler(struct sk_buff **pskb) return RX_HANDLER_PASS; dev = skb->dev; - port = rmnet_get_port(dev); + port = rmnet_get_port_rcu(dev); switch (port->rmnet_mode) { case RMNET_EPMODE_VND: @@ -217,7 +220,7 @@ void rmnet_egress_handler(struct sk_buff *skb) skb->dev = priv->real_dev; mux_id = priv->mux_id; - port = rmnet_get_port(skb->dev); + port = rmnet_get_port_rcu(skb->dev); if (!port) goto drop; diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c index 509dfc895a33ee2d0d5395b18d69bd998468dc1a..26ad40f19c64caae7476c58fb24cf7d3efe4cd13 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c @@ -266,14 +266,6 @@ int rmnet_vnd_dellink(u8 id, struct rmnet_port *port, return 0; } -u8 rmnet_vnd_get_mux(struct net_device *rmnet_dev) -{ - struct rmnet_priv *priv; - - priv = netdev_priv(rmnet_dev); - return priv->mux_id; -} - int rmnet_vnd_do_flow_control(struct net_device *rmnet_dev, int enable) { netdev_dbg(rmnet_dev, "Setting VND TX queue state to %d\n", enable); diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h index 54cbaf3c3bc4309347b5966548a3f4c49d5644f2..14d77c709d4adf63e93ba3220d2818873b2d6bab 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h @@ -16,6 +16,5 @@ int rmnet_vnd_dellink(u8 id, struct rmnet_port *port, struct rmnet_endpoint *ep); void rmnet_vnd_rx_fixup(struct sk_buff *skb, struct net_device *dev); void rmnet_vnd_tx_fixup(struct sk_buff *skb, struct net_device *dev); -u8 rmnet_vnd_get_mux(struct net_device *rmnet_dev); void rmnet_vnd_setup(struct net_device *dev); #endif /* _RMNET_VND_H_ */ diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c index c705743d69f7ab5c806c2a8c9ccfbc4b8c0dbf92..2cc8184b7e6b5338864b4f5bf5db57b2d6b2c73f 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c @@ -2277,7 +2277,7 @@ static int __init sxgbe_cmdline_opt(char *str) if (!str || !*str) return -EINVAL; while ((opt = strsep(&str, ",")) != NULL) { - if (!strncmp(opt, "eee_timer:", 6)) { + if (!strncmp(opt, "eee_timer:", 10)) { if (kstrtoint(opt + 10, 0, &eee_timer)) goto err; } diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 52113b7529d6fecd3bcbb5332a98a39a358befb4..3f16bd807c6ef65b71917a9a5af5b7235db18b9b 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -2853,11 +2853,24 @@ efx_ef10_handle_tx_event(struct efx_channel *channel, efx_qword_t *event) } /* Transmit timestamps are only available for 8XXX series. They result - * in three events per packet. These occur in order, and are: - * - the normal completion event + * in up to three events per packet. These occur in order, and are: + * - the normal completion event (may be omitted) * - the low part of the timestamp * - the high part of the timestamp * + * It's possible for multiple completion events to appear before the + * corresponding timestamps. So we can for example get: + * COMP N + * COMP N+1 + * TS_LO N + * TS_HI N + * TS_LO N+1 + * TS_HI N+1 + * + * In addition it's also possible for the adjacent completions to be + * merged, so we may not see COMP N above. As such, the completion + * events are not very useful here. + * * Each part of the timestamp is itself split across two 16 bit * fields in the event. */ @@ -2865,17 +2878,7 @@ efx_ef10_handle_tx_event(struct efx_channel *channel, efx_qword_t *event) switch (tx_ev_type) { case TX_TIMESTAMP_EVENT_TX_EV_COMPLETION: - /* In case of Queue flush or FLR, we might have received - * the previous TX completion event but not the Timestamp - * events. - */ - if (tx_queue->completed_desc_ptr != tx_queue->ptr_mask) - efx_xmit_done(tx_queue, tx_queue->completed_desc_ptr); - - tx_ev_desc_ptr = EFX_QWORD_FIELD(*event, - ESF_DZ_TX_DESCR_INDX); - tx_queue->completed_desc_ptr = - tx_ev_desc_ptr & tx_queue->ptr_mask; + /* Ignore this event - see above. */ break; case TX_TIMESTAMP_EVENT_TX_EV_TSTAMP_LO: @@ -2887,8 +2890,7 @@ efx_ef10_handle_tx_event(struct efx_channel *channel, efx_qword_t *event) ts_part = efx_ef10_extract_event_ts(event); tx_queue->completed_timestamp_major = ts_part; - efx_xmit_done(tx_queue, tx_queue->completed_desc_ptr); - tx_queue->completed_desc_ptr = tx_queue->ptr_mask; + efx_xmit_done_single(tx_queue); break; default: diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h index f1bdb04efbe4d326ebc12f7f1fd544467249825f..95395d67ea2d662878d0dc8cac63b90424db1200 100644 --- a/drivers/net/ethernet/sfc/efx.h +++ b/drivers/net/ethernet/sfc/efx.h @@ -20,6 +20,7 @@ netdev_tx_t efx_hard_start_xmit(struct sk_buff *skb, struct net_device *net_dev); netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb); void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index); +void efx_xmit_done_single(struct efx_tx_queue *tx_queue); int efx_setup_tc(struct net_device *net_dev, enum tc_setup_type type, void *type_data); extern unsigned int efx_piobuf_size; diff --git a/drivers/net/ethernet/sfc/efx_channels.c b/drivers/net/ethernet/sfc/efx_channels.c index aeb5e8aa2f2a2ba76c679ffa41dc929aff2c0bd1..73d4e39b5b1662e231e32ecc6aaae8a39e55a158 100644 --- a/drivers/net/ethernet/sfc/efx_channels.c +++ b/drivers/net/ethernet/sfc/efx_channels.c @@ -583,6 +583,7 @@ struct efx_channel *efx_copy_channel(const struct efx_channel *old_channel) if (tx_queue->channel) tx_queue->channel = channel; tx_queue->buffer = NULL; + tx_queue->cb_page = NULL; memset(&tx_queue->txd, 0, sizeof(tx_queue->txd)); } diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index 9f9886f222c864d9dfb06bf6c39ce2900c064648..8164f0edcbf0aa13f57cc24420fb8965374d5589 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -208,8 +208,6 @@ struct efx_tx_buffer { * avoid cache-line ping-pong between the xmit path and the * completion path. * @merge_events: Number of TX merged completion events - * @completed_desc_ptr: Most recent completed pointer - only used with - * timestamping. * @completed_timestamp_major: Top part of the most recent tx timestamp. * @completed_timestamp_minor: Low part of the most recent tx timestamp. * @insert_count: Current insert pointer @@ -269,7 +267,6 @@ struct efx_tx_queue { unsigned int merge_events; unsigned int bytes_compl; unsigned int pkts_compl; - unsigned int completed_desc_ptr; u32 completed_timestamp_major; u32 completed_timestamp_minor; diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c index af15a737c675611919a65d5394447900dbac3f26..59b4f16896a81e561ce6df586c255b6a8639bf4e 100644 --- a/drivers/net/ethernet/sfc/ptp.c +++ b/drivers/net/ethernet/sfc/ptp.c @@ -560,13 +560,45 @@ efx_ptp_mac_nic_to_ktime_correction(struct efx_nic *efx, u32 nic_major, u32 nic_minor, s32 correction) { + u32 sync_timestamp; ktime_t kt = { 0 }; + s16 delta; if (!(nic_major & 0x80000000)) { WARN_ON_ONCE(nic_major >> 16); - /* Use the top bits from the latest sync event. */ - nic_major &= 0xffff; - nic_major |= (last_sync_timestamp_major(efx) & 0xffff0000); + + /* Medford provides 48 bits of timestamp, so we must get the top + * 16 bits from the timesync event state. + * + * We only have the lower 16 bits of the time now, but we do + * have a full resolution timestamp at some point in past. As + * long as the difference between the (real) now and the sync + * is less than 2^15, then we can reconstruct the difference + * between those two numbers using only the lower 16 bits of + * each. + * + * Put another way + * + * a - b = ((a mod k) - b) mod k + * + * when -k/2 < (a-b) < k/2. In our case k is 2^16. We know + * (a mod k) and b, so can calculate the delta, a - b. + * + */ + sync_timestamp = last_sync_timestamp_major(efx); + + /* Because delta is s16 this does an implicit mask down to + * 16 bits which is what we need, assuming + * MEDFORD_TX_SECS_EVENT_BITS is 16. delta is signed so that + * we can deal with the (unlikely) case of sync timestamps + * arriving from the future. + */ + delta = nic_major - sync_timestamp; + + /* Recover the fully specified time now, by applying the offset + * to the (fully specified) sync time. + */ + nic_major = sync_timestamp + delta; kt = ptp->nic_to_kernel_time(nic_major, nic_minor, correction); diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index 04d7f41d7ed90c4107a0093718523d57b2a17aa5..8aafc54a4684469d645e9304733e6f8f49c6a5b3 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -535,6 +535,44 @@ netdev_tx_t efx_hard_start_xmit(struct sk_buff *skb, return efx_enqueue_skb(tx_queue, skb); } +void efx_xmit_done_single(struct efx_tx_queue *tx_queue) +{ + unsigned int pkts_compl = 0, bytes_compl = 0; + unsigned int read_ptr; + bool finished = false; + + read_ptr = tx_queue->read_count & tx_queue->ptr_mask; + + while (!finished) { + struct efx_tx_buffer *buffer = &tx_queue->buffer[read_ptr]; + + if (!efx_tx_buffer_in_use(buffer)) { + struct efx_nic *efx = tx_queue->efx; + + netif_err(efx, hw, efx->net_dev, + "TX queue %d spurious single TX completion\n", + tx_queue->queue); + efx_schedule_reset(efx, RESET_TYPE_TX_SKIP); + return; + } + + /* Need to check the flag before dequeueing. */ + if (buffer->flags & EFX_TX_BUF_SKB) + finished = true; + efx_dequeue_buffer(tx_queue, buffer, &pkts_compl, &bytes_compl); + + ++tx_queue->read_count; + read_ptr = tx_queue->read_count & tx_queue->ptr_mask; + } + + tx_queue->pkts_compl += pkts_compl; + tx_queue->bytes_compl += bytes_compl; + + EFX_WARN_ON_PARANOID(pkts_compl != 1); + + efx_xmit_done_check_empty(tx_queue); +} + void efx_init_tx_queue_core_txq(struct efx_tx_queue *tx_queue) { struct efx_nic *efx = tx_queue->efx; diff --git a/drivers/net/ethernet/sfc/tx_common.c b/drivers/net/ethernet/sfc/tx_common.c index b1571e9789d02b94f93902dfeff24386fbabc42f..70876df1da69b92b741975ad3095ef4432ef158b 100644 --- a/drivers/net/ethernet/sfc/tx_common.c +++ b/drivers/net/ethernet/sfc/tx_common.c @@ -80,7 +80,6 @@ void efx_init_tx_queue(struct efx_tx_queue *tx_queue) tx_queue->xmit_more_available = false; tx_queue->timestamping = (efx_ptp_use_mac_tx_timestamps(efx) && tx_queue->channel == efx_ptp_channel(efx)); - tx_queue->completed_desc_ptr = tx_queue->ptr_mask; tx_queue->completed_timestamp_major = 0; tx_queue->completed_timestamp_minor = 0; @@ -210,10 +209,9 @@ static void efx_dequeue_buffers(struct efx_tx_queue *tx_queue, while (read_ptr != stop_index) { struct efx_tx_buffer *buffer = &tx_queue->buffer[read_ptr]; - if (!(buffer->flags & EFX_TX_BUF_OPTION) && - unlikely(buffer->len == 0)) { + if (!efx_tx_buffer_in_use(buffer)) { netif_err(efx, tx_err, efx->net_dev, - "TX queue %d spurious TX completion id %x\n", + "TX queue %d spurious TX completion id %d\n", tx_queue->queue, read_ptr); efx_schedule_reset(efx, RESET_TYPE_TX_SKIP); return; @@ -226,6 +224,19 @@ static void efx_dequeue_buffers(struct efx_tx_queue *tx_queue, } } +void efx_xmit_done_check_empty(struct efx_tx_queue *tx_queue) +{ + if ((int)(tx_queue->read_count - tx_queue->old_write_count) >= 0) { + tx_queue->old_write_count = READ_ONCE(tx_queue->write_count); + if (tx_queue->read_count == tx_queue->old_write_count) { + /* Ensure that read_count is flushed. */ + smp_mb(); + tx_queue->empty_read_count = + tx_queue->read_count | EFX_EMPTY_COUNT_VALID; + } + } +} + void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index) { unsigned int fill_level, pkts_compl = 0, bytes_compl = 0; @@ -256,15 +267,7 @@ void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index) netif_tx_wake_queue(tx_queue->core_txq); } - /* Check whether the hardware queue is now empty */ - if ((int)(tx_queue->read_count - tx_queue->old_write_count) >= 0) { - tx_queue->old_write_count = READ_ONCE(tx_queue->write_count); - if (tx_queue->read_count == tx_queue->old_write_count) { - smp_mb(); - tx_queue->empty_read_count = - tx_queue->read_count | EFX_EMPTY_COUNT_VALID; - } - } + efx_xmit_done_check_empty(tx_queue); } /* Remove buffers put into a tx_queue for the current packet. diff --git a/drivers/net/ethernet/sfc/tx_common.h b/drivers/net/ethernet/sfc/tx_common.h index f92f1fe3a87ff27baed559478a628fadf2c8818c..99cf7ce2f36c9a169f1239c1e9d1ac17334aaa03 100644 --- a/drivers/net/ethernet/sfc/tx_common.h +++ b/drivers/net/ethernet/sfc/tx_common.h @@ -21,6 +21,12 @@ void efx_dequeue_buffer(struct efx_tx_queue *tx_queue, unsigned int *pkts_compl, unsigned int *bytes_compl); +static inline bool efx_tx_buffer_in_use(struct efx_tx_buffer *buffer) +{ + return buffer->len || (buffer->flags & EFX_TX_BUF_OPTION); +} + +void efx_xmit_done_check_empty(struct efx_tx_queue *tx_queue); void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index); void efx_enqueue_unwind(struct efx_tx_queue *tx_queue, diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c index b7032422393f69bd8c3ecd97bd8bee83258fdfff..67ddf782d98a5ab1c685b4fe8f7b4ae9acac7bf9 100644 --- a/drivers/net/ethernet/socionext/sni_ave.c +++ b/drivers/net/ethernet/socionext/sni_ave.c @@ -1810,6 +1810,9 @@ static int ave_pro4_get_pinmode(struct ave_private *priv, break; case PHY_INTERFACE_MODE_MII: case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: priv->pinmode_val = 0; break; default: @@ -1854,6 +1857,9 @@ static int ave_ld20_get_pinmode(struct ave_private *priv, priv->pinmode_val = SG_ETPINMODE_RMII(0); break; case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: priv->pinmode_val = 0; break; default: @@ -1876,6 +1882,9 @@ static int ave_pxs3_get_pinmode(struct ave_private *priv, priv->pinmode_val = SG_ETPINMODE_RMII(arg); break; case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: priv->pinmode_val = 0; break; default: diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c index d0356fbd1e4309056919926a9aa677dc9586af2a..542784300620ff41407c00fe7c6e948fc15cba32 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c @@ -24,6 +24,7 @@ static void dwmac1000_core_init(struct mac_device_info *hw, struct net_device *dev) { + struct stmmac_priv *priv = netdev_priv(dev); void __iomem *ioaddr = hw->pcsr; u32 value = readl(ioaddr + GMAC_CONTROL); int mtu = dev->mtu; @@ -35,7 +36,7 @@ static void dwmac1000_core_init(struct mac_device_info *hw, * Broadcom tags can look like invalid LLC/SNAP packets and cause the * hardware to truncate packets on reception. */ - if (netdev_uses_dsa(dev)) + if (netdev_uses_dsa(dev) || !priv->plat->enh_desc) value &= ~GMAC_CONTROL_ACS; if (mtu > 1500) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 5836b21edd7ed7b54604acb60f0d95501c1169d3..7da18c9afa01d2843d431f47430d58a6df171e05 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -4405,6 +4405,8 @@ static void stmmac_init_fs(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); + rtnl_lock(); + /* Create per netdev entries */ priv->dbgfs_dir = debugfs_create_dir(dev->name, stmmac_fs_dir); @@ -4416,14 +4418,13 @@ static void stmmac_init_fs(struct net_device *dev) debugfs_create_file("dma_cap", 0444, priv->dbgfs_dir, dev, &stmmac_dma_cap_fops); - register_netdevice_notifier(&stmmac_notifier); + rtnl_unlock(); } static void stmmac_exit_fs(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); - unregister_netdevice_notifier(&stmmac_notifier); debugfs_remove_recursive(priv->dbgfs_dir); } #endif /* CONFIG_DEBUG_FS */ @@ -4940,14 +4941,14 @@ int stmmac_dvr_remove(struct device *dev) netdev_info(priv->dev, "%s: removing driver", __func__); -#ifdef CONFIG_DEBUG_FS - stmmac_exit_fs(ndev); -#endif stmmac_stop_all_dma(priv); stmmac_mac_set(priv, priv->ioaddr, false); netif_carrier_off(ndev); unregister_netdev(ndev); +#ifdef CONFIG_DEBUG_FS + stmmac_exit_fs(ndev); +#endif phylink_destroy(priv->phylink); if (priv->plat->stmmac_rst) reset_control_assert(priv->plat->stmmac_rst); @@ -5166,6 +5167,7 @@ static int __init stmmac_init(void) /* Create debugfs main directory if it doesn't exist yet */ if (!stmmac_fs_dir) stmmac_fs_dir = debugfs_create_dir(STMMAC_RESOURCE_NAME, NULL); + register_netdevice_notifier(&stmmac_notifier); #endif return 0; @@ -5174,6 +5176,7 @@ static int __init stmmac_init(void) static void __exit stmmac_exit(void) { #ifdef CONFIG_DEBUG_FS + unregister_netdevice_notifier(&stmmac_notifier); debugfs_remove_recursive(stmmac_fs_dir); #endif } diff --git a/drivers/net/ethernet/sun/sunvnet_common.c b/drivers/net/ethernet/sun/sunvnet_common.c index c23ce838ff631280e981c9e0ab9d0bfce16c3ea9..8dc6c9ff22e1f289b5422ab1199c0867a6d3445b 100644 --- a/drivers/net/ethernet/sun/sunvnet_common.c +++ b/drivers/net/ethernet/sun/sunvnet_common.c @@ -1350,27 +1350,12 @@ sunvnet_start_xmit_common(struct sk_buff *skb, struct net_device *dev, if (vio_version_after_eq(&port->vio, 1, 3)) localmtu -= VLAN_HLEN; - if (skb->protocol == htons(ETH_P_IP)) { - struct flowi4 fl4; - struct rtable *rt = NULL; - - memset(&fl4, 0, sizeof(fl4)); - fl4.flowi4_oif = dev->ifindex; - fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos); - fl4.daddr = ip_hdr(skb)->daddr; - fl4.saddr = ip_hdr(skb)->saddr; - - rt = ip_route_output_key(dev_net(dev), &fl4); - if (!IS_ERR(rt)) { - skb_dst_set(skb, &rt->dst); - icmp_send(skb, ICMP_DEST_UNREACH, - ICMP_FRAG_NEEDED, - htonl(localmtu)); - } - } + if (skb->protocol == htons(ETH_P_IP)) + icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, + htonl(localmtu)); #if IS_ENABLED(CONFIG_IPV6) else if (skb->protocol == htons(ETH_P_IPV6)) - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, localmtu); + icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, localmtu); #endif goto out_dropped; } diff --git a/drivers/net/ethernet/xilinx/ll_temac.h b/drivers/net/ethernet/xilinx/ll_temac.h index 276292bca334d853aace75bbefcfc95477e0491d..53fb8141f1a673e7e2be3a25d0873d8d26451eab 100644 --- a/drivers/net/ethernet/xilinx/ll_temac.h +++ b/drivers/net/ethernet/xilinx/ll_temac.h @@ -375,10 +375,14 @@ struct temac_local { int tx_bd_next; int tx_bd_tail; int rx_bd_ci; + int rx_bd_tail; /* DMA channel control setup */ u32 tx_chnl_ctrl; u32 rx_chnl_ctrl; + u8 coalesce_count_rx; + + struct delayed_work restart_work; }; /* Wrappers for temac_ior()/temac_iow() function pointers above */ diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index 6f11f52c9a9ed31a41722e5737ab546b64400517..9461acec6f70f8a0e9d7de88444dd573cc0c8551 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -51,6 +51,7 @@ #include #include #include +#include #include #include #include @@ -367,6 +368,8 @@ static int temac_dma_bd_init(struct net_device *ndev) skb_dma_addr = dma_map_single(ndev->dev.parent, skb->data, XTE_MAX_JUMBO_FRAME_SIZE, DMA_FROM_DEVICE); + if (dma_mapping_error(ndev->dev.parent, skb_dma_addr)) + goto out; lp->rx_bd_v[i].phys = cpu_to_be32(skb_dma_addr); lp->rx_bd_v[i].len = cpu_to_be32(XTE_MAX_JUMBO_FRAME_SIZE); lp->rx_bd_v[i].app0 = cpu_to_be32(STS_CTRL_APP0_IRQONEND); @@ -387,12 +390,13 @@ static int temac_dma_bd_init(struct net_device *ndev) lp->tx_bd_next = 0; lp->tx_bd_tail = 0; lp->rx_bd_ci = 0; + lp->rx_bd_tail = RX_BD_NUM - 1; /* Enable RX DMA transfers */ wmb(); lp->dma_out(lp, RX_CURDESC_PTR, lp->rx_bd_p); lp->dma_out(lp, RX_TAILDESC_PTR, - lp->rx_bd_p + (sizeof(*lp->rx_bd_v) * (RX_BD_NUM - 1))); + lp->rx_bd_p + (sizeof(*lp->rx_bd_v) * lp->rx_bd_tail)); /* Prepare for TX DMA transfer */ lp->dma_out(lp, TX_CURDESC_PTR, lp->tx_bd_p); @@ -788,6 +792,9 @@ static void temac_start_xmit_done(struct net_device *ndev) stat = be32_to_cpu(cur_p->app0); } + /* Matches barrier in temac_start_xmit */ + smp_mb(); + netif_wake_queue(ndev); } @@ -830,9 +837,19 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev) cur_p = &lp->tx_bd_v[lp->tx_bd_tail]; if (temac_check_tx_bd_space(lp, num_frag + 1)) { - if (!netif_queue_stopped(ndev)) - netif_stop_queue(ndev); - return NETDEV_TX_BUSY; + if (netif_queue_stopped(ndev)) + return NETDEV_TX_BUSY; + + netif_stop_queue(ndev); + + /* Matches barrier in temac_start_xmit_done */ + smp_mb(); + + /* Space might have just been freed - check again */ + if (temac_check_tx_bd_space(lp, num_frag)) + return NETDEV_TX_BUSY; + + netif_wake_queue(ndev); } cur_p->app0 = 0; @@ -850,12 +867,16 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev) skb_dma_addr = dma_map_single(ndev->dev.parent, skb->data, skb_headlen(skb), DMA_TO_DEVICE); cur_p->len = cpu_to_be32(skb_headlen(skb)); + if (WARN_ON_ONCE(dma_mapping_error(ndev->dev.parent, skb_dma_addr))) { + dev_kfree_skb_any(skb); + ndev->stats.tx_dropped++; + return NETDEV_TX_OK; + } cur_p->phys = cpu_to_be32(skb_dma_addr); ptr_to_txbd((void *)skb, cur_p); for (ii = 0; ii < num_frag; ii++) { - lp->tx_bd_tail++; - if (lp->tx_bd_tail >= TX_BD_NUM) + if (++lp->tx_bd_tail >= TX_BD_NUM) lp->tx_bd_tail = 0; cur_p = &lp->tx_bd_v[lp->tx_bd_tail]; @@ -863,6 +884,27 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev) skb_frag_address(frag), skb_frag_size(frag), DMA_TO_DEVICE); + if (dma_mapping_error(ndev->dev.parent, skb_dma_addr)) { + if (--lp->tx_bd_tail < 0) + lp->tx_bd_tail = TX_BD_NUM - 1; + cur_p = &lp->tx_bd_v[lp->tx_bd_tail]; + while (--ii >= 0) { + --frag; + dma_unmap_single(ndev->dev.parent, + be32_to_cpu(cur_p->phys), + skb_frag_size(frag), + DMA_TO_DEVICE); + if (--lp->tx_bd_tail < 0) + lp->tx_bd_tail = TX_BD_NUM - 1; + cur_p = &lp->tx_bd_v[lp->tx_bd_tail]; + } + dma_unmap_single(ndev->dev.parent, + be32_to_cpu(cur_p->phys), + skb_headlen(skb), DMA_TO_DEVICE); + dev_kfree_skb_any(skb); + ndev->stats.tx_dropped++; + return NETDEV_TX_OK; + } cur_p->phys = cpu_to_be32(skb_dma_addr); cur_p->len = cpu_to_be32(skb_frag_size(frag)); cur_p->app0 = 0; @@ -884,31 +926,56 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev) return NETDEV_TX_OK; } +static int ll_temac_recv_buffers_available(struct temac_local *lp) +{ + int available; + + if (!lp->rx_skb[lp->rx_bd_ci]) + return 0; + available = 1 + lp->rx_bd_tail - lp->rx_bd_ci; + if (available <= 0) + available += RX_BD_NUM; + return available; +} static void ll_temac_recv(struct net_device *ndev) { struct temac_local *lp = netdev_priv(ndev); - struct sk_buff *skb, *new_skb; - unsigned int bdstat; - struct cdmac_bd *cur_p; - dma_addr_t tail_p, skb_dma_addr; - int length; unsigned long flags; + int rx_bd; + bool update_tail = false; spin_lock_irqsave(&lp->rx_lock, flags); - tail_p = lp->rx_bd_p + sizeof(*lp->rx_bd_v) * lp->rx_bd_ci; - cur_p = &lp->rx_bd_v[lp->rx_bd_ci]; - - bdstat = be32_to_cpu(cur_p->app0); - while ((bdstat & STS_CTRL_APP0_CMPLT)) { + /* Process all received buffers, passing them on network + * stack. After this, the buffer descriptors will be in an + * un-allocated stage, where no skb is allocated for it, and + * they are therefore not available for TEMAC/DMA. + */ + do { + struct cdmac_bd *bd = &lp->rx_bd_v[lp->rx_bd_ci]; + struct sk_buff *skb = lp->rx_skb[lp->rx_bd_ci]; + unsigned int bdstat = be32_to_cpu(bd->app0); + int length; + + /* While this should not normally happen, we can end + * here when GFP_ATOMIC allocations fail, and we + * therefore have un-allocated buffers. + */ + if (!skb) + break; - skb = lp->rx_skb[lp->rx_bd_ci]; - length = be32_to_cpu(cur_p->app4) & 0x3FFF; + /* Loop over all completed buffer descriptors */ + if (!(bdstat & STS_CTRL_APP0_CMPLT)) + break; - dma_unmap_single(ndev->dev.parent, be32_to_cpu(cur_p->phys), + dma_unmap_single(ndev->dev.parent, be32_to_cpu(bd->phys), XTE_MAX_JUMBO_FRAME_SIZE, DMA_FROM_DEVICE); + /* The buffer is not valid for DMA anymore */ + bd->phys = 0; + bd->len = 0; + length = be32_to_cpu(bd->app4) & 0x3FFF; skb_put(skb, length); skb->protocol = eth_type_trans(skb, ndev); skb_checksum_none_assert(skb); @@ -923,43 +990,102 @@ static void ll_temac_recv(struct net_device *ndev) * (back) for proper IP checksum byte order * (be16). */ - skb->csum = htons(be32_to_cpu(cur_p->app3) & 0xFFFF); + skb->csum = htons(be32_to_cpu(bd->app3) & 0xFFFF); skb->ip_summed = CHECKSUM_COMPLETE; } if (!skb_defer_rx_timestamp(skb)) netif_rx(skb); + /* The skb buffer is now owned by network stack above */ + lp->rx_skb[lp->rx_bd_ci] = NULL; ndev->stats.rx_packets++; ndev->stats.rx_bytes += length; - new_skb = netdev_alloc_skb_ip_align(ndev, - XTE_MAX_JUMBO_FRAME_SIZE); - if (!new_skb) { - spin_unlock_irqrestore(&lp->rx_lock, flags); - return; + rx_bd = lp->rx_bd_ci; + if (++lp->rx_bd_ci >= RX_BD_NUM) + lp->rx_bd_ci = 0; + } while (rx_bd != lp->rx_bd_tail); + + /* DMA operations will halt when the last buffer descriptor is + * processed (ie. the one pointed to by RX_TAILDESC_PTR). + * When that happens, no more interrupt events will be + * generated. No IRQ_COAL or IRQ_DLY, and not even an + * IRQ_ERR. To avoid stalling, we schedule a delayed work + * when there is a potential risk of that happening. The work + * will call this function, and thus re-schedule itself until + * enough buffers are available again. + */ + if (ll_temac_recv_buffers_available(lp) < lp->coalesce_count_rx) + schedule_delayed_work(&lp->restart_work, HZ / 1000); + + /* Allocate new buffers for those buffer descriptors that were + * passed to network stack. Note that GFP_ATOMIC allocations + * can fail (e.g. when a larger burst of GFP_ATOMIC + * allocations occurs), so while we try to allocate all + * buffers in the same interrupt where they were processed, we + * continue with what we could get in case of allocation + * failure. Allocation of remaining buffers will be retried + * in following calls. + */ + while (1) { + struct sk_buff *skb; + struct cdmac_bd *bd; + dma_addr_t skb_dma_addr; + + rx_bd = lp->rx_bd_tail + 1; + if (rx_bd >= RX_BD_NUM) + rx_bd = 0; + bd = &lp->rx_bd_v[rx_bd]; + + if (bd->phys) + break; /* All skb's allocated */ + + skb = netdev_alloc_skb_ip_align(ndev, XTE_MAX_JUMBO_FRAME_SIZE); + if (!skb) { + dev_warn(&ndev->dev, "skb alloc failed\n"); + break; } - cur_p->app0 = cpu_to_be32(STS_CTRL_APP0_IRQONEND); - skb_dma_addr = dma_map_single(ndev->dev.parent, new_skb->data, + skb_dma_addr = dma_map_single(ndev->dev.parent, skb->data, XTE_MAX_JUMBO_FRAME_SIZE, DMA_FROM_DEVICE); - cur_p->phys = cpu_to_be32(skb_dma_addr); - cur_p->len = cpu_to_be32(XTE_MAX_JUMBO_FRAME_SIZE); - lp->rx_skb[lp->rx_bd_ci] = new_skb; + if (WARN_ON_ONCE(dma_mapping_error(ndev->dev.parent, + skb_dma_addr))) { + dev_kfree_skb_any(skb); + break; + } - lp->rx_bd_ci++; - if (lp->rx_bd_ci >= RX_BD_NUM) - lp->rx_bd_ci = 0; + bd->phys = cpu_to_be32(skb_dma_addr); + bd->len = cpu_to_be32(XTE_MAX_JUMBO_FRAME_SIZE); + bd->app0 = cpu_to_be32(STS_CTRL_APP0_IRQONEND); + lp->rx_skb[rx_bd] = skb; - cur_p = &lp->rx_bd_v[lp->rx_bd_ci]; - bdstat = be32_to_cpu(cur_p->app0); + lp->rx_bd_tail = rx_bd; + update_tail = true; + } + + /* Move tail pointer when buffers have been allocated */ + if (update_tail) { + lp->dma_out(lp, RX_TAILDESC_PTR, + lp->rx_bd_p + sizeof(*lp->rx_bd_v) * lp->rx_bd_tail); } - lp->dma_out(lp, RX_TAILDESC_PTR, tail_p); spin_unlock_irqrestore(&lp->rx_lock, flags); } +/* Function scheduled to ensure a restart in case of DMA halt + * condition caused by running out of buffer descriptors. + */ +static void ll_temac_restart_work_func(struct work_struct *work) +{ + struct temac_local *lp = container_of(work, struct temac_local, + restart_work.work); + struct net_device *ndev = lp->ndev; + + ll_temac_recv(ndev); +} + static irqreturn_t ll_temac_tx_irq(int irq, void *_ndev) { struct net_device *ndev = _ndev; @@ -1052,6 +1178,8 @@ static int temac_stop(struct net_device *ndev) dev_dbg(&ndev->dev, "temac_close()\n"); + cancel_delayed_work_sync(&lp->restart_work); + free_irq(lp->tx_irq, ndev); free_irq(lp->rx_irq, ndev); @@ -1173,6 +1301,7 @@ static int temac_probe(struct platform_device *pdev) lp->dev = &pdev->dev; lp->options = XTE_OPTION_DEFAULTS; spin_lock_init(&lp->rx_lock); + INIT_DELAYED_WORK(&lp->restart_work, ll_temac_restart_work_func); /* Setup mutex for synchronization of indirect register access */ if (pdata) { @@ -1279,6 +1408,7 @@ static int temac_probe(struct platform_device *pdev) */ lp->tx_chnl_ctrl = 0x10220000; lp->rx_chnl_ctrl = 0xff070000; + lp->coalesce_count_rx = 0x07; /* Finished with the DMA node; drop the reference */ of_node_put(dma_np); @@ -1310,11 +1440,14 @@ static int temac_probe(struct platform_device *pdev) (pdata->tx_irq_count << 16); else lp->tx_chnl_ctrl = 0x10220000; - if (pdata->rx_irq_timeout || pdata->rx_irq_count) + if (pdata->rx_irq_timeout || pdata->rx_irq_count) { lp->rx_chnl_ctrl = (pdata->rx_irq_timeout << 24) | (pdata->rx_irq_count << 16); - else + lp->coalesce_count_rx = pdata->rx_irq_count; + } else { lp->rx_chnl_ctrl = 0xff070000; + lp->coalesce_count_rx = 0x07; + } } /* Error handle returned DMA RX and TX interrupts */ diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index af07ea760b359ba99a550e733f8327a6144b5957..672cd2caf2fbec6f1020f4dc30adfb8d96a8f917 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -546,8 +546,8 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev, mtu < ntohs(iph->tot_len)) { netdev_dbg(dev, "packet too big, fragmentation needed\n"); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, - htonl(mtu)); + icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, + htonl(mtu)); goto err_rt; } diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index ae3f3084c2ed29bd19522f27f51283275310beaa..1b320bcf150a4ddc91204e21b3bac4a1140cad5e 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -99,7 +99,7 @@ static struct netvsc_device *alloc_net_device(void) init_waitqueue_head(&net_device->wait_drain); net_device->destroy = false; - net_device->tx_disable = false; + net_device->tx_disable = true; net_device->max_pkt = RNDIS_MAX_PKT_DEFAULT; net_device->pkt_align = RNDIS_PKT_ALIGN_DEFAULT; diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 65e12cb07f453fb0472d5bb527748d6ee8a18f92..2c0a24c606fc7dc49cbf247d22e8082f2cad2013 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -1068,6 +1068,7 @@ static int netvsc_attach(struct net_device *ndev, } /* In any case device is now ready */ + nvdev->tx_disable = false; netif_device_attach(ndev); /* Note: enable and attach happen when sub-channels setup */ @@ -2476,6 +2477,8 @@ static int netvsc_probe(struct hv_device *dev, else net->max_mtu = ETH_DATA_LEN; + nvdev->tx_disable = false; + ret = register_netdevice(net); if (ret != 0) { pr_err("Unable to register netdev.\n"); diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 30cd0c4f0be0b4d1dea2c0a4d68d0e33d1931ebc..8801d093135c3e72ca22643a8fbc7bf896727e4b 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -293,6 +293,7 @@ void ipvlan_process_multicast(struct work_struct *work) } if (dev) dev_put(dev); + cond_resched(); } } @@ -498,19 +499,21 @@ static int ipvlan_process_outbound(struct sk_buff *skb) struct ethhdr *ethh = eth_hdr(skb); int ret = NET_XMIT_DROP; - /* In this mode we dont care about multicast and broadcast traffic */ - if (is_multicast_ether_addr(ethh->h_dest)) { - pr_debug_ratelimited("Dropped {multi|broad}cast of type=[%x]\n", - ntohs(skb->protocol)); - kfree_skb(skb); - goto out; - } - /* The ipvlan is a pseudo-L2 device, so the packets that we receive * will have L2; which need to discarded and processed further * in the net-ns of the main-device. */ if (skb_mac_header_was_set(skb)) { + /* In this mode we dont care about + * multicast and broadcast traffic */ + if (is_multicast_ether_addr(ethh->h_dest)) { + pr_debug_ratelimited( + "Dropped {multi|broad}cast of type=[%x]\n", + ntohs(skb->protocol)); + kfree_skb(skb); + goto out; + } + skb_pull(skb, sizeof(*ethh)); skb->mac_header = (typeof(skb->mac_header))~0U; skb_reset_network_header(skb); diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index a70662261a5a28d7947c33461d2f657037258adf..f195f278a83aa296c4c1285794b19b8fbc4ac497 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -164,7 +164,6 @@ static void ipvlan_uninit(struct net_device *dev) static int ipvlan_open(struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); - struct net_device *phy_dev = ipvlan->phy_dev; struct ipvl_addr *addr; if (ipvlan->port->mode == IPVLAN_MODE_L3 || @@ -178,7 +177,7 @@ static int ipvlan_open(struct net_device *dev) ipvlan_ht_addr_add(ipvlan, addr); rcu_read_unlock(); - return dev_uc_add(phy_dev, phy_dev->dev_addr); + return 0; } static int ipvlan_stop(struct net_device *dev) @@ -190,8 +189,6 @@ static int ipvlan_stop(struct net_device *dev) dev_uc_unsync(phy_dev, dev); dev_mc_unsync(phy_dev, dev); - dev_uc_del(phy_dev, phy_dev->dev_addr); - rcu_read_lock(); list_for_each_entry_rcu(addr, &ipvlan->addrs, anode) ipvlan_ht_addr_del(addr); diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 45bfd99f17fa9f6adae6a2e25fc821b23c8c8df4..6ec6fc191a6e469d1149d9e7c79009e5ae55be1b 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -424,6 +424,11 @@ static struct macsec_eth_header *macsec_ethhdr(struct sk_buff *skb) return (struct macsec_eth_header *)skb_mac_header(skb); } +static sci_t dev_to_sci(struct net_device *dev, __be16 port) +{ + return make_sci(dev->dev_addr, port); +} + static void __macsec_pn_wrapped(struct macsec_secy *secy, struct macsec_tx_sa *tx_sa) { @@ -3268,6 +3273,20 @@ static int macsec_set_mac_address(struct net_device *dev, void *p) out: ether_addr_copy(dev->dev_addr, addr->sa_data); + macsec->secy.sci = dev_to_sci(dev, MACSEC_PORT_ES); + + /* If h/w offloading is available, propagate to the device */ + if (macsec_is_offloaded(macsec)) { + const struct macsec_ops *ops; + struct macsec_context ctx; + + ops = macsec_get_ops(macsec, &ctx); + if (ops) { + ctx.secy = &macsec->secy; + macsec_offload(ops->mdo_upd_secy, &ctx); + } + } + return 0; } @@ -3342,6 +3361,7 @@ static const struct device_type macsec_type = { static const struct nla_policy macsec_rtnl_policy[IFLA_MACSEC_MAX + 1] = { [IFLA_MACSEC_SCI] = { .type = NLA_U64 }, + [IFLA_MACSEC_PORT] = { .type = NLA_U16 }, [IFLA_MACSEC_ICV_LEN] = { .type = NLA_U8 }, [IFLA_MACSEC_CIPHER_SUITE] = { .type = NLA_U64 }, [IFLA_MACSEC_WINDOW] = { .type = NLA_U32 }, @@ -3592,11 +3612,6 @@ static bool sci_exists(struct net_device *dev, sci_t sci) return false; } -static sci_t dev_to_sci(struct net_device *dev, __be16 port) -{ - return make_sci(dev->dev_addr, port); -} - static int macsec_add_dev(struct net_device *dev, sci_t sci, u8 icv_len) { struct macsec_dev *macsec = macsec_priv(dev); diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 81aa7adf480123cc15e1f8b2722128d6b2fa6236..e7289d67268fc72caf8fe186a8065454270b2190 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -334,6 +334,8 @@ static void macvlan_process_broadcast(struct work_struct *w) if (src) dev_put(src->dev); consume_skb(skb); + + cond_resched(); } } diff --git a/drivers/net/phy/bcm63xx.c b/drivers/net/phy/bcm63xx.c index 23f1958ba6ad4f6000aa0c5de4d22dca908ef248..459fb2069c7e0121d4d5c15856365b15143c834c 100644 --- a/drivers/net/phy/bcm63xx.c +++ b/drivers/net/phy/bcm63xx.c @@ -73,6 +73,7 @@ static struct phy_driver bcm63xx_driver[] = { /* same phy as above, with just a different OUI */ .phy_id = 0x002bdc00, .phy_id_mask = 0xfffffc00, + .name = "Broadcom BCM63XX (2)", /* PHY_BASIC_FEATURES */ .flags = PHY_IS_INTERNAL, .config_init = bcm63xx_config_init, diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index 7d68b28bb8938de99fb2f979cd33df9975e82903..a62229a8b1a41eca2de85cf2e3574ea31953eb95 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -410,7 +410,7 @@ static int bcm5481_config_aneg(struct phy_device *phydev) struct device_node *np = phydev->mdio.dev.of_node; int ret; - /* Aneg firsly. */ + /* Aneg firstly. */ ret = genphy_config_aneg(phydev); /* Then we can set up the delay. */ @@ -463,7 +463,7 @@ static int bcm54616s_config_aneg(struct phy_device *phydev) { int ret; - /* Aneg firsly. */ + /* Aneg firstly. */ if (phydev->dev_flags & PHY_BCM_FLAGS_MODE_1000BX) ret = genphy_c37_config_aneg(phydev); else diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 28e33ece4ce17aa132a214d2be32761bf3827cb4..9a8badafea8ac95e123d14694437f60bc44eb453 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -1306,6 +1306,9 @@ static int marvell_read_status_page_an(struct phy_device *phydev, } } + if (!(status & MII_M1011_PHY_STATUS_RESOLVED)) + return 0; + if (status & MII_M1011_PHY_STATUS_FULLDUPLEX) phydev->duplex = DUPLEX_FULL; else @@ -1365,6 +1368,8 @@ static int marvell_read_status_page(struct phy_device *phydev, int page) linkmode_zero(phydev->lp_advertising); phydev->pause = 0; phydev->asym_pause = 0; + phydev->speed = SPEED_UNKNOWN; + phydev->duplex = DUPLEX_UNKNOWN; if (phydev->autoneg == AUTONEG_ENABLE) err = marvell_read_status_page_an(phydev, fiber, status); diff --git a/drivers/net/phy/mdio-bcm-iproc.c b/drivers/net/phy/mdio-bcm-iproc.c index 7e9975d2506691ee77f319a6fb0741596a8e1bde..f1ded03f0229b1460ba992166434f3290ec23c37 100644 --- a/drivers/net/phy/mdio-bcm-iproc.c +++ b/drivers/net/phy/mdio-bcm-iproc.c @@ -178,6 +178,23 @@ static int iproc_mdio_remove(struct platform_device *pdev) return 0; } +#ifdef CONFIG_PM_SLEEP +int iproc_mdio_resume(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct iproc_mdio_priv *priv = platform_get_drvdata(pdev); + + /* restore the mii clock configuration */ + iproc_mdio_config_clk(priv->base); + + return 0; +} + +static const struct dev_pm_ops iproc_mdio_pm_ops = { + .resume = iproc_mdio_resume +}; +#endif /* CONFIG_PM_SLEEP */ + static const struct of_device_id iproc_mdio_of_match[] = { { .compatible = "brcm,iproc-mdio", }, { /* sentinel */ }, @@ -188,6 +205,9 @@ static struct platform_driver iproc_mdio_driver = { .driver = { .name = "iproc-mdio", .of_match_table = iproc_mdio_of_match, +#ifdef CONFIG_PM_SLEEP + .pm = &iproc_mdio_pm_ops, +#endif }, .probe = iproc_mdio_probe, .remove = iproc_mdio_remove, diff --git a/drivers/net/phy/mscc.c b/drivers/net/phy/mscc.c index 937ac7da278944c3d9c39cd5b16a879ea116b2b6..f686f40f6bdcceb1807275f02dc57abd84c666a4 100644 --- a/drivers/net/phy/mscc.c +++ b/drivers/net/phy/mscc.c @@ -345,11 +345,11 @@ enum macsec_bank { BIT(VSC8531_FORCE_LED_OFF) | \ BIT(VSC8531_FORCE_LED_ON)) -#define MSCC_VSC8584_REVB_INT8051_FW "mscc_vsc8584_revb_int8051_fb48.bin" +#define MSCC_VSC8584_REVB_INT8051_FW "microchip/mscc_vsc8584_revb_int8051_fb48.bin" #define MSCC_VSC8584_REVB_INT8051_FW_START_ADDR 0xe800 #define MSCC_VSC8584_REVB_INT8051_FW_CRC 0xfb48 -#define MSCC_VSC8574_REVB_INT8051_FW "mscc_vsc8574_revb_int8051_29e8.bin" +#define MSCC_VSC8574_REVB_INT8051_FW "microchip/mscc_vsc8574_revb_int8051_29e8.bin" #define MSCC_VSC8574_REVB_INT8051_FW_START_ADDR 0x4000 #define MSCC_VSC8574_REVB_INT8051_FW_CRC 0x29e8 diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c index a1caeee1223617dab21b488858b14b5d0ef2aa2a..dd2e23fb67c068674144f5c1afc97ca682bb6b8f 100644 --- a/drivers/net/phy/phy-c45.c +++ b/drivers/net/phy/phy-c45.c @@ -167,7 +167,7 @@ EXPORT_SYMBOL_GPL(genphy_c45_restart_aneg); */ int genphy_c45_check_and_restart_aneg(struct phy_device *phydev, bool restart) { - int ret = 0; + int ret; if (!restart) { /* Configure and restart aneg if it wasn't set before */ @@ -180,9 +180,9 @@ int genphy_c45_check_and_restart_aneg(struct phy_device *phydev, bool restart) } if (restart) - ret = genphy_c45_restart_aneg(phydev); + return genphy_c45_restart_aneg(phydev); - return ret; + return 0; } EXPORT_SYMBOL_GPL(genphy_c45_check_and_restart_aneg); diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index d76e038cf2cb5f7972cd0e375f7fab8d93bc13fe..355bfdef48d2b1f6c276e51bab37d3ee995a213e 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -727,7 +727,8 @@ static irqreturn_t phy_interrupt(int irq, void *phy_dat) phy_trigger_machine(phydev); } - if (phy_clear_interrupt(phydev)) + /* did_interrupt() may have cleared the interrupt already */ + if (!phydev->drv->did_interrupt && phy_clear_interrupt(phydev)) goto phy_err; return IRQ_HANDLED; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 6a5056e0ae77578cc44006eaec2fef72cf646717..28e3c5c0e3c30ca7063bd1e2f8f5b4c9414c4040 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -247,7 +247,7 @@ static bool mdio_bus_phy_may_suspend(struct phy_device *phydev) * MDIO bus driver and clock gated at this point. */ if (!netdev) - return !phydev->suspended; + goto out; if (netdev->wol_enabled) return false; @@ -267,7 +267,8 @@ static bool mdio_bus_phy_may_suspend(struct phy_device *phydev) if (device_may_wakeup(&netdev->dev)) return false; - return true; +out: + return !phydev->suspended; } static int mdio_bus_phy_suspend(struct device *dev) @@ -285,6 +286,8 @@ static int mdio_bus_phy_suspend(struct device *dev) if (!mdio_bus_phy_may_suspend(phydev)) return 0; + phydev->suspended_by_mdio_bus = 1; + return phy_suspend(phydev); } @@ -293,9 +296,11 @@ static int mdio_bus_phy_resume(struct device *dev) struct phy_device *phydev = to_phy_device(dev); int ret; - if (!mdio_bus_phy_may_suspend(phydev)) + if (!phydev->suspended_by_mdio_bus) goto no_resume; + phydev->suspended_by_mdio_bus = 0; + ret = phy_resume(phydev); if (ret < 0) return ret; @@ -1792,7 +1797,7 @@ EXPORT_SYMBOL(genphy_restart_aneg); */ int genphy_check_and_restart_aneg(struct phy_device *phydev, bool restart) { - int ret = 0; + int ret; if (!restart) { /* Advertisement hasn't changed, but maybe aneg was never on to @@ -1807,9 +1812,9 @@ int genphy_check_and_restart_aneg(struct phy_device *phydev, bool restart) } if (restart) - ret = genphy_restart_aneg(phydev); + return genphy_restart_aneg(phydev); - return ret; + return 0; } EXPORT_SYMBOL(genphy_check_and_restart_aneg); diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 70b9a143db84afb8e7cc114942354f961084b696..6e66b8e77ec7b5c017c7e0a8cf654153441c3633 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -761,8 +761,14 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy, config.interface = interface; ret = phylink_validate(pl, supported, &config); - if (ret) + if (ret) { + phylink_warn(pl, "validation of %s with support %*pb and advertisement %*pb failed: %d\n", + phy_modes(config.interface), + __ETHTOOL_LINK_MODE_MASK_NBITS, phy->supported, + __ETHTOOL_LINK_MODE_MASK_NBITS, config.advertising, + ret); return ret; + } phy->phylink = pl; phy->phy_link_change = phylink_phy_change; diff --git a/drivers/net/slip/slhc.c b/drivers/net/slip/slhc.c index 58a69f830d29bd507e5108e893d92bb8608ad8a3..f78ceba42e57e4564544b26e6701c6f0901cb3fa 100644 --- a/drivers/net/slip/slhc.c +++ b/drivers/net/slip/slhc.c @@ -232,7 +232,7 @@ slhc_compress(struct slcompress *comp, unsigned char *icp, int isize, struct cstate *cs = lcs->next; unsigned long deltaS, deltaA; short changes = 0; - int hlen; + int nlen, hlen; unsigned char new_seq[16]; unsigned char *cp = new_seq; struct iphdr *ip; @@ -248,6 +248,8 @@ slhc_compress(struct slcompress *comp, unsigned char *icp, int isize, return isize; ip = (struct iphdr *) icp; + if (ip->version != 4 || ip->ihl < 5) + return isize; /* Bail if this packet isn't TCP, or is an IP fragment */ if (ip->protocol != IPPROTO_TCP || (ntohs(ip->frag_off) & 0x3fff)) { @@ -258,10 +260,14 @@ slhc_compress(struct slcompress *comp, unsigned char *icp, int isize, comp->sls_o_tcp++; return isize; } - /* Extract TCP header */ + nlen = ip->ihl * 4; + if (isize < nlen + sizeof(*th)) + return isize; - th = (struct tcphdr *)(((unsigned char *)ip) + ip->ihl*4); - hlen = ip->ihl*4 + th->doff*4; + th = (struct tcphdr *)(icp + nlen); + if (th->doff < sizeof(struct tcphdr) / 4) + return isize; + hlen = nlen + th->doff * 4; /* Bail if the TCP packet isn't `compressible' (i.e., ACK isn't set or * some other control bit is set). Also uncompressible if diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c index 6f4d7ba8b1094eac73b0ea503bee81d9d976178c..babb01888b786c2e77c9d7b4844f44d31b9c7bce 100644 --- a/drivers/net/slip/slip.c +++ b/drivers/net/slip/slip.c @@ -863,7 +863,10 @@ static int slip_open(struct tty_struct *tty) tty->disc_data = NULL; clear_bit(SLF_INUSE, &sl->flags); sl_free_netdev(sl->dev); + /* do not call free_netdev before rtnl_unlock */ + rtnl_unlock(); free_netdev(sl->dev); + return err; err_exit: rtnl_unlock(); diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index ca70a1d840eb38522a20a47b4404a325e7aeb956..4004f98e50d9fc58a8d8d6449448840d3c9da748 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -2240,6 +2240,8 @@ team_nl_option_policy[TEAM_ATTR_OPTION_MAX + 1] = { [TEAM_ATTR_OPTION_CHANGED] = { .type = NLA_FLAG }, [TEAM_ATTR_OPTION_TYPE] = { .type = NLA_U8 }, [TEAM_ATTR_OPTION_DATA] = { .type = NLA_BINARY }, + [TEAM_ATTR_OPTION_PORT_IFINDEX] = { .type = NLA_U32 }, + [TEAM_ATTR_OPTION_ARRAY_INDEX] = { .type = NLA_U32 }, }; static int team_nl_cmd_noop(struct sk_buff *skb, struct genl_info *info) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 9485c8d1de8a37c78b210dd2a9b41aea5c1c2eb7..5754bb6ca0eeccc129b16b3b9ff433d067d00e34 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -61,7 +61,6 @@ enum qmi_wwan_flags { enum qmi_wwan_quirks { QMI_WWAN_QUIRK_DTR = 1 << 0, /* needs "set DTR" request */ - QMI_WWAN_QUIRK_QUECTEL_DYNCFG = 1 << 1, /* check num. endpoints */ }; struct qmimux_hdr { @@ -338,6 +337,9 @@ static void qmi_wwan_netdev_setup(struct net_device *net) netdev_dbg(net, "mode: raw IP\n"); } else if (!net->header_ops) { /* don't bother if already set */ ether_setup(net); + /* Restoring min/max mtu values set originally by usbnet */ + net->min_mtu = 0; + net->max_mtu = ETH_MAX_MTU; clear_bit(EVENT_NO_IP_ALIGN, &dev->flags); netdev_dbg(net, "mode: Ethernet\n"); } @@ -916,16 +918,6 @@ static const struct driver_info qmi_wwan_info_quirk_dtr = { .data = QMI_WWAN_QUIRK_DTR, }; -static const struct driver_info qmi_wwan_info_quirk_quectel_dyncfg = { - .description = "WWAN/QMI device", - .flags = FLAG_WWAN | FLAG_SEND_ZLP, - .bind = qmi_wwan_bind, - .unbind = qmi_wwan_unbind, - .manage_power = qmi_wwan_manage_power, - .rx_fixup = qmi_wwan_rx_fixup, - .data = QMI_WWAN_QUIRK_DTR | QMI_WWAN_QUIRK_QUECTEL_DYNCFG, -}; - #define HUAWEI_VENDOR_ID 0x12D1 /* map QMI/wwan function by a fixed interface number */ @@ -946,14 +938,18 @@ static const struct driver_info qmi_wwan_info_quirk_quectel_dyncfg = { #define QMI_GOBI_DEVICE(vend, prod) \ QMI_FIXED_INTF(vend, prod, 0) -/* Quectel does not use fixed interface numbers on at least some of their - * devices. We need to check the number of endpoints to ensure that we bind to - * the correct interface. +/* Many devices have QMI and DIAG functions which are distinguishable + * from other vendor specific functions by class, subclass and + * protocol all being 0xff. The DIAG function has exactly 2 endpoints + * and is silently rejected when probed. + * + * This makes it possible to match dynamically numbered QMI functions + * as seen on e.g. many Quectel modems. */ -#define QMI_QUIRK_QUECTEL_DYNCFG(vend, prod) \ +#define QMI_MATCH_FF_FF_FF(vend, prod) \ USB_DEVICE_AND_INTERFACE_INFO(vend, prod, USB_CLASS_VENDOR_SPEC, \ USB_SUBCLASS_VENDOR_SPEC, 0xff), \ - .driver_info = (unsigned long)&qmi_wwan_info_quirk_quectel_dyncfg + .driver_info = (unsigned long)&qmi_wwan_info_quirk_dtr static const struct usb_device_id products[] = { /* 1. CDC ECM like devices match on the control interface */ @@ -1059,10 +1055,10 @@ static const struct usb_device_id products[] = { USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x581d, USB_CLASS_VENDOR_SPEC, 1, 7), .driver_info = (unsigned long)&qmi_wwan_info, }, - {QMI_QUIRK_QUECTEL_DYNCFG(0x2c7c, 0x0125)}, /* Quectel EC25, EC20 R2.0 Mini PCIe */ - {QMI_QUIRK_QUECTEL_DYNCFG(0x2c7c, 0x0306)}, /* Quectel EP06/EG06/EM06 */ - {QMI_QUIRK_QUECTEL_DYNCFG(0x2c7c, 0x0512)}, /* Quectel EG12/EM12 */ - {QMI_QUIRK_QUECTEL_DYNCFG(0x2c7c, 0x0800)}, /* Quectel RM500Q-GL */ + {QMI_MATCH_FF_FF_FF(0x2c7c, 0x0125)}, /* Quectel EC25, EC20 R2.0 Mini PCIe */ + {QMI_MATCH_FF_FF_FF(0x2c7c, 0x0306)}, /* Quectel EP06/EG06/EM06 */ + {QMI_MATCH_FF_FF_FF(0x2c7c, 0x0512)}, /* Quectel EG12/EM12 */ + {QMI_MATCH_FF_FF_FF(0x2c7c, 0x0800)}, /* Quectel RM500Q-GL */ /* 3. Combined interface devices matching on interface number */ {QMI_FIXED_INTF(0x0408, 0xea42, 4)}, /* Yota / Megafon M100-1 */ @@ -1363,6 +1359,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x413c, 0x81b6, 8)}, /* Dell Wireless 5811e */ {QMI_FIXED_INTF(0x413c, 0x81b6, 10)}, /* Dell Wireless 5811e */ {QMI_FIXED_INTF(0x413c, 0x81d7, 0)}, /* Dell Wireless 5821e */ + {QMI_FIXED_INTF(0x413c, 0x81d7, 1)}, /* Dell Wireless 5821e preproduction config */ {QMI_FIXED_INTF(0x413c, 0x81e0, 0)}, /* Dell Wireless 5821e with eSIM support*/ {QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)}, /* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */ {QMI_FIXED_INTF(0x03f0, 0x9d1d, 1)}, /* HP lt4120 Snapdragon X5 LTE */ @@ -1454,7 +1451,6 @@ static int qmi_wwan_probe(struct usb_interface *intf, { struct usb_device_id *id = (struct usb_device_id *)prod; struct usb_interface_descriptor *desc = &intf->cur_altsetting->desc; - const struct driver_info *info; /* Workaround to enable dynamic IDs. This disables usbnet * blacklisting functionality. Which, if required, can be @@ -1490,12 +1486,8 @@ static int qmi_wwan_probe(struct usb_interface *intf, * different. Ignore the current interface if the number of endpoints * equals the number for the diag interface (two). */ - info = (void *)id->driver_info; - - if (info->data & QMI_WWAN_QUIRK_QUECTEL_DYNCFG) { - if (desc->bNumEndpoints == 2) - return -ENODEV; - } + if (desc->bNumEndpoints == 2) + return -ENODEV; return usbnet_probe(intf, id); } diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 78ddbaf6401b6c953971e4dd6848688483fba89f..95b19ce96513c53b1dc1f2c89fc9d255f4a334bc 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -3221,6 +3221,8 @@ static u16 r8153_phy_status(struct r8152 *tp, u16 desired) } msleep(20); + if (test_bit(RTL8152_UNPLUG, &tp->flags)) + break; } return data; @@ -5402,7 +5404,10 @@ static void r8153_init(struct r8152 *tp) if (ocp_read_word(tp, MCU_TYPE_PLA, PLA_BOOT_CTRL) & AUTOLOAD_DONE) break; + msleep(20); + if (test_bit(RTL8152_UNPLUG, &tp->flags)) + break; } data = r8153_phy_status(tp, 0); @@ -5539,7 +5544,10 @@ static void r8153b_init(struct r8152 *tp) if (ocp_read_word(tp, MCU_TYPE_PLA, PLA_BOOT_CTRL) & AUTOLOAD_DONE) break; + msleep(20); + if (test_bit(RTL8152_UNPLUG, &tp->flags)) + break; } data = r8153_phy_status(tp, 0); diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 8cdc4415fa706913e7fb66ef73abd472fa1edda8..d4cbb9e8c63f62f8dcb40806f959a5ad0b9e7d7d 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -328,7 +328,7 @@ static void veth_get_stats64(struct net_device *dev, rcu_read_lock(); peer = rcu_dereference(priv->peer); if (peer) { - tot->rx_dropped += veth_stats_tx(peer, &packets, &bytes); + veth_stats_tx(peer, &packets, &bytes); tot->rx_bytes += bytes; tot->rx_packets += packets; diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c index 16b19824b9ad0385404fb6f084407df0a4033518..cdc96968b0f4ba93c5e078f5ec46ace576f9d214 100644 --- a/drivers/net/wireguard/device.c +++ b/drivers/net/wireguard/device.c @@ -203,9 +203,9 @@ static netdev_tx_t wg_xmit(struct sk_buff *skb, struct net_device *dev) err: ++dev->stats.tx_errors; if (skb->protocol == htons(ETH_P_IP)) - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0); + icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0); else if (skb->protocol == htons(ETH_P_IPV6)) - icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0); + icmpv6_ndo_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0); kfree_skb(skb); return ret; } @@ -258,6 +258,8 @@ static void wg_setup(struct net_device *dev) enum { WG_NETDEV_FEATURES = NETIF_F_HW_CSUM | NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO | NETIF_F_GSO_SOFTWARE | NETIF_F_HIGHDMA }; + const int overhead = MESSAGE_MINIMUM_LENGTH + sizeof(struct udphdr) + + max(sizeof(struct ipv6hdr), sizeof(struct iphdr)); dev->netdev_ops = &netdev_ops; dev->hard_header_len = 0; @@ -271,9 +273,8 @@ static void wg_setup(struct net_device *dev) dev->features |= WG_NETDEV_FEATURES; dev->hw_features |= WG_NETDEV_FEATURES; dev->hw_enc_features |= WG_NETDEV_FEATURES; - dev->mtu = ETH_DATA_LEN - MESSAGE_MINIMUM_LENGTH - - sizeof(struct udphdr) - - max(sizeof(struct ipv6hdr), sizeof(struct iphdr)); + dev->mtu = ETH_DATA_LEN - overhead; + dev->max_mtu = round_down(INT_MAX, MESSAGE_PADDING_MULTIPLE) - overhead; SET_NETDEV_DEVTYPE(dev, &device_type); diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c index 9c6bab9c981f4a41d2bf008e0de739d2bd484c02..4a153894cee259504587f88e90e6ce78bfa68ea3 100644 --- a/drivers/net/wireguard/receive.c +++ b/drivers/net/wireguard/receive.c @@ -118,10 +118,13 @@ static void wg_receive_handshake_packet(struct wg_device *wg, under_load = skb_queue_len(&wg->incoming_handshakes) >= MAX_QUEUED_INCOMING_HANDSHAKES / 8; - if (under_load) + if (under_load) { last_under_load = ktime_get_coarse_boottime_ns(); - else if (last_under_load) + } else if (last_under_load) { under_load = !wg_birthdate_has_expired(last_under_load, 1); + if (!under_load) + last_under_load = 0; + } mac_state = wg_cookie_validate_packet(&wg->cookie_checker, skb, under_load); if ((under_load && mac_state == VALID_MAC_WITH_COOKIE) || diff --git a/drivers/net/wireguard/send.c b/drivers/net/wireguard/send.c index c13260563446079ae5d0fca896f1ddf64fdb4c65..7348c10cbae3db54bfcb31f23c2753185735f876 100644 --- a/drivers/net/wireguard/send.c +++ b/drivers/net/wireguard/send.c @@ -143,16 +143,22 @@ static void keep_key_fresh(struct wg_peer *peer) static unsigned int calculate_skb_padding(struct sk_buff *skb) { + unsigned int padded_size, last_unit = skb->len; + + if (unlikely(!PACKET_CB(skb)->mtu)) + return ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE) - last_unit; + /* We do this modulo business with the MTU, just in case the networking * layer gives us a packet that's bigger than the MTU. In that case, we * wouldn't want the final subtraction to overflow in the case of the - * padded_size being clamped. + * padded_size being clamped. Fortunately, that's very rarely the case, + * so we optimize for that not happening. */ - unsigned int last_unit = skb->len % PACKET_CB(skb)->mtu; - unsigned int padded_size = ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE); + if (unlikely(last_unit > PACKET_CB(skb)->mtu)) + last_unit %= PACKET_CB(skb)->mtu; - if (padded_size > PACKET_CB(skb)->mtu) - padded_size = PACKET_CB(skb)->mtu; + padded_size = min(PACKET_CB(skb)->mtu, + ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE)); return padded_size - last_unit; } diff --git a/drivers/net/wireguard/socket.c b/drivers/net/wireguard/socket.c index 262f3b5c819d5a3c7c3b2691ddc510298dc4b31a..b0d6541582d312eeed1a5a25123cb27380cd038f 100644 --- a/drivers/net/wireguard/socket.c +++ b/drivers/net/wireguard/socket.c @@ -432,7 +432,6 @@ void wg_socket_reinit(struct wg_device *wg, struct sock *new4, wg->incoming_port = ntohs(inet_sk(new4)->inet_sport); mutex_unlock(&wg->socket_update_lock); synchronize_rcu(); - synchronize_net(); sock_free(old4); sock_free(old6); } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c index 70b29bf16bb979b1789e4f2e19e9b62798a9fea4..60296a754af26a2ad9acc5ba1852b5f3438074d4 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c @@ -308,7 +308,8 @@ iwl_parse_nvm_sections(struct iwl_mvm *mvm) } /* PHY_SKU section is mandatory in B0 */ - if (!mvm->nvm_sections[NVM_SECTION_TYPE_PHY_SKU].data) { + if (mvm->trans->cfg->nvm_type == IWL_NVM_EXT && + !mvm->nvm_sections[NVM_SECTION_TYPE_PHY_SKU].data) { IWL_ERR(mvm, "Can't parse phy_sku in B0, empty sections\n"); return NULL; diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c index 6173c80189ba3e10c31a6b5f5f4575d7e06933e5..1847f55e199b0971969a0b1610be6620c5981150 100644 --- a/drivers/net/wireless/mediatek/mt76/dma.c +++ b/drivers/net/wireless/mediatek/mt76/dma.c @@ -447,10 +447,13 @@ mt76_add_fragment(struct mt76_dev *dev, struct mt76_queue *q, void *data, struct page *page = virt_to_head_page(data); int offset = data - page_address(page); struct sk_buff *skb = q->rx_head; + struct skb_shared_info *shinfo = skb_shinfo(skb); - offset += q->buf_offset; - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, offset, len, - q->buf_size); + if (shinfo->nr_frags < ARRAY_SIZE(shinfo->frags)) { + offset += q->buf_offset; + skb_add_rx_frag(skb, shinfo->nr_frags, page, offset, len, + q->buf_size); + } if (more) return; diff --git a/drivers/nfc/pn544/i2c.c b/drivers/nfc/pn544/i2c.c index 720c89d6066ef5567ebb55b72bca566a0b8336e0..4ac8cb262559ce5401dbd6a28e7f09ce0298ded4 100644 --- a/drivers/nfc/pn544/i2c.c +++ b/drivers/nfc/pn544/i2c.c @@ -225,6 +225,7 @@ static void pn544_hci_i2c_platform_init(struct pn544_i2c_phy *phy) out: gpiod_set_value_cansleep(phy->gpiod_en, !phy->en_polarity); + usleep_range(10000, 15000); } static void pn544_hci_i2c_enable_mode(struct pn544_i2c_phy *phy, int run_mode) diff --git a/drivers/nfc/pn544/pn544.c b/drivers/nfc/pn544/pn544.c index 2b83156efe3fff981404e56330ac377430f0f58c..b788870473e85d7d1c89493fce399ee37993b138 100644 --- a/drivers/nfc/pn544/pn544.c +++ b/drivers/nfc/pn544/pn544.c @@ -682,7 +682,7 @@ static int pn544_hci_tm_send(struct nfc_hci_dev *hdev, struct sk_buff *skb) static int pn544_hci_check_presence(struct nfc_hci_dev *hdev, struct nfc_target *target) { - pr_debug("supported protocol %d\b", target->supported_protocols); + pr_debug("supported protocol %d\n", target->supported_protocols); if (target->supported_protocols & (NFC_PROTO_ISO14443_MASK | NFC_PROTO_ISO14443_B_MASK)) { return nfc_hci_send_cmd(hdev, target->hci_reader_gate, diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 5dc32b72e7faab7875640106514ab88d4976ebf9..a4d8c90ee7cc4b2d0f74e9a9a0de49a5e6916667 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -66,8 +66,8 @@ MODULE_PARM_DESC(streams, "turn on support for Streams write directives"); * nvme_reset_wq - hosts nvme reset works * nvme_delete_wq - hosts nvme delete works * - * nvme_wq will host works such are scan, aen handling, fw activation, - * keep-alive error recovery, periodic reconnects etc. nvme_reset_wq + * nvme_wq will host works such as scan, aen handling, fw activation, + * keep-alive, periodic reconnects etc. nvme_reset_wq * runs reset works which also flush works hosted on nvme_wq for * serialization purposes. nvme_delete_wq host controller deletion * works which flush reset works for serialization. @@ -976,7 +976,7 @@ static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status) startka = true; spin_unlock_irqrestore(&ctrl->lock, flags); if (startka) - schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ); + queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ); } static int nvme_keep_alive(struct nvme_ctrl *ctrl) @@ -1006,7 +1006,7 @@ static void nvme_keep_alive_work(struct work_struct *work) dev_dbg(ctrl->device, "reschedule traffic based keep-alive timer\n"); ctrl->comp_seen = false; - schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ); + queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ); return; } @@ -1023,7 +1023,7 @@ static void nvme_start_keep_alive(struct nvme_ctrl *ctrl) if (unlikely(ctrl->kato == 0)) return; - schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ); + queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ); } void nvme_stop_keep_alive(struct nvme_ctrl *ctrl) @@ -1165,8 +1165,8 @@ static int nvme_identify_ns(struct nvme_ctrl *ctrl, static int nvme_features(struct nvme_ctrl *dev, u8 op, unsigned int fid, unsigned int dword11, void *buffer, size_t buflen, u32 *result) { + union nvme_result res = { 0 }; struct nvme_command c; - union nvme_result res; int ret; memset(&c, 0, sizeof(c)); @@ -3867,7 +3867,7 @@ static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl) if (!log) return; - if (nvme_get_log(ctrl, NVME_NSID_ALL, 0, NVME_LOG_FW_SLOT, log, + if (nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_FW_SLOT, 0, log, sizeof(*log), 0)) dev_warn(ctrl->device, "Get FW SLOT INFO log error\n"); kfree(log); diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 797c18337d9621b24b63227f214222d20cf2ee3e..a11900cf3a365ba4d48531b17226a27524dc4bc9 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -715,6 +715,7 @@ int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) } INIT_WORK(&ctrl->ana_work, nvme_ana_work); + kfree(ctrl->ana_log_buf); ctrl->ana_log_buf = kmalloc(ctrl->ana_log_size, GFP_KERNEL); if (!ctrl->ana_log_buf) { error = -ENOMEM; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index da392b50f73e7d28833008d1bf4c6e015309d199..d3f23d6254e47a4d1a2cfd53323a327aca17c013 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1078,9 +1078,9 @@ static int nvme_poll(struct blk_mq_hw_ctx *hctx) spin_lock(&nvmeq->cq_poll_lock); found = nvme_process_cq(nvmeq, &start, &end, -1); + nvme_complete_cqes(nvmeq, start, end); spin_unlock(&nvmeq->cq_poll_lock); - nvme_complete_cqes(nvmeq, start, end); return found; } @@ -1401,6 +1401,23 @@ static void nvme_disable_admin_queue(struct nvme_dev *dev, bool shutdown) nvme_poll_irqdisable(nvmeq, -1); } +/* + * Called only on a device that has been disabled and after all other threads + * that can check this device's completion queues have synced. This is the + * last chance for the driver to see a natural completion before + * nvme_cancel_request() terminates all incomplete requests. + */ +static void nvme_reap_pending_cqes(struct nvme_dev *dev) +{ + u16 start, end; + int i; + + for (i = dev->ctrl.queue_count - 1; i > 0; i--) { + nvme_process_cq(&dev->queues[i], &start, &end, -1); + nvme_complete_cqes(&dev->queues[i], start, end); + } +} + static int nvme_cmb_qdepth(struct nvme_dev *dev, int nr_io_queues, int entry_size) { @@ -2235,11 +2252,6 @@ static bool __nvme_disable_io_queues(struct nvme_dev *dev, u8 opcode) if (timeout == 0) return false; - /* handle any remaining CQEs */ - if (opcode == nvme_admin_delete_cq && - !test_bit(NVMEQ_DELETE_ERROR, &nvmeq->flags)) - nvme_poll_irqdisable(nvmeq, -1); - sent--; if (nr_queues) goto retry; @@ -2428,6 +2440,7 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) nvme_suspend_io_queues(dev); nvme_suspend_queue(&dev->queues[0]); nvme_pci_disable(dev); + nvme_reap_pending_cqes(dev); blk_mq_tagset_busy_iter(&dev->tagset, nvme_cancel_request, &dev->ctrl); blk_mq_tagset_busy_iter(&dev->admin_tagset, nvme_cancel_request, &dev->ctrl); @@ -2734,6 +2747,18 @@ static unsigned long check_vendor_combination_bug(struct pci_dev *pdev) (dmi_match(DMI_BOARD_NAME, "PRIME B350M-A") || dmi_match(DMI_BOARD_NAME, "PRIME Z370-A"))) return NVME_QUIRK_NO_APST; + } else if ((pdev->vendor == 0x144d && (pdev->device == 0xa801 || + pdev->device == 0xa808 || pdev->device == 0xa809)) || + (pdev->vendor == 0x1e0f && pdev->device == 0x0001)) { + /* + * Forcing to use host managed nvme power settings for + * lowest idle power with quick resume latency on + * Samsung and Toshiba SSDs based on suspend behavior + * on Coffee Lake board for LENOVO C640 + */ + if ((dmi_match(DMI_BOARD_VENDOR, "LENOVO")) && + dmi_match(DMI_BOARD_NAME, "LNVNB161216")) + return NVME_QUIRK_SIMPLE_SUSPEND; } return 0; @@ -3096,7 +3121,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_NO_DEEPEST_PS | NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) }, - { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) }, + { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001), + .driver_data = NVME_QUIRK_SINGLE_VECTOR }, { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) }, { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2005), .driver_data = NVME_QUIRK_SINGLE_VECTOR | diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 2a47c6c5007e1280a320f9776afe10005e23b98a..0fe08c4dfd2f1f288bf2eff304d1d6c79ed51481 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -850,9 +850,11 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl, if (new) blk_mq_free_tag_set(ctrl->ctrl.admin_tagset); out_free_async_qe: - nvme_rdma_free_qe(ctrl->device->dev, &ctrl->async_event_sqe, - sizeof(struct nvme_command), DMA_TO_DEVICE); - ctrl->async_event_sqe.data = NULL; + if (ctrl->async_event_sqe.data) { + nvme_rdma_free_qe(ctrl->device->dev, &ctrl->async_event_sqe, + sizeof(struct nvme_command), DMA_TO_DEVICE); + ctrl->async_event_sqe.data = NULL; + } out_free_queue: nvme_rdma_free_queue(&ctrl->queues[0]); return error; @@ -1088,7 +1090,7 @@ static void nvme_rdma_error_recovery(struct nvme_rdma_ctrl *ctrl) if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING)) return; - queue_work(nvme_wq, &ctrl->err_work); + queue_work(nvme_reset_wq, &ctrl->err_work); } static void nvme_rdma_wr_error(struct ib_cq *cq, struct ib_wc *wc, diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 6d43b23a0fc8bc15d2870da5fa850802ac9b8356..49d4373b84eb392531d7ce6f60099a41c042907d 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -422,7 +422,7 @@ static void nvme_tcp_error_recovery(struct nvme_ctrl *ctrl) if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) return; - queue_work(nvme_wq, &to_tcp_ctrl(ctrl)->err_work); + queue_work(nvme_reset_wq, &to_tcp_ctrl(ctrl)->err_work); } static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue, @@ -1054,7 +1054,12 @@ static void nvme_tcp_io_work(struct work_struct *w) } else if (unlikely(result < 0)) { dev_err(queue->ctrl->ctrl.device, "failed to send request %d\n", result); - if (result != -EPIPE) + + /* + * Fail the request unless peer closed the connection, + * in which case error recovery flow will complete all. + */ + if ((result != -EPIPE) && (result != -ECONNRESET)) nvme_tcp_fail_request(queue->request); nvme_tcp_done_send_req(queue); return; diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index af674fc0bb1e48939376cabed1b53eb8f65f4c55..5bb5342b8d0c7a729d6f7a1aff8f157cf59fe5b4 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -515,7 +515,7 @@ static int nvmet_try_send_data_pdu(struct nvmet_tcp_cmd *cmd) return 1; } -static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd) +static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd, bool last_in_batch) { struct nvmet_tcp_queue *queue = cmd->queue; int ret; @@ -523,9 +523,15 @@ static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd) while (cmd->cur_sg) { struct page *page = sg_page(cmd->cur_sg); u32 left = cmd->cur_sg->length - cmd->offset; + int flags = MSG_DONTWAIT; + + if ((!last_in_batch && cmd->queue->send_list_len) || + cmd->wbytes_done + left < cmd->req.transfer_len || + queue->data_digest || !queue->nvme_sq.sqhd_disabled) + flags |= MSG_MORE; ret = kernel_sendpage(cmd->queue->sock, page, cmd->offset, - left, MSG_DONTWAIT | MSG_MORE); + left, flags); if (ret <= 0) return ret; @@ -660,7 +666,7 @@ static int nvmet_tcp_try_send_one(struct nvmet_tcp_queue *queue, } if (cmd->state == NVMET_TCP_SEND_DATA) { - ret = nvmet_try_send_data(cmd); + ret = nvmet_try_send_data(cmd, last_in_batch); if (ret <= 0) goto done_send; } diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index 8270bbf505fbe4d873b7a67d17ffc07daeac3da6..9f982c0627a0d1bab11f11c775e778f58a7902bc 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -306,6 +306,7 @@ int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np) rc = of_mdiobus_register_phy(mdio, child, addr); if (rc && rc != -ENODEV) goto unregister; + break; } } } diff --git a/drivers/pci/controller/pcie-brcmstb.c b/drivers/pci/controller/pcie-brcmstb.c index d20aabc26273c4c2ceda98338efb6e439aebb9e5..3a10e678c7f474f631caf7c195bd7889b6f71516 100644 --- a/drivers/pci/controller/pcie-brcmstb.c +++ b/drivers/pci/controller/pcie-brcmstb.c @@ -670,7 +670,7 @@ static inline int brcm_pcie_get_rc_bar2_size_and_offset(struct brcm_pcie *pcie, * outbound memory @ 3GB). So instead it will start at the 1x * multiple of its size */ - if (!*rc_bar2_size || *rc_bar2_offset % *rc_bar2_size || + if (!*rc_bar2_size || (*rc_bar2_offset & (*rc_bar2_size - 1)) || (*rc_bar2_offset < SZ_4G && *rc_bar2_offset > SZ_2G)) { dev_err(dev, "Invalid rc_bar2_offset/size: size 0x%llx, off 0x%llx\n", *rc_bar2_size, *rc_bar2_offset); diff --git a/drivers/perf/arm_pmu_acpi.c b/drivers/perf/arm_pmu_acpi.c index acce8781c456cd7a3e36ca07bc8d18946a7fefd1..f5c7a845cd7bf24d9aec4778d2e155d630df1b6f 100644 --- a/drivers/perf/arm_pmu_acpi.c +++ b/drivers/perf/arm_pmu_acpi.c @@ -24,8 +24,6 @@ static int arm_pmu_acpi_register_irq(int cpu) int gsi, trigger; gicc = acpi_cpu_get_madt_gicc(cpu); - if (WARN_ON(!gicc)) - return -EINVAL; gsi = gicc->performance_interrupt; @@ -64,11 +62,10 @@ static void arm_pmu_acpi_unregister_irq(int cpu) int gsi; gicc = acpi_cpu_get_madt_gicc(cpu); - if (!gicc) - return; gsi = gicc->performance_interrupt; - acpi_unregister_gsi(gsi); + if (gsi) + acpi_unregister_gsi(gsi); } #if IS_ENABLED(CONFIG_ARM_SPE_PMU) diff --git a/drivers/perf/arm_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c index d704eccc548f62d2a1317ecb0e972893eb49c1e0..f01a57e5a5f3502320345d582bfaf2c887f64c14 100644 --- a/drivers/perf/arm_smmuv3_pmu.c +++ b/drivers/perf/arm_smmuv3_pmu.c @@ -771,7 +771,7 @@ static int smmu_pmu_probe(struct platform_device *pdev) smmu_pmu->reloc_base = smmu_pmu->reg_base; } - irq = platform_get_irq(pdev, 0); + irq = platform_get_irq_optional(pdev, 0); if (irq > 0) smmu_pmu->irq = irq; diff --git a/drivers/perf/fsl_imx8_ddr_perf.c b/drivers/perf/fsl_imx8_ddr_perf.c index 95dca2cb526500325dc56e9dd6a4f55e620a6eb2..90884d14f95faea01082bfd82c587ecedbd31667 100644 --- a/drivers/perf/fsl_imx8_ddr_perf.c +++ b/drivers/perf/fsl_imx8_ddr_perf.c @@ -388,9 +388,10 @@ static void ddr_perf_counter_enable(struct ddr_pmu *pmu, int config, if (enable) { /* - * must disable first, then enable again - * otherwise, cycle counter will not work - * if previous state is enabled. + * cycle counter is special which should firstly write 0 then + * write 1 into CLEAR bit to clear it. Other counters only + * need write 0 into CLEAR bit and it turns out to be 1 by + * hardware. Below enable flow is harmless for all counters. */ writel(0, pmu->base + reg); val = CNTL_EN | CNTL_CLEAR; @@ -398,7 +399,8 @@ static void ddr_perf_counter_enable(struct ddr_pmu *pmu, int config, writel(val, pmu->base + reg); } else { /* Disable counter */ - writel(0, pmu->base + reg); + val = readl_relaxed(pmu->base + reg) & CNTL_EN_MASK; + writel(val, pmu->base + reg); } } diff --git a/drivers/phy/allwinner/phy-sun50i-usb3.c b/drivers/phy/allwinner/phy-sun50i-usb3.c index 1169f3e83a6f16b661bd66c7490ddfe9842aac92..b1c04f71a31d9e6e5d0c33ad6b13f7c9e5d81159 100644 --- a/drivers/phy/allwinner/phy-sun50i-usb3.c +++ b/drivers/phy/allwinner/phy-sun50i-usb3.c @@ -49,7 +49,7 @@ #define SUNXI_LOS_BIAS(n) ((n) << 3) #define SUNXI_LOS_BIAS_MASK GENMASK(5, 3) #define SUNXI_TXVBOOSTLVL(n) ((n) << 0) -#define SUNXI_TXVBOOSTLVL_MASK GENMASK(0, 2) +#define SUNXI_TXVBOOSTLVL_MASK GENMASK(2, 0) struct sun50i_usb3_phy { struct phy *phy; diff --git a/drivers/phy/broadcom/phy-brcm-sata.c b/drivers/phy/broadcom/phy-brcm-sata.c index 4710cfcc3037f346fe08035e3f65eef8a479f890..18251f232172b7c544c823cab82e05ee601ea2b9 100644 --- a/drivers/phy/broadcom/phy-brcm-sata.c +++ b/drivers/phy/broadcom/phy-brcm-sata.c @@ -186,29 +186,6 @@ enum sata_phy_ctrl_regs { PHY_CTRL_1_RESET = BIT(0), }; -static inline void __iomem *brcm_sata_pcb_base(struct brcm_sata_port *port) -{ - struct brcm_sata_phy *priv = port->phy_priv; - u32 size = 0; - - switch (priv->version) { - case BRCM_SATA_PHY_STB_16NM: - case BRCM_SATA_PHY_STB_28NM: - case BRCM_SATA_PHY_IPROC_NS2: - case BRCM_SATA_PHY_DSL_28NM: - size = SATA_PCB_REG_28NM_SPACE_SIZE; - break; - case BRCM_SATA_PHY_STB_40NM: - size = SATA_PCB_REG_40NM_SPACE_SIZE; - break; - default: - dev_err(priv->dev, "invalid phy version\n"); - break; - } - - return priv->phy_base + (port->portnum * size); -} - static inline void __iomem *brcm_sata_ctrl_base(struct brcm_sata_port *port) { struct brcm_sata_phy *priv = port->phy_priv; @@ -226,19 +203,34 @@ static inline void __iomem *brcm_sata_ctrl_base(struct brcm_sata_port *port) return priv->ctrl_base + (port->portnum * size); } -static void brcm_sata_phy_wr(void __iomem *pcb_base, u32 bank, +static void brcm_sata_phy_wr(struct brcm_sata_port *port, u32 bank, u32 ofs, u32 msk, u32 value) { + struct brcm_sata_phy *priv = port->phy_priv; + void __iomem *pcb_base = priv->phy_base; u32 tmp; + if (priv->version == BRCM_SATA_PHY_STB_40NM) + bank += (port->portnum * SATA_PCB_REG_40NM_SPACE_SIZE); + else + pcb_base += (port->portnum * SATA_PCB_REG_28NM_SPACE_SIZE); + writel(bank, pcb_base + SATA_PCB_BANK_OFFSET); tmp = readl(pcb_base + SATA_PCB_REG_OFFSET(ofs)); tmp = (tmp & msk) | value; writel(tmp, pcb_base + SATA_PCB_REG_OFFSET(ofs)); } -static u32 brcm_sata_phy_rd(void __iomem *pcb_base, u32 bank, u32 ofs) +static u32 brcm_sata_phy_rd(struct brcm_sata_port *port, u32 bank, u32 ofs) { + struct brcm_sata_phy *priv = port->phy_priv; + void __iomem *pcb_base = priv->phy_base; + + if (priv->version == BRCM_SATA_PHY_STB_40NM) + bank += (port->portnum * SATA_PCB_REG_40NM_SPACE_SIZE); + else + pcb_base += (port->portnum * SATA_PCB_REG_28NM_SPACE_SIZE); + writel(bank, pcb_base + SATA_PCB_BANK_OFFSET); return readl(pcb_base + SATA_PCB_REG_OFFSET(ofs)); } @@ -250,16 +242,15 @@ static u32 brcm_sata_phy_rd(void __iomem *pcb_base, u32 bank, u32 ofs) static void brcm_stb_sata_ssc_init(struct brcm_sata_port *port) { - void __iomem *base = brcm_sata_pcb_base(port); struct brcm_sata_phy *priv = port->phy_priv; u32 tmp; /* override the TX spread spectrum setting */ tmp = TXPMD_CONTROL1_TX_SSC_EN_FRC_VAL | TXPMD_CONTROL1_TX_SSC_EN_FRC; - brcm_sata_phy_wr(base, TXPMD_REG_BANK, TXPMD_CONTROL1, ~tmp, tmp); + brcm_sata_phy_wr(port, TXPMD_REG_BANK, TXPMD_CONTROL1, ~tmp, tmp); /* set fixed min freq */ - brcm_sata_phy_wr(base, TXPMD_REG_BANK, TXPMD_TX_FREQ_CTRL_CONTROL2, + brcm_sata_phy_wr(port, TXPMD_REG_BANK, TXPMD_TX_FREQ_CTRL_CONTROL2, ~TXPMD_TX_FREQ_CTRL_CONTROL2_FMIN_MASK, STB_FMIN_VAL_DEFAULT); @@ -271,7 +262,7 @@ static void brcm_stb_sata_ssc_init(struct brcm_sata_port *port) tmp = STB_FMAX_VAL_DEFAULT; } - brcm_sata_phy_wr(base, TXPMD_REG_BANK, TXPMD_TX_FREQ_CTRL_CONTROL3, + brcm_sata_phy_wr(port, TXPMD_REG_BANK, TXPMD_TX_FREQ_CTRL_CONTROL3, ~TXPMD_TX_FREQ_CTRL_CONTROL3_FMAX_MASK, tmp); } @@ -280,7 +271,6 @@ static void brcm_stb_sata_ssc_init(struct brcm_sata_port *port) static int brcm_stb_sata_rxaeq_init(struct brcm_sata_port *port) { - void __iomem *base = brcm_sata_pcb_base(port); u32 tmp = 0, reg = 0; switch (port->rxaeq_mode) { @@ -301,8 +291,8 @@ static int brcm_stb_sata_rxaeq_init(struct brcm_sata_port *port) break; } - brcm_sata_phy_wr(base, AEQRX_REG_BANK_0, reg, ~tmp, tmp); - brcm_sata_phy_wr(base, AEQRX_REG_BANK_1, reg, ~tmp, tmp); + brcm_sata_phy_wr(port, AEQRX_REG_BANK_0, reg, ~tmp, tmp); + brcm_sata_phy_wr(port, AEQRX_REG_BANK_1, reg, ~tmp, tmp); return 0; } @@ -316,18 +306,17 @@ static int brcm_stb_sata_init(struct brcm_sata_port *port) static int brcm_stb_sata_16nm_ssc_init(struct brcm_sata_port *port) { - void __iomem *base = brcm_sata_pcb_base(port); u32 tmp, value; /* Reduce CP tail current to 1/16th of its default value */ - brcm_sata_phy_wr(base, PLL1_REG_BANK, PLL1_ACTRL6, 0, 0x141); + brcm_sata_phy_wr(port, PLL1_REG_BANK, PLL1_ACTRL6, 0, 0x141); /* Turn off CP tail current boost */ - brcm_sata_phy_wr(base, PLL1_REG_BANK, PLL1_ACTRL8, 0, 0xc006); + brcm_sata_phy_wr(port, PLL1_REG_BANK, PLL1_ACTRL8, 0, 0xc006); /* Set a specific AEQ equalizer value */ tmp = AEQ_FRC_EQ_FORCE_VAL | AEQ_FRC_EQ_FORCE; - brcm_sata_phy_wr(base, AEQRX_REG_BANK_0, AEQ_FRC_EQ, + brcm_sata_phy_wr(port, AEQRX_REG_BANK_0, AEQ_FRC_EQ, ~(tmp | AEQ_RFZ_FRC_VAL | AEQ_FRC_EQ_VAL_MASK << AEQ_FRC_EQ_VAL_SHIFT), tmp | 32 << AEQ_FRC_EQ_VAL_SHIFT); @@ -337,7 +326,7 @@ static int brcm_stb_sata_16nm_ssc_init(struct brcm_sata_port *port) value = 0x52; else value = 0; - brcm_sata_phy_wr(base, RXPMD_REG_BANK, RXPMD_RX_CDR_CONTROL1, + brcm_sata_phy_wr(port, RXPMD_REG_BANK, RXPMD_RX_CDR_CONTROL1, ~RXPMD_RX_PPM_VAL_MASK, value); /* Set proportional loop bandwith Gen1/2/3 */ @@ -352,7 +341,7 @@ static int brcm_stb_sata_16nm_ssc_init(struct brcm_sata_port *port) value = 1 << RXPMD_G1_CDR_PROP_BW_SHIFT | 1 << RXPMD_G2_CDR_PROP_BW_SHIFT | 1 << RXPMD_G3_CDR_PROB_BW_SHIFT; - brcm_sata_phy_wr(base, RXPMD_REG_BANK, RXPMD_RX_CDR_CDR_PROP_BW, ~tmp, + brcm_sata_phy_wr(port, RXPMD_REG_BANK, RXPMD_RX_CDR_CDR_PROP_BW, ~tmp, value); /* Set CDR integral loop acquisition bandwidth for Gen1/2/3 */ @@ -365,7 +354,7 @@ static int brcm_stb_sata_16nm_ssc_init(struct brcm_sata_port *port) 1 << RXPMD_G3_CDR_ACQ_INT_BW_SHIFT; else value = 0; - brcm_sata_phy_wr(base, RXPMD_REG_BANK, RXPMD_RX_CDR_CDR_ACQ_INTEG_BW, + brcm_sata_phy_wr(port, RXPMD_REG_BANK, RXPMD_RX_CDR_CDR_ACQ_INTEG_BW, ~tmp, value); /* Set CDR integral loop locking bandwidth to 1 for Gen 1/2/3 */ @@ -378,7 +367,7 @@ static int brcm_stb_sata_16nm_ssc_init(struct brcm_sata_port *port) 1 << RXPMD_G3_CDR_LOCK_INT_BW_SHIFT; else value = 0; - brcm_sata_phy_wr(base, RXPMD_REG_BANK, RXPMD_RX_CDR_CDR_LOCK_INTEG_BW, + brcm_sata_phy_wr(port, RXPMD_REG_BANK, RXPMD_RX_CDR_CDR_LOCK_INTEG_BW, ~tmp, value); /* Set no guard band and clamp CDR */ @@ -387,11 +376,11 @@ static int brcm_stb_sata_16nm_ssc_init(struct brcm_sata_port *port) value = 0x51; else value = 0; - brcm_sata_phy_wr(base, RXPMD_REG_BANK, RXPMD_RX_FREQ_MON_CONTROL1, + brcm_sata_phy_wr(port, RXPMD_REG_BANK, RXPMD_RX_FREQ_MON_CONTROL1, ~tmp, RXPMD_MON_CORRECT_EN | value); /* Turn on/off SSC */ - brcm_sata_phy_wr(base, TX_REG_BANK, TX_ACTRL5, ~TX_ACTRL5_SSC_EN, + brcm_sata_phy_wr(port, TX_REG_BANK, TX_ACTRL5, ~TX_ACTRL5_SSC_EN, port->ssc_en ? TX_ACTRL5_SSC_EN : 0); return 0; @@ -411,7 +400,6 @@ static int brcm_ns2_sata_init(struct brcm_sata_port *port) { int try; unsigned int val; - void __iomem *base = brcm_sata_pcb_base(port); void __iomem *ctrl_base = brcm_sata_ctrl_base(port); struct device *dev = port->phy_priv->dev; @@ -421,24 +409,24 @@ static int brcm_ns2_sata_init(struct brcm_sata_port *port) val |= (0x4 << OOB_CTRL1_BURST_MIN_SHIFT); val |= (0x9 << OOB_CTRL1_WAKE_IDLE_MAX_SHIFT); val |= (0x3 << OOB_CTRL1_WAKE_IDLE_MIN_SHIFT); - brcm_sata_phy_wr(base, OOB_REG_BANK, OOB_CTRL1, 0x0, val); + brcm_sata_phy_wr(port, OOB_REG_BANK, OOB_CTRL1, 0x0, val); val = 0x0; val |= (0x1b << OOB_CTRL2_RESET_IDLE_MAX_SHIFT); val |= (0x2 << OOB_CTRL2_BURST_CNT_SHIFT); val |= (0x9 << OOB_CTRL2_RESET_IDLE_MIN_SHIFT); - brcm_sata_phy_wr(base, OOB_REG_BANK, OOB_CTRL2, 0x0, val); + brcm_sata_phy_wr(port, OOB_REG_BANK, OOB_CTRL2, 0x0, val); /* Configure PHY PLL register bank 1 */ val = NS2_PLL1_ACTRL2_MAGIC; - brcm_sata_phy_wr(base, PLL1_REG_BANK, PLL1_ACTRL2, 0x0, val); + brcm_sata_phy_wr(port, PLL1_REG_BANK, PLL1_ACTRL2, 0x0, val); val = NS2_PLL1_ACTRL3_MAGIC; - brcm_sata_phy_wr(base, PLL1_REG_BANK, PLL1_ACTRL3, 0x0, val); + brcm_sata_phy_wr(port, PLL1_REG_BANK, PLL1_ACTRL3, 0x0, val); val = NS2_PLL1_ACTRL4_MAGIC; - brcm_sata_phy_wr(base, PLL1_REG_BANK, PLL1_ACTRL4, 0x0, val); + brcm_sata_phy_wr(port, PLL1_REG_BANK, PLL1_ACTRL4, 0x0, val); /* Configure PHY BLOCK0 register bank */ /* Set oob_clk_sel to refclk/2 */ - brcm_sata_phy_wr(base, BLOCK0_REG_BANK, BLOCK0_SPARE, + brcm_sata_phy_wr(port, BLOCK0_REG_BANK, BLOCK0_SPARE, ~BLOCK0_SPARE_OOB_CLK_SEL_MASK, BLOCK0_SPARE_OOB_CLK_SEL_REFBY2); @@ -451,7 +439,7 @@ static int brcm_ns2_sata_init(struct brcm_sata_port *port) /* Wait for PHY PLL lock by polling pll_lock bit */ try = 50; while (try) { - val = brcm_sata_phy_rd(base, BLOCK0_REG_BANK, + val = brcm_sata_phy_rd(port, BLOCK0_REG_BANK, BLOCK0_XGXSSTATUS); if (val & BLOCK0_XGXSSTATUS_PLL_LOCK) break; @@ -471,9 +459,7 @@ static int brcm_ns2_sata_init(struct brcm_sata_port *port) static int brcm_nsp_sata_init(struct brcm_sata_port *port) { - struct brcm_sata_phy *priv = port->phy_priv; struct device *dev = port->phy_priv->dev; - void __iomem *base = priv->phy_base; unsigned int oob_bank; unsigned int val, try; @@ -490,36 +476,36 @@ static int brcm_nsp_sata_init(struct brcm_sata_port *port) val |= (0x06 << OOB_CTRL1_BURST_MIN_SHIFT); val |= (0x0f << OOB_CTRL1_WAKE_IDLE_MAX_SHIFT); val |= (0x06 << OOB_CTRL1_WAKE_IDLE_MIN_SHIFT); - brcm_sata_phy_wr(base, oob_bank, OOB_CTRL1, 0x0, val); + brcm_sata_phy_wr(port, oob_bank, OOB_CTRL1, 0x0, val); val = 0x0; val |= (0x2e << OOB_CTRL2_RESET_IDLE_MAX_SHIFT); val |= (0x02 << OOB_CTRL2_BURST_CNT_SHIFT); val |= (0x16 << OOB_CTRL2_RESET_IDLE_MIN_SHIFT); - brcm_sata_phy_wr(base, oob_bank, OOB_CTRL2, 0x0, val); + brcm_sata_phy_wr(port, oob_bank, OOB_CTRL2, 0x0, val); - brcm_sata_phy_wr(base, PLL_REG_BANK_0, PLL_ACTRL2, + brcm_sata_phy_wr(port, PLL_REG_BANK_0, PLL_ACTRL2, ~(PLL_ACTRL2_SELDIV_MASK << PLL_ACTRL2_SELDIV_SHIFT), 0x0c << PLL_ACTRL2_SELDIV_SHIFT); - brcm_sata_phy_wr(base, PLL_REG_BANK_0, PLL_CAP_CONTROL, + brcm_sata_phy_wr(port, PLL_REG_BANK_0, PLL_CAP_CONTROL, 0xff0, 0x4f0); val = PLLCONTROL_0_FREQ_DET_RESTART | PLLCONTROL_0_FREQ_MONITOR; - brcm_sata_phy_wr(base, PLL_REG_BANK_0, PLL_REG_BANK_0_PLLCONTROL_0, + brcm_sata_phy_wr(port, PLL_REG_BANK_0, PLL_REG_BANK_0_PLLCONTROL_0, ~val, val); val = PLLCONTROL_0_SEQ_START; - brcm_sata_phy_wr(base, PLL_REG_BANK_0, PLL_REG_BANK_0_PLLCONTROL_0, + brcm_sata_phy_wr(port, PLL_REG_BANK_0, PLL_REG_BANK_0_PLLCONTROL_0, ~val, 0); mdelay(10); - brcm_sata_phy_wr(base, PLL_REG_BANK_0, PLL_REG_BANK_0_PLLCONTROL_0, + brcm_sata_phy_wr(port, PLL_REG_BANK_0, PLL_REG_BANK_0_PLLCONTROL_0, ~val, val); /* Wait for pll_seq_done bit */ try = 50; while (--try) { - val = brcm_sata_phy_rd(base, BLOCK0_REG_BANK, + val = brcm_sata_phy_rd(port, BLOCK0_REG_BANK, BLOCK0_XGXSSTATUS); if (val & BLOCK0_XGXSSTATUS_PLL_LOCK) break; @@ -546,27 +532,25 @@ static int brcm_nsp_sata_init(struct brcm_sata_port *port) static int brcm_sr_sata_init(struct brcm_sata_port *port) { - struct brcm_sata_phy *priv = port->phy_priv; struct device *dev = port->phy_priv->dev; - void __iomem *base = priv->phy_base; unsigned int val, try; /* Configure PHY PLL register bank 1 */ val = SR_PLL1_ACTRL2_MAGIC; - brcm_sata_phy_wr(base, PLL1_REG_BANK, PLL1_ACTRL2, 0x0, val); + brcm_sata_phy_wr(port, PLL1_REG_BANK, PLL1_ACTRL2, 0x0, val); val = SR_PLL1_ACTRL3_MAGIC; - brcm_sata_phy_wr(base, PLL1_REG_BANK, PLL1_ACTRL3, 0x0, val); + brcm_sata_phy_wr(port, PLL1_REG_BANK, PLL1_ACTRL3, 0x0, val); val = SR_PLL1_ACTRL4_MAGIC; - brcm_sata_phy_wr(base, PLL1_REG_BANK, PLL1_ACTRL4, 0x0, val); + brcm_sata_phy_wr(port, PLL1_REG_BANK, PLL1_ACTRL4, 0x0, val); /* Configure PHY PLL register bank 0 */ val = SR_PLL0_ACTRL6_MAGIC; - brcm_sata_phy_wr(base, PLL_REG_BANK_0, PLL_ACTRL6, 0x0, val); + brcm_sata_phy_wr(port, PLL_REG_BANK_0, PLL_ACTRL6, 0x0, val); /* Wait for PHY PLL lock by polling pll_lock bit */ try = 50; do { - val = brcm_sata_phy_rd(base, BLOCK0_REG_BANK, + val = brcm_sata_phy_rd(port, BLOCK0_REG_BANK, BLOCK0_XGXSSTATUS); if (val & BLOCK0_XGXSSTATUS_PLL_LOCK) break; @@ -581,7 +565,7 @@ static int brcm_sr_sata_init(struct brcm_sata_port *port) } /* Invert Tx polarity */ - brcm_sata_phy_wr(base, TX_REG_BANK, TX_ACTRL0, + brcm_sata_phy_wr(port, TX_REG_BANK, TX_ACTRL0, ~TX_ACTRL0_TXPOL_FLIP, TX_ACTRL0_TXPOL_FLIP); /* Configure OOB control to handle 100MHz reference clock */ @@ -589,52 +573,51 @@ static int brcm_sr_sata_init(struct brcm_sata_port *port) (0x4 << OOB_CTRL1_BURST_MIN_SHIFT) | (0x8 << OOB_CTRL1_WAKE_IDLE_MAX_SHIFT) | (0x3 << OOB_CTRL1_WAKE_IDLE_MIN_SHIFT)); - brcm_sata_phy_wr(base, OOB_REG_BANK, OOB_CTRL1, 0x0, val); + brcm_sata_phy_wr(port, OOB_REG_BANK, OOB_CTRL1, 0x0, val); val = ((0x1b << OOB_CTRL2_RESET_IDLE_MAX_SHIFT) | (0x2 << OOB_CTRL2_BURST_CNT_SHIFT) | (0x9 << OOB_CTRL2_RESET_IDLE_MIN_SHIFT)); - brcm_sata_phy_wr(base, OOB_REG_BANK, OOB_CTRL2, 0x0, val); + brcm_sata_phy_wr(port, OOB_REG_BANK, OOB_CTRL2, 0x0, val); return 0; } static int brcm_dsl_sata_init(struct brcm_sata_port *port) { - void __iomem *base = brcm_sata_pcb_base(port); struct device *dev = port->phy_priv->dev; unsigned int try; u32 tmp; - brcm_sata_phy_wr(base, PLL1_REG_BANK, PLL1_ACTRL7, 0, 0x873); + brcm_sata_phy_wr(port, PLL1_REG_BANK, PLL1_ACTRL7, 0, 0x873); - brcm_sata_phy_wr(base, PLL1_REG_BANK, PLL1_ACTRL6, 0, 0xc000); + brcm_sata_phy_wr(port, PLL1_REG_BANK, PLL1_ACTRL6, 0, 0xc000); - brcm_sata_phy_wr(base, PLL_REG_BANK_0, PLL_REG_BANK_0_PLLCONTROL_0, + brcm_sata_phy_wr(port, PLL_REG_BANK_0, PLL_REG_BANK_0_PLLCONTROL_0, 0, 0x3089); usleep_range(1000, 2000); - brcm_sata_phy_wr(base, PLL_REG_BANK_0, PLL_REG_BANK_0_PLLCONTROL_0, + brcm_sata_phy_wr(port, PLL_REG_BANK_0, PLL_REG_BANK_0_PLLCONTROL_0, 0, 0x3088); usleep_range(1000, 2000); - brcm_sata_phy_wr(base, AEQRX_REG_BANK_1, AEQRX_SLCAL0_CTRL0, + brcm_sata_phy_wr(port, AEQRX_REG_BANK_1, AEQRX_SLCAL0_CTRL0, 0, 0x3000); - brcm_sata_phy_wr(base, AEQRX_REG_BANK_1, AEQRX_SLCAL1_CTRL0, + brcm_sata_phy_wr(port, AEQRX_REG_BANK_1, AEQRX_SLCAL1_CTRL0, 0, 0x3000); usleep_range(1000, 2000); - brcm_sata_phy_wr(base, PLL_REG_BANK_0, PLL_CAP_CHARGE_TIME, 0, 0x32); + brcm_sata_phy_wr(port, PLL_REG_BANK_0, PLL_CAP_CHARGE_TIME, 0, 0x32); - brcm_sata_phy_wr(base, PLL_REG_BANK_0, PLL_VCO_CAL_THRESH, 0, 0xa); + brcm_sata_phy_wr(port, PLL_REG_BANK_0, PLL_VCO_CAL_THRESH, 0, 0xa); - brcm_sata_phy_wr(base, PLL_REG_BANK_0, PLL_FREQ_DET_TIME, 0, 0x64); + brcm_sata_phy_wr(port, PLL_REG_BANK_0, PLL_FREQ_DET_TIME, 0, 0x64); usleep_range(1000, 2000); /* Acquire PLL lock */ try = 50; while (try) { - tmp = brcm_sata_phy_rd(base, BLOCK0_REG_BANK, + tmp = brcm_sata_phy_rd(port, BLOCK0_REG_BANK, BLOCK0_XGXSSTATUS); if (tmp & BLOCK0_XGXSSTATUS_PLL_LOCK) break; @@ -687,10 +670,9 @@ static int brcm_sata_phy_init(struct phy *phy) static void brcm_stb_sata_calibrate(struct brcm_sata_port *port) { - void __iomem *base = brcm_sata_pcb_base(port); u32 tmp = BIT(8); - brcm_sata_phy_wr(base, RXPMD_REG_BANK, RXPMD_RX_FREQ_MON_CONTROL1, + brcm_sata_phy_wr(port, RXPMD_REG_BANK, RXPMD_RX_FREQ_MON_CONTROL1, ~tmp, tmp); } diff --git a/drivers/phy/motorola/phy-mapphone-mdm6600.c b/drivers/phy/motorola/phy-mapphone-mdm6600.c index f20524f0c21d9aea86013601ec47c381bf32db26..94a34cf75eb3975d5b27073061fa40e141b6f06b 100644 --- a/drivers/phy/motorola/phy-mapphone-mdm6600.c +++ b/drivers/phy/motorola/phy-mapphone-mdm6600.c @@ -20,6 +20,7 @@ #define PHY_MDM6600_PHY_DELAY_MS 4000 /* PHY enable 2.2s to 3.5s */ #define PHY_MDM6600_ENABLED_DELAY_MS 8000 /* 8s more total for MDM6600 */ +#define PHY_MDM6600_WAKE_KICK_MS 600 /* time on after GPIO toggle */ #define MDM6600_MODEM_IDLE_DELAY_MS 1000 /* modem after USB suspend */ #define MDM6600_MODEM_WAKE_DELAY_MS 200 /* modem response after idle */ @@ -243,10 +244,24 @@ static irqreturn_t phy_mdm6600_wakeirq_thread(int irq, void *data) { struct phy_mdm6600 *ddata = data; struct gpio_desc *mode_gpio1; + int error, wakeup; mode_gpio1 = ddata->mode_gpios->desc[PHY_MDM6600_MODE1]; - dev_dbg(ddata->dev, "OOB wake on mode_gpio1: %i\n", - gpiod_get_value(mode_gpio1)); + wakeup = gpiod_get_value(mode_gpio1); + if (!wakeup) + return IRQ_NONE; + + dev_dbg(ddata->dev, "OOB wake on mode_gpio1: %i\n", wakeup); + error = pm_runtime_get_sync(ddata->dev); + if (error < 0) { + pm_runtime_put_noidle(ddata->dev); + + return IRQ_NONE; + } + + /* Just wake-up and kick the autosuspend timer */ + pm_runtime_mark_last_busy(ddata->dev); + pm_runtime_put_autosuspend(ddata->dev); return IRQ_HANDLED; } @@ -496,8 +511,14 @@ static void phy_mdm6600_modem_wake(struct work_struct *work) ddata = container_of(work, struct phy_mdm6600, modem_wake_work.work); phy_mdm6600_wake_modem(ddata); + + /* + * The modem does not always stay awake 1.2 seconds after toggling + * the wake GPIO, and sometimes it idles after about some 600 ms + * making writes time out. + */ schedule_delayed_work(&ddata->modem_wake_work, - msecs_to_jiffies(MDM6600_MODEM_IDLE_DELAY_MS)); + msecs_to_jiffies(PHY_MDM6600_WAKE_KICK_MS)); } static int __maybe_unused phy_mdm6600_runtime_suspend(struct device *dev) diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c index cd5a6c95dbdc1f3e1b544242de5953dfb55fccbe..a27b8d578d7fc449dab7facd3e3a6993375621f1 100644 --- a/drivers/phy/phy-core.c +++ b/drivers/phy/phy-core.c @@ -688,11 +688,9 @@ struct phy *phy_get(struct device *dev, const char *string) get_device(&phy->dev); link = device_link_add(dev, &phy->dev, DL_FLAG_STATELESS); - if (!link) { - dev_err(dev, "failed to create device link to %s\n", + if (!link) + dev_dbg(dev, "failed to create device link to %s\n", dev_name(phy->dev.parent)); - return ERR_PTR(-EINVAL); - } return phy; } @@ -803,11 +801,9 @@ struct phy *devm_of_phy_get(struct device *dev, struct device_node *np, } link = device_link_add(dev, &phy->dev, DL_FLAG_STATELESS); - if (!link) { - dev_err(dev, "failed to create device link to %s\n", + if (!link) + dev_dbg(dev, "failed to create device link to %s\n", dev_name(phy->dev.parent)); - return ERR_PTR(-EINVAL); - } return phy; } @@ -852,11 +848,9 @@ struct phy *devm_of_phy_get_by_index(struct device *dev, struct device_node *np, devres_add(dev, ptr); link = device_link_add(dev, &phy->dev, DL_FLAG_STATELESS); - if (!link) { - dev_err(dev, "failed to create device link to %s\n", + if (!link) + dev_dbg(dev, "failed to create device link to %s\n", dev_name(phy->dev.parent)); - return ERR_PTR(-EINVAL); - } return phy; } diff --git a/drivers/phy/ti/phy-gmii-sel.c b/drivers/phy/ti/phy-gmii-sel.c index a28bd15297f53401bf0d390d020a359f21303a26..1c536fc03c83c83e29dc57ae622d9220b3b9c92e 100644 --- a/drivers/phy/ti/phy-gmii-sel.c +++ b/drivers/phy/ti/phy-gmii-sel.c @@ -80,20 +80,20 @@ static int phy_gmii_sel_mode(struct phy *phy, enum phy_mode mode, int submode) break; case PHY_INTERFACE_MODE_MII: - mode = AM33XX_GMII_SEL_MODE_MII; + case PHY_INTERFACE_MODE_GMII: + gmii_sel_mode = AM33XX_GMII_SEL_MODE_MII; break; default: - dev_warn(dev, - "port%u: unsupported mode: \"%s\". Defaulting to MII.\n", - if_phy->id, phy_modes(rgmii_id)); + dev_warn(dev, "port%u: unsupported mode: \"%s\"\n", + if_phy->id, phy_modes(submode)); return -EINVAL; } if_phy->phy_if_mode = submode; dev_dbg(dev, "%s id:%u mode:%u rgmii_id:%d rmii_clk_ext:%d\n", - __func__, if_phy->id, mode, rgmii_id, + __func__, if_phy->id, submode, rgmii_id, if_phy->rmii_clock_external); regfield = if_phy->fields[PHY_GMII_SEL_PORT_MODE]; diff --git a/drivers/pinctrl/cirrus/pinctrl-madera-core.c b/drivers/pinctrl/cirrus/pinctrl-madera-core.c index 7b6409ef553c949ad25c0b4e63f496073a833b1b..dce2626384a903aeab78cc01d5ddd762097194ab 100644 --- a/drivers/pinctrl/cirrus/pinctrl-madera-core.c +++ b/drivers/pinctrl/cirrus/pinctrl-madera-core.c @@ -1073,13 +1073,26 @@ static int madera_pin_probe(struct platform_device *pdev) return ret; } + platform_set_drvdata(pdev, priv); + dev_dbg(priv->dev, "pinctrl probed ok\n"); return 0; } +static int madera_pin_remove(struct platform_device *pdev) +{ + struct madera_pin_private *priv = platform_get_drvdata(pdev); + + if (priv->madera->pdata.gpio_configs) + pinctrl_unregister_mappings(priv->madera->pdata.gpio_configs); + + return 0; +} + static struct platform_driver madera_pin_driver = { .probe = madera_pin_probe, + .remove = madera_pin_remove, .driver = { .name = "madera-pinctrl", }, diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c index 446d84fe0e31c7ec471bfc7fa66a3e782996ac04..f23c55e221955ed0a7721019aedc2c31c27ec4d5 100644 --- a/drivers/pinctrl/core.c +++ b/drivers/pinctrl/core.c @@ -2021,7 +2021,6 @@ static int pinctrl_claim_hogs(struct pinctrl_dev *pctldev) return PTR_ERR(pctldev->p); } - kref_get(&pctldev->p->users); pctldev->hog_default = pinctrl_lookup_state(pctldev->p, PINCTRL_STATE_DEFAULT); if (IS_ERR(pctldev->hog_default)) { diff --git a/drivers/pinctrl/freescale/pinctrl-scu.c b/drivers/pinctrl/freescale/pinctrl-scu.c index 73bf1d9f9cc6f098d572a4769bd689258c4b24b0..23cf04bdfc55d4551852463eabc6a8c81550f080 100644 --- a/drivers/pinctrl/freescale/pinctrl-scu.c +++ b/drivers/pinctrl/freescale/pinctrl-scu.c @@ -23,12 +23,12 @@ struct imx_sc_msg_req_pad_set { struct imx_sc_rpc_msg hdr; u32 val; u16 pad; -} __packed; +} __packed __aligned(4); struct imx_sc_msg_req_pad_get { struct imx_sc_rpc_msg hdr; u16 pad; -} __packed; +} __packed __aligned(4); struct imx_sc_msg_resp_pad_get { struct imx_sc_rpc_msg hdr; diff --git a/drivers/pinctrl/meson/pinctrl-meson-gxl.c b/drivers/pinctrl/meson/pinctrl-meson-gxl.c index 1b6e8646700f9b31510a82ddff5e41e0438dde77..2ac921c83da9140fa2907bc89db297cd0ef5071d 100644 --- a/drivers/pinctrl/meson/pinctrl-meson-gxl.c +++ b/drivers/pinctrl/meson/pinctrl-meson-gxl.c @@ -147,8 +147,8 @@ static const unsigned int sdio_d0_pins[] = { GPIOX_0 }; static const unsigned int sdio_d1_pins[] = { GPIOX_1 }; static const unsigned int sdio_d2_pins[] = { GPIOX_2 }; static const unsigned int sdio_d3_pins[] = { GPIOX_3 }; -static const unsigned int sdio_cmd_pins[] = { GPIOX_4 }; -static const unsigned int sdio_clk_pins[] = { GPIOX_5 }; +static const unsigned int sdio_clk_pins[] = { GPIOX_4 }; +static const unsigned int sdio_cmd_pins[] = { GPIOX_5 }; static const unsigned int sdio_irq_pins[] = { GPIOX_7 }; static const unsigned int nand_ce0_pins[] = { BOOT_8 }; diff --git a/drivers/pinctrl/pinctrl-falcon.c b/drivers/pinctrl/pinctrl-falcon.c index a454f57c264eede94a37a7d51573fc3c717c2982..62c02b969327f8f0b1e9f7da2e25adf16f4aaa7c 100644 --- a/drivers/pinctrl/pinctrl-falcon.c +++ b/drivers/pinctrl/pinctrl-falcon.c @@ -451,7 +451,7 @@ static int pinctrl_falcon_probe(struct platform_device *pdev) falcon_info.clk[*bank] = clk_get(&ppdev->dev, NULL); if (IS_ERR(falcon_info.clk[*bank])) { dev_err(&ppdev->dev, "failed to get clock\n"); - of_node_put(np) + of_node_put(np); return PTR_ERR(falcon_info.clk[*bank]); } falcon_info.membase[*bank] = devm_ioremap_resource(&pdev->dev, diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c index 9a8daa256a32136e5ce044e594074d351b59bc54..1a948c3f54b7ca4ad6fd246d097d34f7a9115583 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.c +++ b/drivers/pinctrl/qcom/pinctrl-msm.c @@ -1104,7 +1104,6 @@ static int msm_gpio_init(struct msm_pinctrl *pctrl) pctrl->irq_chip.irq_mask = msm_gpio_irq_mask; pctrl->irq_chip.irq_unmask = msm_gpio_irq_unmask; pctrl->irq_chip.irq_ack = msm_gpio_irq_ack; - pctrl->irq_chip.irq_eoi = irq_chip_eoi_parent; pctrl->irq_chip.irq_set_type = msm_gpio_irq_set_type; pctrl->irq_chip.irq_set_wake = msm_gpio_irq_set_wake; pctrl->irq_chip.irq_request_resources = msm_gpio_irq_reqres; @@ -1118,7 +1117,7 @@ static int msm_gpio_init(struct msm_pinctrl *pctrl) if (!chip->irq.parent_domain) return -EPROBE_DEFER; chip->irq.child_to_parent_hwirq = msm_gpio_wakeirq; - + pctrl->irq_chip.irq_eoi = irq_chip_eoi_parent; /* * Let's skip handling the GPIOs, if the parent irqchip * is handling the direct connect IRQ of the GPIO. diff --git a/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c b/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c index fba1d41d20ece4a245872e5ed99a0ebd2612df66..338a15d08629440d8d6290a6be0f0a2b42daf63f 100644 --- a/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c +++ b/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c @@ -794,7 +794,7 @@ static int pm8xxx_gpio_probe(struct platform_device *pdev) girq->fwnode = of_node_to_fwnode(pctrl->dev->of_node); girq->parent_domain = parent_domain; girq->child_to_parent_hwirq = pm8xxx_child_to_parent_hwirq; - girq->populate_parent_alloc_arg = gpiochip_populate_parent_fwspec_fourcell; + girq->populate_parent_alloc_arg = gpiochip_populate_parent_fwspec_twocell; girq->child_offset_to_irq = pm8xxx_child_offset_to_irq; girq->child_irq_domain_ops.translate = pm8xxx_domain_translate; diff --git a/drivers/platform/chrome/wilco_ec/properties.c b/drivers/platform/chrome/wilco_ec/properties.c index e69682c95ea2d7f3a0d678b3c7bd3384aa905a7b..62f27610dd33a18cb8e67922489e6811c284eae7 100644 --- a/drivers/platform/chrome/wilco_ec/properties.c +++ b/drivers/platform/chrome/wilco_ec/properties.c @@ -5,7 +5,7 @@ #include #include -#include +#include /* Operation code; what the EC should do with the property */ enum ec_property_op { diff --git a/drivers/regulator/stm32-vrefbuf.c b/drivers/regulator/stm32-vrefbuf.c index bdfaf7edb75a1b9e10690cae08e5e6cb53a72d3b..992bc18101ef58285616fa0b9bea8e288b47d3b5 100644 --- a/drivers/regulator/stm32-vrefbuf.c +++ b/drivers/regulator/stm32-vrefbuf.c @@ -88,7 +88,7 @@ static int stm32_vrefbuf_disable(struct regulator_dev *rdev) } val = readl_relaxed(priv->base + STM32_VREFBUF_CSR); - val = (val & ~STM32_ENVR) | STM32_HIZ; + val &= ~STM32_ENVR; writel_relaxed(val, priv->base + STM32_VREFBUF_CSR); pm_runtime_mark_last_busy(priv->dev); @@ -175,6 +175,7 @@ static const struct regulator_desc stm32_vrefbuf_regu = { .volt_table = stm32_vrefbuf_voltages, .n_voltages = ARRAY_SIZE(stm32_vrefbuf_voltages), .ops = &stm32_vrefbuf_volt_ops, + .off_on_delay = 1000, .type = REGULATOR_VOLTAGE, .owner = THIS_MODULE, }; diff --git a/drivers/reset/Kconfig b/drivers/reset/Kconfig index 461b0e506a26f9d572b44c71f402085fa53f8766..d9efbfd29646371d9c4c05f44201234d16d36419 100644 --- a/drivers/reset/Kconfig +++ b/drivers/reset/Kconfig @@ -51,6 +51,7 @@ config RESET_BRCMSTB config RESET_BRCMSTB_RESCAL bool "Broadcom STB RESCAL reset controller" + depends on HAS_IOMEM default ARCH_BRCMSTB || COMPILE_TEST help This enables the RESCAL reset controller for SATA, PCIe0, or PCIe1 on @@ -73,7 +74,7 @@ config RESET_IMX7 config RESET_INTEL_GW bool "Intel Reset Controller Driver" - depends on OF + depends on OF && HAS_IOMEM select REGMAP_MMIO help This enables the reset controller driver for Intel Gateway SoCs. diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig index 34c8b6c7e0954ef9a49a6f693900896cf7621101..8e503881d9d6ab629d56516379914a824a6f33e4 100644 --- a/drivers/rtc/Kconfig +++ b/drivers/rtc/Kconfig @@ -327,6 +327,7 @@ config RTC_DRV_MAX6900 config RTC_DRV_MAX8907 tristate "Maxim MAX8907" depends on MFD_MAX8907 || COMPILE_TEST + select REGMAP_IRQ help If you say yes here you will get support for the RTC of Maxim MAX8907 PMIC. diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 6cca72782af6a004c02734f2d7d9b21c34770167..cf87eb27879f087cdc125e2c248916f0909a41c1 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -178,6 +178,8 @@ struct dasd_block *dasd_alloc_block(void) (unsigned long) block); INIT_LIST_HEAD(&block->ccw_queue); spin_lock_init(&block->queue_lock); + INIT_LIST_HEAD(&block->format_list); + spin_lock_init(&block->format_lock); timer_setup(&block->timer, dasd_block_timeout, 0); spin_lock_init(&block->profile.lock); @@ -1779,20 +1781,26 @@ void dasd_int_handler(struct ccw_device *cdev, unsigned long intparm, if (dasd_ese_needs_format(cqr->block, irb)) { if (rq_data_dir((struct request *)cqr->callback_data) == READ) { - device->discipline->ese_read(cqr); + device->discipline->ese_read(cqr, irb); cqr->status = DASD_CQR_SUCCESS; cqr->stopclk = now; dasd_device_clear_timer(device); dasd_schedule_device_bh(device); return; } - fcqr = device->discipline->ese_format(device, cqr); + fcqr = device->discipline->ese_format(device, cqr, irb); if (IS_ERR(fcqr)) { + if (PTR_ERR(fcqr) == -EINVAL) { + cqr->status = DASD_CQR_ERROR; + return; + } /* * If we can't format now, let the request go * one extra round. Maybe we can format later. */ cqr->status = DASD_CQR_QUEUED; + dasd_schedule_device_bh(device); + return; } else { fcqr->status = DASD_CQR_QUEUED; cqr->status = DASD_CQR_QUEUED; @@ -2748,11 +2756,13 @@ static void __dasd_cleanup_cqr(struct dasd_ccw_req *cqr) { struct request *req; blk_status_t error = BLK_STS_OK; + unsigned int proc_bytes; int status; req = (struct request *) cqr->callback_data; dasd_profile_end(cqr->block, cqr, req); + proc_bytes = cqr->proc_bytes; status = cqr->block->base->discipline->free_cp(cqr, req); if (status < 0) error = errno_to_blk_status(status); @@ -2783,7 +2793,18 @@ static void __dasd_cleanup_cqr(struct dasd_ccw_req *cqr) blk_mq_end_request(req, error); blk_mq_run_hw_queues(req->q, true); } else { - blk_mq_complete_request(req); + /* + * Partial completed requests can happen with ESE devices. + * During read we might have gotten a NRF error and have to + * complete a request partially. + */ + if (proc_bytes) { + blk_update_request(req, BLK_STS_OK, + blk_rq_bytes(req) - proc_bytes); + blk_mq_requeue_request(req, true); + } else { + blk_mq_complete_request(req); + } } } diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index a28b9ff823780de364ba7e79d871a92c464bce49..ad44d22e88591232ef59f5e4e9ec98564ef34a9d 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -207,6 +207,45 @@ static void set_ch_t(struct ch_t *geo, __u32 cyl, __u8 head) geo->head |= head; } +/* + * calculate failing track from sense data depending if + * it is an EAV device or not + */ +static int dasd_eckd_track_from_irb(struct irb *irb, struct dasd_device *device, + sector_t *track) +{ + struct dasd_eckd_private *private = device->private; + u8 *sense = NULL; + u32 cyl; + u8 head; + + sense = dasd_get_sense(irb); + if (!sense) { + DBF_DEV_EVENT(DBF_WARNING, device, "%s", + "ESE error no sense data\n"); + return -EINVAL; + } + if (!(sense[27] & DASD_SENSE_BIT_2)) { + DBF_DEV_EVENT(DBF_WARNING, device, "%s", + "ESE error no valid track data\n"); + return -EINVAL; + } + + if (sense[27] & DASD_SENSE_BIT_3) { + /* enhanced addressing */ + cyl = sense[30] << 20; + cyl |= (sense[31] & 0xF0) << 12; + cyl |= sense[28] << 8; + cyl |= sense[29]; + } else { + cyl = sense[29] << 8; + cyl |= sense[30]; + } + head = sense[31] & 0x0F; + *track = cyl * private->rdc_data.trk_per_cyl + head; + return 0; +} + static int set_timestamp(struct ccw1 *ccw, struct DE_eckd_data *data, struct dasd_device *device) { @@ -2986,6 +3025,37 @@ static int dasd_eckd_format_device(struct dasd_device *base, 0, NULL); } +static bool test_and_set_format_track(struct dasd_format_entry *to_format, + struct dasd_block *block) +{ + struct dasd_format_entry *format; + unsigned long flags; + bool rc = false; + + spin_lock_irqsave(&block->format_lock, flags); + list_for_each_entry(format, &block->format_list, list) { + if (format->track == to_format->track) { + rc = true; + goto out; + } + } + list_add_tail(&to_format->list, &block->format_list); + +out: + spin_unlock_irqrestore(&block->format_lock, flags); + return rc; +} + +static void clear_format_track(struct dasd_format_entry *format, + struct dasd_block *block) +{ + unsigned long flags; + + spin_lock_irqsave(&block->format_lock, flags); + list_del_init(&format->list); + spin_unlock_irqrestore(&block->format_lock, flags); +} + /* * Callback function to free ESE format requests. */ @@ -2993,15 +3063,19 @@ static void dasd_eckd_ese_format_cb(struct dasd_ccw_req *cqr, void *data) { struct dasd_device *device = cqr->startdev; struct dasd_eckd_private *private = device->private; + struct dasd_format_entry *format = data; + clear_format_track(format, cqr->basedev->block); private->count--; dasd_ffree_request(cqr, device); } static struct dasd_ccw_req * -dasd_eckd_ese_format(struct dasd_device *startdev, struct dasd_ccw_req *cqr) +dasd_eckd_ese_format(struct dasd_device *startdev, struct dasd_ccw_req *cqr, + struct irb *irb) { struct dasd_eckd_private *private; + struct dasd_format_entry *format; struct format_data_t fdata; unsigned int recs_per_trk; struct dasd_ccw_req *fcqr; @@ -3011,23 +3085,39 @@ dasd_eckd_ese_format(struct dasd_device *startdev, struct dasd_ccw_req *cqr) struct request *req; sector_t first_trk; sector_t last_trk; + sector_t curr_trk; int rc; req = cqr->callback_data; - base = cqr->block->base; + block = cqr->block; + base = block->base; private = base->private; - block = base->block; blksize = block->bp_block; recs_per_trk = recs_per_track(&private->rdc_data, 0, blksize); + format = &startdev->format_entry; first_trk = blk_rq_pos(req) >> block->s2b_shift; sector_div(first_trk, recs_per_trk); last_trk = (blk_rq_pos(req) + blk_rq_sectors(req) - 1) >> block->s2b_shift; sector_div(last_trk, recs_per_trk); + rc = dasd_eckd_track_from_irb(irb, base, &curr_trk); + if (rc) + return ERR_PTR(rc); - fdata.start_unit = first_trk; - fdata.stop_unit = last_trk; + if (curr_trk < first_trk || curr_trk > last_trk) { + DBF_DEV_EVENT(DBF_WARNING, startdev, + "ESE error track %llu not within range %llu - %llu\n", + curr_trk, first_trk, last_trk); + return ERR_PTR(-EINVAL); + } + format->track = curr_trk; + /* test if track is already in formatting by another thread */ + if (test_and_set_format_track(format, block)) + return ERR_PTR(-EEXIST); + + fdata.start_unit = curr_trk; + fdata.stop_unit = curr_trk; fdata.blksize = blksize; fdata.intensity = private->uses_cdl ? DASD_FMT_INT_COMPAT : 0; @@ -3044,6 +3134,7 @@ dasd_eckd_ese_format(struct dasd_device *startdev, struct dasd_ccw_req *cqr) return fcqr; fcqr->callback = dasd_eckd_ese_format_cb; + fcqr->callback_data = (void *) format; return fcqr; } @@ -3051,29 +3142,87 @@ dasd_eckd_ese_format(struct dasd_device *startdev, struct dasd_ccw_req *cqr) /* * When data is read from an unformatted area of an ESE volume, this function * returns zeroed data and thereby mimics a read of zero data. + * + * The first unformatted track is the one that got the NRF error, the address is + * encoded in the sense data. + * + * All tracks before have returned valid data and should not be touched. + * All tracks after the unformatted track might be formatted or not. This is + * currently not known, remember the processed data and return the remainder of + * the request to the blocklayer in __dasd_cleanup_cqr(). */ -static void dasd_eckd_ese_read(struct dasd_ccw_req *cqr) +static int dasd_eckd_ese_read(struct dasd_ccw_req *cqr, struct irb *irb) { + struct dasd_eckd_private *private; + sector_t first_trk, last_trk; + sector_t first_blk, last_blk; unsigned int blksize, off; + unsigned int recs_per_trk; struct dasd_device *base; struct req_iterator iter; + struct dasd_block *block; + unsigned int skip_block; + unsigned int blk_count; struct request *req; struct bio_vec bv; + sector_t curr_trk; + sector_t end_blk; char *dst; + int rc; req = (struct request *) cqr->callback_data; base = cqr->block->base; blksize = base->block->bp_block; + block = cqr->block; + private = base->private; + skip_block = 0; + blk_count = 0; + + recs_per_trk = recs_per_track(&private->rdc_data, 0, blksize); + first_trk = first_blk = blk_rq_pos(req) >> block->s2b_shift; + sector_div(first_trk, recs_per_trk); + last_trk = last_blk = + (blk_rq_pos(req) + blk_rq_sectors(req) - 1) >> block->s2b_shift; + sector_div(last_trk, recs_per_trk); + rc = dasd_eckd_track_from_irb(irb, base, &curr_trk); + if (rc) + return rc; + + /* sanity check if the current track from sense data is valid */ + if (curr_trk < first_trk || curr_trk > last_trk) { + DBF_DEV_EVENT(DBF_WARNING, base, + "ESE error track %llu not within range %llu - %llu\n", + curr_trk, first_trk, last_trk); + return -EINVAL; + } + + /* + * if not the first track got the NRF error we have to skip over valid + * blocks + */ + if (curr_trk != first_trk) + skip_block = curr_trk * recs_per_trk - first_blk; + + /* we have no information beyond the current track */ + end_blk = (curr_trk + 1) * recs_per_trk; rq_for_each_segment(bv, req, iter) { dst = page_address(bv.bv_page) + bv.bv_offset; for (off = 0; off < bv.bv_len; off += blksize) { - if (dst && rq_data_dir(req) == READ) { + if (first_blk + blk_count >= end_blk) { + cqr->proc_bytes = blk_count * blksize; + return 0; + } + if (dst && !skip_block) { dst += off; memset(dst, 0, blksize); + } else { + skip_block--; } + blk_count++; } } + return 0; } /* diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h index 91c9f9586e0f645f87fe9899fb7f3e437ee85bb8..fa552f9f1666713313ccb644e425d2b41f229942 100644 --- a/drivers/s390/block/dasd_int.h +++ b/drivers/s390/block/dasd_int.h @@ -187,6 +187,7 @@ struct dasd_ccw_req { void (*callback)(struct dasd_ccw_req *, void *data); void *callback_data; + unsigned int proc_bytes; /* bytes for partial completion */ }; /* @@ -387,8 +388,9 @@ struct dasd_discipline { int (*ext_pool_warn_thrshld)(struct dasd_device *); int (*ext_pool_oos)(struct dasd_device *); int (*ext_pool_exhaust)(struct dasd_device *, struct dasd_ccw_req *); - struct dasd_ccw_req *(*ese_format)(struct dasd_device *, struct dasd_ccw_req *); - void (*ese_read)(struct dasd_ccw_req *); + struct dasd_ccw_req *(*ese_format)(struct dasd_device *, + struct dasd_ccw_req *, struct irb *); + int (*ese_read)(struct dasd_ccw_req *, struct irb *); }; extern struct dasd_discipline *dasd_diag_discipline_pointer; @@ -474,6 +476,11 @@ struct dasd_profile { spinlock_t lock; }; +struct dasd_format_entry { + struct list_head list; + sector_t track; +}; + struct dasd_device { /* Block device stuff. */ struct dasd_block *block; @@ -539,6 +546,7 @@ struct dasd_device { struct dentry *debugfs_dentry; struct dentry *hosts_dentry; struct dasd_profile profile; + struct dasd_format_entry format_entry; }; struct dasd_block { @@ -564,6 +572,9 @@ struct dasd_block { struct dentry *debugfs_dentry; struct dasd_profile profile; + + struct list_head format_list; + spinlock_t format_lock; }; struct dasd_attention_data { diff --git a/drivers/s390/cio/blacklist.c b/drivers/s390/cio/blacklist.c index da642e811f7f06853ed77defd599afa0eab98a37..4dd2eb6348569965dc4df362e8a6a6f689976f3a 100644 --- a/drivers/s390/cio/blacklist.c +++ b/drivers/s390/cio/blacklist.c @@ -303,8 +303,10 @@ static void * cio_ignore_proc_seq_next(struct seq_file *s, void *it, loff_t *offset) { struct ccwdev_iter *iter; + loff_t p = *offset; - if (*offset >= (__MAX_SUBCHANNEL + 1) * (__MAX_SSID + 1)) + (*offset)++; + if (p >= (__MAX_SUBCHANNEL + 1) * (__MAX_SSID + 1)) return NULL; iter = it; if (iter->devno == __MAX_SUBCHANNEL) { @@ -314,7 +316,6 @@ cio_ignore_proc_seq_next(struct seq_file *s, void *it, loff_t *offset) return NULL; } else iter->devno++; - (*offset)++; return iter; } diff --git a/drivers/s390/cio/chp.c b/drivers/s390/cio/chp.c index 51038ec309c12ef3f3eae351d332ed7a13694eda..dfcbe54591fbda24eb32a4ead5c7c36ec7fd8162 100644 --- a/drivers/s390/cio/chp.c +++ b/drivers/s390/cio/chp.c @@ -135,7 +135,7 @@ static ssize_t chp_measurement_chars_read(struct file *filp, struct channel_path *chp; struct device *device; - device = container_of(kobj, struct device, kobj); + device = kobj_to_dev(kobj); chp = to_channelpath(device); if (chp->cmg == -1) return 0; @@ -184,7 +184,7 @@ static ssize_t chp_measurement_read(struct file *filp, struct kobject *kobj, struct device *device; unsigned int size; - device = container_of(kobj, struct device, kobj); + device = kobj_to_dev(kobj); chp = to_channelpath(device); css = to_css(chp->dev.parent); diff --git a/drivers/s390/cio/qdio.h b/drivers/s390/cio/qdio.h index 4b0798472643105aca0942671e0badc225bb549d..ff74eb5fce5024512e438e99cefa7bf7a5f31a27 100644 --- a/drivers/s390/cio/qdio.h +++ b/drivers/s390/cio/qdio.h @@ -182,11 +182,9 @@ enum qdio_queue_irq_states { }; struct qdio_input_q { - /* input buffer acknowledgement flag */ - int polling; /* first ACK'ed buffer */ int ack_start; - /* how much sbals are acknowledged with qebsm */ + /* how many SBALs are acknowledged */ int ack_count; /* last time of noticing incoming data */ u64 timestamp; diff --git a/drivers/s390/cio/qdio_debug.c b/drivers/s390/cio/qdio_debug.c index 35410e6eda2eaaf0de6bf16a9d942cf870eec940..9c0370b27426213fbec0da3732ee872323dcc3b5 100644 --- a/drivers/s390/cio/qdio_debug.c +++ b/drivers/s390/cio/qdio_debug.c @@ -124,9 +124,8 @@ static int qstat_show(struct seq_file *m, void *v) seq_printf(m, "nr_used: %d ftc: %d\n", atomic_read(&q->nr_buf_used), q->first_to_check); if (q->is_input_q) { - seq_printf(m, "polling: %d ack start: %d ack count: %d\n", - q->u.in.polling, q->u.in.ack_start, - q->u.in.ack_count); + seq_printf(m, "ack start: %d ack count: %d\n", + q->u.in.ack_start, q->u.in.ack_count); seq_printf(m, "DSCI: %x IRQs disabled: %u\n", *(u8 *)q->irq_ptr->dsci, test_bit(QDIO_QUEUE_IRQS_DISABLED, diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c index f8b897b7e78b4204ec21f486e765e2f3ae19db84..3475317c42e5ace277cb41019a4c540fd41d91b1 100644 --- a/drivers/s390/cio/qdio_main.c +++ b/drivers/s390/cio/qdio_main.c @@ -393,19 +393,15 @@ int debug_get_buf_state(struct qdio_q *q, unsigned int bufnr, static inline void qdio_stop_polling(struct qdio_q *q) { - if (!q->u.in.polling) + if (!q->u.in.ack_count) return; - q->u.in.polling = 0; qperf_inc(q, stop_polling); /* show the card that we are not polling anymore */ - if (is_qebsm(q)) { - set_buf_states(q, q->u.in.ack_start, SLSB_P_INPUT_NOT_INIT, - q->u.in.ack_count); - q->u.in.ack_count = 0; - } else - set_buf_state(q, q->u.in.ack_start, SLSB_P_INPUT_NOT_INIT); + set_buf_states(q, q->u.in.ack_start, SLSB_P_INPUT_NOT_INIT, + q->u.in.ack_count); + q->u.in.ack_count = 0; } static inline void account_sbals(struct qdio_q *q, unsigned int count) @@ -451,8 +447,7 @@ static inline void inbound_primed(struct qdio_q *q, unsigned int start, /* for QEBSM the ACK was already set by EQBS */ if (is_qebsm(q)) { - if (!q->u.in.polling) { - q->u.in.polling = 1; + if (!q->u.in.ack_count) { q->u.in.ack_count = count; q->u.in.ack_start = start; return; @@ -471,12 +466,12 @@ static inline void inbound_primed(struct qdio_q *q, unsigned int start, * or by the next inbound run. */ new = add_buf(start, count - 1); - if (q->u.in.polling) { + if (q->u.in.ack_count) { /* reset the previous ACK but first set the new one */ set_buf_state(q, new, SLSB_P_INPUT_ACK); set_buf_state(q, q->u.in.ack_start, SLSB_P_INPUT_NOT_INIT); } else { - q->u.in.polling = 1; + q->u.in.ack_count = 1; set_buf_state(q, new, SLSB_P_INPUT_ACK); } @@ -1479,13 +1474,12 @@ static int handle_inbound(struct qdio_q *q, unsigned int callflags, qperf_inc(q, inbound_call); - if (!q->u.in.polling) + if (!q->u.in.ack_count) goto set; /* protect against stop polling setting an ACK for an emptied slsb */ if (count == QDIO_MAX_BUFFERS_PER_Q) { /* overwriting everything, just delete polling status */ - q->u.in.polling = 0; q->u.in.ack_count = 0; goto set; } else if (buf_in_between(q->u.in.ack_start, bufnr, count)) { @@ -1495,15 +1489,14 @@ static int handle_inbound(struct qdio_q *q, unsigned int callflags, diff = sub_buf(diff, q->u.in.ack_start); q->u.in.ack_count -= diff; if (q->u.in.ack_count <= 0) { - q->u.in.polling = 0; q->u.in.ack_count = 0; goto set; } q->u.in.ack_start = add_buf(q->u.in.ack_start, diff); + } else { + /* the only ACK will be deleted */ + q->u.in.ack_count = 0; } - else - /* the only ACK will be deleted, so stop polling */ - q->u.in.polling = 0; } set: diff --git a/drivers/s390/cio/qdio_setup.c b/drivers/s390/cio/qdio_setup.c index dc430bd86ade93039579f2d0d32e370857dfab40..e115623b86b298267e34d09d4da37366421d321c 100644 --- a/drivers/s390/cio/qdio_setup.c +++ b/drivers/s390/cio/qdio_setup.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include "cio.h" @@ -205,7 +206,7 @@ static void setup_storage_lists(struct qdio_q *q, struct qdio_irq *irq_ptr, /* fill in sl */ for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; j++) - q->sl->element[j].sbal = (unsigned long)q->sbal[j]; + q->sl->element[j].sbal = virt_to_phys(q->sbal[j]); } static void setup_queues(struct qdio_irq *irq_ptr, @@ -536,7 +537,7 @@ void qdio_print_subchannel_info(struct qdio_irq *irq_ptr, int qdio_enable_async_operation(struct qdio_output_q *outq) { outq->aobs = kcalloc(QDIO_MAX_BUFFERS_PER_Q, sizeof(struct qaob *), - GFP_ATOMIC); + GFP_KERNEL); if (!outq->aobs) { outq->use_cq = 0; return -ENOMEM; diff --git a/drivers/s390/cio/vfio_ccw_trace.h b/drivers/s390/cio/vfio_ccw_trace.h index 30162a318a8a12e4860919e7c6a50b040f265379..f5d31887d41341a8c99f8d301b9e25afc21ec029 100644 --- a/drivers/s390/cio/vfio_ccw_trace.h +++ b/drivers/s390/cio/vfio_ccw_trace.h @@ -1,5 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 - * Tracepoints for vfio_ccw driver +/* SPDX-License-Identifier: GPL-2.0 */ +/* Tracepoints for vfio_ccw driver * * Copyright IBM Corp. 2018 * diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h index bb35ba4a8d243955545596908170fbdd10620400..4348fdff1c61ec95f1e81526361fee3bd6b550b5 100644 --- a/drivers/s390/crypto/ap_bus.h +++ b/drivers/s390/crypto/ap_bus.h @@ -162,7 +162,7 @@ struct ap_card { unsigned int functions; /* AP device function bitfield. */ int queue_depth; /* AP queue depth.*/ int id; /* AP card number. */ - atomic_t total_request_count; /* # requests ever for this AP device.*/ + atomic64_t total_request_count; /* # requests ever for this AP device.*/ }; #define to_ap_card(x) container_of((x), struct ap_card, ap_dev.device) @@ -179,7 +179,7 @@ struct ap_queue { enum ap_state state; /* State of the AP device. */ int pendingq_count; /* # requests on pendingq list. */ int requestq_count; /* # requests on requestq list. */ - int total_request_count; /* # requests ever for this AP device.*/ + u64 total_request_count; /* # requests ever for this AP device.*/ int request_timeout; /* Request timeout in jiffies. */ struct timer_list timeout; /* Timer for request timeouts. */ struct list_head pendingq; /* List of message sent to AP queue. */ diff --git a/drivers/s390/crypto/ap_card.c b/drivers/s390/crypto/ap_card.c index 63b4cc6cd7e596f7b51681391eb17ddffb6d0512..e85bfca1ed163575989cae3e8120b235369ba0b4 100644 --- a/drivers/s390/crypto/ap_card.c +++ b/drivers/s390/crypto/ap_card.c @@ -63,13 +63,13 @@ static ssize_t request_count_show(struct device *dev, char *buf) { struct ap_card *ac = to_ap_card(dev); - unsigned int req_cnt; + u64 req_cnt; req_cnt = 0; spin_lock_bh(&ap_list_lock); - req_cnt = atomic_read(&ac->total_request_count); + req_cnt = atomic64_read(&ac->total_request_count); spin_unlock_bh(&ap_list_lock); - return snprintf(buf, PAGE_SIZE, "%d\n", req_cnt); + return snprintf(buf, PAGE_SIZE, "%llu\n", req_cnt); } static ssize_t request_count_store(struct device *dev, @@ -83,7 +83,7 @@ static ssize_t request_count_store(struct device *dev, for_each_ap_queue(aq, ac) aq->total_request_count = 0; spin_unlock_bh(&ap_list_lock); - atomic_set(&ac->total_request_count, 0); + atomic64_set(&ac->total_request_count, 0); return count; } diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c index 37c3bdc3642dc6756dbcf10a6a34f2d9974fb930..a317ab48493203e8082b0acc1a57fdd8fe62524b 100644 --- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -479,12 +479,12 @@ static ssize_t request_count_show(struct device *dev, char *buf) { struct ap_queue *aq = to_ap_queue(dev); - unsigned int req_cnt; + u64 req_cnt; spin_lock_bh(&aq->lock); req_cnt = aq->total_request_count; spin_unlock_bh(&aq->lock); - return snprintf(buf, PAGE_SIZE, "%d\n", req_cnt); + return snprintf(buf, PAGE_SIZE, "%llu\n", req_cnt); } static ssize_t request_count_store(struct device *dev, @@ -676,7 +676,7 @@ void ap_queue_message(struct ap_queue *aq, struct ap_message *ap_msg) list_add_tail(&ap_msg->list, &aq->requestq); aq->requestq_count++; aq->total_request_count++; - atomic_inc(&aq->card->total_request_count); + atomic64_inc(&aq->card->total_request_count); /* Send/receive as many request from the queue as possible. */ ap_wait(ap_sm_event_loop(aq, AP_EVENT_POLL)); spin_unlock_bh(&aq->lock); diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c index 71dae64ba99491c66bd5897c662d1d5a3910b7c9..2f33c5fcf676d1241139067d1336f78289e78702 100644 --- a/drivers/s390/crypto/pkey_api.c +++ b/drivers/s390/crypto/pkey_api.c @@ -994,7 +994,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, return -EFAULT; rc = cca_sec2protkey(ksp.cardnr, ksp.domain, ksp.seckey.seckey, ksp.protkey.protkey, - NULL, &ksp.protkey.type); + &ksp.protkey.len, &ksp.protkey.type); DEBUG_DBG("%s cca_sec2protkey()=%d\n", __func__, rc); if (rc) break; diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index a42257d6c79e8eb60bc94de510229e207535e0b7..56a405dce8bcf32c468443d5249ce466285d999c 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -606,8 +606,8 @@ static inline bool zcrypt_card_compare(struct zcrypt_card *zc, weight += atomic_read(&zc->load); pref_weight += atomic_read(&pref_zc->load); if (weight == pref_weight) - return atomic_read(&zc->card->total_request_count) > - atomic_read(&pref_zc->card->total_request_count); + return atomic64_read(&zc->card->total_request_count) > + atomic64_read(&pref_zc->card->total_request_count); return weight > pref_weight; } @@ -1226,11 +1226,12 @@ static void zcrypt_qdepth_mask(char qdepth[], size_t max_adapters) spin_unlock(&zcrypt_list_lock); } -static void zcrypt_perdev_reqcnt(int reqcnt[], size_t max_adapters) +static void zcrypt_perdev_reqcnt(u32 reqcnt[], size_t max_adapters) { struct zcrypt_card *zc; struct zcrypt_queue *zq; int card; + u64 cnt; memset(reqcnt, 0, sizeof(int) * max_adapters); spin_lock(&zcrypt_list_lock); @@ -1242,8 +1243,9 @@ static void zcrypt_perdev_reqcnt(int reqcnt[], size_t max_adapters) || card >= max_adapters) continue; spin_lock(&zq->queue->lock); - reqcnt[card] = zq->queue->total_request_count; + cnt = zq->queue->total_request_count; spin_unlock(&zq->queue->lock); + reqcnt[card] = (cnt < UINT_MAX) ? (u32) cnt : UINT_MAX; } } local_bh_enable(); @@ -1421,9 +1423,9 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd, return 0; } case ZCRYPT_PERDEV_REQCNT: { - int *reqcnt; + u32 *reqcnt; - reqcnt = kcalloc(AP_DEVICES, sizeof(int), GFP_KERNEL); + reqcnt = kcalloc(AP_DEVICES, sizeof(u32), GFP_KERNEL); if (!reqcnt) return -ENOMEM; zcrypt_perdev_reqcnt(reqcnt, AP_DEVICES); @@ -1480,7 +1482,7 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd, } case Z90STAT_PERDEV_REQCNT: { /* the old ioctl supports only 64 adapters */ - int reqcnt[MAX_ZDEV_CARDIDS]; + u32 reqcnt[MAX_ZDEV_CARDIDS]; zcrypt_perdev_reqcnt(reqcnt, MAX_ZDEV_CARDIDS); if (copy_to_user((int __user *) arg, reqcnt, sizeof(reqcnt))) diff --git a/drivers/s390/crypto/zcrypt_ep11misc.c b/drivers/s390/crypto/zcrypt_ep11misc.c index d4caf46ff9df155963bf7d01a431212e70fd53d1..2afe2153b34e32e9bc9b25b8a8026d0a0db01be2 100644 --- a/drivers/s390/crypto/zcrypt_ep11misc.c +++ b/drivers/s390/crypto/zcrypt_ep11misc.c @@ -887,7 +887,7 @@ static int ep11_unwrapkey(u16 card, u16 domain, /* empty pin tag */ *p++ = 0x04; *p++ = 0; - /* encrytped key value tag and bytes */ + /* encrypted key value tag and bytes */ p += asn1tag_write(p, 0x04, enckey, enckeysize); /* reply cprb and payload */ @@ -1095,7 +1095,7 @@ int ep11_clr2keyblob(u16 card, u16 domain, u32 keybitsize, u32 keygenflags, /* Step 1: generate AES 256 bit random kek key */ rc = ep11_genaeskey(card, domain, 256, - 0x00006c00, /* EN/DECRYTP, WRAP/UNWRAP */ + 0x00006c00, /* EN/DECRYPT, WRAP/UNWRAP */ kek, &keklen); if (rc) { DEBUG_ERR( diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 9575a627a1e18d446cf79dd7cb4011dfa2f2accf..468cada49e72c012544dbbbbb47ad8c7585a6213 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -369,7 +369,7 @@ enum qeth_qdio_info_states { struct qeth_buffer_pool_entry { struct list_head list; struct list_head init_list; - void *elements[QDIO_MAX_ELEMENTS_PER_BUFFER]; + struct page *elements[QDIO_MAX_ELEMENTS_PER_BUFFER]; }; struct qeth_qdio_buffer_pool { @@ -983,7 +983,7 @@ extern const struct attribute_group qeth_device_blkt_group; extern const struct device_type qeth_generic_devtype; const char *qeth_get_cardname_short(struct qeth_card *); -int qeth_realloc_buffer_pool(struct qeth_card *, int); +int qeth_resize_buffer_pool(struct qeth_card *card, unsigned int count); int qeth_core_load_discipline(struct qeth_card *, enum qeth_discipline_id); void qeth_core_free_discipline(struct qeth_card *); diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 9639938581f58e3b0c4151260ce34046b49eeced..6d3f2f14b4143fdf5584001786ea82c0a62a2cca 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -65,7 +65,6 @@ static struct lock_class_key qdio_out_skb_queue_key; static void qeth_issue_next_read_cb(struct qeth_card *card, struct qeth_cmd_buffer *iob, unsigned int data_length); -static void qeth_free_buffer_pool(struct qeth_card *); static int qeth_qdio_establish(struct qeth_card *); static void qeth_free_qdio_queues(struct qeth_card *card); static void qeth_notify_skbs(struct qeth_qdio_out_q *queue, @@ -212,49 +211,121 @@ void qeth_clear_working_pool_list(struct qeth_card *card) } EXPORT_SYMBOL_GPL(qeth_clear_working_pool_list); +static void qeth_free_pool_entry(struct qeth_buffer_pool_entry *entry) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(entry->elements); i++) { + if (entry->elements[i]) + __free_page(entry->elements[i]); + } + + kfree(entry); +} + +static void qeth_free_buffer_pool(struct qeth_card *card) +{ + struct qeth_buffer_pool_entry *entry, *tmp; + + list_for_each_entry_safe(entry, tmp, &card->qdio.init_pool.entry_list, + init_list) { + list_del(&entry->init_list); + qeth_free_pool_entry(entry); + } +} + +static struct qeth_buffer_pool_entry *qeth_alloc_pool_entry(unsigned int pages) +{ + struct qeth_buffer_pool_entry *entry; + unsigned int i; + + entry = kzalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + return NULL; + + for (i = 0; i < pages; i++) { + entry->elements[i] = alloc_page(GFP_KERNEL); + + if (!entry->elements[i]) { + qeth_free_pool_entry(entry); + return NULL; + } + } + + return entry; +} + static int qeth_alloc_buffer_pool(struct qeth_card *card) { - struct qeth_buffer_pool_entry *pool_entry; - void *ptr; - int i, j; + unsigned int buf_elements = QETH_MAX_BUFFER_ELEMENTS(card); + unsigned int i; QETH_CARD_TEXT(card, 5, "alocpool"); for (i = 0; i < card->qdio.init_pool.buf_count; ++i) { - pool_entry = kzalloc(sizeof(*pool_entry), GFP_KERNEL); - if (!pool_entry) { + struct qeth_buffer_pool_entry *entry; + + entry = qeth_alloc_pool_entry(buf_elements); + if (!entry) { qeth_free_buffer_pool(card); return -ENOMEM; } - for (j = 0; j < QETH_MAX_BUFFER_ELEMENTS(card); ++j) { - ptr = (void *) __get_free_page(GFP_KERNEL); - if (!ptr) { - while (j > 0) - free_page((unsigned long) - pool_entry->elements[--j]); - kfree(pool_entry); - qeth_free_buffer_pool(card); - return -ENOMEM; - } - pool_entry->elements[j] = ptr; - } - list_add(&pool_entry->init_list, - &card->qdio.init_pool.entry_list); + + list_add(&entry->init_list, &card->qdio.init_pool.entry_list); } return 0; } -int qeth_realloc_buffer_pool(struct qeth_card *card, int bufcnt) +int qeth_resize_buffer_pool(struct qeth_card *card, unsigned int count) { + unsigned int buf_elements = QETH_MAX_BUFFER_ELEMENTS(card); + struct qeth_qdio_buffer_pool *pool = &card->qdio.init_pool; + struct qeth_buffer_pool_entry *entry, *tmp; + int delta = count - pool->buf_count; + LIST_HEAD(entries); + QETH_CARD_TEXT(card, 2, "realcbp"); - /* TODO: steel/add buffers from/to a running card's buffer pool (?) */ - qeth_clear_working_pool_list(card); - qeth_free_buffer_pool(card); - card->qdio.in_buf_pool.buf_count = bufcnt; - card->qdio.init_pool.buf_count = bufcnt; - return qeth_alloc_buffer_pool(card); + /* Defer until queue is allocated: */ + if (!card->qdio.in_q) + goto out; + + /* Remove entries from the pool: */ + while (delta < 0) { + entry = list_first_entry(&pool->entry_list, + struct qeth_buffer_pool_entry, + init_list); + list_del(&entry->init_list); + qeth_free_pool_entry(entry); + + delta++; + } + + /* Allocate additional entries: */ + while (delta > 0) { + entry = qeth_alloc_pool_entry(buf_elements); + if (!entry) { + list_for_each_entry_safe(entry, tmp, &entries, + init_list) { + list_del(&entry->init_list); + qeth_free_pool_entry(entry); + } + + return -ENOMEM; + } + + list_add(&entry->init_list, &entries); + + delta--; + } + + list_splice(&entries, &pool->entry_list); + +out: + card->qdio.in_buf_pool.buf_count = count; + pool->buf_count = count; + return 0; } -EXPORT_SYMBOL_GPL(qeth_realloc_buffer_pool); +EXPORT_SYMBOL_GPL(qeth_resize_buffer_pool); static void qeth_free_qdio_queue(struct qeth_qdio_q *q) { @@ -1128,9 +1199,10 @@ static void qeth_clear_output_buffer(struct qeth_qdio_out_q *queue, qeth_tx_complete_buf(buf, error, budget); for (i = 0; i < queue->max_elements; ++i) { - if (buf->buffer->element[i].addr && buf->is_header[i]) - kmem_cache_free(qeth_core_header_cache, - buf->buffer->element[i].addr); + void *data = phys_to_virt(buf->buffer->element[i].addr); + + if (data && buf->is_header[i]) + kmem_cache_free(qeth_core_header_cache, data); buf->is_header[i] = 0; } @@ -1169,19 +1241,6 @@ void qeth_drain_output_queues(struct qeth_card *card) } EXPORT_SYMBOL_GPL(qeth_drain_output_queues); -static void qeth_free_buffer_pool(struct qeth_card *card) -{ - struct qeth_buffer_pool_entry *pool_entry, *tmp; - int i = 0; - list_for_each_entry_safe(pool_entry, tmp, - &card->qdio.init_pool.entry_list, init_list){ - for (i = 0; i < QETH_MAX_BUFFER_ELEMENTS(card); ++i) - free_page((unsigned long)pool_entry->elements[i]); - list_del(&pool_entry->init_list); - kfree(pool_entry); - } -} - static int qeth_osa_set_output_queues(struct qeth_card *card, bool single) { unsigned int count = single ? 1 : card->dev->num_tx_queues; @@ -1203,7 +1262,6 @@ static int qeth_osa_set_output_queues(struct qeth_card *card, bool single) if (count == 1) dev_info(&card->gdev->dev, "Priority Queueing not supported\n"); - card->qdio.default_out_queue = single ? 0 : QETH_DEFAULT_QUEUE; card->qdio.no_out_queues = count; return 0; } @@ -2392,7 +2450,6 @@ static void qeth_free_qdio_queues(struct qeth_card *card) return; qeth_free_cq(card); - cancel_delayed_work_sync(&card->buffer_reclaim_work); for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; ++j) { if (card->qdio.in_q->bufs[j].rx_skb) dev_kfree_skb_any(card->qdio.in_q->bufs[j].rx_skb); @@ -2574,7 +2631,6 @@ static struct qeth_buffer_pool_entry *qeth_find_free_buffer_pool_entry( struct list_head *plh; struct qeth_buffer_pool_entry *entry; int i, free; - struct page *page; if (list_empty(&card->qdio.in_buf_pool.entry_list)) return NULL; @@ -2583,7 +2639,7 @@ static struct qeth_buffer_pool_entry *qeth_find_free_buffer_pool_entry( entry = list_entry(plh, struct qeth_buffer_pool_entry, list); free = 1; for (i = 0; i < QETH_MAX_BUFFER_ELEMENTS(card); ++i) { - if (page_count(virt_to_page(entry->elements[i])) > 1) { + if (page_count(entry->elements[i]) > 1) { free = 0; break; } @@ -2598,15 +2654,15 @@ static struct qeth_buffer_pool_entry *qeth_find_free_buffer_pool_entry( entry = list_entry(card->qdio.in_buf_pool.entry_list.next, struct qeth_buffer_pool_entry, list); for (i = 0; i < QETH_MAX_BUFFER_ELEMENTS(card); ++i) { - if (page_count(virt_to_page(entry->elements[i])) > 1) { - page = alloc_page(GFP_ATOMIC); - if (!page) { + if (page_count(entry->elements[i]) > 1) { + struct page *page = alloc_page(GFP_ATOMIC); + + if (!page) return NULL; - } else { - free_page((unsigned long)entry->elements[i]); - entry->elements[i] = page_address(page); - QETH_CARD_STAT_INC(card, rx_sg_alloc_page); - } + + __free_page(entry->elements[i]); + entry->elements[i] = page; + QETH_CARD_STAT_INC(card, rx_sg_alloc_page); } } list_del_init(&entry->list); @@ -2624,12 +2680,12 @@ static int qeth_init_input_buffer(struct qeth_card *card, ETH_HLEN + sizeof(struct ipv6hdr)); if (!buf->rx_skb) - return 1; + return -ENOMEM; } pool_entry = qeth_find_free_buffer_pool_entry(card); if (!pool_entry) - return 1; + return -ENOBUFS; /* * since the buffer is accessed only from the input_tasklet @@ -2641,7 +2697,8 @@ static int qeth_init_input_buffer(struct qeth_card *card, buf->pool_entry = pool_entry; for (i = 0; i < QETH_MAX_BUFFER_ELEMENTS(card); ++i) { buf->buffer->element[i].length = PAGE_SIZE; - buf->buffer->element[i].addr = pool_entry->elements[i]; + buf->buffer->element[i].addr = + page_to_phys(pool_entry->elements[i]); if (i == QETH_MAX_BUFFER_ELEMENTS(card) - 1) buf->buffer->element[i].eflags = SBAL_EFLAGS_LAST_ENTRY; else @@ -2673,10 +2730,15 @@ static int qeth_init_qdio_queues(struct qeth_card *card) /* inbound queue */ qdio_reset_buffers(card->qdio.in_q->qdio_bufs, QDIO_MAX_BUFFERS_PER_Q); memset(&card->rx, 0, sizeof(struct qeth_rx)); + qeth_initialize_working_pool_list(card); /*give only as many buffers to hardware as we have buffer pool entries*/ - for (i = 0; i < card->qdio.in_buf_pool.buf_count - 1; ++i) - qeth_init_input_buffer(card, &card->qdio.in_q->bufs[i]); + for (i = 0; i < card->qdio.in_buf_pool.buf_count - 1; i++) { + rc = qeth_init_input_buffer(card, &card->qdio.in_q->bufs[i]); + if (rc) + return rc; + } + card->qdio.in_q->next_buf_to_init = card->qdio.in_buf_pool.buf_count - 1; rc = do_QDIO(CARD_DDEV(card), QDIO_FLAG_SYNC_INPUT, 0, 0, @@ -3459,9 +3521,8 @@ static void qeth_qdio_cq_handler(struct qeth_card *card, unsigned int qdio_err, while ((e < QDIO_MAX_ELEMENTS_PER_BUFFER) && buffer->element[e].addr) { - unsigned long phys_aob_addr; + unsigned long phys_aob_addr = buffer->element[e].addr; - phys_aob_addr = (unsigned long) buffer->element[e].addr; qeth_qdio_handle_aob(card, phys_aob_addr); ++e; } @@ -3750,7 +3811,7 @@ static unsigned int __qeth_fill_buffer(struct sk_buff *skb, elem_length = min_t(unsigned int, length, PAGE_SIZE - offset_in_page(data)); - buffer->element[element].addr = data; + buffer->element[element].addr = virt_to_phys(data); buffer->element[element].length = elem_length; length -= elem_length; if (is_first_elem) { @@ -3780,7 +3841,7 @@ static unsigned int __qeth_fill_buffer(struct sk_buff *skb, elem_length = min_t(unsigned int, length, PAGE_SIZE - offset_in_page(data)); - buffer->element[element].addr = data; + buffer->element[element].addr = virt_to_phys(data); buffer->element[element].length = elem_length; buffer->element[element].eflags = SBAL_EFLAGS_MIDDLE_FRAG; @@ -3820,7 +3881,7 @@ static unsigned int qeth_fill_buffer(struct qeth_qdio_out_buffer *buf, int element = buf->next_element_to_fill; is_first_elem = false; - buffer->element[element].addr = hdr; + buffer->element[element].addr = virt_to_phys(hdr); buffer->element[element].length = hd_len; buffer->element[element].eflags = SBAL_EFLAGS_FIRST_FRAG; /* remember to free cache-allocated qeth_hdr: */ @@ -4746,10 +4807,10 @@ static void qeth_qdio_establish_cq(struct qeth_card *card, if (card->options.cq == QETH_CQ_ENABLED) { int offset = QDIO_MAX_BUFFERS_PER_Q * (card->qdio.no_in_queues - 1); - for (i = 0; i < QDIO_MAX_BUFFERS_PER_Q; ++i) { - in_sbal_ptrs[offset + i] = (struct qdio_buffer *) - virt_to_phys(card->qdio.c_q->bufs[i].buffer); - } + + for (i = 0; i < QDIO_MAX_BUFFERS_PER_Q; i++) + in_sbal_ptrs[offset + i] = + card->qdio.c_q->bufs[i].buffer; queue_start_poll[card->qdio.no_in_queues - 1] = NULL; } @@ -4783,10 +4844,9 @@ static int qeth_qdio_establish(struct qeth_card *card) rc = -ENOMEM; goto out_free_qib_param; } - for (i = 0; i < QDIO_MAX_BUFFERS_PER_Q; ++i) { - in_sbal_ptrs[i] = (struct qdio_buffer *) - virt_to_phys(card->qdio.in_q->bufs[i].buffer); - } + + for (i = 0; i < QDIO_MAX_BUFFERS_PER_Q; i++) + in_sbal_ptrs[i] = card->qdio.in_q->bufs[i].buffer; queue_start_poll = kcalloc(card->qdio.no_in_queues, sizeof(void *), GFP_KERNEL); @@ -4807,11 +4867,11 @@ static int qeth_qdio_establish(struct qeth_card *card) rc = -ENOMEM; goto out_free_queue_start_poll; } + for (i = 0, k = 0; i < card->qdio.no_out_queues; ++i) - for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; ++j, ++k) { - out_sbal_ptrs[k] = (struct qdio_buffer *)virt_to_phys( - card->qdio.out_qs[i]->bufs[j]->buffer); - } + for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; j++, k++) + out_sbal_ptrs[k] = + card->qdio.out_qs[i]->bufs[j]->buffer; memset(&init_data, 0, sizeof(struct qdio_initialize)); init_data.cdev = CARD_DDEV(card); @@ -5289,7 +5349,7 @@ static int qeth_extract_skb(struct qeth_card *card, offset = 0; } - hdr = element->addr + offset; + hdr = phys_to_virt(element->addr) + offset; offset += sizeof(*hdr); skb = NULL; @@ -5344,7 +5404,7 @@ static int qeth_extract_skb(struct qeth_card *card, } use_rx_sg = (card->options.cq == QETH_CQ_ENABLED) || - ((skb_len >= card->options.rx_sg_cb) && + (skb_len > card->options.rx_sg_cb && !atomic_read(&card->force_alloc_skb) && !IS_OSN(card)); @@ -5388,7 +5448,7 @@ static int qeth_extract_skb(struct qeth_card *card, walk_packet: while (skb_len) { int data_len = min(skb_len, (int)(element->length - offset)); - char *data = element->addr + offset; + char *data = phys_to_virt(element->addr) + offset; skb_len -= data_len; offset += data_len; @@ -5447,7 +5507,6 @@ static int qeth_extract_skbs(struct qeth_card *card, int budget, { int work_done = 0; - WARN_ON_ONCE(!budget); *done = false; while (budget) { diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c index 2bd9993aa60b8c89546331a25c6013b43646def6..78cae61bc924cb958eed75d041d698b51403e69b 100644 --- a/drivers/s390/net/qeth_core_sys.c +++ b/drivers/s390/net/qeth_core_sys.c @@ -247,8 +247,8 @@ static ssize_t qeth_dev_bufcnt_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct qeth_card *card = dev_get_drvdata(dev); + unsigned int cnt; char *tmp; - int cnt, old_cnt; int rc = 0; mutex_lock(&card->conf_mutex); @@ -257,13 +257,12 @@ static ssize_t qeth_dev_bufcnt_store(struct device *dev, goto out; } - old_cnt = card->qdio.in_buf_pool.buf_count; cnt = simple_strtoul(buf, &tmp, 10); cnt = (cnt < QETH_IN_BUF_COUNT_MIN) ? QETH_IN_BUF_COUNT_MIN : ((cnt > QETH_IN_BUF_COUNT_MAX) ? QETH_IN_BUF_COUNT_MAX : cnt); - if (old_cnt != cnt) { - rc = qeth_realloc_buffer_pool(card, cnt); - } + + rc = qeth_resize_buffer_pool(card, cnt); + out: mutex_unlock(&card->conf_mutex); return rc ? rc : count; diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 692bd26234018f2a260fa16d3085616390a6fab9..8fb29371788b5cedc5356a3f1c81cce1b1163065 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -284,6 +284,7 @@ static void qeth_l2_stop_card(struct qeth_card *card) if (card->state == CARD_STATE_SOFTSETUP) { qeth_clear_ipacmd_list(card); qeth_drain_output_queues(card); + cancel_delayed_work_sync(&card->buffer_reclaim_work); card->state = CARD_STATE_DOWN; } @@ -1707,15 +1708,14 @@ int qeth_l2_vnicc_set_state(struct qeth_card *card, u32 vnicc, bool state) QETH_CARD_TEXT(card, 2, "vniccsch"); - /* do not change anything if BridgePort is enabled */ - if (qeth_bridgeport_is_in_use(card)) - return -EBUSY; - /* check if characteristic and enable/disable are supported */ if (!(card->options.vnicc.sup_chars & vnicc) || !(card->options.vnicc.set_char_sup & vnicc)) return -EOPNOTSUPP; + if (qeth_bridgeport_is_in_use(card)) + return -EBUSY; + /* set enable/disable command and store wanted characteristic */ if (state) { cmd = IPA_VNICC_ENABLE; @@ -1761,14 +1761,13 @@ int qeth_l2_vnicc_get_state(struct qeth_card *card, u32 vnicc, bool *state) QETH_CARD_TEXT(card, 2, "vniccgch"); - /* do not get anything if BridgePort is enabled */ - if (qeth_bridgeport_is_in_use(card)) - return -EBUSY; - /* check if characteristic is supported */ if (!(card->options.vnicc.sup_chars & vnicc)) return -EOPNOTSUPP; + if (qeth_bridgeport_is_in_use(card)) + return -EBUSY; + /* if card is ready, query current VNICC state */ if (qeth_card_hw_is_reachable(card)) rc = qeth_l2_vnicc_query_chars(card); @@ -1786,15 +1785,14 @@ int qeth_l2_vnicc_set_timeout(struct qeth_card *card, u32 timeout) QETH_CARD_TEXT(card, 2, "vniccsto"); - /* do not change anything if BridgePort is enabled */ - if (qeth_bridgeport_is_in_use(card)) - return -EBUSY; - /* check if characteristic and set_timeout are supported */ if (!(card->options.vnicc.sup_chars & QETH_VNICC_LEARNING) || !(card->options.vnicc.getset_timeout_sup & QETH_VNICC_LEARNING)) return -EOPNOTSUPP; + if (qeth_bridgeport_is_in_use(card)) + return -EBUSY; + /* do we need to do anything? */ if (card->options.vnicc.learning_timeout == timeout) return rc; @@ -1823,14 +1821,14 @@ int qeth_l2_vnicc_get_timeout(struct qeth_card *card, u32 *timeout) QETH_CARD_TEXT(card, 2, "vniccgto"); - /* do not get anything if BridgePort is enabled */ - if (qeth_bridgeport_is_in_use(card)) - return -EBUSY; - /* check if characteristic and get_timeout are supported */ if (!(card->options.vnicc.sup_chars & QETH_VNICC_LEARNING) || !(card->options.vnicc.getset_timeout_sup & QETH_VNICC_LEARNING)) return -EOPNOTSUPP; + + if (qeth_bridgeport_is_in_use(card)) + return -EBUSY; + /* if card is ready, get timeout. Otherwise, just return stored value */ *timeout = card->options.vnicc.learning_timeout; if (qeth_card_hw_is_reachable(card)) diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 317d56647a4a3b8965b155be0fcfc83b0bdc157e..82f800d1d7b3aacb54099b53160ea0a6c06b803f 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -1178,6 +1178,7 @@ static void qeth_l3_stop_card(struct qeth_card *card) qeth_l3_clear_ip_htable(card, 1); qeth_clear_ipacmd_list(card); qeth_drain_output_queues(card); + cancel_delayed_work_sync(&card->buffer_reclaim_work); card->state = CARD_STATE_DOWN; } diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c index 29f2517d2a31b325928e10324215ca85680263fd..a3d1c3bdfadb17d033ec23fcc1aa3367aa4437fc 100644 --- a/drivers/s390/net/qeth_l3_sys.c +++ b/drivers/s390/net/qeth_l3_sys.c @@ -206,12 +206,11 @@ static ssize_t qeth_l3_dev_sniffer_store(struct device *dev, qdio_get_ssqd_desc(CARD_DDEV(card), &card->ssqd); if (card->ssqd.qdioac2 & CHSC_AC2_SNIFFER_AVAILABLE) { card->options.sniffer = i; - if (card->qdio.init_pool.buf_count != - QETH_IN_BUF_COUNT_MAX) - qeth_realloc_buffer_pool(card, - QETH_IN_BUF_COUNT_MAX); - } else + qeth_resize_buffer_pool(card, QETH_IN_BUF_COUNT_MAX); + } else { rc = -EPERM; + } + break; default: rc = -EINVAL; diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c index 223a805f0b0bf4bcef3da55d73c86f9705c72463..cae9b7ff79b086e565d63ee8c74122a9dec8a377 100644 --- a/drivers/s390/scsi/zfcp_fsf.c +++ b/drivers/s390/scsi/zfcp_fsf.c @@ -2510,7 +2510,7 @@ void zfcp_fsf_reqid_check(struct zfcp_qdio *qdio, int sbal_idx) for (idx = 0; idx < QDIO_MAX_ELEMENTS_PER_BUFFER; idx++) { sbale = &sbal->element[idx]; - req_id = (unsigned long) sbale->addr; + req_id = sbale->addr; fsf_req = zfcp_reqlist_find_rm(adapter->req_list, req_id); if (!fsf_req) { diff --git a/drivers/s390/scsi/zfcp_fsf.h b/drivers/s390/scsi/zfcp_fsf.h index 2b1e4da1944f572acc88a29726245e9934d00d72..4bfb79f20588b24f00c81e9d094b75a507bb7068 100644 --- a/drivers/s390/scsi/zfcp_fsf.h +++ b/drivers/s390/scsi/zfcp_fsf.h @@ -410,7 +410,7 @@ struct fsf_qtcb_bottom_port { u8 cb_util; u8 a_util; u8 res2; - u16 temperature; + s16 temperature; u16 vcc; u16 tx_bias; u16 tx_power; diff --git a/drivers/s390/scsi/zfcp_qdio.c b/drivers/s390/scsi/zfcp_qdio.c index 661436a92f8e69903200a568304276b3f3b1b12f..f0d6296e673b46ae27c24ae5dd873f466c58e2b4 100644 --- a/drivers/s390/scsi/zfcp_qdio.c +++ b/drivers/s390/scsi/zfcp_qdio.c @@ -98,7 +98,7 @@ static void zfcp_qdio_int_resp(struct ccw_device *cdev, unsigned int qdio_err, memset(pl, 0, ZFCP_QDIO_MAX_SBALS_PER_REQ * sizeof(void *)); sbale = qdio->res_q[idx]->element; - req_id = (u64) sbale->addr; + req_id = sbale->addr; scount = min(sbale->scount + 1, ZFCP_QDIO_MAX_SBALS_PER_REQ + 1); /* incl. signaling SBAL */ @@ -199,7 +199,7 @@ int zfcp_qdio_sbals_from_sg(struct zfcp_qdio *qdio, struct zfcp_qdio_req *q_req, q_req->sbal_number); return -EINVAL; } - sbale->addr = sg_virt(sg); + sbale->addr = sg_phys(sg); sbale->length = sg->length; } return 0; @@ -418,7 +418,7 @@ int zfcp_qdio_open(struct zfcp_qdio *qdio) sbale->length = 0; sbale->eflags = SBAL_EFLAGS_LAST_ENTRY; sbale->sflags = 0; - sbale->addr = NULL; + sbale->addr = 0; } if (do_QDIO(cdev, QDIO_FLAG_SYNC_INPUT, 0, 0, QDIO_MAX_BUFFERS_PER_Q)) diff --git a/drivers/s390/scsi/zfcp_qdio.h b/drivers/s390/scsi/zfcp_qdio.h index 2a816a37b3c018399157926ef8ffbcfe94d52a7a..6b43d6b254bef2e34757a4bafe92bc3d0a19129a 100644 --- a/drivers/s390/scsi/zfcp_qdio.h +++ b/drivers/s390/scsi/zfcp_qdio.h @@ -122,14 +122,14 @@ void zfcp_qdio_req_init(struct zfcp_qdio *qdio, struct zfcp_qdio_req *q_req, % QDIO_MAX_BUFFERS_PER_Q; sbale = zfcp_qdio_sbale_req(qdio, q_req); - sbale->addr = (void *) req_id; + sbale->addr = req_id; sbale->eflags = 0; sbale->sflags = SBAL_SFLAGS0_COMMAND | sbtype; if (unlikely(!data)) return; sbale++; - sbale->addr = data; + sbale->addr = virt_to_phys(data); sbale->length = len; } @@ -152,7 +152,7 @@ void zfcp_qdio_fill_next(struct zfcp_qdio *qdio, struct zfcp_qdio_req *q_req, BUG_ON(q_req->sbale_curr == qdio->max_sbale_per_sbal - 1); q_req->sbale_curr++; sbale = zfcp_qdio_sbale_curr(qdio, q_req); - sbale->addr = data; + sbale->addr = virt_to_phys(data); sbale->length = len; } diff --git a/drivers/s390/scsi/zfcp_sysfs.c b/drivers/s390/scsi/zfcp_sysfs.c index 494b9fe9cc944c55011f16ccf04bea12d92f40a9..a711a0d151002d7b16212d15130a1362b1ff7a13 100644 --- a/drivers/s390/scsi/zfcp_sysfs.c +++ b/drivers/s390/scsi/zfcp_sysfs.c @@ -800,7 +800,7 @@ static ZFCP_DEV_ATTR(adapter_diag, b2b_credit, 0400, static ZFCP_DEV_ATTR(adapter_diag_sfp, _name, 0400, \ zfcp_sysfs_adapter_diag_sfp_##_name##_show, NULL) -ZFCP_DEFINE_DIAG_SFP_ATTR(temperature, temperature, 5, "%hu"); +ZFCP_DEFINE_DIAG_SFP_ATTR(temperature, temperature, 6, "%hd"); ZFCP_DEFINE_DIAG_SFP_ATTR(vcc, vcc, 5, "%hu"); ZFCP_DEFINE_DIAG_SFP_ATTR(tx_bias, tx_bias, 5, "%hu"); ZFCP_DEFINE_DIAG_SFP_ATTR(tx_power, tx_power, 5, "%hu"); diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index ae45cbe98ae23957306c700ae0a6e1e1de05493c..cd8db134987153572ca6c3636f02a207297aa0d5 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -9950,6 +9950,7 @@ static void ipr_init_ioa_cfg(struct ipr_ioa_cfg *ioa_cfg, ioa_cfg->max_devs_supported = ipr_max_devs; if (ioa_cfg->sis64) { + host->max_channel = IPR_MAX_SIS64_BUSES; host->max_id = IPR_MAX_SIS64_TARGETS_PER_BUS; host->max_lun = IPR_MAX_SIS64_LUNS_PER_TARGET; if (ipr_max_devs > IPR_MAX_SIS64_DEVS) @@ -9958,6 +9959,7 @@ static void ipr_init_ioa_cfg(struct ipr_ioa_cfg *ioa_cfg, + ((sizeof(struct ipr_config_table_entry64) * ioa_cfg->max_devs_supported))); } else { + host->max_channel = IPR_VSET_BUS; host->max_id = IPR_MAX_NUM_TARGETS_PER_BUS; host->max_lun = IPR_MAX_NUM_LUNS_PER_TARGET; if (ipr_max_devs > IPR_MAX_PHYSICAL_DEVS) @@ -9967,7 +9969,6 @@ static void ipr_init_ioa_cfg(struct ipr_ioa_cfg *ioa_cfg, * ioa_cfg->max_devs_supported))); } - host->max_channel = IPR_VSET_BUS; host->unique_id = host->host_no; host->max_cmd_len = IPR_MAX_CDB_LEN; host->can_queue = ioa_cfg->max_cmds; diff --git a/drivers/scsi/ipr.h b/drivers/scsi/ipr.h index a67baeb36d1f7e942149427b349f5d8cd456e843..b97aa9ac2ffe5e09645850b30d5b0ac3d70740cb 100644 --- a/drivers/scsi/ipr.h +++ b/drivers/scsi/ipr.h @@ -1300,6 +1300,7 @@ struct ipr_resource_entry { #define IPR_ARRAY_VIRTUAL_BUS 0x1 #define IPR_VSET_VIRTUAL_BUS 0x2 #define IPR_IOAFP_VIRTUAL_BUS 0x3 +#define IPR_MAX_SIS64_BUSES 0x4 #define IPR_GET_RES_PHYS_LOC(res) \ (((res)->bus << 24) | ((res)->target << 8) | (res)->lun) diff --git a/drivers/scsi/libfc/fc_disc.c b/drivers/scsi/libfc/fc_disc.c index 9c5f7c9178c66351a5c74e0b1e8c12c359ae8776..2b865c6423e293b6e3b4a04cac83a5a4923d0e72 100644 --- a/drivers/scsi/libfc/fc_disc.c +++ b/drivers/scsi/libfc/fc_disc.c @@ -628,6 +628,8 @@ static void fc_disc_gpn_id_resp(struct fc_seq *sp, struct fc_frame *fp, } out: kref_put(&rdata->kref, fc_rport_destroy); + if (!IS_ERR(fp)) + fc_frame_free(fp); } /** diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c index f3b36fd0a0ebd6f5d09690f12b20f4360d12ea47..b2ad96564484000ca4ca1c10bb9f984601a8ace9 100644 --- a/drivers/scsi/megaraid/megaraid_sas_fusion.c +++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c @@ -623,7 +623,8 @@ megasas_alloc_request_fusion(struct megasas_instance *instance) fusion->io_request_frames = dma_pool_alloc(fusion->io_request_frames_pool, - GFP_KERNEL, &fusion->io_request_frames_phys); + GFP_KERNEL | __GFP_NOWARN, + &fusion->io_request_frames_phys); if (!fusion->io_request_frames) { if (instance->max_fw_cmds >= (MEGASAS_REDUCE_QD_COUNT * 2)) { instance->max_fw_cmds -= MEGASAS_REDUCE_QD_COUNT; @@ -661,7 +662,7 @@ megasas_alloc_request_fusion(struct megasas_instance *instance) fusion->io_request_frames = dma_pool_alloc(fusion->io_request_frames_pool, - GFP_KERNEL, + GFP_KERNEL | __GFP_NOWARN, &fusion->io_request_frames_phys); if (!fusion->io_request_frames) { diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index e4282bce583475a046a679093d4ddf6cc706b105..f45c22b097269b555255731065d301f6a47b7315 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -161,6 +161,7 @@ int sd_zbc_report_zones(struct gendisk *disk, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data) { struct scsi_disk *sdkp = scsi_disk(disk); + sector_t capacity = logical_to_sectors(sdkp->device, sdkp->capacity); unsigned int nr, i; unsigned char *buf; size_t offset, buflen = 0; @@ -171,11 +172,15 @@ int sd_zbc_report_zones(struct gendisk *disk, sector_t sector, /* Not a zoned device */ return -EOPNOTSUPP; + if (!capacity) + /* Device gone or invalid */ + return -ENODEV; + buf = sd_zbc_alloc_report_buffer(sdkp, nr_zones, &buflen); if (!buf) return -ENOMEM; - while (zone_idx < nr_zones && sector < get_capacity(disk)) { + while (zone_idx < nr_zones && sector < capacity) { ret = sd_zbc_do_report_zones(sdkp, buf, buflen, sectors_to_logical(sdkp->device, sector), true); if (ret) diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 0fbb8fe6e521b9edf427435b4d6ef2a41008054b..e4240e4ae8bbdcae4f850778deae56968c937c05 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -688,7 +688,7 @@ static const struct block_device_operations sr_bdops = .release = sr_block_release, .ioctl = sr_block_ioctl, #ifdef CONFIG_COMPAT - .ioctl = sr_block_compat_ioctl, + .compat_ioctl = sr_block_compat_ioctl, #endif .check_events = sr_block_check_events, .revalidate_disk = sr_block_revalidate_disk, diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index abd0e6b05f7913a9c3ba3dbac66a57abb078f74d..2d705694636c235c71534cdae3b13eb17bd4a6a8 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -3884,18 +3884,25 @@ EXPORT_SYMBOL_GPL(ufshcd_uic_hibern8_exit); void ufshcd_auto_hibern8_update(struct ufs_hba *hba, u32 ahit) { unsigned long flags; + bool update = false; - if (!(hba->capabilities & MASK_AUTO_HIBERN8_SUPPORT)) + if (!ufshcd_is_auto_hibern8_supported(hba)) return; spin_lock_irqsave(hba->host->host_lock, flags); - if (hba->ahit == ahit) - goto out_unlock; - hba->ahit = ahit; - if (!pm_runtime_suspended(hba->dev)) - ufshcd_writel(hba, hba->ahit, REG_AUTO_HIBERNATE_IDLE_TIMER); -out_unlock: + if (hba->ahit != ahit) { + hba->ahit = ahit; + update = true; + } spin_unlock_irqrestore(hba->host->host_lock, flags); + + if (update && !pm_runtime_suspended(hba->dev)) { + pm_runtime_get_sync(hba->dev); + ufshcd_hold(hba, false); + ufshcd_auto_hibern8_enable(hba); + ufshcd_release(hba); + pm_runtime_put(hba->dev); + } } EXPORT_SYMBOL_GPL(ufshcd_auto_hibern8_update); diff --git a/drivers/slimbus/qcom-ngd-ctrl.c b/drivers/slimbus/qcom-ngd-ctrl.c index e3f5ebc0c05ec5cde6daa1a6b5940b68d644fecc..fc2575fef51bafa8c4055f69a3008cc962b60326 100644 --- a/drivers/slimbus/qcom-ngd-ctrl.c +++ b/drivers/slimbus/qcom-ngd-ctrl.c @@ -1320,6 +1320,9 @@ static const struct of_device_id qcom_slim_ngd_dt_match[] = { { .compatible = "qcom,slim-ngd-v1.5.0", .data = &ngd_v1_5_offset_info, + },{ + .compatible = "qcom,slim-ngd-v2.1.0", + .data = &ngd_v1_5_offset_info, }, {} }; diff --git a/drivers/soc/imx/soc-imx-scu.c b/drivers/soc/imx/soc-imx-scu.c index fb70b8a3f7c523964e1aec543341638bf7929e36..20d37eaeb5f2cc3ae49845278359642254f850e2 100644 --- a/drivers/soc/imx/soc-imx-scu.c +++ b/drivers/soc/imx/soc-imx-scu.c @@ -25,7 +25,7 @@ struct imx_sc_msg_misc_get_soc_id { u32 id; } resp; } data; -} __packed; +} __packed __aligned(4); struct imx_sc_msg_misc_get_soc_uid { struct imx_sc_rpc_msg hdr; diff --git a/drivers/soc/tegra/fuse/fuse-tegra30.c b/drivers/soc/tegra/fuse/fuse-tegra30.c index f68f4e1c215d123959e80a4e5db9c2bdfcd23939..e6037f900fb70ab31884be5f0cc48cd2c6e4aed3 100644 --- a/drivers/soc/tegra/fuse/fuse-tegra30.c +++ b/drivers/soc/tegra/fuse/fuse-tegra30.c @@ -36,7 +36,8 @@ defined(CONFIG_ARCH_TEGRA_124_SOC) || \ defined(CONFIG_ARCH_TEGRA_132_SOC) || \ defined(CONFIG_ARCH_TEGRA_210_SOC) || \ - defined(CONFIG_ARCH_TEGRA_186_SOC) + defined(CONFIG_ARCH_TEGRA_186_SOC) || \ + defined(CONFIG_ARCH_TEGRA_194_SOC) static u32 tegra30_fuse_read_early(struct tegra_fuse *fuse, unsigned int offset) { if (WARN_ON(!fuse->base)) diff --git a/drivers/spi/atmel-quadspi.c b/drivers/spi/atmel-quadspi.c index fd8007ebb14589ba6ef0d5419878ab5e573687ae..13def7f78b9e99c9829af817496c794071042981 100644 --- a/drivers/spi/atmel-quadspi.c +++ b/drivers/spi/atmel-quadspi.c @@ -149,6 +149,7 @@ struct atmel_qspi { struct clk *qspick; struct platform_device *pdev; const struct atmel_qspi_caps *caps; + resource_size_t mmap_size; u32 pending; u32 mr; u32 scr; @@ -329,6 +330,14 @@ static int atmel_qspi_exec_op(struct spi_mem *mem, const struct spi_mem_op *op) u32 sr, offset; int err; + /* + * Check if the address exceeds the MMIO window size. An improvement + * would be to add support for regular SPI mode and fall back to it + * when the flash memories overrun the controller's memory space. + */ + if (op->addr.val + op->data.nbytes > aq->mmap_size) + return -ENOTSUPP; + err = atmel_qspi_set_cfg(aq, op, &offset); if (err) return err; @@ -480,6 +489,8 @@ static int atmel_qspi_probe(struct platform_device *pdev) goto exit; } + aq->mmap_size = resource_size(res); + /* Get the peripheral clock */ aq->pclk = devm_clk_get(&pdev->dev, "pclk"); if (IS_ERR(aq->pclk)) diff --git a/drivers/spi/spi-bcm63xx-hsspi.c b/drivers/spi/spi-bcm63xx-hsspi.c index 7327309ea3d51772ad5c57edbc3d509192d93d05..6c235306c0e4a8658e31fed475e37057d94a3663 100644 --- a/drivers/spi/spi-bcm63xx-hsspi.c +++ b/drivers/spi/spi-bcm63xx-hsspi.c @@ -366,7 +366,6 @@ static int bcm63xx_hsspi_probe(struct platform_device *pdev) goto out_disable_clk; rate = clk_get_rate(pll_clk); - clk_disable_unprepare(pll_clk); if (!rate) { ret = -EINVAL; goto out_disable_pll_clk; diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c index 7e2292c11d120b44d904c93c7433724a0ea7371e..e9e256718ef4aa9806937acc29ad5554411350d2 100644 --- a/drivers/spi/spi-omap2-mcspi.c +++ b/drivers/spi/spi-omap2-mcspi.c @@ -130,6 +130,7 @@ struct omap2_mcspi { int fifo_depth; bool slave_aborted; unsigned int pin_dir:1; + size_t max_xfer_len; }; struct omap2_mcspi_cs { @@ -974,20 +975,12 @@ static int omap2_mcspi_setup_transfer(struct spi_device *spi, * Note that we currently allow DMA only if we get a channel * for both rx and tx. Otherwise we'll do PIO for both rx and tx. */ -static int omap2_mcspi_request_dma(struct spi_device *spi) +static int omap2_mcspi_request_dma(struct omap2_mcspi *mcspi, + struct omap2_mcspi_dma *mcspi_dma) { - struct spi_master *master = spi->master; - struct omap2_mcspi *mcspi; - struct omap2_mcspi_dma *mcspi_dma; int ret = 0; - mcspi = spi_master_get_devdata(master); - mcspi_dma = mcspi->dma_channels + spi->chip_select; - - init_completion(&mcspi_dma->dma_rx_completion); - init_completion(&mcspi_dma->dma_tx_completion); - - mcspi_dma->dma_rx = dma_request_chan(&master->dev, + mcspi_dma->dma_rx = dma_request_chan(mcspi->dev, mcspi_dma->dma_rx_ch_name); if (IS_ERR(mcspi_dma->dma_rx)) { ret = PTR_ERR(mcspi_dma->dma_rx); @@ -995,7 +988,7 @@ static int omap2_mcspi_request_dma(struct spi_device *spi) goto no_dma; } - mcspi_dma->dma_tx = dma_request_chan(&master->dev, + mcspi_dma->dma_tx = dma_request_chan(mcspi->dev, mcspi_dma->dma_tx_ch_name); if (IS_ERR(mcspi_dma->dma_tx)) { ret = PTR_ERR(mcspi_dma->dma_tx); @@ -1004,20 +997,40 @@ static int omap2_mcspi_request_dma(struct spi_device *spi) mcspi_dma->dma_rx = NULL; } + init_completion(&mcspi_dma->dma_rx_completion); + init_completion(&mcspi_dma->dma_tx_completion); + no_dma: return ret; } +static void omap2_mcspi_release_dma(struct spi_master *master) +{ + struct omap2_mcspi *mcspi = spi_master_get_devdata(master); + struct omap2_mcspi_dma *mcspi_dma; + int i; + + for (i = 0; i < master->num_chipselect; i++) { + mcspi_dma = &mcspi->dma_channels[i]; + + if (mcspi_dma->dma_rx) { + dma_release_channel(mcspi_dma->dma_rx); + mcspi_dma->dma_rx = NULL; + } + if (mcspi_dma->dma_tx) { + dma_release_channel(mcspi_dma->dma_tx); + mcspi_dma->dma_tx = NULL; + } + } +} + static int omap2_mcspi_setup(struct spi_device *spi) { int ret; struct omap2_mcspi *mcspi = spi_master_get_devdata(spi->master); struct omap2_mcspi_regs *ctx = &mcspi->ctx; - struct omap2_mcspi_dma *mcspi_dma; struct omap2_mcspi_cs *cs = spi->controller_state; - mcspi_dma = &mcspi->dma_channels[spi->chip_select]; - if (!cs) { cs = kzalloc(sizeof *cs, GFP_KERNEL); if (!cs) @@ -1042,13 +1055,6 @@ static int omap2_mcspi_setup(struct spi_device *spi) } } - if (!mcspi_dma->dma_rx || !mcspi_dma->dma_tx) { - ret = omap2_mcspi_request_dma(spi); - if (ret) - dev_warn(&spi->dev, "not using DMA for McSPI (%d)\n", - ret); - } - ret = pm_runtime_get_sync(mcspi->dev); if (ret < 0) { pm_runtime_put_noidle(mcspi->dev); @@ -1065,12 +1071,8 @@ static int omap2_mcspi_setup(struct spi_device *spi) static void omap2_mcspi_cleanup(struct spi_device *spi) { - struct omap2_mcspi *mcspi; - struct omap2_mcspi_dma *mcspi_dma; struct omap2_mcspi_cs *cs; - mcspi = spi_master_get_devdata(spi->master); - if (spi->controller_state) { /* Unlink controller state from context save list */ cs = spi->controller_state; @@ -1079,19 +1081,6 @@ static void omap2_mcspi_cleanup(struct spi_device *spi) kfree(cs); } - if (spi->chip_select < spi->master->num_chipselect) { - mcspi_dma = &mcspi->dma_channels[spi->chip_select]; - - if (mcspi_dma->dma_rx) { - dma_release_channel(mcspi_dma->dma_rx); - mcspi_dma->dma_rx = NULL; - } - if (mcspi_dma->dma_tx) { - dma_release_channel(mcspi_dma->dma_tx); - mcspi_dma->dma_tx = NULL; - } - } - if (gpio_is_valid(spi->cs_gpio)) gpio_free(spi->cs_gpio); } @@ -1302,9 +1291,24 @@ static bool omap2_mcspi_can_dma(struct spi_master *master, if (spi_controller_is_slave(master)) return true; + master->dma_rx = mcspi_dma->dma_rx; + master->dma_tx = mcspi_dma->dma_tx; + return (xfer->len >= DMA_MIN_BYTES); } +static size_t omap2_mcspi_max_xfer_size(struct spi_device *spi) +{ + struct omap2_mcspi *mcspi = spi_master_get_devdata(spi->master); + struct omap2_mcspi_dma *mcspi_dma = + &mcspi->dma_channels[spi->chip_select]; + + if (mcspi->max_xfer_len && mcspi_dma->dma_rx) + return mcspi->max_xfer_len; + + return SIZE_MAX; +} + static int omap2_mcspi_controller_setup(struct omap2_mcspi *mcspi) { struct spi_master *master = mcspi->master; @@ -1373,6 +1377,11 @@ static struct omap2_mcspi_platform_config omap4_pdata = { .regs_offset = OMAP4_MCSPI_REG_OFFSET, }; +static struct omap2_mcspi_platform_config am654_pdata = { + .regs_offset = OMAP4_MCSPI_REG_OFFSET, + .max_xfer_len = SZ_4K - 1, +}; + static const struct of_device_id omap_mcspi_of_match[] = { { .compatible = "ti,omap2-mcspi", @@ -1382,6 +1391,10 @@ static const struct of_device_id omap_mcspi_of_match[] = { .compatible = "ti,omap4-mcspi", .data = &omap4_pdata, }, + { + .compatible = "ti,am654-mcspi", + .data = &am654_pdata, + }, { }, }; MODULE_DEVICE_TABLE(of, omap_mcspi_of_match); @@ -1439,6 +1452,10 @@ static int omap2_mcspi_probe(struct platform_device *pdev) mcspi->pin_dir = pdata->pin_dir; } regs_offset = pdata->regs_offset; + if (pdata->max_xfer_len) { + mcspi->max_xfer_len = pdata->max_xfer_len; + master->max_transfer_size = omap2_mcspi_max_xfer_size; + } r = platform_get_resource(pdev, IORESOURCE_MEM, 0); mcspi->base = devm_ioremap_resource(&pdev->dev, r); @@ -1464,6 +1481,11 @@ static int omap2_mcspi_probe(struct platform_device *pdev) for (i = 0; i < master->num_chipselect; i++) { sprintf(mcspi->dma_channels[i].dma_rx_ch_name, "rx%d", i); sprintf(mcspi->dma_channels[i].dma_tx_ch_name, "tx%d", i); + + status = omap2_mcspi_request_dma(mcspi, + &mcspi->dma_channels[i]); + if (status == -EPROBE_DEFER) + goto free_master; } status = platform_get_irq(pdev, 0); @@ -1501,6 +1523,7 @@ static int omap2_mcspi_probe(struct platform_device *pdev) pm_runtime_put_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); free_master: + omap2_mcspi_release_dma(master); spi_master_put(master); return status; } @@ -1510,6 +1533,8 @@ static int omap2_mcspi_remove(struct platform_device *pdev) struct spi_master *master = platform_get_drvdata(pdev); struct omap2_mcspi *mcspi = spi_master_get_devdata(master); + omap2_mcspi_release_dma(master); + pm_runtime_dont_use_autosuspend(mcspi->dev); pm_runtime_put_sync(mcspi->dev); pm_runtime_disable(&pdev->dev); diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c index 4c7a71f0fb3e3fc7a2d53f6bd076ce8ac364e171..2e318158fca97686200ff2aa6b8169158911c204 100644 --- a/drivers/spi/spi-pxa2xx.c +++ b/drivers/spi/spi-pxa2xx.c @@ -70,6 +70,10 @@ MODULE_ALIAS("platform:pxa2xx-spi"); #define LPSS_CAPS_CS_EN_SHIFT 9 #define LPSS_CAPS_CS_EN_MASK (0xf << LPSS_CAPS_CS_EN_SHIFT) +#define LPSS_PRIV_CLOCK_GATE 0x38 +#define LPSS_PRIV_CLOCK_GATE_CLK_CTL_MASK 0x3 +#define LPSS_PRIV_CLOCK_GATE_CLK_CTL_FORCE_ON 0x3 + struct lpss_config { /* LPSS offset from drv_data->ioaddr */ unsigned offset; @@ -86,6 +90,8 @@ struct lpss_config { unsigned cs_sel_shift; unsigned cs_sel_mask; unsigned cs_num; + /* Quirks */ + unsigned cs_clk_stays_gated : 1; }; /* Keep these sorted with enum pxa_ssp_type */ @@ -156,6 +162,7 @@ static const struct lpss_config lpss_platforms[] = { .tx_threshold_hi = 56, .cs_sel_shift = 8, .cs_sel_mask = 3 << 8, + .cs_clk_stays_gated = true, }, }; @@ -383,6 +390,22 @@ static void lpss_ssp_cs_control(struct spi_device *spi, bool enable) else value |= LPSS_CS_CONTROL_CS_HIGH; __lpss_ssp_write_priv(drv_data, config->reg_cs_ctrl, value); + if (config->cs_clk_stays_gated) { + u32 clkgate; + + /* + * Changing CS alone when dynamic clock gating is on won't + * actually flip CS at that time. This ruins SPI transfers + * that specify delays, or have no data. Toggle the clock mode + * to force on briefly to poke the CS pin to move. + */ + clkgate = __lpss_ssp_read_priv(drv_data, LPSS_PRIV_CLOCK_GATE); + value = (clkgate & ~LPSS_PRIV_CLOCK_GATE_CLK_CTL_MASK) | + LPSS_PRIV_CLOCK_GATE_CLK_CTL_FORCE_ON; + + __lpss_ssp_write_priv(drv_data, LPSS_PRIV_CLOCK_GATE, value); + __lpss_ssp_write_priv(drv_data, LPSS_PRIV_CLOCK_GATE, clkgate); + } } static void cs_assert(struct spi_device *spi) diff --git a/drivers/spi/spi-qup.c b/drivers/spi/spi-qup.c index dd3434a407ea669380e770760dcac4629f7e2fe0..a364b99497e26310fb4de0e7a3f546bfb61fcbd7 100644 --- a/drivers/spi/spi-qup.c +++ b/drivers/spi/spi-qup.c @@ -1217,6 +1217,11 @@ static int spi_qup_suspend(struct device *device) struct spi_qup *controller = spi_master_get_devdata(master); int ret; + if (pm_runtime_suspended(device)) { + ret = spi_qup_pm_resume_runtime(device); + if (ret) + return ret; + } ret = spi_master_suspend(master); if (ret) return ret; @@ -1225,10 +1230,8 @@ static int spi_qup_suspend(struct device *device) if (ret) return ret; - if (!pm_runtime_suspended(device)) { - clk_disable_unprepare(controller->cclk); - clk_disable_unprepare(controller->iclk); - } + clk_disable_unprepare(controller->cclk); + clk_disable_unprepare(controller->iclk); return 0; } diff --git a/drivers/spi/spi-zynqmp-gqspi.c b/drivers/spi/spi-zynqmp-gqspi.c index 60c4de4e448568f2a2b54ce1da5f21ea510401da..7412a3042a8d2c69be4c438ef4af2bf89f4f131e 100644 --- a/drivers/spi/spi-zynqmp-gqspi.c +++ b/drivers/spi/spi-zynqmp-gqspi.c @@ -401,9 +401,6 @@ static void zynqmp_qspi_chipselect(struct spi_device *qspi, bool is_high) zynqmp_gqspi_write(xqspi, GQSPI_GEN_FIFO_OFST, genfifoentry); - /* Dummy generic FIFO entry */ - zynqmp_gqspi_write(xqspi, GQSPI_GEN_FIFO_OFST, 0x0); - /* Manually start the generic FIFO command */ zynqmp_gqspi_write(xqspi, GQSPI_CONFIG_OFST, zynqmp_gqspi_read(xqspi, GQSPI_CONFIG_OFST) | diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 38b4c78df506c060fa49d9b86e97020e7a910b48..755221bc3745c0602bc1bb9a2e2dafbb890f3988 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -2639,7 +2639,7 @@ int spi_register_controller(struct spi_controller *ctlr) if (ctlr->use_gpio_descriptors) { status = spi_get_gpio_descs(ctlr); if (status) - return status; + goto free_bus_id; /* * A controller using GPIO descriptors always * supports SPI_CS_HIGH if need be. @@ -2649,7 +2649,7 @@ int spi_register_controller(struct spi_controller *ctlr) /* Legacy code path for GPIOs from DT */ status = of_spi_get_gpio_numbers(ctlr); if (status) - return status; + goto free_bus_id; } } @@ -2657,17 +2657,14 @@ int spi_register_controller(struct spi_controller *ctlr) * Even if it's just one always-selected device, there must * be at least one chipselect. */ - if (!ctlr->num_chipselect) - return -EINVAL; + if (!ctlr->num_chipselect) { + status = -EINVAL; + goto free_bus_id; + } status = device_add(&ctlr->dev); - if (status < 0) { - /* free bus id */ - mutex_lock(&board_lock); - idr_remove(&spi_master_idr, ctlr->bus_num); - mutex_unlock(&board_lock); - goto done; - } + if (status < 0) + goto free_bus_id; dev_dbg(dev, "registered %s %s\n", spi_controller_is_slave(ctlr) ? "slave" : "master", dev_name(&ctlr->dev)); @@ -2683,11 +2680,7 @@ int spi_register_controller(struct spi_controller *ctlr) status = spi_controller_initialize_queue(ctlr); if (status) { device_del(&ctlr->dev); - /* free bus id */ - mutex_lock(&board_lock); - idr_remove(&spi_master_idr, ctlr->bus_num); - mutex_unlock(&board_lock); - goto done; + goto free_bus_id; } } /* add statistics */ @@ -2702,7 +2695,12 @@ int spi_register_controller(struct spi_controller *ctlr) /* Register devices from the device tree and ACPI */ of_register_spi_devices(ctlr); acpi_register_spi_devices(ctlr); -done: + return status; + +free_bus_id: + mutex_lock(&board_lock); + idr_remove(&spi_master_idr, ctlr->bus_num); + mutex_unlock(&board_lock); return status; } EXPORT_SYMBOL_GPL(spi_register_controller); diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c index 1e217e3e9486ebd9d1147a3e95700f43d5e7935f..2ab6e782f14c2527ae7c698d1975530594e33c70 100644 --- a/drivers/spi/spidev.c +++ b/drivers/spi/spidev.c @@ -396,6 +396,7 @@ spidev_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) else retval = get_user(tmp, (u32 __user *)arg); if (retval == 0) { + struct spi_controller *ctlr = spi->controller; u32 save = spi->mode; if (tmp & ~SPI_MODE_MASK) { @@ -403,6 +404,10 @@ spidev_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) break; } + if (ctlr->use_gpio_descriptors && ctlr->cs_gpiods && + ctlr->cs_gpiods[spi->chip_select]) + tmp |= SPI_CS_HIGH; + tmp |= spi->mode & ~SPI_MODE_MASK; spi->mode = (u16)tmp; retval = spi_setup(spi); diff --git a/drivers/spmi/spmi-pmic-arb.c b/drivers/spmi/spmi-pmic-arb.c index 97acc2ba2912fa33396803d9554bc38d9268ab70..de844b412110702c1e17af0501be843c6fa522ed 100644 --- a/drivers/spmi/spmi-pmic-arb.c +++ b/drivers/spmi/spmi-pmic-arb.c @@ -731,6 +731,7 @@ static int qpnpint_irq_domain_translate(struct irq_domain *d, return 0; } +static struct lock_class_key qpnpint_irq_lock_class, qpnpint_irq_request_class; static void qpnpint_irq_domain_map(struct spmi_pmic_arb *pmic_arb, struct irq_domain *domain, unsigned int virq, @@ -746,6 +747,9 @@ static void qpnpint_irq_domain_map(struct spmi_pmic_arb *pmic_arb, else handler = handle_level_irq; + + irq_set_lockdep_class(virq, &qpnpint_irq_lock_class, + &qpnpint_irq_request_class); irq_domain_set_info(domain, virq, hwirq, &pmic_arb_irqchip, pmic_arb, handler, NULL, NULL); } diff --git a/drivers/staging/android/Kconfig b/drivers/staging/android/Kconfig index d6d605d5cbde919b372b533910813051b7f91e35..8d8fd5c29349a836cd3444dac91c2ffa02e10dec 100644 --- a/drivers/staging/android/Kconfig +++ b/drivers/staging/android/Kconfig @@ -14,14 +14,6 @@ config ASHMEM It is, in theory, a good memory allocator for low-memory devices, because it can discard shared memory units when under memory pressure. -config ANDROID_VSOC - tristate "Android Virtual SoC support" - depends on PCI_MSI - help - This option adds support for the Virtual SoC driver needed to boot - a 'cuttlefish' Android image inside QEmu. The driver interacts with - a QEmu ivshmem device. If built as a module, it will be called vsoc. - source "drivers/staging/android/ion/Kconfig" endif # if ANDROID diff --git a/drivers/staging/android/Makefile b/drivers/staging/android/Makefile index 14bd9c6ce10d3868051306e64213bf57d9dffaac..3b66cd0b0ec56d3a9d1da56b280333d3a4cdb078 100644 --- a/drivers/staging/android/Makefile +++ b/drivers/staging/android/Makefile @@ -4,4 +4,3 @@ ccflags-y += -I$(src) # needed for trace events obj-y += ion/ obj-$(CONFIG_ASHMEM) += ashmem.o -obj-$(CONFIG_ANDROID_VSOC) += vsoc.o diff --git a/drivers/staging/android/TODO b/drivers/staging/android/TODO index 767dd98fd92d55f91398c9e5a824782034634650..80eccfaf6db53c40f8beadee75e5f778e7532d44 100644 --- a/drivers/staging/android/TODO +++ b/drivers/staging/android/TODO @@ -9,14 +9,5 @@ ion/ - Split /dev/ion up into multiple nodes (e.g. /dev/ion/heap0) - Better test framework (integration with VGEM was suggested) -vsoc.c, uapi/vsoc_shm.h - - The current driver uses the same wait queue for all of the futexes in a - region. This will cause false wakeups in regions with a large number of - waiting threads. We should eventually use multiple queues and select the - queue based on the region. - - Add debugfs support for examining the permissions of regions. - - Remove VSOC_WAIT_FOR_INCOMING_INTERRUPT ioctl. This functionality has been - superseded by the futex and is there for legacy reasons. - Please send patches to Greg Kroah-Hartman and Cc: Arve Hjønnevåg and Riley Andrews diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c index 5891d0744a760b2fb8e690ac6fea2e91d96927a3..8044510d8ec673667a7ba9c90426e961a28e89c3 100644 --- a/drivers/staging/android/ashmem.c +++ b/drivers/staging/android/ashmem.c @@ -351,8 +351,23 @@ static inline vm_flags_t calc_vm_may_flags(unsigned long prot) _calc_vm_trans(prot, PROT_EXEC, VM_MAYEXEC); } +static int ashmem_vmfile_mmap(struct file *file, struct vm_area_struct *vma) +{ + /* do not allow to mmap ashmem backing shmem file directly */ + return -EPERM; +} + +static unsigned long +ashmem_vmfile_get_unmapped_area(struct file *file, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags) +{ + return current->mm->get_unmapped_area(file, addr, len, pgoff, flags); +} + static int ashmem_mmap(struct file *file, struct vm_area_struct *vma) { + static struct file_operations vmfile_fops; struct ashmem_area *asma = file->private_data; int ret = 0; @@ -393,6 +408,19 @@ static int ashmem_mmap(struct file *file, struct vm_area_struct *vma) } vmfile->f_mode |= FMODE_LSEEK; asma->file = vmfile; + /* + * override mmap operation of the vmfile so that it can't be + * remapped which would lead to creation of a new vma with no + * asma permission checks. Have to override get_unmapped_area + * as well to prevent VM_BUG_ON check for f_ops modification. + */ + if (!vmfile_fops.mmap) { + vmfile_fops = *vmfile->f_op; + vmfile_fops.mmap = ashmem_vmfile_mmap; + vmfile_fops.get_unmapped_area = + ashmem_vmfile_get_unmapped_area; + } + vmfile->f_op = &vmfile_fops; } get_file(asma->file); diff --git a/drivers/staging/android/uapi/vsoc_shm.h b/drivers/staging/android/uapi/vsoc_shm.h deleted file mode 100644 index 6291fb24efb24f17248f3bbcd8e10bea05838034..0000000000000000000000000000000000000000 --- a/drivers/staging/android/uapi/vsoc_shm.h +++ /dev/null @@ -1,295 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 2017 Google, Inc. - * - */ - -#ifndef _UAPI_LINUX_VSOC_SHM_H -#define _UAPI_LINUX_VSOC_SHM_H - -#include - -/** - * A permission is a token that permits a receiver to read and/or write an area - * of memory within a Vsoc region. - * - * An fd_scoped permission grants both read and write access, and can be - * attached to a file description (see open(2)). - * Ownership of the area can then be shared by passing a file descriptor - * among processes. - * - * begin_offset and end_offset define the area of memory that is controlled by - * the permission. owner_offset points to a word, also in shared memory, that - * controls ownership of the area. - * - * ownership of the region expires when the associated file description is - * released. - * - * At most one permission can be attached to each file description. - * - * This is useful when implementing HALs like gralloc that scope and pass - * ownership of shared resources via file descriptors. - * - * The caller is responsibe for doing any fencing. - * - * The calling process will normally identify a currently free area of - * memory. It will construct a proposed fd_scoped_permission_arg structure: - * - * begin_offset and end_offset describe the area being claimed - * - * owner_offset points to the location in shared memory that indicates the - * owner of the area. - * - * owned_value is the value that will be stored in owner_offset iff the - * permission can be granted. It must be different than VSOC_REGION_FREE. - * - * Two fd_scoped_permission structures are compatible if they vary only by - * their owned_value fields. - * - * The driver ensures that, for any group of simultaneous callers proposing - * compatible fd_scoped_permissions, it will accept exactly one of the - * propopsals. The other callers will get a failure with errno of EAGAIN. - * - * A process receiving a file descriptor can identify the region being - * granted using the VSOC_GET_FD_SCOPED_PERMISSION ioctl. - */ -struct fd_scoped_permission { - __u32 begin_offset; - __u32 end_offset; - __u32 owner_offset; - __u32 owned_value; -}; - -/* - * This value represents a free area of memory. The driver expects to see this - * value at owner_offset when creating a permission otherwise it will not do it, - * and will write this value back once the permission is no longer needed. - */ -#define VSOC_REGION_FREE ((__u32)0) - -/** - * ioctl argument for VSOC_CREATE_FD_SCOPE_PERMISSION - */ -struct fd_scoped_permission_arg { - struct fd_scoped_permission perm; - __s32 managed_region_fd; -}; - -#define VSOC_NODE_FREE ((__u32)0) - -/* - * Describes a signal table in shared memory. Each non-zero entry in the - * table indicates that the receiver should signal the futex at the given - * offset. Offsets are relative to the region, not the shared memory window. - * - * interrupt_signalled_offset is used to reliably signal interrupts across the - * vmm boundary. There are two roles: transmitter and receiver. For example, - * in the host_to_guest_signal_table the host is the transmitter and the - * guest is the receiver. The protocol is as follows: - * - * 1. The transmitter should convert the offset of the futex to an offset - * in the signal table [0, (1 << num_nodes_lg2)) - * The transmitter can choose any appropriate hashing algorithm, including - * hash = futex_offset & ((1 << num_nodes_lg2) - 1) - * - * 3. The transmitter should atomically compare and swap futex_offset with 0 - * at hash. There are 3 possible outcomes - * a. The swap fails because the futex_offset is already in the table. - * The transmitter should stop. - * b. Some other offset is in the table. This is a hash collision. The - * transmitter should move to another table slot and try again. One - * possible algorithm: - * hash = (hash + 1) & ((1 << num_nodes_lg2) - 1) - * c. The swap worked. Continue below. - * - * 3. The transmitter atomically swaps 1 with the value at the - * interrupt_signalled_offset. There are two outcomes: - * a. The prior value was 1. In this case an interrupt has already been - * posted. The transmitter is done. - * b. The prior value was 0, indicating that the receiver may be sleeping. - * The transmitter will issue an interrupt. - * - * 4. On waking the receiver immediately exchanges a 0 with the - * interrupt_signalled_offset. If it receives a 0 then this a spurious - * interrupt. That may occasionally happen in the current protocol, but - * should be rare. - * - * 5. The receiver scans the signal table by atomicaly exchanging 0 at each - * location. If a non-zero offset is returned from the exchange the - * receiver wakes all sleepers at the given offset: - * futex((int*)(region_base + old_value), FUTEX_WAKE, MAX_INT); - * - * 6. The receiver thread then does a conditional wait, waking immediately - * if the value at interrupt_signalled_offset is non-zero. This catches cases - * here additional signals were posted while the table was being scanned. - * On the guest the wait is handled via the VSOC_WAIT_FOR_INCOMING_INTERRUPT - * ioctl. - */ -struct vsoc_signal_table_layout { - /* log_2(Number of signal table entries) */ - __u32 num_nodes_lg2; - /* - * Offset to the first signal table entry relative to the start of the - * region - */ - __u32 futex_uaddr_table_offset; - /* - * Offset to an atomic_t / atomic uint32_t. A non-zero value indicates - * that one or more offsets are currently posted in the table. - * semi-unique access to an entry in the table - */ - __u32 interrupt_signalled_offset; -}; - -#define VSOC_REGION_WHOLE ((__s32)0) -#define VSOC_DEVICE_NAME_SZ 16 - -/** - * Each HAL would (usually) talk to a single device region - * Mulitple entities care about these regions: - * - The ivshmem_server will populate the regions in shared memory - * - The guest kernel will read the region, create minor device nodes, and - * allow interested parties to register for FUTEX_WAKE events in the region - * - HALs will access via the minor device nodes published by the guest kernel - * - Host side processes will access the region via the ivshmem_server: - * 1. Pass name to ivshmem_server at a UNIX socket - * 2. ivshmemserver will reply with 2 fds: - * - host->guest doorbell fd - * - guest->host doorbell fd - * - fd for the shared memory region - * - region offset - * 3. Start a futex receiver thread on the doorbell fd pointed at the - * signal_nodes - */ -struct vsoc_device_region { - __u16 current_version; - __u16 min_compatible_version; - __u32 region_begin_offset; - __u32 region_end_offset; - __u32 offset_of_region_data; - struct vsoc_signal_table_layout guest_to_host_signal_table; - struct vsoc_signal_table_layout host_to_guest_signal_table; - /* Name of the device. Must always be terminated with a '\0', so - * the longest supported device name is 15 characters. - */ - char device_name[VSOC_DEVICE_NAME_SZ]; - /* There are two ways that permissions to access regions are handled: - * - When subdivided_by is VSOC_REGION_WHOLE, any process that can - * open the device node for the region gains complete access to it. - * - When subdivided is set processes that open the region cannot - * access it. Access to a sub-region must be established by invoking - * the VSOC_CREATE_FD_SCOPE_PERMISSION ioctl on the region - * referenced in subdivided_by, providing a fileinstance - * (represented by a fd) opened on this region. - */ - __u32 managed_by; -}; - -/* - * The vsoc layout descriptor. - * The first 4K should be reserved for the shm header and region descriptors. - * The regions should be page aligned. - */ - -struct vsoc_shm_layout_descriptor { - __u16 major_version; - __u16 minor_version; - - /* size of the shm. This may be redundant but nice to have */ - __u32 size; - - /* number of shared memory regions */ - __u32 region_count; - - /* The offset to the start of region descriptors */ - __u32 vsoc_region_desc_offset; -}; - -/* - * This specifies the current version that should be stored in - * vsoc_shm_layout_descriptor.major_version and - * vsoc_shm_layout_descriptor.minor_version. - * It should be updated only if the vsoc_device_region and - * vsoc_shm_layout_descriptor structures have changed. - * Versioning within each region is transferred - * via the min_compatible_version and current_version fields in - * vsoc_device_region. The driver does not consult these fields: they are left - * for the HALs and host processes and will change independently of the layout - * version. - */ -#define CURRENT_VSOC_LAYOUT_MAJOR_VERSION 2 -#define CURRENT_VSOC_LAYOUT_MINOR_VERSION 0 - -#define VSOC_CREATE_FD_SCOPED_PERMISSION \ - _IOW(0xF5, 0, struct fd_scoped_permission) -#define VSOC_GET_FD_SCOPED_PERMISSION _IOR(0xF5, 1, struct fd_scoped_permission) - -/* - * This is used to signal the host to scan the guest_to_host_signal_table - * for new futexes to wake. This sends an interrupt if one is not already - * in flight. - */ -#define VSOC_MAYBE_SEND_INTERRUPT_TO_HOST _IO(0xF5, 2) - -/* - * When this returns the guest will scan host_to_guest_signal_table to - * check for new futexes to wake. - */ -/* TODO(ghartman): Consider moving this to the bottom half */ -#define VSOC_WAIT_FOR_INCOMING_INTERRUPT _IO(0xF5, 3) - -/* - * Guest HALs will use this to retrieve the region description after - * opening their device node. - */ -#define VSOC_DESCRIBE_REGION _IOR(0xF5, 4, struct vsoc_device_region) - -/* - * Wake any threads that may be waiting for a host interrupt on this region. - * This is mostly used during shutdown. - */ -#define VSOC_SELF_INTERRUPT _IO(0xF5, 5) - -/* - * This is used to signal the host to scan the guest_to_host_signal_table - * for new futexes to wake. This sends an interrupt unconditionally. - */ -#define VSOC_SEND_INTERRUPT_TO_HOST _IO(0xF5, 6) - -enum wait_types { - VSOC_WAIT_UNDEFINED = 0, - VSOC_WAIT_IF_EQUAL = 1, - VSOC_WAIT_IF_EQUAL_TIMEOUT = 2 -}; - -/* - * Wait for a condition to be true - * - * Note, this is sized and aligned so the 32 bit and 64 bit layouts are - * identical. - */ -struct vsoc_cond_wait { - /* Input: Offset of the 32 bit word to check */ - __u32 offset; - /* Input: Value that will be compared with the offset */ - __u32 value; - /* Monotonic time to wake at in seconds */ - __u64 wake_time_sec; - /* Input: Monotonic time to wait in nanoseconds */ - __u32 wake_time_nsec; - /* Input: Type of wait */ - __u32 wait_type; - /* Output: Number of times the thread woke before returning. */ - __u32 wakes; - /* Ensure that we're 8-byte aligned and 8 byte length for 32/64 bit - * compatibility. - */ - __u32 reserved_1; -}; - -#define VSOC_COND_WAIT _IOWR(0xF5, 7, struct vsoc_cond_wait) - -/* Wake any local threads waiting at the offset given in arg */ -#define VSOC_COND_WAKE _IO(0xF5, 8) - -#endif /* _UAPI_LINUX_VSOC_SHM_H */ diff --git a/drivers/staging/android/vsoc.c b/drivers/staging/android/vsoc.c deleted file mode 100644 index 1240bb0317d95a61c21bad5262ae469953b75104..0000000000000000000000000000000000000000 --- a/drivers/staging/android/vsoc.c +++ /dev/null @@ -1,1149 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * drivers/android/staging/vsoc.c - * - * Android Virtual System on a Chip (VSoC) driver - * - * Copyright (C) 2017 Google, Inc. - * - * Author: ghartman@google.com - * - * Based on drivers/char/kvm_ivshmem.c - driver for KVM Inter-VM shared memory - * Copyright 2009 Cam Macdonell - * - * Based on cirrusfb.c and 8139cp.c: - * Copyright 1999-2001 Jeff Garzik - * Copyright 2001-2004 Jeff Garzik - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include "uapi/vsoc_shm.h" - -#define VSOC_DEV_NAME "vsoc" - -/* - * Description of the ivshmem-doorbell PCI device used by QEmu. These - * constants follow docs/specs/ivshmem-spec.txt, which can be found in - * the QEmu repository. This was last reconciled with the version that - * came out with 2.8 - */ - -/* - * These constants are determined KVM Inter-VM shared memory device - * register offsets - */ -enum { - INTR_MASK = 0x00, /* Interrupt Mask */ - INTR_STATUS = 0x04, /* Interrupt Status */ - IV_POSITION = 0x08, /* VM ID */ - DOORBELL = 0x0c, /* Doorbell */ -}; - -static const int REGISTER_BAR; /* Equal to 0 */ -static const int MAX_REGISTER_BAR_LEN = 0x100; -/* - * The MSI-x BAR is not used directly. - * - * static const int MSI_X_BAR = 1; - */ -static const int SHARED_MEMORY_BAR = 2; - -struct vsoc_region_data { - char name[VSOC_DEVICE_NAME_SZ + 1]; - wait_queue_head_t interrupt_wait_queue; - /* TODO(b/73664181): Use multiple futex wait queues */ - wait_queue_head_t futex_wait_queue; - /* Flag indicating that an interrupt has been signalled by the host. */ - atomic_t *incoming_signalled; - /* Flag indicating the guest has signalled the host. */ - atomic_t *outgoing_signalled; - bool irq_requested; - bool device_created; -}; - -struct vsoc_device { - /* Kernel virtual address of REGISTER_BAR. */ - void __iomem *regs; - /* Physical address of SHARED_MEMORY_BAR. */ - phys_addr_t shm_phys_start; - /* Kernel virtual address of SHARED_MEMORY_BAR. */ - void __iomem *kernel_mapped_shm; - /* Size of the entire shared memory window in bytes. */ - size_t shm_size; - /* - * Pointer to the virtual address of the shared memory layout structure. - * This is probably identical to kernel_mapped_shm, but saving this - * here saves a lot of annoying casts. - */ - struct vsoc_shm_layout_descriptor *layout; - /* - * Points to a table of region descriptors in the kernel's virtual - * address space. Calculated from - * vsoc_shm_layout_descriptor.vsoc_region_desc_offset - */ - struct vsoc_device_region *regions; - /* Head of a list of permissions that have been granted. */ - struct list_head permissions; - struct pci_dev *dev; - /* Per-region (and therefore per-interrupt) information. */ - struct vsoc_region_data *regions_data; - /* - * Table of msi-x entries. This has to be separated from struct - * vsoc_region_data because the kernel deals with them as an array. - */ - struct msix_entry *msix_entries; - /* Mutex that protectes the permission list */ - struct mutex mtx; - /* Major number assigned by the kernel */ - int major; - /* Character device assigned by the kernel */ - struct cdev cdev; - /* Device class assigned by the kernel */ - struct class *class; - /* - * Flags that indicate what we've initialized. These are used to do an - * orderly cleanup of the device. - */ - bool enabled_device; - bool requested_regions; - bool cdev_added; - bool class_added; - bool msix_enabled; -}; - -static struct vsoc_device vsoc_dev; - -/* - * TODO(ghartman): Add a /sys filesystem entry that summarizes the permissions. - */ - -struct fd_scoped_permission_node { - struct fd_scoped_permission permission; - struct list_head list; -}; - -struct vsoc_private_data { - struct fd_scoped_permission_node *fd_scoped_permission_node; -}; - -static long vsoc_ioctl(struct file *, unsigned int, unsigned long); -static int vsoc_mmap(struct file *, struct vm_area_struct *); -static int vsoc_open(struct inode *, struct file *); -static int vsoc_release(struct inode *, struct file *); -static ssize_t vsoc_read(struct file *, char __user *, size_t, loff_t *); -static ssize_t vsoc_write(struct file *, const char __user *, size_t, loff_t *); -static loff_t vsoc_lseek(struct file *filp, loff_t offset, int origin); -static int -do_create_fd_scoped_permission(struct vsoc_device_region *region_p, - struct fd_scoped_permission_node *np, - struct fd_scoped_permission_arg __user *arg); -static void -do_destroy_fd_scoped_permission(struct vsoc_device_region *owner_region_p, - struct fd_scoped_permission *perm); -static long do_vsoc_describe_region(struct file *, - struct vsoc_device_region __user *); -static ssize_t vsoc_get_area(struct file *filp, __u32 *perm_off); - -/** - * Validate arguments on entry points to the driver. - */ -inline int vsoc_validate_inode(struct inode *inode) -{ - if (iminor(inode) >= vsoc_dev.layout->region_count) { - dev_err(&vsoc_dev.dev->dev, - "describe_region: invalid region %d\n", iminor(inode)); - return -ENODEV; - } - return 0; -} - -inline int vsoc_validate_filep(struct file *filp) -{ - int ret = vsoc_validate_inode(file_inode(filp)); - - if (ret) - return ret; - if (!filp->private_data) { - dev_err(&vsoc_dev.dev->dev, - "No private data on fd, region %d\n", - iminor(file_inode(filp))); - return -EBADFD; - } - return 0; -} - -/* Converts from shared memory offset to virtual address */ -static inline void *shm_off_to_virtual_addr(__u32 offset) -{ - return (void __force *)vsoc_dev.kernel_mapped_shm + offset; -} - -/* Converts from shared memory offset to physical address */ -static inline phys_addr_t shm_off_to_phys_addr(__u32 offset) -{ - return vsoc_dev.shm_phys_start + offset; -} - -/** - * Convenience functions to obtain the region from the inode or file. - * Dangerous to call before validating the inode/file. - */ -static -inline struct vsoc_device_region *vsoc_region_from_inode(struct inode *inode) -{ - return &vsoc_dev.regions[iminor(inode)]; -} - -static -inline struct vsoc_device_region *vsoc_region_from_filep(struct file *inode) -{ - return vsoc_region_from_inode(file_inode(inode)); -} - -static inline uint32_t vsoc_device_region_size(struct vsoc_device_region *r) -{ - return r->region_end_offset - r->region_begin_offset; -} - -static const struct file_operations vsoc_ops = { - .owner = THIS_MODULE, - .open = vsoc_open, - .mmap = vsoc_mmap, - .read = vsoc_read, - .unlocked_ioctl = vsoc_ioctl, - .compat_ioctl = vsoc_ioctl, - .write = vsoc_write, - .llseek = vsoc_lseek, - .release = vsoc_release, -}; - -static struct pci_device_id vsoc_id_table[] = { - {0x1af4, 0x1110, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, - {0}, -}; - -MODULE_DEVICE_TABLE(pci, vsoc_id_table); - -static void vsoc_remove_device(struct pci_dev *pdev); -static int vsoc_probe_device(struct pci_dev *pdev, - const struct pci_device_id *ent); - -static struct pci_driver vsoc_pci_driver = { - .name = "vsoc", - .id_table = vsoc_id_table, - .probe = vsoc_probe_device, - .remove = vsoc_remove_device, -}; - -static int -do_create_fd_scoped_permission(struct vsoc_device_region *region_p, - struct fd_scoped_permission_node *np, - struct fd_scoped_permission_arg __user *arg) -{ - struct file *managed_filp; - s32 managed_fd; - atomic_t *owner_ptr = NULL; - struct vsoc_device_region *managed_region_p; - - if (copy_from_user(&np->permission, - &arg->perm, sizeof(np->permission)) || - copy_from_user(&managed_fd, - &arg->managed_region_fd, sizeof(managed_fd))) { - return -EFAULT; - } - managed_filp = fdget(managed_fd).file; - /* Check that it's a valid fd, */ - if (!managed_filp || vsoc_validate_filep(managed_filp)) - return -EPERM; - /* EEXIST if the given fd already has a permission. */ - if (((struct vsoc_private_data *)managed_filp->private_data)-> - fd_scoped_permission_node) - return -EEXIST; - managed_region_p = vsoc_region_from_filep(managed_filp); - /* Check that the provided region is managed by this one */ - if (&vsoc_dev.regions[managed_region_p->managed_by] != region_p) - return -EPERM; - /* The area must be well formed and have non-zero size */ - if (np->permission.begin_offset >= np->permission.end_offset) - return -EINVAL; - /* The area must fit in the memory window */ - if (np->permission.end_offset > - vsoc_device_region_size(managed_region_p)) - return -ERANGE; - /* The area must be in the region data section */ - if (np->permission.begin_offset < - managed_region_p->offset_of_region_data) - return -ERANGE; - /* The area must be page aligned */ - if (!PAGE_ALIGNED(np->permission.begin_offset) || - !PAGE_ALIGNED(np->permission.end_offset)) - return -EINVAL; - /* Owner offset must be naturally aligned in the window */ - if (np->permission.owner_offset & - (sizeof(np->permission.owner_offset) - 1)) - return -EINVAL; - /* The owner flag must reside in the owner memory */ - if (np->permission.owner_offset + sizeof(np->permission.owner_offset) > - vsoc_device_region_size(region_p)) - return -ERANGE; - /* The owner flag must reside in the data section */ - if (np->permission.owner_offset < region_p->offset_of_region_data) - return -EINVAL; - /* The owner value must change to claim the memory */ - if (np->permission.owned_value == VSOC_REGION_FREE) - return -EINVAL; - owner_ptr = - (atomic_t *)shm_off_to_virtual_addr(region_p->region_begin_offset + - np->permission.owner_offset); - /* We've already verified that this is in the shared memory window, so - * it should be safe to write to this address. - */ - if (atomic_cmpxchg(owner_ptr, - VSOC_REGION_FREE, - np->permission.owned_value) != VSOC_REGION_FREE) { - return -EBUSY; - } - ((struct vsoc_private_data *)managed_filp->private_data)-> - fd_scoped_permission_node = np; - /* The file offset needs to be adjusted if the calling - * process did any read/write operations on the fd - * before creating the permission. - */ - if (managed_filp->f_pos) { - if (managed_filp->f_pos > np->permission.end_offset) { - /* If the offset is beyond the permission end, set it - * to the end. - */ - managed_filp->f_pos = np->permission.end_offset; - } else { - /* If the offset is within the permission interval - * keep it there otherwise reset it to zero. - */ - if (managed_filp->f_pos < np->permission.begin_offset) { - managed_filp->f_pos = 0; - } else { - managed_filp->f_pos -= - np->permission.begin_offset; - } - } - } - return 0; -} - -static void -do_destroy_fd_scoped_permission_node(struct vsoc_device_region *owner_region_p, - struct fd_scoped_permission_node *node) -{ - if (node) { - do_destroy_fd_scoped_permission(owner_region_p, - &node->permission); - mutex_lock(&vsoc_dev.mtx); - list_del(&node->list); - mutex_unlock(&vsoc_dev.mtx); - kfree(node); - } -} - -static void -do_destroy_fd_scoped_permission(struct vsoc_device_region *owner_region_p, - struct fd_scoped_permission *perm) -{ - atomic_t *owner_ptr = NULL; - int prev = 0; - - if (!perm) - return; - owner_ptr = (atomic_t *)shm_off_to_virtual_addr - (owner_region_p->region_begin_offset + perm->owner_offset); - prev = atomic_xchg(owner_ptr, VSOC_REGION_FREE); - if (prev != perm->owned_value) - dev_err(&vsoc_dev.dev->dev, - "%x-%x: owner (%s) %x: expected to be %x was %x", - perm->begin_offset, perm->end_offset, - owner_region_p->device_name, perm->owner_offset, - perm->owned_value, prev); -} - -static long do_vsoc_describe_region(struct file *filp, - struct vsoc_device_region __user *dest) -{ - struct vsoc_device_region *region_p; - int retval = vsoc_validate_filep(filp); - - if (retval) - return retval; - region_p = vsoc_region_from_filep(filp); - if (copy_to_user(dest, region_p, sizeof(*region_p))) - return -EFAULT; - return 0; -} - -/** - * Implements the inner logic of cond_wait. Copies to and from userspace are - * done in the helper function below. - */ -static int handle_vsoc_cond_wait(struct file *filp, struct vsoc_cond_wait *arg) -{ - DEFINE_WAIT(wait); - u32 region_number = iminor(file_inode(filp)); - struct vsoc_region_data *data = vsoc_dev.regions_data + region_number; - struct hrtimer_sleeper timeout, *to = NULL; - int ret = 0; - struct vsoc_device_region *region_p = vsoc_region_from_filep(filp); - atomic_t *address = NULL; - ktime_t wake_time; - - /* Ensure that the offset is aligned */ - if (arg->offset & (sizeof(uint32_t) - 1)) - return -EADDRNOTAVAIL; - /* Ensure that the offset is within shared memory */ - if (((uint64_t)arg->offset) + region_p->region_begin_offset + - sizeof(uint32_t) > region_p->region_end_offset) - return -E2BIG; - address = shm_off_to_virtual_addr(region_p->region_begin_offset + - arg->offset); - - /* Ensure that the type of wait is valid */ - switch (arg->wait_type) { - case VSOC_WAIT_IF_EQUAL: - break; - case VSOC_WAIT_IF_EQUAL_TIMEOUT: - to = &timeout; - break; - default: - return -EINVAL; - } - - if (to) { - /* Copy the user-supplied timesec into the kernel structure. - * We do things this way to flatten differences between 32 bit - * and 64 bit timespecs. - */ - if (arg->wake_time_nsec >= NSEC_PER_SEC) - return -EINVAL; - wake_time = ktime_set(arg->wake_time_sec, arg->wake_time_nsec); - - hrtimer_init_sleeper_on_stack(to, CLOCK_MONOTONIC, - HRTIMER_MODE_ABS); - hrtimer_set_expires_range_ns(&to->timer, wake_time, - current->timer_slack_ns); - } - - while (1) { - prepare_to_wait(&data->futex_wait_queue, &wait, - TASK_INTERRUPTIBLE); - /* - * Check the sentinel value after prepare_to_wait. If the value - * changes after this check the writer will call signal, - * changing the task state from INTERRUPTIBLE to RUNNING. That - * will ensure that schedule() will eventually schedule this - * task. - */ - if (atomic_read(address) != arg->value) { - ret = 0; - break; - } - if (to) { - hrtimer_sleeper_start_expires(to, HRTIMER_MODE_ABS); - if (likely(to->task)) - freezable_schedule(); - hrtimer_cancel(&to->timer); - if (!to->task) { - ret = -ETIMEDOUT; - break; - } - } else { - freezable_schedule(); - } - /* Count the number of times that we woke up. This is useful - * for unit testing. - */ - ++arg->wakes; - if (signal_pending(current)) { - ret = -EINTR; - break; - } - } - finish_wait(&data->futex_wait_queue, &wait); - if (to) - destroy_hrtimer_on_stack(&to->timer); - return ret; -} - -/** - * Handles the details of copying from/to userspace to ensure that the copies - * happen on all of the return paths of cond_wait. - */ -static int do_vsoc_cond_wait(struct file *filp, - struct vsoc_cond_wait __user *untrusted_in) -{ - struct vsoc_cond_wait arg; - int rval = 0; - - if (copy_from_user(&arg, untrusted_in, sizeof(arg))) - return -EFAULT; - /* wakes is an out parameter. Initialize it to something sensible. */ - arg.wakes = 0; - rval = handle_vsoc_cond_wait(filp, &arg); - if (copy_to_user(untrusted_in, &arg, sizeof(arg))) - return -EFAULT; - return rval; -} - -static int do_vsoc_cond_wake(struct file *filp, uint32_t offset) -{ - struct vsoc_device_region *region_p = vsoc_region_from_filep(filp); - u32 region_number = iminor(file_inode(filp)); - struct vsoc_region_data *data = vsoc_dev.regions_data + region_number; - /* Ensure that the offset is aligned */ - if (offset & (sizeof(uint32_t) - 1)) - return -EADDRNOTAVAIL; - /* Ensure that the offset is within shared memory */ - if (((uint64_t)offset) + region_p->region_begin_offset + - sizeof(uint32_t) > region_p->region_end_offset) - return -E2BIG; - /* - * TODO(b/73664181): Use multiple futex wait queues. - * We need to wake every sleeper when the condition changes. Typically - * only a single thread will be waiting on the condition, but there - * are exceptions. The worst case is about 10 threads. - */ - wake_up_interruptible_all(&data->futex_wait_queue); - return 0; -} - -static long vsoc_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) -{ - int rv = 0; - struct vsoc_device_region *region_p; - u32 reg_num; - struct vsoc_region_data *reg_data; - int retval = vsoc_validate_filep(filp); - - if (retval) - return retval; - region_p = vsoc_region_from_filep(filp); - reg_num = iminor(file_inode(filp)); - reg_data = vsoc_dev.regions_data + reg_num; - switch (cmd) { - case VSOC_CREATE_FD_SCOPED_PERMISSION: - { - struct fd_scoped_permission_node *node = NULL; - - node = kzalloc(sizeof(*node), GFP_KERNEL); - /* We can't allocate memory for the permission */ - if (!node) - return -ENOMEM; - INIT_LIST_HEAD(&node->list); - rv = do_create_fd_scoped_permission - (region_p, - node, - (struct fd_scoped_permission_arg __user *)arg); - if (!rv) { - mutex_lock(&vsoc_dev.mtx); - list_add(&node->list, &vsoc_dev.permissions); - mutex_unlock(&vsoc_dev.mtx); - } else { - kfree(node); - return rv; - } - } - break; - - case VSOC_GET_FD_SCOPED_PERMISSION: - { - struct fd_scoped_permission_node *node = - ((struct vsoc_private_data *)filp->private_data)-> - fd_scoped_permission_node; - if (!node) - return -ENOENT; - if (copy_to_user - ((struct fd_scoped_permission __user *)arg, - &node->permission, sizeof(node->permission))) - return -EFAULT; - } - break; - - case VSOC_MAYBE_SEND_INTERRUPT_TO_HOST: - if (!atomic_xchg(reg_data->outgoing_signalled, 1)) { - writel(reg_num, vsoc_dev.regs + DOORBELL); - return 0; - } else { - return -EBUSY; - } - break; - - case VSOC_SEND_INTERRUPT_TO_HOST: - writel(reg_num, vsoc_dev.regs + DOORBELL); - return 0; - case VSOC_WAIT_FOR_INCOMING_INTERRUPT: - wait_event_interruptible - (reg_data->interrupt_wait_queue, - (atomic_read(reg_data->incoming_signalled) != 0)); - break; - - case VSOC_DESCRIBE_REGION: - return do_vsoc_describe_region - (filp, - (struct vsoc_device_region __user *)arg); - - case VSOC_SELF_INTERRUPT: - atomic_set(reg_data->incoming_signalled, 1); - wake_up_interruptible(®_data->interrupt_wait_queue); - break; - - case VSOC_COND_WAIT: - return do_vsoc_cond_wait(filp, - (struct vsoc_cond_wait __user *)arg); - case VSOC_COND_WAKE: - return do_vsoc_cond_wake(filp, arg); - - default: - return -EINVAL; - } - return 0; -} - -static ssize_t vsoc_read(struct file *filp, char __user *buffer, size_t len, - loff_t *poffset) -{ - __u32 area_off; - const void *area_p; - ssize_t area_len; - int retval = vsoc_validate_filep(filp); - - if (retval) - return retval; - area_len = vsoc_get_area(filp, &area_off); - area_p = shm_off_to_virtual_addr(area_off); - area_p += *poffset; - area_len -= *poffset; - if (area_len <= 0) - return 0; - if (area_len < len) - len = area_len; - if (copy_to_user(buffer, area_p, len)) - return -EFAULT; - *poffset += len; - return len; -} - -static loff_t vsoc_lseek(struct file *filp, loff_t offset, int origin) -{ - ssize_t area_len = 0; - int retval = vsoc_validate_filep(filp); - - if (retval) - return retval; - area_len = vsoc_get_area(filp, NULL); - switch (origin) { - case SEEK_SET: - break; - - case SEEK_CUR: - if (offset > 0 && offset + filp->f_pos < 0) - return -EOVERFLOW; - offset += filp->f_pos; - break; - - case SEEK_END: - if (offset > 0 && offset + area_len < 0) - return -EOVERFLOW; - offset += area_len; - break; - - case SEEK_DATA: - if (offset >= area_len) - return -EINVAL; - if (offset < 0) - offset = 0; - break; - - case SEEK_HOLE: - /* Next hole is always the end of the region, unless offset is - * beyond that - */ - if (offset < area_len) - offset = area_len; - break; - - default: - return -EINVAL; - } - - if (offset < 0 || offset > area_len) - return -EINVAL; - filp->f_pos = offset; - - return offset; -} - -static ssize_t vsoc_write(struct file *filp, const char __user *buffer, - size_t len, loff_t *poffset) -{ - __u32 area_off; - void *area_p; - ssize_t area_len; - int retval = vsoc_validate_filep(filp); - - if (retval) - return retval; - area_len = vsoc_get_area(filp, &area_off); - area_p = shm_off_to_virtual_addr(area_off); - area_p += *poffset; - area_len -= *poffset; - if (area_len <= 0) - return 0; - if (area_len < len) - len = area_len; - if (copy_from_user(area_p, buffer, len)) - return -EFAULT; - *poffset += len; - return len; -} - -static irqreturn_t vsoc_interrupt(int irq, void *region_data_v) -{ - struct vsoc_region_data *region_data = - (struct vsoc_region_data *)region_data_v; - int reg_num = region_data - vsoc_dev.regions_data; - - if (unlikely(!region_data)) - return IRQ_NONE; - - if (unlikely(reg_num < 0 || - reg_num >= vsoc_dev.layout->region_count)) { - dev_err(&vsoc_dev.dev->dev, - "invalid irq @%p reg_num=0x%04x\n", - region_data, reg_num); - return IRQ_NONE; - } - if (unlikely(vsoc_dev.regions_data + reg_num != region_data)) { - dev_err(&vsoc_dev.dev->dev, - "irq not aligned @%p reg_num=0x%04x\n", - region_data, reg_num); - return IRQ_NONE; - } - wake_up_interruptible(®ion_data->interrupt_wait_queue); - return IRQ_HANDLED; -} - -static int vsoc_probe_device(struct pci_dev *pdev, - const struct pci_device_id *ent) -{ - int result; - int i; - resource_size_t reg_size; - dev_t devt; - - vsoc_dev.dev = pdev; - result = pci_enable_device(pdev); - if (result) { - dev_err(&pdev->dev, - "pci_enable_device failed %s: error %d\n", - pci_name(pdev), result); - return result; - } - vsoc_dev.enabled_device = true; - result = pci_request_regions(pdev, "vsoc"); - if (result < 0) { - dev_err(&pdev->dev, "pci_request_regions failed\n"); - vsoc_remove_device(pdev); - return -EBUSY; - } - vsoc_dev.requested_regions = true; - /* Set up the control registers in BAR 0 */ - reg_size = pci_resource_len(pdev, REGISTER_BAR); - if (reg_size > MAX_REGISTER_BAR_LEN) - vsoc_dev.regs = - pci_iomap(pdev, REGISTER_BAR, MAX_REGISTER_BAR_LEN); - else - vsoc_dev.regs = pci_iomap(pdev, REGISTER_BAR, reg_size); - - if (!vsoc_dev.regs) { - dev_err(&pdev->dev, - "cannot map registers of size %zu\n", - (size_t)reg_size); - vsoc_remove_device(pdev); - return -EBUSY; - } - - /* Map the shared memory in BAR 2 */ - vsoc_dev.shm_phys_start = pci_resource_start(pdev, SHARED_MEMORY_BAR); - vsoc_dev.shm_size = pci_resource_len(pdev, SHARED_MEMORY_BAR); - - dev_info(&pdev->dev, "shared memory @ DMA %pa size=0x%zx\n", - &vsoc_dev.shm_phys_start, vsoc_dev.shm_size); - vsoc_dev.kernel_mapped_shm = pci_iomap_wc(pdev, SHARED_MEMORY_BAR, 0); - if (!vsoc_dev.kernel_mapped_shm) { - dev_err(&vsoc_dev.dev->dev, "cannot iomap region\n"); - vsoc_remove_device(pdev); - return -EBUSY; - } - - vsoc_dev.layout = (struct vsoc_shm_layout_descriptor __force *) - vsoc_dev.kernel_mapped_shm; - dev_info(&pdev->dev, "major_version: %d\n", - vsoc_dev.layout->major_version); - dev_info(&pdev->dev, "minor_version: %d\n", - vsoc_dev.layout->minor_version); - dev_info(&pdev->dev, "size: 0x%x\n", vsoc_dev.layout->size); - dev_info(&pdev->dev, "regions: %d\n", vsoc_dev.layout->region_count); - if (vsoc_dev.layout->major_version != - CURRENT_VSOC_LAYOUT_MAJOR_VERSION) { - dev_err(&vsoc_dev.dev->dev, - "driver supports only major_version %d\n", - CURRENT_VSOC_LAYOUT_MAJOR_VERSION); - vsoc_remove_device(pdev); - return -EBUSY; - } - result = alloc_chrdev_region(&devt, 0, vsoc_dev.layout->region_count, - VSOC_DEV_NAME); - if (result) { - dev_err(&vsoc_dev.dev->dev, "alloc_chrdev_region failed\n"); - vsoc_remove_device(pdev); - return -EBUSY; - } - vsoc_dev.major = MAJOR(devt); - cdev_init(&vsoc_dev.cdev, &vsoc_ops); - vsoc_dev.cdev.owner = THIS_MODULE; - result = cdev_add(&vsoc_dev.cdev, devt, vsoc_dev.layout->region_count); - if (result) { - dev_err(&vsoc_dev.dev->dev, "cdev_add error\n"); - vsoc_remove_device(pdev); - return -EBUSY; - } - vsoc_dev.cdev_added = true; - vsoc_dev.class = class_create(THIS_MODULE, VSOC_DEV_NAME); - if (IS_ERR(vsoc_dev.class)) { - dev_err(&vsoc_dev.dev->dev, "class_create failed\n"); - vsoc_remove_device(pdev); - return PTR_ERR(vsoc_dev.class); - } - vsoc_dev.class_added = true; - vsoc_dev.regions = (struct vsoc_device_region __force *) - ((void *)vsoc_dev.layout + - vsoc_dev.layout->vsoc_region_desc_offset); - vsoc_dev.msix_entries = - kcalloc(vsoc_dev.layout->region_count, - sizeof(vsoc_dev.msix_entries[0]), GFP_KERNEL); - if (!vsoc_dev.msix_entries) { - dev_err(&vsoc_dev.dev->dev, - "unable to allocate msix_entries\n"); - vsoc_remove_device(pdev); - return -ENOSPC; - } - vsoc_dev.regions_data = - kcalloc(vsoc_dev.layout->region_count, - sizeof(vsoc_dev.regions_data[0]), GFP_KERNEL); - if (!vsoc_dev.regions_data) { - dev_err(&vsoc_dev.dev->dev, - "unable to allocate regions' data\n"); - vsoc_remove_device(pdev); - return -ENOSPC; - } - for (i = 0; i < vsoc_dev.layout->region_count; ++i) - vsoc_dev.msix_entries[i].entry = i; - - result = pci_enable_msix_exact(vsoc_dev.dev, vsoc_dev.msix_entries, - vsoc_dev.layout->region_count); - if (result) { - dev_info(&pdev->dev, "pci_enable_msix failed: %d\n", result); - vsoc_remove_device(pdev); - return -ENOSPC; - } - /* Check that all regions are well formed */ - for (i = 0; i < vsoc_dev.layout->region_count; ++i) { - const struct vsoc_device_region *region = vsoc_dev.regions + i; - - if (!PAGE_ALIGNED(region->region_begin_offset) || - !PAGE_ALIGNED(region->region_end_offset)) { - dev_err(&vsoc_dev.dev->dev, - "region %d not aligned (%x:%x)", i, - region->region_begin_offset, - region->region_end_offset); - vsoc_remove_device(pdev); - return -EFAULT; - } - if (region->region_begin_offset >= region->region_end_offset || - region->region_end_offset > vsoc_dev.shm_size) { - dev_err(&vsoc_dev.dev->dev, - "region %d offsets are wrong: %x %x %zx", - i, region->region_begin_offset, - region->region_end_offset, vsoc_dev.shm_size); - vsoc_remove_device(pdev); - return -EFAULT; - } - if (region->managed_by >= vsoc_dev.layout->region_count) { - dev_err(&vsoc_dev.dev->dev, - "region %d has invalid owner: %u", - i, region->managed_by); - vsoc_remove_device(pdev); - return -EFAULT; - } - } - vsoc_dev.msix_enabled = true; - for (i = 0; i < vsoc_dev.layout->region_count; ++i) { - const struct vsoc_device_region *region = vsoc_dev.regions + i; - size_t name_sz = sizeof(vsoc_dev.regions_data[i].name) - 1; - const struct vsoc_signal_table_layout *h_to_g_signal_table = - ®ion->host_to_guest_signal_table; - const struct vsoc_signal_table_layout *g_to_h_signal_table = - ®ion->guest_to_host_signal_table; - - vsoc_dev.regions_data[i].name[name_sz] = '\0'; - memcpy(vsoc_dev.regions_data[i].name, region->device_name, - name_sz); - dev_info(&pdev->dev, "region %d name=%s\n", - i, vsoc_dev.regions_data[i].name); - init_waitqueue_head - (&vsoc_dev.regions_data[i].interrupt_wait_queue); - init_waitqueue_head(&vsoc_dev.regions_data[i].futex_wait_queue); - vsoc_dev.regions_data[i].incoming_signalled = - shm_off_to_virtual_addr(region->region_begin_offset) + - h_to_g_signal_table->interrupt_signalled_offset; - vsoc_dev.regions_data[i].outgoing_signalled = - shm_off_to_virtual_addr(region->region_begin_offset) + - g_to_h_signal_table->interrupt_signalled_offset; - result = request_irq(vsoc_dev.msix_entries[i].vector, - vsoc_interrupt, 0, - vsoc_dev.regions_data[i].name, - vsoc_dev.regions_data + i); - if (result) { - dev_info(&pdev->dev, - "request_irq failed irq=%d vector=%d\n", - i, vsoc_dev.msix_entries[i].vector); - vsoc_remove_device(pdev); - return -ENOSPC; - } - vsoc_dev.regions_data[i].irq_requested = true; - if (!device_create(vsoc_dev.class, NULL, - MKDEV(vsoc_dev.major, i), - NULL, vsoc_dev.regions_data[i].name)) { - dev_err(&vsoc_dev.dev->dev, "device_create failed\n"); - vsoc_remove_device(pdev); - return -EBUSY; - } - vsoc_dev.regions_data[i].device_created = true; - } - return 0; -} - -/* - * This should undo all of the allocations in the probe function in reverse - * order. - * - * Notes: - * - * The device may have been partially initialized, so double check - * that the allocations happened. - * - * This function may be called multiple times, so mark resources as freed - * as they are deallocated. - */ -static void vsoc_remove_device(struct pci_dev *pdev) -{ - int i; - /* - * pdev is the first thing to be set on probe and the last thing - * to be cleared here. If it's NULL then there is no cleanup. - */ - if (!pdev || !vsoc_dev.dev) - return; - dev_info(&pdev->dev, "remove_device\n"); - if (vsoc_dev.regions_data) { - for (i = 0; i < vsoc_dev.layout->region_count; ++i) { - if (vsoc_dev.regions_data[i].device_created) { - device_destroy(vsoc_dev.class, - MKDEV(vsoc_dev.major, i)); - vsoc_dev.regions_data[i].device_created = false; - } - if (vsoc_dev.regions_data[i].irq_requested) - free_irq(vsoc_dev.msix_entries[i].vector, NULL); - vsoc_dev.regions_data[i].irq_requested = false; - } - kfree(vsoc_dev.regions_data); - vsoc_dev.regions_data = NULL; - } - if (vsoc_dev.msix_enabled) { - pci_disable_msix(pdev); - vsoc_dev.msix_enabled = false; - } - kfree(vsoc_dev.msix_entries); - vsoc_dev.msix_entries = NULL; - vsoc_dev.regions = NULL; - if (vsoc_dev.class_added) { - class_destroy(vsoc_dev.class); - vsoc_dev.class_added = false; - } - if (vsoc_dev.cdev_added) { - cdev_del(&vsoc_dev.cdev); - vsoc_dev.cdev_added = false; - } - if (vsoc_dev.major && vsoc_dev.layout) { - unregister_chrdev_region(MKDEV(vsoc_dev.major, 0), - vsoc_dev.layout->region_count); - vsoc_dev.major = 0; - } - vsoc_dev.layout = NULL; - if (vsoc_dev.kernel_mapped_shm) { - pci_iounmap(pdev, vsoc_dev.kernel_mapped_shm); - vsoc_dev.kernel_mapped_shm = NULL; - } - if (vsoc_dev.regs) { - pci_iounmap(pdev, vsoc_dev.regs); - vsoc_dev.regs = NULL; - } - if (vsoc_dev.requested_regions) { - pci_release_regions(pdev); - vsoc_dev.requested_regions = false; - } - if (vsoc_dev.enabled_device) { - pci_disable_device(pdev); - vsoc_dev.enabled_device = false; - } - /* Do this last: it indicates that the device is not initialized. */ - vsoc_dev.dev = NULL; -} - -static void __exit vsoc_cleanup_module(void) -{ - vsoc_remove_device(vsoc_dev.dev); - pci_unregister_driver(&vsoc_pci_driver); -} - -static int __init vsoc_init_module(void) -{ - int err = -ENOMEM; - - INIT_LIST_HEAD(&vsoc_dev.permissions); - mutex_init(&vsoc_dev.mtx); - - err = pci_register_driver(&vsoc_pci_driver); - if (err < 0) - return err; - return 0; -} - -static int vsoc_open(struct inode *inode, struct file *filp) -{ - /* Can't use vsoc_validate_filep because filp is still incomplete */ - int ret = vsoc_validate_inode(inode); - - if (ret) - return ret; - filp->private_data = - kzalloc(sizeof(struct vsoc_private_data), GFP_KERNEL); - if (!filp->private_data) - return -ENOMEM; - return 0; -} - -static int vsoc_release(struct inode *inode, struct file *filp) -{ - struct vsoc_private_data *private_data = NULL; - struct fd_scoped_permission_node *node = NULL; - struct vsoc_device_region *owner_region_p = NULL; - int retval = vsoc_validate_filep(filp); - - if (retval) - return retval; - private_data = (struct vsoc_private_data *)filp->private_data; - if (!private_data) - return 0; - - node = private_data->fd_scoped_permission_node; - if (node) { - owner_region_p = vsoc_region_from_inode(inode); - if (owner_region_p->managed_by != VSOC_REGION_WHOLE) { - owner_region_p = - &vsoc_dev.regions[owner_region_p->managed_by]; - } - do_destroy_fd_scoped_permission_node(owner_region_p, node); - private_data->fd_scoped_permission_node = NULL; - } - kfree(private_data); - filp->private_data = NULL; - - return 0; -} - -/* - * Returns the device relative offset and length of the area specified by the - * fd scoped permission. If there is no fd scoped permission set, a default - * permission covering the entire region is assumed, unless the region is owned - * by another one, in which case the default is a permission with zero size. - */ -static ssize_t vsoc_get_area(struct file *filp, __u32 *area_offset) -{ - __u32 off = 0; - ssize_t length = 0; - struct vsoc_device_region *region_p; - struct fd_scoped_permission *perm; - - region_p = vsoc_region_from_filep(filp); - off = region_p->region_begin_offset; - perm = &((struct vsoc_private_data *)filp->private_data)-> - fd_scoped_permission_node->permission; - if (perm) { - off += perm->begin_offset; - length = perm->end_offset - perm->begin_offset; - } else if (region_p->managed_by == VSOC_REGION_WHOLE) { - /* No permission set and the regions is not owned by another, - * default to full region access. - */ - length = vsoc_device_region_size(region_p); - } else { - /* return zero length, access is denied. */ - length = 0; - } - if (area_offset) - *area_offset = off; - return length; -} - -static int vsoc_mmap(struct file *filp, struct vm_area_struct *vma) -{ - unsigned long len = vma->vm_end - vma->vm_start; - __u32 area_off; - phys_addr_t mem_off; - ssize_t area_len; - int retval = vsoc_validate_filep(filp); - - if (retval) - return retval; - area_len = vsoc_get_area(filp, &area_off); - /* Add the requested offset */ - area_off += (vma->vm_pgoff << PAGE_SHIFT); - area_len -= (vma->vm_pgoff << PAGE_SHIFT); - if (area_len < len) - return -EINVAL; - vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); - mem_off = shm_off_to_phys_addr(area_off); - if (io_remap_pfn_range(vma, vma->vm_start, mem_off >> PAGE_SHIFT, - len, vma->vm_page_prot)) - return -EAGAIN; - return 0; -} - -module_init(vsoc_init_module); -module_exit(vsoc_cleanup_module); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Greg Hartman "); -MODULE_DESCRIPTION("VSoC interpretation of QEmu's ivshmem device"); -MODULE_VERSION("1.0"); diff --git a/drivers/staging/greybus/audio_manager.c b/drivers/staging/greybus/audio_manager.c index 9b19ea9d3fa144f9c81a8f3dc558cdad2d8b2a87..9a3f7c034ab49e7f141408f35f225798dc395f7c 100644 --- a/drivers/staging/greybus/audio_manager.c +++ b/drivers/staging/greybus/audio_manager.c @@ -92,8 +92,8 @@ void gb_audio_manager_remove_all(void) list_for_each_entry_safe(module, next, &modules_list, list) { list_del(&module->list); - kobject_put(&module->kobj); ida_simple_remove(&module_id, module->id); + kobject_put(&module->kobj); } is_empty = list_empty(&modules_list); diff --git a/drivers/staging/greybus/tools/loopback_test.c b/drivers/staging/greybus/tools/loopback_test.c index ba6f905f26fadc56a804a5099027364a37610e86..69c6dce9be314d0553dbb229ff0cac0ee103c762 100644 --- a/drivers/staging/greybus/tools/loopback_test.c +++ b/drivers/staging/greybus/tools/loopback_test.c @@ -19,6 +19,7 @@ #include #define MAX_NUM_DEVICES 10 +#define MAX_SYSFS_PREFIX 0x80 #define MAX_SYSFS_PATH 0x200 #define CSV_MAX_LINE 0x1000 #define SYSFS_MAX_INT 0x20 @@ -67,7 +68,7 @@ struct loopback_results { }; struct loopback_device { - char name[MAX_SYSFS_PATH]; + char name[MAX_STR_LEN]; char sysfs_entry[MAX_SYSFS_PATH]; char debugfs_entry[MAX_SYSFS_PATH]; struct loopback_results results; @@ -93,8 +94,8 @@ struct loopback_test { int stop_all; int poll_count; char test_name[MAX_STR_LEN]; - char sysfs_prefix[MAX_SYSFS_PATH]; - char debugfs_prefix[MAX_SYSFS_PATH]; + char sysfs_prefix[MAX_SYSFS_PREFIX]; + char debugfs_prefix[MAX_SYSFS_PREFIX]; struct timespec poll_timeout; struct loopback_device devices[MAX_NUM_DEVICES]; struct loopback_results aggregate_results; @@ -637,7 +638,7 @@ int find_loopback_devices(struct loopback_test *t) static int open_poll_files(struct loopback_test *t) { struct loopback_device *dev; - char buf[MAX_STR_LEN]; + char buf[MAX_SYSFS_PATH + MAX_STR_LEN]; char dummy; int fds_idx = 0; int i; @@ -655,7 +656,7 @@ static int open_poll_files(struct loopback_test *t) goto err; } read(t->fds[fds_idx].fd, &dummy, 1); - t->fds[fds_idx].events = EPOLLERR|EPOLLPRI; + t->fds[fds_idx].events = POLLERR | POLLPRI; t->fds[fds_idx].revents = 0; fds_idx++; } @@ -748,7 +749,7 @@ static int wait_for_complete(struct loopback_test *t) } for (i = 0; i < t->poll_count; i++) { - if (t->fds[i].revents & EPOLLPRI) { + if (t->fds[i].revents & POLLPRI) { /* Dummy read to clear the event */ read(t->fds[i].fd, &dummy, 1); number_of_events++; @@ -907,10 +908,10 @@ int main(int argc, char *argv[]) t.iteration_max = atoi(optarg); break; case 'S': - snprintf(t.sysfs_prefix, MAX_SYSFS_PATH, "%s", optarg); + snprintf(t.sysfs_prefix, MAX_SYSFS_PREFIX, "%s", optarg); break; case 'D': - snprintf(t.debugfs_prefix, MAX_SYSFS_PATH, "%s", optarg); + snprintf(t.debugfs_prefix, MAX_SYSFS_PREFIX, "%s", optarg); break; case 'm': t.mask = atol(optarg); @@ -961,10 +962,10 @@ int main(int argc, char *argv[]) } if (!strcmp(t.sysfs_prefix, "")) - snprintf(t.sysfs_prefix, MAX_SYSFS_PATH, "%s", sysfs_prefix); + snprintf(t.sysfs_prefix, MAX_SYSFS_PREFIX, "%s", sysfs_prefix); if (!strcmp(t.debugfs_prefix, "")) - snprintf(t.debugfs_prefix, MAX_SYSFS_PATH, "%s", debugfs_prefix); + snprintf(t.debugfs_prefix, MAX_SYSFS_PREFIX, "%s", debugfs_prefix); ret = find_loopback_devices(&t); if (ret) diff --git a/drivers/staging/media/hantro/hantro_drv.c b/drivers/staging/media/hantro/hantro_drv.c index 97c615a2f057fc2c69b54e1c3c1168abcdaf52b4..c988353261352ef22126a22bf8cae0f2bed335c9 100644 --- a/drivers/staging/media/hantro/hantro_drv.c +++ b/drivers/staging/media/hantro/hantro_drv.c @@ -558,13 +558,13 @@ static int hantro_attach_func(struct hantro_dev *vpu, goto err_rel_entity1; /* Connect the three entities */ - ret = media_create_pad_link(&func->vdev.entity, 0, &func->proc, 1, + ret = media_create_pad_link(&func->vdev.entity, 0, &func->proc, 0, MEDIA_LNK_FL_IMMUTABLE | MEDIA_LNK_FL_ENABLED); if (ret) goto err_rel_entity2; - ret = media_create_pad_link(&func->proc, 0, &func->sink, 0, + ret = media_create_pad_link(&func->proc, 1, &func->sink, 0, MEDIA_LNK_FL_IMMUTABLE | MEDIA_LNK_FL_ENABLED); if (ret) diff --git a/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c b/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c index 9b6ea86d1dcfa6d0c16b23b1fb870292f9e68ee9..ba53959e1303b8f39778f1245c97ce0d5c0563bc 100644 --- a/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c +++ b/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c @@ -2009,21 +2009,16 @@ static int wpa_supplicant_ioctl(struct net_device *dev, struct iw_point *p) struct ieee_param *param; uint ret = 0; - if (p->length < sizeof(struct ieee_param) || !p->pointer) { - ret = -EINVAL; - goto out; - } + if (!p->pointer || p->length != sizeof(struct ieee_param)) + return -EINVAL; param = (struct ieee_param *)rtw_malloc(p->length); - if (!param) { - ret = -ENOMEM; - goto out; - } + if (!param) + return -ENOMEM; if (copy_from_user(param, p->pointer, p->length)) { kfree(param); - ret = -EFAULT; - goto out; + return -EFAULT; } switch (param->cmd) { @@ -2054,9 +2049,6 @@ static int wpa_supplicant_ioctl(struct net_device *dev, struct iw_point *p) ret = -EFAULT; kfree(param); - -out: - return ret; } @@ -2791,26 +2783,19 @@ static int rtw_hostapd_ioctl(struct net_device *dev, struct iw_point *p) * so, we just check hw_init_completed */ - if (!padapter->hw_init_completed) { - ret = -EPERM; - goto out; - } + if (!padapter->hw_init_completed) + return -EPERM; - if (!p->pointer) { - ret = -EINVAL; - goto out; - } + if (!p->pointer || p->length != sizeof(struct ieee_param)) + return -EINVAL; param = (struct ieee_param *)rtw_malloc(p->length); - if (!param) { - ret = -ENOMEM; - goto out; - } + if (!param) + return -ENOMEM; if (copy_from_user(param, p->pointer, p->length)) { kfree(param); - ret = -EFAULT; - goto out; + return -EFAULT; } switch (param->cmd) { @@ -2865,7 +2850,6 @@ static int rtw_hostapd_ioctl(struct net_device *dev, struct iw_point *p) if (ret == 0 && copy_to_user(p->pointer, param, p->length)) ret = -EFAULT; kfree(param); -out: return ret; } #endif diff --git a/drivers/staging/rtl8188eu/os_dep/usb_intf.c b/drivers/staging/rtl8188eu/os_dep/usb_intf.c index b5d42f411dd810bd2670c6a34c9217609bbdbbd3..845c8817281c6b2527902b46b86e1c94657065f6 100644 --- a/drivers/staging/rtl8188eu/os_dep/usb_intf.c +++ b/drivers/staging/rtl8188eu/os_dep/usb_intf.c @@ -38,6 +38,7 @@ static const struct usb_device_id rtw_usb_id_tbl[] = { {USB_DEVICE(0x2001, 0x331B)}, /* D-Link DWA-121 rev B1 */ {USB_DEVICE(0x2357, 0x010c)}, /* TP-Link TL-WN722N v2 */ {USB_DEVICE(0x2357, 0x0111)}, /* TP-Link TL-WN727N v5.21 */ + {USB_DEVICE(0x2C4E, 0x0102)}, /* MERCUSYS MW150US v2 */ {USB_DEVICE(0x0df6, 0x0076)}, /* Sitecom N150 v2 */ {USB_DEVICE(USB_VENDER_ID_REALTEK, 0xffef)}, /* Rosewill RNX-N150NUB */ {} /* Terminating entry */ diff --git a/drivers/staging/rtl8723bs/hal/rtl8723bs_xmit.c b/drivers/staging/rtl8723bs/hal/rtl8723bs_xmit.c index b44e902ed338cef7cd523bdde3b89e7341aec980..b6d56cfb0a190af048c0da4ef2501b02c048e241 100644 --- a/drivers/staging/rtl8723bs/hal/rtl8723bs_xmit.c +++ b/drivers/staging/rtl8723bs/hal/rtl8723bs_xmit.c @@ -476,14 +476,13 @@ int rtl8723bs_xmit_thread(void *context) s32 ret; struct adapter *padapter; struct xmit_priv *pxmitpriv; - u8 thread_name[20] = "RTWHALXT"; - + u8 thread_name[20]; ret = _SUCCESS; padapter = context; pxmitpriv = &padapter->xmitpriv; - rtw_sprintf(thread_name, 20, "%s-"ADPT_FMT, thread_name, ADPT_ARG(padapter)); + rtw_sprintf(thread_name, 20, "RTWHALXT-" ADPT_FMT, ADPT_ARG(padapter)); thread_enter(thread_name); DBG_871X("start "FUNC_ADPT_FMT"\n", FUNC_ADPT_ARG(padapter)); diff --git a/drivers/staging/rtl8723bs/os_dep/ioctl_linux.c b/drivers/staging/rtl8723bs/os_dep/ioctl_linux.c index db6528a01229d6789152e17cd1c22af672d38eb7..9b9038e7deb1090c7bee57a4c299abaa71dcf517 100644 --- a/drivers/staging/rtl8723bs/os_dep/ioctl_linux.c +++ b/drivers/staging/rtl8723bs/os_dep/ioctl_linux.c @@ -3373,21 +3373,16 @@ static int wpa_supplicant_ioctl(struct net_device *dev, struct iw_point *p) /* down(&ieee->wx_sem); */ - if (p->length < sizeof(struct ieee_param) || !p->pointer) { - ret = -EINVAL; - goto out; - } + if (!p->pointer || p->length != sizeof(struct ieee_param)) + return -EINVAL; param = rtw_malloc(p->length); - if (param == NULL) { - ret = -ENOMEM; - goto out; - } + if (param == NULL) + return -ENOMEM; if (copy_from_user(param, p->pointer, p->length)) { kfree(param); - ret = -EFAULT; - goto out; + return -EFAULT; } switch (param->cmd) { @@ -3421,12 +3416,8 @@ static int wpa_supplicant_ioctl(struct net_device *dev, struct iw_point *p) kfree(param); -out: - /* up(&ieee->wx_sem); */ - return ret; - } static int rtw_set_encryption(struct net_device *dev, struct ieee_param *param, u32 param_len) @@ -4200,28 +4191,19 @@ static int rtw_hostapd_ioctl(struct net_device *dev, struct iw_point *p) * so, we just check hw_init_completed */ - if (!padapter->hw_init_completed) { - ret = -EPERM; - goto out; - } - + if (!padapter->hw_init_completed) + return -EPERM; - /* if (p->length < sizeof(struct ieee_param) || !p->pointer) { */ - if (!p->pointer) { - ret = -EINVAL; - goto out; - } + if (!p->pointer || p->length != sizeof(*param)) + return -EINVAL; param = rtw_malloc(p->length); - if (param == NULL) { - ret = -ENOMEM; - goto out; - } + if (param == NULL) + return -ENOMEM; if (copy_from_user(param, p->pointer, p->length)) { kfree(param); - ret = -EFAULT; - goto out; + return -EFAULT; } /* DBG_871X("%s, cmd =%d\n", __func__, param->cmd); */ @@ -4321,13 +4303,8 @@ static int rtw_hostapd_ioctl(struct net_device *dev, struct iw_point *p) if (ret == 0 && copy_to_user(p->pointer, param, p->length)) ret = -EFAULT; - kfree(param); - -out: - return ret; - } static int rtw_wx_set_priv(struct net_device *dev, diff --git a/drivers/staging/speakup/main.c b/drivers/staging/speakup/main.c index 488f2539aa9a835125afe264ab5b23d7ce4137f5..81ecfd1a200dda4818518752c26964479bf99904 100644 --- a/drivers/staging/speakup/main.c +++ b/drivers/staging/speakup/main.c @@ -561,7 +561,7 @@ static u_long get_word(struct vc_data *vc) return 0; } else if (tmpx < vc->vc_cols - 2 && (ch == SPACE || ch == 0 || (ch < 0x100 && IS_WDLM(ch))) && - get_char(vc, (u_short *)&tmp_pos + 1, &temp) > SPACE) { + get_char(vc, (u_short *)tmp_pos + 1, &temp) > SPACE) { tmp_pos += 2; tmpx++; } else { diff --git a/drivers/staging/speakup/selection.c b/drivers/staging/speakup/selection.c index a8b4d0c5ab7e0e312d0463e8c26ce295bb551fc9..032f3264fba12bd925f7cad46f379b6de8b90a22 100644 --- a/drivers/staging/speakup/selection.c +++ b/drivers/staging/speakup/selection.c @@ -51,9 +51,7 @@ static void __speakup_set_selection(struct work_struct *work) goto unref; } - console_lock(); set_selection_kernel(&sel, tty); - console_unlock(); unref: tty_kref_put(tty); diff --git a/drivers/staging/vt6656/dpc.c b/drivers/staging/vt6656/dpc.c index 821aae8ca402fa3cac7ed2bca2f93fc3cdd62961..a0b60e7d1086731c6647777f493d9dc43fb6bfb1 100644 --- a/drivers/staging/vt6656/dpc.c +++ b/drivers/staging/vt6656/dpc.c @@ -98,7 +98,7 @@ int vnt_rx_data(struct vnt_private *priv, struct vnt_rcb *ptr_rcb, vnt_rf_rssi_to_dbm(priv, tail->rssi, &rx_dbm); - priv->bb_pre_ed_rssi = (u8)rx_dbm + 1; + priv->bb_pre_ed_rssi = (u8)-rx_dbm + 1; priv->current_rssi = priv->bb_pre_ed_rssi; skb_pull(skb, sizeof(*head)); diff --git a/drivers/staging/wfx/Documentation/devicetree/bindings/net/wireless/siliabs,wfx.txt b/drivers/staging/wfx/Documentation/devicetree/bindings/net/wireless/siliabs,wfx.txt index 26de6762b94241959effee09ca1b5ed233f52da8..081d58abd5accd3552f042567c0633092e021f3b 100644 --- a/drivers/staging/wfx/Documentation/devicetree/bindings/net/wireless/siliabs,wfx.txt +++ b/drivers/staging/wfx/Documentation/devicetree/bindings/net/wireless/siliabs,wfx.txt @@ -93,5 +93,5 @@ Some properties are recognized either by SPI and SDIO versions: Must contains 64 hexadecimal digits. Not supported in current version. WFx driver also supports `mac-address` and `local-mac-address` as described in -Documentation/devicetree/binding/net/ethernet.txt +Documentation/devicetree/bindings/net/ethernet.txt diff --git a/drivers/staging/wfx/hif_tx.c b/drivers/staging/wfx/hif_tx.c index 2428363371fa1e087ce22fc94a519ef25a8332ec..77bca43aca4280692fc4f499c0e4d835b07f9cc1 100644 --- a/drivers/staging/wfx/hif_tx.c +++ b/drivers/staging/wfx/hif_tx.c @@ -140,6 +140,7 @@ int hif_shutdown(struct wfx_dev *wdev) else control_reg_write(wdev, 0); mutex_unlock(&wdev->hif_cmd.lock); + mutex_unlock(&wdev->hif_cmd.key_renew_lock); kfree(hif); return ret; } @@ -289,7 +290,7 @@ int hif_stop_scan(struct wfx_vif *wvif) } int hif_join(struct wfx_vif *wvif, const struct ieee80211_bss_conf *conf, - const struct ieee80211_channel *channel, const u8 *ssidie) + struct ieee80211_channel *channel, const u8 *ssid, int ssidlen) { int ret; struct hif_msg *hif; @@ -307,9 +308,9 @@ int hif_join(struct wfx_vif *wvif, const struct ieee80211_bss_conf *conf, body->basic_rate_set = cpu_to_le32(wfx_rate_mask_to_hw(wvif->wdev, conf->basic_rates)); memcpy(body->bssid, conf->bssid, sizeof(body->bssid)); - if (!conf->ibss_joined && ssidie) { - body->ssid_length = cpu_to_le32(ssidie[1]); - memcpy(body->ssid, &ssidie[2], ssidie[1]); + if (!conf->ibss_joined && ssid) { + body->ssid_length = cpu_to_le32(ssidlen); + memcpy(body->ssid, ssid, ssidlen); } wfx_fill_header(hif, wvif->id, HIF_REQ_ID_JOIN, sizeof(*body)); ret = wfx_cmd_send(wvif->wdev, hif, NULL, 0, false); @@ -427,9 +428,9 @@ int hif_start(struct wfx_vif *wvif, const struct ieee80211_bss_conf *conf, struct hif_msg *hif; struct hif_req_start *body = wfx_alloc_hif(sizeof(*body), &hif); - body->dtim_period = conf->dtim_period, - body->short_preamble = conf->use_short_preamble, - body->channel_number = cpu_to_le16(channel->hw_value), + body->dtim_period = conf->dtim_period; + body->short_preamble = conf->use_short_preamble; + body->channel_number = cpu_to_le16(channel->hw_value); body->beacon_interval = cpu_to_le32(conf->beacon_int); body->basic_rate_set = cpu_to_le32(wfx_rate_mask_to_hw(wvif->wdev, conf->basic_rates)); diff --git a/drivers/staging/wfx/hif_tx.h b/drivers/staging/wfx/hif_tx.h index 20977e461718bc7aef5c4fa96702055e20ad9d90..f8520a14c14cdeae03dbb9334567df7ad40700ac 100644 --- a/drivers/staging/wfx/hif_tx.h +++ b/drivers/staging/wfx/hif_tx.h @@ -46,7 +46,7 @@ int hif_scan(struct wfx_vif *wvif, struct cfg80211_scan_request *req80211, int chan_start, int chan_num); int hif_stop_scan(struct wfx_vif *wvif); int hif_join(struct wfx_vif *wvif, const struct ieee80211_bss_conf *conf, - const struct ieee80211_channel *channel, const u8 *ssidie); + struct ieee80211_channel *channel, const u8 *ssid, int ssidlen); int hif_set_pm(struct wfx_vif *wvif, bool ps, int dynamic_ps_timeout); int hif_set_bss_params(struct wfx_vif *wvif, const struct hif_req_set_bss_params *arg); diff --git a/drivers/staging/wfx/hif_tx_mib.h b/drivers/staging/wfx/hif_tx_mib.h index bf3769c2a9b63487818673b01ee020526d1cb971..26b1406f9f6c462ce552bbdc25e44a920dd5d3a7 100644 --- a/drivers/staging/wfx/hif_tx_mib.h +++ b/drivers/staging/wfx/hif_tx_mib.h @@ -191,10 +191,10 @@ static inline int hif_set_block_ack_policy(struct wfx_vif *wvif, } static inline int hif_set_association_mode(struct wfx_vif *wvif, - struct ieee80211_bss_conf *info, - struct ieee80211_sta_ht_cap *ht_cap) + struct ieee80211_bss_conf *info) { int basic_rates = wfx_rate_mask_to_hw(wvif->wdev, info->basic_rates); + struct ieee80211_sta *sta = NULL; struct hif_mib_set_association_mode val = { .preambtype_use = 1, .mode = 1, @@ -204,12 +204,17 @@ static inline int hif_set_association_mode(struct wfx_vif *wvif, .basic_rate_set = cpu_to_le32(basic_rates) }; + rcu_read_lock(); // protect sta + if (info->bssid && !info->ibss_joined) + sta = ieee80211_find_sta(wvif->vif, info->bssid); + // FIXME: it is strange to not retrieve all information from bss_info - if (ht_cap && ht_cap->ht_supported) { - val.mpdu_start_spacing = ht_cap->ampdu_density; + if (sta && sta->ht_cap.ht_supported) { + val.mpdu_start_spacing = sta->ht_cap.ampdu_density; if (!(info->ht_operation_mode & IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT)) - val.greenfield = !!(ht_cap->cap & IEEE80211_HT_CAP_GRN_FLD); + val.greenfield = !!(sta->ht_cap.cap & IEEE80211_HT_CAP_GRN_FLD); } + rcu_read_unlock(); return hif_write_mib(wvif->wdev, wvif->id, HIF_MIB_ID_SET_ASSOCIATION_MODE, &val, sizeof(val)); diff --git a/drivers/staging/wfx/sta.c b/drivers/staging/wfx/sta.c index 03d0f224ffdbe9d7ae9b465a0b1c4d3e88115f8f..af4f4bbd057257fa4eba60cc42c65d91fcb4bd06 100644 --- a/drivers/staging/wfx/sta.c +++ b/drivers/staging/wfx/sta.c @@ -491,9 +491,11 @@ static void wfx_set_mfp(struct wfx_vif *wvif, static void wfx_do_join(struct wfx_vif *wvif) { int ret; - const u8 *ssidie; struct ieee80211_bss_conf *conf = &wvif->vif->bss_conf; struct cfg80211_bss *bss = NULL; + u8 ssid[IEEE80211_MAX_SSID_LEN]; + const u8 *ssidie = NULL; + int ssidlen = 0; wfx_tx_lock_flush(wvif->wdev); @@ -514,11 +516,14 @@ static void wfx_do_join(struct wfx_vif *wvif) if (!wvif->beacon_int) wvif->beacon_int = 1; - rcu_read_lock(); + rcu_read_lock(); // protect ssidie if (!conf->ibss_joined) ssidie = ieee80211_bss_get_ie(bss, WLAN_EID_SSID); - else - ssidie = NULL; + if (ssidie) { + ssidlen = ssidie[1]; + memcpy(ssid, &ssidie[2], ssidie[1]); + } + rcu_read_unlock(); wfx_tx_flush(wvif->wdev); @@ -527,10 +532,8 @@ static void wfx_do_join(struct wfx_vif *wvif) wfx_set_mfp(wvif, bss); - /* Perform actual join */ wvif->wdev->tx_burst_idx = -1; - ret = hif_join(wvif, conf, wvif->channel, ssidie); - rcu_read_unlock(); + ret = hif_join(wvif, conf, wvif->channel, ssid, ssidlen); if (ret) { ieee80211_connection_loss(wvif->vif); wvif->join_complete_status = -1; @@ -605,7 +608,9 @@ int wfx_sta_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif, int i; for (i = 0; i < ARRAY_SIZE(sta_priv->buffered); i++) - WARN(sta_priv->buffered[i], "release station while Tx is in progress"); + if (sta_priv->buffered[i]) + dev_warn(wvif->wdev->dev, "release station while %d pending frame on queue %d", + sta_priv->buffered[i], i); // FIXME: see note in wfx_sta_add() if (vif->type == NL80211_IFTYPE_STATION) return 0; @@ -689,6 +694,7 @@ static void wfx_join_finalize(struct wfx_vif *wvif, wfx_rate_mask_to_hw(wvif->wdev, sta->supp_rates[wvif->channel->band]); else wvif->bss_params.operational_rate_set = -1; + rcu_read_unlock(); if (sta && info->ht_operation_mode & IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT) hif_dual_cts_protection(wvif, true); @@ -701,8 +707,7 @@ static void wfx_join_finalize(struct wfx_vif *wvif, wvif->bss_params.beacon_lost_count = 20; wvif->bss_params.aid = info->aid; - hif_set_association_mode(wvif, info, sta ? &sta->ht_cap : NULL); - rcu_read_unlock(); + hif_set_association_mode(wvif, info); if (!info->ibss_joined) { hif_keep_alive_period(wvif, 30 /* sec */); diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index b94ed4e30770688891a407d1c9dba88d3110f3b8..09e55ea0bf5d5dc6af5c2010940d1aa0504bfae5 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -1165,9 +1165,7 @@ int iscsit_setup_scsi_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, hdr->cmdsn, be32_to_cpu(hdr->data_length), payload_length, conn->cid); - if (target_get_sess_cmd(&cmd->se_cmd, true) < 0) - return iscsit_add_reject_cmd(cmd, - ISCSI_REASON_WAITING_FOR_LOGOUT, buf); + target_get_sess_cmd(&cmd->se_cmd, true); cmd->sense_reason = transport_lookup_cmd_lun(&cmd->se_cmd, scsilun_to_int(&hdr->lun)); @@ -2004,9 +2002,7 @@ iscsit_handle_task_mgt_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, conn->sess->se_sess, 0, DMA_NONE, TCM_SIMPLE_TAG, cmd->sense_buffer + 2); - if (target_get_sess_cmd(&cmd->se_cmd, true) < 0) - return iscsit_add_reject_cmd(cmd, - ISCSI_REASON_WAITING_FOR_LOGOUT, buf); + target_get_sess_cmd(&cmd->se_cmd, true); /* * TASK_REASSIGN for ERL=2 / connection stays inside of @@ -4149,6 +4145,9 @@ int iscsit_close_connection( iscsit_stop_nopin_response_timer(conn); iscsit_stop_nopin_timer(conn); + if (conn->conn_transport->iscsit_wait_conn) + conn->conn_transport->iscsit_wait_conn(conn); + /* * During Connection recovery drop unacknowledged out of order * commands for this connection, and prepare the other commands @@ -4231,11 +4230,6 @@ int iscsit_close_connection( * must wait until they have completed. */ iscsit_check_conn_usage_count(conn); - target_sess_cmd_list_set_waiting(sess->se_sess); - target_wait_for_sess_cmds(sess->se_sess); - - if (conn->conn_transport->iscsit_wait_conn) - conn->conn_transport->iscsit_wait_conn(conn); ahash_request_free(conn->conn_tx_hash); if (conn->conn_rx_hash) { diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index ea482d4b1f00e8f03b36d8fc280f319ee03f7f4d..0ae9e60fc4d59b0056cdecfd1cbcc8391dd684f0 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -666,6 +666,11 @@ static int transport_cmd_check_stop_to_fabric(struct se_cmd *cmd) target_remove_from_state_list(cmd); + /* + * Clear struct se_cmd->se_lun before the handoff to FE. + */ + cmd->se_lun = NULL; + spin_lock_irqsave(&cmd->t_state_lock, flags); /* * Determine if frontend context caller is requesting the stopping of @@ -693,6 +698,17 @@ static int transport_cmd_check_stop_to_fabric(struct se_cmd *cmd) return cmd->se_tfo->check_stop_free(cmd); } +static void transport_lun_remove_cmd(struct se_cmd *cmd) +{ + struct se_lun *lun = cmd->se_lun; + + if (!lun) + return; + + if (cmpxchg(&cmd->lun_ref_active, true, false)) + percpu_ref_put(&lun->lun_ref); +} + static void target_complete_failure_work(struct work_struct *work) { struct se_cmd *cmd = container_of(work, struct se_cmd, work); @@ -783,6 +799,8 @@ static void target_handle_abort(struct se_cmd *cmd) WARN_ON_ONCE(kref_read(&cmd->cmd_kref) == 0); + transport_lun_remove_cmd(cmd); + transport_cmd_check_stop_to_fabric(cmd); } @@ -1708,6 +1726,7 @@ static void target_complete_tmr_failure(struct work_struct *work) se_cmd->se_tmr_req->response = TMR_LUN_DOES_NOT_EXIST; se_cmd->se_tfo->queue_tm_rsp(se_cmd); + transport_lun_remove_cmd(se_cmd); transport_cmd_check_stop_to_fabric(se_cmd); } @@ -1898,6 +1917,7 @@ void transport_generic_request_failure(struct se_cmd *cmd, goto queue_full; check_stop: + transport_lun_remove_cmd(cmd); transport_cmd_check_stop_to_fabric(cmd); return; @@ -2195,6 +2215,7 @@ static void transport_complete_qf(struct se_cmd *cmd) transport_handle_queue_full(cmd, cmd->se_dev, ret, false); return; } + transport_lun_remove_cmd(cmd); transport_cmd_check_stop_to_fabric(cmd); } @@ -2289,6 +2310,7 @@ static void target_complete_ok_work(struct work_struct *work) if (ret) goto queue_full; + transport_lun_remove_cmd(cmd); transport_cmd_check_stop_to_fabric(cmd); return; } @@ -2314,6 +2336,7 @@ static void target_complete_ok_work(struct work_struct *work) if (ret) goto queue_full; + transport_lun_remove_cmd(cmd); transport_cmd_check_stop_to_fabric(cmd); return; } @@ -2349,6 +2372,7 @@ static void target_complete_ok_work(struct work_struct *work) if (ret) goto queue_full; + transport_lun_remove_cmd(cmd); transport_cmd_check_stop_to_fabric(cmd); return; } @@ -2384,6 +2408,7 @@ static void target_complete_ok_work(struct work_struct *work) break; } + transport_lun_remove_cmd(cmd); transport_cmd_check_stop_to_fabric(cmd); return; @@ -2710,6 +2735,9 @@ int transport_generic_free_cmd(struct se_cmd *cmd, int wait_for_tasks) */ if (cmd->state_active) target_remove_from_state_list(cmd); + + if (cmd->se_lun) + transport_lun_remove_cmd(cmd); } if (aborted) cmd->free_compl = &compl; @@ -2781,9 +2809,6 @@ static void target_release_cmd_kref(struct kref *kref) struct completion *abrt_compl = se_cmd->abrt_compl; unsigned long flags; - if (se_cmd->lun_ref_active) - percpu_ref_put(&se_cmd->se_lun->lun_ref); - if (se_sess) { spin_lock_irqsave(&se_sess->sess_cmd_lock, flags); list_del_init(&se_cmd->se_cmd_list); diff --git a/drivers/tee/amdtee/Kconfig b/drivers/tee/amdtee/Kconfig index 4e32b6413b41ffefdef8d4abaf93d3a7f5a93097..191f9715fa9afcb3ee98fb2ee509e64a9a448b94 100644 --- a/drivers/tee/amdtee/Kconfig +++ b/drivers/tee/amdtee/Kconfig @@ -3,6 +3,6 @@ config AMDTEE tristate "AMD-TEE" default m - depends on CRYPTO_DEV_SP_PSP + depends on CRYPTO_DEV_SP_PSP && CRYPTO_DEV_CCP_DD help This implements AMD's Trusted Execution Environment (TEE) driver. diff --git a/drivers/tee/amdtee/core.c b/drivers/tee/amdtee/core.c index 6370bb55f51230fda81a60661d2f6a2530df0f18..0026eb6f13cee46a2898f3a44b08c8b5a4c3ee0b 100644 --- a/drivers/tee/amdtee/core.c +++ b/drivers/tee/amdtee/core.c @@ -212,6 +212,19 @@ static int copy_ta_binary(struct tee_context *ctx, void *ptr, void **ta, return rc; } +static void destroy_session(struct kref *ref) +{ + struct amdtee_session *sess = container_of(ref, struct amdtee_session, + refcount); + + /* Unload the TA from TEE */ + handle_unload_ta(sess->ta_handle); + mutex_lock(&session_list_mutex); + list_del(&sess->list_node); + mutex_unlock(&session_list_mutex); + kfree(sess); +} + int amdtee_open_session(struct tee_context *ctx, struct tee_ioctl_open_session_arg *arg, struct tee_param *param) @@ -236,15 +249,13 @@ int amdtee_open_session(struct tee_context *ctx, /* Load the TA binary into TEE environment */ handle_load_ta(ta, ta_size, arg); - if (arg->ret == TEEC_SUCCESS) { - mutex_lock(&session_list_mutex); - sess = alloc_session(ctxdata, arg->session); - mutex_unlock(&session_list_mutex); - } - if (arg->ret != TEEC_SUCCESS) goto out; + mutex_lock(&session_list_mutex); + sess = alloc_session(ctxdata, arg->session); + mutex_unlock(&session_list_mutex); + if (!sess) { rc = -ENOMEM; goto out; @@ -259,40 +270,29 @@ int amdtee_open_session(struct tee_context *ctx, if (i >= TEE_NUM_SESSIONS) { pr_err("reached maximum session count %d\n", TEE_NUM_SESSIONS); + kref_put(&sess->refcount, destroy_session); rc = -ENOMEM; goto out; } /* Open session with loaded TA */ handle_open_session(arg, &session_info, param); - - if (arg->ret == TEEC_SUCCESS) { - sess->session_info[i] = session_info; - set_session_id(sess->ta_handle, i, &arg->session); - } else { + if (arg->ret != TEEC_SUCCESS) { pr_err("open_session failed %d\n", arg->ret); spin_lock(&sess->lock); clear_bit(i, sess->sess_mask); spin_unlock(&sess->lock); + kref_put(&sess->refcount, destroy_session); + goto out; } + + sess->session_info[i] = session_info; + set_session_id(sess->ta_handle, i, &arg->session); out: free_pages((u64)ta, get_order(ta_size)); return rc; } -static void destroy_session(struct kref *ref) -{ - struct amdtee_session *sess = container_of(ref, struct amdtee_session, - refcount); - - /* Unload the TA from TEE */ - handle_unload_ta(sess->ta_handle); - mutex_lock(&session_list_mutex); - list_del(&sess->list_node); - mutex_unlock(&session_list_mutex); - kfree(sess); -} - int amdtee_close_session(struct tee_context *ctx, u32 session) { struct amdtee_context_data *ctxdata = ctx->data; diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index ad5479f211744ffee22c0062b6013956d385c2be..a2ce99051c51f8cd395e1893be12fc7e2ddce84a 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -348,6 +348,12 @@ static int tb_switch_nvm_read(void *priv, unsigned int offset, void *val, return ret; } +static int tb_switch_nvm_no_read(void *priv, unsigned int offset, void *val, + size_t bytes) +{ + return -EPERM; +} + static int tb_switch_nvm_write(void *priv, unsigned int offset, void *val, size_t bytes) { @@ -393,6 +399,7 @@ static struct nvmem_device *register_nvmem(struct tb_switch *sw, int id, config.read_only = true; } else { config.name = "nvm_non_active"; + config.reg_read = tb_switch_nvm_no_read; config.reg_write = tb_switch_nvm_write; config.root_only = true; } @@ -947,7 +954,7 @@ static bool tb_port_is_width_supported(struct tb_port *port, int width) ret = tb_port_read(port, &phy, TB_CFG_PORT, port->cap_phy + LANE_ADP_CS_0, 1); if (ret) - return ret; + return false; widths = (phy & LANE_ADP_CS_0_SUPPORTED_WIDTH_MASK) >> LANE_ADP_CS_0_SUPPORTED_WIDTH_SHIFT; diff --git a/drivers/tty/serdev/core.c b/drivers/tty/serdev/core.c index 42345e79920c229285cf95cf4c150690a5dfb04c..c5f0d936b003ae597c7ac05cce724793311e7492 100644 --- a/drivers/tty/serdev/core.c +++ b/drivers/tty/serdev/core.c @@ -18,6 +18,7 @@ #include #include #include +#include static bool is_registered; static DEFINE_IDA(ctrl_ida); @@ -631,6 +632,15 @@ static int acpi_serdev_check_resources(struct serdev_controller *ctrl, if (ret) return ret; + /* + * Apple machines provide an empty resource template, so on those + * machines just look for immediate children with a "baud" property + * (from the _DSM method) instead. + */ + if (!lookup.controller_handle && x86_apple_machine && + !acpi_dev_get_property(adev, "baud", ACPI_TYPE_BUFFER, NULL)) + acpi_get_parent(adev->handle, &lookup.controller_handle); + /* Make sure controller and ResourceSource handle match */ if (ACPI_HANDLE(ctrl->dev.parent) != lookup.controller_handle) return -ENODEV; diff --git a/drivers/tty/serdev/serdev-ttyport.c b/drivers/tty/serdev/serdev-ttyport.c index d1cdd2ab8b4c00b9665f2ca4cb62107ee6e78187..d367803e2044fb9e8c4f7837866fd09260f343e9 100644 --- a/drivers/tty/serdev/serdev-ttyport.c +++ b/drivers/tty/serdev/serdev-ttyport.c @@ -265,7 +265,6 @@ struct device *serdev_tty_port_register(struct tty_port *port, struct device *parent, struct tty_driver *drv, int idx) { - const struct tty_port_client_operations *old_ops; struct serdev_controller *ctrl; struct serport *serport; int ret; @@ -284,7 +283,6 @@ struct device *serdev_tty_port_register(struct tty_port *port, ctrl->ops = &ctrl_ops; - old_ops = port->client_ops; port->client_ops = &client_ops; port->client_data = ctrl; @@ -297,7 +295,7 @@ struct device *serdev_tty_port_register(struct tty_port *port, err_reset_data: port->client_data = NULL; - port->client_ops = old_ops; + port->client_ops = &tty_port_default_client_ops; serdev_controller_put(ctrl); return ERR_PTR(ret); @@ -312,8 +310,8 @@ int serdev_tty_port_unregister(struct tty_port *port) return -ENODEV; serdev_controller_remove(ctrl); - port->client_ops = NULL; port->client_data = NULL; + port->client_ops = &tty_port_default_client_ops; serdev_controller_put(ctrl); return 0; diff --git a/drivers/tty/serial/8250/8250_aspeed_vuart.c b/drivers/tty/serial/8250/8250_aspeed_vuart.c index d657aa14c3e4b588eccbfc62e899ec31b1145b1a..c33e02cbde9303110a094f8d63523197e22f9d5d 100644 --- a/drivers/tty/serial/8250/8250_aspeed_vuart.c +++ b/drivers/tty/serial/8250/8250_aspeed_vuart.c @@ -446,7 +446,6 @@ static int aspeed_vuart_probe(struct platform_device *pdev) port.port.line = rc; port.port.irq = irq_of_parse_and_map(np, 0); - port.port.irqflags = IRQF_SHARED; port.port.handle_irq = aspeed_vuart_handle_irq; port.port.iotype = UPIO_MEM; port.port.type = PORT_16550A; diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c index 0894a22fd70280eee749cb14f2101c51b051f9c8..f2a33c9082a681c3520f102fcc95d755724055e5 100644 --- a/drivers/tty/serial/8250/8250_core.c +++ b/drivers/tty/serial/8250/8250_core.c @@ -174,7 +174,7 @@ static int serial_link_irq_chain(struct uart_8250_port *up) struct hlist_head *h; struct hlist_node *n; struct irq_info *i; - int ret, irq_flags = up->port.flags & UPF_SHARE_IRQ ? IRQF_SHARED : 0; + int ret; mutex_lock(&hash_mutex); @@ -209,9 +209,8 @@ static int serial_link_irq_chain(struct uart_8250_port *up) INIT_LIST_HEAD(&up->list); i->head = &up->list; spin_unlock_irq(&i->lock); - irq_flags |= up->port.irqflags; ret = request_irq(up->port.irq, serial8250_interrupt, - irq_flags, up->port.name, i); + up->port.irqflags, up->port.name, i); if (ret < 0) serial_do_unlink(i, up); } diff --git a/drivers/tty/serial/8250/8250_exar.c b/drivers/tty/serial/8250/8250_exar.c index 91e9b070d36d1d44d94b0408747412538e1e05f8..d330da76d6b6d1bba022862f5dd3332b12ffee11 100644 --- a/drivers/tty/serial/8250/8250_exar.c +++ b/drivers/tty/serial/8250/8250_exar.c @@ -25,6 +25,14 @@ #include "8250.h" +#define PCI_DEVICE_ID_ACCES_COM_2S 0x1052 +#define PCI_DEVICE_ID_ACCES_COM_4S 0x105d +#define PCI_DEVICE_ID_ACCES_COM_8S 0x106c +#define PCI_DEVICE_ID_ACCES_COM232_8 0x10a8 +#define PCI_DEVICE_ID_ACCES_COM_2SM 0x10d2 +#define PCI_DEVICE_ID_ACCES_COM_4SM 0x10db +#define PCI_DEVICE_ID_ACCES_COM_8SM 0x10ea + #define PCI_DEVICE_ID_COMMTECH_4224PCI335 0x0002 #define PCI_DEVICE_ID_COMMTECH_4222PCI335 0x0004 #define PCI_DEVICE_ID_COMMTECH_2324PCI335 0x000a @@ -677,6 +685,22 @@ static int __maybe_unused exar_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(exar_pci_pm, exar_suspend, exar_resume); +static const struct exar8250_board acces_com_2x = { + .num_ports = 2, + .setup = pci_xr17c154_setup, +}; + +static const struct exar8250_board acces_com_4x = { + .num_ports = 4, + .setup = pci_xr17c154_setup, +}; + +static const struct exar8250_board acces_com_8x = { + .num_ports = 8, + .setup = pci_xr17c154_setup, +}; + + static const struct exar8250_board pbn_fastcom335_2 = { .num_ports = 2, .setup = pci_fastcom335_setup, @@ -745,6 +769,15 @@ static const struct exar8250_board pbn_exar_XR17V8358 = { } static const struct pci_device_id exar_pci_tbl[] = { + EXAR_DEVICE(ACCESSIO, ACCES_COM_2S, acces_com_2x), + EXAR_DEVICE(ACCESSIO, ACCES_COM_4S, acces_com_4x), + EXAR_DEVICE(ACCESSIO, ACCES_COM_8S, acces_com_8x), + EXAR_DEVICE(ACCESSIO, ACCES_COM232_8, acces_com_8x), + EXAR_DEVICE(ACCESSIO, ACCES_COM_2SM, acces_com_2x), + EXAR_DEVICE(ACCESSIO, ACCES_COM_4SM, acces_com_4x), + EXAR_DEVICE(ACCESSIO, ACCES_COM_8SM, acces_com_8x), + + CONNECT_DEVICE(XR17C152, UART_2_232, pbn_connect), CONNECT_DEVICE(XR17C154, UART_4_232, pbn_connect), CONNECT_DEVICE(XR17C158, UART_8_232, pbn_connect), diff --git a/drivers/tty/serial/8250/8250_of.c b/drivers/tty/serial/8250/8250_of.c index 531ad67395e0a5488dd662a0b29f3b7293761c4a..f6687756ec5e1efd797ea7097facfb07a6466c20 100644 --- a/drivers/tty/serial/8250/8250_of.c +++ b/drivers/tty/serial/8250/8250_of.c @@ -202,7 +202,6 @@ static int of_platform_serial_setup(struct platform_device *ofdev, port->type = type; port->uartclk = clk; - port->irqflags |= IRQF_SHARED; if (of_property_read_bool(np, "no-loopback-test")) port->flags |= UPF_SKIP_TEST; diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 430e3467aff7bf49c221401a39b2968fb8c0e7eb..0325f2e53b74507eff7b9156193e8e7dbdbcaced 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -2177,6 +2177,10 @@ int serial8250_do_startup(struct uart_port *port) } } + /* Check if we need to have shared IRQs */ + if (port->irq && (up->port.flags & UPF_SHARE_IRQ)) + up->port.irqflags |= IRQF_SHARED; + if (port->irq && !(up->port.flags & UPF_NO_THRE_TEST)) { unsigned char iir1; /* diff --git a/drivers/tty/serial/ar933x_uart.c b/drivers/tty/serial/ar933x_uart.c index 3bdd56a1021b26d6e74ff98ad6f0e25f25f5de08..ea12f10610b64dd46062735fc4e682213c407167 100644 --- a/drivers/tty/serial/ar933x_uart.c +++ b/drivers/tty/serial/ar933x_uart.c @@ -286,6 +286,10 @@ static void ar933x_uart_set_termios(struct uart_port *port, ar933x_uart_rmw_set(up, AR933X_UART_CS_REG, AR933X_UART_CS_HOST_INT_EN); + /* enable RX and TX ready overide */ + ar933x_uart_rmw_set(up, AR933X_UART_CS_REG, + AR933X_UART_CS_TX_READY_ORIDE | AR933X_UART_CS_RX_READY_ORIDE); + /* reenable the UART */ ar933x_uart_rmw(up, AR933X_UART_CS_REG, AR933X_UART_CS_IF_MODE_M << AR933X_UART_CS_IF_MODE_S, @@ -418,6 +422,10 @@ static int ar933x_uart_startup(struct uart_port *port) ar933x_uart_rmw_set(up, AR933X_UART_CS_REG, AR933X_UART_CS_HOST_INT_EN); + /* enable RX and TX ready overide */ + ar933x_uart_rmw_set(up, AR933X_UART_CS_REG, + AR933X_UART_CS_TX_READY_ORIDE | AR933X_UART_CS_RX_READY_ORIDE); + /* Enable RX interrupts */ up->ier = AR933X_UART_INT_RX_VALID; ar933x_uart_write(up, AR933X_UART_INT_EN_REG, up->ier); diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c index c15c398c88a938bd49494f959a3cb8da5b983620..a39c87a7c2e180923ce54ff5a2b03f5c641e86f5 100644 --- a/drivers/tty/serial/atmel_serial.c +++ b/drivers/tty/serial/atmel_serial.c @@ -570,7 +570,8 @@ static void atmel_stop_tx(struct uart_port *port) atmel_uart_writel(port, ATMEL_US_IDR, atmel_port->tx_done_mask); if (atmel_uart_is_half_duplex(port)) - atmel_start_rx(port); + if (!atomic_read(&atmel_port->tasklet_shutdown)) + atmel_start_rx(port); } diff --git a/drivers/tty/serial/cpm_uart/cpm_uart_core.c b/drivers/tty/serial/cpm_uart/cpm_uart_core.c index 19d5a4cf29a62e1685d1051a3cb4ada1d6fdcf7f..d4b81b06e0cbf79b9e52413d528023133a1bd053 100644 --- a/drivers/tty/serial/cpm_uart/cpm_uart_core.c +++ b/drivers/tty/serial/cpm_uart/cpm_uart_core.c @@ -1373,6 +1373,7 @@ static struct console cpm_scc_uart_console = { static int __init cpm_uart_console_init(void) { + cpm_muram_init(); register_console(&cpm_scc_uart_console); return 0; } diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index 91e2805e64416f5e54d4bbe52ee6594e0cad8e45..c31b8f3db6bf681b3df61d89431c8a957688d47d 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -264,6 +264,7 @@ struct lpuart_port { int rx_dma_rng_buf_len; unsigned int dma_tx_nents; wait_queue_head_t dma_wait; + bool id_allocated; }; struct lpuart_soc_data { @@ -2390,6 +2391,8 @@ static int __init lpuart32_imx_early_console_setup(struct earlycon_device *devic OF_EARLYCON_DECLARE(lpuart, "fsl,vf610-lpuart", lpuart_early_console_setup); OF_EARLYCON_DECLARE(lpuart32, "fsl,ls1021a-lpuart", lpuart32_early_console_setup); OF_EARLYCON_DECLARE(lpuart32, "fsl,imx7ulp-lpuart", lpuart32_imx_early_console_setup); +EARLYCON_DECLARE(lpuart, lpuart_early_console_setup); +EARLYCON_DECLARE(lpuart32, lpuart32_early_console_setup); #define LPUART_CONSOLE (&lpuart_console) #define LPUART32_CONSOLE (&lpuart32_console) @@ -2420,19 +2423,6 @@ static int lpuart_probe(struct platform_device *pdev) if (!sport) return -ENOMEM; - ret = of_alias_get_id(np, "serial"); - if (ret < 0) { - ret = ida_simple_get(&fsl_lpuart_ida, 0, UART_NR, GFP_KERNEL); - if (ret < 0) { - dev_err(&pdev->dev, "port line is full, add device failed\n"); - return ret; - } - } - if (ret >= ARRAY_SIZE(lpuart_ports)) { - dev_err(&pdev->dev, "serial%d out of range\n", ret); - return -EINVAL; - } - sport->port.line = ret; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); sport->port.membase = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(sport->port.membase)) @@ -2477,9 +2467,25 @@ static int lpuart_probe(struct platform_device *pdev) } } + ret = of_alias_get_id(np, "serial"); + if (ret < 0) { + ret = ida_simple_get(&fsl_lpuart_ida, 0, UART_NR, GFP_KERNEL); + if (ret < 0) { + dev_err(&pdev->dev, "port line is full, add device failed\n"); + return ret; + } + sport->id_allocated = true; + } + if (ret >= ARRAY_SIZE(lpuart_ports)) { + dev_err(&pdev->dev, "serial%d out of range\n", ret); + ret = -EINVAL; + goto failed_out_of_range; + } + sport->port.line = ret; + ret = lpuart_enable_clks(sport); if (ret) - return ret; + goto failed_clock_enable; sport->port.uartclk = lpuart_get_baud_clk_rate(sport); lpuart_ports[sport->port.line] = sport; @@ -2529,6 +2535,10 @@ static int lpuart_probe(struct platform_device *pdev) failed_attach_port: failed_irq_request: lpuart_disable_clks(sport); +failed_clock_enable: +failed_out_of_range: + if (sport->id_allocated) + ida_simple_remove(&fsl_lpuart_ida, sport->port.line); return ret; } @@ -2538,7 +2548,8 @@ static int lpuart_remove(struct platform_device *pdev) uart_remove_one_port(&lpuart_reg, &sport->port); - ida_simple_remove(&fsl_lpuart_ida, sport->port.line); + if (sport->id_allocated) + ida_simple_remove(&fsl_lpuart_ida, sport->port.line); lpuart_disable_clks(sport); diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index 0c6c63166250d73890b020e67ac6653d3c7ae114..d337782b36486c86db6084c24975dbe0ffbf8bdc 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -599,7 +599,7 @@ static void imx_uart_dma_tx(struct imx_port *sport) sport->tx_bytes = uart_circ_chars_pending(xmit); - if (xmit->tail < xmit->head) { + if (xmit->tail < xmit->head || xmit->head == 0) { sport->dma_tx_nents = 1; sg_init_one(sgl, xmit->buf + xmit->tail, sport->tx_bytes); } else { diff --git a/drivers/tty/serial/mvebu-uart.c b/drivers/tty/serial/mvebu-uart.c index c12a12556339f5c7b3b26aa4e5fa4efe04d0ce20..4e9a590712cb28fe4839d5adf6dfde9a719da13f 100644 --- a/drivers/tty/serial/mvebu-uart.c +++ b/drivers/tty/serial/mvebu-uart.c @@ -851,7 +851,7 @@ static int mvebu_uart_probe(struct platform_device *pdev) port->membase = devm_ioremap_resource(&pdev->dev, reg); if (IS_ERR(port->membase)) - return -PTR_ERR(port->membase); + return PTR_ERR(port->membase); mvuart = devm_kzalloc(&pdev->dev, sizeof(struct mvebu_uart), GFP_KERNEL); diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c index 191abb18fc2a7e9208f69c1896c03106b716c270..0bd1684cabb390dff5ecd854e9553690408fac6b 100644 --- a/drivers/tty/serial/qcom_geni_serial.c +++ b/drivers/tty/serial/qcom_geni_serial.c @@ -129,6 +129,7 @@ static int handle_rx_console(struct uart_port *uport, u32 bytes, bool drop); static int handle_rx_uart(struct uart_port *uport, u32 bytes, bool drop); static unsigned int qcom_geni_serial_tx_empty(struct uart_port *port); static void qcom_geni_serial_stop_rx(struct uart_port *uport); +static void qcom_geni_serial_handle_rx(struct uart_port *uport, bool drop); static const unsigned long root_freq[] = {7372800, 14745600, 19200000, 29491200, 32000000, 48000000, 64000000, 80000000, @@ -599,7 +600,7 @@ static void qcom_geni_serial_stop_rx(struct uart_port *uport) u32 irq_en; u32 status; struct qcom_geni_serial_port *port = to_dev_port(uport, uport); - u32 irq_clear = S_CMD_DONE_EN; + u32 s_irq_status; irq_en = readl(uport->membase + SE_GENI_S_IRQ_EN); irq_en &= ~(S_RX_FIFO_WATERMARK_EN | S_RX_FIFO_LAST_EN); @@ -615,10 +616,19 @@ static void qcom_geni_serial_stop_rx(struct uart_port *uport) return; geni_se_cancel_s_cmd(&port->se); - qcom_geni_serial_poll_bit(uport, SE_GENI_S_CMD_CTRL_REG, - S_GENI_CMD_CANCEL, false); + qcom_geni_serial_poll_bit(uport, SE_GENI_S_IRQ_STATUS, + S_CMD_CANCEL_EN, true); + /* + * If timeout occurs secondary engine remains active + * and Abort sequence is executed. + */ + s_irq_status = readl(uport->membase + SE_GENI_S_IRQ_STATUS); + /* Flush the Rx buffer */ + if (s_irq_status & S_RX_FIFO_LAST_EN) + qcom_geni_serial_handle_rx(uport, true); + writel(s_irq_status, uport->membase + SE_GENI_S_IRQ_CLEAR); + status = readl(uport->membase + SE_GENI_STATUS); - writel(irq_clear, uport->membase + SE_GENI_S_IRQ_CLEAR); if (status & S_GENI_CMD_ACTIVE) qcom_geni_serial_abort_rx(uport); } diff --git a/drivers/tty/serial/serial-tegra.c b/drivers/tty/serial/serial-tegra.c index 33034b852a51fa52238d7d86c0ea7329170e967f..8de8bac9c6c7200fd84530645d79d4d7b6b80eb7 100644 --- a/drivers/tty/serial/serial-tegra.c +++ b/drivers/tty/serial/serial-tegra.c @@ -692,11 +692,22 @@ static void tegra_uart_copy_rx_to_tty(struct tegra_uart_port *tup, count, DMA_TO_DEVICE); } +static void do_handle_rx_pio(struct tegra_uart_port *tup) +{ + struct tty_struct *tty = tty_port_tty_get(&tup->uport.state->port); + struct tty_port *port = &tup->uport.state->port; + + tegra_uart_handle_rx_pio(tup, port); + if (tty) { + tty_flip_buffer_push(port); + tty_kref_put(tty); + } +} + static void tegra_uart_rx_buffer_push(struct tegra_uart_port *tup, unsigned int residue) { struct tty_port *port = &tup->uport.state->port; - struct tty_struct *tty = tty_port_tty_get(port); unsigned int count; async_tx_ack(tup->rx_dma_desc); @@ -705,11 +716,7 @@ static void tegra_uart_rx_buffer_push(struct tegra_uart_port *tup, /* If we are here, DMA is stopped */ tegra_uart_copy_rx_to_tty(tup, port, count); - tegra_uart_handle_rx_pio(tup, port); - if (tty) { - tty_flip_buffer_push(port); - tty_kref_put(tty); - } + do_handle_rx_pio(tup); } static void tegra_uart_rx_dma_complete(void *args) @@ -749,8 +756,10 @@ static void tegra_uart_terminate_rx_dma(struct tegra_uart_port *tup) { struct dma_tx_state state; - if (!tup->rx_dma_active) + if (!tup->rx_dma_active) { + do_handle_rx_pio(tup); return; + } dmaengine_terminate_all(tup->rx_dma_chan); dmaengine_tx_status(tup->rx_dma_chan, tup->rx_cookie, &state); @@ -816,18 +825,6 @@ static void tegra_uart_handle_modem_signal_change(struct uart_port *u) uart_handle_cts_change(&tup->uport, msr & UART_MSR_CTS); } -static void do_handle_rx_pio(struct tegra_uart_port *tup) -{ - struct tty_struct *tty = tty_port_tty_get(&tup->uport.state->port); - struct tty_port *port = &tup->uport.state->port; - - tegra_uart_handle_rx_pio(tup, port); - if (tty) { - tty_flip_buffer_push(port); - tty_kref_put(tty); - } -} - static irqreturn_t tegra_uart_isr(int irq, void *data) { struct tegra_uart_port *tup = data; diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index a1453fe1086217d6a4e137a73fe954acee44676c..5a6f36b391d95d8662d82984f8842f3948545bca 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -1589,9 +1589,7 @@ void tty_kclose(struct tty_struct *tty) tty_debug_hangup(tty, "freeing structure\n"); /* * The release_tty function takes care of the details of clearing - * the slots and preserving the termios structure. The tty_unlock_pair - * should be safe as we keep a kref while the tty is locked (so the - * unlock never unlocks a freed tty). + * the slots and preserving the termios structure. */ mutex_lock(&tty_mutex); tty_port_set_kopened(tty->port, 0); @@ -1621,9 +1619,7 @@ void tty_release_struct(struct tty_struct *tty, int idx) tty_debug_hangup(tty, "freeing structure\n"); /* * The release_tty function takes care of the details of clearing - * the slots and preserving the termios structure. The tty_unlock_pair - * should be safe as we keep a kref while the tty is locked (so the - * unlock never unlocks a freed tty). + * the slots and preserving the termios structure. */ mutex_lock(&tty_mutex); release_tty(tty, idx); @@ -2734,9 +2730,11 @@ static int compat_tty_tiocgserial(struct tty_struct *tty, struct serial_struct32 v32; struct serial_struct v; int err; - memset(&v, 0, sizeof(struct serial_struct)); - if (!tty->ops->set_serial) + memset(&v, 0, sizeof(v)); + memset(&v32, 0, sizeof(v32)); + + if (!tty->ops->get_serial) return -ENOTTY; err = tty->ops->get_serial(tty, &v); if (!err) { diff --git a/drivers/tty/tty_port.c b/drivers/tty/tty_port.c index 044c3cbdcfa40664497d13bd00e607584eff99c7..ea80bf872f543c2883fd2fb86e66805f4f44b639 100644 --- a/drivers/tty/tty_port.c +++ b/drivers/tty/tty_port.c @@ -52,10 +52,11 @@ static void tty_port_default_wakeup(struct tty_port *port) } } -static const struct tty_port_client_operations default_client_ops = { +const struct tty_port_client_operations tty_port_default_client_ops = { .receive_buf = tty_port_default_receive_buf, .write_wakeup = tty_port_default_wakeup, }; +EXPORT_SYMBOL_GPL(tty_port_default_client_ops); void tty_port_init(struct tty_port *port) { @@ -68,7 +69,7 @@ void tty_port_init(struct tty_port *port) spin_lock_init(&port->lock); port->close_delay = (50 * HZ) / 100; port->closing_wait = (3000 * HZ) / 100; - port->client_ops = &default_client_ops; + port->client_ops = &tty_port_default_client_ops; kref_init(&port->kref); } EXPORT_SYMBOL(tty_port_init); diff --git a/drivers/tty/vt/selection.c b/drivers/tty/vt/selection.c index 78732feaf65bc237ccf26fb4685198e957e6a1c1..d7d2e4b844bcd7fc316709bde2bed61e6613dd4c 100644 --- a/drivers/tty/vt/selection.c +++ b/drivers/tty/vt/selection.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include @@ -29,6 +30,8 @@ #include #include +#include + /* Don't take this from : 011-015 on the screen aren't spaces */ #define isspace(c) ((c) == ' ') @@ -43,6 +46,7 @@ static volatile int sel_start = -1; /* cleared by clear_selection */ static int sel_end; static int sel_buffer_lth; static char *sel_buffer; +static DEFINE_MUTEX(sel_lock); /* clear_selection, highlight and highlight_pointer can be called from interrupt (via scrollback/front) */ @@ -177,14 +181,14 @@ int set_selection_user(const struct tiocl_selection __user *sel, return set_selection_kernel(&v, tty); } -int set_selection_kernel(struct tiocl_selection *v, struct tty_struct *tty) +static int __set_selection_kernel(struct tiocl_selection *v, struct tty_struct *tty) { struct vc_data *vc = vc_cons[fg_console].d; int new_sel_start, new_sel_end, spc; char *bp, *obp; int i, ps, pe, multiplier; u32 c; - int mode; + int mode, ret = 0; poke_blanked_console(); @@ -332,7 +336,21 @@ int set_selection_kernel(struct tiocl_selection *v, struct tty_struct *tty) } } sel_buffer_lth = bp - sel_buffer; - return 0; + + return ret; +} + +int set_selection_kernel(struct tiocl_selection *v, struct tty_struct *tty) +{ + int ret; + + mutex_lock(&sel_lock); + console_lock(); + ret = __set_selection_kernel(v, tty); + console_unlock(); + mutex_unlock(&sel_lock); + + return ret; } EXPORT_SYMBOL_GPL(set_selection_kernel); @@ -350,6 +368,7 @@ int paste_selection(struct tty_struct *tty) unsigned int count; struct tty_ldisc *ld; DECLARE_WAITQUEUE(wait, current); + int ret = 0; console_lock(); poke_blanked_console(); @@ -361,10 +380,17 @@ int paste_selection(struct tty_struct *tty) tty_buffer_lock_exclusive(&vc->port); add_wait_queue(&vc->paste_wait, &wait); + mutex_lock(&sel_lock); while (sel_buffer && sel_buffer_lth > pasted) { set_current_state(TASK_INTERRUPTIBLE); + if (signal_pending(current)) { + ret = -EINTR; + break; + } if (tty_throttled(tty)) { + mutex_unlock(&sel_lock); schedule(); + mutex_lock(&sel_lock); continue; } __set_current_state(TASK_RUNNING); @@ -373,11 +399,12 @@ int paste_selection(struct tty_struct *tty) count); pasted += count; } + mutex_unlock(&sel_lock); remove_wait_queue(&vc->paste_wait, &wait); __set_current_state(TASK_RUNNING); tty_buffer_unlock_exclusive(&vc->port); tty_ldisc_deref(ld); - return 0; + return ret; } EXPORT_SYMBOL_GPL(paste_selection); diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 35d21cdb60d0b82b0c786c235b7b873409efc774..15d27698054ab55aa841853bbb7d40940a423415 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -936,10 +936,21 @@ static void flush_scrollback(struct vc_data *vc) WARN_CONSOLE_UNLOCKED(); set_origin(vc); - if (vc->vc_sw->con_flush_scrollback) + if (vc->vc_sw->con_flush_scrollback) { vc->vc_sw->con_flush_scrollback(vc); - else + } else if (con_is_visible(vc)) { + /* + * When no con_flush_scrollback method is provided then the + * legacy way for flushing the scrollback buffer is to use + * a side effect of the con_switch method. We do it only on + * the foreground console as background consoles have no + * scrollback buffers in that case and we obviously don't + * want to switch to them. + */ + hide_cursor(vc); vc->vc_sw->con_switch(vc); + set_cursor(vc); + } } /* @@ -3035,10 +3046,8 @@ int tioclinux(struct tty_struct *tty, unsigned long arg) switch (type) { case TIOCL_SETSEL: - console_lock(); ret = set_selection_user((struct tiocl_selection __user *)(p+1), tty); - console_unlock(); break; case TIOCL_PASTESEL: ret = paste_selection(tty); diff --git a/drivers/tty/vt/vt_ioctl.c b/drivers/tty/vt/vt_ioctl.c index 8b0ed139592f95bf4c42fdfbd88273dec874372e..ee6c91ef1f6cf726b8b50f40128fe1dca8effabd 100644 --- a/drivers/tty/vt/vt_ioctl.c +++ b/drivers/tty/vt/vt_ioctl.c @@ -876,15 +876,20 @@ int vt_ioctl(struct tty_struct *tty, return -EINVAL; for (i = 0; i < MAX_NR_CONSOLES; i++) { + struct vc_data *vcp; + if (!vc_cons[i].d) continue; console_lock(); - if (v.v_vlin) - vc_cons[i].d->vc_scan_lines = v.v_vlin; - if (v.v_clin) - vc_cons[i].d->vc_font.height = v.v_clin; - vc_cons[i].d->vc_resize_user = 1; - vc_resize(vc_cons[i].d, v.v_cols, v.v_rows); + vcp = vc_cons[i].d; + if (vcp) { + if (v.v_vlin) + vcp->vc_scan_lines = v.v_vlin; + if (v.v_clin) + vcp->vc_font.height = v.v_clin; + vcp->vc_resize_user = 1; + vc_resize(vcp, v.v_cols, v.v_rows); + } console_unlock(); } break; diff --git a/drivers/usb/cdns3/gadget.c b/drivers/usb/cdns3/gadget.c index 736b0c6e27fe046bfac9b7449b0a8aafefdb0b85..3574dbb093667771334060aa0c4d9488ecf66575 100644 --- a/drivers/usb/cdns3/gadget.c +++ b/drivers/usb/cdns3/gadget.c @@ -2550,7 +2550,7 @@ int cdns3_gadget_ep_dequeue(struct usb_ep *ep, /* Update ring only if removed request is on pending_req_list list */ if (req_on_hw_ring) { link_trb->buffer = TRB_BUFFER(priv_ep->trb_pool_dma + - (priv_req->start_trb * TRB_SIZE)); + ((priv_req->end_trb + 1) * TRB_SIZE)); link_trb->control = (link_trb->control & TRB_CYCLE) | TRB_TYPE(TRB_LINK) | TRB_CHAIN; @@ -2595,11 +2595,21 @@ int __cdns3_gadget_ep_clear_halt(struct cdns3_endpoint *priv_ep) { struct cdns3_device *priv_dev = priv_ep->cdns3_dev; struct usb_request *request; + struct cdns3_request *priv_req; + struct cdns3_trb *trb = NULL; int ret; int val; trace_cdns3_halt(priv_ep, 0, 0); + request = cdns3_next_request(&priv_ep->pending_req_list); + if (request) { + priv_req = to_cdns3_request(request); + trb = priv_req->trb; + if (trb) + trb->control = trb->control ^ TRB_CYCLE; + } + writel(EP_CMD_CSTALL | EP_CMD_EPRST, &priv_dev->regs->ep_cmd); /* wait for EPRST cleared */ @@ -2610,10 +2620,11 @@ int __cdns3_gadget_ep_clear_halt(struct cdns3_endpoint *priv_ep) priv_ep->flags &= ~(EP_STALLED | EP_STALL_PENDING); - request = cdns3_next_request(&priv_ep->pending_req_list); - - if (request) + if (request) { + if (trb) + trb->control = trb->control ^ TRB_CYCLE; cdns3_rearm_transfer(priv_ep, 1); + } cdns3_start_all_request(priv_dev, priv_ep); return ret; diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c index ffaf46f5d062fe2c4ba9e465f8141fd2b3a154f4..4c4ac30db4987b2d18a5619638d8f7e6c3c7f6ea 100644 --- a/drivers/usb/chipidea/udc.c +++ b/drivers/usb/chipidea/udc.c @@ -1530,18 +1530,19 @@ static const struct usb_ep_ops usb_ep_ops = { static void ci_hdrc_gadget_connect(struct usb_gadget *_gadget, int is_active) { struct ci_hdrc *ci = container_of(_gadget, struct ci_hdrc, gadget); - unsigned long flags; if (is_active) { pm_runtime_get_sync(&_gadget->dev); hw_device_reset(ci); - spin_lock_irqsave(&ci->lock, flags); + spin_lock_irq(&ci->lock); if (ci->driver) { hw_device_state(ci, ci->ep0out->qh.dma); usb_gadget_set_state(_gadget, USB_STATE_POWERED); + spin_unlock_irq(&ci->lock); usb_udc_vbus_handler(_gadget, true); + } else { + spin_unlock_irq(&ci->lock); } - spin_unlock_irqrestore(&ci->lock, flags); } else { usb_udc_vbus_handler(_gadget, false); if (ci->driver) diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 62f4fb9b362f14533c86ba324588158517787019..47f09a6ce7bda47a28d2b4390bce144548e49d6e 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -896,10 +896,10 @@ static int get_serial_info(struct tty_struct *tty, struct serial_struct *ss) ss->xmit_fifo_size = acm->writesize; ss->baud_base = le32_to_cpu(acm->line.dwDTERate); - ss->close_delay = acm->port.close_delay / 10; + ss->close_delay = jiffies_to_msecs(acm->port.close_delay) / 10; ss->closing_wait = acm->port.closing_wait == ASYNC_CLOSING_WAIT_NONE ? ASYNC_CLOSING_WAIT_NONE : - acm->port.closing_wait / 10; + jiffies_to_msecs(acm->port.closing_wait) / 10; return 0; } @@ -907,24 +907,32 @@ static int set_serial_info(struct tty_struct *tty, struct serial_struct *ss) { struct acm *acm = tty->driver_data; unsigned int closing_wait, close_delay; + unsigned int old_closing_wait, old_close_delay; int retval = 0; - close_delay = ss->close_delay * 10; + close_delay = msecs_to_jiffies(ss->close_delay * 10); closing_wait = ss->closing_wait == ASYNC_CLOSING_WAIT_NONE ? - ASYNC_CLOSING_WAIT_NONE : ss->closing_wait * 10; + ASYNC_CLOSING_WAIT_NONE : + msecs_to_jiffies(ss->closing_wait * 10); + + /* we must redo the rounding here, so that the values match */ + old_close_delay = jiffies_to_msecs(acm->port.close_delay) / 10; + old_closing_wait = acm->port.closing_wait == ASYNC_CLOSING_WAIT_NONE ? + ASYNC_CLOSING_WAIT_NONE : + jiffies_to_msecs(acm->port.closing_wait) / 10; mutex_lock(&acm->port.mutex); - if (!capable(CAP_SYS_ADMIN)) { - if ((close_delay != acm->port.close_delay) || - (closing_wait != acm->port.closing_wait)) + if ((ss->close_delay != old_close_delay) || + (ss->closing_wait != old_closing_wait)) { + if (!capable(CAP_SYS_ADMIN)) retval = -EPERM; - else - retval = -EOPNOTSUPP; - } else { - acm->port.close_delay = close_delay; - acm->port.closing_wait = closing_wait; - } + else { + acm->port.close_delay = close_delay; + acm->port.closing_wait = closing_wait; + } + } else + retval = -EOPNOTSUPP; mutex_unlock(&acm->port.mutex); return retval; diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c index 26bc05e48d8a7414121dd348e7dfc06e6916cedc..b7918f6954344321412f550e262b6183c0d2a292 100644 --- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -256,6 +256,7 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, struct usb_host_interface *ifp, int num_ep, unsigned char *buffer, int size) { + struct usb_device *udev = to_usb_device(ddev); unsigned char *buffer0 = buffer; struct usb_endpoint_descriptor *d; struct usb_host_endpoint *endpoint; @@ -297,6 +298,16 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, goto skip_to_next_endpoint_or_interface_descriptor; } + /* Ignore blacklisted endpoints */ + if (udev->quirks & USB_QUIRK_ENDPOINT_BLACKLIST) { + if (usb_endpoint_is_blacklisted(udev, ifp, d)) { + dev_warn(ddev, "config %d interface %d altsetting %d has a blacklisted endpoint with address 0x%X, skipping\n", + cfgno, inum, asnum, + d->bEndpointAddress); + goto skip_to_next_endpoint_or_interface_descriptor; + } + } + endpoint = &ifp->endpoint[ifp->desc.bNumEndpoints]; ++ifp->desc.bNumEndpoints; @@ -311,7 +322,7 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, j = 255; if (usb_endpoint_xfer_int(d)) { i = 1; - switch (to_usb_device(ddev)->speed) { + switch (udev->speed) { case USB_SPEED_SUPER_PLUS: case USB_SPEED_SUPER: case USB_SPEED_HIGH: @@ -332,8 +343,7 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, /* * This quirk fixes bIntervals reported in ms. */ - if (to_usb_device(ddev)->quirks & - USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL) { + if (udev->quirks & USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL) { n = clamp(fls(d->bInterval) + 3, i, j); i = j = n; } @@ -341,8 +351,7 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, * This quirk fixes bIntervals reported in * linear microframes. */ - if (to_usb_device(ddev)->quirks & - USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL) { + if (udev->quirks & USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL) { n = clamp(fls(d->bInterval), i, j); i = j = n; } @@ -359,7 +368,7 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, } else if (usb_endpoint_xfer_isoc(d)) { i = 1; j = 16; - switch (to_usb_device(ddev)->speed) { + switch (udev->speed) { case USB_SPEED_HIGH: n = 7; /* 8 ms = 2^(7-1) uframes */ break; @@ -381,8 +390,7 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, * explicitly forbidden by the USB spec. In an attempt to make * them usable, we will try treating them as Interrupt endpoints. */ - if (to_usb_device(ddev)->speed == USB_SPEED_LOW && - usb_endpoint_xfer_bulk(d)) { + if (udev->speed == USB_SPEED_LOW && usb_endpoint_xfer_bulk(d)) { dev_warn(ddev, "config %d interface %d altsetting %d " "endpoint 0x%X is Bulk; changing to Interrupt\n", cfgno, inum, asnum, d->bEndpointAddress); @@ -406,7 +414,7 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, /* Find the highest legal maxpacket size for this endpoint */ i = 0; /* additional transactions per microframe */ - switch (to_usb_device(ddev)->speed) { + switch (udev->speed) { case USB_SPEED_LOW: maxpacket_maxes = low_speed_maxpacket_maxes; break; @@ -442,8 +450,7 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, * maxpacket sizes other than 512. High speed HCDs may not * be able to handle that particular bug, so let's warn... */ - if (to_usb_device(ddev)->speed == USB_SPEED_HIGH - && usb_endpoint_xfer_bulk(d)) { + if (udev->speed == USB_SPEED_HIGH && usb_endpoint_xfer_bulk(d)) { if (maxp != 512) dev_warn(ddev, "config %d interface %d altsetting %d " "bulk endpoint 0x%X has invalid maxpacket %d\n", @@ -452,7 +459,7 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, } /* Parse a possible SuperSpeed endpoint companion descriptor */ - if (to_usb_device(ddev)->speed >= USB_SPEED_SUPER) + if (udev->speed >= USB_SPEED_SUPER) usb_parse_ss_endpoint_companion(ddev, cfgno, inum, asnum, endpoint, buffer, size); diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 3405b146edc94f3e6fa153a769fcccccb7ee4465..54cd8ef795ec042027a19e30ef754309adcf2329 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -38,7 +38,9 @@ #include "otg_whitelist.h" #define USB_VENDOR_GENESYS_LOGIC 0x05e3 +#define USB_VENDOR_SMSC 0x0424 #define HUB_QUIRK_CHECK_PORT_AUTOSUSPEND 0x01 +#define HUB_QUIRK_DISABLE_AUTOSUSPEND 0x02 #define USB_TP_TRANSMISSION_DELAY 40 /* ns */ #define USB_TP_TRANSMISSION_DELAY_MAX 65535 /* ns */ @@ -986,13 +988,17 @@ int usb_remove_device(struct usb_device *udev) { struct usb_hub *hub; struct usb_interface *intf; + int ret; if (!udev->parent) /* Can't remove a root hub */ return -EINVAL; hub = usb_hub_to_struct_hub(udev->parent); intf = to_usb_interface(hub->intfdev); - usb_autopm_get_interface(intf); + ret = usb_autopm_get_interface(intf); + if (ret < 0) + return ret; + set_bit(udev->portnum, hub->removed_bits); hub_port_logical_disconnect(hub, udev->portnum); usb_autopm_put_interface(intf); @@ -1217,11 +1223,6 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) #ifdef CONFIG_PM udev->reset_resume = 1; #endif - /* Don't set the change_bits when the device - * was powered off. - */ - if (test_bit(port1, hub->power_bits)) - set_bit(port1, hub->change_bits); } else { /* The power session is gone; tell hub_wq */ @@ -1731,6 +1732,10 @@ static void hub_disconnect(struct usb_interface *intf) kfree(hub->buffer); pm_suspend_ignore_children(&intf->dev, false); + + if (hub->quirk_disable_autosuspend) + usb_autopm_put_interface(intf); + kref_put(&hub->kref, hub_release); } @@ -1863,6 +1868,11 @@ static int hub_probe(struct usb_interface *intf, const struct usb_device_id *id) if (id->driver_info & HUB_QUIRK_CHECK_PORT_AUTOSUSPEND) hub->quirk_check_port_auto_suspend = 1; + if (id->driver_info & HUB_QUIRK_DISABLE_AUTOSUSPEND) { + hub->quirk_disable_autosuspend = 1; + usb_autopm_get_interface_no_resume(intf); + } + if (hub_configure(hub, &desc->endpoint[0].desc) >= 0) return 0; @@ -5599,6 +5609,10 @@ static void hub_event(struct work_struct *work) } static const struct usb_device_id hub_id_table[] = { + { .match_flags = USB_DEVICE_ID_MATCH_VENDOR | USB_DEVICE_ID_MATCH_INT_CLASS, + .idVendor = USB_VENDOR_SMSC, + .bInterfaceClass = USB_CLASS_HUB, + .driver_info = HUB_QUIRK_DISABLE_AUTOSUSPEND}, { .match_flags = USB_DEVICE_ID_MATCH_VENDOR | USB_DEVICE_ID_MATCH_INT_CLASS, .idVendor = USB_VENDOR_GENESYS_LOGIC, diff --git a/drivers/usb/core/hub.h b/drivers/usb/core/hub.h index a9e24e4b8df146b30bfab2c8857a713ff6da7c97..a97dd1ba964ee5086a57972906fcc2a7271f5cb7 100644 --- a/drivers/usb/core/hub.h +++ b/drivers/usb/core/hub.h @@ -61,6 +61,7 @@ struct usb_hub { unsigned quiescing:1; unsigned disconnected:1; unsigned in_reset:1; + unsigned quirk_disable_autosuspend:1; unsigned quirk_check_port_auto_suspend:1; diff --git a/drivers/usb/core/port.c b/drivers/usb/core/port.c index bbbb35fa639fa43e6666eebfdb86c909595f6cf8..235a7c6455036ac7a6f110f943c678b09b1a24f0 100644 --- a/drivers/usb/core/port.c +++ b/drivers/usb/core/port.c @@ -213,7 +213,10 @@ static int usb_port_runtime_resume(struct device *dev) if (!port_dev->is_superspeed && peer) pm_runtime_get_sync(&peer->dev); - usb_autopm_get_interface(intf); + retval = usb_autopm_get_interface(intf); + if (retval < 0) + return retval; + retval = usb_hub_set_port_power(hdev, hub, port1, true); msleep(hub_power_on_good_delay(hub)); if (udev && !retval) { @@ -266,7 +269,10 @@ static int usb_port_runtime_suspend(struct device *dev) if (usb_port_block_power_off) return -EBUSY; - usb_autopm_get_interface(intf); + retval = usb_autopm_get_interface(intf); + if (retval < 0) + return retval; + retval = usb_hub_set_port_power(hdev, hub, port1, false); usb_clear_port_feature(hdev, port1, USB_PORT_FEAT_C_CONNECTION); if (!port_dev->is_superspeed) diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 6b6413073584339ba9e271e17ffa63fc4f883aa4..da30b5664ff3d5da22c5219159545e9faa72fdca 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -231,6 +231,9 @@ static const struct usb_device_id usb_quirk_list[] = { /* Logitech PTZ Pro Camera */ { USB_DEVICE(0x046d, 0x0853), .driver_info = USB_QUIRK_DELAY_INIT }, + /* Logitech Screen Share */ + { USB_DEVICE(0x046d, 0x086c), .driver_info = USB_QUIRK_NO_LPM }, + /* Logitech Quickcam Fusion */ { USB_DEVICE(0x046d, 0x08c1), .driver_info = USB_QUIRK_RESET_RESUME }, @@ -354,6 +357,10 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x0904, 0x6103), .driver_info = USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL }, + /* Sound Devices USBPre2 */ + { USB_DEVICE(0x0926, 0x0202), .driver_info = + USB_QUIRK_ENDPOINT_BLACKLIST }, + /* Keytouch QWERTY Panel keyboard */ { USB_DEVICE(0x0926, 0x3333), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, @@ -371,6 +378,12 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x0b05, 0x17e0), .driver_info = USB_QUIRK_IGNORE_REMOTE_WAKEUP }, + /* Realtek hub in Dell WD19 (Type-C) */ + { USB_DEVICE(0x0bda, 0x0487), .driver_info = USB_QUIRK_NO_LPM }, + + /* Generic RTL8153 based ethernet adapters */ + { USB_DEVICE(0x0bda, 0x8153), .driver_info = USB_QUIRK_NO_LPM }, + /* Action Semiconductor flash disk */ { USB_DEVICE(0x10d6, 0x2200), .driver_info = USB_QUIRK_STRING_FETCH_255 }, @@ -445,6 +458,9 @@ static const struct usb_device_id usb_quirk_list[] = { /* INTEL VALUE SSD */ { USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME }, + /* novation SoundControl XL */ + { USB_DEVICE(0x1235, 0x0061), .driver_info = USB_QUIRK_RESET_RESUME }, + { } /* terminating entry must be last */ }; @@ -472,6 +488,39 @@ static const struct usb_device_id usb_amd_resume_quirk_list[] = { { } /* terminating entry must be last */ }; +/* + * Entries for blacklisted endpoints that should be ignored when parsing + * configuration descriptors. + * + * Matched for devices with USB_QUIRK_ENDPOINT_BLACKLIST. + */ +static const struct usb_device_id usb_endpoint_blacklist[] = { + { USB_DEVICE_INTERFACE_NUMBER(0x0926, 0x0202, 1), .driver_info = 0x85 }, + { } +}; + +bool usb_endpoint_is_blacklisted(struct usb_device *udev, + struct usb_host_interface *intf, + struct usb_endpoint_descriptor *epd) +{ + const struct usb_device_id *id; + unsigned int address; + + for (id = usb_endpoint_blacklist; id->match_flags; ++id) { + if (!usb_match_device(udev, id)) + continue; + + if (!usb_match_one_id_intf(udev, intf, id)) + continue; + + address = id->driver_info; + if (address == epd->bEndpointAddress) + return true; + } + + return false; +} + static bool usb_match_any_interface(struct usb_device *udev, const struct usb_device_id *id) { diff --git a/drivers/usb/core/usb.h b/drivers/usb/core/usb.h index cf4783cf661a86ab521155b125961ce01e3fbf2d..3ad0ee57e859fb00990bcf733112c553b25c65b1 100644 --- a/drivers/usb/core/usb.h +++ b/drivers/usb/core/usb.h @@ -37,6 +37,9 @@ extern void usb_authorize_interface(struct usb_interface *); extern void usb_detect_quirks(struct usb_device *udev); extern void usb_detect_interface_quirks(struct usb_device *udev); extern void usb_release_quirk_list(void); +extern bool usb_endpoint_is_blacklisted(struct usb_device *udev, + struct usb_host_interface *intf, + struct usb_endpoint_descriptor *epd); extern int usb_remove_device(struct usb_device *udev); extern int usb_get_device_descriptor(struct usb_device *dev, diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c index 88f7d6d4ff2db1f81d4429cd1343e9e93c540903..92ed32ec160769783a14729a9aa31575057c22f3 100644 --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -1083,11 +1083,6 @@ static void dwc2_hsotg_start_req(struct dwc2_hsotg *hsotg, else packets = 1; /* send one packet if length is zero. */ - if (hs_ep->isochronous && length > (hs_ep->mc * hs_ep->ep.maxpacket)) { - dev_err(hsotg->dev, "req length > maxpacket*mc\n"); - return; - } - if (dir_in && index != 0) if (hs_ep->isochronous) epsize = DXEPTSIZ_MC(packets); @@ -1391,6 +1386,13 @@ static int dwc2_hsotg_ep_queue(struct usb_ep *ep, struct usb_request *req, req->actual = 0; req->status = -EINPROGRESS; + /* Don't queue ISOC request if length greater than mps*mc */ + if (hs_ep->isochronous && + req->length > (hs_ep->mc * hs_ep->ep.maxpacket)) { + dev_err(hs->dev, "req length > maxpacket*mc\n"); + return -EINVAL; + } + /* In DDMA mode for ISOC's don't queue request if length greater * than descriptor limits. */ @@ -1632,6 +1634,7 @@ static int dwc2_hsotg_process_req_status(struct dwc2_hsotg *hsotg, struct dwc2_hsotg_ep *ep0 = hsotg->eps_out[0]; struct dwc2_hsotg_ep *ep; __le16 reply; + u16 status; int ret; dev_dbg(hsotg->dev, "%s: USB_REQ_GET_STATUS\n", __func__); @@ -1643,11 +1646,10 @@ static int dwc2_hsotg_process_req_status(struct dwc2_hsotg *hsotg, switch (ctrl->bRequestType & USB_RECIP_MASK) { case USB_RECIP_DEVICE: - /* - * bit 0 => self powered - * bit 1 => remote wakeup - */ - reply = cpu_to_le16(0); + status = 1 << USB_DEVICE_SELF_POWERED; + status |= hsotg->remote_wakeup_allowed << + USB_DEVICE_REMOTE_WAKEUP; + reply = cpu_to_le16(status); break; case USB_RECIP_INTERFACE: @@ -1758,7 +1760,10 @@ static int dwc2_hsotg_process_req_feature(struct dwc2_hsotg *hsotg, case USB_RECIP_DEVICE: switch (wValue) { case USB_DEVICE_REMOTE_WAKEUP: - hsotg->remote_wakeup_allowed = 1; + if (set) + hsotg->remote_wakeup_allowed = 1; + else + hsotg->remote_wakeup_allowed = 0; break; case USB_DEVICE_TEST_MODE: @@ -1768,16 +1773,17 @@ static int dwc2_hsotg_process_req_feature(struct dwc2_hsotg *hsotg, return -EINVAL; hsotg->test_mode = wIndex >> 8; - ret = dwc2_hsotg_send_reply(hsotg, ep0, NULL, 0); - if (ret) { - dev_err(hsotg->dev, - "%s: failed to send reply\n", __func__); - return ret; - } break; default: return -ENOENT; } + + ret = dwc2_hsotg_send_reply(hsotg, ep0, NULL, 0); + if (ret) { + dev_err(hsotg->dev, + "%s: failed to send reply\n", __func__); + return ret; + } break; case USB_RECIP_ENDPOINT: diff --git a/drivers/usb/dwc3/debug.h b/drivers/usb/dwc3/debug.h index e56beb9d1e36c83f002052ed8ef85f75786d0b28..4a13ceaf40935abfa909495050ef37df0b40f46b 100644 --- a/drivers/usb/dwc3/debug.h +++ b/drivers/usb/dwc3/debug.h @@ -256,86 +256,77 @@ static inline const char *dwc3_ep_event_string(char *str, size_t size, u8 epnum = event->endpoint_number; size_t len; int status; - int ret; - ret = snprintf(str, size, "ep%d%s: ", epnum >> 1, + len = scnprintf(str, size, "ep%d%s: ", epnum >> 1, (epnum & 1) ? "in" : "out"); - if (ret < 0) - return "UNKNOWN"; status = event->status; switch (event->endpoint_event) { case DWC3_DEPEVT_XFERCOMPLETE: - len = strlen(str); - snprintf(str + len, size - len, "Transfer Complete (%c%c%c)", + len += scnprintf(str + len, size - len, + "Transfer Complete (%c%c%c)", status & DEPEVT_STATUS_SHORT ? 'S' : 's', status & DEPEVT_STATUS_IOC ? 'I' : 'i', status & DEPEVT_STATUS_LST ? 'L' : 'l'); - len = strlen(str); - if (epnum <= 1) - snprintf(str + len, size - len, " [%s]", + scnprintf(str + len, size - len, " [%s]", dwc3_ep0_state_string(ep0state)); break; case DWC3_DEPEVT_XFERINPROGRESS: - len = strlen(str); - - snprintf(str + len, size - len, "Transfer In Progress [%d] (%c%c%c)", + scnprintf(str + len, size - len, + "Transfer In Progress [%d] (%c%c%c)", event->parameters, status & DEPEVT_STATUS_SHORT ? 'S' : 's', status & DEPEVT_STATUS_IOC ? 'I' : 'i', status & DEPEVT_STATUS_LST ? 'M' : 'm'); break; case DWC3_DEPEVT_XFERNOTREADY: - len = strlen(str); - - snprintf(str + len, size - len, "Transfer Not Ready [%d]%s", + len += scnprintf(str + len, size - len, + "Transfer Not Ready [%d]%s", event->parameters, status & DEPEVT_STATUS_TRANSFER_ACTIVE ? " (Active)" : " (Not Active)"); - len = strlen(str); - /* Control Endpoints */ if (epnum <= 1) { int phase = DEPEVT_STATUS_CONTROL_PHASE(event->status); switch (phase) { case DEPEVT_STATUS_CONTROL_DATA: - snprintf(str + ret, size - ret, + scnprintf(str + len, size - len, " [Data Phase]"); break; case DEPEVT_STATUS_CONTROL_STATUS: - snprintf(str + ret, size - ret, + scnprintf(str + len, size - len, " [Status Phase]"); } } break; case DWC3_DEPEVT_RXTXFIFOEVT: - snprintf(str + ret, size - ret, "FIFO"); + scnprintf(str + len, size - len, "FIFO"); break; case DWC3_DEPEVT_STREAMEVT: status = event->status; switch (status) { case DEPEVT_STREAMEVT_FOUND: - snprintf(str + ret, size - ret, " Stream %d Found", + scnprintf(str + len, size - len, " Stream %d Found", event->parameters); break; case DEPEVT_STREAMEVT_NOTFOUND: default: - snprintf(str + ret, size - ret, " Stream Not Found"); + scnprintf(str + len, size - len, " Stream Not Found"); break; } break; case DWC3_DEPEVT_EPCMDCMPLT: - snprintf(str + ret, size - ret, "Endpoint Command Complete"); + scnprintf(str + len, size - len, "Endpoint Command Complete"); break; default: - snprintf(str, size, "UNKNOWN"); + scnprintf(str + len, size - len, "UNKNOWN"); } return str; diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 1b8014ab0b25098a3d976c98cdf036646aac885f..1e00bf2d65a2045e139317d297831e39815ba005 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1071,7 +1071,14 @@ static void dwc3_prepare_one_trb_sg(struct dwc3_ep *dep, unsigned int rem = length % maxp; unsigned chain = true; - if (sg_is_last(s)) + /* + * IOMMU driver is coalescing the list of sgs which shares a + * page boundary into one and giving it to USB driver. With + * this the number of sgs mapped is not equal to the number of + * sgs passed. So mark the chain bit to false if it isthe last + * mapped sg. + */ + if (i == remaining - 1) chain = false; if (rem && usb_endpoint_dir_out(dep->endpoint.desc) && !chain) { @@ -2429,7 +2436,8 @@ static int dwc3_gadget_ep_reclaim_completed_trb(struct dwc3_ep *dep, if (event->status & DEPEVT_STATUS_SHORT && !chain) return 1; - if (event->status & DEPEVT_STATUS_IOC) + if ((trb->ctrl & DWC3_TRB_CTRL_IOC) || + (trb->ctrl & DWC3_TRB_CTRL_LST)) return 1; return 0; diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index 3b4f67000315c952073068552669f2d10cc87d5d..223f72d4d9eddf2734a4148ce21cd52a358b4102 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -437,12 +437,14 @@ static u8 encode_bMaxPower(enum usb_device_speed speed, val = CONFIG_USB_GADGET_VBUS_DRAW; if (!val) return 0; - switch (speed) { - case USB_SPEED_SUPER: - return DIV_ROUND_UP(val, 8); - default: - return DIV_ROUND_UP(val, 2); - } + if (speed < USB_SPEED_SUPER) + return min(val, 500U) / 2; + else + /* + * USB 3.x supports up to 900mA, but since 900 isn't divisible + * by 8 the integral division will effectively cap to 896mA. + */ + return min(val, 900U) / 8; } static int config_buf(struct usb_configuration *config, @@ -854,6 +856,10 @@ static int set_config(struct usb_composite_dev *cdev, /* when we return, be sure our power usage is valid */ power = c->MaxPower ? c->MaxPower : CONFIG_USB_GADGET_VBUS_DRAW; + if (gadget->speed < USB_SPEED_SUPER) + power = min(power, 500U); + else + power = min(power, 900U); done: usb_gadget_vbus_draw(gadget, power); if (result >= 0 && cdev->delayed_status) @@ -2280,7 +2286,7 @@ void composite_resume(struct usb_gadget *gadget) { struct usb_composite_dev *cdev = get_gadget_data(gadget); struct usb_function *f; - u16 maxpower; + unsigned maxpower; /* REVISIT: should we have config level * suspend/resume callbacks? @@ -2294,10 +2300,14 @@ void composite_resume(struct usb_gadget *gadget) f->resume(f); } - maxpower = cdev->config->MaxPower; + maxpower = cdev->config->MaxPower ? + cdev->config->MaxPower : CONFIG_USB_GADGET_VBUS_DRAW; + if (gadget->speed < USB_SPEED_SUPER) + maxpower = min(maxpower, 500U); + else + maxpower = min(maxpower, 900U); - usb_gadget_vbus_draw(gadget, maxpower ? - maxpower : CONFIG_USB_GADGET_VBUS_DRAW); + usb_gadget_vbus_draw(gadget, maxpower); } cdev->suspended = 0; diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 6171d28331e6d7999e5afa3a2b99e42ea1ec5168..571917677d358f4f62dbf34ee7a17a9dce0755f4 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -1162,18 +1162,19 @@ static int ffs_aio_cancel(struct kiocb *kiocb) { struct ffs_io_data *io_data = kiocb->private; struct ffs_epfile *epfile = kiocb->ki_filp->private_data; + unsigned long flags; int value; ENTER(); - spin_lock_irq(&epfile->ffs->eps_lock); + spin_lock_irqsave(&epfile->ffs->eps_lock, flags); if (likely(io_data && io_data->ep && io_data->req)) value = usb_ep_dequeue(io_data->ep, io_data->req); else value = -EINVAL; - spin_unlock_irq(&epfile->ffs->eps_lock); + spin_unlock_irqrestore(&epfile->ffs->eps_lock, flags); return value; } diff --git a/drivers/usb/gadget/function/u_audio.c b/drivers/usb/gadget/function/u_audio.c index 6d956f190f5ac7322cbcf8a26d444aa13e1117b5..e6d32c536781247908904b7e9252901e064fad0b 100644 --- a/drivers/usb/gadget/function/u_audio.c +++ b/drivers/usb/gadget/function/u_audio.c @@ -361,7 +361,7 @@ int u_audio_start_capture(struct g_audio *audio_dev) ep = audio_dev->out_ep; prm = &uac->c_prm; config_ep_by_speed(gadget, &audio_dev->func, ep); - req_len = prm->max_psize; + req_len = ep->maxpacket; prm->ep_enabled = true; usb_ep_enable(ep); @@ -379,7 +379,7 @@ int u_audio_start_capture(struct g_audio *audio_dev) req->context = &prm->ureq[i]; req->length = req_len; req->complete = u_audio_iso_complete; - req->buf = prm->rbuf + i * prm->max_psize; + req->buf = prm->rbuf + i * ep->maxpacket; } if (usb_ep_queue(ep, prm->ureq[i].req, GFP_ATOMIC)) @@ -430,9 +430,9 @@ int u_audio_start_playback(struct g_audio *audio_dev) uac->p_pktsize = min_t(unsigned int, uac->p_framesize * (params->p_srate / uac->p_interval), - prm->max_psize); + ep->maxpacket); - if (uac->p_pktsize < prm->max_psize) + if (uac->p_pktsize < ep->maxpacket) uac->p_pktsize_residue = uac->p_framesize * (params->p_srate % uac->p_interval); else @@ -457,7 +457,7 @@ int u_audio_start_playback(struct g_audio *audio_dev) req->context = &prm->ureq[i]; req->length = req_len; req->complete = u_audio_iso_complete; - req->buf = prm->rbuf + i * prm->max_psize; + req->buf = prm->rbuf + i * ep->maxpacket; } if (usb_ep_queue(ep, prm->ureq[i].req, GFP_ATOMIC)) diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c index f986e5c559748d43fb598753a44ffaf46e0a081c..8167d379e115ba5ae7874478f863d0b16c84f4a4 100644 --- a/drivers/usb/gadget/function/u_serial.c +++ b/drivers/usb/gadget/function/u_serial.c @@ -561,8 +561,10 @@ static int gs_start_io(struct gs_port *port) port->n_read = 0; started = gs_start_rx(port); - /* unblock any pending writes into our circular buffer */ if (started) { + gs_start_tx(port); + /* Unblock any pending writes into our circular buffer, in case + * we didn't in gs_start_tx() */ tty_wakeup(port->port.tty); } else { gs_free_requests(ep, head, &port->read_allocated); diff --git a/drivers/usb/gadget/udc/udc-xilinx.c b/drivers/usb/gadget/udc/udc-xilinx.c index 29d8e5f8bb58397ec6402f22cf723e5774f6f132..b1cfc8279c3d2d00c3ee594011124e8dd46735ba 100644 --- a/drivers/usb/gadget/udc/udc-xilinx.c +++ b/drivers/usb/gadget/udc/udc-xilinx.c @@ -1399,7 +1399,6 @@ static int xudc_start(struct usb_gadget *gadget, /** * xudc_stop - stops the device. * @gadget: pointer to the usb gadget structure - * @driver: pointer to usb gadget driver structure * * Return: zero always */ diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index 7a3a29e5e9d29d33bec4e9ff45e50f26986dbf96..af92b2576fe91c5d497ab0aa8145aeaabd9ab5c9 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -55,6 +55,7 @@ static u8 usb_bos_descriptor [] = { static int xhci_create_usb3_bos_desc(struct xhci_hcd *xhci, char *buf, u16 wLength) { + struct xhci_port_cap *port_cap = NULL; int i, ssa_count; u32 temp; u16 desc_size, ssp_cap_size, ssa_size = 0; @@ -64,16 +65,24 @@ static int xhci_create_usb3_bos_desc(struct xhci_hcd *xhci, char *buf, ssp_cap_size = sizeof(usb_bos_descriptor) - desc_size; /* does xhci support USB 3.1 Enhanced SuperSpeed */ - if (xhci->usb3_rhub.min_rev >= 0x01) { + for (i = 0; i < xhci->num_port_caps; i++) { + if (xhci->port_caps[i].maj_rev == 0x03 && + xhci->port_caps[i].min_rev >= 0x01) { + usb3_1 = true; + port_cap = &xhci->port_caps[i]; + break; + } + } + + if (usb3_1) { /* does xhci provide a PSI table for SSA speed attributes? */ - if (xhci->usb3_rhub.psi_count) { + if (port_cap->psi_count) { /* two SSA entries for each unique PSI ID, RX and TX */ - ssa_count = xhci->usb3_rhub.psi_uid_count * 2; + ssa_count = port_cap->psi_uid_count * 2; ssa_size = ssa_count * sizeof(u32); ssp_cap_size -= 16; /* skip copying the default SSA */ } desc_size += ssp_cap_size; - usb3_1 = true; } memcpy(buf, &usb_bos_descriptor, min(desc_size, wLength)); @@ -99,7 +108,7 @@ static int xhci_create_usb3_bos_desc(struct xhci_hcd *xhci, char *buf, } /* If PSI table exists, add the custom speed attributes from it */ - if (usb3_1 && xhci->usb3_rhub.psi_count) { + if (usb3_1 && port_cap->psi_count) { u32 ssp_cap_base, bm_attrib, psi, psi_mant, psi_exp; int offset; @@ -111,7 +120,7 @@ static int xhci_create_usb3_bos_desc(struct xhci_hcd *xhci, char *buf, /* attribute count SSAC bits 4:0 and ID count SSIC bits 8:5 */ bm_attrib = (ssa_count - 1) & 0x1f; - bm_attrib |= (xhci->usb3_rhub.psi_uid_count - 1) << 5; + bm_attrib |= (port_cap->psi_uid_count - 1) << 5; put_unaligned_le32(bm_attrib, &buf[ssp_cap_base + 4]); if (wLength < desc_size + ssa_size) @@ -124,8 +133,8 @@ static int xhci_create_usb3_bos_desc(struct xhci_hcd *xhci, char *buf, * USB 3.1 requires two SSA entries (RX and TX) for every link */ offset = desc_size; - for (i = 0; i < xhci->usb3_rhub.psi_count; i++) { - psi = xhci->usb3_rhub.psi[i]; + for (i = 0; i < port_cap->psi_count; i++) { + psi = port_cap->psi[i]; psi &= ~USB_SSP_SUBLINK_SPEED_RSVD; psi_exp = XHCI_EXT_PORT_PSIE(psi); psi_mant = XHCI_EXT_PORT_PSIM(psi); diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 3b1388fa2f36e74093e2dc2abc0083cd650266c5..884c601bfa15f8d809a44bab42f11809a9c1e93c 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -1475,9 +1475,15 @@ int xhci_endpoint_init(struct xhci_hcd *xhci, /* Allow 3 retries for everything but isoc, set CErr = 3 */ if (!usb_endpoint_xfer_isoc(&ep->desc)) err_count = 3; - /* Some devices get this wrong */ - if (usb_endpoint_xfer_bulk(&ep->desc) && udev->speed == USB_SPEED_HIGH) - max_packet = 512; + /* HS bulk max packet should be 512, FS bulk supports 8, 16, 32 or 64 */ + if (usb_endpoint_xfer_bulk(&ep->desc)) { + if (udev->speed == USB_SPEED_HIGH) + max_packet = 512; + if (udev->speed == USB_SPEED_FULL) { + max_packet = rounddown_pow_of_two(max_packet); + max_packet = clamp_val(max_packet, 8, 64); + } + } /* xHCI 1.0 and 1.1 indicates that ctrl ep avg TRB Length should be 8 */ if (usb_endpoint_xfer_control(&ep->desc) && xhci->hci_version >= 0x100) avg_trb_len = 8; @@ -1909,17 +1915,17 @@ void xhci_mem_cleanup(struct xhci_hcd *xhci) xhci->usb3_rhub.num_ports = 0; xhci->num_active_eps = 0; kfree(xhci->usb2_rhub.ports); - kfree(xhci->usb2_rhub.psi); kfree(xhci->usb3_rhub.ports); - kfree(xhci->usb3_rhub.psi); kfree(xhci->hw_ports); kfree(xhci->rh_bw); kfree(xhci->ext_caps); + for (i = 0; i < xhci->num_port_caps; i++) + kfree(xhci->port_caps[i].psi); + kfree(xhci->port_caps); + xhci->num_port_caps = 0; xhci->usb2_rhub.ports = NULL; - xhci->usb2_rhub.psi = NULL; xhci->usb3_rhub.ports = NULL; - xhci->usb3_rhub.psi = NULL; xhci->hw_ports = NULL; xhci->rh_bw = NULL; xhci->ext_caps = NULL; @@ -2120,6 +2126,7 @@ static void xhci_add_in_port(struct xhci_hcd *xhci, unsigned int num_ports, u8 major_revision, minor_revision; struct xhci_hub *rhub; struct device *dev = xhci_to_hcd(xhci)->self.sysdev; + struct xhci_port_cap *port_cap; temp = readl(addr); major_revision = XHCI_EXT_PORT_MAJOR(temp); @@ -2154,31 +2161,39 @@ static void xhci_add_in_port(struct xhci_hcd *xhci, unsigned int num_ports, /* WTF? "Valid values are ‘1’ to MaxPorts" */ return; - rhub->psi_count = XHCI_EXT_PORT_PSIC(temp); - if (rhub->psi_count) { - rhub->psi = kcalloc_node(rhub->psi_count, sizeof(*rhub->psi), - GFP_KERNEL, dev_to_node(dev)); - if (!rhub->psi) - rhub->psi_count = 0; + port_cap = &xhci->port_caps[xhci->num_port_caps++]; + if (xhci->num_port_caps > max_caps) + return; + + port_cap->maj_rev = major_revision; + port_cap->min_rev = minor_revision; + port_cap->psi_count = XHCI_EXT_PORT_PSIC(temp); - rhub->psi_uid_count++; - for (i = 0; i < rhub->psi_count; i++) { - rhub->psi[i] = readl(addr + 4 + i); + if (port_cap->psi_count) { + port_cap->psi = kcalloc_node(port_cap->psi_count, + sizeof(*port_cap->psi), + GFP_KERNEL, dev_to_node(dev)); + if (!port_cap->psi) + port_cap->psi_count = 0; + + port_cap->psi_uid_count++; + for (i = 0; i < port_cap->psi_count; i++) { + port_cap->psi[i] = readl(addr + 4 + i); /* count unique ID values, two consecutive entries can * have the same ID if link is assymetric */ - if (i && (XHCI_EXT_PORT_PSIV(rhub->psi[i]) != - XHCI_EXT_PORT_PSIV(rhub->psi[i - 1]))) - rhub->psi_uid_count++; + if (i && (XHCI_EXT_PORT_PSIV(port_cap->psi[i]) != + XHCI_EXT_PORT_PSIV(port_cap->psi[i - 1]))) + port_cap->psi_uid_count++; xhci_dbg(xhci, "PSIV:%d PSIE:%d PLT:%d PFD:%d LP:%d PSIM:%d\n", - XHCI_EXT_PORT_PSIV(rhub->psi[i]), - XHCI_EXT_PORT_PSIE(rhub->psi[i]), - XHCI_EXT_PORT_PLT(rhub->psi[i]), - XHCI_EXT_PORT_PFD(rhub->psi[i]), - XHCI_EXT_PORT_LP(rhub->psi[i]), - XHCI_EXT_PORT_PSIM(rhub->psi[i])); + XHCI_EXT_PORT_PSIV(port_cap->psi[i]), + XHCI_EXT_PORT_PSIE(port_cap->psi[i]), + XHCI_EXT_PORT_PLT(port_cap->psi[i]), + XHCI_EXT_PORT_PFD(port_cap->psi[i]), + XHCI_EXT_PORT_LP(port_cap->psi[i]), + XHCI_EXT_PORT_PSIM(port_cap->psi[i])); } } /* cache usb2 port capabilities */ @@ -2213,6 +2228,7 @@ static void xhci_add_in_port(struct xhci_hcd *xhci, unsigned int num_ports, continue; } hw_port->rhub = rhub; + hw_port->port_cap = port_cap; rhub->num_ports++; } /* FIXME: Should we disable ports not in the Extended Capabilities? */ @@ -2303,6 +2319,11 @@ static int xhci_setup_port_arrays(struct xhci_hcd *xhci, gfp_t flags) if (!xhci->ext_caps) return -ENOMEM; + xhci->port_caps = kcalloc_node(cap_count, sizeof(*xhci->port_caps), + flags, dev_to_node(dev)); + if (!xhci->port_caps) + return -ENOMEM; + offset = cap_start; while (offset) { diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 4917c5b033faccd0f6b9fe903dbf99cb8a47d62c..1fddc41fa1f38408acd9859226c021508b4f61a6 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -49,6 +49,7 @@ #define PCI_DEVICE_ID_INTEL_TITAN_RIDGE_4C_XHCI 0x15ec #define PCI_DEVICE_ID_INTEL_TITAN_RIDGE_DD_XHCI 0x15f0 #define PCI_DEVICE_ID_INTEL_ICE_LAKE_XHCI 0x8a13 +#define PCI_DEVICE_ID_INTEL_CML_XHCI 0xa3af #define PCI_DEVICE_ID_AMD_PROMONTORYA_4 0x43b9 #define PCI_DEVICE_ID_AMD_PROMONTORYA_3 0x43ba @@ -135,7 +136,8 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) xhci->quirks |= XHCI_AMD_PLL_FIX; if (pdev->vendor == PCI_VENDOR_ID_AMD && - (pdev->device == 0x15e0 || + (pdev->device == 0x145c || + pdev->device == 0x15e0 || pdev->device == 0x15e1 || pdev->device == 0x43bb)) xhci->quirks |= XHCI_SUSPEND_DELAY; @@ -187,7 +189,8 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) pdev->device == PCI_DEVICE_ID_INTEL_BROXTON_M_XHCI || pdev->device == PCI_DEVICE_ID_INTEL_BROXTON_B_XHCI || pdev->device == PCI_DEVICE_ID_INTEL_APL_XHCI || - pdev->device == PCI_DEVICE_ID_INTEL_DNV_XHCI)) { + pdev->device == PCI_DEVICE_ID_INTEL_DNV_XHCI || + pdev->device == PCI_DEVICE_ID_INTEL_CML_XHCI)) { xhci->quirks |= XHCI_PME_STUCK_QUIRK; } if (pdev->vendor == PCI_VENDOR_ID_INTEL && @@ -302,6 +305,9 @@ static int xhci_pci_setup(struct usb_hcd *hcd) if (!usb_hcd_is_primary_hcd(hcd)) return 0; + if (xhci->quirks & XHCI_PME_STUCK_QUIRK) + xhci_pme_acpi_rtd3_enable(pdev); + xhci_dbg(xhci, "Got SBRN %u\n", (unsigned int) xhci->sbrn); /* Find any debug ports */ @@ -359,9 +365,6 @@ static int xhci_pci_probe(struct pci_dev *dev, const struct pci_device_id *id) HCC_MAX_PSA(xhci->hcc_params) >= 4) xhci->shared_hcd->can_do_streams = 1; - if (xhci->quirks & XHCI_PME_STUCK_QUIRK) - xhci_pme_acpi_rtd3_enable(dev); - /* USB-2 and USB-3 roothubs initialized, allow runtime pm suspend */ pm_runtime_put_noidle(&dev->dev); diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index d90cd5ec09cf2d2129fd4f3d47f8bffb692d03d0..315b4552693c79848146e325099c37350d7131e3 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -445,6 +445,7 @@ MODULE_DEVICE_TABLE(acpi, usb_xhci_acpi_match); static struct platform_driver usb_xhci_driver = { .probe = xhci_plat_probe, .remove = xhci_plat_remove, + .shutdown = usb_hcd_platform_shutdown, .driver = { .name = "xhci-hcd", .pm = &xhci_plat_pm_ops, diff --git a/drivers/usb/host/xhci-trace.h b/drivers/usb/host/xhci-trace.h index 56eb867803a62ee9cee1601fd0009129240df1f3..b19582b2a72c0f4a586261ce79011b1a647a7387 100644 --- a/drivers/usb/host/xhci-trace.h +++ b/drivers/usb/host/xhci-trace.h @@ -289,23 +289,12 @@ DECLARE_EVENT_CLASS(xhci_log_urb, ), TP_printk("ep%d%s-%s: urb %p pipe %u slot %d length %d/%d sgs %d/%d stream %d flags %08x", __entry->epnum, __entry->dir_in ? "in" : "out", - ({ char *s; - switch (__entry->type) { - case USB_ENDPOINT_XFER_INT: - s = "intr"; - break; - case USB_ENDPOINT_XFER_CONTROL: - s = "control"; - break; - case USB_ENDPOINT_XFER_BULK: - s = "bulk"; - break; - case USB_ENDPOINT_XFER_ISOC: - s = "isoc"; - break; - default: - s = "UNKNOWN"; - } s; }), __entry->urb, __entry->pipe, __entry->slot_id, + __print_symbolic(__entry->type, + { USB_ENDPOINT_XFER_INT, "intr" }, + { USB_ENDPOINT_XFER_CONTROL, "control" }, + { USB_ENDPOINT_XFER_BULK, "bulk" }, + { USB_ENDPOINT_XFER_ISOC, "isoc" }), + __entry->urb, __entry->pipe, __entry->slot_id, __entry->actual, __entry->length, __entry->num_mapped_sgs, __entry->num_sgs, __entry->stream, __entry->flags ) diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 13d8838cd552be01b145e0d2f78dc815c3ffad0b..3ecee10fdcdc7dfd697b24310de0ad3885421f10 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1702,12 +1702,20 @@ struct xhci_bus_state { * Intel Lynx Point LP xHCI host. */ #define XHCI_MAX_REXIT_TIMEOUT_MS 20 +struct xhci_port_cap { + u32 *psi; /* array of protocol speed ID entries */ + u8 psi_count; + u8 psi_uid_count; + u8 maj_rev; + u8 min_rev; +}; struct xhci_port { __le32 __iomem *addr; int hw_portnum; int hcd_portnum; struct xhci_hub *rhub; + struct xhci_port_cap *port_cap; }; struct xhci_hub { @@ -1719,9 +1727,6 @@ struct xhci_hub { /* supported prococol extended capabiliy values */ u8 maj_rev; u8 min_rev; - u32 *psi; /* array of protocol speed ID entries */ - u8 psi_count; - u8 psi_uid_count; }; /* There is one xhci_hcd structure per controller */ @@ -1880,6 +1885,9 @@ struct xhci_hcd { /* cached usb2 extened protocol capabilites */ u32 *ext_caps; unsigned int num_ext_caps; + /* cached extended protocol port capabilities */ + struct xhci_port_cap *port_caps; + unsigned int num_port_caps; /* Compliance Mode Recovery Data */ struct timer_list comp_mode_recovery_timer; u32 port_status_u0; diff --git a/drivers/usb/misc/iowarrior.c b/drivers/usb/misc/iowarrior.c index dce44fbf031fb2875498632dba484fe3866ad045..dce20301e367a617277d1ae0f2489f220c4f9ee4 100644 --- a/drivers/usb/misc/iowarrior.c +++ b/drivers/usb/misc/iowarrior.c @@ -33,6 +33,14 @@ #define USB_DEVICE_ID_CODEMERCS_IOWPV2 0x1512 /* full speed iowarrior */ #define USB_DEVICE_ID_CODEMERCS_IOW56 0x1503 +/* fuller speed iowarrior */ +#define USB_DEVICE_ID_CODEMERCS_IOW28 0x1504 +#define USB_DEVICE_ID_CODEMERCS_IOW28L 0x1505 +#define USB_DEVICE_ID_CODEMERCS_IOW100 0x1506 + +/* OEMed devices */ +#define USB_DEVICE_ID_CODEMERCS_IOW24SAG 0x158a +#define USB_DEVICE_ID_CODEMERCS_IOW56AM 0x158b /* Get a minor range for your devices from the usb maintainer */ #ifdef CONFIG_USB_DYNAMIC_MINORS @@ -133,6 +141,11 @@ static const struct usb_device_id iowarrior_ids[] = { {USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOWPV1)}, {USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOWPV2)}, {USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW56)}, + {USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW24SAG)}, + {USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW56AM)}, + {USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW28)}, + {USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW28L)}, + {USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW100)}, {} /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, iowarrior_ids); @@ -357,6 +370,7 @@ static ssize_t iowarrior_write(struct file *file, } switch (dev->product_id) { case USB_DEVICE_ID_CODEMERCS_IOW24: + case USB_DEVICE_ID_CODEMERCS_IOW24SAG: case USB_DEVICE_ID_CODEMERCS_IOWPV1: case USB_DEVICE_ID_CODEMERCS_IOWPV2: case USB_DEVICE_ID_CODEMERCS_IOW40: @@ -371,6 +385,10 @@ static ssize_t iowarrior_write(struct file *file, goto exit; break; case USB_DEVICE_ID_CODEMERCS_IOW56: + case USB_DEVICE_ID_CODEMERCS_IOW56AM: + case USB_DEVICE_ID_CODEMERCS_IOW28: + case USB_DEVICE_ID_CODEMERCS_IOW28L: + case USB_DEVICE_ID_CODEMERCS_IOW100: /* The IOW56 uses asynchronous IO and more urbs */ if (atomic_read(&dev->write_busy) == MAX_WRITES_IN_FLIGHT) { /* Wait until we are below the limit for submitted urbs */ @@ -493,6 +511,7 @@ static long iowarrior_ioctl(struct file *file, unsigned int cmd, switch (cmd) { case IOW_WRITE: if (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW24 || + dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW24SAG || dev->product_id == USB_DEVICE_ID_CODEMERCS_IOWPV1 || dev->product_id == USB_DEVICE_ID_CODEMERCS_IOWPV2 || dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW40) { @@ -767,7 +786,11 @@ static int iowarrior_probe(struct usb_interface *interface, goto error; } - if (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56) { + if ((dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56) || + (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56AM) || + (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW28) || + (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW28L) || + (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW100)) { res = usb_find_last_int_out_endpoint(iface_desc, &dev->int_out_endpoint); if (res) { @@ -780,7 +803,11 @@ static int iowarrior_probe(struct usb_interface *interface, /* we have to check the report_size often, so remember it in the endianness suitable for our machine */ dev->report_size = usb_endpoint_maxp(dev->int_in_endpoint); if ((dev->interface->cur_altsetting->desc.bInterfaceNumber == 0) && - (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56)) + ((dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56) || + (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56AM) || + (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW28) || + (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW28L) || + (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW100))) /* IOWarrior56 has wMaxPacketSize different from report size */ dev->report_size = 7; diff --git a/drivers/usb/misc/usb251xb.c b/drivers/usb/misc/usb251xb.c index 10c9e7f6273eb5010f8391e34b1199a708358e04..29fe5771c21bce1ad28009b2b216a90299668ba4 100644 --- a/drivers/usb/misc/usb251xb.c +++ b/drivers/usb/misc/usb251xb.c @@ -424,10 +424,6 @@ static int usb251xb_get_ofdata(struct usb251xb *hub, return err; } - hub->vdd = devm_regulator_get(dev, "vdd"); - if (IS_ERR(hub->vdd)) - return PTR_ERR(hub->vdd); - if (of_property_read_u16_array(np, "vendor-id", &hub->vendor_id, 1)) hub->vendor_id = USB251XB_DEF_VENDOR_ID; @@ -640,6 +636,13 @@ static int usb251xb_get_ofdata(struct usb251xb *hub, } #endif /* CONFIG_OF */ +static void usb251xb_regulator_disable_action(void *data) +{ + struct usb251xb *hub = data; + + regulator_disable(hub->vdd); +} + static int usb251xb_probe(struct usb251xb *hub) { struct device *dev = hub->dev; @@ -676,10 +679,19 @@ static int usb251xb_probe(struct usb251xb *hub) if (err) return err; + hub->vdd = devm_regulator_get(dev, "vdd"); + if (IS_ERR(hub->vdd)) + return PTR_ERR(hub->vdd); + err = regulator_enable(hub->vdd); if (err) return err; + err = devm_add_action_or_reset(dev, + usb251xb_regulator_disable_action, hub); + if (err) + return err; + err = usb251xb_connect(hub); if (err) { dev_err(dev, "Failed to connect hub (%d)\n", err); diff --git a/drivers/usb/phy/phy-tegra-usb.c b/drivers/usb/phy/phy-tegra-usb.c index 037e8eee737d58d1fefee1f5c4d33ccdcced7376..6153cc35aba0d71cbedaff59f8ae40ae825f43c6 100644 --- a/drivers/usb/phy/phy-tegra-usb.c +++ b/drivers/usb/phy/phy-tegra-usb.c @@ -969,6 +969,10 @@ static int utmi_phy_probe(struct tegra_usb_phy *tegra_phy, return -ENXIO; } + /* + * Note that UTMI pad registers are shared by all PHYs, therefore + * devm_platform_ioremap_resource() can't be used here. + */ tegra_phy->pad_regs = devm_ioremap(&pdev->dev, res->start, resource_size(res)); if (!tegra_phy->pad_regs) { @@ -1087,6 +1091,10 @@ static int tegra_usb_phy_probe(struct platform_device *pdev) return -ENXIO; } + /* + * Note that PHY and USB controller are using shared registers, + * therefore devm_platform_ioremap_resource() can't be used here. + */ tegra_phy->regs = devm_ioremap(&pdev->dev, res->start, resource_size(res)); if (!tegra_phy->regs) { diff --git a/drivers/usb/serial/ch341.c b/drivers/usb/serial/ch341.c index d3f420f3a083570d4d3372514c39430caa9fc8d8..c5ecdcd51ffc6742e09af4954e5c3c272233c208 100644 --- a/drivers/usb/serial/ch341.c +++ b/drivers/usb/serial/ch341.c @@ -205,6 +205,16 @@ static int ch341_get_divisor(speed_t speed) 16 * speed - 16 * CH341_CLKRATE / (clk_div * (div + 1))) div++; + /* + * Prefer lower base clock (fact = 0) if even divisor. + * + * Note that this makes the receiver more tolerant to errors. + */ + if (fact == 1 && div % 2 == 0) { + div /= 2; + fact = 0; + } + return (0x100 - div) << 8 | fact << 2 | ps; } diff --git a/drivers/usb/serial/ir-usb.c b/drivers/usb/serial/ir-usb.c index 79d0586e2b338019b03ddc042d9479544784c60d..172261a908d8d6d94e76996ad28e7fbf3b2cd94a 100644 --- a/drivers/usb/serial/ir-usb.c +++ b/drivers/usb/serial/ir-usb.c @@ -448,7 +448,7 @@ static void ir_set_termios(struct tty_struct *tty, usb_sndbulkpipe(udev, port->bulk_out_endpointAddress), transfer_buffer, 1, &actual_length, 5000); if (ret || actual_length != 1) { - if (actual_length != 1) + if (!ret) ret = -EIO; dev_err(&port->dev, "failed to change line speed: %d\n", ret); } diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 084cc2fff3ae318f4819bc495f865c7952d79983..0b5dcf973d94b5adfe14c9ff15af99c9a9d7d7d1 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1183,6 +1183,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(0) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x110a, 0xff), /* Telit ME910G1 */ .driver_info = NCTRL(0) | RSVD(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x110b, 0xff), /* Telit ME910G1 (ECM) */ + .driver_info = NCTRL(0) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910), .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910_USBCFG4), diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c index aab737e1e7b65aab669f768adab0681962c1b7d8..c5a2995dfa2e371eed561974e09af10adc1df843 100644 --- a/drivers/usb/serial/pl2303.c +++ b/drivers/usb/serial/pl2303.c @@ -99,6 +99,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(SUPERIAL_VENDOR_ID, SUPERIAL_PRODUCT_ID) }, { USB_DEVICE(HP_VENDOR_ID, HP_LD220_PRODUCT_ID) }, { USB_DEVICE(HP_VENDOR_ID, HP_LD220TA_PRODUCT_ID) }, + { USB_DEVICE(HP_VENDOR_ID, HP_LD381_PRODUCT_ID) }, { USB_DEVICE(HP_VENDOR_ID, HP_LD960_PRODUCT_ID) }, { USB_DEVICE(HP_VENDOR_ID, HP_LD960TA_PRODUCT_ID) }, { USB_DEVICE(HP_VENDOR_ID, HP_LCM220_PRODUCT_ID) }, diff --git a/drivers/usb/serial/pl2303.h b/drivers/usb/serial/pl2303.h index a019ea7e6e0eb7f84fa45bcf2de46a5259468a70..52db5519aaf08a520804aa7faf115b5ff26235f4 100644 --- a/drivers/usb/serial/pl2303.h +++ b/drivers/usb/serial/pl2303.h @@ -130,6 +130,7 @@ #define HP_LM920_PRODUCT_ID 0x026b #define HP_TD620_PRODUCT_ID 0x0956 #define HP_LD960_PRODUCT_ID 0x0b39 +#define HP_LD381_PRODUCT_ID 0x0f7f #define HP_LCM220_PRODUCT_ID 0x3139 #define HP_LCM960_PRODUCT_ID 0x3239 #define HP_LD220_PRODUCT_ID 0x3524 diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index 95bba3ba6ac67ec933215f9548df254cc44081f9..3670fda02c3460000b06be6e0d496a3eb014fbb7 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -45,6 +45,7 @@ struct uas_dev_info { struct scsi_cmnd *cmnd[MAX_CMNDS]; spinlock_t lock; struct work_struct work; + struct work_struct scan_work; /* for async scanning */ }; enum { @@ -114,6 +115,17 @@ static void uas_do_work(struct work_struct *work) spin_unlock_irqrestore(&devinfo->lock, flags); } +static void uas_scan_work(struct work_struct *work) +{ + struct uas_dev_info *devinfo = + container_of(work, struct uas_dev_info, scan_work); + struct Scsi_Host *shost = usb_get_intfdata(devinfo->intf); + + dev_dbg(&devinfo->intf->dev, "starting scan\n"); + scsi_scan_host(shost); + dev_dbg(&devinfo->intf->dev, "scan complete\n"); +} + static void uas_add_work(struct uas_cmd_info *cmdinfo) { struct scsi_pointer *scp = (void *)cmdinfo; @@ -982,6 +994,7 @@ static int uas_probe(struct usb_interface *intf, const struct usb_device_id *id) init_usb_anchor(&devinfo->data_urbs); spin_lock_init(&devinfo->lock); INIT_WORK(&devinfo->work, uas_do_work); + INIT_WORK(&devinfo->scan_work, uas_scan_work); result = uas_configure_endpoints(devinfo); if (result) @@ -998,7 +1011,9 @@ static int uas_probe(struct usb_interface *intf, const struct usb_device_id *id) if (result) goto free_streams; - scsi_scan_host(shost); + /* Submit the delayed_work for SCSI-device scanning */ + schedule_work(&devinfo->scan_work); + return result; free_streams: @@ -1166,6 +1181,12 @@ static void uas_disconnect(struct usb_interface *intf) usb_kill_anchored_urbs(&devinfo->data_urbs); uas_zap_pending(devinfo, DID_NO_CONNECT); + /* + * Prevent SCSI scanning (if it hasn't started yet) + * or wait for the SCSI-scanning routine to stop. + */ + cancel_work_sync(&devinfo->scan_work); + scsi_remove_host(shost); uas_free_streams(devinfo); scsi_host_put(shost); diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index 1cd9b6305b06042fecf75942c4f79af41747feea..1880f3e13f57633d7c401998d33f859e0423cc31 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -1258,6 +1258,12 @@ UNUSUAL_DEV( 0x090a, 0x1200, 0x0000, 0x9999, USB_SC_RBC, USB_PR_BULK, NULL, 0 ), +UNUSUAL_DEV(0x090c, 0x1000, 0x1100, 0x1100, + "Samsung", + "Flash Drive FIT", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_MAX_SECTORS_64), + /* aeb */ UNUSUAL_DEV( 0x090c, 0x1132, 0x0000, 0xffff, "Feiya", diff --git a/drivers/usb/typec/ucsi/displayport.c b/drivers/usb/typec/ucsi/displayport.c index 0f1273ae086cbba1ab8df9bf1083fba727f6486e..048381c058a5bfe4dd14aa4a118bc128d30509ef 100644 --- a/drivers/usb/typec/ucsi/displayport.c +++ b/drivers/usb/typec/ucsi/displayport.c @@ -271,6 +271,9 @@ void ucsi_displayport_remove_partner(struct typec_altmode *alt) return; dp = typec_altmode_get_drvdata(alt); + if (!dp) + return; + dp->data.conf = 0; dp->data.status = 0; dp->initialized = false; @@ -285,6 +288,8 @@ struct typec_altmode *ucsi_register_displayport(struct ucsi_connector *con, struct typec_altmode *alt; struct ucsi_dp *dp; + mutex_lock(&con->lock); + /* We can't rely on the firmware with the capabilities. */ desc->vdo |= DP_CAP_DP_SIGNALING | DP_CAP_RECEPTACLE; @@ -293,12 +298,15 @@ struct typec_altmode *ucsi_register_displayport(struct ucsi_connector *con, desc->vdo |= all_assignments << 16; alt = typec_port_register_altmode(con->port, desc); - if (IS_ERR(alt)) + if (IS_ERR(alt)) { + mutex_unlock(&con->lock); return alt; + } dp = devm_kzalloc(&alt->dev, sizeof(*dp), GFP_KERNEL); if (!dp) { typec_unregister_altmode(alt); + mutex_unlock(&con->lock); return ERR_PTR(-ENOMEM); } @@ -311,5 +319,7 @@ struct typec_altmode *ucsi_register_displayport(struct ucsi_connector *con, alt->ops = &ucsi_displayport_ops; typec_altmode_set_drvdata(alt, dp); + mutex_unlock(&con->lock); + return alt; } diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index e158159671fa27a46f34c463a70c3cb461732c6b..18e205eeb9af7c8e20aec27d46d2781aebf9ae5d 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1414,10 +1414,6 @@ static int vhost_net_release(struct inode *inode, struct file *f) static struct socket *get_raw_socket(int fd) { - struct { - struct sockaddr_ll sa; - char buf[MAX_ADDR_LEN]; - } uaddr; int r; struct socket *sock = sockfd_lookup(fd, &r); @@ -1430,11 +1426,7 @@ static struct socket *get_raw_socket(int fd) goto err; } - r = sock->ops->getname(sock, (struct sockaddr *)&uaddr.sa, 0); - if (r < 0) - goto err; - - if (uaddr.sa.sll_family != AF_PACKET) { + if (sock->sk->sk_family != AF_PACKET) { r = -EPFNOSUPPORT; goto err; } diff --git a/drivers/video/backlight/Kconfig b/drivers/video/backlight/Kconfig index 403707a3e503b125ab4afe088babc9bef62bea81..0093bbd0d32659a9a090fac9ec4cb17aa6837de9 100644 --- a/drivers/video/backlight/Kconfig +++ b/drivers/video/backlight/Kconfig @@ -456,6 +456,13 @@ config BACKLIGHT_RAVE_SP help Support for backlight control on RAVE SP device. +config BACKLIGHT_LED + tristate "Generic LED based Backlight Driver" + depends on LEDS_CLASS && OF + help + If you have a LCD backlight adjustable by LED class driver, say Y + to enable this driver. + endif # BACKLIGHT_CLASS_DEVICE endmenu diff --git a/drivers/video/backlight/Makefile b/drivers/video/backlight/Makefile index 6f8777037c372ef1765add544096a8d042f743f6..0c1a1524627ad43032e721dcfd5ea24273474068 100644 --- a/drivers/video/backlight/Makefile +++ b/drivers/video/backlight/Makefile @@ -57,3 +57,4 @@ obj-$(CONFIG_BACKLIGHT_TPS65217) += tps65217_bl.o obj-$(CONFIG_BACKLIGHT_WM831X) += wm831x_bl.o obj-$(CONFIG_BACKLIGHT_ARCXCNN) += arcxcnn_bl.o obj-$(CONFIG_BACKLIGHT_RAVE_SP) += rave-sp-backlight.o +obj-$(CONFIG_BACKLIGHT_LED) += led_bl.o diff --git a/drivers/video/backlight/led_bl.c b/drivers/video/backlight/led_bl.c new file mode 100644 index 0000000000000000000000000000000000000000..3f66549997c8040f81e512b08720f27afdf2f377 --- /dev/null +++ b/drivers/video/backlight/led_bl.c @@ -0,0 +1,260 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2015-2019 Texas Instruments Incorporated - http://www.ti.com/ + * Author: Tomi Valkeinen + * + * Based on pwm_bl.c + */ + +#include +#include +#include +#include + +struct led_bl_data { + struct device *dev; + struct backlight_device *bl_dev; + struct led_classdev **leds; + bool enabled; + int nb_leds; + unsigned int *levels; + unsigned int default_brightness; + unsigned int max_brightness; +}; + +static void led_bl_set_brightness(struct led_bl_data *priv, int level) +{ + int i; + int bkl_brightness; + + if (priv->levels) + bkl_brightness = priv->levels[level]; + else + bkl_brightness = level; + + for (i = 0; i < priv->nb_leds; i++) + led_set_brightness(priv->leds[i], bkl_brightness); + + priv->enabled = true; +} + +static void led_bl_power_off(struct led_bl_data *priv) +{ + int i; + + if (!priv->enabled) + return; + + for (i = 0; i < priv->nb_leds; i++) + led_set_brightness(priv->leds[i], LED_OFF); + + priv->enabled = false; +} + +static int led_bl_update_status(struct backlight_device *bl) +{ + struct led_bl_data *priv = bl_get_data(bl); + int brightness = bl->props.brightness; + + if (bl->props.power != FB_BLANK_UNBLANK || + bl->props.fb_blank != FB_BLANK_UNBLANK || + bl->props.state & BL_CORE_FBBLANK) + brightness = 0; + + if (brightness > 0) + led_bl_set_brightness(priv, brightness); + else + led_bl_power_off(priv); + + return 0; +} + +static const struct backlight_ops led_bl_ops = { + .update_status = led_bl_update_status, +}; + +static int led_bl_get_leds(struct device *dev, + struct led_bl_data *priv) +{ + int i, nb_leds, ret; + struct device_node *node = dev->of_node; + struct led_classdev **leds; + unsigned int max_brightness; + unsigned int default_brightness; + + ret = of_count_phandle_with_args(node, "leds", NULL); + if (ret < 0) { + dev_err(dev, "Unable to get led count\n"); + return -EINVAL; + } + + nb_leds = ret; + if (nb_leds < 1) { + dev_err(dev, "At least one LED must be specified!\n"); + return -EINVAL; + } + + leds = devm_kzalloc(dev, sizeof(struct led_classdev *) * nb_leds, + GFP_KERNEL); + if (!leds) + return -ENOMEM; + + for (i = 0; i < nb_leds; i++) { + leds[i] = devm_of_led_get(dev, i); + if (IS_ERR(leds[i])) + return PTR_ERR(leds[i]); + } + + /* check that the LEDs all have the same brightness range */ + max_brightness = leds[0]->max_brightness; + for (i = 1; i < nb_leds; i++) { + if (max_brightness != leds[i]->max_brightness) { + dev_err(dev, "LEDs must have identical ranges\n"); + return -EINVAL; + } + } + + /* get the default brightness from the first LED from the list */ + default_brightness = leds[0]->brightness; + + priv->nb_leds = nb_leds; + priv->leds = leds; + priv->max_brightness = max_brightness; + priv->default_brightness = default_brightness; + + return 0; +} + +static int led_bl_parse_levels(struct device *dev, + struct led_bl_data *priv) +{ + struct device_node *node = dev->of_node; + int num_levels; + u32 value; + int ret; + + if (!node) + return -ENODEV; + + num_levels = of_property_count_u32_elems(node, "brightness-levels"); + if (num_levels > 1) { + int i; + unsigned int db; + u32 *levels = NULL; + + levels = devm_kzalloc(dev, sizeof(u32) * num_levels, + GFP_KERNEL); + if (!levels) + return -ENOMEM; + + ret = of_property_read_u32_array(node, "brightness-levels", + levels, + num_levels); + if (ret < 0) + return ret; + + /* + * Try to map actual LED brightness to backlight brightness + * level + */ + db = priv->default_brightness; + for (i = 0 ; i < num_levels; i++) { + if ((i && db > levels[i-1]) && db <= levels[i]) + break; + } + priv->default_brightness = i; + priv->max_brightness = num_levels - 1; + priv->levels = levels; + } else if (num_levels >= 0) + dev_warn(dev, "Not enough levels defined\n"); + + ret = of_property_read_u32(node, "default-brightness-level", &value); + if (!ret && value <= priv->max_brightness) + priv->default_brightness = value; + else if (!ret && value > priv->max_brightness) + dev_warn(dev, "Invalid default brightness. Ignoring it\n"); + + return 0; +} + +static int led_bl_probe(struct platform_device *pdev) +{ + struct backlight_properties props; + struct led_bl_data *priv; + int ret, i; + + priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + platform_set_drvdata(pdev, priv); + + priv->dev = &pdev->dev; + + ret = led_bl_get_leds(&pdev->dev, priv); + if (ret) + return ret; + + ret = led_bl_parse_levels(&pdev->dev, priv); + if (ret < 0) { + dev_err(&pdev->dev, "Failed to parse DT data\n"); + return ret; + } + + memset(&props, 0, sizeof(struct backlight_properties)); + props.type = BACKLIGHT_RAW; + props.max_brightness = priv->max_brightness; + props.brightness = priv->default_brightness; + props.power = (priv->default_brightness > 0) ? FB_BLANK_POWERDOWN : + FB_BLANK_UNBLANK; + priv->bl_dev = backlight_device_register(dev_name(&pdev->dev), + &pdev->dev, priv, &led_bl_ops, &props); + if (IS_ERR(priv->bl_dev)) { + dev_err(&pdev->dev, "Failed to register backlight\n"); + return PTR_ERR(priv->bl_dev); + } + + for (i = 0; i < priv->nb_leds; i++) + led_sysfs_disable(priv->leds[i]); + + backlight_update_status(priv->bl_dev); + + return 0; +} + +static int led_bl_remove(struct platform_device *pdev) +{ + struct led_bl_data *priv = platform_get_drvdata(pdev); + struct backlight_device *bl = priv->bl_dev; + int i; + + backlight_device_unregister(bl); + + led_bl_power_off(priv); + for (i = 0; i < priv->nb_leds; i++) + led_sysfs_enable(priv->leds[i]); + + return 0; +} + +static const struct of_device_id led_bl_of_match[] = { + { .compatible = "led-backlight" }, + { } +}; + +MODULE_DEVICE_TABLE(of, led_bl_of_match); + +static struct platform_driver led_bl_driver = { + .driver = { + .name = "led-backlight", + .of_match_table = of_match_ptr(led_bl_of_match), + }, + .probe = led_bl_probe, + .remove = led_bl_remove, +}; + +module_platform_driver(led_bl_driver); + +MODULE_DESCRIPTION("LED based Backlight Driver"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:led-backlight"); diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c index de7b8382aba9930cb1aaabbd7ba3287736073285..998b0de1812f016e6439c1c07f753fea836230b8 100644 --- a/drivers/video/console/vgacon.c +++ b/drivers/video/console/vgacon.c @@ -1316,6 +1316,9 @@ static int vgacon_font_get(struct vc_data *c, struct console_font *font) static int vgacon_resize(struct vc_data *c, unsigned int width, unsigned int height, unsigned int user) { + if ((width << 1) * height > vga_vram_size) + return -EINVAL; + if (width % 2 || width > screen_info.orig_video_cols || height > (screen_info.orig_video_lines * vga_default_font_height)/ c->vc_font.height) diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 7bfe365d93720c8b9c4ebb1809e1e1adc7c5f9f8..341458fd95ca4896e9eb4bd708473dc1df1ff012 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -959,8 +959,8 @@ static int virtballoon_probe(struct virtio_device *vdev) iput(vb->vb_dev_info.inode); out_kern_unmount: kern_unmount(balloon_mnt); -#endif out_del_vqs: +#endif vdev->config->del_vqs(vdev); out_free_vb: kfree(vb); diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 867c7ebd3f107a500b6db20211428feab78fda82..58b96baa8d488a94da858688147c5f9dd6ae4d30 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -2203,10 +2203,10 @@ void vring_del_virtqueue(struct virtqueue *_vq) vq->split.queue_size_in_bytes, vq->split.vring.desc, vq->split.queue_dma_addr); - - kfree(vq->split.desc_state); } } + if (!vq->packed_ring) + kfree(vq->split.desc_state); list_del(&_vq->list); kfree(vq); } diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig index cec868f8db3f9645ac9bd7741f7f60e28c86bbb6..9ea2b43d4b012aebc8571b3b713011733e3d332c 100644 --- a/drivers/watchdog/Kconfig +++ b/drivers/watchdog/Kconfig @@ -207,6 +207,7 @@ config DA9063_WATCHDOG config DA9062_WATCHDOG tristate "Dialog DA9062/61 Watchdog" depends on MFD_DA9062 || COMPILE_TEST + depends on I2C select WATCHDOG_CORE help Support for the watchdog in the DA9062 and DA9061 PMICs. @@ -841,6 +842,7 @@ config MEDIATEK_WATCHDOG tristate "Mediatek SoCs watchdog support" depends on ARCH_MEDIATEK || COMPILE_TEST select WATCHDOG_CORE + select RESET_CONTROLLER help Say Y here to include support for the watchdog timer in Mediatek SoCs. diff --git a/drivers/watchdog/da9062_wdt.c b/drivers/watchdog/da9062_wdt.c index 47eefe072b405ff055ef830e6c831464d39de6e4..0ad15d55071ce5931f8c5b381c29add6017e9683 100644 --- a/drivers/watchdog/da9062_wdt.c +++ b/drivers/watchdog/da9062_wdt.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include @@ -31,6 +32,7 @@ static const unsigned int wdt_timeout[] = { 0, 2, 4, 8, 16, 32, 65, 131 }; struct da9062_watchdog { struct da9062 *hw; struct watchdog_device wdtdev; + bool use_sw_pm; }; static unsigned int da9062_wdt_timeout_to_sel(unsigned int secs) @@ -95,13 +97,6 @@ static int da9062_wdt_stop(struct watchdog_device *wdd) struct da9062_watchdog *wdt = watchdog_get_drvdata(wdd); int ret; - ret = da9062_reset_watchdog_timer(wdt); - if (ret) { - dev_err(wdt->hw->dev, "Failed to ping the watchdog (err = %d)\n", - ret); - return ret; - } - ret = regmap_update_bits(wdt->hw->regmap, DA9062AA_CONTROL_D, DA9062AA_TWDSCALE_MASK, @@ -200,6 +195,8 @@ static int da9062_wdt_probe(struct platform_device *pdev) if (!wdt) return -ENOMEM; + wdt->use_sw_pm = device_property_present(dev, "dlg,use-sw-pm"); + wdt->hw = chip; wdt->wdtdev.info = &da9062_watchdog_info; @@ -226,6 +223,10 @@ static int da9062_wdt_probe(struct platform_device *pdev) static int __maybe_unused da9062_wdt_suspend(struct device *dev) { struct watchdog_device *wdd = dev_get_drvdata(dev); + struct da9062_watchdog *wdt = watchdog_get_drvdata(wdd); + + if (!wdt->use_sw_pm) + return 0; if (watchdog_active(wdd)) return da9062_wdt_stop(wdd); @@ -236,6 +237,10 @@ static int __maybe_unused da9062_wdt_suspend(struct device *dev) static int __maybe_unused da9062_wdt_resume(struct device *dev) { struct watchdog_device *wdd = dev_get_drvdata(dev); + struct da9062_watchdog *wdt = watchdog_get_drvdata(wdd); + + if (!wdt->use_sw_pm) + return 0; if (watchdog_active(wdd)) return da9062_wdt_start(wdd); diff --git a/drivers/watchdog/iTCO_vendor.h b/drivers/watchdog/iTCO_vendor.h index 0f7373ba10d5be065811e429fce8b93f71a2ef4f..69e92e692ae01eacb11c39a9bc45351bbd4768c6 100644 --- a/drivers/watchdog/iTCO_vendor.h +++ b/drivers/watchdog/iTCO_vendor.h @@ -1,10 +1,12 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* iTCO Vendor Specific Support hooks */ #ifdef CONFIG_ITCO_VENDOR_SUPPORT +extern int iTCO_vendorsupport; extern void iTCO_vendor_pre_start(struct resource *, unsigned int); extern void iTCO_vendor_pre_stop(struct resource *); extern int iTCO_vendor_check_noreboot_on(void); #else +#define iTCO_vendorsupport 0 #define iTCO_vendor_pre_start(acpibase, heartbeat) {} #define iTCO_vendor_pre_stop(acpibase) {} #define iTCO_vendor_check_noreboot_on() 1 diff --git a/drivers/watchdog/iTCO_vendor_support.c b/drivers/watchdog/iTCO_vendor_support.c index 4f1b96f59349666ca78b1e9e7a6253ed6c9acc60..cf0eaa04b064d0fea561873fecf3d3b69574acf1 100644 --- a/drivers/watchdog/iTCO_vendor_support.c +++ b/drivers/watchdog/iTCO_vendor_support.c @@ -39,8 +39,10 @@ /* Broken BIOS */ #define BROKEN_BIOS 911 -static int vendorsupport; -module_param(vendorsupport, int, 0); +int iTCO_vendorsupport; +EXPORT_SYMBOL(iTCO_vendorsupport); + +module_param_named(vendorsupport, iTCO_vendorsupport, int, 0); MODULE_PARM_DESC(vendorsupport, "iTCO vendor specific support mode, default=" "0 (none), 1=SuperMicro Pent3, 911=Broken SMI BIOS"); @@ -152,7 +154,7 @@ static void broken_bios_stop(struct resource *smires) void iTCO_vendor_pre_start(struct resource *smires, unsigned int heartbeat) { - switch (vendorsupport) { + switch (iTCO_vendorsupport) { case SUPERMICRO_OLD_BOARD: supermicro_old_pre_start(smires); break; @@ -165,7 +167,7 @@ EXPORT_SYMBOL(iTCO_vendor_pre_start); void iTCO_vendor_pre_stop(struct resource *smires) { - switch (vendorsupport) { + switch (iTCO_vendorsupport) { case SUPERMICRO_OLD_BOARD: supermicro_old_pre_stop(smires); break; @@ -178,7 +180,7 @@ EXPORT_SYMBOL(iTCO_vendor_pre_stop); int iTCO_vendor_check_noreboot_on(void) { - switch (vendorsupport) { + switch (iTCO_vendorsupport) { case SUPERMICRO_OLD_BOARD: return 0; default: @@ -189,13 +191,13 @@ EXPORT_SYMBOL(iTCO_vendor_check_noreboot_on); static int __init iTCO_vendor_init_module(void) { - if (vendorsupport == SUPERMICRO_NEW_BOARD) { + if (iTCO_vendorsupport == SUPERMICRO_NEW_BOARD) { pr_warn("Option vendorsupport=%d is no longer supported, " "please use the w83627hf_wdt driver instead\n", SUPERMICRO_NEW_BOARD); return -EINVAL; } - pr_info("vendor-support=%d\n", vendorsupport); + pr_info("vendor-support=%d\n", iTCO_vendorsupport); return 0; } diff --git a/drivers/watchdog/iTCO_wdt.c b/drivers/watchdog/iTCO_wdt.c index 156360e37714af6f3f7dd9b590222db5253cc9ff..e707c4797f76e57d8e89eb9d5249728c409a58ad 100644 --- a/drivers/watchdog/iTCO_wdt.c +++ b/drivers/watchdog/iTCO_wdt.c @@ -459,13 +459,25 @@ static int iTCO_wdt_probe(struct platform_device *pdev) if (!p->tco_res) return -ENODEV; - p->smi_res = platform_get_resource(pdev, IORESOURCE_IO, ICH_RES_IO_SMI); - if (!p->smi_res) - return -ENODEV; - p->iTCO_version = pdata->version; p->pci_dev = to_pci_dev(dev->parent); + p->smi_res = platform_get_resource(pdev, IORESOURCE_IO, ICH_RES_IO_SMI); + if (p->smi_res) { + /* The TCO logic uses the TCO_EN bit in the SMI_EN register */ + if (!devm_request_region(dev, p->smi_res->start, + resource_size(p->smi_res), + pdev->name)) { + pr_err("I/O address 0x%04llx already in use, device disabled\n", + (u64)SMI_EN(p)); + return -EBUSY; + } + } else if (iTCO_vendorsupport || + turn_SMI_watchdog_clear_off >= p->iTCO_version) { + pr_err("SMI I/O resource is missing\n"); + return -ENODEV; + } + iTCO_wdt_no_reboot_bit_setup(p, pdata); /* @@ -492,14 +504,6 @@ static int iTCO_wdt_probe(struct platform_device *pdev) /* Set the NO_REBOOT bit to prevent later reboots, just for sure */ p->update_no_reboot_bit(p->no_reboot_priv, true); - /* The TCO logic uses the TCO_EN bit in the SMI_EN register */ - if (!devm_request_region(dev, p->smi_res->start, - resource_size(p->smi_res), - pdev->name)) { - pr_err("I/O address 0x%04llx already in use, device disabled\n", - (u64)SMI_EN(p)); - return -EBUSY; - } if (turn_SMI_watchdog_clear_off >= p->iTCO_version) { /* * Bit 13: TCO_EN -> 0 diff --git a/drivers/watchdog/wdat_wdt.c b/drivers/watchdog/wdat_wdt.c index b069349b52f55f92005bd4d6429f2a1a95def739..3065dd670a18289df900c07c93f513c4d9c8f598 100644 --- a/drivers/watchdog/wdat_wdt.c +++ b/drivers/watchdog/wdat_wdt.c @@ -54,6 +54,13 @@ module_param(nowayout, bool, 0); MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default=" __MODULE_STRING(WATCHDOG_NOWAYOUT) ")"); +#define WDAT_DEFAULT_TIMEOUT 30 + +static int timeout = WDAT_DEFAULT_TIMEOUT; +module_param(timeout, int, 0); +MODULE_PARM_DESC(timeout, "Watchdog timeout in seconds (default=" + __MODULE_STRING(WDAT_DEFAULT_TIMEOUT) ")"); + static int wdat_wdt_read(struct wdat_wdt *wdat, const struct wdat_instruction *instr, u32 *value) { @@ -389,7 +396,7 @@ static int wdat_wdt_probe(struct platform_device *pdev) memset(&r, 0, sizeof(r)); r.start = gas->address; - r.end = r.start + gas->access_width - 1; + r.end = r.start + ACPI_ACCESS_BYTE_WIDTH(gas->access_width) - 1; if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) { r.flags = IORESOURCE_MEM; } else if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_IO) { @@ -438,6 +445,22 @@ static int wdat_wdt_probe(struct platform_device *pdev) platform_set_drvdata(pdev, wdat); + /* + * Set initial timeout so that userspace has time to configure the + * watchdog properly after it has opened the device. In some cases + * the BIOS default is too short and causes immediate reboot. + */ + if (timeout * 1000 < wdat->wdd.min_hw_heartbeat_ms || + timeout * 1000 > wdat->wdd.max_hw_heartbeat_ms) { + dev_warn(dev, "Invalid timeout %d given, using %d\n", + timeout, WDAT_DEFAULT_TIMEOUT); + timeout = WDAT_DEFAULT_TIMEOUT; + } + + ret = wdat_wdt_set_timeout(&wdat->wdd, timeout); + if (ret) + return ret; + watchdog_set_nowayout(&wdat->wdd, nowayout); return devm_watchdog_register_device(dev, &wdat->wdd); } diff --git a/drivers/xen/preempt.c b/drivers/xen/preempt.c index 70650b248de5d43dae2b4ae01d1fbebfaa6d4c10..17240c5325a30c799478f1e13df0e503dfa71c09 100644 --- a/drivers/xen/preempt.c +++ b/drivers/xen/preempt.c @@ -33,7 +33,9 @@ asmlinkage __visible void xen_maybe_preempt_hcall(void) * cpu. */ __this_cpu_write(xen_in_preemptible_hcall, false); - _cond_resched(); + local_irq_enable(); + cond_resched(); + local_irq_disable(); __this_cpu_write(xen_in_preemptible_hcall, true); } } diff --git a/drivers/xen/xen-pciback/pciback.h b/drivers/xen/xen-pciback/pciback.h index ce1077e32466ba9064e16d48f7bcb8c14c2c7be8..7c95516a860fa31de6e3ccccc751183550b1c92c 100644 --- a/drivers/xen/xen-pciback/pciback.h +++ b/drivers/xen/xen-pciback/pciback.h @@ -52,7 +52,7 @@ struct xen_pcibk_dev_data { unsigned int ack_intr:1; /* .. and ACK-ing */ unsigned long handled; unsigned int irq; /* Saved in case device transitions to MSI/MSI-X */ - char irq_name[0]; /* xen-pcibk[000:04:00.0] */ + char irq_name[]; /* xen-pcibk[000:04:00.0] */ }; /* Used by XenBus and xen_pcibk_ops.c */ diff --git a/drivers/xen/xenbus/xenbus_comms.c b/drivers/xen/xenbus/xenbus_comms.c index d239fc3c5e3ded66ad28194fcdc7d09a6df801da..eb5151fc8efab02899ce764b99a8d6f2955e9ca7 100644 --- a/drivers/xen/xenbus/xenbus_comms.c +++ b/drivers/xen/xenbus/xenbus_comms.c @@ -313,6 +313,8 @@ static int process_msg(void) req->msg.type = state.msg.type; req->msg.len = state.msg.len; req->body = state.body; + /* write body, then update state */ + virt_wmb(); req->state = xb_req_state_got_reply; req->cb(req); } else @@ -395,6 +397,8 @@ static int process_writes(void) if (state.req->state == xb_req_state_aborted) kfree(state.req); else { + /* write err, then update state */ + virt_wmb(); state.req->state = xb_req_state_got_reply; wake_up(&state.req->wq); } diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index 66975da4f3b60dff1995af08da2b8a835820946a..8c4d05b687b787a1272452bb7dd16b7913e40108 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -239,9 +239,9 @@ int xenbus_dev_probe(struct device *_dev) goto fail; } - spin_lock(&dev->reclaim_lock); + down(&dev->reclaim_sem); err = drv->probe(dev, id); - spin_unlock(&dev->reclaim_lock); + up(&dev->reclaim_sem); if (err) goto fail_put; @@ -271,9 +271,9 @@ int xenbus_dev_remove(struct device *_dev) free_otherend_watch(dev); if (drv->remove) { - spin_lock(&dev->reclaim_lock); + down(&dev->reclaim_sem); drv->remove(dev); - spin_unlock(&dev->reclaim_lock); + up(&dev->reclaim_sem); } module_put(drv->driver.owner); @@ -473,7 +473,7 @@ int xenbus_probe_node(struct xen_bus_type *bus, goto fail; dev_set_name(&xendev->dev, "%s", devname); - spin_lock_init(&xendev->reclaim_lock); + sema_init(&xendev->reclaim_sem, 1); /* Register with generic device framework. */ err = device_register(&xendev->dev); diff --git a/drivers/xen/xenbus/xenbus_probe_backend.c b/drivers/xen/xenbus/xenbus_probe_backend.c index 791f6fe01e91ef1834750796d97cd241bd5f597c..9b2fbe69bccc7cdadb264997e680952ef95fde08 100644 --- a/drivers/xen/xenbus/xenbus_probe_backend.c +++ b/drivers/xen/xenbus/xenbus_probe_backend.c @@ -45,6 +45,7 @@ #include #include #include +#include #include #include @@ -257,10 +258,10 @@ static int backend_reclaim_memory(struct device *dev, void *data) drv = to_xenbus_driver(dev->driver); if (drv && drv->reclaim_memory) { xdev = to_xenbus_device(dev); - if (!spin_trylock(&xdev->reclaim_lock)) + if (down_trylock(&xdev->reclaim_sem)) return 0; drv->reclaim_memory(xdev); - spin_unlock(&xdev->reclaim_lock); + up(&xdev->reclaim_sem); } return 0; } diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c index ddc18da61834e6c04180bd2ada5f55d67e9c057a..3a06eb699f33309f1d836235e6ba160a59c484fb 100644 --- a/drivers/xen/xenbus/xenbus_xs.c +++ b/drivers/xen/xenbus/xenbus_xs.c @@ -191,8 +191,11 @@ static bool xenbus_ok(void) static bool test_reply(struct xb_req_data *req) { - if (req->state == xb_req_state_got_reply || !xenbus_ok()) + if (req->state == xb_req_state_got_reply || !xenbus_ok()) { + /* read req->state before all other fields */ + virt_rmb(); return true; + } /* Make sure to reread req->state each time. */ barrier(); @@ -202,7 +205,7 @@ static bool test_reply(struct xb_req_data *req) static void *read_reply(struct xb_req_data *req) { - while (req->state != xb_req_state_got_reply) { + do { wait_event(req->wq, test_reply(req)); if (!xenbus_ok()) @@ -216,7 +219,7 @@ static void *read_reply(struct xb_req_data *req) if (req->err) return ERR_PTR(req->err); - } + } while (req->state != xb_req_state_got_reply); return req->body; } diff --git a/fs/afs/addr_list.c b/fs/afs/addr_list.c index df415c05939e7ad4f5d7716d68e4f2bead7eecf7..de1ae0bead3baf9192bde373287924c3b0d500fd 100644 --- a/fs/afs/addr_list.c +++ b/fs/afs/addr_list.c @@ -19,7 +19,7 @@ void afs_put_addrlist(struct afs_addr_list *alist) { if (alist && refcount_dec_and_test(&alist->usage)) - call_rcu(&alist->rcu, (rcu_callback_t)kfree); + kfree_rcu(alist, rcu); } /* diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 1d81fc4c3058c328fcbdbe960dafd1a553b26661..35f951ac296f47edbf04dbdd847270b61b757288 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -81,7 +81,7 @@ enum afs_call_state { * List of server addresses. */ struct afs_addr_list { - struct rcu_head rcu; /* Must be first */ + struct rcu_head rcu; refcount_t usage; u32 version; /* Version */ unsigned char max_addrs; diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 404e050ce8eee36c0142706975b5648dd2af72c9..7f09147872dc718d27f53d033ad280516340c5d2 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -856,9 +856,9 @@ static void clear_incompat_bg_bits(struct btrfs_fs_info *fs_info, u64 flags) found_raid1c34 = true; up_read(&sinfo->groups_sem); } - if (found_raid56) + if (!found_raid56) btrfs_clear_fs_incompat(fs_info, RAID56); - if (found_raid1c34) + if (!found_raid1c34) btrfs_clear_fs_incompat(fs_info, RAID1C34); } } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 7fa9bb79ad08e2c5b732185c902bcbbea549a95f..c6c9a6a8e6c84176c3c8223827fc5fcdc9e6bd79 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3164,6 +3164,7 @@ int __cold open_ctree(struct super_block *sb, /* do not make disk changes in broken FS or nologreplay is given */ if (btrfs_super_log_root(disk_super) != 0 && !btrfs_test_opt(fs_info, NOLOGREPLAY)) { + btrfs_info(fs_info, "start tree-log replay"); ret = btrfs_replay_log(fs_info, fs_devices); if (ret) { err = ret; @@ -3199,6 +3200,7 @@ int __cold open_ctree(struct super_block *sb, if (IS_ERR(fs_info->fs_root)) { err = PTR_ERR(fs_info->fs_root); btrfs_warn(fs_info, "failed to read fs tree: %d", err); + fs_info->fs_root = NULL; goto fail_qgroup; } @@ -4275,6 +4277,7 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, cond_resched(); spin_lock(&delayed_refs->lock); } + btrfs_qgroup_destroy_extent_records(trans); spin_unlock(&delayed_refs->lock); @@ -4500,7 +4503,6 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, wake_up(&fs_info->transaction_wait); btrfs_destroy_delayed_inodes(fs_info); - btrfs_assert_delayed_root_empty(fs_info); btrfs_destroy_marked_extents(fs_info, &cur_trans->dirty_pages, EXTENT_DIRTY); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 0163fdd59f8f2156fd58c65e8bdbceb3ae5dec3a..a7bc66121330e1d4d428c93775c2d832041c7d18 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4430,6 +4430,8 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans, ret = alloc_reserved_file_extent(trans, 0, root_objectid, 0, owner, offset, ins, 1); + if (ret) + btrfs_pin_extent(fs_info, ins->objectid, ins->offset, 1); btrfs_put_block_group(block_group); return ret; } diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 6f417ff68980f68f26eb89b6689a732d15a5b2bf..bd6229fb2b6f0cae346f72afc4324463ccfac578 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -237,6 +237,17 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em) struct extent_map *merge = NULL; struct rb_node *rb; + /* + * We can't modify an extent map that is in the tree and that is being + * used by another task, as it can cause that other task to see it in + * inconsistent state during the merging. We always have 1 reference for + * the tree and 1 for this task (which is unpinning the extent map or + * clearing the logging flag), so anything > 2 means it's being used by + * other tasks too. + */ + if (refcount_read(&em->refs) > 2) + return; + if (em->start != 0) { rb = rb_prev(&em->rb_node); if (rb) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 5b3ec93ff911d7af07127fe3a1824024eedcf511..d267eb5caa7b694a55e733ecd070af5a749a6cc8 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4085,6 +4085,8 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, u64 bytes_deleted = 0; bool be_nice = false; bool should_throttle = false; + const u64 lock_start = ALIGN_DOWN(new_size, fs_info->sectorsize); + struct extent_state *cached_state = NULL; BUG_ON(new_size > 0 && min_type != BTRFS_EXTENT_DATA_KEY); @@ -4101,6 +4103,10 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, return -ENOMEM; path->reada = READA_BACK; + if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) + lock_extent_bits(&BTRFS_I(inode)->io_tree, lock_start, (u64)-1, + &cached_state); + /* * We want to drop from the next block forward in case this new size is * not block aligned since we will be keeping the last block of the @@ -4137,7 +4143,6 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, goto out; } - path->leave_spinning = 1; ret = btrfs_search_slot(trans, root, &key, path, -1, 1); if (ret < 0) goto out; @@ -4289,7 +4294,6 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, root == fs_info->tree_root)) { struct btrfs_ref ref = { 0 }; - btrfs_set_path_blocking(path); bytes_deleted += extent_num_bytes; btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, @@ -4365,6 +4369,8 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, if (!ret && last_size > new_size) last_size = new_size; btrfs_ordered_update_i_size(inode, last_size, NULL); + unlock_extent_cached(&BTRFS_I(inode)->io_tree, lock_start, + (u64)-1, &cached_state); } btrfs_free_path(path); @@ -7777,6 +7783,7 @@ static inline blk_status_t btrfs_lookup_and_bind_dio_csum(struct inode *inode, { struct btrfs_io_bio *io_bio = btrfs_io_bio(bio); struct btrfs_io_bio *orig_io_bio = btrfs_io_bio(dip->orig_bio); + u16 csum_size; blk_status_t ret; /* @@ -7796,7 +7803,8 @@ static inline blk_status_t btrfs_lookup_and_bind_dio_csum(struct inode *inode, file_offset -= dip->logical_offset; file_offset >>= inode->i_sb->s_blocksize_bits; - io_bio->csum = (u8 *)(((u32 *)orig_io_bio->csum) + file_offset); + csum_size = btrfs_super_csum_size(btrfs_sb(inode->i_sb)->super_copy); + io_bio->csum = orig_io_bio->csum + csum_size * file_offset; return 0; } @@ -9488,6 +9496,10 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, ret = btrfs_sync_log(trans, BTRFS_I(old_inode)->root, &ctx); if (ret) commit_transaction = true; + } else if (sync_log) { + mutex_lock(&root->log_mutex); + list_del(&ctx.list); + mutex_unlock(&root->log_mutex); } if (commit_transaction) { ret = btrfs_commit_transaction(trans); @@ -9818,6 +9830,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode, struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_key ins; u64 cur_offset = start; + u64 clear_offset = start; u64 i_size; u64 cur_bytes; u64 last_alloc = (u64)-1; @@ -9852,6 +9865,15 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode, btrfs_end_transaction(trans); break; } + + /* + * We've reserved this space, and thus converted it from + * ->bytes_may_use to ->bytes_reserved. Any error that happens + * from here on out we will only need to clear our reservation + * for the remaining unreserved area, so advance our + * clear_offset by our extent size. + */ + clear_offset += ins.offset; btrfs_dec_block_group_reservations(fs_info, ins.objectid); last_alloc = ins.offset; @@ -9931,9 +9953,9 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode, if (own_trans) btrfs_end_transaction(trans); } - if (cur_offset < end) - btrfs_free_reserved_data_space(inode, NULL, cur_offset, - end - cur_offset + 1); + if (clear_offset < end) + btrfs_free_reserved_data_space(inode, NULL, clear_offset, + end - clear_offset + 1); return ret; } diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index ecb9fb6a6fe07f3550efe9e8bb9de463585930d3..a65f189a5b9418e17e28ef90dfb7508e13b173be 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -679,10 +679,15 @@ int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len) } btrfs_start_ordered_extent(inode, ordered, 1); end = ordered->file_offset; + /* + * If the ordered extent had an error save the error but don't + * exit without waiting first for all other ordered extents in + * the range to complete. + */ if (test_bit(BTRFS_ORDERED_IOERR, &ordered->flags)) ret = -EIO; btrfs_put_ordered_extent(ordered); - if (ret || end == 0 || end == start) + if (end == 0 || end == start) break; end--; } diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 98d9a50352d6d2bf6314cf4dc6720303e53e496e..ff1870ff3474a71f1fada625e17effa09917a074 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -4002,3 +4002,16 @@ int btrfs_qgroup_trace_subtree_after_cow(struct btrfs_trans_handle *trans, } return ret; } + +void btrfs_qgroup_destroy_extent_records(struct btrfs_transaction *trans) +{ + struct btrfs_qgroup_extent_record *entry; + struct btrfs_qgroup_extent_record *next; + struct rb_root *root; + + root = &trans->delayed_refs.dirty_extent_root; + rbtree_postorder_for_each_entry_safe(entry, next, root, node) { + ulist_free(entry->old_roots); + kfree(entry); + } +} diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index 236f12224d5205a591251e317cf996dd23fc1e8c..1bc65445946907c171eccc0fe1363b8ce2f0b754 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -414,5 +414,6 @@ int btrfs_qgroup_add_swapped_blocks(struct btrfs_trans_handle *trans, u64 last_snapshot); int btrfs_qgroup_trace_subtree_after_cow(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *eb); +void btrfs_qgroup_destroy_extent_records(struct btrfs_transaction *trans); #endif diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c index b57f3618e58e305f5520dbf7f472df816180b8e4..454a1015d026b741ec1a1b168375755d6df5971a 100644 --- a/fs/btrfs/ref-verify.c +++ b/fs/btrfs/ref-verify.c @@ -744,6 +744,7 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info, */ be = add_block_entry(fs_info, bytenr, num_bytes, ref_root); if (IS_ERR(be)) { + kfree(ref); kfree(ra); ret = PTR_ERR(be); goto out; @@ -757,6 +758,8 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info, "re-allocated a block that still has references to it!"); dump_block_entry(fs_info, be); dump_ref_action(fs_info, ra); + kfree(ref); + kfree(ra); goto out_unlock; } @@ -819,6 +822,7 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info, "dropping a ref for a existing root that doesn't have a ref on the block"); dump_block_entry(fs_info, be); dump_ref_action(fs_info, ra); + kfree(ref); kfree(ra); goto out_unlock; } @@ -834,6 +838,7 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info, "attempting to add another ref for an existing ref on a tree block"); dump_block_entry(fs_info, be); dump_ref_action(fs_info, ra); + kfree(ref); kfree(ra); goto out_unlock; } diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 0616a5434793d100ffa1db67c0afe961c687ba51..67c63858812a9ebc8e3e9448df46968b58c3c3bd 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1834,6 +1834,8 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) } if (btrfs_super_log_root(fs_info->super_copy) != 0) { + btrfs_warn(fs_info, + "mount required to replay tree-log, cannot remount read-write"); ret = -EINVAL; goto restore; } diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 7436422194da32503d87aea85cf3d116f16eb78a..3c10e78924d04db95ad6c70c5f9e194557be5100 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -901,6 +901,12 @@ static int addrm_unknown_feature_attrs(struct btrfs_fs_info *fs_info, bool add) static void __btrfs_sysfs_remove_fsid(struct btrfs_fs_devices *fs_devs) { + if (fs_devs->devinfo_kobj) { + kobject_del(fs_devs->devinfo_kobj); + kobject_put(fs_devs->devinfo_kobj); + fs_devs->devinfo_kobj = NULL; + } + if (fs_devs->devices_kobj) { kobject_del(fs_devs->devices_kobj); kobject_put(fs_devs->devices_kobj); @@ -1289,7 +1295,7 @@ int btrfs_sysfs_add_device_link(struct btrfs_fs_devices *fs_devices, init_completion(&dev->kobj_unregister); error = kobject_init_and_add(&dev->devid_kobj, &devid_ktype, - fs_devices->devices_kobj, "%llu", + fs_devices->devinfo_kobj, "%llu", dev->devid); if (error) { kobject_put(&dev->devid_kobj); @@ -1369,6 +1375,15 @@ int btrfs_sysfs_add_fsid(struct btrfs_fs_devices *fs_devs) return -ENOMEM; } + fs_devs->devinfo_kobj = kobject_create_and_add("devinfo", + &fs_devs->fsid_kobj); + if (!fs_devs->devinfo_kobj) { + btrfs_err(fs_devs->fs_info, + "failed to init sysfs devinfo kobject"); + btrfs_sysfs_remove_fsid(fs_devs); + return -ENOMEM; + } + return 0; } diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 33dcc88b428ad402ed68c1dd6bbfb9dc9ee69d23..beb6c69cd1e55b7d0fb3089b4822269fb6bce38c 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -121,6 +121,8 @@ void btrfs_put_transaction(struct btrfs_transaction *transaction) BUG_ON(!list_empty(&transaction->list)); WARN_ON(!RB_EMPTY_ROOT( &transaction->delayed_refs.href_root.rb_root)); + WARN_ON(!RB_EMPTY_ROOT( + &transaction->delayed_refs.dirty_extent_root)); if (transaction->delayed_refs.pending_csums) btrfs_err(transaction->fs_info, "pending csums is %llu", diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 409f4816fb89c458e9dec591b0951d79816dd7d1..f01552a0785eb2e570f53a551fb69458b866a937 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -258,6 +258,7 @@ struct btrfs_fs_devices { /* sysfs kobjects */ struct kobject fsid_kobj; struct kobject *devices_kobj; + struct kobject *devinfo_kobj; struct completion kobj_unregister; }; diff --git a/fs/ceph/file.c b/fs/ceph/file.c index c3b8e8e0bf17d52c1c2bd90ba093813e22d71906..7e0190b1f821e73a33d252b9e8491bba3cdcaf16 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -1418,6 +1418,7 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from) struct ceph_cap_flush *prealloc_cf; ssize_t count, written = 0; int err, want, got; + bool direct_lock = false; loff_t pos; loff_t limit = max(i_size_read(inode), fsc->max_file_size); @@ -1428,8 +1429,11 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from) if (!prealloc_cf) return -ENOMEM; + if ((iocb->ki_flags & (IOCB_DIRECT | IOCB_APPEND)) == IOCB_DIRECT) + direct_lock = true; + retry_snap: - if (iocb->ki_flags & IOCB_DIRECT) + if (direct_lock) ceph_start_io_direct(inode); else ceph_start_io_write(inode); @@ -1519,14 +1523,15 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from) /* we might need to revert back to that point */ data = *from; - if (iocb->ki_flags & IOCB_DIRECT) { + if (iocb->ki_flags & IOCB_DIRECT) written = ceph_direct_read_write(iocb, &data, snapc, &prealloc_cf); - ceph_end_io_direct(inode); - } else { + else written = ceph_sync_write(iocb, &data, pos, snapc); + if (direct_lock) + ceph_end_io_direct(inode); + else ceph_end_io_write(inode); - } if (written > 0) iov_iter_advance(from, written); ceph_put_snap_context(snapc); @@ -1577,7 +1582,7 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from) goto out_unlocked; out: - if (iocb->ki_flags & IOCB_DIRECT) + if (direct_lock) ceph_end_io_direct(inode); else ceph_end_io_write(inode); diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 1d9f083b8a1153f361a6abff6dd8370aad23b587..c7f150686a53d41295f0e6a1b718d81e7a587344 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -202,6 +202,26 @@ struct ceph_parse_opts_ctx { struct ceph_mount_options *opts; }; +/* + * Remove adjacent slashes and then the trailing slash, unless it is + * the only remaining character. + * + * E.g. "//dir1////dir2///" --> "/dir1/dir2", "///" --> "/". + */ +static void canonicalize_path(char *path) +{ + int i, j = 0; + + for (i = 0; path[i] != '\0'; i++) { + if (path[i] != '/' || j < 1 || path[j - 1] != '/') + path[j++] = path[i]; + } + + if (j > 1 && path[j - 1] == '/') + j--; + path[j] = '\0'; +} + /* * Parse the source parameter. Distinguish the server list from the path. * @@ -224,15 +244,16 @@ static int ceph_parse_source(struct fs_parameter *param, struct fs_context *fc) dev_name_end = strchr(dev_name, '/'); if (dev_name_end) { - kfree(fsopt->server_path); - /* * The server_path will include the whole chars from userland * including the leading '/'. */ + kfree(fsopt->server_path); fsopt->server_path = kstrdup(dev_name_end, GFP_KERNEL); if (!fsopt->server_path) return -ENOMEM; + + canonicalize_path(fsopt->server_path); } else { dev_name_end = dev_name + strlen(dev_name); } @@ -456,73 +477,6 @@ static int strcmp_null(const char *s1, const char *s2) return strcmp(s1, s2); } -/** - * path_remove_extra_slash - Remove the extra slashes in the server path - * @server_path: the server path and could be NULL - * - * Return NULL if the path is NULL or only consists of "/", or a string - * without any extra slashes including the leading slash(es) and the - * slash(es) at the end of the server path, such as: - * "//dir1////dir2///" --> "dir1/dir2" - */ -static char *path_remove_extra_slash(const char *server_path) -{ - const char *path = server_path; - const char *cur, *end; - char *buf, *p; - int len; - - /* if the server path is omitted */ - if (!path) - return NULL; - - /* remove all the leading slashes */ - while (*path == '/') - path++; - - /* if the server path only consists of slashes */ - if (*path == '\0') - return NULL; - - len = strlen(path); - - buf = kmalloc(len + 1, GFP_KERNEL); - if (!buf) - return ERR_PTR(-ENOMEM); - - end = path + len; - p = buf; - do { - cur = strchr(path, '/'); - if (!cur) - cur = end; - - len = cur - path; - - /* including one '/' */ - if (cur != end) - len += 1; - - memcpy(p, path, len); - p += len; - - while (cur <= end && *cur == '/') - cur++; - path = cur; - } while (path < end); - - *p = '\0'; - - /* - * remove the last slash if there has and just to make sure that - * we will get something like "dir1/dir2" - */ - if (*(--p) == '/') - *p = '\0'; - - return buf; -} - static int compare_mount_options(struct ceph_mount_options *new_fsopt, struct ceph_options *new_opt, struct ceph_fs_client *fsc) @@ -530,7 +484,6 @@ static int compare_mount_options(struct ceph_mount_options *new_fsopt, struct ceph_mount_options *fsopt1 = new_fsopt; struct ceph_mount_options *fsopt2 = fsc->mount_options; int ofs = offsetof(struct ceph_mount_options, snapdir_name); - char *p1, *p2; int ret; ret = memcmp(fsopt1, fsopt2, ofs); @@ -540,21 +493,12 @@ static int compare_mount_options(struct ceph_mount_options *new_fsopt, ret = strcmp_null(fsopt1->snapdir_name, fsopt2->snapdir_name); if (ret) return ret; + ret = strcmp_null(fsopt1->mds_namespace, fsopt2->mds_namespace); if (ret) return ret; - p1 = path_remove_extra_slash(fsopt1->server_path); - if (IS_ERR(p1)) - return PTR_ERR(p1); - p2 = path_remove_extra_slash(fsopt2->server_path); - if (IS_ERR(p2)) { - kfree(p1); - return PTR_ERR(p2); - } - ret = strcmp_null(p1, p2); - kfree(p1); - kfree(p2); + ret = strcmp_null(fsopt1->server_path, fsopt2->server_path); if (ret) return ret; @@ -957,7 +901,9 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc, mutex_lock(&fsc->client->mount_mutex); if (!fsc->sb->s_root) { - const char *path, *p; + const char *path = fsc->mount_options->server_path ? + fsc->mount_options->server_path + 1 : ""; + err = __ceph_open_session(fsc->client, started); if (err < 0) goto out; @@ -969,22 +915,11 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc, goto out; } - p = path_remove_extra_slash(fsc->mount_options->server_path); - if (IS_ERR(p)) { - err = PTR_ERR(p); - goto out; - } - /* if the server path is omitted or just consists of '/' */ - if (!p) - path = ""; - else - path = p; dout("mount opening path '%s'\n", path); ceph_fs_debugfs_init(fsc); root = open_root_dentry(fsc, path, started); - kfree(p); if (IS_ERR(root)) { err = PTR_ERR(root); goto out; @@ -1097,10 +1032,6 @@ static int ceph_get_tree(struct fs_context *fc) if (!fc->source) return invalfc(fc, "No source"); -#ifdef CONFIG_CEPH_FS_POSIX_ACL - fc->sb_flags |= SB_POSIXACL; -#endif - /* create client (which we may/may not use) */ fsc = create_fs_client(pctx->opts, pctx->copts); pctx->opts = NULL; @@ -1223,6 +1154,10 @@ static int ceph_init_fs_context(struct fs_context *fc) fsopt->max_readdir_bytes = CEPH_MAX_READDIR_BYTES_DEFAULT; fsopt->congestion_kb = default_congestion_kb(); +#ifdef CONFIG_CEPH_FS_POSIX_ACL + fc->sb_flags |= SB_POSIXACL; +#endif + fc->fs_private = pctx; fc->ops = &ceph_context_ops; return 0; diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 1e456a9011bb73f5717a08cfe4128ae41bda1f59..037cdfb2ad4f51c71885abf93d1d0a1a0ebfccbc 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -91,7 +91,7 @@ struct ceph_mount_options { char *snapdir_name; /* default ".snap" */ char *mds_namespace; /* default NULL */ - char *server_path; /* default "/" */ + char *server_path; /* default NULL (means "/") */ char *fscache_uniq; /* default NULL */ }; diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c index 606f26d862dc18b1326e5c3cf4a9e1c9a746ac70..cc3ada12848d952466cedf9eb1c8dc03abcc1eae 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/cifs/cifs_dfs_ref.c @@ -324,6 +324,8 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt) if (full_path == NULL) goto cdda_exit; + convert_delimiter(full_path, '\\'); + cifs_dbg(FYI, "%s: full_path: %s\n", __func__, full_path); if (!cifs_sb_master_tlink(cifs_sb)) { diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index 440828afcddef783d6d3edf087ddede0f3974b02..716574aab3b6a88c823a1511569511bb6491a94a 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -601,7 +601,7 @@ static void access_flags_to_mode(__le32 ace_flags, int type, umode_t *pmode, ((flags & FILE_EXEC_RIGHTS) == FILE_EXEC_RIGHTS)) *pmode |= (S_IXUGO & (*pbits_to_set)); - cifs_dbg(NOISY, "access flags 0x%x mode now 0x%x\n", flags, *pmode); + cifs_dbg(NOISY, "access flags 0x%x mode now %04o\n", flags, *pmode); return; } @@ -630,7 +630,7 @@ static void mode_to_access_flags(umode_t mode, umode_t bits_to_use, if (mode & S_IXUGO) *pace_flags |= SET_FILE_EXEC_RIGHTS; - cifs_dbg(NOISY, "mode: 0x%x, access flags now 0x%x\n", + cifs_dbg(NOISY, "mode: %04o, access flags now 0x%x\n", mode, *pace_flags); return; } diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index febab27cd8389c5c4149894d3cb47e5845249c95..fa77fe5258b0726ced3bc4a29180590a93c12aaf 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -414,7 +414,7 @@ cifs_show_security(struct seq_file *s, struct cifs_ses *ses) seq_puts(s, "ntlm"); break; case Kerberos: - seq_printf(s, "krb5,cruid=%u", from_kuid_munged(&init_user_ns,ses->cred_uid)); + seq_puts(s, "krb5"); break; case RawNTLMSSP: seq_puts(s, "ntlmssp"); @@ -427,6 +427,10 @@ cifs_show_security(struct seq_file *s, struct cifs_ses *ses) if (ses->sign) seq_puts(s, "i"); + + if (ses->sectype == Kerberos) + seq_printf(s, ",cruid=%u", + from_kuid_munged(&init_user_ns, ses->cred_uid)); } static void @@ -526,6 +530,8 @@ cifs_show_options(struct seq_file *s, struct dentry *root) if (tcon->seal) seq_puts(s, ",seal"); + else if (tcon->ses->server->ignore_signature) + seq_puts(s, ",signloosely"); if (tcon->nocase) seq_puts(s, ",nocase"); if (tcon->local_lease) diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index de82cfa44b1ae6e65ac5859676d729513352fab1..0d956360e984724224a5d28333936499107dd5a5 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -1281,6 +1281,7 @@ struct cifs_fid { __u64 volatile_fid; /* volatile file id for smb2 */ __u8 lease_key[SMB2_LEASE_KEY_SIZE]; /* lease key for smb2 */ __u8 create_guid[16]; + __u32 access; struct cifs_pending_open *pending_open; unsigned int epoch; #ifdef CONFIG_CIFS_DEBUG2 @@ -1741,6 +1742,12 @@ static inline bool is_retryable_error(int error) return false; } + +/* cifs_get_writable_file() flags */ +#define FIND_WR_ANY 0 +#define FIND_WR_FSUID_ONLY 1 +#define FIND_WR_WITH_DELETE 2 + #define MID_FREE 0 #define MID_REQUEST_ALLOCATED 1 #define MID_REQUEST_SUBMITTED 2 diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index 89eaaf46d1cadcab1c719b671d774a0a92efa12e..e5cb681ec13815aacd59dd3a3ce751ba06358765 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -134,11 +134,12 @@ extern bool backup_cred(struct cifs_sb_info *); extern bool is_size_safe_to_change(struct cifsInodeInfo *, __u64 eof); extern void cifs_update_eof(struct cifsInodeInfo *cifsi, loff_t offset, unsigned int bytes_written); -extern struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *, bool); +extern struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *, int); extern int cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, - bool fsuid_only, + int flags, struct cifsFileInfo **ret_file); extern int cifs_get_writable_path(struct cifs_tcon *tcon, const char *name, + int flags, struct cifsFileInfo **ret_file); extern struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *, bool); extern int cifs_get_readable_path(struct cifs_tcon *tcon, const char *name, diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 3c89569e721082895ebcba2f7f4bb33d584ec901..6f6fb3606a5d6094b498c99851d21d81b135b952 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -1492,6 +1492,7 @@ CIFS_open(const unsigned int xid, struct cifs_open_parms *oparms, int *oplock, *oplock = rsp->OplockLevel; /* cifs fid stays in le */ oparms->fid->netfid = rsp->Fid; + oparms->fid->access = desired_access; /* Let caller know file was created so we can set the mode. */ /* Do we care about the CreateAction in any other cases? */ @@ -2115,7 +2116,7 @@ cifs_writev_requeue(struct cifs_writedata *wdata) wdata2->tailsz = tailsz; wdata2->bytes = cur_len; - rc = cifs_get_writable_file(CIFS_I(inode), false, + rc = cifs_get_writable_file(CIFS_I(inode), FIND_WR_ANY, &wdata2->cfile); if (!wdata2->cfile) { cifs_dbg(VFS, "No writable handle to retry writepages rc=%d\n", diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index a941ac7a659d9d748799b87c460486cc00997b75..4804d1df8c1cfb675012f214f9fbc906bb6de1e3 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -4151,7 +4151,7 @@ int cifs_setup_cifs_sb(struct smb_vol *pvolume_info, cifs_sb->mnt_gid = pvolume_info->linux_gid; cifs_sb->mnt_file_mode = pvolume_info->file_mode; cifs_sb->mnt_dir_mode = pvolume_info->dir_mode; - cifs_dbg(FYI, "file mode: 0x%hx dir mode: 0x%hx\n", + cifs_dbg(FYI, "file mode: %04ho dir mode: %04ho\n", cifs_sb->mnt_file_mode, cifs_sb->mnt_dir_mode); cifs_sb->actimeo = pvolume_info->actimeo; diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 0ef099442f209c779a1b2e3588cbaade5cf173c3..36e7b2fd2190b32462eba9c65c424408a15d0fe6 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -555,7 +555,6 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry, if (server->ops->close) server->ops->close(xid, tcon, &fid); cifs_del_pending_open(&open); - fput(file); rc = -ENOMEM; } diff --git a/fs/cifs/file.c b/fs/cifs/file.c index bc9516ab4b34f22281f52056efab27b117afa558..8f9d849a00125c5a21dcbe6fa904b3d5df133f7c 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1169,7 +1169,8 @@ cifs_posix_lock_set(struct file *file, struct file_lock *flock) rc = posix_lock_file(file, flock, NULL); up_write(&cinode->lock_sem); if (rc == FILE_LOCK_DEFERRED) { - rc = wait_event_interruptible(flock->fl_wait, !flock->fl_blocker); + rc = wait_event_interruptible(flock->fl_wait, + list_empty(&flock->fl_blocked_member)); if (!rc) goto try_again; locks_delete_block(flock); @@ -1958,7 +1959,7 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode, /* Return -EBADF if no handle is found and general rc otherwise */ int -cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, bool fsuid_only, +cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, int flags, struct cifsFileInfo **ret_file) { struct cifsFileInfo *open_file, *inv_file = NULL; @@ -1966,7 +1967,8 @@ cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, bool fsuid_only, bool any_available = false; int rc = -EBADF; unsigned int refind = 0; - + bool fsuid_only = flags & FIND_WR_FSUID_ONLY; + bool with_delete = flags & FIND_WR_WITH_DELETE; *ret_file = NULL; /* @@ -1998,6 +2000,8 @@ cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, bool fsuid_only, continue; if (fsuid_only && !uid_eq(open_file->uid, current_fsuid())) continue; + if (with_delete && !(open_file->fid.access & DELETE)) + continue; if (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE) { if (!open_file->invalidHandle) { /* found a good writable file */ @@ -2045,12 +2049,12 @@ cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, bool fsuid_only, } struct cifsFileInfo * -find_writable_file(struct cifsInodeInfo *cifs_inode, bool fsuid_only) +find_writable_file(struct cifsInodeInfo *cifs_inode, int flags) { struct cifsFileInfo *cfile; int rc; - rc = cifs_get_writable_file(cifs_inode, fsuid_only, &cfile); + rc = cifs_get_writable_file(cifs_inode, flags, &cfile); if (rc) cifs_dbg(FYI, "couldn't find writable handle rc=%d", rc); @@ -2059,6 +2063,7 @@ find_writable_file(struct cifsInodeInfo *cifs_inode, bool fsuid_only) int cifs_get_writable_path(struct cifs_tcon *tcon, const char *name, + int flags, struct cifsFileInfo **ret_file) { struct list_head *tmp; @@ -2085,7 +2090,7 @@ cifs_get_writable_path(struct cifs_tcon *tcon, const char *name, kfree(full_path); cinode = CIFS_I(d_inode(cfile->dentry)); spin_unlock(&tcon->open_file_lock); - return cifs_get_writable_file(cinode, 0, ret_file); + return cifs_get_writable_file(cinode, flags, ret_file); } spin_unlock(&tcon->open_file_lock); @@ -2162,7 +2167,8 @@ static int cifs_partialpagewrite(struct page *page, unsigned from, unsigned to) if (mapping->host->i_size - offset < (loff_t)to) to = (unsigned)(mapping->host->i_size - offset); - rc = cifs_get_writable_file(CIFS_I(mapping->host), false, &open_file); + rc = cifs_get_writable_file(CIFS_I(mapping->host), FIND_WR_ANY, + &open_file); if (!rc) { bytes_written = cifs_write(open_file, open_file->pid, write_data, to - from, &offset); @@ -2355,7 +2361,7 @@ static int cifs_writepages(struct address_space *mapping, if (cfile) cifsFileInfo_put(cfile); - rc = cifs_get_writable_file(CIFS_I(inode), false, &cfile); + rc = cifs_get_writable_file(CIFS_I(inode), FIND_WR_ANY, &cfile); /* in case of an error store it to return later */ if (rc) diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 9ba623b601ec2b913d5753240b6c87e2c25dc8ef..b16f8d23e97b58d51b756a4b35e1995dc195120d 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -653,8 +653,8 @@ cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info, */ if ((fattr->cf_nlink < 1) && !tcon->unix_ext && !info->DeletePending) { - cifs_dbg(1, "bogus file nlink value %u\n", - fattr->cf_nlink); + cifs_dbg(VFS, "bogus file nlink value %u\n", + fattr->cf_nlink); fattr->cf_flags |= CIFS_FATTR_UNKNOWN_NLINK; } } @@ -1648,7 +1648,7 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, umode_t mode) struct TCP_Server_Info *server; char *full_path; - cifs_dbg(FYI, "In cifs_mkdir, mode = 0x%hx inode = 0x%p\n", + cifs_dbg(FYI, "In cifs_mkdir, mode = %04ho inode = 0x%p\n", mode, inode); cifs_sb = CIFS_SB(inode->i_sb); @@ -2073,6 +2073,7 @@ int cifs_revalidate_dentry_attr(struct dentry *dentry) struct inode *inode = d_inode(dentry); struct super_block *sb = dentry->d_sb; char *full_path = NULL; + int count = 0; if (inode == NULL) return -ENOENT; @@ -2094,15 +2095,18 @@ int cifs_revalidate_dentry_attr(struct dentry *dentry) full_path, inode, inode->i_count.counter, dentry, cifs_get_time(dentry), jiffies); +again: if (cifs_sb_master_tcon(CIFS_SB(sb))->unix_ext) rc = cifs_get_inode_info_unix(&inode, full_path, sb, xid); else rc = cifs_get_inode_info(&inode, full_path, NULL, sb, xid, NULL); - + if (rc == -EAGAIN && count++ < 10) + goto again; out: kfree(full_path); free_xid(xid); + return rc; } @@ -2187,7 +2191,7 @@ int cifs_getattr(const struct path *path, struct kstat *stat, if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID)) stat->gid = current_fsgid(); } - return rc; + return 0; } int cifs_fiemap(struct inode *inode, struct fiemap_extent_info *fei, u64 start, @@ -2278,7 +2282,7 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs, * writebehind data than the SMB timeout for the SetPathInfo * request would allow */ - open_file = find_writable_file(cifsInode, true); + open_file = find_writable_file(cifsInode, FIND_WR_FSUID_ONLY); if (open_file) { tcon = tlink_tcon(open_file->tlink); server = tcon->ses->server; @@ -2428,7 +2432,7 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) args->ctime = NO_CHANGE_64; args->device = 0; - open_file = find_writable_file(cifsInode, true); + open_file = find_writable_file(cifsInode, FIND_WR_FSUID_ONLY); if (open_file) { u16 nfid = open_file->fid.netfid; u32 npid = open_file->pid; @@ -2531,7 +2535,7 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) rc = 0; if (attrs->ia_valid & ATTR_MTIME) { - rc = cifs_get_writable_file(cifsInode, false, &wfile); + rc = cifs_get_writable_file(cifsInode, FIND_WR_ANY, &wfile); if (!rc) { tcon = tlink_tcon(wfile->tlink); rc = tcon->ses->server->ops->flush(xid, tcon, &wfile->fid); diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index eb994e313c6ae755437f375db1b1bb662c90db75..b130efaf8feb2260da9f4d00fee30fa6e53e599a 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -766,7 +766,7 @@ smb_set_file_info(struct inode *inode, const char *full_path, struct cifs_tcon *tcon; /* if the file is already open for write, just use that fileid */ - open_file = find_writable_file(cinode, true); + open_file = find_writable_file(cinode, FIND_WR_FSUID_ONLY); if (open_file) { fid.netfid = open_file->fid.netfid; netpid = open_file->pid; diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c index 1cf207564ff9676b6901e951a812267380effe10..a8c301ae00ed72f2bbcbbf0f3bf0bf6dfce0e29b 100644 --- a/fs/cifs/smb2inode.c +++ b/fs/cifs/smb2inode.c @@ -521,7 +521,7 @@ smb2_mkdir_setinfo(struct inode *inode, const char *name, cifs_i = CIFS_I(inode); dosattrs = cifs_i->cifsAttrs | ATTR_READONLY; data.Attributes = cpu_to_le32(dosattrs); - cifs_get_writable_path(tcon, name, &cfile); + cifs_get_writable_path(tcon, name, FIND_WR_ANY, &cfile); tmprc = smb2_compound_op(xid, tcon, cifs_sb, name, FILE_WRITE_ATTRIBUTES, FILE_CREATE, CREATE_NOT_FILE, ACL_NO_MODE, @@ -577,7 +577,7 @@ smb2_rename_path(const unsigned int xid, struct cifs_tcon *tcon, { struct cifsFileInfo *cfile; - cifs_get_writable_path(tcon, from_name, &cfile); + cifs_get_writable_path(tcon, from_name, FIND_WR_WITH_DELETE, &cfile); return smb2_set_path_attr(xid, tcon, from_name, to_name, cifs_sb, DELETE, SMB2_OP_RENAME, cfile); diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index baa825f4cec03899d647fd23528fcca8a3b72020..cfe9b800ea8c2e45ec5eff688a4da5ee181f694f 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -1116,7 +1116,8 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, void *data[1]; struct smb2_file_full_ea_info *ea = NULL; struct kvec close_iov[1]; - int rc; + struct smb2_query_info_rsp *rsp; + int rc, used_len = 0; if (smb3_encryption_required(tcon)) flags |= CIFS_TRANSFORM_REQ; @@ -1139,6 +1140,38 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, cifs_sb); if (rc == -ENODATA) goto sea_exit; + } else { + /* If we are adding a attribute we should first check + * if there will be enough space available to store + * the new EA. If not we should not add it since we + * would not be able to even read the EAs back. + */ + rc = smb2_query_info_compound(xid, tcon, utf16_path, + FILE_READ_EA, + FILE_FULL_EA_INFORMATION, + SMB2_O_INFO_FILE, + CIFSMaxBufSize - + MAX_SMB2_CREATE_RESPONSE_SIZE - + MAX_SMB2_CLOSE_RESPONSE_SIZE, + &rsp_iov[1], &resp_buftype[1], cifs_sb); + if (rc == 0) { + rsp = (struct smb2_query_info_rsp *)rsp_iov[1].iov_base; + used_len = le32_to_cpu(rsp->OutputBufferLength); + } + free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base); + resp_buftype[1] = CIFS_NO_BUFFER; + memset(&rsp_iov[1], 0, sizeof(rsp_iov[1])); + rc = 0; + + /* Use a fudge factor of 256 bytes in case we collide + * with a different set_EAs command. + */ + if(CIFSMaxBufSize - MAX_SMB2_CREATE_RESPONSE_SIZE - + MAX_SMB2_CLOSE_RESPONSE_SIZE - 256 < + used_len + ea_name_len + ea_value_len + 1) { + rc = -ENOSPC; + goto sea_exit; + } } } @@ -1331,6 +1364,7 @@ smb2_set_fid(struct cifsFileInfo *cfile, struct cifs_fid *fid, __u32 oplock) cfile->fid.persistent_fid = fid->persistent_fid; cfile->fid.volatile_fid = fid->volatile_fid; + cfile->fid.access = fid->access; #ifdef CONFIG_CIFS_DEBUG2 cfile->fid.mid = fid->mid; #endif /* CIFS_DEBUG2 */ @@ -2188,6 +2222,8 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon, goto qdf_free; } + atomic_inc(&tcon->num_remote_opens); + qd_rsp = (struct smb2_query_directory_rsp *)rsp_iov[1].iov_base; if (qd_rsp->sync_hdr.Status == STATUS_NO_MORE_FILES) { trace_smb3_query_dir_done(xid, fid->persistent_fid, @@ -3294,7 +3330,7 @@ static loff_t smb3_llseek(struct file *file, struct cifs_tcon *tcon, loff_t offs * some servers (Windows2016) will not reflect recent writes in * QUERY_ALLOCATED_RANGES until SMB2_flush is called. */ - wrcfile = find_writable_file(cifsi, false); + wrcfile = find_writable_file(cifsi, FIND_WR_ANY); if (wrcfile) { filemap_write_and_wait(inode->i_mapping); smb2_flush_file(xid, tcon, &wrcfile->fid); @@ -3383,7 +3419,7 @@ static int smb3_fiemap(struct cifs_tcon *tcon, if (rc) goto out; - if (out_data_len < sizeof(struct file_allocated_range_buffer)) { + if (out_data_len && out_data_len < sizeof(struct file_allocated_range_buffer)) { rc = -EINVAL; goto out; } @@ -4795,6 +4831,7 @@ struct smb_version_operations smb21_operations = { .wp_retry_size = smb2_wp_retry_size, .dir_needs_close = smb2_dir_needs_close, .enum_snapshots = smb3_enum_snapshots, + .notify = smb3_notify, .get_dfs_refer = smb2_get_dfs_refer, .select_sectype = smb2_select_sectype, #ifdef CONFIG_CIFS_XATTR diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 1234f9ccab0302b5df63a320f12bf7f397be26c9..28c0be5e69b7fcef9683621f353e4142284edbbe 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -2771,6 +2771,7 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, atomic_inc(&tcon->num_remote_opens); oparms->fid->persistent_fid = rsp->PersistentFileId; oparms->fid->volatile_fid = rsp->VolatileFileId; + oparms->fid->access = oparms->desired_access; #ifdef CONFIG_CIFS_DEBUG2 oparms->fid->mid = le64_to_cpu(rsp->sync_hdr.MessageId); #endif /* CIFS_DEBUG2 */ diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c index 65cb09fa6ead922e87f62a9c20d0e04372f583f2..08c9f216a54dda778edd44152cfabe0385539ef5 100644 --- a/fs/crypto/keysetup.c +++ b/fs/crypto/keysetup.c @@ -538,6 +538,15 @@ int fscrypt_drop_inode(struct inode *inode) return 0; mk = ci->ci_master_key->payload.data[0]; + /* + * With proper, non-racy use of FS_IOC_REMOVE_ENCRYPTION_KEY, all inodes + * protected by the key were cleaned by sync_filesystem(). But if + * userspace is still using the files, inodes can be dirtied between + * then and now. We mustn't lose any writes, so skip dirty inodes here. + */ + if (inode->i_state & I_DIRTY_ALL) + return 0; + /* * Note: since we aren't holding ->mk_secret_sem, the result here can * immediately become outdated. But there's no correctness problem with diff --git a/fs/dax.c b/fs/dax.c index 1f1f0201cad1821a2e2883a10821b02e209a8f11..35da144375a0ad91ed600c06c04b5fc9bf13562b 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -937,12 +937,11 @@ static int dax_writeback_one(struct xa_state *xas, struct dax_device *dax_dev, * on persistent storage prior to completion of the operation. */ int dax_writeback_mapping_range(struct address_space *mapping, - struct block_device *bdev, struct writeback_control *wbc) + struct dax_device *dax_dev, struct writeback_control *wbc) { XA_STATE(xas, &mapping->i_pages, wbc->range_start >> PAGE_SHIFT); struct inode *inode = mapping->host; pgoff_t end_index = wbc->range_end >> PAGE_SHIFT; - struct dax_device *dax_dev; void *entry; int ret = 0; unsigned int scanned = 0; @@ -953,10 +952,6 @@ int dax_writeback_mapping_range(struct address_space *mapping, if (!mapping->nrexceptional || wbc->sync_mode != WB_SYNC_ALL) return 0; - dax_dev = dax_get_by_host(bdev->bd_disk->disk_name); - if (!dax_dev) - return -EIO; - trace_dax_writeback_range(inode, xas.xa_index, end_index); tag_pages_for_writeback(mapping, xas.xa_index, end_index); @@ -977,7 +972,6 @@ int dax_writeback_mapping_range(struct address_space *mapping, xas_lock_irq(&xas); } xas_unlock_irq(&xas); - put_dax(dax_dev); trace_dax_writeback_range_done(inode, xas.xa_index, end_index); return ret; } @@ -1207,6 +1201,9 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, lockdep_assert_held(&inode->i_rwsem); } + if (iocb->ki_flags & IOCB_NOWAIT) + flags |= IOMAP_NOWAIT; + while (iov_iter_count(iter)) { ret = iomap_apply(inode, pos, iov_iter_count(iter), flags, ops, iter, dax_iomap_actor); diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 634b09d18b77f46f5a24f0cd0f75ab8fae0e7876..db987b5110a9966d9d06cd4a4f34292efc87d999 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -1090,21 +1090,12 @@ static const struct file_operations fops_regset32 = { * This function creates a file in debugfs with the given name that reports * the names and values of a set of 32-bit registers. If the @mode variable * is so set it can be read from. Writing is not supported. - * - * This function will return a pointer to a dentry if it succeeds. This - * pointer must be passed to the debugfs_remove() function when the file is - * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, ERR_PTR(-ERROR) will be - * returned. - * - * If debugfs is not enabled in the kernel, the value ERR_PTR(-ENODEV) will - * be returned. */ -struct dentry *debugfs_create_regset32(const char *name, umode_t mode, - struct dentry *parent, - struct debugfs_regset32 *regset) +void debugfs_create_regset32(const char *name, umode_t mode, + struct dentry *parent, + struct debugfs_regset32 *regset) { - return debugfs_create_file(name, mode, parent, regset, &fops_regset32); + debugfs_create_file(name, mode, parent, regset, &fops_regset32); } EXPORT_SYMBOL_GPL(debugfs_create_regset32); diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index db1ef144c63a52327c070f7efa2ce44acce6ba6d..2c449aed1b9209e708c049accbab3050604eb100 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -311,8 +311,10 @@ static int crypt_scatterlist(struct ecryptfs_crypt_stat *crypt_stat, struct extent_crypt_result ecr; int rc = 0; - BUG_ON(!crypt_stat || !crypt_stat->tfm - || !(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED)); + if (!crypt_stat || !crypt_stat->tfm + || !(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED)) + return -EINVAL; + if (unlikely(ecryptfs_verbosity > 0)) { ecryptfs_printk(KERN_DEBUG, "Key size [%zd]; key:\n", crypt_stat->key_size); diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h index 1c1a56be7ea2feb35314419f79aa08ceb12dbd62..e6ac78c62ca4929efd9c22465659a7a84b6ec3ee 100644 --- a/fs/ecryptfs/ecryptfs_kernel.h +++ b/fs/ecryptfs/ecryptfs_kernel.h @@ -8,7 +8,7 @@ * Copyright (C) 2004-2008 International Business Machines Corp. * Author(s): Michael A. Halcrow * Trevor S. Highland - * Tyler Hicks + * Tyler Hicks */ #ifndef ECRYPTFS_KERNEL_H diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c index 7d326aa0308e4da493a97f420bca1ce84cb9f272..af3eb02bbca1db90ebbd1d506fa77b3f2afbf79f 100644 --- a/fs/ecryptfs/keystore.c +++ b/fs/ecryptfs/keystore.c @@ -1304,7 +1304,7 @@ parse_tag_1_packet(struct ecryptfs_crypt_stat *crypt_stat, printk(KERN_WARNING "Tag 1 packet contains key larger " "than ECRYPTFS_MAX_ENCRYPTED_KEY_BYTES\n"); rc = -EINVAL; - goto out; + goto out_free; } memcpy((*new_auth_tok)->session_key.encrypted_key, &data[(*packet_size)], (body_size - (ECRYPTFS_SIG_SIZE + 2))); diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index b8a7ce379ffe67f8ab12923a63a2bd1ceb93d156..e63259fdef2882ab5f6a9217dd9bfea95c9a7928 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -7,7 +7,7 @@ * Copyright (C) 2004-2007 International Business Machines Corp. * Author(s): Michael A. Halcrow * Michael C. Thompson - * Tyler Hicks + * Tyler Hicks */ #include diff --git a/fs/ecryptfs/messaging.c b/fs/ecryptfs/messaging.c index d668e60b85b556dd27b08a345a222688b795257c..8646ba76def3416b141f8fe4f54a5812302e7886 100644 --- a/fs/ecryptfs/messaging.c +++ b/fs/ecryptfs/messaging.c @@ -4,7 +4,7 @@ * * Copyright (C) 2004-2008 International Business Machines Corp. * Author(s): Michael A. Halcrow - * Tyler Hicks + * Tyler Hicks */ #include #include @@ -379,6 +379,7 @@ int __init ecryptfs_init_messaging(void) * ecryptfs_message_buf_len), GFP_KERNEL); if (!ecryptfs_msg_ctx_arr) { + kfree(ecryptfs_daemon_hash); rc = -ENOMEM; goto out; } diff --git a/fs/eventpoll.c b/fs/eventpoll.c index b041b66002db7951acb3172105d5568f90b323b4..eee3c92a9ebf85d4d6509018ffa03ed211a3bdc4 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1854,9 +1854,9 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, waiter = true; init_waitqueue_entry(&wait, current); - spin_lock_irq(&ep->wq.lock); + write_lock_irq(&ep->lock); __add_wait_queue_exclusive(&ep->wq, &wait); - spin_unlock_irq(&ep->wq.lock); + write_unlock_irq(&ep->lock); } for (;;) { @@ -1904,9 +1904,9 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, goto fetch_events; if (waiter) { - spin_lock_irq(&ep->wq.lock); + write_lock_irq(&ep->lock); __remove_wait_queue(&ep->wq, &wait); - spin_unlock_irq(&ep->wq.lock); + write_unlock_irq(&ep->lock); } return res; diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 119667e658904aa877b462259ce4bd472f35f054..c885cf7d724b4830d0e952acbc91f0db1b3b1f63 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -960,8 +960,9 @@ ext2_writepages(struct address_space *mapping, struct writeback_control *wbc) static int ext2_dax_writepages(struct address_space *mapping, struct writeback_control *wbc) { - return dax_writeback_mapping_range(mapping, - mapping->host->i_sb->s_bdev, wbc); + struct ext2_sb_info *sbi = EXT2_SB(mapping->host->i_sb); + + return dax_writeback_mapping_range(mapping, sbi->s_daxdev, wbc); } const struct address_space_operations ext2_aops = { diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 5f993a411251fe54635a468aa89e04ff082c3587..8fd0b3cdab4cdd55e7ad0d374064da49bb2d421e 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -270,6 +270,7 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb, ext4_group_t ngroups = ext4_get_groups_count(sb); struct ext4_group_desc *desc; struct ext4_sb_info *sbi = EXT4_SB(sb); + struct buffer_head *bh_p; if (block_group >= ngroups) { ext4_error(sb, "block_group >= groups_count - block_group = %u," @@ -280,7 +281,14 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb, group_desc = block_group >> EXT4_DESC_PER_BLOCK_BITS(sb); offset = block_group & (EXT4_DESC_PER_BLOCK(sb) - 1); - if (!sbi->s_group_desc[group_desc]) { + bh_p = sbi_array_rcu_deref(sbi, s_group_desc, group_desc); + /* + * sbi_array_rcu_deref returns with rcu unlocked, this is ok since + * the pointer being dereferenced won't be dereferenced again. By + * looking at the usage in add_new_gdb() the value isn't modified, + * just the pointer, and so it remains valid. + */ + if (!bh_p) { ext4_error(sb, "Group descriptor not loaded - " "block_group = %u, group_desc = %u, desc = %u", block_group, group_desc, offset); @@ -288,10 +296,10 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb, } desc = (struct ext4_group_desc *)( - (__u8 *)sbi->s_group_desc[group_desc]->b_data + + (__u8 *)bh_p->b_data + offset * EXT4_DESC_SIZE(sb)); if (bh) - *bh = sbi->s_group_desc[group_desc]; + *bh = bh_p; return desc; } diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c index 1ee04e76bbe0404b95d3a0be205266ff5fdcf4f6..0a734ffb4310616afbfc57940b6c989288d6f0fe 100644 --- a/fs/ext4/block_validity.c +++ b/fs/ext4/block_validity.c @@ -207,6 +207,7 @@ static int ext4_protect_reserved_inode(struct super_block *sb, return PTR_ERR(inode); num = (inode->i_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits; while (i < num) { + cond_resched(); map.m_lblk = i; map.m_len = num - i; n = ext4_map_blocks(NULL, inode, &map, 0); diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index 1f340743c9a890152bae85c701a8650d7b76d197..9aa1f75409b02c569ab46a2739790c64f7450123 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -129,12 +129,14 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) if (err != ERR_BAD_DX_DIR) { return err; } - /* - * We don't set the inode dirty flag since it's not - * critical that it get flushed back to the disk. - */ - ext4_clear_inode_flag(file_inode(file), - EXT4_INODE_INDEX); + /* Can we just clear INDEX flag to ignore htree information? */ + if (!ext4_has_metadata_csum(sb)) { + /* + * We don't set the inode dirty flag since it's not + * critical that it gets flushed back to the disk. + */ + ext4_clear_inode_flag(inode, EXT4_INODE_INDEX); + } } if (ext4_has_inline_data(inode)) { diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 9a2ee2428ecc0e5163ef5537a49323fd1dc30d91..61b37a052052b58b577ad617086dbbcdb90b48f3 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1400,7 +1400,7 @@ struct ext4_sb_info { loff_t s_bitmap_maxbytes; /* max bytes for bitmap files */ struct buffer_head * s_sbh; /* Buffer containing the super block */ struct ext4_super_block *s_es; /* Pointer to the super block in the buffer */ - struct buffer_head **s_group_desc; + struct buffer_head * __rcu *s_group_desc; unsigned int s_mount_opt; unsigned int s_mount_opt2; unsigned int s_mount_flags; @@ -1462,7 +1462,7 @@ struct ext4_sb_info { #endif /* for buddy allocator */ - struct ext4_group_info ***s_group_info; + struct ext4_group_info ** __rcu *s_group_info; struct inode *s_buddy_cache; spinlock_t s_md_lock; unsigned short *s_mb_offsets; @@ -1512,7 +1512,7 @@ struct ext4_sb_info { unsigned int s_extent_max_zeroout_kb; unsigned int s_log_groups_per_flex; - struct flex_groups *s_flex_groups; + struct flex_groups * __rcu *s_flex_groups; ext4_group_t s_flex_groups_allocated; /* workqueue for reserved extent conversions (buffered io) */ @@ -1552,8 +1552,11 @@ struct ext4_sb_info { struct ratelimit_state s_warning_ratelimit_state; struct ratelimit_state s_msg_ratelimit_state; - /* Barrier between changing inodes' journal flags and writepages ops. */ - struct percpu_rw_semaphore s_journal_flag_rwsem; + /* + * Barrier between writepages ops and changing any inode's JOURNAL_DATA + * or EXTENTS flag. + */ + struct percpu_rw_semaphore s_writepages_rwsem; struct dax_device *s_daxdev; #ifdef CONFIG_EXT4_DEBUG unsigned long s_simulate_fail; @@ -1576,6 +1579,23 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count)); } +/* + * Returns: sbi->field[index] + * Used to access an array element from the following sbi fields which require + * rcu protection to avoid dereferencing an invalid pointer due to reassignment + * - s_group_desc + * - s_group_info + * - s_flex_group + */ +#define sbi_array_rcu_deref(sbi, field, index) \ +({ \ + typeof(*((sbi)->field)) _v; \ + rcu_read_lock(); \ + _v = ((typeof(_v)*)rcu_dereference((sbi)->field))[index]; \ + rcu_read_unlock(); \ + _v; \ +}) + /* * Simulate_fail codes */ @@ -2544,8 +2564,11 @@ void ext4_insert_dentry(struct inode *inode, struct ext4_filename *fname); static inline void ext4_update_dx_flag(struct inode *inode) { - if (!ext4_has_feature_dir_index(inode->i_sb)) + if (!ext4_has_feature_dir_index(inode->i_sb)) { + /* ext4_iget() should have caught this... */ + WARN_ON_ONCE(ext4_has_feature_metadata_csum(inode->i_sb)); ext4_clear_inode_flag(inode, EXT4_INODE_INDEX); + } } static const unsigned char ext4_filetype_table[] = { DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK @@ -2727,6 +2750,7 @@ extern int ext4_generic_delete_entry(handle_t *handle, extern bool ext4_empty_dir(struct inode *inode); /* resize.c */ +extern void ext4_kvfree_array_rcu(void *to_free); extern int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input); extern int ext4_group_extend(struct super_block *sb, @@ -2973,13 +2997,13 @@ static inline struct ext4_group_info *ext4_get_group_info(struct super_block *sb, ext4_group_t group) { - struct ext4_group_info ***grp_info; + struct ext4_group_info **grp_info; long indexv, indexh; BUG_ON(group >= EXT4_SB(sb)->s_groups_count); - grp_info = EXT4_SB(sb)->s_group_info; indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb)); indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1); - return grp_info[indexv][indexh]; + grp_info = sbi_array_rcu_deref(EXT4_SB(sb), s_group_info, indexv); + return grp_info[indexh]; } /* @@ -3029,7 +3053,7 @@ static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize) !inode_is_locked(inode)); down_write(&EXT4_I(inode)->i_data_sem); if (newsize > EXT4_I(inode)->i_disksize) - EXT4_I(inode)->i_disksize = newsize; + WRITE_ONCE(EXT4_I(inode)->i_disksize, newsize); up_write(&EXT4_I(inode)->i_data_sem); } diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index c66e8f9451a266669bc70a40b40b3ac1af5849d6..f95ee99091e4c55a827d4cdad01bcc89ef8b3e89 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -328,11 +328,13 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) percpu_counter_inc(&sbi->s_freeinodes_counter); if (sbi->s_log_groups_per_flex) { - ext4_group_t f = ext4_flex_group(sbi, block_group); + struct flex_groups *fg; - atomic_inc(&sbi->s_flex_groups[f].free_inodes); + fg = sbi_array_rcu_deref(sbi, s_flex_groups, + ext4_flex_group(sbi, block_group)); + atomic_inc(&fg->free_inodes); if (is_directory) - atomic_dec(&sbi->s_flex_groups[f].used_dirs); + atomic_dec(&fg->used_dirs); } BUFFER_TRACE(bh2, "call ext4_handle_dirty_metadata"); fatal = ext4_handle_dirty_metadata(handle, NULL, bh2); @@ -368,12 +370,13 @@ static void get_orlov_stats(struct super_block *sb, ext4_group_t g, int flex_size, struct orlov_stats *stats) { struct ext4_group_desc *desc; - struct flex_groups *flex_group = EXT4_SB(sb)->s_flex_groups; if (flex_size > 1) { - stats->free_inodes = atomic_read(&flex_group[g].free_inodes); - stats->free_clusters = atomic64_read(&flex_group[g].free_clusters); - stats->used_dirs = atomic_read(&flex_group[g].used_dirs); + struct flex_groups *fg = sbi_array_rcu_deref(EXT4_SB(sb), + s_flex_groups, g); + stats->free_inodes = atomic_read(&fg->free_inodes); + stats->free_clusters = atomic64_read(&fg->free_clusters); + stats->used_dirs = atomic_read(&fg->used_dirs); return; } @@ -1054,7 +1057,8 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir, if (sbi->s_log_groups_per_flex) { ext4_group_t f = ext4_flex_group(sbi, group); - atomic_inc(&sbi->s_flex_groups[f].used_dirs); + atomic_inc(&sbi_array_rcu_deref(sbi, s_flex_groups, + f)->used_dirs); } } if (ext4_has_group_desc_csum(sb)) { @@ -1077,7 +1081,8 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir, if (sbi->s_log_groups_per_flex) { flex_group = ext4_flex_group(sbi, group); - atomic_dec(&sbi->s_flex_groups[flex_group].free_inodes); + atomic_dec(&sbi_array_rcu_deref(sbi, s_flex_groups, + flex_group)->free_inodes); } inode->i_ino = ino + group * EXT4_INODES_PER_GROUP(sb); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 3313168b680f1375376d71f63d0c8f1d95e87739..fa0ff78dc033f8cda2aa123e13c177ed7728dceb 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2465,7 +2465,7 @@ static int mpage_map_and_submit_extent(handle_t *handle, * truncate are avoided by checking i_size under i_data_sem. */ disksize = ((loff_t)mpd->first_page) << PAGE_SHIFT; - if (disksize > EXT4_I(inode)->i_disksize) { + if (disksize > READ_ONCE(EXT4_I(inode)->i_disksize)) { int err2; loff_t i_size; @@ -2628,7 +2628,7 @@ static int ext4_writepages(struct address_space *mapping, if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; - percpu_down_read(&sbi->s_journal_flag_rwsem); + percpu_down_read(&sbi->s_writepages_rwsem); trace_ext4_writepages(inode, wbc); /* @@ -2849,7 +2849,7 @@ static int ext4_writepages(struct address_space *mapping, out_writepages: trace_ext4_writepages_result(inode, wbc, ret, nr_to_write - wbc->nr_to_write); - percpu_up_read(&sbi->s_journal_flag_rwsem); + percpu_up_read(&sbi->s_writepages_rwsem); return ret; } @@ -2864,13 +2864,13 @@ static int ext4_dax_writepages(struct address_space *mapping, if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; - percpu_down_read(&sbi->s_journal_flag_rwsem); + percpu_down_read(&sbi->s_writepages_rwsem); trace_ext4_writepages(inode, wbc); - ret = dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev, wbc); + ret = dax_writeback_mapping_range(mapping, sbi->s_daxdev, wbc); trace_ext4_writepages_result(inode, wbc, ret, nr_to_write - wbc->nr_to_write); - percpu_up_read(&sbi->s_journal_flag_rwsem); + percpu_up_read(&sbi->s_writepages_rwsem); return ret; } @@ -4644,6 +4644,18 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, ret = -EFSCORRUPTED; goto bad_inode; } + /* + * If dir_index is not enabled but there's dir with INDEX flag set, + * we'd normally treat htree data as empty space. But with metadata + * checksumming that corrupts checksums so forbid that. + */ + if (!ext4_has_feature_dir_index(sb) && ext4_has_metadata_csum(sb) && + ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) { + ext4_error_inode(inode, function, line, 0, + "iget: Dir with htree data on filesystem without dir_index feature."); + ret = -EFSCORRUPTED; + goto bad_inode; + } ei->i_disksize = inode->i_size; #ifdef CONFIG_QUOTA ei->i_reserved_quota = 0; @@ -5849,7 +5861,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) } } - percpu_down_write(&sbi->s_journal_flag_rwsem); + percpu_down_write(&sbi->s_writepages_rwsem); jbd2_journal_lock_updates(journal); /* @@ -5866,7 +5878,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) err = jbd2_journal_flush(journal); if (err < 0) { jbd2_journal_unlock_updates(journal); - percpu_up_write(&sbi->s_journal_flag_rwsem); + percpu_up_write(&sbi->s_writepages_rwsem); return err; } ext4_clear_inode_flag(inode, EXT4_INODE_JOURNAL_DATA); @@ -5874,7 +5886,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) ext4_set_aops(inode); jbd2_journal_unlock_updates(journal); - percpu_up_write(&sbi->s_journal_flag_rwsem); + percpu_up_write(&sbi->s_writepages_rwsem); if (val) up_write(&EXT4_I(inode)->i_mmap_sem); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index f64838187559f25b859ba5acce4d0186a2c4415b..51a78eb65f3cf64744dd82a7ed0735f350a4459f 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2356,7 +2356,7 @@ int ext4_mb_alloc_groupinfo(struct super_block *sb, ext4_group_t ngroups) { struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned size; - struct ext4_group_info ***new_groupinfo; + struct ext4_group_info ***old_groupinfo, ***new_groupinfo; size = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >> EXT4_DESC_PER_BLOCK_BITS(sb); @@ -2369,13 +2369,16 @@ int ext4_mb_alloc_groupinfo(struct super_block *sb, ext4_group_t ngroups) ext4_msg(sb, KERN_ERR, "can't allocate buddy meta group"); return -ENOMEM; } - if (sbi->s_group_info) { - memcpy(new_groupinfo, sbi->s_group_info, + rcu_read_lock(); + old_groupinfo = rcu_dereference(sbi->s_group_info); + if (old_groupinfo) + memcpy(new_groupinfo, old_groupinfo, sbi->s_group_info_size * sizeof(*sbi->s_group_info)); - kvfree(sbi->s_group_info); - } - sbi->s_group_info = new_groupinfo; + rcu_read_unlock(); + rcu_assign_pointer(sbi->s_group_info, new_groupinfo); sbi->s_group_info_size = size / sizeof(*sbi->s_group_info); + if (old_groupinfo) + ext4_kvfree_array_rcu(old_groupinfo); ext4_debug("allocated s_groupinfo array for %d meta_bg's\n", sbi->s_group_info_size); return 0; @@ -2387,6 +2390,7 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, { int i; int metalen = 0; + int idx = group >> EXT4_DESC_PER_BLOCK_BITS(sb); struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_info **meta_group_info; struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits); @@ -2405,12 +2409,12 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, "for a buddy group"); goto exit_meta_group_info; } - sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)] = - meta_group_info; + rcu_read_lock(); + rcu_dereference(sbi->s_group_info)[idx] = meta_group_info; + rcu_read_unlock(); } - meta_group_info = - sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)]; + meta_group_info = sbi_array_rcu_deref(sbi, s_group_info, idx); i = group & (EXT4_DESC_PER_BLOCK(sb) - 1); meta_group_info[i] = kmem_cache_zalloc(cachep, GFP_NOFS); @@ -2458,8 +2462,13 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, exit_group_info: /* If a meta_group_info table has been allocated, release it now */ if (group % EXT4_DESC_PER_BLOCK(sb) == 0) { - kfree(sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)]); - sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)] = NULL; + struct ext4_group_info ***group_info; + + rcu_read_lock(); + group_info = rcu_dereference(sbi->s_group_info); + kfree(group_info[idx]); + group_info[idx] = NULL; + rcu_read_unlock(); } exit_meta_group_info: return -ENOMEM; @@ -2472,6 +2481,7 @@ static int ext4_mb_init_backend(struct super_block *sb) struct ext4_sb_info *sbi = EXT4_SB(sb); int err; struct ext4_group_desc *desc; + struct ext4_group_info ***group_info; struct kmem_cache *cachep; err = ext4_mb_alloc_groupinfo(sb, ngroups); @@ -2507,11 +2517,16 @@ static int ext4_mb_init_backend(struct super_block *sb) while (i-- > 0) kmem_cache_free(cachep, ext4_get_group_info(sb, i)); i = sbi->s_group_info_size; + rcu_read_lock(); + group_info = rcu_dereference(sbi->s_group_info); while (i-- > 0) - kfree(sbi->s_group_info[i]); + kfree(group_info[i]); + rcu_read_unlock(); iput(sbi->s_buddy_cache); err_freesgi: - kvfree(sbi->s_group_info); + rcu_read_lock(); + kvfree(rcu_dereference(sbi->s_group_info)); + rcu_read_unlock(); return -ENOMEM; } @@ -2700,7 +2715,7 @@ int ext4_mb_release(struct super_block *sb) ext4_group_t ngroups = ext4_get_groups_count(sb); ext4_group_t i; int num_meta_group_infos; - struct ext4_group_info *grinfo; + struct ext4_group_info *grinfo, ***group_info; struct ext4_sb_info *sbi = EXT4_SB(sb); struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits); @@ -2719,9 +2734,12 @@ int ext4_mb_release(struct super_block *sb) num_meta_group_infos = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >> EXT4_DESC_PER_BLOCK_BITS(sb); + rcu_read_lock(); + group_info = rcu_dereference(sbi->s_group_info); for (i = 0; i < num_meta_group_infos; i++) - kfree(sbi->s_group_info[i]); - kvfree(sbi->s_group_info); + kfree(group_info[i]); + kvfree(group_info); + rcu_read_unlock(); } kfree(sbi->s_mb_offsets); kfree(sbi->s_mb_maxs); @@ -3020,7 +3038,8 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, ext4_group_t flex_group = ext4_flex_group(sbi, ac->ac_b_ex.fe_group); atomic64_sub(ac->ac_b_ex.fe_len, - &sbi->s_flex_groups[flex_group].free_clusters); + &sbi_array_rcu_deref(sbi, s_flex_groups, + flex_group)->free_clusters); } err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); @@ -4918,7 +4937,8 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, if (sbi->s_log_groups_per_flex) { ext4_group_t flex_group = ext4_flex_group(sbi, block_group); atomic64_add(count_clusters, - &sbi->s_flex_groups[flex_group].free_clusters); + &sbi_array_rcu_deref(sbi, s_flex_groups, + flex_group)->free_clusters); } /* @@ -5075,7 +5095,8 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, if (sbi->s_log_groups_per_flex) { ext4_group_t flex_group = ext4_flex_group(sbi, block_group); atomic64_add(clusters_freed, - &sbi->s_flex_groups[flex_group].free_clusters); + &sbi_array_rcu_deref(sbi, s_flex_groups, + flex_group)->free_clusters); } ext4_mb_unload_buddy(&e4b); diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index 89725fa425732e4933a95b60200b33f40158537d..fb6520f37135509791c35b782ba14dfe328cfa49 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -407,6 +407,7 @@ static int free_ext_block(handle_t *handle, struct inode *inode) int ext4_ext_migrate(struct inode *inode) { + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); handle_t *handle; int retval = 0, i; __le32 *i_data; @@ -431,6 +432,8 @@ int ext4_ext_migrate(struct inode *inode) */ return retval; + percpu_down_write(&sbi->s_writepages_rwsem); + /* * Worst case we can touch the allocation bitmaps, a bgd * block, and a block to link in the orphan list. We do need @@ -441,7 +444,7 @@ int ext4_ext_migrate(struct inode *inode) if (IS_ERR(handle)) { retval = PTR_ERR(handle); - return retval; + goto out_unlock; } goal = (((inode->i_ino - 1) / EXT4_INODES_PER_GROUP(inode->i_sb)) * EXT4_INODES_PER_GROUP(inode->i_sb)) + 1; @@ -452,7 +455,7 @@ int ext4_ext_migrate(struct inode *inode) if (IS_ERR(tmp_inode)) { retval = PTR_ERR(tmp_inode); ext4_journal_stop(handle); - return retval; + goto out_unlock; } i_size_write(tmp_inode, i_size_read(inode)); /* @@ -494,7 +497,7 @@ int ext4_ext_migrate(struct inode *inode) */ ext4_orphan_del(NULL, tmp_inode); retval = PTR_ERR(handle); - goto out; + goto out_tmp_inode; } ei = EXT4_I(inode); @@ -576,10 +579,11 @@ int ext4_ext_migrate(struct inode *inode) ext4_ext_tree_init(handle, tmp_inode); out_stop: ext4_journal_stop(handle); -out: +out_tmp_inode: unlock_new_inode(tmp_inode); iput(tmp_inode); - +out_unlock: + percpu_up_write(&sbi->s_writepages_rwsem); return retval; } @@ -589,7 +593,8 @@ int ext4_ext_migrate(struct inode *inode) int ext4_ind_migrate(struct inode *inode) { struct ext4_extent_header *eh; - struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + struct ext4_super_block *es = sbi->s_es; struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_extent *ex; unsigned int i, len; @@ -613,9 +618,13 @@ int ext4_ind_migrate(struct inode *inode) if (test_opt(inode->i_sb, DELALLOC)) ext4_alloc_da_blocks(inode); + percpu_down_write(&sbi->s_writepages_rwsem); + handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1); - if (IS_ERR(handle)) - return PTR_ERR(handle); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out_unlock; + } down_write(&EXT4_I(inode)->i_data_sem); ret = ext4_ext_check_inode(inode); @@ -650,5 +659,7 @@ int ext4_ind_migrate(struct inode *inode) errout: ext4_journal_stop(handle); up_write(&EXT4_I(inode)->i_data_sem); +out_unlock: + percpu_up_write(&sbi->s_writepages_rwsem); return ret; } diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index 1c44b1a320015d5eda08adffddd4aba47630817c..87f7551c5132ebeee4fc465fb8161af038329b80 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -120,10 +120,10 @@ void __dump_mmp_msg(struct super_block *sb, struct mmp_struct *mmp, { __ext4_warning(sb, function, line, "%s", msg); __ext4_warning(sb, function, line, - "MMP failure info: last update time: %llu, last update " - "node: %s, last update device: %s", - (long long unsigned int) le64_to_cpu(mmp->mmp_time), - mmp->mmp_nodename, mmp->mmp_bdevname); + "MMP failure info: last update time: %llu, last update node: %.*s, last update device: %.*s", + (unsigned long long)le64_to_cpu(mmp->mmp_time), + (int)sizeof(mmp->mmp_nodename), mmp->mmp_nodename, + (int)sizeof(mmp->mmp_bdevname), mmp->mmp_bdevname); } /* @@ -154,6 +154,7 @@ static int kmmpd(void *data) mmp_check_interval = max(EXT4_MMP_CHECK_MULT * mmp_update_interval, EXT4_MMP_MIN_CHECK_INTERVAL); mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval); + BUILD_BUG_ON(sizeof(mmp->mmp_bdevname) < BDEVNAME_SIZE); bdevname(bh->b_bdev, mmp->mmp_bdevname); memcpy(mmp->mmp_nodename, init_utsname()->nodename, @@ -379,7 +380,8 @@ int ext4_multi_mount_protect(struct super_block *sb, /* * Start a kernel thread to update the MMP block periodically. */ - EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, mmpd_data, "kmmpd-%s", + EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, mmpd_data, "kmmpd-%.*s", + (int)sizeof(mmp->mmp_bdevname), bdevname(bh->b_bdev, mmp->mmp_bdevname)); if (IS_ERR(EXT4_SB(sb)->s_mmp_tsk)) { diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 129d2ebae00d05f198fe7c1d23a432dcb1ed710a..b05ea72f38fd1981dce81b4a8cc37ec8fcad7108 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1511,6 +1511,7 @@ static struct buffer_head *__ext4_find_entry(struct inode *dir, /* * We deal with the read-ahead logic here. */ + cond_resched(); if (ra_ptr >= ra_max) { /* Refill the readahead buffer */ ra_ptr = 0; @@ -2213,6 +2214,13 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, retval = ext4_dx_add_entry(handle, &fname, dir, inode); if (!retval || (retval != ERR_BAD_DX_DIR)) goto out; + /* Can we just ignore htree data? */ + if (ext4_has_metadata_csum(sb)) { + EXT4_ERROR_INODE(dir, + "Directory has corrupted htree index."); + retval = -EFSCORRUPTED; + goto out; + } ext4_clear_inode_flag(dir, EXT4_INODE_INDEX); dx_fallback++; ext4_mark_inode_dirty(handle, dir); diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 86a2500ed292f136b93f2ee75e71638567a72646..a50b51270ea9ad976c2f9da7c2cc97b8d2254eb3 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -17,6 +17,33 @@ #include "ext4_jbd2.h" +struct ext4_rcu_ptr { + struct rcu_head rcu; + void *ptr; +}; + +static void ext4_rcu_ptr_callback(struct rcu_head *head) +{ + struct ext4_rcu_ptr *ptr; + + ptr = container_of(head, struct ext4_rcu_ptr, rcu); + kvfree(ptr->ptr); + kfree(ptr); +} + +void ext4_kvfree_array_rcu(void *to_free) +{ + struct ext4_rcu_ptr *ptr = kzalloc(sizeof(*ptr), GFP_KERNEL); + + if (ptr) { + ptr->ptr = to_free; + call_rcu(&ptr->rcu, ext4_rcu_ptr_callback); + return; + } + synchronize_rcu(); + kvfree(to_free); +} + int ext4_resize_begin(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -542,8 +569,8 @@ static int setup_new_flex_group_blocks(struct super_block *sb, brelse(gdb); goto out; } - memcpy(gdb->b_data, sbi->s_group_desc[j]->b_data, - gdb->b_size); + memcpy(gdb->b_data, sbi_array_rcu_deref(sbi, + s_group_desc, j)->b_data, gdb->b_size); set_buffer_uptodate(gdb); err = ext4_handle_dirty_metadata(handle, NULL, gdb); @@ -860,13 +887,15 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, } brelse(dind); - o_group_desc = EXT4_SB(sb)->s_group_desc; + rcu_read_lock(); + o_group_desc = rcu_dereference(EXT4_SB(sb)->s_group_desc); memcpy(n_group_desc, o_group_desc, EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *)); + rcu_read_unlock(); n_group_desc[gdb_num] = gdb_bh; - EXT4_SB(sb)->s_group_desc = n_group_desc; + rcu_assign_pointer(EXT4_SB(sb)->s_group_desc, n_group_desc); EXT4_SB(sb)->s_gdb_count++; - kvfree(o_group_desc); + ext4_kvfree_array_rcu(o_group_desc); le16_add_cpu(&es->s_reserved_gdt_blocks, -1); err = ext4_handle_dirty_super(handle, sb); @@ -909,9 +938,11 @@ static int add_new_gdb_meta_bg(struct super_block *sb, return err; } - o_group_desc = EXT4_SB(sb)->s_group_desc; + rcu_read_lock(); + o_group_desc = rcu_dereference(EXT4_SB(sb)->s_group_desc); memcpy(n_group_desc, o_group_desc, EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *)); + rcu_read_unlock(); n_group_desc[gdb_num] = gdb_bh; BUFFER_TRACE(gdb_bh, "get_write_access"); @@ -922,9 +953,9 @@ static int add_new_gdb_meta_bg(struct super_block *sb, return err; } - EXT4_SB(sb)->s_group_desc = n_group_desc; + rcu_assign_pointer(EXT4_SB(sb)->s_group_desc, n_group_desc); EXT4_SB(sb)->s_gdb_count++; - kvfree(o_group_desc); + ext4_kvfree_array_rcu(o_group_desc); return err; } @@ -1188,7 +1219,8 @@ static int ext4_add_new_descs(handle_t *handle, struct super_block *sb, * use non-sparse filesystems anymore. This is already checked above. */ if (gdb_off) { - gdb_bh = sbi->s_group_desc[gdb_num]; + gdb_bh = sbi_array_rcu_deref(sbi, s_group_desc, + gdb_num); BUFFER_TRACE(gdb_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, gdb_bh); @@ -1270,7 +1302,7 @@ static int ext4_setup_new_descs(handle_t *handle, struct super_block *sb, /* * get_write_access() has been called on gdb_bh by ext4_add_new_desc(). */ - gdb_bh = sbi->s_group_desc[gdb_num]; + gdb_bh = sbi_array_rcu_deref(sbi, s_group_desc, gdb_num); /* Update group descriptor block for new group */ gdp = (struct ext4_group_desc *)(gdb_bh->b_data + gdb_off * EXT4_DESC_SIZE(sb)); @@ -1398,11 +1430,14 @@ static void ext4_update_super(struct super_block *sb, percpu_counter_read(&sbi->s_freeclusters_counter)); if (ext4_has_feature_flex_bg(sb) && sbi->s_log_groups_per_flex) { ext4_group_t flex_group; + struct flex_groups *fg; + flex_group = ext4_flex_group(sbi, group_data[0].group); + fg = sbi_array_rcu_deref(sbi, s_flex_groups, flex_group); atomic64_add(EXT4_NUM_B2C(sbi, free_blocks), - &sbi->s_flex_groups[flex_group].free_clusters); + &fg->free_clusters); atomic_add(EXT4_INODES_PER_GROUP(sb) * flex_gd->count, - &sbi->s_flex_groups[flex_group].free_inodes); + &fg->free_inodes); } /* @@ -1497,7 +1532,8 @@ static int ext4_flex_group_add(struct super_block *sb, for (; gdb_num <= gdb_num_end; gdb_num++) { struct buffer_head *gdb_bh; - gdb_bh = sbi->s_group_desc[gdb_num]; + gdb_bh = sbi_array_rcu_deref(sbi, s_group_desc, + gdb_num); if (old_gdb == gdb_bh->b_blocknr) continue; update_backups(sb, gdb_bh->b_blocknr, gdb_bh->b_data, diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 8434217549b3055daac18216914c8d4d235beef3..0c7c4adb664ec993651ae6dabba860ccd7827567 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1014,6 +1014,8 @@ static void ext4_put_super(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; + struct buffer_head **group_desc; + struct flex_groups **flex_groups; int aborted = 0; int i, err; @@ -1046,15 +1048,23 @@ static void ext4_put_super(struct super_block *sb) if (!sb_rdonly(sb)) ext4_commit_super(sb, 1); + rcu_read_lock(); + group_desc = rcu_dereference(sbi->s_group_desc); for (i = 0; i < sbi->s_gdb_count; i++) - brelse(sbi->s_group_desc[i]); - kvfree(sbi->s_group_desc); - kvfree(sbi->s_flex_groups); + brelse(group_desc[i]); + kvfree(group_desc); + flex_groups = rcu_dereference(sbi->s_flex_groups); + if (flex_groups) { + for (i = 0; i < sbi->s_flex_groups_allocated; i++) + kvfree(flex_groups[i]); + kvfree(flex_groups); + } + rcu_read_unlock(); percpu_counter_destroy(&sbi->s_freeclusters_counter); percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); percpu_counter_destroy(&sbi->s_dirtyclusters_counter); - percpu_free_rwsem(&sbi->s_journal_flag_rwsem); + percpu_free_rwsem(&sbi->s_writepages_rwsem); #ifdef CONFIG_QUOTA for (i = 0; i < EXT4_MAXQUOTAS; i++) kfree(get_qf_name(sb, sbi, i)); @@ -2380,8 +2390,8 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup) { struct ext4_sb_info *sbi = EXT4_SB(sb); - struct flex_groups *new_groups; - int size; + struct flex_groups **old_groups, **new_groups; + int size, i, j; if (!sbi->s_log_groups_per_flex) return 0; @@ -2390,22 +2400,37 @@ int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup) if (size <= sbi->s_flex_groups_allocated) return 0; - size = roundup_pow_of_two(size * sizeof(struct flex_groups)); - new_groups = kvzalloc(size, GFP_KERNEL); + new_groups = kvzalloc(roundup_pow_of_two(size * + sizeof(*sbi->s_flex_groups)), GFP_KERNEL); if (!new_groups) { - ext4_msg(sb, KERN_ERR, "not enough memory for %d flex groups", - size / (int) sizeof(struct flex_groups)); + ext4_msg(sb, KERN_ERR, + "not enough memory for %d flex group pointers", size); return -ENOMEM; } - - if (sbi->s_flex_groups) { - memcpy(new_groups, sbi->s_flex_groups, - (sbi->s_flex_groups_allocated * - sizeof(struct flex_groups))); - kvfree(sbi->s_flex_groups); + for (i = sbi->s_flex_groups_allocated; i < size; i++) { + new_groups[i] = kvzalloc(roundup_pow_of_two( + sizeof(struct flex_groups)), + GFP_KERNEL); + if (!new_groups[i]) { + for (j = sbi->s_flex_groups_allocated; j < i; j++) + kvfree(new_groups[j]); + kvfree(new_groups); + ext4_msg(sb, KERN_ERR, + "not enough memory for %d flex groups", size); + return -ENOMEM; + } } - sbi->s_flex_groups = new_groups; - sbi->s_flex_groups_allocated = size / sizeof(struct flex_groups); + rcu_read_lock(); + old_groups = rcu_dereference(sbi->s_flex_groups); + if (old_groups) + memcpy(new_groups, old_groups, + (sbi->s_flex_groups_allocated * + sizeof(struct flex_groups *))); + rcu_read_unlock(); + rcu_assign_pointer(sbi->s_flex_groups, new_groups); + sbi->s_flex_groups_allocated = size; + if (old_groups) + ext4_kvfree_array_rcu(old_groups); return 0; } @@ -2413,6 +2438,7 @@ static int ext4_fill_flex_info(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_desc *gdp = NULL; + struct flex_groups *fg; ext4_group_t flex_group; int i, err; @@ -2430,12 +2456,11 @@ static int ext4_fill_flex_info(struct super_block *sb) gdp = ext4_get_group_desc(sb, i, NULL); flex_group = ext4_flex_group(sbi, i); - atomic_add(ext4_free_inodes_count(sb, gdp), - &sbi->s_flex_groups[flex_group].free_inodes); + fg = sbi_array_rcu_deref(sbi, s_flex_groups, flex_group); + atomic_add(ext4_free_inodes_count(sb, gdp), &fg->free_inodes); atomic64_add(ext4_free_group_clusters(sb, gdp), - &sbi->s_flex_groups[flex_group].free_clusters); - atomic_add(ext4_used_dirs_count(sb, gdp), - &sbi->s_flex_groups[flex_group].used_dirs); + &fg->free_clusters); + atomic_add(ext4_used_dirs_count(sb, gdp), &fg->used_dirs); } return 1; @@ -3009,17 +3034,11 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly) return 0; } -#ifndef CONFIG_QUOTA - if (ext4_has_feature_quota(sb) && !readonly) { +#if !IS_ENABLED(CONFIG_QUOTA) || !IS_ENABLED(CONFIG_QFMT_V2) + if (!readonly && (ext4_has_feature_quota(sb) || + ext4_has_feature_project(sb))) { ext4_msg(sb, KERN_ERR, - "Filesystem with quota feature cannot be mounted RDWR " - "without CONFIG_QUOTA"); - return 0; - } - if (ext4_has_feature_project(sb) && !readonly) { - ext4_msg(sb, KERN_ERR, - "Filesystem with project quota feature cannot be mounted RDWR " - "without CONFIG_QUOTA"); + "The kernel was not built with CONFIG_QUOTA and CONFIG_QFMT_V2"); return 0; } #endif /* CONFIG_QUOTA */ @@ -3640,9 +3659,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) { struct dax_device *dax_dev = fs_dax_get_by_bdev(sb->s_bdev); char *orig_data = kstrdup(data, GFP_KERNEL); - struct buffer_head *bh; + struct buffer_head *bh, **group_desc; struct ext4_super_block *es = NULL; struct ext4_sb_info *sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); + struct flex_groups **flex_groups; ext4_fsblk_t block; ext4_fsblk_t sb_block = get_sb_block(&data); ext4_fsblk_t logical_sb_block; @@ -3814,6 +3834,15 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) */ sbi->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT; + blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size); + if (blocksize < EXT4_MIN_BLOCK_SIZE || + blocksize > EXT4_MAX_BLOCK_SIZE) { + ext4_msg(sb, KERN_ERR, + "Unsupported filesystem blocksize %d (%d log_block_size)", + blocksize, le32_to_cpu(es->s_log_block_size)); + goto failed_mount; + } + if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) { sbi->s_inode_size = EXT4_GOOD_OLD_INODE_SIZE; sbi->s_first_ino = EXT4_GOOD_OLD_FIRST_INO; @@ -3831,6 +3860,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) ext4_msg(sb, KERN_ERR, "unsupported inode size: %d", sbi->s_inode_size); + ext4_msg(sb, KERN_ERR, "blocksize: %d", blocksize); goto failed_mount; } /* @@ -4033,14 +4063,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (!ext4_feature_set_ok(sb, (sb_rdonly(sb)))) goto failed_mount; - blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size); - if (blocksize < EXT4_MIN_BLOCK_SIZE || - blocksize > EXT4_MAX_BLOCK_SIZE) { - ext4_msg(sb, KERN_ERR, - "Unsupported filesystem blocksize %d (%d log_block_size)", - blocksize, le32_to_cpu(es->s_log_block_size)); - goto failed_mount; - } if (le32_to_cpu(es->s_log_block_size) > (EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) { ext4_msg(sb, KERN_ERR, @@ -4294,9 +4316,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; } } - sbi->s_group_desc = kvmalloc_array(db_count, - sizeof(struct buffer_head *), - GFP_KERNEL); + rcu_assign_pointer(sbi->s_group_desc, + kvmalloc_array(db_count, + sizeof(struct buffer_head *), + GFP_KERNEL)); if (sbi->s_group_desc == NULL) { ext4_msg(sb, KERN_ERR, "not enough memory"); ret = -ENOMEM; @@ -4312,14 +4335,19 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } for (i = 0; i < db_count; i++) { + struct buffer_head *bh; + block = descriptor_loc(sb, logical_sb_block, i); - sbi->s_group_desc[i] = sb_bread_unmovable(sb, block); - if (!sbi->s_group_desc[i]) { + bh = sb_bread_unmovable(sb, block); + if (!bh) { ext4_msg(sb, KERN_ERR, "can't read group descriptor %d", i); db_count = i; goto failed_mount2; } + rcu_read_lock(); + rcu_dereference(sbi->s_group_desc)[i] = bh; + rcu_read_unlock(); } sbi->s_gdb_count = db_count; if (!ext4_check_descriptors(sb, logical_sb_block, &first_not_zeroed)) { @@ -4598,7 +4626,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0, GFP_KERNEL); if (!err) - err = percpu_init_rwsem(&sbi->s_journal_flag_rwsem); + err = percpu_init_rwsem(&sbi->s_writepages_rwsem); if (err) { ext4_msg(sb, KERN_ERR, "insufficient memory"); @@ -4686,13 +4714,19 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) ext4_unregister_li_request(sb); failed_mount6: ext4_mb_release(sb); - if (sbi->s_flex_groups) - kvfree(sbi->s_flex_groups); + rcu_read_lock(); + flex_groups = rcu_dereference(sbi->s_flex_groups); + if (flex_groups) { + for (i = 0; i < sbi->s_flex_groups_allocated; i++) + kvfree(flex_groups[i]); + kvfree(flex_groups); + } + rcu_read_unlock(); percpu_counter_destroy(&sbi->s_freeclusters_counter); percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); percpu_counter_destroy(&sbi->s_dirtyclusters_counter); - percpu_free_rwsem(&sbi->s_journal_flag_rwsem); + percpu_free_rwsem(&sbi->s_writepages_rwsem); failed_mount5: ext4_ext_release(sb); ext4_release_system_zone(sb); @@ -4721,9 +4755,12 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (sbi->s_mmp_tsk) kthread_stop(sbi->s_mmp_tsk); failed_mount2: + rcu_read_lock(); + group_desc = rcu_dereference(sbi->s_group_desc); for (i = 0; i < db_count; i++) - brelse(sbi->s_group_desc[i]); - kvfree(sbi->s_group_desc); + brelse(group_desc[i]); + kvfree(group_desc); + rcu_read_unlock(); failed_mount: if (sbi->s_chksum_driver) crypto_free_shash(sbi->s_chksum_driver); @@ -5585,10 +5622,7 @@ static int ext4_statfs_project(struct super_block *sb, return PTR_ERR(dquot); spin_lock(&dquot->dq_dqb_lock); - limit = 0; - if (dquot->dq_dqb.dqb_bsoftlimit && - (!limit || dquot->dq_dqb.dqb_bsoftlimit < limit)) - limit = dquot->dq_dqb.dqb_bsoftlimit; + limit = dquot->dq_dqb.dqb_bsoftlimit; if (dquot->dq_dqb.dqb_bhardlimit && (!limit || dquot->dq_dqb.dqb_bhardlimit < limit)) limit = dquot->dq_dqb.dqb_bhardlimit; @@ -5603,10 +5637,7 @@ static int ext4_statfs_project(struct super_block *sb, (buf->f_blocks - curblock) : 0; } - limit = 0; - if (dquot->dq_dqb.dqb_isoftlimit && - (!limit || dquot->dq_dqb.dqb_isoftlimit < limit)) - limit = dquot->dq_dqb.dqb_isoftlimit; + limit = dquot->dq_dqb.dqb_isoftlimit; if (dquot->dq_dqb.dqb_ihardlimit && (!limit || dquot->dq_dqb.dqb_ihardlimit < limit)) limit = dquot->dq_dqb.dqb_ihardlimit; diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 594b05ae16c9bf04584ae9c6c4dba50dbdecffcb..71946da8438849859b5240d199b216cf0b424f55 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -750,6 +750,13 @@ static struct inode *fat_alloc_inode(struct super_block *sb) return NULL; init_rwsem(&ei->truncate_lock); + /* Zeroing to allow iput() even if partial initialized inode. */ + ei->mmu_private = 0; + ei->i_start = 0; + ei->i_logstart = 0; + ei->i_attrs = 0; + ei->i_pos = 0; + return &ei->vfs_inode; } @@ -1374,16 +1381,6 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat, return 0; } -static void fat_dummy_inode_init(struct inode *inode) -{ - /* Initialize this dummy inode to work as no-op. */ - MSDOS_I(inode)->mmu_private = 0; - MSDOS_I(inode)->i_start = 0; - MSDOS_I(inode)->i_logstart = 0; - MSDOS_I(inode)->i_attrs = 0; - MSDOS_I(inode)->i_pos = 0; -} - static int fat_read_root(struct inode *inode) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); @@ -1844,13 +1841,11 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, fat_inode = new_inode(sb); if (!fat_inode) goto out_fail; - fat_dummy_inode_init(fat_inode); sbi->fat_inode = fat_inode; fsinfo_inode = new_inode(sb); if (!fsinfo_inode) goto out_fail; - fat_dummy_inode_init(fsinfo_inode); fsinfo_inode->i_ino = MSDOS_FSINFO_INO; sbi->fsinfo_inode = fsinfo_inode; insert_inode_hash(fsinfo_inode); diff --git a/fs/fcntl.c b/fs/fcntl.c index 9bc167562ee80bfdcb8b1c6648576e988bbd04eb..2e4c0fa2074b00c7b4ea43715647368bf680d804 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -735,8 +735,9 @@ static void send_sigio_to_task(struct task_struct *p, return; switch (signum) { - kernel_siginfo_t si; - default: + default: { + kernel_siginfo_t si; + /* Queue a rt signal with the appropriate fd as its value. We use SI_SIGIO as the source, not SI_KERNEL, since kernel signals always get @@ -769,6 +770,7 @@ static void send_sigio_to_task(struct task_struct *p, si.si_fd = fd; if (!do_send_sig_info(signum, &si, p, type)) break; + } /* fall-through - fall back on the old plain SIGIO signal */ case 0: do_send_sig_info(SIGIO, SEND_SIG_PRIV, p, type); diff --git a/fs/file.c b/fs/file.c index a364e1a9b7e8e16a1ebbac2a52c97fb43c84aba0..c8a4e4c86e55c8cce4f38b95d7c94e6d0e3d0613 100644 --- a/fs/file.c +++ b/fs/file.c @@ -540,9 +540,14 @@ static int alloc_fd(unsigned start, unsigned flags) return __alloc_fd(current->files, start, rlimit(RLIMIT_NOFILE), flags); } +int __get_unused_fd_flags(unsigned flags, unsigned long nofile) +{ + return __alloc_fd(current->files, 0, nofile, flags); +} + int get_unused_fd_flags(unsigned flags) { - return __alloc_fd(current->files, 0, rlimit(RLIMIT_NOFILE), flags); + return __get_unused_fd_flags(flags, rlimit(RLIMIT_NOFILE)); } EXPORT_SYMBOL(get_unused_fd_flags); diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 8e02d76fe104aa4438f2076d7450d17683fc636f..97eec7522bf203a929cefd7e0afd67fdd87cd7cb 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -276,12 +276,10 @@ static void flush_bg_queue(struct fuse_conn *fc) void fuse_request_end(struct fuse_conn *fc, struct fuse_req *req) { struct fuse_iqueue *fiq = &fc->iq; - bool async; if (test_and_set_bit(FR_FINISHED, &req->flags)) goto put_request; - async = req->args->end; /* * test_and_set_bit() implies smp_mb() between bit * changing and below intr_entry check. Pairs with @@ -324,7 +322,7 @@ void fuse_request_end(struct fuse_conn *fc, struct fuse_req *req) wake_up(&req->waitq); } - if (async) + if (test_bit(FR_ASYNC, &req->flags)) req->args->end(fc, req->args, req->out.h.error); put_request: fuse_put_request(fc, req); @@ -471,6 +469,8 @@ static void fuse_args_to_req(struct fuse_req *req, struct fuse_args *args) req->in.h.opcode = args->opcode; req->in.h.nodeid = args->nodeid; req->args = args; + if (args->end) + __set_bit(FR_ASYNC, &req->flags); } ssize_t fuse_simple_request(struct fuse_conn *fc, struct fuse_args *args) diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index aa75e2305b7587a8010c3aef405b44aa777f3ae3..ca344bf714045a9408f8a4f9bbcab532e7b7269c 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -301,6 +301,7 @@ struct fuse_io_priv { * FR_SENT: request is in userspace, waiting for an answer * FR_FINISHED: request is finished * FR_PRIVATE: request is on private list + * FR_ASYNC: request is asynchronous */ enum fuse_req_flag { FR_ISREPLY, @@ -314,6 +315,7 @@ enum fuse_req_flag { FR_SENT, FR_FINISHED, FR_PRIVATE, + FR_ASYNC, }; /** diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 2716d56ed0a07e537935c371e19c21c8f986670a..8294851a9dd99acbd548579a38f5cab5745bafd8 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -1248,7 +1248,7 @@ static int gfs2_atomic_open(struct inode *dir, struct dentry *dentry, if (!(file->f_mode & FMODE_OPENED)) return finish_no_open(file, d); dput(d); - return 0; + return excl && (flags & O_CREAT) ? -EEXIST : 0; } BUG_ON(d != NULL); diff --git a/fs/inode.c b/fs/inode.c index 7d57068b6b7aedbc3ddde2b91179853b7e8c6f43..93d9252a00ab4b2ed0fbb274b28e1df468aa71ca 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -138,6 +138,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode) inode->i_sb = sb; inode->i_blkbits = sb->s_blocksize_bits; inode->i_flags = 0; + atomic64_set(&inode->i_sequence, 0); atomic_set(&inode->i_count, 1); inode->i_op = &empty_iops; inode->i_fop = &no_open_fops; diff --git a/fs/io-wq.c b/fs/io-wq.c index cb60a42b9fdfa5bb1aa1832e3d0277051d821c69..5cef075c0b379c11673ebab978d766fa5da80612 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -16,6 +16,7 @@ #include #include #include +#include #include "io-wq.h" @@ -59,6 +60,7 @@ struct io_worker { const struct cred *cur_creds; const struct cred *saved_creds; struct files_struct *restore_files; + struct fs_struct *restore_fs; }; #if BITS_PER_LONG == 64 @@ -151,6 +153,9 @@ static bool __io_worker_unuse(struct io_wqe *wqe, struct io_worker *worker) task_unlock(current); } + if (current->fs != worker->restore_fs) + current->fs = worker->restore_fs; + /* * If we have an active mm, we need to drop the wq lock before unusing * it. If we do, return true and let the caller retry the idle loop. @@ -311,6 +316,7 @@ static void io_worker_start(struct io_wqe *wqe, struct io_worker *worker) worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING); worker->restore_files = current->files; + worker->restore_fs = current->fs; io_wqe_inc_running(wqe, worker); } @@ -481,6 +487,8 @@ static void io_worker_handle_work(struct io_worker *worker) current->files = work->files; task_unlock(current); } + if (work->fs && current->fs != work->fs) + current->fs = work->fs; if (work->mm != worker->mm) io_wq_switch_mm(worker, work); if (worker->cur_creds != work->creds) @@ -494,7 +502,7 @@ static void io_worker_handle_work(struct io_worker *worker) if (worker->mm) work->flags |= IO_WQ_WORK_HAS_MM; - if (wq->get_work && !(work->flags & IO_WQ_WORK_INTERNAL)) { + if (wq->get_work) { put_work = work; wq->get_work(work); } @@ -527,42 +535,23 @@ static void io_worker_handle_work(struct io_worker *worker) } while (1); } -static inline void io_worker_spin_for_work(struct io_wqe *wqe) -{ - int i = 0; - - while (++i < 1000) { - if (io_wqe_run_queue(wqe)) - break; - if (need_resched()) - break; - cpu_relax(); - } -} - static int io_wqe_worker(void *data) { struct io_worker *worker = data; struct io_wqe *wqe = worker->wqe; struct io_wq *wq = wqe->wq; - bool did_work; io_worker_start(wqe, worker); - did_work = false; while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) { set_current_state(TASK_INTERRUPTIBLE); loop: - if (did_work) - io_worker_spin_for_work(wqe); spin_lock_irq(&wqe->lock); if (io_wqe_run_queue(wqe)) { __set_current_state(TASK_RUNNING); io_worker_handle_work(worker); - did_work = true; goto loop; } - did_work = false; /* drops the lock on success, retry */ if (__io_worker_idle(wqe, worker)) { __release(&wqe->lock); @@ -691,11 +680,16 @@ static int io_wq_manager(void *data) /* create fixed workers */ refcount_set(&wq->refs, workers_to_create); for_each_node(node) { + if (!node_online(node)) + continue; if (!create_io_worker(wq, wq->wqes[node], IO_WQ_ACCT_BOUND)) goto err; workers_to_create--; } + while (workers_to_create--) + refcount_dec(&wq->refs); + complete(&wq->done); while (!kthread_should_stop()) { @@ -703,6 +697,9 @@ static int io_wq_manager(void *data) struct io_wqe *wqe = wq->wqes[node]; bool fork_worker[2] = { false, false }; + if (!node_online(node)) + continue; + spin_lock_irq(&wqe->lock); if (io_wqe_need_worker(wqe, IO_WQ_ACCT_BOUND)) fork_worker[IO_WQ_ACCT_BOUND] = true; @@ -750,6 +747,17 @@ static bool io_wq_can_queue(struct io_wqe *wqe, struct io_wqe_acct *acct, return true; } +static void io_run_cancel(struct io_wq_work *work) +{ + do { + struct io_wq_work *old_work = work; + + work->flags |= IO_WQ_WORK_CANCEL; + work->func(&work); + work = (work == old_work) ? NULL : work; + } while (work); +} + static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work) { struct io_wqe_acct *acct = io_work_get_acct(wqe, work); @@ -763,8 +771,7 @@ static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work) * It's close enough to not be an issue, fork() has the same delay. */ if (unlikely(!io_wq_can_queue(wqe, acct, work))) { - work->flags |= IO_WQ_WORK_CANCEL; - work->func(&work); + io_run_cancel(work); return; } @@ -821,7 +828,9 @@ static bool io_wq_for_each_worker(struct io_wqe *wqe, list_for_each_entry_rcu(worker, &wqe->all_list, all_list) { if (io_worker_get(worker)) { - ret = func(worker, data); + /* no task if node is/was offline */ + if (worker->task) + ret = func(worker, data); io_worker_release(worker); if (ret) break; @@ -901,8 +910,7 @@ static enum io_wq_cancel io_wqe_cancel_cb_work(struct io_wqe *wqe, spin_unlock_irqrestore(&wqe->lock, flags); if (found) { - work->flags |= IO_WQ_WORK_CANCEL; - work->func(&work); + io_run_cancel(work); return IO_WQ_CANCEL_OK; } @@ -929,17 +937,19 @@ enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel, return ret; } +struct work_match { + bool (*fn)(struct io_wq_work *, void *data); + void *data; +}; + static bool io_wq_worker_cancel(struct io_worker *worker, void *data) { - struct io_wq_work *work = data; + struct work_match *match = data; unsigned long flags; bool ret = false; - if (worker->cur_work != work) - return false; - spin_lock_irqsave(&worker->lock, flags); - if (worker->cur_work == work && + if (match->fn(worker->cur_work, match->data) && !(worker->cur_work->flags & IO_WQ_WORK_NO_CANCEL)) { send_sig(SIGINT, worker->task, 1); ret = true; @@ -950,15 +960,13 @@ static bool io_wq_worker_cancel(struct io_worker *worker, void *data) } static enum io_wq_cancel io_wqe_cancel_work(struct io_wqe *wqe, - struct io_wq_work *cwork) + struct work_match *match) { struct io_wq_work_node *node, *prev; struct io_wq_work *work; unsigned long flags; bool found = false; - cwork->flags |= IO_WQ_WORK_CANCEL; - /* * First check pending list, if we're lucky we can just remove it * from there. CANCEL_OK means that the work is returned as-new, @@ -968,7 +976,7 @@ static enum io_wq_cancel io_wqe_cancel_work(struct io_wqe *wqe, wq_list_for_each(node, prev, &wqe->work_list) { work = container_of(node, struct io_wq_work, list); - if (work == cwork) { + if (match->fn(work, match->data)) { wq_node_del(&wqe->work_list, node, prev); found = true; break; @@ -977,8 +985,7 @@ static enum io_wq_cancel io_wqe_cancel_work(struct io_wqe *wqe, spin_unlock_irqrestore(&wqe->lock, flags); if (found) { - work->flags |= IO_WQ_WORK_CANCEL; - work->func(&work); + io_run_cancel(work); return IO_WQ_CANCEL_OK; } @@ -989,20 +996,31 @@ static enum io_wq_cancel io_wqe_cancel_work(struct io_wqe *wqe, * completion will run normally in this case. */ rcu_read_lock(); - found = io_wq_for_each_worker(wqe, io_wq_worker_cancel, cwork); + found = io_wq_for_each_worker(wqe, io_wq_worker_cancel, match); rcu_read_unlock(); return found ? IO_WQ_CANCEL_RUNNING : IO_WQ_CANCEL_NOTFOUND; } +static bool io_wq_work_match(struct io_wq_work *work, void *data) +{ + return work == data; +} + enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork) { + struct work_match match = { + .fn = io_wq_work_match, + .data = cwork + }; enum io_wq_cancel ret = IO_WQ_CANCEL_NOTFOUND; int node; + cwork->flags |= IO_WQ_WORK_CANCEL; + for_each_node(node) { struct io_wqe *wqe = wq->wqes[node]; - ret = io_wqe_cancel_work(wqe, cwork); + ret = io_wqe_cancel_work(wqe, &match); if (ret != IO_WQ_CANCEL_NOTFOUND) break; } @@ -1010,38 +1028,33 @@ enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork) return ret; } -struct io_wq_flush_data { - struct io_wq_work work; - struct completion done; -}; - -static void io_wq_flush_func(struct io_wq_work **workptr) +static bool io_wq_pid_match(struct io_wq_work *work, void *data) { - struct io_wq_work *work = *workptr; - struct io_wq_flush_data *data; + pid_t pid = (pid_t) (unsigned long) data; - data = container_of(work, struct io_wq_flush_data, work); - complete(&data->done); + if (work) + return work->task_pid == pid; + return false; } -/* - * Doesn't wait for previously queued work to finish. When this completes, - * it just means that previously queued work was started. - */ -void io_wq_flush(struct io_wq *wq) +enum io_wq_cancel io_wq_cancel_pid(struct io_wq *wq, pid_t pid) { - struct io_wq_flush_data data; + struct work_match match = { + .fn = io_wq_pid_match, + .data = (void *) (unsigned long) pid + }; + enum io_wq_cancel ret = IO_WQ_CANCEL_NOTFOUND; int node; for_each_node(node) { struct io_wqe *wqe = wq->wqes[node]; - init_completion(&data.done); - INIT_IO_WORK(&data.work, io_wq_flush_func); - data.work.flags |= IO_WQ_WORK_INTERNAL; - io_wqe_enqueue(wqe, &data.work); - wait_for_completion(&data.done); + ret = io_wqe_cancel_work(wqe, &match); + if (ret != IO_WQ_CANCEL_NOTFOUND) + break; } + + return ret; } struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data) @@ -1067,12 +1080,15 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data) for_each_node(node) { struct io_wqe *wqe; + int alloc_node = node; - wqe = kzalloc_node(sizeof(struct io_wqe), GFP_KERNEL, node); + if (!node_online(alloc_node)) + alloc_node = NUMA_NO_NODE; + wqe = kzalloc_node(sizeof(struct io_wqe), GFP_KERNEL, alloc_node); if (!wqe) goto err; wq->wqes[node] = wqe; - wqe->node = node; + wqe->node = alloc_node; wqe->acct[IO_WQ_ACCT_BOUND].max_workers = bounded; atomic_set(&wqe->acct[IO_WQ_ACCT_BOUND].nr_running, 0); if (wq->user) { @@ -1080,7 +1096,6 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data) task_rlimit(current, RLIMIT_NPROC); } atomic_set(&wqe->acct[IO_WQ_ACCT_UNBOUND].nr_running, 0); - wqe->node = node; wqe->wq = wq; spin_lock_init(&wqe->lock); INIT_WQ_LIST(&wqe->work_list); diff --git a/fs/io-wq.h b/fs/io-wq.h index 50b3378febf2f3bb01d9b9cf0a8f582d0a72a50e..e5e15f2c93eca47965667fbddfa08b36de5ac3fd 100644 --- a/fs/io-wq.h +++ b/fs/io-wq.h @@ -8,7 +8,6 @@ enum { IO_WQ_WORK_HAS_MM = 2, IO_WQ_WORK_HASHED = 4, IO_WQ_WORK_UNBOUND = 32, - IO_WQ_WORK_INTERNAL = 64, IO_WQ_WORK_CB = 128, IO_WQ_WORK_NO_CANCEL = 256, IO_WQ_WORK_CONCURRENT = 512, @@ -74,18 +73,15 @@ struct io_wq_work { struct files_struct *files; struct mm_struct *mm; const struct cred *creds; + struct fs_struct *fs; unsigned flags; + pid_t task_pid; }; -#define INIT_IO_WORK(work, _func) \ - do { \ - (work)->list.next = NULL; \ - (work)->func = _func; \ - (work)->flags = 0; \ - (work)->files = NULL; \ - (work)->mm = NULL; \ - (work)->creds = NULL; \ - } while (0) \ +#define INIT_IO_WORK(work, _func) \ + do { \ + *(work) = (struct io_wq_work){ .func = _func }; \ + } while (0) \ typedef void (get_work_fn)(struct io_wq_work *); typedef void (put_work_fn)(struct io_wq_work *); @@ -103,10 +99,10 @@ void io_wq_destroy(struct io_wq *wq); void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work); void io_wq_enqueue_hashed(struct io_wq *wq, struct io_wq_work *work, void *val); -void io_wq_flush(struct io_wq *wq); void io_wq_cancel_all(struct io_wq *wq); enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork); +enum io_wq_cancel io_wq_cancel_pid(struct io_wq *wq, pid_t pid); typedef bool (work_cancel_fn)(struct io_wq_work *, void *); diff --git a/fs/io_uring.c b/fs/io_uring.c index 77f22c3da30f59108cb207aca8c78c3f23b6720d..3affd96a98ba70da09f76fd8b0ad96f4ee1ac1f3 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -75,6 +75,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -182,17 +183,12 @@ struct fixed_file_table { struct file **files; }; -enum { - FFD_F_ATOMIC, -}; - struct fixed_file_data { struct fixed_file_table *table; struct io_ring_ctx *ctx; struct percpu_ref refs; struct llist_head put_llist; - unsigned long state; struct work_struct ref_work; struct completion done; }; @@ -204,11 +200,11 @@ struct io_ring_ctx { struct { unsigned int flags; - int compat: 1; - int account_mem: 1; - int cq_overflow_flushed: 1; - int drain_next: 1; - int eventfd_async: 1; + unsigned int compat: 1; + unsigned int account_mem: 1; + unsigned int cq_overflow_flushed: 1; + unsigned int drain_next: 1; + unsigned int eventfd_async: 1; /* * Ring buffer of indices into array of io_uring_sqe, which is @@ -347,6 +343,7 @@ struct io_accept { struct sockaddr __user *addr; int __user *addr_len; int flags; + unsigned long nofile; }; struct io_sync { @@ -401,6 +398,7 @@ struct io_open { struct filename *filename; struct statx __user *buffer; struct open_how how; + unsigned long nofile; }; struct io_files_update { @@ -441,6 +439,7 @@ struct io_async_msghdr { struct iovec *iov; struct sockaddr __user *uaddr; struct msghdr msg; + struct sockaddr_storage addr; }; struct io_async_rw { @@ -450,17 +449,12 @@ struct io_async_rw { ssize_t size; }; -struct io_async_open { - struct filename *filename; -}; - struct io_async_ctx { union { struct io_async_rw rw; struct io_async_msghdr msg; struct io_async_connect connect; struct io_timeout_data timeout; - struct io_async_open open; }; }; @@ -483,6 +477,8 @@ enum { REQ_F_MUST_PUNT_BIT, REQ_F_TIMEOUT_NOSEQ_BIT, REQ_F_COMP_LOCKED_BIT, + REQ_F_NEED_CLEANUP_BIT, + REQ_F_OVERFLOW_BIT, }; enum { @@ -521,6 +517,10 @@ enum { REQ_F_TIMEOUT_NOSEQ = BIT(REQ_F_TIMEOUT_NOSEQ_BIT), /* completion under lock */ REQ_F_COMP_LOCKED = BIT(REQ_F_COMP_LOCKED_BIT), + /* needs cleanup */ + REQ_F_NEED_CLEANUP = BIT(REQ_F_NEED_CLEANUP_BIT), + /* in overflow list */ + REQ_F_OVERFLOW = BIT(REQ_F_OVERFLOW_BIT), }; /* @@ -553,7 +553,6 @@ struct io_kiocb { * llist_node is only used for poll deferred completions */ struct llist_node llist_node; - bool has_user; bool in_async; bool needs_fixed_file; u8 opcode; @@ -614,6 +613,8 @@ struct io_op_def { unsigned not_supported : 1; /* needs file table */ unsigned file_table : 1; + /* needs ->fs */ + unsigned needs_fs : 1; }; static const struct io_op_def io_op_defs[] = { @@ -656,12 +657,14 @@ static const struct io_op_def io_op_defs[] = { .needs_mm = 1, .needs_file = 1, .unbound_nonreg_file = 1, + .needs_fs = 1, }, [IORING_OP_RECVMSG] = { .async_ctx = 1, .needs_mm = 1, .needs_file = 1, .unbound_nonreg_file = 1, + .needs_fs = 1, }, [IORING_OP_TIMEOUT] = { .async_ctx = 1, @@ -692,6 +695,7 @@ static const struct io_op_def io_op_defs[] = { .needs_file = 1, .fd_non_neg = 1, .file_table = 1, + .needs_fs = 1, }, [IORING_OP_CLOSE] = { .needs_file = 1, @@ -705,6 +709,7 @@ static const struct io_op_def io_op_defs[] = { .needs_mm = 1, .needs_file = 1, .fd_non_neg = 1, + .needs_fs = 1, }, [IORING_OP_READ] = { .needs_mm = 1, @@ -736,6 +741,7 @@ static const struct io_op_def io_op_defs[] = { .needs_file = 1, .fd_non_neg = 1, .file_table = 1, + .needs_fs = 1, }, [IORING_OP_EPOLL_CTL] = { .unbound_nonreg_file = 1, @@ -754,6 +760,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, unsigned nr_args); static int io_grab_files(struct io_kiocb *req); static void io_ring_file_ref_flush(struct fixed_file_data *data); +static void io_cleanup_req(struct io_kiocb *req); static struct kmem_cache *req_cachep; @@ -909,6 +916,18 @@ static inline void io_req_work_grab_env(struct io_kiocb *req, } if (!req->work.creds) req->work.creds = get_current_cred(); + if (!req->work.fs && def->needs_fs) { + spin_lock(¤t->fs->lock); + if (!current->fs->in_exec) { + req->work.fs = current->fs; + req->work.fs->users++; + } else { + req->work.flags |= IO_WQ_WORK_CANCEL; + } + spin_unlock(¤t->fs->lock); + } + if (!req->work.task_pid) + req->work.task_pid = task_pid_vnr(current); } static inline void io_req_work_drop_env(struct io_kiocb *req) @@ -921,6 +940,16 @@ static inline void io_req_work_drop_env(struct io_kiocb *req) put_cred(req->work.creds); req->work.creds = NULL; } + if (req->work.fs) { + struct fs_struct *fs = req->work.fs; + + spin_lock(&req->work.fs->lock); + if (--fs->users) + fs = NULL; + spin_unlock(&req->work.fs->lock); + if (fs) + free_fs_struct(fs); + } } static inline bool io_prep_async_work(struct io_kiocb *req, @@ -972,6 +1001,7 @@ static void io_kill_timeout(struct io_kiocb *req) if (ret != -1) { atomic_inc(&req->ctx->cq_timeouts); list_del_init(&req->list); + req->flags |= REQ_F_COMP_LOCKED; io_cqring_fill_event(req, 0); io_put_req(req); } @@ -1074,6 +1104,7 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) req = list_first_entry(&ctx->cq_overflow_list, struct io_kiocb, list); list_move(&req->list, &list); + req->flags &= ~REQ_F_OVERFLOW; if (cqe) { WRITE_ONCE(cqe->user_data, req->user_data); WRITE_ONCE(cqe->res, req->result); @@ -1126,6 +1157,7 @@ static void io_cqring_fill_event(struct io_kiocb *req, long res) set_bit(0, &ctx->sq_check_overflow); set_bit(0, &ctx->cq_check_overflow); } + req->flags |= REQ_F_OVERFLOW; refcount_inc(&req->refs); req->result = res; list_add_tail(&req->list, &ctx->cq_overflow_list); @@ -1226,6 +1258,9 @@ static void __io_req_aux_free(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; + if (req->flags & REQ_F_NEED_CLEANUP) + io_cleanup_req(req); + kfree(req->io); if (req->file) { if (req->flags & REQ_F_FIXED_FILE) @@ -1446,10 +1481,10 @@ static void io_free_req(struct io_kiocb *req) __attribute__((nonnull)) static void io_put_req_find_next(struct io_kiocb *req, struct io_kiocb **nxtptr) { - io_req_find_next(req, nxtptr); - - if (refcount_dec_and_test(&req->refs)) + if (refcount_dec_and_test(&req->refs)) { + io_req_find_next(req, nxtptr); __io_free_req(req); + } } static void io_put_req(struct io_kiocb *req) @@ -1635,11 +1670,17 @@ static void io_iopoll_reap_events(struct io_ring_ctx *ctx) mutex_unlock(&ctx->uring_lock); } -static int __io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events, - long min) +static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events, + long min) { int iters = 0, ret = 0; + /* + * We disallow the app entering submit/complete with polling, but we + * still need to lock the ring to prevent racing with polled issue + * that got punted to a workqueue. + */ + mutex_lock(&ctx->uring_lock); do { int tmin = 0; @@ -1675,21 +1716,6 @@ static int __io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events, ret = 0; } while (min && !*nr_events && !need_resched()); - return ret; -} - -static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events, - long min) -{ - int ret; - - /* - * We disallow the app entering submit/complete with polling, but we - * still need to lock the ring to prevent racing with polled issue - * that got punted to a workqueue. - */ - mutex_lock(&ctx->uring_lock); - ret = __io_iopoll_check(ctx, nr_events, min); mutex_unlock(&ctx->uring_lock); return ret; } @@ -1793,6 +1819,10 @@ static void io_iopoll_req_issued(struct io_kiocb *req) list_add(&req->list, &ctx->poll_list); else list_add_tail(&req->list, &ctx->poll_list); + + if ((ctx->flags & IORING_SETUP_SQPOLL) && + wq_has_sleeper(&ctx->sqo_wait)) + wake_up(&ctx->sqo_wait); } static void io_file_put(struct io_submit_state *state) @@ -2043,7 +2073,7 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req, ssize_t ret; ret = import_single_range(rw, buf, sqe_len, *iovec, iter); *iovec = NULL; - return ret; + return ret < 0 ? ret : sqe_len; } if (req->io) { @@ -2056,9 +2086,6 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req, return iorw->size; } - if (!req->has_user) - return -EFAULT; - #ifdef CONFIG_COMPAT if (req->ctx->compat) return compat_import_iovec(rw, buf, sqe_len, UIO_FASTIOV, @@ -2137,6 +2164,8 @@ static void io_req_map_rw(struct io_kiocb *req, ssize_t io_size, req->io->rw.iov = req->io->rw.fast_iov; memcpy(req->io->rw.iov, fast_iov, sizeof(struct iovec) * iter->nr_segs); + } else { + req->flags |= REQ_F_NEED_CLEANUP; } } @@ -2148,17 +2177,6 @@ static int io_alloc_async_ctx(struct io_kiocb *req) return req->io == NULL; } -static void io_rw_async(struct io_wq_work **workptr) -{ - struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work); - struct iovec *iov = NULL; - - if (req->io->rw.iov != req->io->rw.fast_iov) - iov = req->io->rw.iov; - io_wq_submit_work(workptr); - kfree(iov); -} - static int io_setup_async_rw(struct io_kiocb *req, ssize_t io_size, struct iovec *iovec, struct iovec *fast_iov, struct iov_iter *iter) @@ -2171,7 +2189,6 @@ static int io_setup_async_rw(struct io_kiocb *req, ssize_t io_size, io_req_map_rw(req, io_size, iovec, fast_iov, iter); } - req->work.func = io_rw_async; return 0; } @@ -2189,7 +2206,8 @@ static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, if (unlikely(!(req->file->f_mode & FMODE_READ))) return -EBADF; - if (!req->io) + /* either don't need iovec imported or already have it */ + if (!req->io || req->flags & REQ_F_NEED_CLEANUP) return 0; io = req->io; @@ -2258,8 +2276,8 @@ static int io_read(struct io_kiocb *req, struct io_kiocb **nxt, } } out_free: - if (!io_wq_current_is_worker()) - kfree(iovec); + kfree(iovec); + req->flags &= ~REQ_F_NEED_CLEANUP; return ret; } @@ -2277,7 +2295,8 @@ static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, if (unlikely(!(req->file->f_mode & FMODE_WRITE))) return -EBADF; - if (!req->io) + /* either don't need iovec imported or already have it */ + if (!req->io || req->flags & REQ_F_NEED_CLEANUP) return 0; io = req->io; @@ -2352,6 +2371,12 @@ static int io_write(struct io_kiocb *req, struct io_kiocb **nxt, ret2 = call_write_iter(req->file, kiocb, &iter); else ret2 = loop_rw_iter(WRITE, req->file, kiocb, &iter); + /* + * Raw bdev writes will -EOPNOTSUPP for IOCB_NOWAIT. Just + * retry them without IOCB_NOWAIT. + */ + if (ret2 == -EOPNOTSUPP && (kiocb->ki_flags & IOCB_NOWAIT)) + ret2 = -EAGAIN; if (!force_nonblock || ret2 != -EAGAIN) { kiocb_done(kiocb, ret2, nxt, req->in_async); } else { @@ -2364,8 +2389,8 @@ static int io_write(struct io_kiocb *req, struct io_kiocb **nxt, } } out_free: - if (!io_wq_current_is_worker()) - kfree(iovec); + req->flags &= ~REQ_F_NEED_CLEANUP; + kfree(iovec); return ret; } @@ -2485,6 +2510,9 @@ static void io_fallocate_finish(struct io_wq_work **workptr) struct io_kiocb *nxt = NULL; int ret; + if (io_req_cancelled(req)) + return; + ret = vfs_fallocate(req->file, req->sync.mode, req->sync.off, req->sync.len); if (ret < 0) @@ -2534,6 +2562,10 @@ static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (sqe->ioprio || sqe->buf_index) return -EINVAL; + if (sqe->flags & IOSQE_FIXED_FILE) + return -EBADF; + if (req->flags & REQ_F_NEED_CLEANUP) + return 0; req->open.dfd = READ_ONCE(sqe->fd); req->open.how.mode = READ_ONCE(sqe->len); @@ -2547,6 +2579,8 @@ static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return ret; } + req->open.nofile = rlimit(RLIMIT_NOFILE); + req->flags |= REQ_F_NEED_CLEANUP; return 0; } @@ -2559,6 +2593,10 @@ static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (sqe->ioprio || sqe->buf_index) return -EINVAL; + if (sqe->flags & IOSQE_FIXED_FILE) + return -EBADF; + if (req->flags & REQ_F_NEED_CLEANUP) + return 0; req->open.dfd = READ_ONCE(sqe->fd); fname = u64_to_user_ptr(READ_ONCE(sqe->addr)); @@ -2583,6 +2621,8 @@ static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return ret; } + req->open.nofile = rlimit(RLIMIT_NOFILE); + req->flags |= REQ_F_NEED_CLEANUP; return 0; } @@ -2600,7 +2640,7 @@ static int io_openat2(struct io_kiocb *req, struct io_kiocb **nxt, if (ret) goto err; - ret = get_unused_fd_flags(req->open.how.flags); + ret = __get_unused_fd_flags(req->open.how.flags, req->open.nofile); if (ret < 0) goto err; @@ -2614,6 +2654,7 @@ static int io_openat2(struct io_kiocb *req, struct io_kiocb **nxt, } err: putname(req->open.filename); + req->flags &= ~REQ_F_NEED_CLEANUP; if (ret < 0) req_set_fail_links(req); io_cqring_add_event(req, ret); @@ -2754,6 +2795,10 @@ static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (sqe->ioprio || sqe->buf_index) return -EINVAL; + if (sqe->flags & IOSQE_FIXED_FILE) + return -EBADF; + if (req->flags & REQ_F_NEED_CLEANUP) + return 0; req->open.dfd = READ_ONCE(sqe->fd); req->open.mask = READ_ONCE(sqe->len); @@ -2771,6 +2816,7 @@ static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return ret; } + req->flags |= REQ_F_NEED_CLEANUP; return 0; } @@ -2808,6 +2854,7 @@ static int io_statx(struct io_kiocb *req, struct io_kiocb **nxt, ret = cp_statx(&stat, ctx->buffer); err: putname(ctx->filename); + req->flags &= ~REQ_F_NEED_CLEANUP; if (ret < 0) req_set_fail_links(req); io_cqring_add_event(req, ret); @@ -2827,7 +2874,7 @@ static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) sqe->rw_flags || sqe->buf_index) return -EINVAL; if (sqe->flags & IOSQE_FIXED_FILE) - return -EINVAL; + return -EBADF; req->close.fd = READ_ONCE(sqe->fd); if (req->file->f_op == &io_uring_fops || @@ -2837,24 +2884,26 @@ static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; } +/* only called when __close_fd_get_file() is done */ +static void __io_close_finish(struct io_kiocb *req, struct io_kiocb **nxt) +{ + int ret; + + ret = filp_close(req->close.put_file, req->work.files); + if (ret < 0) + req_set_fail_links(req); + io_cqring_add_event(req, ret); + fput(req->close.put_file); + io_put_req_find_next(req, nxt); +} + static void io_close_finish(struct io_wq_work **workptr) { struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work); struct io_kiocb *nxt = NULL; - /* Invoked with files, we need to do the close */ - if (req->work.files) { - int ret; - - ret = filp_close(req->close.put_file, req->work.files); - if (ret < 0) - req_set_fail_links(req); - io_cqring_add_event(req, ret); - } - - fput(req->close.put_file); - - io_put_req_find_next(req, &nxt); + /* not cancellable, don't do io_req_cancelled() */ + __io_close_finish(req, &nxt); if (nxt) io_wq_assign_next(workptr, nxt); } @@ -2877,22 +2926,8 @@ static int io_close(struct io_kiocb *req, struct io_kiocb **nxt, * No ->flush(), safely close from here and just punt the * fput() to async context. */ - ret = filp_close(req->close.put_file, current->files); - - if (ret < 0) - req_set_fail_links(req); - io_cqring_add_event(req, ret); - - if (io_wq_current_is_worker()) { - struct io_wq_work *old_work, *work; - - old_work = work = &req->work; - io_close_finish(&work); - if (work && work != old_work) - *nxt = container_of(work, struct io_kiocb, work); - return 0; - } - + __io_close_finish(req, nxt); + return 0; eagain: req->work.func = io_close_finish; /* @@ -2960,35 +2995,34 @@ static int io_sync_file_range(struct io_kiocb *req, struct io_kiocb **nxt, return 0; } -#if defined(CONFIG_NET) -static void io_sendrecv_async(struct io_wq_work **workptr) -{ - struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work); - struct iovec *iov = NULL; - - if (req->io->rw.iov != req->io->rw.fast_iov) - iov = req->io->msg.iov; - io_wq_submit_work(workptr); - kfree(iov); -} -#endif - static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { #if defined(CONFIG_NET) struct io_sr_msg *sr = &req->sr_msg; struct io_async_ctx *io = req->io; + int ret; sr->msg_flags = READ_ONCE(sqe->msg_flags); sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr)); sr->len = READ_ONCE(sqe->len); +#ifdef CONFIG_COMPAT + if (req->ctx->compat) + sr->msg_flags |= MSG_CMSG_COMPAT; +#endif + if (!io || req->opcode == IORING_OP_SEND) return 0; + /* iovec is already imported */ + if (req->flags & REQ_F_NEED_CLEANUP) + return 0; io->msg.iov = io->msg.fast_iov; - return sendmsg_copy_msghdr(&io->msg.msg, sr->msg, sr->msg_flags, + ret = sendmsg_copy_msghdr(&io->msg.msg, sr->msg, sr->msg_flags, &io->msg.iov); + if (!ret) + req->flags |= REQ_F_NEED_CLEANUP; + return ret; #else return -EOPNOTSUPP; #endif @@ -3008,12 +3042,11 @@ static int io_sendmsg(struct io_kiocb *req, struct io_kiocb **nxt, sock = sock_from_file(req->file, &ret); if (sock) { struct io_async_ctx io; - struct sockaddr_storage addr; unsigned flags; if (req->io) { kmsg = &req->io->msg; - kmsg->msg.msg_name = &addr; + kmsg->msg.msg_name = &req->io->msg.addr; /* if iov is set, it's allocated already */ if (!kmsg->iov) kmsg->iov = kmsg->fast_iov; @@ -3022,7 +3055,7 @@ static int io_sendmsg(struct io_kiocb *req, struct io_kiocb **nxt, struct io_sr_msg *sr = &req->sr_msg; kmsg = &io.msg; - kmsg->msg.msg_name = &addr; + kmsg->msg.msg_name = &io.msg.addr; io.msg.iov = io.msg.fast_iov; ret = sendmsg_copy_msghdr(&io.msg.msg, sr->msg, @@ -3041,18 +3074,22 @@ static int io_sendmsg(struct io_kiocb *req, struct io_kiocb **nxt, if (force_nonblock && ret == -EAGAIN) { if (req->io) return -EAGAIN; - if (io_alloc_async_ctx(req)) + if (io_alloc_async_ctx(req)) { + if (kmsg->iov != kmsg->fast_iov) + kfree(kmsg->iov); return -ENOMEM; + } + req->flags |= REQ_F_NEED_CLEANUP; memcpy(&req->io->msg, &io.msg, sizeof(io.msg)); - req->work.func = io_sendrecv_async; return -EAGAIN; } if (ret == -ERESTARTSYS) ret = -EINTR; } - if (!io_wq_current_is_worker() && kmsg && kmsg->iov != kmsg->fast_iov) + if (kmsg && kmsg->iov != kmsg->fast_iov) kfree(kmsg->iov); + req->flags &= ~REQ_F_NEED_CLEANUP; io_cqring_add_event(req, ret); if (ret < 0) req_set_fail_links(req); @@ -3120,17 +3157,29 @@ static int io_recvmsg_prep(struct io_kiocb *req, #if defined(CONFIG_NET) struct io_sr_msg *sr = &req->sr_msg; struct io_async_ctx *io = req->io; + int ret; sr->msg_flags = READ_ONCE(sqe->msg_flags); sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr)); sr->len = READ_ONCE(sqe->len); +#ifdef CONFIG_COMPAT + if (req->ctx->compat) + sr->msg_flags |= MSG_CMSG_COMPAT; +#endif + if (!io || req->opcode == IORING_OP_RECV) return 0; + /* iovec is already imported */ + if (req->flags & REQ_F_NEED_CLEANUP) + return 0; io->msg.iov = io->msg.fast_iov; - return recvmsg_copy_msghdr(&io->msg.msg, sr->msg, sr->msg_flags, + ret = recvmsg_copy_msghdr(&io->msg.msg, sr->msg, sr->msg_flags, &io->msg.uaddr, &io->msg.iov); + if (!ret) + req->flags |= REQ_F_NEED_CLEANUP; + return ret; #else return -EOPNOTSUPP; #endif @@ -3150,12 +3199,11 @@ static int io_recvmsg(struct io_kiocb *req, struct io_kiocb **nxt, sock = sock_from_file(req->file, &ret); if (sock) { struct io_async_ctx io; - struct sockaddr_storage addr; unsigned flags; if (req->io) { kmsg = &req->io->msg; - kmsg->msg.msg_name = &addr; + kmsg->msg.msg_name = &req->io->msg.addr; /* if iov is set, it's allocated already */ if (!kmsg->iov) kmsg->iov = kmsg->fast_iov; @@ -3164,7 +3212,7 @@ static int io_recvmsg(struct io_kiocb *req, struct io_kiocb **nxt, struct io_sr_msg *sr = &req->sr_msg; kmsg = &io.msg; - kmsg->msg.msg_name = &addr; + kmsg->msg.msg_name = &io.msg.addr; io.msg.iov = io.msg.fast_iov; ret = recvmsg_copy_msghdr(&io.msg.msg, sr->msg, @@ -3185,18 +3233,22 @@ static int io_recvmsg(struct io_kiocb *req, struct io_kiocb **nxt, if (force_nonblock && ret == -EAGAIN) { if (req->io) return -EAGAIN; - if (io_alloc_async_ctx(req)) + if (io_alloc_async_ctx(req)) { + if (kmsg->iov != kmsg->fast_iov) + kfree(kmsg->iov); return -ENOMEM; + } memcpy(&req->io->msg, &io.msg, sizeof(io.msg)); - req->work.func = io_sendrecv_async; + req->flags |= REQ_F_NEED_CLEANUP; return -EAGAIN; } if (ret == -ERESTARTSYS) ret = -EINTR; } - if (!io_wq_current_is_worker() && kmsg && kmsg->iov != kmsg->fast_iov) + if (kmsg && kmsg->iov != kmsg->fast_iov) kfree(kmsg->iov); + req->flags &= ~REQ_F_NEED_CLEANUP; io_cqring_add_event(req, ret); if (ret < 0) req_set_fail_links(req); @@ -3273,6 +3325,7 @@ static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) accept->addr = u64_to_user_ptr(READ_ONCE(sqe->addr)); accept->addr_len = u64_to_user_ptr(READ_ONCE(sqe->addr2)); accept->flags = READ_ONCE(sqe->accept_flags); + accept->nofile = rlimit(RLIMIT_NOFILE); return 0; #else return -EOPNOTSUPP; @@ -3289,7 +3342,8 @@ static int __io_accept(struct io_kiocb *req, struct io_kiocb **nxt, file_flags = force_nonblock ? O_NONBLOCK : 0; ret = __sys_accept4_file(req->file, file_flags, accept->addr, - accept->addr_len, accept->flags); + accept->addr_len, accept->flags, + accept->nofile); if (ret == -EAGAIN && force_nonblock) return -EAGAIN; if (ret == -ERESTARTSYS) @@ -4083,6 +4137,9 @@ static int io_req_defer_prep(struct io_kiocb *req, { ssize_t ret = 0; + if (!sqe) + return 0; + if (io_op_defs[req->opcode].file_table) { ret = io_grab_files(req); if (unlikely(ret)) @@ -4207,6 +4264,35 @@ static int io_req_defer(struct io_kiocb *req, const struct io_uring_sqe *sqe) return -EIOCBQUEUED; } +static void io_cleanup_req(struct io_kiocb *req) +{ + struct io_async_ctx *io = req->io; + + switch (req->opcode) { + case IORING_OP_READV: + case IORING_OP_READ_FIXED: + case IORING_OP_READ: + case IORING_OP_WRITEV: + case IORING_OP_WRITE_FIXED: + case IORING_OP_WRITE: + if (io->rw.iov != io->rw.fast_iov) + kfree(io->rw.iov); + break; + case IORING_OP_SENDMSG: + case IORING_OP_RECVMSG: + if (io->msg.iov != io->msg.fast_iov) + kfree(io->msg.iov); + break; + case IORING_OP_OPENAT: + case IORING_OP_OPENAT2: + case IORING_OP_STATX: + putname(req->open.filename); + break; + } + + req->flags &= ~REQ_F_NEED_CLEANUP; +} + static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, struct io_kiocb **nxt, bool force_nonblock) { @@ -4446,7 +4532,6 @@ static void io_wq_submit_work(struct io_wq_work **workptr) } if (!ret) { - req->has_user = (work->flags & IO_WQ_WORK_HAS_MM) != 0; req->in_async = true; do { ret = io_issue_sqe(req, NULL, &nxt, false); @@ -4479,7 +4564,7 @@ static int io_req_needs_file(struct io_kiocb *req, int fd) { if (!io_op_defs[req->opcode].needs_file) return 0; - if (fd == -1 && io_op_defs[req->opcode].fd_non_neg) + if ((fd == -1 || fd == AT_FDCWD) && io_op_defs[req->opcode].fd_non_neg) return 0; return 1; } @@ -4639,11 +4724,21 @@ static void __io_queue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_kiocb *linked_timeout; struct io_kiocb *nxt = NULL; + const struct cred *old_creds = NULL; int ret; again: linked_timeout = io_prep_linked_timeout(req); + if (req->work.creds && req->work.creds != current_cred()) { + if (old_creds) + revert_creds(old_creds); + if (old_creds == req->work.creds) + old_creds = NULL; /* restored original creds */ + else + old_creds = override_creds(req->work.creds); + } + ret = io_issue_sqe(req, sqe, &nxt, true); /* @@ -4669,7 +4764,7 @@ static void __io_queue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe) err: /* drop submission reference */ - io_put_req(req); + io_put_req_find_next(req, &nxt); if (linked_timeout) { if (!ret) @@ -4693,6 +4788,8 @@ static void __io_queue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe) goto punt; goto again; } + if (old_creds) + revert_creds(old_creds); } static void io_queue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe) @@ -4737,7 +4834,6 @@ static inline void io_queue_link_head(struct io_kiocb *req) static bool io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, struct io_submit_state *state, struct io_kiocb **link) { - const struct cred *old_creds = NULL; struct io_ring_ctx *ctx = req->ctx; unsigned int sqe_flags; int ret, id; @@ -4752,14 +4848,12 @@ static bool io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, id = READ_ONCE(sqe->personality); if (id) { - const struct cred *personality_creds; - - personality_creds = idr_find(&ctx->personality_idr, id); - if (unlikely(!personality_creds)) { + req->work.creds = idr_find(&ctx->personality_idr, id); + if (unlikely(!req->work.creds)) { ret = -EINVAL; goto err_req; } - old_creds = override_creds(personality_creds); + get_cred(req->work.creds); } /* same numerical values with corresponding REQ_F_*, safe to copy */ @@ -4771,8 +4865,6 @@ static bool io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, err_req: io_cqring_add_event(req, ret); io_double_put_req(req); - if (old_creds) - revert_creds(old_creds); return false; } @@ -4824,6 +4916,11 @@ static bool io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, if (sqe_flags & (IOSQE_IO_LINK|IOSQE_IO_HARDLINK)) { req->flags |= REQ_F_LINK; INIT_LIST_HEAD(&req->link_list); + + if (io_alloc_async_ctx(req)) { + ret = -EAGAIN; + goto err_req; + } ret = io_req_defer_prep(req, sqe); if (ret) req->flags |= REQ_F_FAIL_LINK; @@ -4833,8 +4930,6 @@ static bool io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, } } - if (old_creds) - revert_creds(old_creds); return true; } @@ -4950,6 +5045,7 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr, for (i = 0; i < nr; i++) { const struct io_uring_sqe *sqe; struct io_kiocb *req; + int err; req = io_get_req(ctx, statep); if (unlikely(!req)) { @@ -4966,20 +5062,23 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr, submitted++; if (unlikely(req->opcode >= IORING_OP_LAST)) { - io_cqring_add_event(req, -EINVAL); + err = -EINVAL; +fail_req: + io_cqring_add_event(req, err); io_double_put_req(req); break; } if (io_op_defs[req->opcode].needs_mm && !*mm) { mm_fault = mm_fault || !mmget_not_zero(ctx->sqo_mm); - if (!mm_fault) { - use_mm(ctx->sqo_mm); - *mm = ctx->sqo_mm; + if (unlikely(mm_fault)) { + err = -EFAULT; + goto fail_req; } + use_mm(ctx->sqo_mm); + *mm = ctx->sqo_mm; } - req->has_user = *mm != NULL; req->in_async = async; req->needs_fixed_file = async; trace_io_uring_submit_sqe(ctx, req->opcode, req->user_data, @@ -5011,9 +5110,8 @@ static int io_sq_thread(void *data) const struct cred *old_cred; mm_segment_t old_fs; DEFINE_WAIT(wait); - unsigned inflight; unsigned long timeout; - int ret; + int ret = 0; complete(&ctx->completions[1]); @@ -5021,39 +5119,19 @@ static int io_sq_thread(void *data) set_fs(USER_DS); old_cred = override_creds(ctx->creds); - ret = timeout = inflight = 0; + timeout = jiffies + ctx->sq_thread_idle; while (!kthread_should_park()) { unsigned int to_submit; - if (inflight) { + if (!list_empty(&ctx->poll_list)) { unsigned nr_events = 0; - if (ctx->flags & IORING_SETUP_IOPOLL) { - /* - * inflight is the count of the maximum possible - * entries we submitted, but it can be smaller - * if we dropped some of them. If we don't have - * poll entries available, then we know that we - * have nothing left to poll for. Reset the - * inflight count to zero in that case. - */ - mutex_lock(&ctx->uring_lock); - if (!list_empty(&ctx->poll_list)) - __io_iopoll_check(ctx, &nr_events, 0); - else - inflight = 0; - mutex_unlock(&ctx->uring_lock); - } else { - /* - * Normal IO, just pretend everything completed. - * We don't have to poll completions for that. - */ - nr_events = inflight; - } - - inflight -= nr_events; - if (!inflight) + mutex_lock(&ctx->uring_lock); + if (!list_empty(&ctx->poll_list)) + io_iopoll_getevents(ctx, &nr_events, 0); + else timeout = jiffies + ctx->sq_thread_idle; + mutex_unlock(&ctx->uring_lock); } to_submit = io_sqring_entries(ctx); @@ -5063,6 +5141,18 @@ static int io_sq_thread(void *data) * to enter the kernel to reap and flush events. */ if (!to_submit || ret == -EBUSY) { + /* + * Drop cur_mm before scheduling, we can't hold it for + * long periods (or over schedule()). Do this before + * adding ourselves to the waitqueue, as the unuse/drop + * may sleep. + */ + if (cur_mm) { + unuse_mm(cur_mm); + mmput(cur_mm); + cur_mm = NULL; + } + /* * We're polling. If we're within the defined idle * period, then let us spin without work before going @@ -5070,28 +5160,29 @@ static int io_sq_thread(void *data) * more IO, we should wait for the application to * reap events and wake us up. */ - if (inflight || + if (!list_empty(&ctx->poll_list) || (!time_after(jiffies, timeout) && ret != -EBUSY && !percpu_ref_is_dying(&ctx->refs))) { cond_resched(); continue; } + prepare_to_wait(&ctx->sqo_wait, &wait, + TASK_INTERRUPTIBLE); + /* - * Drop cur_mm before scheduling, we can't hold it for - * long periods (or over schedule()). Do this before - * adding ourselves to the waitqueue, as the unuse/drop - * may sleep. + * While doing polled IO, before going to sleep, we need + * to check if there are new reqs added to poll_list, it + * is because reqs may have been punted to io worker and + * will be added to poll_list later, hence check the + * poll_list again. */ - if (cur_mm) { - unuse_mm(cur_mm); - mmput(cur_mm); - cur_mm = NULL; + if ((ctx->flags & IORING_SETUP_IOPOLL) && + !list_empty_careful(&ctx->poll_list)) { + finish_wait(&ctx->sqo_wait, &wait); + continue; } - prepare_to_wait(&ctx->sqo_wait, &wait, - TASK_INTERRUPTIBLE); - /* Tell userspace we may need a wakeup call */ ctx->rings->sq_flags |= IORING_SQ_NEED_WAKEUP; /* make sure to read SQ tail after writing flags */ @@ -5119,8 +5210,7 @@ static int io_sq_thread(void *data) mutex_lock(&ctx->uring_lock); ret = io_submit_sqes(ctx, to_submit, NULL, -1, &cur_mm, true); mutex_unlock(&ctx->uring_lock); - if (ret > 0) - inflight += ret; + timeout = jiffies + ctx->sq_thread_idle; } set_fs(old_fs); @@ -5254,6 +5344,23 @@ static void io_file_ref_kill(struct percpu_ref *ref) complete(&data->done); } +static void io_file_ref_exit_and_free(struct work_struct *work) +{ + struct fixed_file_data *data; + + data = container_of(work, struct fixed_file_data, ref_work); + + /* + * Ensure any percpu-ref atomic switch callback has run, it could have + * been in progress when the files were being unregistered. Once + * that's done, we can safely exit and free the ref and containing + * data structure. + */ + rcu_barrier(); + percpu_ref_exit(&data->refs); + kfree(data); +} + static int io_sqe_files_unregister(struct io_ring_ctx *ctx) { struct fixed_file_data *data = ctx->file_data; @@ -5266,14 +5373,14 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx) flush_work(&data->ref_work); wait_for_completion(&data->done); io_ring_file_ref_flush(data); - percpu_ref_exit(&data->refs); __io_sqe_files_unregister(ctx); nr_tables = DIV_ROUND_UP(ctx->nr_user_files, IORING_MAX_FILES_TABLE); for (i = 0; i < nr_tables; i++) kfree(data->table[i].files); kfree(data->table); - kfree(data); + INIT_WORK(&data->ref_work, io_file_ref_exit_and_free); + queue_work(system_wq, &data->ref_work); ctx->file_data = NULL; ctx->nr_user_files = 0; return 0; @@ -5525,7 +5632,6 @@ static void io_ring_file_ref_switch(struct work_struct *work) data = container_of(work, struct fixed_file_data, ref_work); io_ring_file_ref_flush(data); - percpu_ref_get(&data->refs); percpu_ref_switch_to_percpu(&data->refs); } @@ -5701,8 +5807,13 @@ static void io_atomic_switch(struct percpu_ref *ref) { struct fixed_file_data *data; + /* + * Juggle reference to ensure we hit zero, if needed, so we can + * switch back to percpu mode + */ data = container_of(ref, struct fixed_file_data, refs); - clear_bit(FFD_F_ATOMIC, &data->state); + percpu_ref_put(&data->refs); + percpu_ref_get(&data->refs); } static bool io_queue_file_removal(struct fixed_file_data *data, @@ -5725,11 +5836,7 @@ static bool io_queue_file_removal(struct fixed_file_data *data, llist_add(&pfile->llist, &data->put_llist); if (pfile == &pfile_stack) { - if (!test_and_set_bit(FFD_F_ATOMIC, &data->state)) { - percpu_ref_put(&data->refs); - percpu_ref_switch_to_atomic(&data->refs, - io_atomic_switch); - } + percpu_ref_switch_to_atomic(&data->refs, io_atomic_switch); wait_for_completion(&done); flush_work(&data->ref_work); return false; @@ -5803,10 +5910,8 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, up->offset++; } - if (ref_switch && !test_and_set_bit(FFD_F_ATOMIC, &data->state)) { - percpu_ref_put(&data->refs); + if (ref_switch) percpu_ref_switch_to_atomic(&data->refs, io_atomic_switch); - } return done ? done : err; } @@ -6264,6 +6369,7 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx) io_sqe_buffer_unregister(ctx); io_sqe_files_unregister(ctx); io_eventfd_unregister(ctx); + idr_destroy(&ctx->personality_idr); #if defined(CONFIG_UNIX) if (ctx->ring_sock) { @@ -6301,7 +6407,7 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait) if (READ_ONCE(ctx->rings->sq.tail) - ctx->cached_sq_head != ctx->rings->sq_ring_entries) mask |= EPOLLOUT | EPOLLWRNORM; - if (READ_ONCE(ctx->rings->cq.head) != ctx->cached_cq_tail) + if (io_cqring_events(ctx, false)) mask |= EPOLLIN | EPOLLRDNORM; return mask; @@ -6393,6 +6499,29 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx, if (!cancel_req) break; + if (cancel_req->flags & REQ_F_OVERFLOW) { + spin_lock_irq(&ctx->completion_lock); + list_del(&cancel_req->list); + cancel_req->flags &= ~REQ_F_OVERFLOW; + if (list_empty(&ctx->cq_overflow_list)) { + clear_bit(0, &ctx->sq_check_overflow); + clear_bit(0, &ctx->cq_check_overflow); + } + spin_unlock_irq(&ctx->completion_lock); + + WRITE_ONCE(ctx->rings->cq_overflow, + atomic_inc_return(&ctx->cached_cq_overflow)); + + /* + * Put inflight ref and overflow ref. If that's + * all we had, then we're done with this request. + */ + if (refcount_sub_and_test(2, &cancel_req->refs)) { + io_put_req(cancel_req); + continue; + } + } + io_wq_cancel_work(ctx->io_wq, &cancel_req->work); io_put_req(cancel_req); schedule(); @@ -6405,6 +6534,13 @@ static int io_uring_flush(struct file *file, void *data) struct io_ring_ctx *ctx = file->private_data; io_uring_cancel_files(ctx, data); + + /* + * If the task is going away, cancel work it may have pending + */ + if (fatal_signal_pending(current) || (current->flags & PF_EXITING)) + io_wq_cancel_pid(ctx->io_wq, task_pid_vnr(current)); + return 0; } @@ -6547,6 +6683,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, return submitted ? submitted : ret; } +#ifdef CONFIG_PROC_FS static int io_uring_show_cred(int id, void *p, void *data) { const struct cred *cred = p; @@ -6620,6 +6757,7 @@ static void io_uring_show_fdinfo(struct seq_file *m, struct file *f) percpu_ref_put(&ctx->refs); } } +#endif static const struct file_operations io_uring_fops = { .release = io_uring_release, @@ -6631,7 +6769,9 @@ static const struct file_operations io_uring_fops = { #endif .poll = io_uring_poll, .fasync = io_uring_fasync, +#ifdef CONFIG_PROC_FS .show_fdinfo = io_uring_show_fdinfo, +#endif }; static int io_allocate_scq_urings(struct io_ring_ctx *ctx, diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 2494095e0340b6c30c450a01c575304b3f4fa4f3..27373f5792a4f7a5a846742cb44e624ad56f5377 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -976,29 +976,33 @@ void jbd2_journal_commit_transaction(journal_t *journal) * it. */ /* - * A buffer which has been freed while still being journaled by - * a previous transaction. - */ - if (buffer_freed(bh)) { + * A buffer which has been freed while still being journaled + * by a previous transaction, refile the buffer to BJ_Forget of + * the running transaction. If the just committed transaction + * contains "add to orphan" operation, we can completely + * invalidate the buffer now. We are rather through in that + * since the buffer may be still accessible when blocksize < + * pagesize and it is attached to the last partial page. + */ + if (buffer_freed(bh) && !jh->b_next_transaction) { + struct address_space *mapping; + + clear_buffer_freed(bh); + clear_buffer_jbddirty(bh); + /* - * If the running transaction is the one containing - * "add to orphan" operation (b_next_transaction != - * NULL), we have to wait for that transaction to - * commit before we can really get rid of the buffer. - * So just clear b_modified to not confuse transaction - * credit accounting and refile the buffer to - * BJ_Forget of the running transaction. If the just - * committed transaction contains "add to orphan" - * operation, we can completely invalidate the buffer - * now. We are rather through in that since the - * buffer may be still accessible when blocksize < - * pagesize and it is attached to the last partial - * page. + * Block device buffers need to stay mapped all the + * time, so it is enough to clear buffer_jbddirty and + * buffer_freed bits. For the file mapping buffers (i.e. + * journalled data) we need to unmap buffer and clear + * more bits. We also need to be careful about the check + * because the data page mapping can get cleared under + * out hands, which alse need not to clear more bits + * because the page and buffers will be freed and can + * never be reused once we are done with them. */ - jh->b_modified = 0; - if (!jh->b_next_transaction) { - clear_buffer_freed(bh); - clear_buffer_jbddirty(bh); + mapping = READ_ONCE(bh->b_page->mapping); + if (mapping && !sb_is_blkdev_sb(mapping->host->i_sb)) { clear_buffer_mapped(bh); clear_buffer_new(bh); clear_buffer_req(bh); diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index e77a5a0b4e46e567336ab894308e1420499576fa..3dccc23cf0102337398c2c7ec99a31aa4e45b192 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -936,8 +936,6 @@ do_get_write_access(handle_t *handle, struct journal_head *jh, char *frozen_buffer = NULL; unsigned long start_lock, time_lock; - if (is_handle_aborted(handle)) - return -EROFS; journal = transaction->t_journal; jbd_debug(5, "journal_head %p, force_copy %d\n", jh, force_copy); @@ -1152,8 +1150,8 @@ static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh, /* For undo access buffer must have data copied */ if (undo && !jh->b_committed_data) goto out; - if (jh->b_transaction != handle->h_transaction && - jh->b_next_transaction != handle->h_transaction) + if (READ_ONCE(jh->b_transaction) != handle->h_transaction && + READ_ONCE(jh->b_next_transaction) != handle->h_transaction) goto out; /* * There are two reasons for the barrier here: @@ -1189,6 +1187,9 @@ int jbd2_journal_get_write_access(handle_t *handle, struct buffer_head *bh) struct journal_head *jh; int rc; + if (is_handle_aborted(handle)) + return -EROFS; + if (jbd2_write_access_granted(handle, bh, false)) return 0; @@ -1326,6 +1327,9 @@ int jbd2_journal_get_undo_access(handle_t *handle, struct buffer_head *bh) struct journal_head *jh; char *committed_data = NULL; + if (is_handle_aborted(handle)) + return -EROFS; + if (jbd2_write_access_granted(handle, bh, true)) return 0; @@ -2329,14 +2333,16 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh, return -EBUSY; } /* - * OK, buffer won't be reachable after truncate. We just set - * j_next_transaction to the running transaction (if there is - * one) and mark buffer as freed so that commit code knows it - * should clear dirty bits when it is done with the buffer. + * OK, buffer won't be reachable after truncate. We just clear + * b_modified to not confuse transaction credit accounting, and + * set j_next_transaction to the running transaction (if there + * is one) and mark buffer as freed so that commit code knows + * it should clear dirty bits when it is done with the buffer. */ set_buffer_freed(bh); if (journal->j_running_transaction && buffer_jbddirty(bh)) jh->b_next_transaction = journal->j_running_transaction; + jh->b_modified = 0; spin_unlock(&journal->j_list_lock); spin_unlock(&jh->b_state_lock); write_unlock(&journal->j_state_lock); @@ -2563,8 +2569,8 @@ bool __jbd2_journal_refile_buffer(struct journal_head *jh) * our jh reference and thus __jbd2_journal_file_buffer() must not * take a new one. */ - jh->b_transaction = jh->b_next_transaction; - jh->b_next_transaction = NULL; + WRITE_ONCE(jh->b_transaction, jh->b_next_transaction); + WRITE_ONCE(jh->b_next_transaction, NULL); if (buffer_freed(bh)) jlist = BJ_Forget; else if (jh->b_modified) diff --git a/fs/locks.c b/fs/locks.c index 44b6da0328426ba0f133733114973f7d7a526e6a..b8a31c1c4fff3c2a4e35c57a953d9bf025569a4b 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -725,7 +725,6 @@ static void __locks_delete_block(struct file_lock *waiter) { locks_delete_global_blocked(waiter); list_del_init(&waiter->fl_blocked_member); - waiter->fl_blocker = NULL; } static void __locks_wake_up_blocks(struct file_lock *blocker) @@ -740,6 +739,13 @@ static void __locks_wake_up_blocks(struct file_lock *blocker) waiter->fl_lmops->lm_notify(waiter); else wake_up(&waiter->fl_wait); + + /* + * The setting of fl_blocker to NULL marks the "done" + * point in deleting a block. Paired with acquire at the top + * of locks_delete_block(). + */ + smp_store_release(&waiter->fl_blocker, NULL); } } @@ -754,24 +760,41 @@ int locks_delete_block(struct file_lock *waiter) int status = -ENOENT; /* - * If fl_blocker is NULL, it won't be set again as this thread - * "owns" the lock and is the only one that might try to claim - * the lock. So it is safe to test fl_blocker locklessly. - * Also if fl_blocker is NULL, this waiter is not listed on - * fl_blocked_requests for some lock, so no other request can - * be added to the list of fl_blocked_requests for this - * request. So if fl_blocker is NULL, it is safe to - * locklessly check if fl_blocked_requests is empty. If both - * of these checks succeed, there is no need to take the lock. + * If fl_blocker is NULL, it won't be set again as this thread "owns" + * the lock and is the only one that might try to claim the lock. + * + * We use acquire/release to manage fl_blocker so that we can + * optimize away taking the blocked_lock_lock in many cases. + * + * The smp_load_acquire guarantees two things: + * + * 1/ that fl_blocked_requests can be tested locklessly. If something + * was recently added to that list it must have been in a locked region + * *before* the locked region when fl_blocker was set to NULL. + * + * 2/ that no other thread is accessing 'waiter', so it is safe to free + * it. __locks_wake_up_blocks is careful not to touch waiter after + * fl_blocker is released. + * + * If a lockless check of fl_blocker shows it to be NULL, we know that + * no new locks can be inserted into its fl_blocked_requests list, and + * can avoid doing anything further if the list is empty. */ - if (waiter->fl_blocker == NULL && + if (!smp_load_acquire(&waiter->fl_blocker) && list_empty(&waiter->fl_blocked_requests)) return status; + spin_lock(&blocked_lock_lock); if (waiter->fl_blocker) status = 0; __locks_wake_up_blocks(waiter); __locks_delete_block(waiter); + + /* + * The setting of fl_blocker to NULL marks the "done" point in deleting + * a block. Paired with acquire at the top of this function. + */ + smp_store_release(&waiter->fl_blocker, NULL); spin_unlock(&blocked_lock_lock); return status; } @@ -1364,7 +1387,8 @@ static int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl) error = posix_lock_inode(inode, fl, NULL); if (error != FILE_LOCK_DEFERRED) break; - error = wait_event_interruptible(fl->fl_wait, !fl->fl_blocker); + error = wait_event_interruptible(fl->fl_wait, + list_empty(&fl->fl_blocked_member)); if (error) break; } @@ -1449,7 +1473,8 @@ int locks_mandatory_area(struct inode *inode, struct file *filp, loff_t start, error = posix_lock_inode(inode, &fl, NULL); if (error != FILE_LOCK_DEFERRED) break; - error = wait_event_interruptible(fl.fl_wait, !fl.fl_blocker); + error = wait_event_interruptible(fl.fl_wait, + list_empty(&fl.fl_blocked_member)); if (!error) { /* * If we've been sleeping someone might have @@ -1652,7 +1677,8 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) locks_dispose_list(&dispose); error = wait_event_interruptible_timeout(new_fl->fl_wait, - !new_fl->fl_blocker, break_time); + list_empty(&new_fl->fl_blocked_member), + break_time); percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); @@ -2136,7 +2162,8 @@ static int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl) error = flock_lock_inode(inode, fl); if (error != FILE_LOCK_DEFERRED) break; - error = wait_event_interruptible(fl->fl_wait, !fl->fl_blocker); + error = wait_event_interruptible(fl->fl_wait, + list_empty(&fl->fl_blocked_member)); if (error) break; } @@ -2413,7 +2440,8 @@ static int do_lock_file_wait(struct file *filp, unsigned int cmd, error = vfs_lock_file(filp, cmd, fl, NULL); if (error != FILE_LOCK_DEFERRED) break; - error = wait_event_interruptible(fl->fl_wait, !fl->fl_blocker); + error = wait_event_interruptible(fl->fl_wait, + list_empty(&fl->fl_blocked_member)); if (error) break; } diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 989c30c98511d9d8404803803e4d1a9b7a462a9a..f1ff3076e4a461d80830103160515576685fee33 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -153,6 +153,7 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init) if ((clp = kzalloc(sizeof(*clp), GFP_KERNEL)) == NULL) goto error_0; + clp->cl_minorversion = cl_init->minorversion; clp->cl_nfs_mod = cl_init->nfs_mod; if (!try_module_get(clp->cl_nfs_mod->owner)) goto error_dealloc; diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 4a841071d8a71dc3a04c89ee44606e6324787acd..1865322de142d0a656e13ac99106fa554bc3d95a 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -42,13 +42,27 @@ static void nfs_mark_delegation_revoked(struct nfs_delegation *delegation) if (!test_and_set_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) { delegation->stateid.type = NFS4_INVALID_STATEID_TYPE; atomic_long_dec(&nfs_active_delegations); + if (!test_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) + nfs_clear_verifier_delegated(delegation->inode); } } +static struct nfs_delegation *nfs_get_delegation(struct nfs_delegation *delegation) +{ + refcount_inc(&delegation->refcount); + return delegation; +} + +static void nfs_put_delegation(struct nfs_delegation *delegation) +{ + if (refcount_dec_and_test(&delegation->refcount)) + __nfs_free_delegation(delegation); +} + static void nfs_free_delegation(struct nfs_delegation *delegation) { nfs_mark_delegation_revoked(delegation); - __nfs_free_delegation(delegation); + nfs_put_delegation(delegation); } /** @@ -241,13 +255,18 @@ void nfs_inode_reclaim_delegation(struct inode *inode, const struct cred *cred, static int nfs_do_return_delegation(struct inode *inode, struct nfs_delegation *delegation, int issync) { + const struct cred *cred; int res = 0; - if (!test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) - res = nfs4_proc_delegreturn(inode, - delegation->cred, + if (!test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) { + spin_lock(&delegation->lock); + cred = get_cred(delegation->cred); + spin_unlock(&delegation->lock); + res = nfs4_proc_delegreturn(inode, cred, &delegation->stateid, issync); + put_cred(cred); + } return res; } @@ -273,9 +292,13 @@ nfs_start_delegation_return_locked(struct nfs_inode *nfsi) if (delegation == NULL) goto out; spin_lock(&delegation->lock); - if (!test_and_set_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) - ret = delegation; + if (!test_and_set_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) { + /* Refcount matched in nfs_end_delegation_return() */ + ret = nfs_get_delegation(delegation); + } spin_unlock(&delegation->lock); + if (ret) + nfs_clear_verifier_delegated(&nfsi->vfs_inode); out: return ret; } @@ -393,6 +416,7 @@ int nfs_inode_set_delegation(struct inode *inode, const struct cred *cred, if (delegation == NULL) return -ENOMEM; nfs4_stateid_copy(&delegation->stateid, stateid); + refcount_set(&delegation->refcount, 1); delegation->type = type; delegation->pagemod_limit = pagemod_limit; delegation->change_attr = inode_peek_iversion_raw(inode); @@ -492,6 +516,8 @@ static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation err = nfs_do_return_delegation(inode, delegation, issync); out: + /* Refcount matched in nfs_start_delegation_return_locked() */ + nfs_put_delegation(delegation); return err; } @@ -686,9 +712,12 @@ void nfs4_inode_return_delegation_on_close(struct inode *inode) list_empty(&NFS_I(inode)->open_files) && !test_and_set_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) { clear_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags); - ret = delegation; + /* Refcount matched in nfs_end_delegation_return() */ + ret = nfs_get_delegation(delegation); } spin_unlock(&delegation->lock); + if (ret) + nfs_clear_verifier_delegated(inode); } out: rcu_read_unlock(); @@ -1088,10 +1117,11 @@ void nfs_delegation_reap_unclaimed(struct nfs_client *clp) delegation = nfs_start_delegation_return_locked(NFS_I(inode)); rcu_read_unlock(); if (delegation != NULL) { - delegation = nfs_detach_delegation(NFS_I(inode), - delegation, server); - if (delegation != NULL) + if (nfs_detach_delegation(NFS_I(inode), delegation, + server) != NULL) nfs_free_delegation(delegation); + /* Match nfs_start_delegation_return_locked */ + nfs_put_delegation(delegation); } iput(inode); nfs_sb_deactive(server->super); diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h index 31b84604d3836c44bca2377e454efba231eb3506..9b00a0b7f8321fab75eeb6b732e9578b54086010 100644 --- a/fs/nfs/delegation.h +++ b/fs/nfs/delegation.h @@ -22,6 +22,7 @@ struct nfs_delegation { unsigned long pagemod_limit; __u64 change_attr; unsigned long flags; + refcount_t refcount; spinlock_t lock; struct rcu_head rcu; }; diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 1320288ff9ec9c7d50d207908d77f3899c7def3b..193d6fb363b7434ae629fc48992812a198b47ec3 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -155,6 +155,7 @@ typedef struct { loff_t current_index; decode_dirent_t decode; + unsigned long dir_verifier; unsigned long timestamp; unsigned long gencount; unsigned int cache_entry_index; @@ -353,6 +354,7 @@ int nfs_readdir_xdr_filler(struct page **pages, nfs_readdir_descriptor_t *desc, again: timestamp = jiffies; gencount = nfs_inc_attr_generation_counter(); + desc->dir_verifier = nfs_save_change_attribute(inode); error = NFS_PROTO(inode)->readdir(file_dentry(file), cred, entry->cookie, pages, NFS_SERVER(inode)->dtsize, desc->plus); if (error < 0) { @@ -455,13 +457,13 @@ void nfs_force_use_readdirplus(struct inode *dir) } static -void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry) +void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry, + unsigned long dir_verifier) { struct qstr filename = QSTR_INIT(entry->name, entry->len); DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); struct dentry *dentry; struct dentry *alias; - struct inode *dir = d_inode(parent); struct inode *inode; int status; @@ -500,7 +502,7 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry) if (nfs_same_file(dentry, entry)) { if (!entry->fh->size) goto out; - nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); + nfs_set_verifier(dentry, dir_verifier); status = nfs_refresh_inode(d_inode(dentry), entry->fattr); if (!status) nfs_setsecurity(d_inode(dentry), entry->fattr, entry->label); @@ -526,7 +528,7 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry) dput(dentry); dentry = alias; } - nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); + nfs_set_verifier(dentry, dir_verifier); out: dput(dentry); } @@ -564,7 +566,8 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en count++; if (desc->plus) - nfs_prime_dcache(file_dentry(desc->file), entry); + nfs_prime_dcache(file_dentry(desc->file), entry, + desc->dir_verifier); status = nfs_readdir_add_to_array(entry, page); if (status != 0) @@ -983,14 +986,113 @@ static int nfs_fsync_dir(struct file *filp, loff_t start, loff_t end, * full lookup on all child dentries of 'dir' whenever a change occurs * on the server that might have invalidated our dcache. * + * Note that we reserve bit '0' as a tag to let us know when a dentry + * was revalidated while holding a delegation on its inode. + * * The caller should be holding dir->i_lock */ void nfs_force_lookup_revalidate(struct inode *dir) { - NFS_I(dir)->cache_change_attribute++; + NFS_I(dir)->cache_change_attribute += 2; } EXPORT_SYMBOL_GPL(nfs_force_lookup_revalidate); +/** + * nfs_verify_change_attribute - Detects NFS remote directory changes + * @dir: pointer to parent directory inode + * @verf: previously saved change attribute + * + * Return "false" if the verifiers doesn't match the change attribute. + * This would usually indicate that the directory contents have changed on + * the server, and that any dentries need revalidating. + */ +static bool nfs_verify_change_attribute(struct inode *dir, unsigned long verf) +{ + return (verf & ~1UL) == nfs_save_change_attribute(dir); +} + +static void nfs_set_verifier_delegated(unsigned long *verf) +{ + *verf |= 1UL; +} + +#if IS_ENABLED(CONFIG_NFS_V4) +static void nfs_unset_verifier_delegated(unsigned long *verf) +{ + *verf &= ~1UL; +} +#endif /* IS_ENABLED(CONFIG_NFS_V4) */ + +static bool nfs_test_verifier_delegated(unsigned long verf) +{ + return verf & 1; +} + +static bool nfs_verifier_is_delegated(struct dentry *dentry) +{ + return nfs_test_verifier_delegated(dentry->d_time); +} + +static void nfs_set_verifier_locked(struct dentry *dentry, unsigned long verf) +{ + struct inode *inode = d_inode(dentry); + + if (!nfs_verifier_is_delegated(dentry) && + !nfs_verify_change_attribute(d_inode(dentry->d_parent), verf)) + goto out; + if (inode && NFS_PROTO(inode)->have_delegation(inode, FMODE_READ)) + nfs_set_verifier_delegated(&verf); +out: + dentry->d_time = verf; +} + +/** + * nfs_set_verifier - save a parent directory verifier in the dentry + * @dentry: pointer to dentry + * @verf: verifier to save + * + * Saves the parent directory verifier in @dentry. If the inode has + * a delegation, we also tag the dentry as having been revalidated + * while holding a delegation so that we know we don't have to + * look it up again after a directory change. + */ +void nfs_set_verifier(struct dentry *dentry, unsigned long verf) +{ + + spin_lock(&dentry->d_lock); + nfs_set_verifier_locked(dentry, verf); + spin_unlock(&dentry->d_lock); +} +EXPORT_SYMBOL_GPL(nfs_set_verifier); + +#if IS_ENABLED(CONFIG_NFS_V4) +/** + * nfs_clear_verifier_delegated - clear the dir verifier delegation tag + * @inode: pointer to inode + * + * Iterates through the dentries in the inode alias list and clears + * the tag used to indicate that the dentry has been revalidated + * while holding a delegation. + * This function is intended for use when the delegation is being + * returned or revoked. + */ +void nfs_clear_verifier_delegated(struct inode *inode) +{ + struct dentry *alias; + + if (!inode) + return; + spin_lock(&inode->i_lock); + hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { + spin_lock(&alias->d_lock); + nfs_unset_verifier_delegated(&alias->d_time); + spin_unlock(&alias->d_lock); + } + spin_unlock(&inode->i_lock); +} +EXPORT_SYMBOL_GPL(nfs_clear_verifier_delegated); +#endif /* IS_ENABLED(CONFIG_NFS_V4) */ + /* * A check for whether or not the parent directory has changed. * In the case it has, we assume that the dentries are untrustworthy @@ -1159,6 +1261,7 @@ nfs_lookup_revalidate_dentry(struct inode *dir, struct dentry *dentry, struct nfs_fh *fhandle; struct nfs_fattr *fattr; struct nfs4_label *label; + unsigned long dir_verifier; int ret; ret = -ENOMEM; @@ -1168,6 +1271,7 @@ nfs_lookup_revalidate_dentry(struct inode *dir, struct dentry *dentry, if (fhandle == NULL || fattr == NULL || IS_ERR(label)) goto out; + dir_verifier = nfs_save_change_attribute(dir); ret = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr, label); if (ret < 0) { switch (ret) { @@ -1188,7 +1292,7 @@ nfs_lookup_revalidate_dentry(struct inode *dir, struct dentry *dentry, goto out; nfs_setsecurity(inode, fattr, label); - nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); + nfs_set_verifier(dentry, dir_verifier); /* set a readdirplus hint that we had a cache miss */ nfs_force_use_readdirplus(dir); @@ -1230,7 +1334,7 @@ nfs_do_lookup_revalidate(struct inode *dir, struct dentry *dentry, goto out_bad; } - if (NFS_PROTO(dir)->have_delegation(inode, FMODE_READ)) + if (nfs_verifier_is_delegated(dentry)) return nfs_lookup_revalidate_delegated(dir, dentry, inode); /* Force a full look up iff the parent directory has changed */ @@ -1415,6 +1519,7 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in struct nfs_fh *fhandle = NULL; struct nfs_fattr *fattr = NULL; struct nfs4_label *label = NULL; + unsigned long dir_verifier; int error; dfprintk(VFS, "NFS: lookup(%pd2)\n", dentry); @@ -1440,6 +1545,7 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in if (IS_ERR(label)) goto out; + dir_verifier = nfs_save_change_attribute(dir); trace_nfs_lookup_enter(dir, dentry, flags); error = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr, label); if (error == -ENOENT) @@ -1463,7 +1569,7 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in goto out_label; dentry = res; } - nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); + nfs_set_verifier(dentry, dir_verifier); out_label: trace_nfs_lookup_exit(dir, dentry, flags, error); nfs4_label_free(label); @@ -1668,7 +1774,7 @@ nfs4_do_lookup_revalidate(struct inode *dir, struct dentry *dentry, if (inode == NULL) goto full_reval; - if (NFS_PROTO(dir)->have_delegation(inode, FMODE_READ)) + if (nfs_verifier_is_delegated(dentry)) return nfs_lookup_revalidate_delegated(dir, dentry, inode); /* NFS only supports OPEN on regular files */ diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c index e1b938457ab9f528d61f44f8d6e83dd45731ce21..e113fcb4bb4c4b7cdfe704cf568ac27430a6b9b3 100644 --- a/fs/nfs/fs_context.c +++ b/fs/nfs/fs_context.c @@ -832,6 +832,8 @@ static int nfs_parse_source(struct fs_context *fc, if (len > maxnamlen) goto out_hostname; + kfree(ctx->nfs_server.hostname); + /* N.B. caller will free nfs_server.hostname in all cases */ ctx->nfs_server.hostname = kmemdup_nul(dev_name, len, GFP_KERNEL); if (!ctx->nfs_server.hostname) @@ -1240,6 +1242,13 @@ static int nfs_fs_context_validate(struct fs_context *fc) } ctx->nfs_mod = nfs_mod; } + + /* Ensure the filesystem context has the correct fs_type */ + if (fc->fs_type != ctx->nfs_mod->nfs_fs) { + module_put(fc->fs_type->owner); + __module_get(ctx->nfs_mod->nfs_fs->owner); + fc->fs_type = ctx->nfs_mod->nfs_fs; + } return 0; out_no_device_name: diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index 52270bfac120b99f3464af019c0ccc74078b8b92..1abf126c2df45b7e6d5815745db756db6b4659d0 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -31,6 +31,7 @@ static DEFINE_SPINLOCK(nfs_fscache_keys_lock); struct nfs_server_key { struct { uint16_t nfsversion; /* NFS protocol version */ + uint32_t minorversion; /* NFSv4 minor version */ uint16_t family; /* address family */ __be16 port; /* IP port */ } hdr; @@ -55,6 +56,7 @@ void nfs_fscache_get_client_cookie(struct nfs_client *clp) memset(&key, 0, sizeof(key)); key.hdr.nfsversion = clp->rpc_ops->version; + key.hdr.minorversion = clp->cl_minorversion; key.hdr.family = clp->cl_addr.ss_family; switch (clp->cl_addr.ss_family) { diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 1309e6f47f3d69e3d8f24d466a15814aa03fff28..11bf15800ac9974204491ab0f7570ca063dbddfb 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -2114,6 +2114,7 @@ static void init_once(void *foo) init_rwsem(&nfsi->rmdir_sem); mutex_init(&nfsi->commit_mutex); nfs4_init_once(nfsi); + nfsi->cache_change_attribute = 0; } static int __init nfs_init_inodecache(void) diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index ad60774049473d3f600267282c275f217aa68510..f3ece8ed32033ab3e4e4e807b9b128b54c1da95a 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -153,7 +153,7 @@ struct vfsmount *nfs_d_automount(struct path *path) /* Open a new filesystem context, transferring parameters from the * parent superblock, including the network namespace. */ - fc = fs_context_for_submount(&nfs_fs_type, path->dentry); + fc = fs_context_for_submount(path->mnt->mnt_sb->s_type, path->dentry); if (IS_ERR(fc)) return ERR_CAST(fc); diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 0cd767e5c9775437aebb7e263de46e4874b7f0de..0bd77cc1f639fa27eb5ffbe0a59081285adad215 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -216,7 +216,6 @@ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init) INIT_LIST_HEAD(&clp->cl_ds_clients); rpc_init_wait_queue(&clp->cl_rpcwaitq, "NFS client"); clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED; - clp->cl_minorversion = cl_init->minorversion; clp->cl_mvops = nfs_v4_minor_ops[cl_init->minorversion]; clp->cl_mig_gen = 1; #if IS_ENABLED(CONFIG_NFS_V4_1) diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index be4eb720d5b69304d969ffb116ceca0a5b0d0b4d..1297919e0fce3173c7dee30d26d68e00a25e4125 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -87,7 +87,6 @@ nfs4_file_open(struct inode *inode, struct file *filp) if (inode != d_inode(dentry)) goto out_drop; - nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); nfs_file_set_open_context(filp, ctx); nfs_fscache_open_file(inode, filp); err = 0; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 95d07a3dc5d1d8b350c1d017b509e710bd31120b..69b7ab7a58157f4d7b3e7787d4d2b1dc9750ff7d 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2974,10 +2974,13 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, struct dentry *dentry; struct nfs4_state *state; fmode_t acc_mode = _nfs4_ctx_to_accessmode(ctx); + struct inode *dir = d_inode(opendata->dir); + unsigned long dir_verifier; unsigned int seq; int ret; seq = raw_seqcount_begin(&sp->so_reclaim_seqcount); + dir_verifier = nfs_save_change_attribute(dir); ret = _nfs4_proc_open(opendata, ctx); if (ret != 0) @@ -3005,8 +3008,19 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, dput(ctx->dentry); ctx->dentry = dentry = alias; } - nfs_set_verifier(dentry, - nfs_save_change_attribute(d_inode(opendata->dir))); + } + + switch(opendata->o_arg.claim) { + default: + break; + case NFS4_OPEN_CLAIM_NULL: + case NFS4_OPEN_CLAIM_DELEGATE_CUR: + case NFS4_OPEN_CLAIM_DELEGATE_PREV: + if (!opendata->rpc_done) + break; + if (opendata->o_res.delegation_type != 0) + dir_verifier = nfs_save_change_attribute(dir); + nfs_set_verifier(dentry, dir_verifier); } /* Parse layoutget results before we check for access */ @@ -5322,7 +5336,7 @@ static void nfs4_proc_write_setup(struct nfs_pgio_header *hdr, hdr->timestamp = jiffies; msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_WRITE]; - nfs4_init_sequence(&hdr->args.seq_args, &hdr->res.seq_res, 1, 0); + nfs4_init_sequence(&hdr->args.seq_args, &hdr->res.seq_res, 0, 0); nfs4_state_protect_write(server->nfs_client, clnt, msg, hdr); } diff --git a/fs/open.c b/fs/open.c index 0788b3715731186f326a24296ed3b00ad870bb46..b69d6eed67e6a93753cce13080ebb2208dee3a0b 100644 --- a/fs/open.c +++ b/fs/open.c @@ -860,9 +860,6 @@ static int do_dentry_open(struct file *f, * the return value of d_splice_alias(), then the caller needs to perform dput() * on it after finish_open(). * - * On successful return @file is a fully instantiated open file. After this, if - * an error occurs in ->atomic_open(), it needs to clean up with fput(). - * * Returns zero on success or -errno if the open failed. */ int finish_open(struct file *file, struct dentry *dentry, diff --git a/fs/overlayfs/Kconfig b/fs/overlayfs/Kconfig index 444e2da4f60e213c28109204fdd997dab4b863a3..714c14c47ca5573053b43fb605c69761d2157562 100644 --- a/fs/overlayfs/Kconfig +++ b/fs/overlayfs/Kconfig @@ -93,6 +93,7 @@ config OVERLAY_FS_XINO_AUTO bool "Overlayfs: auto enable inode number mapping" default n depends on OVERLAY_FS + depends on 64BIT help If this config option is enabled then overlay filesystems will use unused high bits in undelying filesystem inode numbers to map all diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index a5317216de7368f30a15a49a93a3cbfabe7eb71d..87c362f65448b956f5ca425ac40f728dae408dab 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -244,6 +244,9 @@ static void ovl_aio_cleanup_handler(struct ovl_aio_req *aio_req) if (iocb->ki_flags & IOCB_WRITE) { struct inode *inode = file_inode(orig_iocb->ki_filp); + /* Actually acquired in ovl_write_iter() */ + __sb_writers_acquired(file_inode(iocb->ki_filp)->i_sb, + SB_FREEZE_WRITE); file_end_write(iocb->ki_filp); ovl_copyattr(ovl_inode_real(inode), inode); } @@ -346,6 +349,9 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter) goto out; file_start_write(real.file); + /* Pacify lockdep, same trick as done in aio_write() */ + __sb_writers_release(file_inode(real.file)->i_sb, + SB_FREEZE_WRITE); aio_req->fd = real; real.flags = 0; aio_req->orig_iocb = iocb; diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 3623d28aa4fa7d93252f456468f14af5648b80d3..3d3f2b8bdae54fb27aa25f5f15bbef0df5aa384d 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -318,7 +318,12 @@ static inline unsigned int ovl_xino_bits(struct super_block *sb) return ovl_same_dev(sb) ? OVL_FS(sb)->xino_mode : 0; } -static inline int ovl_inode_lock(struct inode *inode) +static inline void ovl_inode_lock(struct inode *inode) +{ + mutex_lock(&OVL_I(inode)->lock); +} + +static inline int ovl_inode_lock_interruptible(struct inode *inode) { return mutex_lock_interruptible(&OVL_I(inode)->lock); } diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 319fe0d355b0b33b5cda8f3227f17a09e8de7049..ac967f1cb6e505725515863395d273122e013129 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1411,6 +1411,8 @@ static int ovl_get_layers(struct super_block *sb, struct ovl_fs *ofs, if (ofs->config.xino == OVL_XINO_ON) pr_info("\"xino=on\" is useless with all layers on same fs, ignore.\n"); ofs->xino_mode = 0; + } else if (ofs->config.xino == OVL_XINO_OFF) { + ofs->xino_mode = -1; } else if (ofs->config.xino == OVL_XINO_ON && ofs->xino_mode < 0) { /* * This is a roundup of number of bits needed for encoding @@ -1623,8 +1625,13 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) sb->s_stack_depth = 0; sb->s_maxbytes = MAX_LFS_FILESIZE; /* Assume underlaying fs uses 32bit inodes unless proven otherwise */ - if (ofs->config.xino != OVL_XINO_OFF) + if (ofs->config.xino != OVL_XINO_OFF) { ofs->xino_mode = BITS_PER_LONG - 32; + if (!ofs->xino_mode) { + pr_warn("xino not supported on 32bit kernel, falling back to xino=off.\n"); + ofs->config.xino = OVL_XINO_OFF; + } + } /* alloc/destroy_inode needed for setting up traps in inode cache */ sb->s_op = &ovl_super_operations; diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index ea005085803f0c5a6eb54ae19f8c6b19d2089c38..042f7eb4f7f419644ec6f4c0f5b4ddae23650a33 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -509,7 +509,7 @@ int ovl_copy_up_start(struct dentry *dentry, int flags) struct inode *inode = d_inode(dentry); int err; - err = ovl_inode_lock(inode); + err = ovl_inode_lock_interruptible(inode); if (!err && ovl_already_copied_up_locked(dentry, flags)) { err = 1; /* Already copied up */ ovl_inode_unlock(inode); @@ -764,7 +764,7 @@ int ovl_nlink_start(struct dentry *dentry) return err; } - err = ovl_inode_lock(inode); + err = ovl_inode_lock_interruptible(inode); if (err) return err; diff --git a/fs/pipe.c b/fs/pipe.c index 5a34d6c22d4cecd530cdfd1486868d577f427d9f..2144507447c5ae493230b5354bf0a0cdcd5ece2d 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -722,9 +722,10 @@ pipe_release(struct inode *inode, struct file *file) if (file->f_mode & FMODE_WRITE) pipe->writers--; - if (pipe->readers || pipe->writers) { - wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM | EPOLLERR | EPOLLHUP); - wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM | EPOLLERR | EPOLLHUP); + /* Was that the last reader or writer, but not the other side? */ + if (!pipe->readers != !pipe->writers) { + wake_up_interruptible_all(&pipe->rd_wait); + wake_up_interruptible_all(&pipe->wr_wait); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); } @@ -1026,8 +1027,8 @@ static int wait_for_partner(struct pipe_inode_info *pipe, unsigned int *cnt) static void wake_up_partner(struct pipe_inode_info *pipe) { - wake_up_interruptible(&pipe->rd_wait); - wake_up_interruptible(&pipe->wr_wait); + wake_up_interruptible_all(&pipe->rd_wait); + wake_up_interruptible_all(&pipe->wr_wait); } static int fifo_open(struct inode *inode, struct file *filp) @@ -1144,7 +1145,7 @@ static int fifo_open(struct inode *inode, struct file *filp) err_wr: if (!--pipe->writers) - wake_up_interruptible(&pipe->rd_wait); + wake_up_interruptible_all(&pipe->rd_wait); ret = -ERESTARTSYS; goto err; @@ -1271,8 +1272,9 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg) pipe->max_usage = nr_slots; pipe->tail = tail; pipe->head = head; - wake_up_interruptible_all(&pipe->rd_wait); - wake_up_interruptible_all(&pipe->wr_wait); + + /* This might have made more room for writers */ + wake_up_interruptible(&pipe->wr_wait); return pipe->max_usage * PAGE_SIZE; out_revert_acct: diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 3a688eb5c5ae4e07e70b78f58ce6261a22770340..58e937be24cee7ab151df55523ed29499938cd16 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -587,7 +587,7 @@ xfs_dax_writepages( xfs_iflags_clear(ip, XFS_ITRUNCATED); return dax_writeback_mapping_range(mapping, - xfs_inode_buftarg(ip)->bt_bdev, wbc); + xfs_inode_buftarg(ip)->bt_daxdev, wbc); } STATIC sector_t diff --git a/fs/zonefs/Kconfig b/fs/zonefs/Kconfig index fb87ad372e297d19b954a7c8187c8657a0f223cb..ef2697b78820d4634f47a258313e7ddca43daa11 100644 --- a/fs/zonefs/Kconfig +++ b/fs/zonefs/Kconfig @@ -2,6 +2,7 @@ config ZONEFS_FS tristate "zonefs filesystem support" depends on BLOCK depends on BLK_DEV_ZONED + select FS_IOMAP help zonefs is a simple file system which exposes zones of a zoned block device (e.g. host-managed or host-aware SMR disk drives) as files. diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index 8bc6ef82d693e06f0dc0da790db63cda8364f989..69aee3dfb6607814cb24d14ea2cdd08642a4c56a 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -601,13 +601,13 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from) ssize_t ret; /* - * For async direct IOs to sequential zone files, ignore IOCB_NOWAIT + * For async direct IOs to sequential zone files, refuse IOCB_NOWAIT * as this can cause write reordering (e.g. the first aio gets EAGAIN * on the inode lock but the second goes through but is now unaligned). */ - if (zi->i_ztype == ZONEFS_ZTYPE_SEQ && !is_sync_kiocb(iocb) - && (iocb->ki_flags & IOCB_NOWAIT)) - iocb->ki_flags &= ~IOCB_NOWAIT; + if (zi->i_ztype == ZONEFS_ZTYPE_SEQ && !is_sync_kiocb(iocb) && + (iocb->ki_flags & IOCB_NOWAIT)) + return -EOPNOTSUPP; if (iocb->ki_flags & IOCB_NOWAIT) { if (!inode_trylock(inode)) diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 00994b1b8681a32f25b3dfaa0e9d4b9755b9f445..8e8be989c2a6f56e9d503580493b8ddb8b7593a5 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -752,6 +752,8 @@ ACPI_HW_DEPENDENT_RETURN_UINT32(u32 acpi_dispatch_gpe(acpi_handle gpe_device, u3 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_disable_all_gpes(void)) ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable_all_runtime_gpes(void)) ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable_all_wakeup_gpes(void)) +ACPI_HW_DEPENDENT_RETURN_UINT32(u32 acpi_any_gpe_status_set(void)) +ACPI_HW_DEPENDENT_RETURN_UINT32(u32 acpi_any_fixed_event_status_set(void)) ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_get_gpe_device(u32 gpe_index, diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h index a2583c2bc0548c8da7ec53f6c535c636661e8ced..4defed58ea338fd61e789751af92c5a04b04088a 100644 --- a/include/acpi/actypes.h +++ b/include/acpi/actypes.h @@ -532,11 +532,12 @@ typedef u64 acpi_integer; strnlen (a, ACPI_NAMESEG_SIZE) == ACPI_NAMESEG_SIZE) /* - * Algorithm to obtain access bit width. + * Algorithm to obtain access bit or byte width. * Can be used with access_width of struct acpi_generic_address and access_size of * struct acpi_resource_generic_register. */ #define ACPI_ACCESS_BIT_WIDTH(size) (1 << ((size) + 2)) +#define ACPI_ACCESS_BYTE_WIDTH(size) (1 << ((size) - 1)) /******************************************************************************* * diff --git a/include/crypto/curve25519.h b/include/crypto/curve25519.h index 4e6dc840b1592c53cb38b3687a2ff3b55fa8364f..9ecb3c1f0f15d4bc7ebe34f5682fbba7b780ee1f 100644 --- a/include/crypto/curve25519.h +++ b/include/crypto/curve25519.h @@ -33,7 +33,8 @@ bool __must_check curve25519(u8 mypublic[CURVE25519_KEY_SIZE], const u8 secret[CURVE25519_KEY_SIZE], const u8 basepoint[CURVE25519_KEY_SIZE]) { - if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CURVE25519)) + if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CURVE25519) && + (!IS_ENABLED(CONFIG_CRYPTO_CURVE25519_X86) || IS_ENABLED(CONFIG_AS_ADX))) curve25519_arch(mypublic, secret, basepoint); else curve25519_generic(mypublic, secret, basepoint); @@ -49,7 +50,8 @@ __must_check curve25519_generate_public(u8 pub[CURVE25519_KEY_SIZE], CURVE25519_KEY_SIZE))) return false; - if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CURVE25519)) + if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CURVE25519) && + (!IS_ENABLED(CONFIG_CRYPTO_CURVE25519_X86) || IS_ENABLED(CONFIG_AS_ADX))) curve25519_base_arch(pub, secret); else curve25519_generic(pub, secret, curve25519_base_point); diff --git a/include/drm/drm_dp_mst_helper.h b/include/drm/drm_dp_mst_helper.h index bcb39da9adb4ac4bd6e2a4455c23033599c88561..41725d88d27e7ff7011bdd95a3886d77c4f73ef1 100644 --- a/include/drm/drm_dp_mst_helper.h +++ b/include/drm/drm_dp_mst_helper.h @@ -81,7 +81,7 @@ struct drm_dp_vcpi { * &drm_dp_mst_topology_mgr.base.lock. * @num_sdp_stream_sinks: Number of stream sinks. Protected by * &drm_dp_mst_topology_mgr.base.lock. - * @available_pbn: Available bandwidth for this port. Protected by + * @full_pbn: Max possible bandwidth for this port. Protected by * &drm_dp_mst_topology_mgr.base.lock. * @next: link to next port on this branch device * @aux: i2c aux transport to talk to device connected to this port, protected @@ -126,7 +126,7 @@ struct drm_dp_mst_port { u8 dpcd_rev; u8 num_sdp_streams; u8 num_sdp_stream_sinks; - uint16_t available_pbn; + uint16_t full_pbn; struct list_head next; /** * @mstb: the branch device connected to this port, if there is one. diff --git a/include/drm/drm_gem_shmem_helper.h b/include/drm/drm_gem_shmem_helper.h index e34a7b7f848a65ec293593061317013f063f12d8..294b2931c4cc0e1375d7d981c936221944b6ba85 100644 --- a/include/drm/drm_gem_shmem_helper.h +++ b/include/drm/drm_gem_shmem_helper.h @@ -96,6 +96,11 @@ struct drm_gem_shmem_object { * The address are un-mapped when the count reaches zero. */ unsigned int vmap_use_count; + + /** + * @map_cached: map object cached (instead of using writecombine). + */ + bool map_cached; }; #define to_drm_gem_shmem_obj(obj) \ diff --git a/include/dt-bindings/clock/imx8mn-clock.h b/include/dt-bindings/clock/imx8mn-clock.h index 0f2b8423ce1d13c9bf35a7b18b55335f82bd31ed..65ac6eb6c7330615457f5d13cacbedadf681d55c 100644 --- a/include/dt-bindings/clock/imx8mn-clock.h +++ b/include/dt-bindings/clock/imx8mn-clock.h @@ -122,8 +122,8 @@ #define IMX8MN_CLK_I2C1 105 #define IMX8MN_CLK_I2C2 106 #define IMX8MN_CLK_I2C3 107 -#define IMX8MN_CLK_I2C4 118 -#define IMX8MN_CLK_UART1 119 +#define IMX8MN_CLK_I2C4 108 +#define IMX8MN_CLK_UART1 109 #define IMX8MN_CLK_UART2 110 #define IMX8MN_CLK_UART3 111 #define IMX8MN_CLK_UART4 112 diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 053ea4b519887eaf7b61baee51657eb0ea2930f1..f629d40c645cd3611200d470e8530b0cf5584c14 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -524,7 +524,7 @@ struct request_queue { unsigned int sg_reserved_size; int node; #ifdef CONFIG_BLK_DEV_IO_TRACE - struct blk_trace *blk_trace; + struct blk_trace __rcu *blk_trace; struct mutex blk_trace_mutex; #endif /* @@ -1494,7 +1494,6 @@ static inline void put_dev_sector(Sector p) } int kblockd_schedule_work(struct work_struct *work); -int kblockd_schedule_work_on(int cpu, struct work_struct *work); int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay); #define MODULE_ALIAS_BLOCKDEV(major,minor) \ diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 7bb2d8de9f308e367bcda4a5484f67483f8fc8e5..3b6ff5902edce65c9ec1dc1ccb0497b0ac521194 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -51,9 +51,13 @@ void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *f **/ #define blk_add_cgroup_trace_msg(q, cg, fmt, ...) \ do { \ - struct blk_trace *bt = (q)->blk_trace; \ + struct blk_trace *bt; \ + \ + rcu_read_lock(); \ + bt = rcu_dereference((q)->blk_trace); \ if (unlikely(bt)) \ __trace_note_message(bt, cg, fmt, ##__VA_ARGS__);\ + rcu_read_unlock(); \ } while (0) #define blk_add_trace_msg(q, fmt, ...) \ blk_add_cgroup_trace_msg(q, NULL, fmt, ##__VA_ARGS__) @@ -61,10 +65,14 @@ void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *f static inline bool blk_trace_note_message_enabled(struct request_queue *q) { - struct blk_trace *bt = q->blk_trace; - if (likely(!bt)) - return false; - return bt->act_mask & BLK_TC_NOTIFY; + struct blk_trace *bt; + bool ret; + + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + ret = bt && (bt->act_mask & BLK_TC_NOTIFY); + rcu_read_unlock(); + return ret; } extern void blk_add_driver_data(struct request_queue *q, struct request *rq, diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h index 7e18c939663e71309ef058b27097658a11cd97c3..d11e183fcb542101417180b12e8cce8a84b8b0df 100644 --- a/include/linux/bootconfig.h +++ b/include/linux/bootconfig.h @@ -10,6 +10,9 @@ #include #include +#define BOOTCONFIG_MAGIC "#BOOTCONFIG\n" +#define BOOTCONFIG_MAGIC_LEN 12 + /* XBC tree node */ struct xbc_node { u16 next; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index d7ddebd0cdec2e2eef29b24cce984fd5ef93e9e6..e75d2191226b9144b1eb102f6679bf6817a3005f 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -62,6 +62,7 @@ struct css_task_iter { struct list_head *mg_tasks_head; struct list_head *dying_tasks_head; + struct list_head *cur_tasks_head; struct css_set *cur_cset; struct css_set *cur_dcset; struct task_struct *cur_task; diff --git a/include/linux/compat.h b/include/linux/compat.h index 11083d84eb23ead8fcc62ca6277b9c904fe9bb6f..df2475be134aa5e53c4daa28fd819741282a7c99 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -248,15 +248,6 @@ typedef struct compat_siginfo { } _sifields; } compat_siginfo_t; -/* - * These functions operate on 32- or 64-bit specs depending on - * COMPAT_USE_64BIT_TIME, hence the void user pointer arguments. - */ -extern int compat_get_timespec(struct timespec *, const void __user *); -extern int compat_put_timespec(const struct timespec *, void __user *); -extern int compat_get_timeval(struct timeval *, const void __user *); -extern int compat_put_timeval(const struct timeval *, void __user *); - struct compat_iovec { compat_uptr_t iov_base; compat_size_t iov_len; @@ -416,26 +407,6 @@ int copy_siginfo_to_user32(struct compat_siginfo __user *to, const kernel_siginf int get_compat_sigevent(struct sigevent *event, const struct compat_sigevent __user *u_event); -static inline int old_timeval32_compare(struct old_timeval32 *lhs, - struct old_timeval32 *rhs) -{ - if (lhs->tv_sec < rhs->tv_sec) - return -1; - if (lhs->tv_sec > rhs->tv_sec) - return 1; - return lhs->tv_usec - rhs->tv_usec; -} - -static inline int old_timespec32_compare(struct old_timespec32 *lhs, - struct old_timespec32 *rhs) -{ - if (lhs->tv_sec < rhs->tv_sec) - return -1; - if (lhs->tv_sec > rhs->tv_sec) - return 1; - return lhs->tv_nsec - rhs->tv_nsec; -} - extern int get_compat_sigset(sigset_t *set, const compat_sigset_t __user *compat); /* diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 018dce868de630f0f6b2168ee8d3d095916ae121..0fb561d1b524eecc489c77e4a673df41c70f19d0 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -201,9 +201,6 @@ static inline bool policy_is_shared(struct cpufreq_policy *policy) return cpumask_weight(policy->cpus) > 1; } -/* /sys/devices/system/cpu/cpufreq: entry point for global variables */ -extern struct kobject *cpufreq_global_kobject; - #ifdef CONFIG_CPU_FREQ unsigned int cpufreq_get(unsigned int cpu); unsigned int cpufreq_quick_get(unsigned int cpu); diff --git a/include/linux/dax.h b/include/linux/dax.h index 9bd8528bd305f16c388975a5e2ee37df83e662ee..328c2dbb4409ce2fd983bf38597563a11e116990 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -129,11 +129,6 @@ static inline bool generic_fsdax_supported(struct dax_device *dax_dev, sectors); } -static inline struct dax_device *fs_dax_get_by_host(const char *host) -{ - return dax_get_by_host(host); -} - static inline void fs_put_dax(struct dax_device *dax_dev) { put_dax(dax_dev); @@ -141,7 +136,7 @@ static inline void fs_put_dax(struct dax_device *dax_dev) struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev); int dax_writeback_mapping_range(struct address_space *mapping, - struct block_device *bdev, struct writeback_control *wbc); + struct dax_device *dax_dev, struct writeback_control *wbc); struct page *dax_layout_busy_page(struct address_space *mapping); dax_entry_t dax_lock_page(struct page *page); @@ -160,11 +155,6 @@ static inline bool generic_fsdax_supported(struct dax_device *dax_dev, return false; } -static inline struct dax_device *fs_dax_get_by_host(const char *host) -{ - return NULL; -} - static inline void fs_put_dax(struct dax_device *dax_dev) { } @@ -180,7 +170,7 @@ static inline struct page *dax_layout_busy_page(struct address_space *mapping) } static inline int dax_writeback_mapping_range(struct address_space *mapping, - struct block_device *bdev, struct writeback_control *wbc) + struct dax_device *dax_dev, struct writeback_control *wbc) { return -EOPNOTSUPP; } diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index 3d013de64f70ec42e330ba04546b34fca02bd2b1..43efcc49f061fe606caa9e208f244d07d3918804 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -127,9 +127,9 @@ struct dentry *debugfs_create_blob(const char *name, umode_t mode, struct dentry *parent, struct debugfs_blob_wrapper *blob); -struct dentry *debugfs_create_regset32(const char *name, umode_t mode, - struct dentry *parent, - struct debugfs_regset32 *regset); +void debugfs_create_regset32(const char *name, umode_t mode, + struct dentry *parent, + struct debugfs_regset32 *regset); void debugfs_print_regs32(struct seq_file *s, const struct debugfs_reg32 *regs, int nregs, void __iomem *base, char *prefix); @@ -304,11 +304,10 @@ static inline struct dentry *debugfs_create_blob(const char *name, umode_t mode, return ERR_PTR(-ENODEV); } -static inline struct dentry *debugfs_create_regset32(const char *name, - umode_t mode, struct dentry *parent, - struct debugfs_regset32 *regset) +static inline void debugfs_create_regset32(const char *name, umode_t mode, + struct dentry *parent, + struct debugfs_regset32 *regset) { - return ERR_PTR(-ENODEV); } static inline void debugfs_print_regs32(struct seq_file *s, const struct debugfs_reg32 *regs, diff --git a/include/linux/device.h b/include/linux/device.h index 0cd7c647c16c6acc316df7ce03d9bf779f25ab34..fa04dfd22bbcd46655b7ac3bfaa14784927c0ef3 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -798,6 +798,17 @@ static inline struct device_node *dev_of_node(struct device *dev) return dev->of_node; } +static inline bool dev_has_sync_state(struct device *dev) +{ + if (!dev) + return false; + if (dev->driver && dev->driver->sync_state) + return true; + if (dev->bus && dev->bus->sync_state) + return true; + return false; +} + /* * High level routines for use by the bus drivers */ diff --git a/include/linux/dmar.h b/include/linux/dmar.h index f64ca27dc210469a9da89ac4083bd0532e2abf29..d7bf029df737d3b52a93f490b2d3109f3c3247a8 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -69,19 +69,23 @@ struct dmar_pci_notify_info { extern struct rw_semaphore dmar_global_lock; extern struct list_head dmar_drhd_units; -#define for_each_drhd_unit(drhd) \ - list_for_each_entry_rcu(drhd, &dmar_drhd_units, list) +#define for_each_drhd_unit(drhd) \ + list_for_each_entry_rcu(drhd, &dmar_drhd_units, list, \ + dmar_rcu_check()) #define for_each_active_drhd_unit(drhd) \ - list_for_each_entry_rcu(drhd, &dmar_drhd_units, list) \ + list_for_each_entry_rcu(drhd, &dmar_drhd_units, list, \ + dmar_rcu_check()) \ if (drhd->ignored) {} else #define for_each_active_iommu(i, drhd) \ - list_for_each_entry_rcu(drhd, &dmar_drhd_units, list) \ + list_for_each_entry_rcu(drhd, &dmar_drhd_units, list, \ + dmar_rcu_check()) \ if (i=drhd->iommu, drhd->ignored) {} else #define for_each_iommu(i, drhd) \ - list_for_each_entry_rcu(drhd, &dmar_drhd_units, list) \ + list_for_each_entry_rcu(drhd, &dmar_drhd_units, list, \ + dmar_rcu_check()) \ if (i=drhd->iommu, 0) {} else static inline bool dmar_rcu_check(void) diff --git a/include/linux/file.h b/include/linux/file.h index c6c7b24ea9f74ca923c7be13d49882fa6ee2fa94..142d102f285e54916782613a3ac0e33ca58323be 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -85,6 +85,7 @@ extern int f_dupfd(unsigned int from, struct file *file, unsigned flags); extern int replace_fd(unsigned fd, struct file *file, unsigned flags); extern void set_close_on_exec(unsigned int fd, int flag); extern bool get_close_on_exec(unsigned int fd); +extern int __get_unused_fd_flags(unsigned flags, unsigned long nofile); extern int get_unused_fd_flags(unsigned flags); extern void put_unused_fd(unsigned int fd); diff --git a/include/linux/fs.h b/include/linux/fs.h index 3cd4fe6b845e7ff8c6263488030bd3553c302850..abedbffe2c9e41e2c4711592bd2776e3d9dcbb77 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -698,6 +698,7 @@ struct inode { struct rcu_head i_rcu; }; atomic64_t i_version; + atomic64_t i_sequence; /* see futex */ atomic_t i_count; atomic_t i_dio_count; atomic_t i_writecount; diff --git a/include/linux/futex.h b/include/linux/futex.h index 5cc3fed27d4c2e142d2edf1d582785c5902561e1..b70df27d7e85c2c257c3467780d7b835b58d9fe1 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -31,23 +31,26 @@ struct task_struct; union futex_key { struct { + u64 i_seq; unsigned long pgoff; - struct inode *inode; - int offset; + unsigned int offset; } shared; struct { + union { + struct mm_struct *mm; + u64 __tmp; + }; unsigned long address; - struct mm_struct *mm; - int offset; + unsigned int offset; } private; struct { + u64 ptr; unsigned long word; - void *ptr; - int offset; + unsigned int offset; } both; }; -#define FUTEX_KEY_INIT (union futex_key) { .both = { .ptr = NULL } } +#define FUTEX_KEY_INIT (union futex_key) { .both = { .ptr = 0ULL } } #ifdef CONFIG_FUTEX enum { diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 6fbe58538ad6303fed1aa86898d8b5d9dcc82f8d..07dc91835b9891f41f6f098b8d65ae91d2cc9c16 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -245,18 +245,6 @@ static inline bool disk_part_scan_enabled(struct gendisk *disk) !(disk->flags & GENHD_FL_NO_PART_SCAN); } -static inline bool disk_has_partitions(struct gendisk *disk) -{ - bool ret = false; - - rcu_read_lock(); - if (rcu_dereference(disk->part_tbl)->len > 1) - ret = true; - rcu_read_unlock(); - - return ret; -} - static inline dev_t disk_devt(struct gendisk *disk) { return MKDEV(disk->major, disk->first_minor); @@ -298,6 +286,7 @@ extern void disk_part_iter_exit(struct disk_part_iter *piter); extern struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector); +bool disk_has_partitions(struct gendisk *disk); /* * Macros to operate on percpu disk statistics: diff --git a/include/linux/hid.h b/include/linux/hid.h index cd41f209043f6dabe779040724883e14b75129c6..875f71132b1425b494ba9eb538f29543cb857753 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -492,7 +492,7 @@ struct hid_report_enum { }; #define HID_MIN_BUFFER_SIZE 64 /* make sure there is at least a packet size of space */ -#define HID_MAX_BUFFER_SIZE 4096 /* 4kb */ +#define HID_MAX_BUFFER_SIZE 8192 /* 8kb */ #define HID_CONTROL_FIFO_SIZE 256 /* to init devices with >100 reports */ #define HID_OUTPUT_FIFO_SIZE 64 diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index ef1cbb5f454f7aa105db534ecc1ddbb56df333ce..33d37960231441d63a1d7a3d611da916734fc2cd 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -22,12 +22,22 @@ extern int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn); int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type, unsigned int data_len); +#if IS_ENABLED(CONFIG_NF_NAT) +void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info); +#else +#define icmpv6_ndo_send icmpv6_send +#endif + #else static inline void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) { +} +static inline void icmpv6_ndo_send(struct sk_buff *skb, + u8 type, u8 code, __u32 info) +{ } #endif diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h index 39faaaf843e1efb864ad148c710ed9cec7a82381..c91cf2dee12abd9fe4225c7000dcc2c25fbef0ed 100644 --- a/include/linux/inet_diag.h +++ b/include/linux/inet_diag.h @@ -2,15 +2,10 @@ #ifndef _INET_DIAG_H_ #define _INET_DIAG_H_ 1 +#include #include -struct net; -struct sock; struct inet_hashinfo; -struct nlattr; -struct nlmsghdr; -struct sk_buff; -struct netlink_callback; struct inet_diag_handler { void (*dump)(struct sk_buff *skb, @@ -62,6 +57,17 @@ int inet_diag_bc_sk(const struct nlattr *_bc, struct sock *sk); void inet_diag_msg_common_fill(struct inet_diag_msg *r, struct sock *sk); +static inline size_t inet_diag_msg_attrs_size(void) +{ + return nla_total_size(1) /* INET_DIAG_SHUTDOWN */ + + nla_total_size(1) /* INET_DIAG_TOS */ +#if IS_ENABLED(CONFIG_IPV6) + + nla_total_size(1) /* INET_DIAG_TCLASS */ + + nla_total_size(1) /* INET_DIAG_SKV6ONLY */ +#endif + + nla_total_size(4) /* INET_DIAG_MARK */ + + nla_total_size(4); /* INET_DIAG_CLASS_ID */ +} int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, struct inet_diag_msg *r, int ext, struct user_namespace *user_ns, bool net_admin); diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 4a16b39ae353ee8be6c908a597575c33aaa0cc25..980234ae0312259e938f0dc5c63dc4209fa7aed8 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -123,6 +123,8 @@ #define dmar_readq(a) readq(a) #define dmar_writeq(a,v) writeq(v,a) +#define dmar_readl(a) readl(a) +#define dmar_writel(a, v) writel(v, a) #define DMAR_VER_MAJOR(v) (((v) & 0xf0) >> 4) #define DMAR_VER_MINOR(v) ((v) & 0x0f) diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h index 94f047a8a845424f5ea34a73f8adb5b2ef5d57b9..d7c403d0dd27d84ecdc8d8b094739e32b85968e2 100644 --- a/include/linux/intel-svm.h +++ b/include/linux/intel-svm.h @@ -122,7 +122,7 @@ static inline int intel_svm_unbind_mm(struct device *dev, int pasid) BUG(); } -static int intel_svm_is_pasid_valid(struct device *dev, int pasid) +static inline int intel_svm_is_pasid_valid(struct device *dev, int pasid) { return -EINVAL; } diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index b2d47571ab676fcf81a301f1df091ad33f1eb7b6..8d062e86d954e11ef5fb46a8b00bb12287b6ad8b 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -192,7 +192,7 @@ enum { IRQ_DOMAIN_FLAG_HIERARCHY = (1 << 0), /* Irq domain name was allocated in __irq_domain_add() */ - IRQ_DOMAIN_NAME_ALLOCATED = (1 << 6), + IRQ_DOMAIN_NAME_ALLOCATED = (1 << 1), /* Irq domain is an IPI domain with virq per cpu */ IRQ_DOMAIN_FLAG_IPI_PER_CPU = (1 << 2), diff --git a/include/linux/ktime.h b/include/linux/ktime.h index b2bb44f87f5a3edb6ee6f179c83fcde42a363fe5..d1fb05135665b7df5add8c3b2cb2d690fade6b7e 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -66,33 +66,15 @@ static inline ktime_t ktime_set(const s64 secs, const unsigned long nsecs) */ #define ktime_sub_ns(kt, nsval) ((kt) - (nsval)) -/* convert a timespec to ktime_t format: */ -static inline ktime_t timespec_to_ktime(struct timespec ts) -{ - return ktime_set(ts.tv_sec, ts.tv_nsec); -} - /* convert a timespec64 to ktime_t format: */ static inline ktime_t timespec64_to_ktime(struct timespec64 ts) { return ktime_set(ts.tv_sec, ts.tv_nsec); } -/* convert a timeval to ktime_t format: */ -static inline ktime_t timeval_to_ktime(struct timeval tv) -{ - return ktime_set(tv.tv_sec, tv.tv_usec * NSEC_PER_USEC); -} - -/* Map the ktime_t to timespec conversion to ns_to_timespec function */ -#define ktime_to_timespec(kt) ns_to_timespec((kt)) - /* Map the ktime_t to timespec conversion to ns_to_timespec function */ #define ktime_to_timespec64(kt) ns_to_timespec64((kt)) -/* Map the ktime_t to timeval conversion to ns_to_timeval function */ -#define ktime_to_timeval(kt) ns_to_timeval((kt)) - /* Convert ktime_t to nanoseconds */ static inline s64 ktime_to_ns(const ktime_t kt) { @@ -215,25 +197,6 @@ static inline ktime_t ktime_sub_ms(const ktime_t kt, const u64 msec) extern ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs); -/** - * ktime_to_timespec_cond - convert a ktime_t variable to timespec - * format only if the variable contains data - * @kt: the ktime_t variable to convert - * @ts: the timespec variable to store the result in - * - * Return: %true if there was a successful conversion, %false if kt was 0. - */ -static inline __must_check bool ktime_to_timespec_cond(const ktime_t kt, - struct timespec *ts) -{ - if (kt) { - *ts = ktime_to_timespec(kt); - return true; - } else { - return false; - } -} - /** * ktime_to_timespec64_cond - convert a ktime_t variable to timespec64 * format only if the variable contains data diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index e89eb67356cb39b225cbfff924c1a41e49197006..bcb9b2ac0791dc341fea7d3623778351bf34ffd8 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -889,6 +889,8 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu); bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu); bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu); +int kvm_arch_post_init_vm(struct kvm *kvm); +void kvm_arch_pre_destroy_vm(struct kvm *kvm); #ifndef __KVM_HAVE_ARCH_VM_ALLOC /* @@ -1342,7 +1344,7 @@ static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val) #endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */ struct kvm_vcpu *kvm_get_running_vcpu(void); -struct kvm_vcpu __percpu **kvm_get_running_vcpus(void); +struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void); #ifdef CONFIG_HAVE_KVM_IRQ_BYPASS bool kvm_arch_has_irq_bypass(void); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index ff8c9d527bb415d23d1fa6556a25e894145434b6..bfdf41537cf1facc8d24a2556e43df994c6832a4 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -688,7 +688,10 @@ struct mlx5_ifc_flow_table_nic_cap_bits { u8 nic_rx_multi_path_tirs[0x1]; u8 nic_rx_multi_path_tirs_fts[0x1]; u8 allow_sniffer_and_nic_rx_shared_tir[0x1]; - u8 reserved_at_3[0x1d]; + u8 reserved_at_3[0x4]; + u8 sw_owner_reformat_supported[0x1]; + u8 reserved_at_8[0x18]; + u8 encap_general_header[0x1]; u8 reserved_at_21[0xa]; u8 log_max_packet_reformat_context[0x5]; diff --git a/include/linux/mm.h b/include/linux/mm.h index 52269e56c514d24d318d982b805c5c9e9d7d3082..c54fb96cb1e6cc0fd85ab8cd337fe3b1b3f274b3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2715,6 +2715,10 @@ static inline bool debug_pagealloc_enabled_static(void) #if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_ARCH_HAS_SET_DIRECT_MAP) extern void __kernel_map_pages(struct page *page, int numpages, int enable); +/* + * When called in DEBUG_PAGEALLOC context, the call should most likely be + * guarded by debug_pagealloc_enabled() or debug_pagealloc_enabled_static() + */ static inline void kernel_map_pages(struct page *page, int numpages, int enable) { diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index ba703384bea0c8d4fa2b37717b8656f7e9a04227..4c5eb3aa8e723e8368ed2f9737b460d31224b6e4 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -333,6 +333,7 @@ struct mmc_host { MMC_CAP_UHS_SDR50 | MMC_CAP_UHS_SDR104 | \ MMC_CAP_UHS_DDR50) #define MMC_CAP_SYNC_RUNTIME_PM (1 << 21) /* Synced runtime PM suspends. */ +#define MMC_CAP_NEED_RSP_BUSY (1 << 22) /* Commands with R1B can't use R1. */ #define MMC_CAP_DRIVER_TYPE_A (1 << 23) /* Host supports Driver Type A */ #define MMC_CAP_DRIVER_TYPE_C (1 << 24) /* Host supports Driver Type C */ #define MMC_CAP_DRIVER_TYPE_D (1 << 25) /* Host supports Driver Type D */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a9c6b5c61d2719616fbc5c45cf37a2d967379ba4..6c3f7032e8d9d720aba0022662e72eccf6f1da2f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -72,6 +72,8 @@ void netdev_set_default_ethtool_ops(struct net_device *dev, #define NET_RX_SUCCESS 0 /* keep 'em coming, baby */ #define NET_RX_DROP 1 /* packet dropped */ +#define MAX_NEST_DEV 8 + /* * Transmit return codes: transmit return codes originate from three different * namespaces: @@ -1616,6 +1618,7 @@ enum netdev_priv_flags { * and drivers will need to set them appropriately. * * @mpls_features: Mask of features inheritable by MPLS + * @gso_partial_features: value(s) from NETIF_F_GSO\* * * @ifindex: interface index * @group: The group the device belongs to @@ -1640,8 +1643,11 @@ enum netdev_priv_flags { * @netdev_ops: Includes several pointers to callbacks, * if one wants to override the ndo_*() functions * @ethtool_ops: Management operations + * @l3mdev_ops: Layer 3 master device operations * @ndisc_ops: Includes callbacks for different IPv6 neighbour * discovery handling. Necessary for e.g. 6LoWPAN. + * @xfrmdev_ops: Transformation offload operations + * @tlsdev_ops: Transport Layer Security offload operations * @header_ops: Includes callbacks for creating,parsing,caching,etc * of Layer 2 headers. * @@ -1680,6 +1686,7 @@ enum netdev_priv_flags { * @dev_port: Used to differentiate devices that share * the same function * @addr_list_lock: XXX: need comments on this one + * @name_assign_type: network interface name assignment type * @uc_promisc: Counter that indicates promiscuous mode * has been enabled due to the need to listen to * additional unicast addresses in a device that @@ -1702,6 +1709,9 @@ enum netdev_priv_flags { * @ip6_ptr: IPv6 specific data * @ax25_ptr: AX.25 specific data * @ieee80211_ptr: IEEE 802.11 specific data, assign before registering + * @ieee802154_ptr: IEEE 802.15.4 low-rate Wireless Personal Area Network + * device struct + * @mpls_ptr: mpls_dev struct pointer * * @dev_addr: Hw address (before bcast, * because most packets are unicast) @@ -1710,6 +1720,8 @@ enum netdev_priv_flags { * @num_rx_queues: Number of RX queues * allocated at register_netdev() time * @real_num_rx_queues: Number of RX queues currently active in device + * @xdp_prog: XDP sockets filter program pointer + * @gro_flush_timeout: timeout for GRO layer in NAPI * * @rx_handler: handler for received packets * @rx_handler_data: XXX: need comments on this one @@ -1731,10 +1743,14 @@ enum netdev_priv_flags { * @qdisc: Root qdisc from userspace point of view * @tx_queue_len: Max frames per queue allowed * @tx_global_lock: XXX: need comments on this one + * @xdp_bulkq: XDP device bulk queue + * @xps_cpus_map: all CPUs map for XPS device + * @xps_rxqs_map: all RXQs map for XPS device * * @xps_maps: XXX: need comments on this one * @miniq_egress: clsact qdisc specific data for * egress processing + * @qdisc_hash: qdisc hash table * @watchdog_timeo: Represents the timeout that is used by * the watchdog (see dev_watchdog()) * @watchdog_timer: List of timers @@ -3548,7 +3564,7 @@ static inline unsigned int netif_attrmask_next(int n, const unsigned long *srcp, } /** - * netif_attrmask_next_and - get the next CPU/Rx queue in *src1p & *src2p + * netif_attrmask_next_and - get the next CPU/Rx queue in \*src1p & \*src2p * @n: CPU/Rx queue index * @src1p: the first CPUs/Rx queues mask pointer * @src2p: the second CPUs/Rx queues mask pointer @@ -4375,11 +4391,8 @@ void *netdev_lower_get_next(struct net_device *dev, ldev; \ ldev = netdev_lower_get_next(dev, &(iter))) -struct net_device *netdev_all_lower_get_next(struct net_device *dev, +struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, struct list_head **iter); -struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev, - struct list_head **iter); - int netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *lower_dev, void *data), diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 908d38dbcb91f0b1e7040b230c2506fb3f67f14e..5448c8b443dbf52aeac423ee987d19bb63b23e76 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -121,6 +121,7 @@ struct ip_set_ext { u32 timeout; u8 packets_op; u8 bytes_op; + bool target; }; struct ip_set; @@ -187,6 +188,14 @@ struct ip_set_type_variant { /* Return true if "b" set is the same as "a" * according to the create set parameters */ bool (*same_set)(const struct ip_set *a, const struct ip_set *b); + /* Region-locking is used */ + bool region_lock; +}; + +struct ip_set_region { + spinlock_t lock; /* Region lock */ + size_t ext_size; /* Size of the dynamic extensions */ + u32 elements; /* Number of elements vs timeout */ }; /* The core set type structure */ @@ -501,7 +510,7 @@ ip_set_init_skbinfo(struct ip_set_skbinfo *skbinfo, } #define IP_SET_INIT_KEXT(skb, opt, set) \ - { .bytes = (skb)->len, .packets = 1, \ + { .bytes = (skb)->len, .packets = 1, .target = true,\ .timeout = ip_set_adt_opt_timeout(opt, set) } #define IP_SET_INIT_UEXT(set) \ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index a5f8f03ecd59e1f6dce820247cd18b69a157be11..5d5b91e54f736b33722ffd553985471579e3be76 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -337,35 +337,17 @@ static inline int nfs_server_capable(struct inode *inode, int cap) return NFS_SERVER(inode)->caps & cap; } -static inline void nfs_set_verifier(struct dentry * dentry, unsigned long verf) -{ - dentry->d_time = verf; -} - /** * nfs_save_change_attribute - Returns the inode attribute change cookie * @dir - pointer to parent directory inode - * The "change attribute" is updated every time we finish an operation - * that will result in a metadata change on the server. + * The "cache change attribute" is updated when we need to revalidate + * our dentry cache after a directory was seen to change on the server. */ static inline unsigned long nfs_save_change_attribute(struct inode *dir) { return NFS_I(dir)->cache_change_attribute; } -/** - * nfs_verify_change_attribute - Detects NFS remote directory changes - * @dir - pointer to parent directory inode - * @chattr - previously saved change attribute - * Return "false" if the verifiers doesn't match the change attribute. - * This would usually indicate that the directory contents have changed on - * the server, and that any dentries need revalidating. - */ -static inline int nfs_verify_change_attribute(struct inode *dir, unsigned long chattr) -{ - return chattr == NFS_I(dir)->cache_change_attribute; -} - /* * linux/fs/nfs/inode.c */ @@ -495,6 +477,10 @@ extern const struct file_operations nfs_dir_operations; extern const struct dentry_operations nfs_dentry_operations; extern void nfs_force_lookup_revalidate(struct inode *dir); +extern void nfs_set_verifier(struct dentry * dentry, unsigned long verf); +#if IS_ENABLED(CONFIG_NFS_V4) +extern void nfs_clear_verifier_delegated(struct inode *inode); +#endif /* IS_ENABLED(CONFIG_NFS_V4) */ extern struct dentry *nfs_add_or_obtain(struct dentry *dentry, struct nfs_fh *fh, struct nfs_fattr *fattr, struct nfs4_label *label); diff --git a/include/linux/of_clk.h b/include/linux/of_clk.h index c86fcad23fc21725a14a98d45adc006b38c789ec..31b73a0da9db33e8a61ae7e30b8d6fe5830d8272 100644 --- a/include/linux/of_clk.h +++ b/include/linux/of_clk.h @@ -11,17 +11,17 @@ struct of_device_id; #if defined(CONFIG_COMMON_CLK) && defined(CONFIG_OF) -unsigned int of_clk_get_parent_count(struct device_node *np); -const char *of_clk_get_parent_name(struct device_node *np, int index); +unsigned int of_clk_get_parent_count(const struct device_node *np); +const char *of_clk_get_parent_name(const struct device_node *np, int index); void of_clk_init(const struct of_device_id *matches); #else /* !CONFIG_COMMON_CLK || !CONFIG_OF */ -static inline unsigned int of_clk_get_parent_count(struct device_node *np) +static inline unsigned int of_clk_get_parent_count(const struct device_node *np) { return 0; } -static inline const char *of_clk_get_parent_name(struct device_node *np, +static inline const char *of_clk_get_parent_name(const struct device_node *np, int index) { return NULL; diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 1bf83c8fcaa77e31cd3acd8e2f16c54e6ea05bf5..77de28bfefb0186a2516f643f112a73b792cca55 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -311,7 +311,7 @@ static inline int TestClearPage##uname(struct page *page) { return 0; } __PAGEFLAG(Locked, locked, PF_NO_TAIL) PAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) __CLEARPAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) -PAGEFLAG(Error, error, PF_NO_COMPOUND) TESTCLEARFLAG(Error, error, PF_NO_COMPOUND) +PAGEFLAG(Error, error, PF_NO_TAIL) TESTCLEARFLAG(Error, error, PF_NO_TAIL) PAGEFLAG(Referenced, referenced, PF_HEAD) TESTCLEARFLAG(Referenced, referenced, PF_HEAD) __SETPAGEFLAG(Referenced, referenced, PF_HEAD) diff --git a/include/linux/phy.h b/include/linux/phy.h index c570e162e05e58745d613325b0d93a6bbabf3ace..452e8ba8665f1078f5777e38a3acb293483c49df 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -357,6 +357,7 @@ struct macsec_ops; * is_gigabit_capable: Set to true if PHY supports 1000Mbps * has_fixups: Set to true if this phy has fixups/quirks. * suspended: Set to true if this phy has been suspended successfully. + * suspended_by_mdio_bus: Set to true if this phy was suspended by MDIO bus. * sysfs_links: Internal boolean tracking sysfs symbolic links setup/removal. * loopback_enabled: Set true if this phy has been loopbacked successfully. * state: state of the PHY for management purposes @@ -396,6 +397,7 @@ struct phy_device { unsigned is_gigabit_capable:1; unsigned has_fixups:1; unsigned suspended:1; + unsigned suspended_by_mdio_bus:1; unsigned sysfs_links:1; unsigned loopback_enabled:1; @@ -557,6 +559,7 @@ struct phy_driver { /* * Checks if the PHY generated an interrupt. * For multi-PHY devices with shared PHY interrupt pin + * Set interrupt bits have to be cleared. */ int (*did_interrupt)(struct phy_device *phydev); diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index d5765039652a5c1e94ba7d3a20795473b4711a4d..ae58fad7f1e0d8a96274cd71c77b727259a20971 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -29,7 +29,8 @@ struct pipe_buffer { /** * struct pipe_inode_info - a linux kernel pipe * @mutex: mutex protecting the whole thing - * @wait: reader/writer wait point in case of empty/full pipe + * @rd_wait: reader wait point in case of empty pipe + * @wr_wait: writer wait point in case of full pipe * @head: The point of buffer production * @tail: The point of buffer consumption * @max_usage: The maximum number of slots that may be used in the ring diff --git a/include/linux/platform_data/spi-omap2-mcspi.h b/include/linux/platform_data/spi-omap2-mcspi.h index 0bf9fddb830640dd282c38ee1a001e9c9d2b4f6e..3b400b1919a9bd8a9a446da90e37a3582af15de9 100644 --- a/include/linux/platform_data/spi-omap2-mcspi.h +++ b/include/linux/platform_data/spi-omap2-mcspi.h @@ -11,6 +11,7 @@ struct omap2_mcspi_platform_config { unsigned short num_cs; unsigned int regs_offset; unsigned int pin_dir:1; + size_t max_xfer_len; }; struct omap2_mcspi_device_config { diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 276a03c246919ee57be5495808a4043c7abdcaac..041bfa412aa09521813c057fbfc3f273dfda062b 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -24,7 +24,7 @@ struct platform_device { int id; bool id_auto; struct device dev; - u64 dma_mask; + u64 platform_dma_mask; u32 num_resources; struct resource *resource; diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h index e5b752027a031b119ce09a982b93f935c736c93d..9670b54b484a6f7849a15e458a7f63246f425b2b 100644 --- a/include/linux/rculist_nulls.h +++ b/include/linux/rculist_nulls.h @@ -145,6 +145,13 @@ static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n, } } +/* after that hlist_nulls_del will work */ +static inline void hlist_nulls_add_fake(struct hlist_nulls_node *n) +{ + n->pprev = &n->next; + n->next = (struct hlist_nulls_node *)NULLS_MARKER(NULL); +} + /** * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type * @tpos: the type * to use as a loop cursor. diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index beb9a9da16994cac25b2d564c9aaaf75376efc66..70ebef866cc82ada0c6c1f69cc2a57e23cb732ba 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -972,9 +972,9 @@ static inline int rhashtable_lookup_insert_key( /** * rhashtable_lookup_get_insert_key - lookup and insert object into hash table * @ht: hash table + * @key: key * @obj: pointer to hash head inside object * @params: hash table parameters - * @data: pointer to element data already in hashes * * Just like rhashtable_lookup_insert_key(), but this function returns the * object if it exists, NULL if it does not and the insertion was successful, diff --git a/include/linux/sched/nohz.h b/include/linux/sched/nohz.h index 1abe91ff6e4a2091f97fc903e56c96c9de78fb92..6d67e9a5af6bb48a77c14b85c09496181520914d 100644 --- a/include/linux/sched/nohz.h +++ b/include/linux/sched/nohz.h @@ -15,9 +15,11 @@ static inline void nohz_balance_enter_idle(int cpu) { } #ifdef CONFIG_NO_HZ_COMMON void calc_load_nohz_start(void); +void calc_load_nohz_remote(struct rq *rq); void calc_load_nohz_stop(void); #else static inline void calc_load_nohz_start(void) { } +static inline void calc_load_nohz_remote(struct rq *rq) { } static inline void calc_load_nohz_stop(void) { } #endif /* CONFIG_NO_HZ_COMMON */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ca8806b693882e9ae933d70d0bb6c4cbd3ca81bd..5b50278c4bc852b7659f9af8e392a45630111d0b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -611,9 +611,15 @@ typedef unsigned char *sk_buff_data_t; * @next: Next buffer in list * @prev: Previous buffer in list * @tstamp: Time we arrived/left + * @skb_mstamp_ns: (aka @tstamp) earliest departure time; start point + * for retransmit timer * @rbnode: RB tree node, alternative to next/prev for netem/tcp + * @list: queue head * @sk: Socket we are owned by + * @ip_defrag_offset: (aka @sk) alternate use of @sk, used in + * fragmentation management * @dev: Device we arrived on/are leaving by + * @dev_scratch: (aka @dev) alternate use of @dev when @dev would be %NULL * @cb: Control buffer. Free for use by every layer. Put private vars here * @_skb_refdst: destination entry (with norefcount bit) * @sp: the security path, used for xfrm @@ -632,6 +638,9 @@ typedef unsigned char *sk_buff_data_t; * @pkt_type: Packet class * @fclone: skbuff clone status * @ipvs_property: skbuff is owned by ipvs + * @inner_protocol_type: whether the inner protocol is + * ENCAP_TYPE_ETHER or ENCAP_TYPE_IPPROTO + * @remcsum_offload: remote checksum offload is enabled * @offload_fwd_mark: Packet was L2-forwarded in hardware * @offload_l3_fwd_mark: Packet was L3-forwarded in hardware * @tc_skip_classify: do not classify packet. set by IFB device @@ -650,6 +659,8 @@ typedef unsigned char *sk_buff_data_t; * @tc_index: Traffic control index * @hash: the packet hash * @queue_mapping: Queue mapping for multiqueue devices + * @head_frag: skb was allocated from page fragments, + * not allocated by kmalloc() or vmalloc(). * @pfmemalloc: skbuff was allocated from PFMEMALLOC reserves * @active_extensions: active extensions (skb_ext_id types) * @ndisc_nodetype: router type (from link layer) @@ -660,15 +671,28 @@ typedef unsigned char *sk_buff_data_t; * @wifi_acked_valid: wifi_acked was set * @wifi_acked: whether frame was acked on wifi or not * @no_fcs: Request NIC to treat last 4 bytes as Ethernet FCS + * @encapsulation: indicates the inner headers in the skbuff are valid + * @encap_hdr_csum: software checksum is needed + * @csum_valid: checksum is already valid * @csum_not_inet: use CRC32c to resolve CHECKSUM_PARTIAL + * @csum_complete_sw: checksum was completed by software + * @csum_level: indicates the number of consecutive checksums found in + * the packet minus one that have been verified as + * CHECKSUM_UNNECESSARY (max 3) * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB * @napi_id: id of the NAPI struct this skb came from + * @sender_cpu: (aka @napi_id) source CPU in XPS * @secmark: security marking * @mark: Generic packet mark + * @reserved_tailroom: (aka @mark) number of bytes of free space available + * at the tail of an sk_buff + * @vlan_present: VLAN tag is present * @vlan_proto: vlan encapsulation protocol * @vlan_tci: vlan tag control information * @inner_protocol: Protocol (encapsulation) + * @inner_ipproto: (aka @inner_protocol) stores ipproto when + * skb->inner_protocol_type == ENCAP_TYPE_IPPROTO; * @inner_transport_header: Inner transport layer header (encapsulation) * @inner_network_header: Network layer header (encapsulation) * @inner_mac_header: Link layer header (encapsulation) @@ -750,7 +774,9 @@ struct sk_buff { #endif #define CLONED_OFFSET() offsetof(struct sk_buff, __cloned_offset) + /* private: */ __u8 __cloned_offset[0]; + /* public: */ __u8 cloned:1, nohdr:1, fclone:2, @@ -775,7 +801,9 @@ struct sk_buff { #endif #define PKT_TYPE_OFFSET() offsetof(struct sk_buff, __pkt_type_offset) + /* private: */ __u8 __pkt_type_offset[0]; + /* public: */ __u8 pkt_type:3; __u8 ignore_df:1; __u8 nf_trace:1; @@ -798,7 +826,9 @@ struct sk_buff { #define PKT_VLAN_PRESENT_BIT 0 #endif #define PKT_VLAN_PRESENT_OFFSET() offsetof(struct sk_buff, __pkt_vlan_present_offset) + /* private: */ __u8 __pkt_vlan_present_offset[0]; + /* public: */ __u8 vlan_present:1; __u8 csum_complete_sw:1; __u8 csum_level:2; diff --git a/include/linux/socket.h b/include/linux/socket.h index 2d23134031016e6efefc93c6270c0efa7c4d60f2..15f3412d481e45ff48c49a7a44bcd56b6dd1a70c 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -401,7 +401,8 @@ extern int __sys_sendto(int fd, void __user *buff, size_t len, int addr_len); extern int __sys_accept4_file(struct file *file, unsigned file_flags, struct sockaddr __user *upeer_sockaddr, - int __user *upeer_addrlen, int flags); + int __user *upeer_addrlen, int flags, + unsigned long nofile); extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); extern int __sys_socket(int family, int type, int protocol); diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 4a230c2f1c317ab87c725afee60cb2a3e275a308..2b2055b035eee13b44b8021f540424758f3a52eb 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -191,7 +191,7 @@ struct platform_s2idle_ops { int (*begin)(void); int (*prepare)(void); int (*prepare_late)(void); - void (*wake)(void); + bool (*wake)(void); void (*restore_early)(void); void (*restore)(void); void (*end)(void); diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index cde3dc18e21a2cdee5ef36183d180946e45be0ea..046bb94bd4d61da998a809a82eebdc22691c0ee7 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -64,6 +64,9 @@ extern void swiotlb_tbl_sync_single(struct device *hwdev, size_t size, enum dma_data_direction dir, enum dma_sync_target target); +dma_addr_t swiotlb_map(struct device *dev, phys_addr_t phys, + size_t size, enum dma_data_direction dir, unsigned long attrs); + #ifdef CONFIG_SWIOTLB extern enum swiotlb_force swiotlb_force; extern phys_addr_t io_tlb_start, io_tlb_end; @@ -73,8 +76,6 @@ static inline bool is_swiotlb_buffer(phys_addr_t paddr) return paddr >= io_tlb_start && paddr < io_tlb_end; } -bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr, - size_t size, enum dma_data_direction dir, unsigned long attrs); void __init swiotlb_exit(void); unsigned int swiotlb_max_segment(void); size_t swiotlb_max_mapping_size(struct device *dev); @@ -85,12 +86,6 @@ static inline bool is_swiotlb_buffer(phys_addr_t paddr) { return false; } -static inline bool swiotlb_map(struct device *dev, phys_addr_t *phys, - dma_addr_t *dma_addr, size_t size, enum dma_data_direction dir, - unsigned long attrs) -{ - return false; -} static inline void swiotlb_exit(void) { } diff --git a/include/linux/time32.h b/include/linux/time32.h index cad4c318600213430212947cbec7a63859654f3c..cf9320cd2d0bda2ab247e234dbdd53a778eeec24 100644 --- a/include/linux/time32.h +++ b/include/linux/time32.h @@ -12,8 +12,6 @@ #include #include -#define TIME_T_MAX (__kernel_old_time_t)((1UL << ((sizeof(__kernel_old_time_t) << 3) - 1)) - 1) - typedef s32 old_time32_t; struct old_timespec32 { @@ -73,162 +71,12 @@ struct __kernel_timex; int get_old_timex32(struct __kernel_timex *, const struct old_timex32 __user *); int put_old_timex32(struct old_timex32 __user *, const struct __kernel_timex *); -#if __BITS_PER_LONG == 64 - -/* timespec64 is defined as timespec here */ -static inline struct timespec timespec64_to_timespec(const struct timespec64 ts64) -{ - return *(const struct timespec *)&ts64; -} - -static inline struct timespec64 timespec_to_timespec64(const struct timespec ts) -{ - return *(const struct timespec64 *)&ts; -} - -#else -static inline struct timespec timespec64_to_timespec(const struct timespec64 ts64) -{ - struct timespec ret; - - ret.tv_sec = (time_t)ts64.tv_sec; - ret.tv_nsec = ts64.tv_nsec; - return ret; -} - -static inline struct timespec64 timespec_to_timespec64(const struct timespec ts) -{ - struct timespec64 ret; - - ret.tv_sec = ts.tv_sec; - ret.tv_nsec = ts.tv_nsec; - return ret; -} -#endif - -static inline int timespec_equal(const struct timespec *a, - const struct timespec *b) -{ - return (a->tv_sec == b->tv_sec) && (a->tv_nsec == b->tv_nsec); -} - -/* - * lhs < rhs: return <0 - * lhs == rhs: return 0 - * lhs > rhs: return >0 - */ -static inline int timespec_compare(const struct timespec *lhs, const struct timespec *rhs) -{ - if (lhs->tv_sec < rhs->tv_sec) - return -1; - if (lhs->tv_sec > rhs->tv_sec) - return 1; - return lhs->tv_nsec - rhs->tv_nsec; -} - -/* - * Returns true if the timespec is norm, false if denorm: - */ -static inline bool timespec_valid(const struct timespec *ts) -{ - /* Dates before 1970 are bogus */ - if (ts->tv_sec < 0) - return false; - /* Can't have more nanoseconds then a second */ - if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) - return false; - return true; -} - -/** - * timespec_to_ns - Convert timespec to nanoseconds - * @ts: pointer to the timespec variable to be converted - * - * Returns the scalar nanosecond representation of the timespec - * parameter. - */ -static inline s64 timespec_to_ns(const struct timespec *ts) -{ - return ((s64) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec; -} - /** - * ns_to_timespec - Convert nanoseconds to timespec - * @nsec: the nanoseconds value to be converted - * - * Returns the timespec representation of the nsec parameter. - */ -extern struct timespec ns_to_timespec(const s64 nsec); - -/** - * timespec_add_ns - Adds nanoseconds to a timespec - * @a: pointer to timespec to be incremented - * @ns: unsigned nanoseconds value to be added - * - * This must always be inlined because its used from the x86-64 vdso, - * which cannot call other kernel functions. - */ -static __always_inline void timespec_add_ns(struct timespec *a, u64 ns) -{ - a->tv_sec += __iter_div_u64_rem(a->tv_nsec + ns, NSEC_PER_SEC, &ns); - a->tv_nsec = ns; -} - -static inline unsigned long mktime(const unsigned int year, - const unsigned int mon, const unsigned int day, - const unsigned int hour, const unsigned int min, - const unsigned int sec) -{ - return mktime64(year, mon, day, hour, min, sec); -} - -static inline bool timeval_valid(const struct timeval *tv) -{ - /* Dates before 1970 are bogus */ - if (tv->tv_sec < 0) - return false; - - /* Can't have more microseconds then a second */ - if (tv->tv_usec < 0 || tv->tv_usec >= USEC_PER_SEC) - return false; - - return true; -} - -/** - * timeval_to_ns - Convert timeval to nanoseconds - * @ts: pointer to the timeval variable to be converted - * - * Returns the scalar nanosecond representation of the timeval - * parameter. - */ -static inline s64 timeval_to_ns(const struct timeval *tv) -{ - return ((s64) tv->tv_sec * NSEC_PER_SEC) + - tv->tv_usec * NSEC_PER_USEC; -} - -/** - * ns_to_timeval - Convert nanoseconds to timeval + * ns_to_kernel_old_timeval - Convert nanoseconds to timeval * @nsec: the nanoseconds value to be converted * * Returns the timeval representation of the nsec parameter. */ -extern struct timeval ns_to_timeval(const s64 nsec); extern struct __kernel_old_timeval ns_to_kernel_old_timeval(s64 nsec); -/* - * Old names for the 32-bit time_t interfaces, these will be removed - * when everything uses the new names. - */ -#define compat_time_t old_time32_t -#define compat_timeval old_timeval32 -#define compat_timespec old_timespec32 -#define compat_itimerspec old_itimerspec32 -#define ns_to_compat_timeval ns_to_old_timeval32 -#define get_compat_itimerspec64 get_old_itimerspec32 -#define put_compat_itimerspec64 put_old_itimerspec32 -#define compat_get_timespec64 get_old_timespec32 -#define compat_put_timespec64 put_old_timespec32 - #endif diff --git a/include/linux/timekeeping32.h b/include/linux/timekeeping32.h index cc59cc9e0e841dc8980882837afb03a5ae10a51e..266017fc9ee9c194bd5013161a442007e23cd9cf 100644 --- a/include/linux/timekeeping32.h +++ b/include/linux/timekeeping32.h @@ -11,36 +11,4 @@ static inline unsigned long get_seconds(void) return ktime_get_real_seconds(); } -static inline void getnstimeofday(struct timespec *ts) -{ - struct timespec64 ts64; - - ktime_get_real_ts64(&ts64); - *ts = timespec64_to_timespec(ts64); -} - -static inline void ktime_get_ts(struct timespec *ts) -{ - struct timespec64 ts64; - - ktime_get_ts64(&ts64); - *ts = timespec64_to_timespec(ts64); -} - -static inline void getrawmonotonic(struct timespec *ts) -{ - struct timespec64 ts64; - - ktime_get_raw_ts64(&ts64); - *ts = timespec64_to_timespec(ts64); -} - -static inline void getboottime(struct timespec *ts) -{ - struct timespec64 ts64; - - getboottime64(&ts64); - *ts = timespec64_to_timespec(ts64); -} - #endif diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index af2c85d3a1dde028e7fad140da14ef62f56a6127..6c7a10a6d71e59ead3e12003399b4f97993ebc6e 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -440,7 +440,7 @@ struct synth_event_trace_state { struct synth_event *event; unsigned int cur_field; unsigned int n_u64; - bool enabled; + bool disabled; bool add_next; bool add_name; }; diff --git a/include/linux/tty.h b/include/linux/tty.h index bfa4e2ee94a9de340321ecdd4141272643ca9115..bd5fe0e907e8c1c219a496120d49a0fa42b8c736 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -225,6 +225,8 @@ struct tty_port_client_operations { void (*write_wakeup)(struct tty_port *port); }; +extern const struct tty_port_client_operations tty_port_default_client_ops; + struct tty_port { struct tty_bufhead buf; /* Locked internally */ struct tty_struct *tty; /* Back pointer */ diff --git a/include/linux/types.h b/include/linux/types.h index eb870ad42919de7fb1e6a41ded184460b0cb0b81..d3021c87917953be758958fdf0fef4731702224c 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -65,11 +65,6 @@ typedef __kernel_ssize_t ssize_t; typedef __kernel_ptrdiff_t ptrdiff_t; #endif -#ifndef _TIME_T -#define _TIME_T -typedef __kernel_old_time_t time_t; -#endif - #ifndef _CLOCK_T #define _CLOCK_T typedef __kernel_clock_t clock_t; diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index a1be64c9940fb4ad4e2365f226419f050d6addba..22c1f579afe3020b22ed36a40523ab34c08a3292 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -69,4 +69,7 @@ /* Hub needs extra delay after resetting its port. */ #define USB_QUIRK_HUB_SLOW_RESET BIT(14) +/* device has blacklisted endpoints */ +#define USB_QUIRK_ENDPOINT_BLACKLIST BIT(15) + #endif /* __LINUX_USB_QUIRKS_H */ diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index ec38132366992efdcddafd4e8bab9e2edcb3aa1c..0507a162ccd0e7ba4edf007654084effe3b5579a 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -141,8 +141,9 @@ extern int remap_vmalloc_range_partial(struct vm_area_struct *vma, extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, unsigned long pgoff); -void vmalloc_sync_all(void); - +void vmalloc_sync_mappings(void); +void vmalloc_sync_unmappings(void); + /* * Lowlevel-APIs (not for driver use!) */ diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 4261d1c6e87b1a24fafa650dab1c1092cdbcd926..e48554e6526c0f09dd2f2c0d89477b851d8b6f05 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -487,6 +487,19 @@ extern void wq_worker_comm(char *buf, size_t size, struct task_struct *task); * * We queue the work to the CPU on which it was submitted, but if the CPU dies * it can be processed by another CPU. + * + * Memory-ordering properties: If it returns %true, guarantees that all stores + * preceding the call to queue_work() in the program order will be visible from + * the CPU which will execute @work by the time such work executes, e.g., + * + * { x is initially 0 } + * + * CPU0 CPU1 + * + * WRITE_ONCE(x, 1); [ @work is being executed ] + * r0 = queue_work(wq, work); r1 = READ_ONCE(x); + * + * Forbids: r0 == true && r1 == 0 */ static inline bool queue_work(struct workqueue_struct *wq, struct work_struct *work) @@ -546,6 +559,9 @@ static inline bool schedule_work_on(int cpu, struct work_struct *work) * This puts a job in the kernel-global workqueue if it was not already * queued and leaves it in the same position on the kernel-global * workqueue otherwise. + * + * Shares the same memory-ordering properties of queue_work(), cf. the + * DocBook header of queue_work(). */ static inline bool schedule_work(struct work_struct *work) { diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index 54e227e6b06a78902941ea20be01da76ac7ae08b..a259050f84afcda7076a894226ed268bc116a8f0 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -108,6 +108,7 @@ struct fib_rule_notifier_info { [FRA_OIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, \ [FRA_PRIORITY] = { .type = NLA_U32 }, \ [FRA_FWMARK] = { .type = NLA_U32 }, \ + [FRA_TUN_ID] = { .type = NLA_U64 }, \ [FRA_FWMASK] = { .type = NLA_U32 }, \ [FRA_TABLE] = { .type = NLA_U32 }, \ [FRA_SUPPRESS_PREFIXLEN] = { .type = NLA_U32 }, \ diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index d93017a7ce5c147a3efc3083ba37f50a619ab73a..62838391582760a6e4101a2c9dde0b3dd9922218 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -5,6 +5,7 @@ #include #include #include +#include #include struct sk_buff; @@ -33,7 +34,6 @@ enum flow_dissect_ret { /** * struct flow_dissector_key_basic: - * @thoff: Transport header offset * @n_proto: Network header protocol (eg. IPv4/IPv6) * @ip_proto: Transport header protocol (eg. TCP/UDP) */ @@ -349,4 +349,12 @@ struct bpf_flow_dissector { void *data_end; }; +static inline void +flow_dissector_init_keys(struct flow_dissector_key_control *key_control, + struct flow_dissector_key_basic *key_basic) +{ + memset(key_control, 0, sizeof(*key_control)); + memset(key_basic, 0, sizeof(*key_basic)); +} + #endif diff --git a/include/net/icmp.h b/include/net/icmp.h index 5d4bfdba9adf03759affb01617245a290e339a8f..9ac2d2672a938626b28ccbd7e8d5095bcf2910f5 100644 --- a/include/net/icmp.h +++ b/include/net/icmp.h @@ -43,6 +43,12 @@ static inline void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 __icmp_send(skb_in, type, code, info, &IPCB(skb_in)->opt); } +#if IS_ENABLED(CONFIG_NF_NAT) +void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info); +#else +#define icmp_ndo_send icmp_send +#endif + int icmp_rcv(struct sk_buff *skb); int icmp_err(struct sk_buff *skb, u32 info); int icmp_init(void); diff --git a/include/net/mac80211.h b/include/net/mac80211.h index aa145808e57a2377994ec4b9b0c858dbd98fbdd5..77e6b5a83b065fff4e80cec8dd86227d248e4a0b 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1004,12 +1004,11 @@ ieee80211_rate_get_vht_nss(const struct ieee80211_tx_rate *rate) struct ieee80211_tx_info { /* common information */ u32 flags; - u8 band; - - u8 hw_queue; - - u16 ack_frame_id:6; - u16 tx_time_est:10; + u32 band:3, + ack_frame_id:13, + hw_queue:4, + tx_time_est:10; + /* 2 free bits */ union { struct { diff --git a/include/net/sock.h b/include/net/sock.h index 02162b0378f73f9221aec78e7adedd7124ef652b..328564525526914f9d7aed9216a2fd5f8c255af4 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -117,19 +117,26 @@ typedef __u64 __bitwise __addrpair; * struct sock_common - minimal network layer representation of sockets * @skc_daddr: Foreign IPv4 addr * @skc_rcv_saddr: Bound local IPv4 addr + * @skc_addrpair: 8-byte-aligned __u64 union of @skc_daddr & @skc_rcv_saddr * @skc_hash: hash value used with various protocol lookup tables * @skc_u16hashes: two u16 hash values used by UDP lookup tables * @skc_dport: placeholder for inet_dport/tw_dport * @skc_num: placeholder for inet_num/tw_num + * @skc_portpair: __u32 union of @skc_dport & @skc_num * @skc_family: network address family * @skc_state: Connection state * @skc_reuse: %SO_REUSEADDR setting * @skc_reuseport: %SO_REUSEPORT setting + * @skc_ipv6only: socket is IPV6 only + * @skc_net_refcnt: socket is using net ref counting * @skc_bound_dev_if: bound device index if != 0 * @skc_bind_node: bind hash linkage for various protocol lookup tables * @skc_portaddr_node: second hash linkage for UDP/UDP-Lite protocol * @skc_prot: protocol handlers inside a network family * @skc_net: reference to the network namespace of this socket + * @skc_v6_daddr: IPV6 destination address + * @skc_v6_rcv_saddr: IPV6 source address + * @skc_cookie: socket's cookie value * @skc_node: main hash linkage for various protocol lookup tables * @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol * @skc_tx_queue_mapping: tx queue number for this connection @@ -137,7 +144,15 @@ typedef __u64 __bitwise __addrpair; * @skc_flags: place holder for sk_flags * %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE, * %SO_OOBINLINE settings, %SO_TIMESTAMPING settings + * @skc_listener: connection request listener socket (aka rsk_listener) + * [union with @skc_flags] + * @skc_tw_dr: (aka tw_dr) ptr to &struct inet_timewait_death_row + * [union with @skc_flags] * @skc_incoming_cpu: record/match cpu processing incoming packets + * @skc_rcv_wnd: (aka rsk_rcv_wnd) TCP receive window size (possibly scaled) + * [union with @skc_incoming_cpu] + * @skc_tw_rcv_nxt: (aka tw_rcv_nxt) TCP window next expected seq number + * [union with @skc_incoming_cpu] * @skc_refcnt: reference count * * This is the minimal network layer representation of sockets, the header @@ -245,6 +260,7 @@ struct bpf_sk_storage; * @sk_dst_cache: destination cache * @sk_dst_pending_confirm: need to confirm neighbour * @sk_policy: flow policy + * @sk_rx_skb_cache: cache copy of recently accessed RX skb * @sk_receive_queue: incoming packets * @sk_wmem_alloc: transmit queue bytes committed * @sk_tsq_flags: TCP Small Queues flags @@ -265,6 +281,8 @@ struct bpf_sk_storage; * @sk_no_check_rx: allow zero checksum in RX packets * @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO) * @sk_route_nocaps: forbidden route capabilities (e.g NETIF_F_GSO_MASK) + * @sk_route_forced_caps: static, forced route capabilities + * (set in tcp_init_sock()) * @sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4) * @sk_gso_max_size: Maximum GSO segment size to build * @sk_gso_max_segs: Maximum number of GSO segments @@ -303,6 +321,8 @@ struct bpf_sk_storage; * @sk_frag: cached page frag * @sk_peek_off: current peek_offset value * @sk_send_head: front of stuff to transmit + * @tcp_rtx_queue: TCP re-transmit queue [union with @sk_send_head] + * @sk_tx_skb_cache: cache copy of recently accessed TX skb * @sk_security: used by security modules * @sk_mark: generic packet mark * @sk_cgrp_data: cgroup data for this cgroup @@ -313,11 +333,14 @@ struct bpf_sk_storage; * @sk_write_space: callback to indicate there is bf sending space available * @sk_error_report: callback to indicate errors (e.g. %MSG_ERRQUEUE) * @sk_backlog_rcv: callback to process the backlog + * @sk_validate_xmit_skb: ptr to an optional validate function * @sk_destruct: called at sock freeing time, i.e. when all refcnt == 0 * @sk_reuseport_cb: reuseport group container + * @sk_bpf_storage: ptr to cache and control for bpf_sk_storage * @sk_rcu: used during RCU grace period * @sk_clockid: clockid used by time-based scheduling (SO_TXTIME) * @sk_txtime_deadline_mode: set deadline mode for SO_TXTIME + * @sk_txtime_report_errors: set report errors mode for SO_TXTIME * @sk_txtime_unused: unused txtime flags */ struct sock { @@ -393,7 +416,9 @@ struct sock { struct sk_filter __rcu *sk_filter; union { struct socket_wq __rcu *sk_wq; + /* private: */ struct socket_wq *sk_wq_raw; + /* public: */ }; #ifdef CONFIG_XFRM struct xfrm_policy __rcu *sk_policy[2]; @@ -2017,7 +2042,7 @@ static inline int skb_copy_to_page_nocache(struct sock *sk, struct iov_iter *fro * sk_wmem_alloc_get - returns write allocations * @sk: socket * - * Returns sk_wmem_alloc minus initial offset of one + * Return: sk_wmem_alloc minus initial offset of one */ static inline int sk_wmem_alloc_get(const struct sock *sk) { @@ -2028,7 +2053,7 @@ static inline int sk_wmem_alloc_get(const struct sock *sk) * sk_rmem_alloc_get - returns read allocations * @sk: socket * - * Returns sk_rmem_alloc + * Return: sk_rmem_alloc */ static inline int sk_rmem_alloc_get(const struct sock *sk) { @@ -2039,7 +2064,7 @@ static inline int sk_rmem_alloc_get(const struct sock *sk) * sk_has_allocations - check if allocations are outstanding * @sk: socket * - * Returns true if socket has write or read allocations + * Return: true if socket has write or read allocations */ static inline bool sk_has_allocations(const struct sock *sk) { @@ -2050,7 +2075,7 @@ static inline bool sk_has_allocations(const struct sock *sk) * skwq_has_sleeper - check if there are any waiting processes * @wq: struct socket_wq * - * Returns true if socket_wq has waiting processes + * Return: true if socket_wq has waiting processes * * The purpose of the skwq_has_sleeper and sock_poll_wait is to wrap the memory * barrier call. They were added due to the race found within the tcp code. @@ -2238,6 +2263,9 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, * gfpflags_allow_blocking() isn't enough here as direct reclaim may nest * inside other socket operations and end up recursing into sk_page_frag() * while it's already in use. + * + * Return: a per task page_frag if context allows that, + * otherwise a per socket one. */ static inline struct page_frag *sk_page_frag(struct sock *sk) { @@ -2432,6 +2460,7 @@ static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags) &skb_shinfo(skb)->tskey); } +DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key); /** * sk_eat_skb - Release a skb if it is no longer needed * @sk: socket to eat this skb from @@ -2440,7 +2469,6 @@ static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags) * This routine must be called with interrupts disabled or with the socket * locked so that the sk_buff queue operation is ok. */ -DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key); static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb) { __skb_unlink(skb, &sk->sk_receive_queue); diff --git a/include/scsi/iscsi_proto.h b/include/scsi/iscsi_proto.h index 533f56733ba84053e1ecb6f30d2fa344b900dda2..b71b5c4f418c5e5e5460bcbcbdb9742226ce70c3 100644 --- a/include/scsi/iscsi_proto.h +++ b/include/scsi/iscsi_proto.h @@ -627,7 +627,6 @@ struct iscsi_reject { #define ISCSI_REASON_BOOKMARK_INVALID 9 #define ISCSI_REASON_BOOKMARK_NO_RESOURCES 10 #define ISCSI_REASON_NEGOTIATION_RESET 11 -#define ISCSI_REASON_WAITING_FOR_LOGOUT 12 /* Max. number of Key=Value pairs in a text message */ #define MAX_KEY_VALUE_PAIRS 8192 diff --git a/include/soc/mscc/ocelot_dev.h b/include/soc/mscc/ocelot_dev.h index 0a50d53bbd3f8d9f76a2a3b7a0f71865da7147cd..7c08437061fcdb158292328a0b6e17c816f74b16 100644 --- a/include/soc/mscc/ocelot_dev.h +++ b/include/soc/mscc/ocelot_dev.h @@ -74,7 +74,7 @@ #define DEV_MAC_TAGS_CFG_TAG_ID_M GENMASK(31, 16) #define DEV_MAC_TAGS_CFG_TAG_ID_X(x) (((x) & GENMASK(31, 16)) >> 16) #define DEV_MAC_TAGS_CFG_VLAN_LEN_AWR_ENA BIT(2) -#define DEV_MAC_TAGS_CFG_PB_ENA BIT(1) +#define DEV_MAC_TAGS_CFG_VLAN_DBL_AWR_ENA BIT(1) #define DEV_MAC_TAGS_CFG_VLAN_AWR_ENA BIT(0) #define DEV_MAC_ADV_CHK_CFG 0x2c diff --git a/include/sound/rawmidi.h b/include/sound/rawmidi.h index 40ab20439fee21d650fdb9d72beb817ceb4b71aa..a36b7227a15ad5dee698a60d3c15d5fae63c04ee 100644 --- a/include/sound/rawmidi.h +++ b/include/sound/rawmidi.h @@ -77,9 +77,9 @@ struct snd_rawmidi_substream { struct list_head list; /* list of all substream for given stream */ int stream; /* direction */ int number; /* substream number */ - unsigned int opened: 1, /* open flag */ - append: 1, /* append flag (merge more streams) */ - active_sensing: 1; /* send active sensing when close */ + bool opened; /* open flag */ + bool append; /* append flag (merge more streams) */ + bool active_sensing; /* send active sensing when close */ int use_count; /* use counter (for output) */ size_t bytes; struct snd_rawmidi *rmidi; diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h index 2a306c6f3fbcb7595302d9a30f70d9f62a05ca65..1b6afbc1a4ed10676c0bc188b1065d1936c2427c 100644 --- a/include/sound/soc-dapm.h +++ b/include/sound/soc-dapm.h @@ -392,8 +392,6 @@ int snd_soc_dapm_get_enum_double(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol); int snd_soc_dapm_put_enum_double(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol); -int snd_soc_dapm_put_enum_double_locked(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol); int snd_soc_dapm_info_pin_switch(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_info *uinfo); int snd_soc_dapm_get_pin_switch(struct snd_kcontrol *kcontrol, diff --git a/include/sound/soc.h b/include/sound/soc.h index f0e4f36f83bfa7d349f54d278cc46e5db235d8bb..8a2266676b2dd2054e7e93903a31f9dfd57fa80e 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -1157,7 +1157,7 @@ struct snd_soc_pcm_runtime { ((i) < rtd->num_codecs) && ((dai) = rtd->codec_dais[i]); \ (i)++) #define for_each_rtd_codec_dai_rollback(rtd, i, dai) \ - for (; ((--i) >= 0) && ((dai) = rtd->codec_dais[i]);) + for (; (--(i) >= 0) && ((dai) = rtd->codec_dais[i]);) void snd_soc_close_delayed_work(struct snd_soc_pcm_runtime *rtd); diff --git a/include/uapi/asm-generic/posix_types.h b/include/uapi/asm-generic/posix_types.h index 2f9c80595ba771e41767beb5d814b3204a39d332..b5f7594eee7ab26ced0d3041ffa04a2662a39818 100644 --- a/include/uapi/asm-generic/posix_types.h +++ b/include/uapi/asm-generic/posix_types.h @@ -87,7 +87,9 @@ typedef struct { typedef __kernel_long_t __kernel_off_t; typedef long long __kernel_loff_t; typedef __kernel_long_t __kernel_old_time_t; +#ifndef __KERNEL__ typedef __kernel_long_t __kernel_time_t; +#endif typedef long long __kernel_time64_t; typedef __kernel_long_t __kernel_clock_t; typedef int __kernel_timer_t; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f1d74a2bd23493635afcbd6a7336c2fd2806f471..22f235260a3a352cf4223249fc1d26f2fce62f34 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1045,9 +1045,9 @@ union bpf_attr { * supports redirection to the egress interface, and accepts no * flag at all. * - * The same effect can be attained with the more generic - * **bpf_redirect_map**\ (), which requires specific maps to be - * used but offers better performance. + * The same effect can also be attained with the more generic + * **bpf_redirect_map**\ (), which uses a BPF map to store the + * redirect target instead of providing it directly to the helper. * Return * For XDP, the helper returns **XDP_REDIRECT** on success or * **XDP_ABORTED** on error. For other program types, the values @@ -1611,13 +1611,11 @@ union bpf_attr { * the caller. Any higher bits in the *flags* argument must be * unset. * - * When used to redirect packets to net devices, this helper - * provides a high performance increase over **bpf_redirect**\ (). - * This is due to various implementation details of the underlying - * mechanisms, one of which is the fact that **bpf_redirect_map**\ - * () tries to send packet as a "bulk" to the device. + * See also bpf_redirect(), which only supports redirecting to an + * ifindex, but doesn't require a map to do so. * Return - * **XDP_REDIRECT** on success, or **XDP_ABORTED** on error. + * **XDP_REDIRECT** on success, or the value of the two lower bits + * of the **flags* argument on error. * * int bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags) * Description diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h index 2df8ceca1f9b8479ff0537d421baec643a7de2cc..6622912c2342edc0acf9a55f8a1affa2f12a4763 100644 --- a/include/uapi/linux/dm-ioctl.h +++ b/include/uapi/linux/dm-ioctl.h @@ -272,9 +272,9 @@ enum { #define DM_DEV_SET_GEOMETRY _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl) #define DM_VERSION_MAJOR 4 -#define DM_VERSION_MINOR 41 +#define DM_VERSION_MINOR 42 #define DM_VERSION_PATCHLEVEL 0 -#define DM_VERSION_EXTRA "-ioctl (2019-09-16)" +#define DM_VERSION_EXTRA "-ioctl (2020-02-27)" /* Status bits */ #define DM_READONLY_FLAG (1 << 0) /* In/Out */ diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index 1521073b634800f5ee1c01e08ff86742dab0d2f5..8533bf07450f0b483678a125e272af4c6505d9dc 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -74,6 +74,8 @@ enum { #define IPPROTO_UDPLITE IPPROTO_UDPLITE IPPROTO_MPLS = 137, /* MPLS in IP (RFC 4023) */ #define IPPROTO_MPLS IPPROTO_MPLS + IPPROTO_ETHERNET = 143, /* Ethernet-within-IPv6 Encapsulation */ +#define IPPROTO_ETHERNET IPPROTO_ETHERNET IPPROTO_RAW = 255, /* Raw IP packets */ #define IPPROTO_RAW IPPROTO_RAW IPPROTO_MPTCP = 262, /* Multipath TCP connection */ diff --git a/include/uapi/linux/netfilter/nf_conntrack_common.h b/include/uapi/linux/netfilter/nf_conntrack_common.h index 336014bf8868c3f04b92cdbf31bdf2ccafc68a71..b6f0bb1dc7998e67add1a97a62b69a07f68147e2 100644 --- a/include/uapi/linux/netfilter/nf_conntrack_common.h +++ b/include/uapi/linux/netfilter/nf_conntrack_common.h @@ -97,6 +97,15 @@ enum ip_conntrack_status { IPS_UNTRACKED_BIT = 12, IPS_UNTRACKED = (1 << IPS_UNTRACKED_BIT), +#ifdef __KERNEL__ + /* Re-purposed for in-kernel use: + * Tags a conntrack entry that clashed with an existing entry + * on insert. + */ + IPS_NAT_CLASH_BIT = IPS_UNTRACKED_BIT, + IPS_NAT_CLASH = IPS_UNTRACKED, +#endif + /* Conntrack got a helper explicitly attached via CT target. */ IPS_HELPER_BIT = 13, IPS_HELPER = (1 << IPS_HELPER_BIT), @@ -110,7 +119,8 @@ enum ip_conntrack_status { */ IPS_UNCHANGEABLE_MASK = (IPS_NAT_DONE_MASK | IPS_NAT_MASK | IPS_EXPECTED | IPS_CONFIRMED | IPS_DYING | - IPS_SEQ_ADJUST | IPS_TEMPLATE | IPS_OFFLOAD), + IPS_SEQ_ADJUST | IPS_TEMPLATE | IPS_UNTRACKED | + IPS_OFFLOAD), __IPS_MAX_BIT = 15, }; diff --git a/include/uapi/linux/swab.h b/include/uapi/linux/swab.h index fa7f97da5b7687125c5ca5eb1527419639a1b8e8..7272f85d6d6ab5e24dd806e7f88760eaafcd7326 100644 --- a/include/uapi/linux/swab.h +++ b/include/uapi/linux/swab.h @@ -135,9 +135,9 @@ static inline __attribute_const__ __u32 __fswahb32(__u32 val) static __always_inline unsigned long __swab(const unsigned long y) { -#if BITS_PER_LONG == 64 +#if __BITS_PER_LONG == 64 return __swab64(y); -#else /* BITS_PER_LONG == 32 */ +#else /* __BITS_PER_LONG == 32 */ return __swab32(y); #endif } diff --git a/include/uapi/linux/time.h b/include/uapi/linux/time.h index a655aa28dc6efcbf0da9a845bc1cbd09e47545e3..4f4b6e48e01c426560483c6c4277228334cbfddf 100644 --- a/include/uapi/linux/time.h +++ b/include/uapi/linux/time.h @@ -5,6 +5,7 @@ #include #include +#ifndef __KERNEL__ #ifndef _STRUCT_TIMESPEC #define _STRUCT_TIMESPEC struct timespec { @@ -18,6 +19,17 @@ struct timeval { __kernel_suseconds_t tv_usec; /* microseconds */ }; +struct itimerspec { + struct timespec it_interval;/* timer period */ + struct timespec it_value; /* timer expiration */ +}; + +struct itimerval { + struct timeval it_interval;/* timer interval */ + struct timeval it_value; /* current value */ +}; +#endif + struct timezone { int tz_minuteswest; /* minutes west of Greenwich */ int tz_dsttime; /* type of dst correction */ @@ -31,16 +43,6 @@ struct timezone { #define ITIMER_VIRTUAL 1 #define ITIMER_PROF 2 -struct itimerspec { - struct timespec it_interval; /* timer period */ - struct timespec it_value; /* timer expiration */ -}; - -struct itimerval { - struct timeval it_interval; /* timer interval */ - struct timeval it_value; /* current value */ -}; - /* * The IDs of the various system clocks (for POSIX.1b interval timers): */ diff --git a/include/uapi/linux/usb/charger.h b/include/uapi/linux/usb/charger.h index 5f72af35b3ed768fd3bc1e2d8ca3f4f6ecaea47f..ad22079125bff2ba34f03b74e6cfd5e2eb460479 100644 --- a/include/uapi/linux/usb/charger.h +++ b/include/uapi/linux/usb/charger.h @@ -14,18 +14,18 @@ * ACA (Accessory Charger Adapters) */ enum usb_charger_type { - UNKNOWN_TYPE, - SDP_TYPE, - DCP_TYPE, - CDP_TYPE, - ACA_TYPE, + UNKNOWN_TYPE = 0, + SDP_TYPE = 1, + DCP_TYPE = 2, + CDP_TYPE = 3, + ACA_TYPE = 4, }; /* USB charger state */ enum usb_charger_state { - USB_CHARGER_DEFAULT, - USB_CHARGER_PRESENT, - USB_CHARGER_ABSENT, + USB_CHARGER_DEFAULT = 0, + USB_CHARGER_PRESENT = 1, + USB_CHARGER_ABSENT = 2, }; #endif /* _UAPI__LINUX_USB_CHARGER_H */ diff --git a/include/xen/interface/io/tpmif.h b/include/xen/interface/io/tpmif.h index 28e7dcd75e829a3b45b44d66a0f07526f30a1283..f8aa8bac5196b4cf36e0d45fa05f52cc209adf3b 100644 --- a/include/xen/interface/io/tpmif.h +++ b/include/xen/interface/io/tpmif.h @@ -46,7 +46,7 @@ struct vtpm_shared_page { uint8_t pad; uint8_t nr_extra_pages; /* extra pages for long packets; may be zero */ - uint32_t extra_pages[0]; /* grant IDs; length in nr_extra_pages */ + uint32_t extra_pages[]; /* grant IDs; length in nr_extra_pages */ }; #endif diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h index 89a889585ba0148c5bd3854583694f82e7ed99f1..850a43bd69d32b8da48162b5430e2ff2b50673ef 100644 --- a/include/xen/xenbus.h +++ b/include/xen/xenbus.h @@ -42,6 +42,7 @@ #include #include #include +#include #include #include #include @@ -76,7 +77,7 @@ struct xenbus_device { enum xenbus_state state; struct completion down; struct work_struct work; - spinlock_t reclaim_lock; + struct semaphore reclaim_sem; }; static inline struct xenbus_device *to_xenbus_device(struct device *dev) diff --git a/init/Kconfig b/init/Kconfig index cfee56c151f14fe390a5d4780b840313526c04bb..4f717bfdbfe2d1e15fa65ef5357b4fd20bdd70f5 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -767,8 +767,7 @@ config ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH bool config CC_HAS_INT128 - def_bool y - depends on !$(cc-option,-D__SIZEOF_INT128__=0) + def_bool !$(cc-option,$(m64-flag) -D__SIZEOF_INT128__=0) && 64BIT # # For architectures that know their GCC __int128 support is sound @@ -1226,14 +1225,12 @@ endif config BOOT_CONFIG bool "Boot config support" - depends on BLK_DEV_INITRD - select LIBXBC - default y + select BLK_DEV_INITRD help Extra boot config allows system admin to pass a config file as complemental extension of kernel cmdline when booting. The boot config file must be attached at the end of initramfs - with checksum and size. + with checksum, size and magic word. See for details. If unsure, say Y. diff --git a/init/main.c b/init/main.c index cc0ee4873419ce36558a3ec8d2561f78d6407e1c..ee4947af823f3bb81ce5502781d24c4de6d3eb7f 100644 --- a/init/main.c +++ b/init/main.c @@ -142,6 +142,15 @@ static char *extra_command_line; /* Extra init arguments */ static char *extra_init_args; +#ifdef CONFIG_BOOT_CONFIG +/* Is bootconfig on command line? */ +static bool bootconfig_found; +static bool initargs_found; +#else +# define bootconfig_found false +# define initargs_found false +#endif + static char *execute_command; static char *ramdisk_execute_command; @@ -259,7 +268,6 @@ static int __init xbc_snprint_cmdline(char *buf, size_t size, { struct xbc_node *knode, *vnode; char *end = buf + size; - char c = '\"'; const char *val; int ret; @@ -270,25 +278,20 @@ static int __init xbc_snprint_cmdline(char *buf, size_t size, return ret; vnode = xbc_node_get_child(knode); - ret = snprintf(buf, rest(buf, end), "%s%c", xbc_namebuf, - vnode ? '=' : ' '); - if (ret < 0) - return ret; - buf += ret; - if (!vnode) + if (!vnode) { + ret = snprintf(buf, rest(buf, end), "%s ", xbc_namebuf); + if (ret < 0) + return ret; + buf += ret; continue; - - c = '\"'; + } xbc_array_for_each_value(vnode, val) { - ret = snprintf(buf, rest(buf, end), "%c%s", c, val); + ret = snprintf(buf, rest(buf, end), "%s=\"%s\" ", + xbc_namebuf, val); if (ret < 0) return ret; buf += ret; - c = ','; } - if (rest(buf, end) > 2) - strcpy(buf, "\" "); - buf += 2; } return buf - (end - size); @@ -326,7 +329,7 @@ static char * __init xbc_make_cmdline(const char *key) return new_cmdline; } -u32 boot_config_checksum(unsigned char *p, u32 size) +static u32 boot_config_checksum(unsigned char *p, u32 size) { u32 ret = 0; @@ -336,23 +339,40 @@ u32 boot_config_checksum(unsigned char *p, u32 size) return ret; } +static int __init bootconfig_params(char *param, char *val, + const char *unused, void *arg) +{ + if (strcmp(param, "bootconfig") == 0) { + bootconfig_found = true; + } else if (strcmp(param, "--") == 0) { + initargs_found = true; + } + return 0; +} + static void __init setup_boot_config(const char *cmdline) { + static char tmp_cmdline[COMMAND_LINE_SIZE] __initdata; u32 size, csum; char *data, *copy; - const char *p; u32 *hdr; int ret; - p = strstr(cmdline, "bootconfig"); - if (!p || (p != cmdline && !isspace(*(p-1))) || - (p[10] && !isspace(p[10]))) + strlcpy(tmp_cmdline, boot_command_line, COMMAND_LINE_SIZE); + parse_args("bootconfig", tmp_cmdline, NULL, 0, 0, 0, NULL, + bootconfig_params); + + if (!bootconfig_found) return; if (!initrd_end) goto not_found; - hdr = (u32 *)(initrd_end - 8); + data = (char *)initrd_end - BOOTCONFIG_MAGIC_LEN; + if (memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN)) + goto not_found; + + hdr = (u32 *)(data - 8); size = hdr[0]; csum = hdr[1]; @@ -396,6 +416,14 @@ static void __init setup_boot_config(const char *cmdline) } #else #define setup_boot_config(cmdline) do { } while (0) + +static int __init warn_bootconfig(char *str) +{ + pr_warn("WARNING: 'bootconfig' found on the kernel command line but CONFIG_BOOTCONFIG is not set.\n"); + return 0; +} +early_param("bootconfig", warn_bootconfig); + #endif /* Change NUL term back to "=", to make "param" the whole string. */ @@ -562,11 +590,12 @@ static void __init setup_command_line(char *command_line) * to init. */ len = strlen(saved_command_line); - if (!strstr(boot_command_line, " -- ")) { + if (initargs_found) { + saved_command_line[len++] = ' '; + } else { strcpy(saved_command_line + len, " -- "); len += 4; - } else - saved_command_line[len++] = ' '; + } strcpy(saved_command_line + len, extra_init_args); } diff --git a/ipc/sem.c b/ipc/sem.c index 4f4303f320776cfb0b7f8de192d9f43e72a34087..3687b71151b3921860613dcc7089fa2831f6237e 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -2384,11 +2384,9 @@ void exit_sem(struct task_struct *tsk) ipc_assert_locked_object(&sma->sem_perm); list_del(&un->list_id); - /* we are the last process using this ulp, acquiring ulp->lock - * isn't required. Besides that, we are also protected against - * IPC_RMID as we hold sma->sem_perm lock now - */ + spin_lock(&ulp->lock); list_del_rcu(&un->list_proc); + spin_unlock(&ulp->lock); /* perform adjustments registered in un */ for (i = 0; i < sma->sem_nsems; i++) { diff --git a/kernel/audit.c b/kernel/audit.c index 17b0d523afb35cea50ee0ea8c5063c08b4cd209e..9ddfe2aa6671ff3d6558ee86c97cb64c5a9b3189 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1101,13 +1101,11 @@ static void audit_log_feature_change(int which, u32 old_feature, u32 new_feature audit_log_end(ab); } -static int audit_set_feature(struct sk_buff *skb) +static int audit_set_feature(struct audit_features *uaf) { - struct audit_features *uaf; int i; BUILD_BUG_ON(AUDIT_LAST_FEATURE + 1 > ARRAY_SIZE(audit_feature_names)); - uaf = nlmsg_data(nlmsg_hdr(skb)); /* if there is ever a version 2 we should handle that here */ @@ -1175,6 +1173,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) { u32 seq; void *data; + int data_len; int err; struct audit_buffer *ab; u16 msg_type = nlh->nlmsg_type; @@ -1188,6 +1187,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) seq = nlh->nlmsg_seq; data = nlmsg_data(nlh); + data_len = nlmsg_len(nlh); switch (msg_type) { case AUDIT_GET: { @@ -1211,7 +1211,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) struct audit_status s; memset(&s, 0, sizeof(s)); /* guard against past and future API changes */ - memcpy(&s, data, min_t(size_t, sizeof(s), nlmsg_len(nlh))); + memcpy(&s, data, min_t(size_t, sizeof(s), data_len)); if (s.mask & AUDIT_STATUS_ENABLED) { err = audit_set_enabled(s.enabled); if (err < 0) @@ -1315,7 +1315,9 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) return err; break; case AUDIT_SET_FEATURE: - err = audit_set_feature(skb); + if (data_len < sizeof(struct audit_features)) + return -EINVAL; + err = audit_set_feature(data); if (err) return err; break; @@ -1327,6 +1329,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) err = audit_filter(msg_type, AUDIT_FILTER_USER); if (err == 1) { /* match or error */ + char *str = data; + err = 0; if (msg_type == AUDIT_USER_TTY) { err = tty_audit_push(); @@ -1334,26 +1338,24 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) break; } audit_log_user_recv_msg(&ab, msg_type); - if (msg_type != AUDIT_USER_TTY) + if (msg_type != AUDIT_USER_TTY) { + /* ensure NULL termination */ + str[data_len - 1] = '\0'; audit_log_format(ab, " msg='%.*s'", AUDIT_MESSAGE_TEXT_MAX, - (char *)data); - else { - int size; - + str); + } else { audit_log_format(ab, " data="); - size = nlmsg_len(nlh); - if (size > 0 && - ((unsigned char *)data)[size - 1] == '\0') - size--; - audit_log_n_untrustedstring(ab, data, size); + if (data_len > 0 && str[data_len - 1] == '\0') + data_len--; + audit_log_n_untrustedstring(ab, str, data_len); } audit_log_end(ab); } break; case AUDIT_ADD_RULE: case AUDIT_DEL_RULE: - if (nlmsg_len(nlh) < sizeof(struct audit_rule_data)) + if (data_len < sizeof(struct audit_rule_data)) return -EINVAL; if (audit_enabled == AUDIT_LOCKED) { audit_log_common_recv_msg(audit_context(), &ab, @@ -1365,7 +1367,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) audit_log_end(ab); return -EPERM; } - err = audit_rule_change(msg_type, seq, data, nlmsg_len(nlh)); + err = audit_rule_change(msg_type, seq, data, data_len); break; case AUDIT_LIST_RULES: err = audit_list_rules_send(skb, seq); @@ -1380,7 +1382,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) case AUDIT_MAKE_EQUIV: { void *bufp = data; u32 sizes[2]; - size_t msglen = nlmsg_len(nlh); + size_t msglen = data_len; char *old, *new; err = -EINVAL; @@ -1456,7 +1458,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) memset(&s, 0, sizeof(s)); /* guard against past and future API changes */ - memcpy(&s, data, min_t(size_t, sizeof(s), nlmsg_len(nlh))); + memcpy(&s, data, min_t(size_t, sizeof(s), data_len)); /* check if new data is valid */ if ((s.enabled != 0 && s.enabled != 1) || (s.log_passwd != 0 && s.log_passwd != 1)) diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index b0126e9c0743e8d8adf07bc12404c852b2eab29b..026e34da4ace994e75408990b564d52e25352eea 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -456,6 +456,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, bufp = data->buf; for (i = 0; i < data->field_count; i++) { struct audit_field *f = &entry->rule.fields[i]; + u32 f_val; err = -EINVAL; @@ -464,12 +465,12 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, goto exit_free; f->type = data->fields[i]; - f->val = data->values[i]; + f_val = data->values[i]; /* Support legacy tests for a valid loginuid */ - if ((f->type == AUDIT_LOGINUID) && (f->val == AUDIT_UID_UNSET)) { + if ((f->type == AUDIT_LOGINUID) && (f_val == AUDIT_UID_UNSET)) { f->type = AUDIT_LOGINUID_SET; - f->val = 0; + f_val = 0; entry->rule.pflags |= AUDIT_LOGINUID_LEGACY; } @@ -485,7 +486,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, case AUDIT_SUID: case AUDIT_FSUID: case AUDIT_OBJ_UID: - f->uid = make_kuid(current_user_ns(), f->val); + f->uid = make_kuid(current_user_ns(), f_val); if (!uid_valid(f->uid)) goto exit_free; break; @@ -494,11 +495,12 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, case AUDIT_SGID: case AUDIT_FSGID: case AUDIT_OBJ_GID: - f->gid = make_kgid(current_user_ns(), f->val); + f->gid = make_kgid(current_user_ns(), f_val); if (!gid_valid(f->gid)) goto exit_free; break; case AUDIT_ARCH: + f->val = f_val; entry->rule.arch_f = f; break; case AUDIT_SUBJ_USER: @@ -511,11 +513,13 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: - str = audit_unpack_string(&bufp, &remain, f->val); - if (IS_ERR(str)) + str = audit_unpack_string(&bufp, &remain, f_val); + if (IS_ERR(str)) { + err = PTR_ERR(str); goto exit_free; - entry->rule.buflen += f->val; - + } + entry->rule.buflen += f_val; + f->lsm_str = str; err = security_audit_rule_init(f->type, f->op, str, (void **)&f->lsm_rule); /* Keep currently invalid fields around in case they @@ -524,68 +528,71 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, pr_warn("audit rule for LSM \'%s\' is invalid\n", str); err = 0; - } - if (err) { - kfree(str); + } else if (err) goto exit_free; - } else - f->lsm_str = str; break; case AUDIT_WATCH: - str = audit_unpack_string(&bufp, &remain, f->val); - if (IS_ERR(str)) + str = audit_unpack_string(&bufp, &remain, f_val); + if (IS_ERR(str)) { + err = PTR_ERR(str); goto exit_free; - entry->rule.buflen += f->val; - - err = audit_to_watch(&entry->rule, str, f->val, f->op); + } + err = audit_to_watch(&entry->rule, str, f_val, f->op); if (err) { kfree(str); goto exit_free; } + entry->rule.buflen += f_val; break; case AUDIT_DIR: - str = audit_unpack_string(&bufp, &remain, f->val); - if (IS_ERR(str)) + str = audit_unpack_string(&bufp, &remain, f_val); + if (IS_ERR(str)) { + err = PTR_ERR(str); goto exit_free; - entry->rule.buflen += f->val; - + } err = audit_make_tree(&entry->rule, str, f->op); kfree(str); if (err) goto exit_free; + entry->rule.buflen += f_val; break; case AUDIT_INODE: + f->val = f_val; err = audit_to_inode(&entry->rule, f); if (err) goto exit_free; break; case AUDIT_FILTERKEY: - if (entry->rule.filterkey || f->val > AUDIT_MAX_KEY_LEN) + if (entry->rule.filterkey || f_val > AUDIT_MAX_KEY_LEN) goto exit_free; - str = audit_unpack_string(&bufp, &remain, f->val); - if (IS_ERR(str)) + str = audit_unpack_string(&bufp, &remain, f_val); + if (IS_ERR(str)) { + err = PTR_ERR(str); goto exit_free; - entry->rule.buflen += f->val; + } + entry->rule.buflen += f_val; entry->rule.filterkey = str; break; case AUDIT_EXE: - if (entry->rule.exe || f->val > PATH_MAX) + if (entry->rule.exe || f_val > PATH_MAX) goto exit_free; - str = audit_unpack_string(&bufp, &remain, f->val); + str = audit_unpack_string(&bufp, &remain, f_val); if (IS_ERR(str)) { err = PTR_ERR(str); goto exit_free; } - entry->rule.buflen += f->val; - - audit_mark = audit_alloc_mark(&entry->rule, str, f->val); + audit_mark = audit_alloc_mark(&entry->rule, str, f_val); if (IS_ERR(audit_mark)) { kfree(str); err = PTR_ERR(audit_mark); goto exit_free; } + entry->rule.buflen += f_val; entry->rule.exe = audit_mark; break; + default: + f->val = f_val; + break; } } diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 805c43b083e956940b990cede2b3cad0f0e3692a..787140095e58d5d0882a50b32ad30d64dcb89a75 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -4142,9 +4142,9 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, * EFAULT - verifier bug * 0 - 99% match. The last 1% is validated by the verifier. */ -int btf_check_func_type_match(struct bpf_verifier_log *log, - struct btf *btf1, const struct btf_type *t1, - struct btf *btf2, const struct btf_type *t2) +static int btf_check_func_type_match(struct bpf_verifier_log *log, + struct btf *btf1, const struct btf_type *t1, + struct btf *btf2, const struct btf_type *t2) { const struct btf_param *args1, *args2; const char *fn1, *fn2, *s1, *s2; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 2d182c4ee9d9964a6ec55ea102a5de9c7b6fc811..a1468e3f5af24e33acbfaa392db9770cea249668 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -56,6 +56,7 @@ struct htab_elem { union { struct bpf_htab *htab; struct pcpu_freelist_node fnode; + struct htab_elem *batch_flink; }; }; }; @@ -126,6 +127,17 @@ static void htab_free_elems(struct bpf_htab *htab) bpf_map_area_free(htab->elems); } +/* The LRU list has a lock (lru_lock). Each htab bucket has a lock + * (bucket_lock). If both locks need to be acquired together, the lock + * order is always lru_lock -> bucket_lock and this only happens in + * bpf_lru_list.c logic. For example, certain code path of + * bpf_lru_pop_free(), which is called by function prealloc_lru_pop(), + * will acquire lru_lock first followed by acquiring bucket_lock. + * + * In hashtab.c, to avoid deadlock, lock acquisition of + * bucket_lock followed by lru_lock is not allowed. In such cases, + * bucket_lock needs to be released first before acquiring lru_lock. + */ static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key, u32 hash) { @@ -1256,10 +1268,12 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map, void __user *ukeys = u64_to_user_ptr(attr->batch.keys); void *ubatch = u64_to_user_ptr(attr->batch.in_batch); u32 batch, max_count, size, bucket_size; + struct htab_elem *node_to_free = NULL; u64 elem_map_flags, map_flags; struct hlist_nulls_head *head; struct hlist_nulls_node *n; - unsigned long flags; + unsigned long flags = 0; + bool locked = false; struct htab_elem *l; struct bucket *b; int ret = 0; @@ -1319,15 +1333,25 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map, dst_val = values; b = &htab->buckets[batch]; head = &b->head; - raw_spin_lock_irqsave(&b->lock, flags); + /* do not grab the lock unless need it (bucket_cnt > 0). */ + if (locked) + raw_spin_lock_irqsave(&b->lock, flags); bucket_cnt = 0; hlist_nulls_for_each_entry_rcu(l, n, head, hash_node) bucket_cnt++; + if (bucket_cnt && !locked) { + locked = true; + goto again_nocopy; + } + if (bucket_cnt > (max_count - total)) { if (total == 0) ret = -ENOSPC; + /* Note that since bucket_cnt > 0 here, it is implicit + * that the locked was grabbed, so release it. + */ raw_spin_unlock_irqrestore(&b->lock, flags); rcu_read_unlock(); this_cpu_dec(bpf_prog_active); @@ -1337,6 +1361,9 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map, if (bucket_cnt > bucket_size) { bucket_size = bucket_cnt; + /* Note that since bucket_cnt > 0 here, it is implicit + * that the locked was grabbed, so release it. + */ raw_spin_unlock_irqrestore(&b->lock, flags); rcu_read_unlock(); this_cpu_dec(bpf_prog_active); @@ -1346,6 +1373,10 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map, goto alloc; } + /* Next block is only safe to run if you have grabbed the lock */ + if (!locked) + goto next_batch; + hlist_nulls_for_each_entry_safe(l, n, head, hash_node) { memcpy(dst_key, l->key, key_size); @@ -1370,16 +1401,33 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map, } if (do_delete) { hlist_nulls_del_rcu(&l->hash_node); - if (is_lru_map) - bpf_lru_push_free(&htab->lru, &l->lru_node); - else + + /* bpf_lru_push_free() will acquire lru_lock, which + * may cause deadlock. See comments in function + * prealloc_lru_pop(). Let us do bpf_lru_push_free() + * after releasing the bucket lock. + */ + if (is_lru_map) { + l->batch_flink = node_to_free; + node_to_free = l; + } else { free_htab_elem(htab, l); + } } dst_key += key_size; dst_val += value_size; } raw_spin_unlock_irqrestore(&b->lock, flags); + locked = false; + + while (node_to_free) { + l = node_to_free; + node_to_free = node_to_free->batch_flink; + bpf_lru_push_free(&htab->lru, &l->lru_node); + } + +next_batch: /* If we are not copying data, we can go to next bucket and avoid * unlocking the rcu. */ diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index 2c5dc6541eceed031acd4b0953d29b8f2a48870a..bd09290e364844a35a3c80bc56a63037356c9966 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -321,7 +321,7 @@ int bpf_prog_offload_info_fill(struct bpf_prog_info *info, ulen = info->jited_prog_len; info->jited_prog_len = aux->offload->jited_len; - if (info->jited_prog_len & ulen) { + if (info->jited_prog_len && ulen) { uinsns = u64_to_user_ptr(info->jited_prog_insns); ulen = min_t(u32, info->jited_prog_len, ulen); if (copy_to_user(uinsns, aux->offload->jited_image, ulen)) { diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index be1a1c83cdd1808a16d695ef42370cd667fd5aed..f2d7cea86ffe187788c9247834fe8bcc90f8fc8b 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -471,6 +471,7 @@ static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos) */ p++; if (p >= end) { + (*pos)++; return NULL; } else { *pos = *p; @@ -782,7 +783,7 @@ void cgroup1_release_agent(struct work_struct *work) pathbuf = kmalloc(PATH_MAX, GFP_KERNEL); agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL); - if (!pathbuf || !agentbuf) + if (!pathbuf || !agentbuf || !strlen(agentbuf)) goto out; spin_lock_irq(&css_set_lock); diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index db552b9f9377991c3e8a59f3c8c757364eaf45ca..3dead0416b9164f91113f28d921dd8dc5390f3f6 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3542,21 +3542,21 @@ static int cpu_stat_show(struct seq_file *seq, void *v) static int cgroup_io_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; - struct psi_group *psi = cgroup_id(cgrp) == 1 ? &psi_system : &cgrp->psi; + struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : &cgrp->psi; return psi_show(seq, psi, PSI_IO); } static int cgroup_memory_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; - struct psi_group *psi = cgroup_id(cgrp) == 1 ? &psi_system : &cgrp->psi; + struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : &cgrp->psi; return psi_show(seq, psi, PSI_MEM); } static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; - struct psi_group *psi = cgroup_id(cgrp) == 1 ? &psi_system : &cgrp->psi; + struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : &cgrp->psi; return psi_show(seq, psi, PSI_CPU); } @@ -4400,12 +4400,16 @@ static void css_task_iter_advance_css_set(struct css_task_iter *it) } } while (!css_set_populated(cset) && list_empty(&cset->dying_tasks)); - if (!list_empty(&cset->tasks)) + if (!list_empty(&cset->tasks)) { it->task_pos = cset->tasks.next; - else if (!list_empty(&cset->mg_tasks)) + it->cur_tasks_head = &cset->tasks; + } else if (!list_empty(&cset->mg_tasks)) { it->task_pos = cset->mg_tasks.next; - else + it->cur_tasks_head = &cset->mg_tasks; + } else { it->task_pos = cset->dying_tasks.next; + it->cur_tasks_head = &cset->dying_tasks; + } it->tasks_head = &cset->tasks; it->mg_tasks_head = &cset->mg_tasks; @@ -4463,10 +4467,14 @@ static void css_task_iter_advance(struct css_task_iter *it) else it->task_pos = it->task_pos->next; - if (it->task_pos == it->tasks_head) + if (it->task_pos == it->tasks_head) { it->task_pos = it->mg_tasks_head->next; - if (it->task_pos == it->mg_tasks_head) + it->cur_tasks_head = it->mg_tasks_head; + } + if (it->task_pos == it->mg_tasks_head) { it->task_pos = it->dying_tasks_head->next; + it->cur_tasks_head = it->dying_tasks_head; + } if (it->task_pos == it->dying_tasks_head) css_task_iter_advance_css_set(it); } else { @@ -4485,11 +4493,12 @@ static void css_task_iter_advance(struct css_task_iter *it) goto repeat; /* and dying leaders w/o live member threads */ - if (!atomic_read(&task->signal->live)) + if (it->cur_tasks_head == it->dying_tasks_head && + !atomic_read(&task->signal->live)) goto repeat; } else { /* skip all dying ones */ - if (task->flags & PF_EXITING) + if (it->cur_tasks_head == it->dying_tasks_head) goto repeat; } } @@ -4595,6 +4604,9 @@ static void *cgroup_procs_next(struct seq_file *s, void *v, loff_t *pos) struct kernfs_open_file *of = s->private; struct css_task_iter *it = of->priv; + if (pos) + (*pos)++; + return css_task_iter_next(it); } @@ -4610,7 +4622,7 @@ static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos, * from position 0, so we can simply keep iterating on !0 *pos. */ if (!it) { - if (WARN_ON_ONCE((*pos)++)) + if (WARN_ON_ONCE((*pos))) return ERR_PTR(-EINVAL); it = kzalloc(sizeof(*it), GFP_KERNEL); @@ -4618,10 +4630,11 @@ static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos, return ERR_PTR(-ENOMEM); of->priv = it; css_task_iter_start(&cgrp->self, iter_flags, it); - } else if (!(*pos)++) { + } else if (!(*pos)) { css_task_iter_end(it); css_task_iter_start(&cgrp->self, iter_flags, it); - } + } else + return it->cur_task; return cgroup_procs_next(s, NULL, NULL); } @@ -5927,11 +5940,14 @@ void cgroup_post_fork(struct task_struct *child) spin_lock_irq(&css_set_lock); - WARN_ON_ONCE(!list_empty(&child->cg_list)); - cset = task_css_set(current); /* current is @child's parent */ - get_css_set(cset); - cset->nr_tasks++; - css_set_move_task(child, NULL, cset, false); + /* init tasks are special, only link regular threads */ + if (likely(child->pid)) { + WARN_ON_ONCE(!list_empty(&child->cg_list)); + cset = task_css_set(current); /* current is @child's parent */ + get_css_set(cset); + cset->nr_tasks++; + css_set_move_task(child, NULL, cset, false); + } /* * If the cgroup has to be frozen, the new task has too. Let's set @@ -6255,6 +6271,10 @@ void cgroup_sk_alloc(struct sock_cgroup_data *skcd) return; } + /* Don't associate the sock with unrelated interrupted task's cgroup. */ + if (in_interrupt()) + return; + rcu_read_lock(); while (true) { diff --git a/kernel/compat.c b/kernel/compat.c index 95005f849c68f372e0e9b92d7926ea711d5600fa..843dd17e6078b6d530ecc46260703b390f9abbe4 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -26,70 +26,6 @@ #include -static int __compat_get_timeval(struct timeval *tv, const struct old_timeval32 __user *ctv) -{ - return (!access_ok(ctv, sizeof(*ctv)) || - __get_user(tv->tv_sec, &ctv->tv_sec) || - __get_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0; -} - -static int __compat_put_timeval(const struct timeval *tv, struct old_timeval32 __user *ctv) -{ - return (!access_ok(ctv, sizeof(*ctv)) || - __put_user(tv->tv_sec, &ctv->tv_sec) || - __put_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0; -} - -static int __compat_get_timespec(struct timespec *ts, const struct old_timespec32 __user *cts) -{ - return (!access_ok(cts, sizeof(*cts)) || - __get_user(ts->tv_sec, &cts->tv_sec) || - __get_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0; -} - -static int __compat_put_timespec(const struct timespec *ts, struct old_timespec32 __user *cts) -{ - return (!access_ok(cts, sizeof(*cts)) || - __put_user(ts->tv_sec, &cts->tv_sec) || - __put_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0; -} - -int compat_get_timeval(struct timeval *tv, const void __user *utv) -{ - if (COMPAT_USE_64BIT_TIME) - return copy_from_user(tv, utv, sizeof(*tv)) ? -EFAULT : 0; - else - return __compat_get_timeval(tv, utv); -} -EXPORT_SYMBOL_GPL(compat_get_timeval); - -int compat_put_timeval(const struct timeval *tv, void __user *utv) -{ - if (COMPAT_USE_64BIT_TIME) - return copy_to_user(utv, tv, sizeof(*tv)) ? -EFAULT : 0; - else - return __compat_put_timeval(tv, utv); -} -EXPORT_SYMBOL_GPL(compat_put_timeval); - -int compat_get_timespec(struct timespec *ts, const void __user *uts) -{ - if (COMPAT_USE_64BIT_TIME) - return copy_from_user(ts, uts, sizeof(*ts)) ? -EFAULT : 0; - else - return __compat_get_timespec(ts, uts); -} -EXPORT_SYMBOL_GPL(compat_get_timespec); - -int compat_put_timespec(const struct timespec *ts, void __user *uts) -{ - if (COMPAT_USE_64BIT_TIME) - return copy_to_user(uts, ts, sizeof(*ts)) ? -EFAULT : 0; - else - return __compat_put_timespec(ts, uts); -} -EXPORT_SYMBOL_GPL(compat_put_timespec); - #ifdef __ARCH_WANT_SYS_SIGPROCMASK /* diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c index daa4e6eefdde86e898668b3c9ebdb55b2c6b59f3..8bc6f2d670f956f24f4786b7dafb1d49b69beb85 100644 --- a/kernel/dma/contiguous.c +++ b/kernel/dma/contiguous.c @@ -302,9 +302,16 @@ static int __init rmem_cma_setup(struct reserved_mem *rmem) phys_addr_t align = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order); phys_addr_t mask = align - 1; unsigned long node = rmem->fdt_node; + bool default_cma = of_get_flat_dt_prop(node, "linux,cma-default", NULL); struct cma *cma; int err; + if (size_cmdline != -1 && default_cma) { + pr_info("Reserved memory: bypass %s node, using cmdline CMA params instead\n", + rmem->name); + return -EBUSY; + } + if (!of_get_flat_dt_prop(node, "reusable", NULL) || of_get_flat_dt_prop(node, "no-map", NULL)) return -EINVAL; @@ -322,7 +329,7 @@ static int __init rmem_cma_setup(struct reserved_mem *rmem) /* Architecture specific contiguous memory fixup. */ dma_contiguous_early_fixup(rmem->base, rmem->size); - if (of_get_flat_dt_prop(node, "linux,cma-default", NULL)) + if (default_cma) dma_contiguous_set_default(cma); rmem->ops = &rmem_cma_ops; diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 6af7ae83c4ada1534bcf7dc203de907515e24fea..ac7956c38f693f2bc6346411ff2b097a003967dd 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -23,18 +23,6 @@ */ unsigned int zone_dma_bits __ro_after_init = 24; -static void report_addr(struct device *dev, dma_addr_t dma_addr, size_t size) -{ - if (!dev->dma_mask) { - dev_err_once(dev, "DMA map on device without dma_mask\n"); - } else if (*dev->dma_mask >= DMA_BIT_MASK(32) || dev->bus_dma_limit) { - dev_err_once(dev, - "overflow %pad+%zu of DMA mask %llx bus limit %llx\n", - &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit); - } - WARN_ON_ONCE(1); -} - static inline dma_addr_t phys_to_dma_direct(struct device *dev, phys_addr_t phys) { @@ -357,13 +345,6 @@ void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, EXPORT_SYMBOL(dma_direct_unmap_sg); #endif -static inline bool dma_direct_possible(struct device *dev, dma_addr_t dma_addr, - size_t size) -{ - return swiotlb_force != SWIOTLB_FORCE && - dma_capable(dev, dma_addr, size, true); -} - dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, unsigned long attrs) @@ -371,9 +352,16 @@ dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, phys_addr_t phys = page_to_phys(page) + offset; dma_addr_t dma_addr = phys_to_dma(dev, phys); - if (unlikely(!dma_direct_possible(dev, dma_addr, size)) && - !swiotlb_map(dev, &phys, &dma_addr, size, dir, attrs)) { - report_addr(dev, dma_addr, size); + if (unlikely(swiotlb_force == SWIOTLB_FORCE)) + return swiotlb_map(dev, phys, size, dir, attrs); + + if (unlikely(!dma_capable(dev, dma_addr, size, true))) { + if (swiotlb_force != SWIOTLB_NO_FORCE) + return swiotlb_map(dev, phys, size, dir, attrs); + + dev_WARN_ONCE(dev, 1, + "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n", + &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit); return DMA_MAPPING_ERROR; } @@ -411,7 +399,10 @@ dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr, dma_addr_t dma_addr = paddr; if (unlikely(!dma_capable(dev, dma_addr, size, false))) { - report_addr(dev, dma_addr, size); + dev_err_once(dev, + "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n", + &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit); + WARN_ON_ONCE(1); return DMA_MAPPING_ERROR; } @@ -472,28 +463,26 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma, } #endif /* CONFIG_MMU */ -/* - * Because 32-bit DMA masks are so common we expect every architecture to be - * able to satisfy them - either by not supporting more physical memory, or by - * providing a ZONE_DMA32. If neither is the case, the architecture needs to - * use an IOMMU instead of the direct mapping. - */ int dma_direct_supported(struct device *dev, u64 mask) { - u64 min_mask; + u64 min_mask = (max_pfn - 1) << PAGE_SHIFT; - if (IS_ENABLED(CONFIG_ZONE_DMA)) - min_mask = DMA_BIT_MASK(zone_dma_bits); - else - min_mask = DMA_BIT_MASK(32); - - min_mask = min_t(u64, min_mask, (max_pfn - 1) << PAGE_SHIFT); + /* + * Because 32-bit DMA masks are so common we expect every architecture + * to be able to satisfy them - either by not supporting more physical + * memory, or by providing a ZONE_DMA32. If neither is the case, the + * architecture needs to use an IOMMU instead of the direct mapping. + */ + if (mask >= DMA_BIT_MASK(32)) + return 1; /* * This check needs to be against the actual bit mask value, so * use __phys_to_dma() here so that the SME encryption mask isn't * part of the check. */ + if (IS_ENABLED(CONFIG_ZONE_DMA)) + min_mask = min_t(u64, min_mask, DMA_BIT_MASK(zone_dma_bits)); return mask >= __phys_to_dma(dev, min_mask); } diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 9280d6f8271ed4360bab41cfb2d8dc66d75ca203..c19379fabd200ebb13c5a134b4f366291751982b 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -22,6 +22,7 @@ #include #include +#include #include #include #include @@ -656,35 +657,38 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr, } /* - * Create a swiotlb mapping for the buffer at @phys, and in case of DMAing + * Create a swiotlb mapping for the buffer at @paddr, and in case of DMAing * to the device copy the data into it as well. */ -bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr, - size_t size, enum dma_data_direction dir, unsigned long attrs) +dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size, + enum dma_data_direction dir, unsigned long attrs) { - trace_swiotlb_bounced(dev, *dma_addr, size, swiotlb_force); + phys_addr_t swiotlb_addr; + dma_addr_t dma_addr; - if (unlikely(swiotlb_force == SWIOTLB_NO_FORCE)) { - dev_warn_ratelimited(dev, - "Cannot do DMA to address %pa\n", phys); - return false; - } + trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size, + swiotlb_force); - /* Oh well, have to allocate and map a bounce buffer. */ - *phys = swiotlb_tbl_map_single(dev, __phys_to_dma(dev, io_tlb_start), - *phys, size, size, dir, attrs); - if (*phys == (phys_addr_t)DMA_MAPPING_ERROR) - return false; + swiotlb_addr = swiotlb_tbl_map_single(dev, + __phys_to_dma(dev, io_tlb_start), + paddr, size, size, dir, attrs); + if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR) + return DMA_MAPPING_ERROR; /* Ensure that the address returned is DMA'ble */ - *dma_addr = __phys_to_dma(dev, *phys); - if (unlikely(!dma_capable(dev, *dma_addr, size, true))) { - swiotlb_tbl_unmap_single(dev, *phys, size, size, dir, + dma_addr = __phys_to_dma(dev, swiotlb_addr); + if (unlikely(!dma_capable(dev, dma_addr, size, true))) { + swiotlb_tbl_unmap_single(dev, swiotlb_addr, size, size, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC); - return false; + dev_WARN_ONCE(dev, 1, + "swiotlb addr %pad+%zu overflow (mask %llx, bus limit %llx).\n", + &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit); + return DMA_MAPPING_ERROR; } - return true; + if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + arch_sync_dma_for_device(swiotlb_addr, size, dir); + return dma_addr; } size_t swiotlb_max_mapping_size(struct device *dev) diff --git a/kernel/exit.c b/kernel/exit.c index 2833ffb0c2110c482010954e73ed836395eaa6a6..0b81b26a872a066fca5b6fbdd78404e9a2570d49 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -619,8 +619,8 @@ static void forget_original_parent(struct task_struct *father, reaper = find_new_reaper(father, reaper); list_for_each_entry(p, &father->children, sibling) { for_each_thread(p, t) { - t->real_parent = reaper; - BUG_ON((!t->ptrace) != (t->parent == father)); + RCU_INIT_POINTER(t->real_parent, reaper); + BUG_ON((!t->ptrace) != (rcu_access_pointer(t->parent) == father)); if (likely(!t->ptrace)) t->parent = t->real_parent; if (t->pdeath_signal) diff --git a/kernel/fork.c b/kernel/fork.c index 60a1295f4384363ae9b35e589c02e52fbf914a26..86425305cd4acc59b9d1c6a76a4c912d73ca2059 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1508,7 +1508,7 @@ static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk) return 0; } sig = kmem_cache_alloc(sighand_cachep, GFP_KERNEL); - rcu_assign_pointer(tsk->sighand, sig); + RCU_INIT_POINTER(tsk->sighand, sig); if (!sig) return -ENOMEM; diff --git a/kernel/futex.c b/kernel/futex.c index 0cf84c8664f207c574325b899ef2e57f01295a94..82dfacb3250ea997aa129cf53ffa4312200bd2be 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -385,9 +385,9 @@ static inline int hb_waiters_pending(struct futex_hash_bucket *hb) */ static struct futex_hash_bucket *hash_futex(union futex_key *key) { - u32 hash = jhash2((u32*)&key->both.word, - (sizeof(key->both.word)+sizeof(key->both.ptr))/4, + u32 hash = jhash2((u32 *)key, offsetof(typeof(*key), both.offset) / 4, key->both.offset); + return &futex_queues[hash & (futex_hashsize - 1)]; } @@ -429,7 +429,7 @@ static void get_futex_key_refs(union futex_key *key) switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) { case FUT_OFF_INODE: - ihold(key->shared.inode); /* implies smp_mb(); (B) */ + smp_mb(); /* explicit smp_mb(); (B) */ break; case FUT_OFF_MMSHARED: futex_get_mm(key); /* implies smp_mb(); (B) */ @@ -463,7 +463,6 @@ static void drop_futex_key_refs(union futex_key *key) switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) { case FUT_OFF_INODE: - iput(key->shared.inode); break; case FUT_OFF_MMSHARED: mmdrop(key->private.mm); @@ -505,6 +504,46 @@ futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout, return timeout; } +/* + * Generate a machine wide unique identifier for this inode. + * + * This relies on u64 not wrapping in the life-time of the machine; which with + * 1ns resolution means almost 585 years. + * + * This further relies on the fact that a well formed program will not unmap + * the file while it has a (shared) futex waiting on it. This mapping will have + * a file reference which pins the mount and inode. + * + * If for some reason an inode gets evicted and read back in again, it will get + * a new sequence number and will _NOT_ match, even though it is the exact same + * file. + * + * It is important that match_futex() will never have a false-positive, esp. + * for PI futexes that can mess up the state. The above argues that false-negatives + * are only possible for malformed programs. + */ +static u64 get_inode_sequence_number(struct inode *inode) +{ + static atomic64_t i_seq; + u64 old; + + /* Does the inode already have a sequence number? */ + old = atomic64_read(&inode->i_sequence); + if (likely(old)) + return old; + + for (;;) { + u64 new = atomic64_add_return(1, &i_seq); + if (WARN_ON_ONCE(!new)) + continue; + + old = atomic64_cmpxchg_relaxed(&inode->i_sequence, 0, new); + if (old) + return old; + return new; + } +} + /** * get_futex_key() - Get parameters which are the keys for a futex * @uaddr: virtual address of the futex @@ -517,9 +556,15 @@ futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout, * * The key words are stored in @key on success. * - * For shared mappings, it's (page->index, file_inode(vma->vm_file), - * offset_within_page). For private mappings, it's (uaddr, current->mm). - * We can usually work out the index without swapping in the page. + * For shared mappings (when @fshared), the key is: + * ( inode->i_sequence, page->index, offset_within_page ) + * [ also see get_inode_sequence_number() ] + * + * For private mappings (or when !@fshared), the key is: + * ( current->mm, address, 0 ) + * + * This allows (cross process, where applicable) identification of the futex + * without keeping the page pinned for the duration of the FUTEX_WAIT. * * lock_page() might sleep, the caller should not hold a spinlock. */ @@ -659,8 +704,6 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, enum futex_a key->private.mm = mm; key->private.address = address; - get_futex_key_refs(key); /* implies smp_mb(); (B) */ - } else { struct inode *inode; @@ -692,40 +735,14 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, enum futex_a goto again; } - /* - * Take a reference unless it is about to be freed. Previously - * this reference was taken by ihold under the page lock - * pinning the inode in place so i_lock was unnecessary. The - * only way for this check to fail is if the inode was - * truncated in parallel which is almost certainly an - * application bug. In such a case, just retry. - * - * We are not calling into get_futex_key_refs() in file-backed - * cases, therefore a successful atomic_inc return below will - * guarantee that get_futex_key() will still imply smp_mb(); (B). - */ - if (!atomic_inc_not_zero(&inode->i_count)) { - rcu_read_unlock(); - put_page(page); - - goto again; - } - - /* Should be impossible but lets be paranoid for now */ - if (WARN_ON_ONCE(inode->i_mapping != mapping)) { - err = -EFAULT; - rcu_read_unlock(); - iput(inode); - - goto out; - } - key->both.offset |= FUT_OFF_INODE; /* inode-based key */ - key->shared.inode = inode; + key->shared.i_seq = get_inode_sequence_number(inode); key->shared.pgoff = basepage_index(tail); rcu_read_unlock(); } + get_futex_key_refs(key); /* implies smp_mb(); (B) */ + out: put_page(page); return err; diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 3924fbe829d4a8aeaa32750580212b0f008d7f39..c9d8eb7f5c029244b4db5f68cae4463412064077 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -128,8 +128,6 @@ static inline void unregister_handler_proc(unsigned int irq, extern bool irq_can_set_affinity_usr(unsigned int irq); -extern int irq_select_affinity_usr(unsigned int irq); - extern void irq_set_thread_affinity(struct irq_desc *desc); extern int irq_do_set_affinity(struct irq_data *data, diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 3089a60ea8f98ffeb58c0d497d1172cc15718e1e..7eee98c38f25ca20047ed75c268fae4550949bdd 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -481,23 +481,9 @@ int irq_setup_affinity(struct irq_desc *desc) { return irq_select_affinity(irq_desc_get_irq(desc)); } -#endif +#endif /* CONFIG_AUTO_IRQ_AFFINITY */ +#endif /* CONFIG_SMP */ -/* - * Called when a bogus affinity is set via /proc/irq - */ -int irq_select_affinity_usr(unsigned int irq) -{ - struct irq_desc *desc = irq_to_desc(irq); - unsigned long flags; - int ret; - - raw_spin_lock_irqsave(&desc->lock, flags); - ret = irq_setup_affinity(desc); - raw_spin_unlock_irqrestore(&desc->lock, flags); - return ret; -} -#endif /** * irq_set_vcpu_affinity - Set vcpu affinity for the interrupt diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index 9e5783d98033ee183e389ca9efa3681e0b642743..32c071d7bc0338ac73253c586e04de7fc816a873 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -111,6 +111,28 @@ static int irq_affinity_list_proc_show(struct seq_file *m, void *v) return show_irq_affinity(AFFINITY_LIST, m); } +#ifndef CONFIG_AUTO_IRQ_AFFINITY +static inline int irq_select_affinity_usr(unsigned int irq) +{ + /* + * If the interrupt is started up already then this fails. The + * interrupt is assigned to an online CPU already. There is no + * point to move it around randomly. Tell user space that the + * selected mask is bogus. + * + * If not then any change to the affinity is pointless because the + * startup code invokes irq_setup_affinity() which will select + * a online CPU anyway. + */ + return -EINVAL; +} +#else +/* ALPHA magic affinity auto selector. Keep it for historical reasons. */ +static inline int irq_select_affinity_usr(unsigned int irq) +{ + return irq_select_affinity(irq); +} +#endif static ssize_t write_irq_affinity(int type, struct file *file, const char __user *buffer, size_t count, loff_t *pos) diff --git a/kernel/notifier.c b/kernel/notifier.c index 63d7501ac638b5f8424ce10482682564a81b6cb2..5989bbb93039e61da64a4b260c10b86f4e7349fd 100644 --- a/kernel/notifier.c +++ b/kernel/notifier.c @@ -519,7 +519,7 @@ NOKPROBE_SYMBOL(notify_die); int register_die_notifier(struct notifier_block *nb) { - vmalloc_sync_all(); + vmalloc_sync_mappings(); return atomic_notifier_chain_register(&die_chain, nb); } EXPORT_SYMBOL_GPL(register_die_notifier); diff --git a/kernel/pid.c b/kernel/pid.c index 0f4ecb57214cb840d9d1d866669865316fd4a380..647b4bb457b5945d16f217ab7ad785cd2b2f84d1 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -247,6 +247,16 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid, tmp = tmp->parent; } + /* + * ENOMEM is not the most obvious choice especially for the case + * where the child subreaper has already exited and the pid + * namespace denies the creation of any new processes. But ENOMEM + * is what we have exposed to userspace for a long time and it is + * documented behavior for pid namespaces. So we can't easily + * change it even if there were an error code better suited. + */ + retval = -ENOMEM; + if (unlikely(is_child_reaper(pid))) { if (pid_ns_prepare_proc(ns)) goto out_free; diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index ddade80ad27670c33f84bbbedd1328edf42a3ace..d82b7b88d616ee4ea792d6ec6340dd46f00a42ad 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1681,7 +1681,7 @@ static unsigned long minimum_image_size(unsigned long saveable) * hibernation for allocations made while saving the image and for device * drivers, in case they need to allocate memory from their hibernation * callbacks (these two numbers are given by PAGES_FOR_IO (which is a rough - * estimate) and reserverd_size divided by PAGE_SIZE (which is tunable through + * estimate) and reserved_size divided by PAGE_SIZE (which is tunable through * /sys/power/reserved_size, respectively). To make this happen, we compute the * total number of available page frames and allocate at least * diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 2c47280fbfc7a4a92f89769cf7e30c7cb60784e9..8b1bb5ee7e5d668992067daacf8c5af6bc73285f 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -131,11 +131,12 @@ static void s2idle_loop(void) * to avoid them upfront. */ for (;;) { - if (s2idle_ops && s2idle_ops->wake) - s2idle_ops->wake(); - - if (pm_wakeup_pending()) + if (s2idle_ops && s2idle_ops->wake) { + if (s2idle_ops->wake()) + break; + } else if (pm_wakeup_pending()) { break; + } pm_wakeup_clear(false); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index fc1dfc0076045dc2bfcb3f0bd9b60e1ec2e7ac09..1a9983da4408deb36315639228e84a0131a36e00 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -552,27 +552,32 @@ void resched_cpu(int cpu) */ int get_nohz_timer_target(void) { - int i, cpu = smp_processor_id(); + int i, cpu = smp_processor_id(), default_cpu = -1; struct sched_domain *sd; - if (!idle_cpu(cpu) && housekeeping_cpu(cpu, HK_FLAG_TIMER)) - return cpu; + if (housekeeping_cpu(cpu, HK_FLAG_TIMER)) { + if (!idle_cpu(cpu)) + return cpu; + default_cpu = cpu; + } rcu_read_lock(); for_each_domain(cpu, sd) { - for_each_cpu(i, sched_domain_span(sd)) { + for_each_cpu_and(i, sched_domain_span(sd), + housekeeping_cpumask(HK_FLAG_TIMER)) { if (cpu == i) continue; - if (!idle_cpu(i) && housekeeping_cpu(i, HK_FLAG_TIMER)) { + if (!idle_cpu(i)) { cpu = i; goto unlock; } } } - if (!housekeeping_cpu(cpu, HK_FLAG_TIMER)) - cpu = housekeeping_any_cpu(HK_FLAG_TIMER); + if (default_cpu == -1) + default_cpu = housekeeping_any_cpu(HK_FLAG_TIMER); + cpu = default_cpu; unlock: rcu_read_unlock(); return cpu; @@ -1442,17 +1447,6 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) #ifdef CONFIG_SMP -static inline bool is_per_cpu_kthread(struct task_struct *p) -{ - if (!(p->flags & PF_KTHREAD)) - return false; - - if (p->nr_cpus_allowed != 1) - return false; - - return true; -} - /* * Per-CPU kthreads are allowed to run on !active && online CPUs, see * __set_cpus_allowed_ptr() and select_fallback_rq(). @@ -3669,28 +3663,32 @@ static void sched_tick_remote(struct work_struct *work) * statistics and checks timeslices in a time-independent way, regardless * of when exactly it is running. */ - if (idle_cpu(cpu) || !tick_nohz_tick_stopped_cpu(cpu)) + if (!tick_nohz_tick_stopped_cpu(cpu)) goto out_requeue; rq_lock_irq(rq, &rf); curr = rq->curr; - if (is_idle_task(curr) || cpu_is_offline(cpu)) + if (cpu_is_offline(cpu)) goto out_unlock; + curr = rq->curr; update_rq_clock(rq); - delta = rq_clock_task(rq) - curr->se.exec_start; - /* - * Make sure the next tick runs within a reasonable - * amount of time. - */ - WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3); + if (!is_idle_task(curr)) { + /* + * Make sure the next tick runs within a reasonable + * amount of time. + */ + delta = rq_clock_task(rq) - curr->se.exec_start; + WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3); + } curr->sched_class->task_tick(rq, curr, 0); + calc_load_nohz_remote(rq); out_unlock: rq_unlock_irq(rq, &rf); - out_requeue: + /* * Run the remote tick once per second (1Hz). This arbitrary * frequency is large enough to avoid overload but short enough @@ -7063,8 +7061,15 @@ void sched_move_task(struct task_struct *tsk) if (queued) enqueue_task(rq, tsk, queue_flags); - if (running) + if (running) { set_next_task(rq, tsk); + /* + * After changing group, the running task may have joined a + * throttled one but it's still the running task. Trigger a + * resched to make sure that task can still run. + */ + resched_curr(rq); + } task_rq_unlock(rq, tsk, &rf); } @@ -7260,7 +7265,7 @@ capacity_from_percent(char *buf) &req.percent); if (req.ret) return req; - if (req.percent > UCLAMP_PERCENT_SCALE) { + if ((u64)req.percent > UCLAMP_PERCENT_SCALE) { req.ret = -ERANGE; return req; } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index fe4e0d775375680504d1bc2167996bb975f028a8..c1217bfe5e819083ba7bbfd99fd8e3453d34f4a7 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3516,7 +3516,6 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) * attach_entity_load_avg - attach this entity to its cfs_rq load avg * @cfs_rq: cfs_rq to attach to * @se: sched_entity to attach - * @flags: migration hints * * Must call update_cfs_rq_load_avg() before this, since we rely on * cfs_rq->avg.last_update_time being current. @@ -5912,6 +5911,20 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) (available_idle_cpu(prev) || sched_idle_cpu(prev))) return prev; + /* + * Allow a per-cpu kthread to stack with the wakee if the + * kworker thread and the tasks previous CPUs are the same. + * The assumption is that the wakee queued work for the + * per-cpu kthread that is now complete and the wakeup is + * essentially a sync wakeup. An obvious example of this + * pattern is IO completions. + */ + if (is_per_cpu_kthread(current) && + prev == smp_processor_id() && + this_rq()->nr_running <= 1) { + return prev; + } + /* Check a recently used CPU as a potential idle candidate: */ recent_used_cpu = p->recent_used_cpu; if (recent_used_cpu != prev && @@ -8324,6 +8337,8 @@ static inline void update_sg_wakeup_stats(struct sched_domain *sd, sgs->group_capacity = group->sgc->capacity; + sgs->group_weight = group->group_weight; + sgs->group_type = group_classify(sd->imbalance_pct, group, sgs); /* @@ -8658,10 +8673,6 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s /* * Try to use spare capacity of local group without overloading it or * emptying busiest. - * XXX Spreading tasks across NUMA nodes is not always the best policy - * and special care should be taken for SD_NUMA domain level before - * spreading the tasks. For now, load_balance() fully relies on - * NUMA_BALANCING and fbq_classify_group/rq to override the decision. */ if (local->group_type == group_has_spare) { if (busiest->group_type > group_fully_busy) { @@ -8701,16 +8712,37 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s env->migration_type = migrate_task; lsub_positive(&nr_diff, local->sum_nr_running); env->imbalance = nr_diff >> 1; - return; - } + } else { - /* - * If there is no overload, we just want to even the number of - * idle cpus. - */ - env->migration_type = migrate_task; - env->imbalance = max_t(long, 0, (local->idle_cpus - + /* + * If there is no overload, we just want to even the number of + * idle cpus. + */ + env->migration_type = migrate_task; + env->imbalance = max_t(long, 0, (local->idle_cpus - busiest->idle_cpus) >> 1); + } + + /* Consider allowing a small imbalance between NUMA groups */ + if (env->sd->flags & SD_NUMA) { + unsigned int imbalance_min; + + /* + * Compute an allowed imbalance based on a simple + * pair of communicating tasks that should remain + * local and ignore them. + * + * NOTE: Generally this would have been based on + * the domain size and this was evaluated. However, + * the benefit is similar across a range of workloads + * and machines but scaling by the domain size adds + * the risk that lower domains have to be rebalanced. + */ + imbalance_min = 2; + if (busiest->sum_nr_running <= imbalance_min) + env->imbalance = 0; + } + return; } diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index 28a516575c181535d21eebc0fd9625983a9eafd9..de22da666ac7392038bdbf18d4c162d867d6f4b6 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -231,16 +231,11 @@ static inline int calc_load_read_idx(void) return calc_load_idx & 1; } -void calc_load_nohz_start(void) +static void calc_load_nohz_fold(struct rq *rq) { - struct rq *this_rq = this_rq(); long delta; - /* - * We're going into NO_HZ mode, if there's any pending delta, fold it - * into the pending NO_HZ delta. - */ - delta = calc_load_fold_active(this_rq, 0); + delta = calc_load_fold_active(rq, 0); if (delta) { int idx = calc_load_write_idx(); @@ -248,6 +243,24 @@ void calc_load_nohz_start(void) } } +void calc_load_nohz_start(void) +{ + /* + * We're going into NO_HZ mode, if there's any pending delta, fold it + * into the pending NO_HZ delta. + */ + calc_load_nohz_fold(this_rq()); +} + +/* + * Keep track of the load for NOHZ_FULL, must be called between + * calc_load_nohz_{start,stop}(). + */ +void calc_load_nohz_remote(struct rq *rq) +{ + calc_load_nohz_fold(rq); +} + void calc_load_nohz_stop(void) { struct rq *this_rq = this_rq(); @@ -268,7 +281,7 @@ void calc_load_nohz_stop(void) this_rq->calc_load_update += LOAD_FREQ; } -static long calc_load_nohz_fold(void) +static long calc_load_nohz_read(void) { int idx = calc_load_read_idx(); long delta = 0; @@ -323,7 +336,7 @@ static void calc_global_nohz(void) } #else /* !CONFIG_NO_HZ_COMMON */ -static inline long calc_load_nohz_fold(void) { return 0; } +static inline long calc_load_nohz_read(void) { return 0; } static inline void calc_global_nohz(void) { } #endif /* CONFIG_NO_HZ_COMMON */ @@ -346,7 +359,7 @@ void calc_global_load(unsigned long ticks) /* * Fold the 'old' NO_HZ-delta to include all NO_HZ CPUs. */ - delta = calc_load_nohz_fold(); + delta = calc_load_nohz_read(); if (delta) atomic_long_add(delta, &calc_load_tasks); diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index ac4bd0ca11cce3149d8e5a76020e339c725edad3..028520702717713286874d34147bf41f21207be2 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -1199,6 +1199,9 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf, if (static_branch_likely(&psi_disabled)) return -EOPNOTSUPP; + if (!nbytes) + return -EINVAL; + buf_size = min(nbytes, sizeof(buf)); if (copy_from_user(buf, user_buf, buf_size)) return -EFAULT; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 1a88dc8ad11b71266480a1ef260cc522fee099ee..9ea647835fd6f37abb88197b25f2c5cf7dcf8424 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -896,7 +896,7 @@ struct rq { */ unsigned long nr_uninterruptible; - struct task_struct *curr; + struct task_struct __rcu *curr; struct task_struct *idle; struct task_struct *stop; unsigned long next_balance; @@ -2479,3 +2479,16 @@ static inline void membarrier_switch_mm(struct rq *rq, { } #endif + +#ifdef CONFIG_SMP +static inline bool is_per_cpu_kthread(struct task_struct *p) +{ + if (!(p->flags & PF_KTHREAD)) + return false; + + if (p->nr_cpus_allowed != 1) + return false; + + return true; +} +#endif diff --git a/kernel/signal.c b/kernel/signal.c index 9ad8dea93dbb23482d18b24c3be220cb775f80eb..5b2396350dd183cc3ce04d115763cc590d5e3cc0 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -413,27 +413,32 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimi { struct sigqueue *q = NULL; struct user_struct *user; + int sigpending; /* * Protect access to @t credentials. This can go away when all * callers hold rcu read lock. + * + * NOTE! A pending signal will hold on to the user refcount, + * and we get/put the refcount only when the sigpending count + * changes from/to zero. */ rcu_read_lock(); - user = get_uid(__task_cred(t)->user); - atomic_inc(&user->sigpending); + user = __task_cred(t)->user; + sigpending = atomic_inc_return(&user->sigpending); + if (sigpending == 1) + get_uid(user); rcu_read_unlock(); - if (override_rlimit || - atomic_read(&user->sigpending) <= - task_rlimit(t, RLIMIT_SIGPENDING)) { + if (override_rlimit || likely(sigpending <= task_rlimit(t, RLIMIT_SIGPENDING))) { q = kmem_cache_alloc(sigqueue_cachep, flags); } else { print_dropped_signal(sig); } if (unlikely(q == NULL)) { - atomic_dec(&user->sigpending); - free_uid(user); + if (atomic_dec_and_test(&user->sigpending)) + free_uid(user); } else { INIT_LIST_HEAD(&q->list); q->flags = 0; @@ -447,8 +452,8 @@ static void __sigqueue_free(struct sigqueue *q) { if (q->flags & SIGQUEUE_PREALLOC) return; - atomic_dec(&q->user->sigpending); - free_uid(q->user); + if (atomic_dec_and_test(&q->user->sigpending)) + free_uid(q->user); kmem_cache_free(sigqueue_cachep, q); } diff --git a/kernel/sys.c b/kernel/sys.c index f9bc5c303e3f42be77cb88c5b4a630f765165ee2..d325f3ab624a9a0b41ffd83911807d683f0aba22 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -47,6 +47,7 @@ #include #include #include +#include #include #include @@ -2546,6 +2547,7 @@ static int do_sysinfo(struct sysinfo *info) memset(info, 0, sizeof(struct sysinfo)); ktime_get_boottime_ts64(&tp); + timens_add_boottime(&tp); info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0); get_avenrun(info->loads, 0, SI_LOAD_SHIFT - FSHIFT); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index d396aaaf19a329203e4e03dfaa3f33fffa93e0f1..ad5b88a53c5a87528c77bb1f2e8cac25de2e75d3 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -805,15 +805,6 @@ static struct ctl_table kern_table[] = { .extra2 = &maxolduid, }, #ifdef CONFIG_S390 -#ifdef CONFIG_MATHEMU - { - .procname = "ieee_emulation_warnings", - .data = &sysctl_ieee_emulation_warnings, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif { .procname = "userprocess_debug", .data = &show_unhandled_signals, diff --git a/kernel/time/time.c b/kernel/time/time.c index cdd7386115ff9de912b4ad405640ee391d9178d9..3985b2b32d083e06acfee3c83f952426660dbe9d 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -449,49 +449,6 @@ time64_t mktime64(const unsigned int year0, const unsigned int mon0, } EXPORT_SYMBOL(mktime64); -/** - * ns_to_timespec - Convert nanoseconds to timespec - * @nsec: the nanoseconds value to be converted - * - * Returns the timespec representation of the nsec parameter. - */ -struct timespec ns_to_timespec(const s64 nsec) -{ - struct timespec ts; - s32 rem; - - if (!nsec) - return (struct timespec) {0, 0}; - - ts.tv_sec = div_s64_rem(nsec, NSEC_PER_SEC, &rem); - if (unlikely(rem < 0)) { - ts.tv_sec--; - rem += NSEC_PER_SEC; - } - ts.tv_nsec = rem; - - return ts; -} -EXPORT_SYMBOL(ns_to_timespec); - -/** - * ns_to_timeval - Convert nanoseconds to timeval - * @nsec: the nanoseconds value to be converted - * - * Returns the timeval representation of the nsec parameter. - */ -struct timeval ns_to_timeval(const s64 nsec) -{ - struct timespec ts = ns_to_timespec(nsec); - struct timeval tv; - - tv.tv_sec = ts.tv_sec; - tv.tv_usec = (suseconds_t) ts.tv_nsec / 1000; - - return tv; -} -EXPORT_SYMBOL(ns_to_timeval); - struct __kernel_old_timeval ns_to_kernel_old_timeval(const s64 nsec) { struct timespec64 ts = ns_to_timespec64(nsec); diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 91e885194dbce47f7f75bbda244aadcca8672986..402eef84c859ac0b7356ca89f22446b00e0b757e 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -143,8 +143,8 @@ if FTRACE config BOOTTIME_TRACING bool "Boot-time Tracing support" - depends on BOOT_CONFIG && TRACING - default y + depends on TRACING + select BOOT_CONFIG help Enable developer to setup ftrace subsystem via supplemental kernel cmdline at boot time for debugging (tracing) driver diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 0735ae8545d86a21d5595392e5b7805b4d75ad13..ca39dc3230cb3a9e075735ac331968cbac879caf 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -335,6 +335,7 @@ static void put_probe_ref(void) static void blk_trace_cleanup(struct blk_trace *bt) { + synchronize_rcu(); blk_trace_free(bt); put_probe_ref(); } @@ -629,8 +630,10 @@ static int compat_blk_trace_setup(struct request_queue *q, char *name, static int __blk_trace_startstop(struct request_queue *q, int start) { int ret; - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + bt = rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex)); if (bt == NULL) return -EINVAL; @@ -740,8 +743,8 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) void blk_trace_shutdown(struct request_queue *q) { mutex_lock(&q->blk_trace_mutex); - - if (q->blk_trace) { + if (rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex))) { __blk_trace_startstop(q, 0); __blk_trace_remove(q); } @@ -752,8 +755,10 @@ void blk_trace_shutdown(struct request_queue *q) #ifdef CONFIG_BLK_CGROUP static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + /* We don't use the 'bt' value here except as an optimization... */ + bt = rcu_dereference_protected(q->blk_trace, 1); if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP)) return 0; @@ -796,10 +801,14 @@ blk_trace_request_get_cgid(struct request_queue *q, struct request *rq) static void blk_add_trace_rq(struct request *rq, int error, unsigned int nr_bytes, u32 what, u64 cgid) { - struct blk_trace *bt = rq->q->blk_trace; + struct blk_trace *bt; - if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(rq->q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + } if (blk_rq_is_passthrough(rq)) what |= BLK_TC_ACT(BLK_TC_PC); @@ -808,6 +817,7 @@ static void blk_add_trace_rq(struct request *rq, int error, __blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, req_op(rq), rq->cmd_flags, what, error, 0, NULL, cgid); + rcu_read_unlock(); } static void blk_add_trace_rq_insert(void *ignore, @@ -853,14 +863,19 @@ static void blk_add_trace_rq_complete(void *ignore, struct request *rq, static void blk_add_trace_bio(struct request_queue *q, struct bio *bio, u32 what, int error) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; - if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + } __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf, what, error, 0, NULL, blk_trace_bio_get_cgid(q, bio)); + rcu_read_unlock(); } static void blk_add_trace_bio_bounce(void *ignore, @@ -905,11 +920,14 @@ static void blk_add_trace_getrq(void *ignore, if (bio) blk_add_trace_bio(q, bio, BLK_TA_GETRQ, 0); else { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) __blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_GETRQ, 0, 0, NULL, 0); + rcu_read_unlock(); } } @@ -921,27 +939,35 @@ static void blk_add_trace_sleeprq(void *ignore, if (bio) blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ, 0); else { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) __blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_SLEEPRQ, 0, 0, NULL, 0); + rcu_read_unlock(); } } static void blk_add_trace_plug(void *ignore, struct request_queue *q) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) __blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, 0); + rcu_read_unlock(); } static void blk_add_trace_unplug(void *ignore, struct request_queue *q, unsigned int depth, bool explicit) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) { __be64 rpdu = cpu_to_be64(depth); u32 what; @@ -953,14 +979,17 @@ static void blk_add_trace_unplug(void *ignore, struct request_queue *q, __blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, 0); } + rcu_read_unlock(); } static void blk_add_trace_split(void *ignore, struct request_queue *q, struct bio *bio, unsigned int pdu) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) { __be64 rpdu = cpu_to_be64(pdu); @@ -969,6 +998,7 @@ static void blk_add_trace_split(void *ignore, BLK_TA_SPLIT, bio->bi_status, sizeof(rpdu), &rpdu, blk_trace_bio_get_cgid(q, bio)); } + rcu_read_unlock(); } /** @@ -988,11 +1018,15 @@ static void blk_add_trace_bio_remap(void *ignore, struct request_queue *q, struct bio *bio, dev_t dev, sector_t from) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; struct blk_io_trace_remap r; - if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + } r.device_from = cpu_to_be32(dev); r.device_to = cpu_to_be32(bio_dev(bio)); @@ -1001,6 +1035,7 @@ static void blk_add_trace_bio_remap(void *ignore, __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf, BLK_TA_REMAP, bio->bi_status, sizeof(r), &r, blk_trace_bio_get_cgid(q, bio)); + rcu_read_unlock(); } /** @@ -1021,11 +1056,15 @@ static void blk_add_trace_rq_remap(void *ignore, struct request *rq, dev_t dev, sector_t from) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; struct blk_io_trace_remap r; - if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + } r.device_from = cpu_to_be32(dev); r.device_to = cpu_to_be32(disk_devt(rq->rq_disk)); @@ -1034,6 +1073,7 @@ static void blk_add_trace_rq_remap(void *ignore, __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), rq_data_dir(rq), 0, BLK_TA_REMAP, 0, sizeof(r), &r, blk_trace_request_get_cgid(q, rq)); + rcu_read_unlock(); } /** @@ -1051,14 +1091,19 @@ void blk_add_driver_data(struct request_queue *q, struct request *rq, void *data, size_t len) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; - if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + } __blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0, 0, BLK_TA_DRV_DATA, 0, len, data, blk_trace_request_get_cgid(q, rq)); + rcu_read_unlock(); } EXPORT_SYMBOL_GPL(blk_add_driver_data); @@ -1597,6 +1642,7 @@ static int blk_trace_remove_queue(struct request_queue *q) return -EINVAL; put_probe_ref(); + synchronize_rcu(); blk_trace_free(bt); return 0; } @@ -1758,6 +1804,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, struct hd_struct *p = dev_to_part(dev); struct request_queue *q; struct block_device *bdev; + struct blk_trace *bt; ssize_t ret = -ENXIO; bdev = bdget(part_devt(p)); @@ -1770,21 +1817,23 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, mutex_lock(&q->blk_trace_mutex); + bt = rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex)); if (attr == &dev_attr_enable) { - ret = sprintf(buf, "%u\n", !!q->blk_trace); + ret = sprintf(buf, "%u\n", !!bt); goto out_unlock_bdev; } - if (q->blk_trace == NULL) + if (bt == NULL) ret = sprintf(buf, "disabled\n"); else if (attr == &dev_attr_act_mask) - ret = blk_trace_mask2str(buf, q->blk_trace->act_mask); + ret = blk_trace_mask2str(buf, bt->act_mask); else if (attr == &dev_attr_pid) - ret = sprintf(buf, "%u\n", q->blk_trace->pid); + ret = sprintf(buf, "%u\n", bt->pid); else if (attr == &dev_attr_start_lba) - ret = sprintf(buf, "%llu\n", q->blk_trace->start_lba); + ret = sprintf(buf, "%llu\n", bt->start_lba); else if (attr == &dev_attr_end_lba) - ret = sprintf(buf, "%llu\n", q->blk_trace->end_lba); + ret = sprintf(buf, "%llu\n", bt->end_lba); out_unlock_bdev: mutex_unlock(&q->blk_trace_mutex); @@ -1801,6 +1850,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, struct block_device *bdev; struct request_queue *q; struct hd_struct *p; + struct blk_trace *bt; u64 value; ssize_t ret = -EINVAL; @@ -1831,8 +1881,10 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, mutex_lock(&q->blk_trace_mutex); + bt = rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex)); if (attr == &dev_attr_enable) { - if (!!value == !!q->blk_trace) { + if (!!value == !!bt) { ret = 0; goto out_unlock_bdev; } @@ -1844,18 +1896,21 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, } ret = 0; - if (q->blk_trace == NULL) + if (bt == NULL) { ret = blk_trace_setup_queue(q, bdev); + bt = rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex)); + } if (ret == 0) { if (attr == &dev_attr_act_mask) - q->blk_trace->act_mask = value; + bt->act_mask = value; else if (attr == &dev_attr_pid) - q->blk_trace->pid = value; + bt->pid = value; else if (attr == &dev_attr_start_lba) - q->blk_trace->start_lba = value; + bt->start_lba = value; else if (attr == &dev_attr_end_lba) - q->blk_trace->end_lba = value; + bt->end_lba = value; } out_unlock_bdev: diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 3f7ee102868a21b2374735c8ea7492004d178ce7..fd81c7de77a7047945452682a6725390a5d2c343 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1547,6 +1547,8 @@ static struct dyn_ftrace *lookup_rec(unsigned long start, unsigned long end) rec = bsearch(&key, pg->records, pg->index, sizeof(struct dyn_ftrace), ftrace_cmp_recs); + if (rec) + break; } return rec; } diff --git a/kernel/trace/synth_event_gen_test.c b/kernel/trace/synth_event_gen_test.c index 4aefe003cb7c3415685f6a9eb31c7f3a3f29fb87..7d56d621ffea879e91ac127475527173dc745380 100644 --- a/kernel/trace/synth_event_gen_test.c +++ b/kernel/trace/synth_event_gen_test.c @@ -111,11 +111,11 @@ static int __init test_gen_synth_cmd(void) /* Create some bogus values just for testing */ vals[0] = 777; /* next_pid_field */ - vals[1] = (u64)"hula hoops"; /* next_comm_field */ + vals[1] = (u64)(long)"hula hoops"; /* next_comm_field */ vals[2] = 1000000; /* ts_ns */ vals[3] = 1000; /* ts_ms */ - vals[4] = smp_processor_id(); /* cpu */ - vals[5] = (u64)"thneed"; /* my_string_field */ + vals[4] = raw_smp_processor_id(); /* cpu */ + vals[5] = (u64)(long)"thneed"; /* my_string_field */ vals[6] = 598; /* my_int_field */ /* Now generate a gen_synth_test event */ @@ -218,11 +218,11 @@ static int __init test_empty_synth_event(void) /* Create some bogus values just for testing */ vals[0] = 777; /* next_pid_field */ - vals[1] = (u64)"tiddlywinks"; /* next_comm_field */ + vals[1] = (u64)(long)"tiddlywinks"; /* next_comm_field */ vals[2] = 1000000; /* ts_ns */ vals[3] = 1000; /* ts_ms */ - vals[4] = smp_processor_id(); /* cpu */ - vals[5] = (u64)"thneed_2.0"; /* my_string_field */ + vals[4] = raw_smp_processor_id(); /* cpu */ + vals[5] = (u64)(long)"thneed_2.0"; /* my_string_field */ vals[6] = 399; /* my_int_field */ /* Now trace an empty_synth_test event */ @@ -290,11 +290,11 @@ static int __init test_create_synth_event(void) /* Create some bogus values just for testing */ vals[0] = 777; /* next_pid_field */ - vals[1] = (u64)"tiddlywinks"; /* next_comm_field */ + vals[1] = (u64)(long)"tiddlywinks"; /* next_comm_field */ vals[2] = 1000000; /* ts_ns */ vals[3] = 1000; /* ts_ms */ - vals[4] = smp_processor_id(); /* cpu */ - vals[5] = (u64)"thneed"; /* my_string_field */ + vals[4] = raw_smp_processor_id(); /* cpu */ + vals[5] = (u64)(long)"thneed"; /* my_string_field */ vals[6] = 398; /* my_int_field */ /* Now generate a create_synth_test event */ @@ -330,7 +330,7 @@ static int __init test_add_next_synth_val(void) goto out; /* next_comm_field */ - ret = synth_event_add_next_val((u64)"slinky", &trace_state); + ret = synth_event_add_next_val((u64)(long)"slinky", &trace_state); if (ret) goto out; @@ -345,12 +345,12 @@ static int __init test_add_next_synth_val(void) goto out; /* cpu */ - ret = synth_event_add_next_val(smp_processor_id(), &trace_state); + ret = synth_event_add_next_val(raw_smp_processor_id(), &trace_state); if (ret) goto out; /* my_string_field */ - ret = synth_event_add_next_val((u64)"thneed_2.01", &trace_state); + ret = synth_event_add_next_val((u64)(long)"thneed_2.01", &trace_state); if (ret) goto out; @@ -388,7 +388,7 @@ static int __init test_add_synth_val(void) if (ret) goto out; - ret = synth_event_add_val("cpu", smp_processor_id(), &trace_state); + ret = synth_event_add_val("cpu", raw_smp_processor_id(), &trace_state); if (ret) goto out; @@ -396,12 +396,12 @@ static int __init test_add_synth_val(void) if (ret) goto out; - ret = synth_event_add_val("next_comm_field", (u64)"silly putty", + ret = synth_event_add_val("next_comm_field", (u64)(long)"silly putty", &trace_state); if (ret) goto out; - ret = synth_event_add_val("my_string_field", (u64)"thneed_9", + ret = synth_event_add_val("my_string_field", (u64)(long)"thneed_9", &trace_state); if (ret) goto out; @@ -423,13 +423,13 @@ static int __init test_trace_synth_event(void) /* Trace some bogus values just for testing */ ret = synth_event_trace(create_synth_test, 7, /* number of values */ - 444, /* next_pid_field */ - (u64)"clackers", /* next_comm_field */ - 1000000, /* ts_ns */ - 1000, /* ts_ms */ - smp_processor_id(), /* cpu */ - (u64)"Thneed", /* my_string_field */ - 999); /* my_int_field */ + (u64)444, /* next_pid_field */ + (u64)(long)"clackers", /* next_comm_field */ + (u64)1000000, /* ts_ns */ + (u64)1000, /* ts_ms */ + (u64)raw_smp_processor_id(), /* cpu */ + (u64)(long)"Thneed", /* my_string_field */ + (u64)999); /* my_int_field */ return ret; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index c797a15a1fc77ef672c0269d3e9a2048f168edd2..6b11e4e2150cea92de1f4c007efe4ea9c0c219e8 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1837,6 +1837,7 @@ static __init int init_trace_selftests(void) pr_info("Running postponed tracer tests:\n"); + tracing_selftest_running = true; list_for_each_entry_safe(p, n, &postponed_selftests, list) { /* This loop can take minutes when sanitizers are enabled, so * lets make sure we allow RCU processing. @@ -1859,6 +1860,7 @@ static __init int init_trace_selftests(void) list_del(&p->list); kfree(p); } + tracing_selftest_running = false; out: mutex_unlock(&trace_types_lock); diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index e7ce7cdac62f3016ae541e0cb4302fd31f5abf41..5f6834a2bf4119ef4a30879cac479e0cbc0e5bdf 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -821,6 +821,29 @@ static const char *synth_field_fmt(char *type) return fmt; } +static void print_synth_event_num_val(struct trace_seq *s, + char *print_fmt, char *name, + int size, u64 val, char *space) +{ + switch (size) { + case 1: + trace_seq_printf(s, print_fmt, name, (u8)val, space); + break; + + case 2: + trace_seq_printf(s, print_fmt, name, (u16)val, space); + break; + + case 4: + trace_seq_printf(s, print_fmt, name, (u32)val, space); + break; + + default: + trace_seq_printf(s, print_fmt, name, val, space); + break; + } +} + static enum print_line_t print_synth_event(struct trace_iterator *iter, int flags, struct trace_event *event) @@ -859,10 +882,13 @@ static enum print_line_t print_synth_event(struct trace_iterator *iter, } else { struct trace_print_flags __flags[] = { __def_gfpflag_names, {-1, NULL} }; + char *space = (i == se->n_fields - 1 ? "" : " "); - trace_seq_printf(s, print_fmt, se->fields[i]->name, - entry->fields[n_u64], - i == se->n_fields - 1 ? "" : " "); + print_synth_event_num_val(s, print_fmt, + se->fields[i]->name, + se->fields[i]->size, + entry->fields[n_u64], + space); if (strcmp(se->fields[i]->type, "gfp_t") == 0) { trace_seq_puts(s, " ("); @@ -1798,6 +1824,62 @@ void synth_event_cmd_init(struct dynevent_cmd *cmd, char *buf, int maxlen) } EXPORT_SYMBOL_GPL(synth_event_cmd_init); +static inline int +__synth_event_trace_start(struct trace_event_file *file, + struct synth_event_trace_state *trace_state) +{ + int entry_size, fields_size = 0; + int ret = 0; + + memset(trace_state, '\0', sizeof(*trace_state)); + + /* + * Normal event tracing doesn't get called at all unless the + * ENABLED bit is set (which attaches the probe thus allowing + * this code to be called, etc). Because this is called + * directly by the user, we don't have that but we still need + * to honor not logging when disabled. For the the iterated + * trace case, we save the enabed state upon start and just + * ignore the following data calls. + */ + if (!(file->flags & EVENT_FILE_FL_ENABLED) || + trace_trigger_soft_disabled(file)) { + trace_state->disabled = true; + ret = -ENOENT; + goto out; + } + + trace_state->event = file->event_call->data; + + fields_size = trace_state->event->n_u64 * sizeof(u64); + + /* + * Avoid ring buffer recursion detection, as this event + * is being performed within another event. + */ + trace_state->buffer = file->tr->array_buffer.buffer; + ring_buffer_nest_start(trace_state->buffer); + + entry_size = sizeof(*trace_state->entry) + fields_size; + trace_state->entry = trace_event_buffer_reserve(&trace_state->fbuffer, + file, + entry_size); + if (!trace_state->entry) { + ring_buffer_nest_end(trace_state->buffer); + ret = -EINVAL; + } +out: + return ret; +} + +static inline void +__synth_event_trace_end(struct synth_event_trace_state *trace_state) +{ + trace_event_buffer_commit(&trace_state->fbuffer); + + ring_buffer_nest_end(trace_state->buffer); +} + /** * synth_event_trace - Trace a synthetic event * @file: The trace_event_file representing the synthetic event @@ -1819,71 +1901,61 @@ EXPORT_SYMBOL_GPL(synth_event_cmd_init); */ int synth_event_trace(struct trace_event_file *file, unsigned int n_vals, ...) { - struct trace_event_buffer fbuffer; - struct synth_trace_event *entry; - struct trace_buffer *buffer; - struct synth_event *event; + struct synth_event_trace_state state; unsigned int i, n_u64; - int fields_size = 0; va_list args; - int ret = 0; - - /* - * Normal event generation doesn't get called at all unless - * the ENABLED bit is set (which attaches the probe thus - * allowing this code to be called, etc). Because this is - * called directly by the user, we don't have that but we - * still need to honor not logging when disabled. - */ - if (!(file->flags & EVENT_FILE_FL_ENABLED)) - return 0; - - event = file->event_call->data; - - if (n_vals != event->n_fields) - return -EINVAL; - - if (trace_trigger_soft_disabled(file)) - return -EINVAL; - - fields_size = event->n_u64 * sizeof(u64); + int ret; - /* - * Avoid ring buffer recursion detection, as this event - * is being performed within another event. - */ - buffer = file->tr->array_buffer.buffer; - ring_buffer_nest_start(buffer); + ret = __synth_event_trace_start(file, &state); + if (ret) { + if (ret == -ENOENT) + ret = 0; /* just disabled, not really an error */ + return ret; + } - entry = trace_event_buffer_reserve(&fbuffer, file, - sizeof(*entry) + fields_size); - if (!entry) { + if (n_vals != state.event->n_fields) { ret = -EINVAL; goto out; } va_start(args, n_vals); - for (i = 0, n_u64 = 0; i < event->n_fields; i++) { + for (i = 0, n_u64 = 0; i < state.event->n_fields; i++) { u64 val; val = va_arg(args, u64); - if (event->fields[i]->is_string) { + if (state.event->fields[i]->is_string) { char *str_val = (char *)(long)val; - char *str_field = (char *)&entry->fields[n_u64]; + char *str_field = (char *)&state.entry->fields[n_u64]; strscpy(str_field, str_val, STR_VAR_LEN_MAX); n_u64 += STR_VAR_LEN_MAX / sizeof(u64); } else { - entry->fields[n_u64] = val; + struct synth_field *field = state.event->fields[i]; + + switch (field->size) { + case 1: + *(u8 *)&state.entry->fields[n_u64] = (u8)val; + break; + + case 2: + *(u16 *)&state.entry->fields[n_u64] = (u16)val; + break; + + case 4: + *(u32 *)&state.entry->fields[n_u64] = (u32)val; + break; + + default: + state.entry->fields[n_u64] = val; + break; + } n_u64++; } } va_end(args); - - trace_event_buffer_commit(&fbuffer); out: - ring_buffer_nest_end(buffer); + __synth_event_trace_end(&state); return ret; } @@ -1910,64 +1982,55 @@ EXPORT_SYMBOL_GPL(synth_event_trace); int synth_event_trace_array(struct trace_event_file *file, u64 *vals, unsigned int n_vals) { - struct trace_event_buffer fbuffer; - struct synth_trace_event *entry; - struct trace_buffer *buffer; - struct synth_event *event; + struct synth_event_trace_state state; unsigned int i, n_u64; - int fields_size = 0; - int ret = 0; - - /* - * Normal event generation doesn't get called at all unless - * the ENABLED bit is set (which attaches the probe thus - * allowing this code to be called, etc). Because this is - * called directly by the user, we don't have that but we - * still need to honor not logging when disabled. - */ - if (!(file->flags & EVENT_FILE_FL_ENABLED)) - return 0; - - event = file->event_call->data; - - if (n_vals != event->n_fields) - return -EINVAL; - - if (trace_trigger_soft_disabled(file)) - return -EINVAL; - - fields_size = event->n_u64 * sizeof(u64); + int ret; - /* - * Avoid ring buffer recursion detection, as this event - * is being performed within another event. - */ - buffer = file->tr->array_buffer.buffer; - ring_buffer_nest_start(buffer); + ret = __synth_event_trace_start(file, &state); + if (ret) { + if (ret == -ENOENT) + ret = 0; /* just disabled, not really an error */ + return ret; + } - entry = trace_event_buffer_reserve(&fbuffer, file, - sizeof(*entry) + fields_size); - if (!entry) { + if (n_vals != state.event->n_fields) { ret = -EINVAL; goto out; } - for (i = 0, n_u64 = 0; i < event->n_fields; i++) { - if (event->fields[i]->is_string) { + for (i = 0, n_u64 = 0; i < state.event->n_fields; i++) { + if (state.event->fields[i]->is_string) { char *str_val = (char *)(long)vals[i]; - char *str_field = (char *)&entry->fields[n_u64]; + char *str_field = (char *)&state.entry->fields[n_u64]; strscpy(str_field, str_val, STR_VAR_LEN_MAX); n_u64 += STR_VAR_LEN_MAX / sizeof(u64); } else { - entry->fields[n_u64] = vals[i]; + struct synth_field *field = state.event->fields[i]; + u64 val = vals[i]; + + switch (field->size) { + case 1: + *(u8 *)&state.entry->fields[n_u64] = (u8)val; + break; + + case 2: + *(u16 *)&state.entry->fields[n_u64] = (u16)val; + break; + + case 4: + *(u32 *)&state.entry->fields[n_u64] = (u32)val; + break; + + default: + state.entry->fields[n_u64] = val; + break; + } n_u64++; } } - - trace_event_buffer_commit(&fbuffer); out: - ring_buffer_nest_end(buffer); + __synth_event_trace_end(&state); return ret; } @@ -2004,58 +2067,15 @@ EXPORT_SYMBOL_GPL(synth_event_trace_array); int synth_event_trace_start(struct trace_event_file *file, struct synth_event_trace_state *trace_state) { - struct synth_trace_event *entry; - int fields_size = 0; - int ret = 0; - - if (!trace_state) { - ret = -EINVAL; - goto out; - } - - memset(trace_state, '\0', sizeof(*trace_state)); - - /* - * Normal event tracing doesn't get called at all unless the - * ENABLED bit is set (which attaches the probe thus allowing - * this code to be called, etc). Because this is called - * directly by the user, we don't have that but we still need - * to honor not logging when disabled. For the the iterated - * trace case, we save the enabed state upon start and just - * ignore the following data calls. - */ - if (!(file->flags & EVENT_FILE_FL_ENABLED)) { - trace_state->enabled = false; - goto out; - } - - trace_state->enabled = true; - - trace_state->event = file->event_call->data; - - if (trace_trigger_soft_disabled(file)) { - ret = -EINVAL; - goto out; - } - - fields_size = trace_state->event->n_u64 * sizeof(u64); + int ret; - /* - * Avoid ring buffer recursion detection, as this event - * is being performed within another event. - */ - trace_state->buffer = file->tr->array_buffer.buffer; - ring_buffer_nest_start(trace_state->buffer); + if (!trace_state) + return -EINVAL; - entry = trace_event_buffer_reserve(&trace_state->fbuffer, file, - sizeof(*entry) + fields_size); - if (!entry) { - ret = -EINVAL; - goto out; - } + ret = __synth_event_trace_start(file, trace_state); + if (ret == -ENOENT) + ret = 0; /* just disabled, not really an error */ - trace_state->entry = entry; -out: return ret; } EXPORT_SYMBOL_GPL(synth_event_trace_start); @@ -2088,7 +2108,7 @@ static int __synth_event_add_val(const char *field_name, u64 val, trace_state->add_next = true; } - if (!trace_state->enabled) + if (trace_state->disabled) goto out; event = trace_state->event; @@ -2122,8 +2142,25 @@ static int __synth_event_add_val(const char *field_name, u64 val, str_field = (char *)&entry->fields[field->offset]; strscpy(str_field, str_val, STR_VAR_LEN_MAX); - } else - entry->fields[field->offset] = val; + } else { + switch (field->size) { + case 1: + *(u8 *)&trace_state->entry->fields[field->offset] = (u8)val; + break; + + case 2: + *(u16 *)&trace_state->entry->fields[field->offset] = (u16)val; + break; + + case 4: + *(u32 *)&trace_state->entry->fields[field->offset] = (u32)val; + break; + + default: + trace_state->entry->fields[field->offset] = val; + break; + } + } out: return ret; } @@ -2223,9 +2260,7 @@ int synth_event_trace_end(struct synth_event_trace_state *trace_state) if (!trace_state) return -EINVAL; - trace_event_buffer_commit(&trace_state->fbuffer); - - ring_buffer_nest_end(trace_state->buffer); + __synth_event_trace_end(trace_state); return 0; } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index d8264ebb95814a53cdfd1031b03b8e869a2c5f00..362cca52f5de2dba861376c0e5c286d66c5ceb4e 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1012,7 +1012,7 @@ int __kprobe_event_add_fields(struct dynevent_cmd *cmd, ...) { struct dynevent_arg arg; va_list args; - int ret; + int ret = 0; if (cmd->type != DYNEVENT_TYPE_KPROBE) return -EINVAL; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 301db4406bc37ab1805806573124fe696c41518e..4e01c448b4b48fed8e1f53cbc9970422d796db53 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1411,14 +1411,16 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, return; rcu_read_lock(); retry: - if (req_cpu == WORK_CPU_UNBOUND) - cpu = wq_select_unbound_cpu(raw_smp_processor_id()); - /* pwq which will be used unless @work is executing elsewhere */ - if (!(wq->flags & WQ_UNBOUND)) - pwq = per_cpu_ptr(wq->cpu_pwqs, cpu); - else + if (wq->flags & WQ_UNBOUND) { + if (req_cpu == WORK_CPU_UNBOUND) + cpu = wq_select_unbound_cpu(raw_smp_processor_id()); pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu)); + } else { + if (req_cpu == WORK_CPU_UNBOUND) + cpu = raw_smp_processor_id(); + pwq = per_cpu_ptr(wq->cpu_pwqs, cpu); + } /* * If @work was previously on a different pool, it might still be diff --git a/lib/Kconfig b/lib/Kconfig index 0cf875fd627c062149c1ec4e34e181d0b34357bf..bc7e56370129257a7c459cccc68741522ed94528 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -573,9 +573,6 @@ config DIMLIB config LIBFDT bool -config LIBXBC - bool - config OID_REGISTRY tristate help diff --git a/lib/Makefile b/lib/Makefile index 5d64890d6b6a25e6d9d7c303608c8a8828ebb225..611872c0692693f8e6c5048f1e5902ecdf429511 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -230,7 +230,7 @@ $(foreach file, $(libfdt_files), \ $(eval CFLAGS_$(file) = -I $(srctree)/scripts/dtc/libfdt)) lib-$(CONFIG_LIBFDT) += $(libfdt_files) -lib-$(CONFIG_LIBXBC) += bootconfig.o +lib-$(CONFIG_BOOT_CONFIG) += bootconfig.o obj-$(CONFIG_RBTREE_TEST) += rbtree_test.o obj-$(CONFIG_INTERVAL_TREE_TEST) += interval_tree_test.o diff --git a/lib/bootconfig.c b/lib/bootconfig.c index afb2e767e6fe83b7ce42f29aba58c935c6b709cb..ec3ce7fd299f6f36ca3a07897b45bf876e0c2db2 100644 --- a/lib/bootconfig.c +++ b/lib/bootconfig.c @@ -6,12 +6,13 @@ #define pr_fmt(fmt) "bootconfig: " fmt +#include #include #include #include #include +#include #include -#include #include /* @@ -23,7 +24,7 @@ * node (for array). */ -static struct xbc_node xbc_nodes[XBC_NODE_MAX] __initdata; +static struct xbc_node *xbc_nodes __initdata; static int xbc_node_num __initdata; static char *xbc_data __initdata; static size_t xbc_data_size __initdata; @@ -532,7 +533,7 @@ struct xbc_node *find_match_node(struct xbc_node *node, char *k) static int __init __xbc_add_key(char *k) { - struct xbc_node *node; + struct xbc_node *node, *child; if (!xbc_valid_keyword(k)) return xbc_parse_error("Invalid keyword", k); @@ -542,8 +543,12 @@ static int __init __xbc_add_key(char *k) if (!last_parent) /* the first level */ node = find_match_node(xbc_nodes, k); - else - node = find_match_node(xbc_node_get_child(last_parent), k); + else { + child = xbc_node_get_child(last_parent); + if (child && xbc_node_is_value(child)) + return xbc_parse_error("Subkey is mixed with value", k); + node = find_match_node(child, k); + } if (node) last_parent = node; @@ -573,10 +578,10 @@ static int __init __xbc_parse_keys(char *k) return __xbc_add_key(k); } -static int __init xbc_parse_kv(char **k, char *v) +static int __init xbc_parse_kv(char **k, char *v, int op) { struct xbc_node *prev_parent = last_parent; - struct xbc_node *node; + struct xbc_node *child; char *next; int c, ret; @@ -584,12 +589,19 @@ static int __init xbc_parse_kv(char **k, char *v) if (ret) return ret; + child = xbc_node_get_child(last_parent); + if (child) { + if (xbc_node_is_key(child)) + return xbc_parse_error("Value is mixed with subkey", v); + else if (op == '=') + return xbc_parse_error("Value is redefined", v); + } + c = __xbc_parse_value(&v, &next); if (c < 0) return c; - node = xbc_add_sibling(v, XBC_VALUE); - if (!node) + if (!xbc_add_sibling(v, XBC_VALUE)) return -ENOMEM; if (c == ',') { /* Array */ @@ -719,7 +731,8 @@ void __init xbc_destroy_all(void) xbc_data = NULL; xbc_data_size = 0; xbc_node_num = 0; - memset(xbc_nodes, 0, sizeof(xbc_nodes)); + memblock_free(__pa(xbc_nodes), sizeof(struct xbc_node) * XBC_NODE_MAX); + xbc_nodes = NULL; } /** @@ -748,13 +761,20 @@ int __init xbc_init(char *buf) return -ERANGE; } + xbc_nodes = memblock_alloc(sizeof(struct xbc_node) * XBC_NODE_MAX, + SMP_CACHE_BYTES); + if (!xbc_nodes) { + pr_err("Failed to allocate memory for bootconfig nodes.\n"); + return -ENOMEM; + } + memset(xbc_nodes, 0, sizeof(struct xbc_node) * XBC_NODE_MAX); xbc_data = buf; xbc_data_size = ret + 1; last_parent = NULL; p = buf; do { - q = strpbrk(p, "{}=;\n#"); + q = strpbrk(p, "{}=+;\n#"); if (!q) { p = skip_spaces(p); if (*p != '\0') @@ -765,8 +785,15 @@ int __init xbc_init(char *buf) c = *q; *q++ = '\0'; switch (c) { + case '+': + if (*q++ != '=') { + ret = xbc_parse_error("Wrong '+' operator", + q - 2); + break; + } + /* Fall through */ case '=': - ret = xbc_parse_kv(&p, q); + ret = xbc_parse_kv(&p, q, c); break; case '{': ret = xbc_open_brace(&p, q); diff --git a/lib/crypto/chacha20poly1305.c b/lib/crypto/chacha20poly1305.c index 6d83cafebc69ce06b3b37b96f665f3537a0748b5..ad0699ce702f954bbae3aa899b7acda21a289fd2 100644 --- a/lib/crypto/chacha20poly1305.c +++ b/lib/crypto/chacha20poly1305.c @@ -235,6 +235,9 @@ bool chacha20poly1305_crypt_sg_inplace(struct scatterlist *src, __le64 lens[2]; } b __aligned(16); + if (WARN_ON(src_len > INT_MAX)) + return false; + chacha_load_key(b.k, key); b.iv[0] = 0; diff --git a/lib/stackdepot.c b/lib/stackdepot.c index ed717dd08ff37216a7c90a531f23b2eac0e2be1a..81c69c08d1d157189d253a0cbe2a2bbd82cff421 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -83,15 +83,19 @@ static bool init_stack_slab(void **prealloc) return true; if (stack_slabs[depot_index] == NULL) { stack_slabs[depot_index] = *prealloc; + *prealloc = NULL; } else { - stack_slabs[depot_index + 1] = *prealloc; + /* If this is the last depot slab, do not touch the next one. */ + if (depot_index + 1 < STACK_ALLOC_MAX_SLABS) { + stack_slabs[depot_index + 1] = *prealloc; + *prealloc = NULL; + } /* * This smp_store_release pairs with smp_load_acquire() from * |next_slab_inited| above and in stack_depot_save(). */ smp_store_release(&next_slab_inited, 1); } - *prealloc = NULL; return true; } diff --git a/lib/string.c b/lib/string.c index f607b967d9785b206c135f466ca114367cb4727d..6012c385fb314d810bd8a2ff4f18b9e8a3a517db 100644 --- a/lib/string.c +++ b/lib/string.c @@ -699,6 +699,14 @@ EXPORT_SYMBOL(sysfs_streq); * @n: number of strings in the array or -1 for NULL terminated arrays * @string: string to match with * + * This routine will look for a string in an array of strings up to the + * n-th element in the array or until the first NULL element. + * + * Historically the value of -1 for @n, was used to search in arrays that + * are NULL terminated. However, the function does not make a distinction + * when finishing the search: either @n elements have been compared OR + * the first NULL element was found. + * * Return: * index of a @string in the @array if matches, or %-EINVAL otherwise. */ @@ -727,6 +735,14 @@ EXPORT_SYMBOL(match_string); * * Returns index of @str in the @array or -EINVAL, just like match_string(). * Uses sysfs_streq instead of strcmp for matching. + * + * This routine will look for a string in an array of strings up to the + * n-th element in the array or until the first NULL element. + * + * Historically the value of -1 for @n, was used to search in arrays that + * are NULL terminated. However, the function does not make a distinction + * when finishing the search: either @n elements have been compared OR + * the first NULL element was found. */ int __sysfs_match_string(const char * const *array, size_t n, const char *str) { diff --git a/mm/huge_memory.c b/mm/huge_memory.c index b08b199f9a111004e5bfcb92fbdd9870368529a4..24ad53b4dfc0576c6cde8acf94cf6fe478553684 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3043,8 +3043,7 @@ void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, return; flush_cache_range(vma, address, address + HPAGE_PMD_SIZE); - pmdval = *pvmw->pmd; - pmdp_invalidate(vma, address, pvmw->pmd); + pmdval = pmdp_invalidate(vma, address, pvmw->pmd); if (pmd_dirty(pmdval)) set_page_dirty(page); entry = make_migration_entry(page, pmd_write(pmdval)); diff --git a/mm/madvise.c b/mm/madvise.c index 43b47d3fae02e1cf86c0b9a98c5ce16471874841..4bb30ed6c8d216cdc6bff02ef2b89d0331479f09 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -335,12 +335,14 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, } page = pmd_page(orig_pmd); + + /* Do not interfere with other mappings of this page */ + if (page_mapcount(page) != 1) + goto huge_unlock; + if (next - addr != HPAGE_PMD_SIZE) { int err; - if (page_mapcount(page) != 1) - goto huge_unlock; - get_page(page); spin_unlock(ptl); lock_page(page); @@ -426,6 +428,10 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, continue; } + /* Do not interfere with other mappings of this page */ + if (page_mapcount(page) != 1) + continue; + VM_BUG_ON_PAGE(PageTransCompound(page), page); if (pte_young(ptent)) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 6f6dc8712e392e5e958868c6bcc191cee3d1e888..7a4bd8b9adc213fdd21da52e6842c036b1c4c81a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -409,8 +409,10 @@ int memcg_expand_shrinker_maps(int new_id) if (mem_cgroup_is_root(memcg)) continue; ret = memcg_expand_one_shrinker_map(memcg, size, old_size); - if (ret) + if (ret) { + mem_cgroup_iter_break(NULL, memcg); goto unlock; + } } unlock: if (!ret) @@ -2295,28 +2297,41 @@ static void high_work_func(struct work_struct *work) #define MEMCG_DELAY_SCALING_SHIFT 14 /* - * Scheduled by try_charge() to be executed from the userland return path - * and reclaims memory over the high limit. + * Get the number of jiffies that we should penalise a mischievous cgroup which + * is exceeding its memory.high by checking both it and its ancestors. */ -void mem_cgroup_handle_over_high(void) +static unsigned long calculate_high_delay(struct mem_cgroup *memcg, + unsigned int nr_pages) { - unsigned long usage, high, clamped_high; - unsigned long pflags; - unsigned long penalty_jiffies, overage; - unsigned int nr_pages = current->memcg_nr_pages_over_high; - struct mem_cgroup *memcg; + unsigned long penalty_jiffies; + u64 max_overage = 0; - if (likely(!nr_pages)) - return; + do { + unsigned long usage, high; + u64 overage; - memcg = get_mem_cgroup_from_mm(current->mm); - reclaim_high(memcg, nr_pages, GFP_KERNEL); - current->memcg_nr_pages_over_high = 0; + usage = page_counter_read(&memcg->memory); + high = READ_ONCE(memcg->high); + + /* + * Prevent division by 0 in overage calculation by acting as if + * it was a threshold of 1 page + */ + high = max(high, 1UL); + + overage = usage - high; + overage <<= MEMCG_DELAY_PRECISION_SHIFT; + overage = div64_u64(overage, high); + + if (overage > max_overage) + max_overage = overage; + } while ((memcg = parent_mem_cgroup(memcg)) && + !mem_cgroup_is_root(memcg)); + + if (!max_overage) + return 0; /* - * memory.high is breached and reclaim is unable to keep up. Throttle - * allocators proactively to slow down excessive growth. - * * We use overage compared to memory.high to calculate the number of * jiffies to sleep (penalty_jiffies). Ideally this value should be * fairly lenient on small overages, and increasingly harsh when the @@ -2324,24 +2339,9 @@ void mem_cgroup_handle_over_high(void) * its crazy behaviour, so we exponentially increase the delay based on * overage amount. */ - - usage = page_counter_read(&memcg->memory); - high = READ_ONCE(memcg->high); - - if (usage <= high) - goto out; - - /* - * Prevent division by 0 in overage calculation by acting as if it was a - * threshold of 1 page - */ - clamped_high = max(high, 1UL); - - overage = div_u64((u64)(usage - high) << MEMCG_DELAY_PRECISION_SHIFT, - clamped_high); - - penalty_jiffies = ((u64)overage * overage * HZ) - >> (MEMCG_DELAY_PRECISION_SHIFT + MEMCG_DELAY_SCALING_SHIFT); + penalty_jiffies = max_overage * max_overage * HZ; + penalty_jiffies >>= MEMCG_DELAY_PRECISION_SHIFT; + penalty_jiffies >>= MEMCG_DELAY_SCALING_SHIFT; /* * Factor in the task's own contribution to the overage, such that four @@ -2358,7 +2358,32 @@ void mem_cgroup_handle_over_high(void) * application moving forwards and also permit diagnostics, albeit * extremely slowly. */ - penalty_jiffies = min(penalty_jiffies, MEMCG_MAX_HIGH_DELAY_JIFFIES); + return min(penalty_jiffies, MEMCG_MAX_HIGH_DELAY_JIFFIES); +} + +/* + * Scheduled by try_charge() to be executed from the userland return path + * and reclaims memory over the high limit. + */ +void mem_cgroup_handle_over_high(void) +{ + unsigned long penalty_jiffies; + unsigned long pflags; + unsigned int nr_pages = current->memcg_nr_pages_over_high; + struct mem_cgroup *memcg; + + if (likely(!nr_pages)) + return; + + memcg = get_mem_cgroup_from_mm(current->mm); + reclaim_high(memcg, nr_pages, GFP_KERNEL); + current->memcg_nr_pages_over_high = 0; + + /* + * memory.high is breached and reclaim is unable to keep up. Throttle + * allocators proactively to slow down excessive growth. + */ + penalty_jiffies = calculate_high_delay(memcg, nr_pages); /* * Don't sleep if the amount of jiffies this memcg owes us is so low @@ -4025,7 +4050,7 @@ static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg, struct mem_cgroup_thresholds *thresholds; struct mem_cgroup_threshold_ary *new; unsigned long usage; - int i, j, size; + int i, j, size, entries; mutex_lock(&memcg->thresholds_lock); @@ -4045,14 +4070,20 @@ static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg, __mem_cgroup_threshold(memcg, type == _MEMSWAP); /* Calculate new number of threshold */ - size = 0; + size = entries = 0; for (i = 0; i < thresholds->primary->size; i++) { if (thresholds->primary->entries[i].eventfd != eventfd) size++; + else + entries++; } new = thresholds->spare; + /* If no items related to eventfd have been cleared, nothing to do */ + if (!entries) + goto unlock; + /* Set thresholds array to NULL if we don't have thresholds */ if (!size) { kfree(new); @@ -6680,19 +6711,9 @@ void mem_cgroup_sk_alloc(struct sock *sk) if (!mem_cgroup_sockets_enabled) return; - /* - * Socket cloning can throw us here with sk_memcg already - * filled. It won't however, necessarily happen from - * process context. So the test for root memcg given - * the current task's memcg won't help us in this case. - * - * Respecting the original socket's memcg is a better - * decision in this case. - */ - if (sk->sk_memcg) { - css_get(&sk->sk_memcg->css); + /* Do not associate the sock with unrelated interrupted task's memcg. */ + if (in_interrupt()) return; - } rcu_read_lock(); memcg = mem_cgroup_from_task(current); diff --git a/mm/memory.c b/mm/memory.c index 0bccc622e4822b03d47ef5ec7714d9b17009ed55..e8bfdf0d9d1dd98c0341bdfc9adc11ae4a948cb7 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2257,7 +2257,7 @@ static inline bool cow_user_page(struct page *dst, struct page *src, bool ret; void *kaddr; void __user *uaddr; - bool force_mkyoung; + bool locked = false; struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; unsigned long addr = vmf->address; @@ -2282,11 +2282,11 @@ static inline bool cow_user_page(struct page *dst, struct page *src, * On architectures with software "accessed" bits, we would * take a double page fault, so mark it accessed here. */ - force_mkyoung = arch_faults_on_old_pte() && !pte_young(vmf->orig_pte); - if (force_mkyoung) { + if (arch_faults_on_old_pte() && !pte_young(vmf->orig_pte)) { pte_t entry; vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); + locked = true; if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) { /* * Other thread has already handled the fault @@ -2310,18 +2310,37 @@ static inline bool cow_user_page(struct page *dst, struct page *src, * zeroes. */ if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { + if (locked) + goto warn; + + /* Re-validate under PTL if the page is still mapped */ + vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); + locked = true; + if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) { + /* The PTE changed under us. Retry page fault. */ + ret = false; + goto pte_unlock; + } + /* - * Give a warn in case there can be some obscure - * use-case + * The same page can be mapped back since last copy attampt. + * Try to copy again under PTL. */ - WARN_ON_ONCE(1); - clear_page(kaddr); + if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { + /* + * Give a warn in case there can be some obscure + * use-case + */ +warn: + WARN_ON_ONCE(1); + clear_page(kaddr); + } } ret = true; pte_unlock: - if (force_mkyoung) + if (locked) pte_unmap_unlock(vmf->pte, vmf->ptl); kunmap_atomic(kaddr); flush_dcache_page(dst); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 0a54ffac8c682ae5c940642c6b5d45cfb22cada5..19389cdc16a502f04726f4e12bab64cb8e4e1879 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -574,7 +574,13 @@ EXPORT_SYMBOL_GPL(restore_online_page_callback); void generic_online_page(struct page *page, unsigned int order) { - kernel_map_pages(page, 1 << order, 1); + /* + * Freeing the page with debug_pagealloc enabled will try to unmap it, + * so we should map it first. This is better than introducing a special + * case in page freeing fast path. + */ + if (debug_pagealloc_enabled_static()) + kernel_map_pages(page, 1 << order, 1); __free_pages_core(page, order); totalram_pages_add(1UL << order); #ifdef CONFIG_HIGHMEM diff --git a/mm/mmap.c b/mm/mmap.c index 6756b8bb00334c023c73d1a8112785d205e5c927..d681a20eb4ea9fc604caeedbc2b396083360462d 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -195,8 +195,6 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) bool downgraded = false; LIST_HEAD(uf); - brk = untagged_addr(brk); - if (down_write_killable(&mm->mmap_sem)) return -EINTR; @@ -1557,8 +1555,6 @@ unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, struct file *file = NULL; unsigned long retval; - addr = untagged_addr(addr); - if (!(flags & MAP_ANONYMOUS)) { audit_mmap_fd(fd, flags); file = fget(fd); diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index ef3973a5d34a9481ede0a2e34d22371c9dbc5e60..06852b896fa6362b7569b4fff7392c80ec37350e 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -307,7 +307,8 @@ static void mn_hlist_release(struct mmu_notifier_subscriptions *subscriptions, * ->release returns. */ id = srcu_read_lock(&srcu); - hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist) + hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist, + srcu_read_lock_held(&srcu)) /* * If ->release runs before mmu_notifier_unregister it must be * handled, as it's the only way for the driver to flush all @@ -370,7 +371,8 @@ int __mmu_notifier_clear_flush_young(struct mm_struct *mm, id = srcu_read_lock(&srcu); hlist_for_each_entry_rcu(subscription, - &mm->notifier_subscriptions->list, hlist) { + &mm->notifier_subscriptions->list, hlist, + srcu_read_lock_held(&srcu)) { if (subscription->ops->clear_flush_young) young |= subscription->ops->clear_flush_young( subscription, mm, start, end); @@ -389,7 +391,8 @@ int __mmu_notifier_clear_young(struct mm_struct *mm, id = srcu_read_lock(&srcu); hlist_for_each_entry_rcu(subscription, - &mm->notifier_subscriptions->list, hlist) { + &mm->notifier_subscriptions->list, hlist, + srcu_read_lock_held(&srcu)) { if (subscription->ops->clear_young) young |= subscription->ops->clear_young(subscription, mm, start, end); @@ -407,7 +410,8 @@ int __mmu_notifier_test_young(struct mm_struct *mm, id = srcu_read_lock(&srcu); hlist_for_each_entry_rcu(subscription, - &mm->notifier_subscriptions->list, hlist) { + &mm->notifier_subscriptions->list, hlist, + srcu_read_lock_held(&srcu)) { if (subscription->ops->test_young) { young = subscription->ops->test_young(subscription, mm, address); @@ -428,7 +432,8 @@ void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address, id = srcu_read_lock(&srcu); hlist_for_each_entry_rcu(subscription, - &mm->notifier_subscriptions->list, hlist) { + &mm->notifier_subscriptions->list, hlist, + srcu_read_lock_held(&srcu)) { if (subscription->ops->change_pte) subscription->ops->change_pte(subscription, mm, address, pte); @@ -476,7 +481,8 @@ static int mn_hlist_invalidate_range_start( int id; id = srcu_read_lock(&srcu); - hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist) { + hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist, + srcu_read_lock_held(&srcu)) { const struct mmu_notifier_ops *ops = subscription->ops; if (ops->invalidate_range_start) { @@ -528,7 +534,8 @@ mn_hlist_invalidate_end(struct mmu_notifier_subscriptions *subscriptions, int id; id = srcu_read_lock(&srcu); - hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist) { + hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist, + srcu_read_lock_held(&srcu)) { /* * Call invalidate_range here too to avoid the need for the * subsystem of having to register an invalidate_range_end @@ -582,7 +589,8 @@ void __mmu_notifier_invalidate_range(struct mm_struct *mm, id = srcu_read_lock(&srcu); hlist_for_each_entry_rcu(subscription, - &mm->notifier_subscriptions->list, hlist) { + &mm->notifier_subscriptions->list, hlist, + srcu_read_lock_held(&srcu)) { if (subscription->ops->invalidate_range) subscription->ops->invalidate_range(subscription, mm, start, end); @@ -714,7 +722,8 @@ find_get_mmu_notifier(struct mm_struct *mm, const struct mmu_notifier_ops *ops) spin_lock(&mm->notifier_subscriptions->lock); hlist_for_each_entry_rcu(subscription, - &mm->notifier_subscriptions->list, hlist) { + &mm->notifier_subscriptions->list, hlist, + lockdep_is_held(&mm->notifier_subscriptions->lock)) { if (subscription->ops != ops) continue; diff --git a/mm/mprotect.c b/mm/mprotect.c index 7a8e84f86831b4e4f2a8cdf535bf48fb9990979e..311c0dadf71c9f5eb51b4d2004028fe0fe9cc4d8 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -161,6 +161,31 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, return pages; } +/* + * Used when setting automatic NUMA hinting protection where it is + * critical that a numa hinting PMD is not confused with a bad PMD. + */ +static inline int pmd_none_or_clear_bad_unless_trans_huge(pmd_t *pmd) +{ + pmd_t pmdval = pmd_read_atomic(pmd); + + /* See pmd_none_or_trans_huge_or_clear_bad for info on barrier */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + barrier(); +#endif + + if (pmd_none(pmdval)) + return 1; + if (pmd_trans_huge(pmdval)) + return 0; + if (unlikely(pmd_bad(pmdval))) { + pmd_clear_bad(pmd); + return 1; + } + + return 0; +} + static inline unsigned long change_pmd_range(struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, pgprot_t newprot, int dirty_accountable, int prot_numa) @@ -178,8 +203,17 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, unsigned long this_pages; next = pmd_addr_end(addr, end); - if (!is_swap_pmd(*pmd) && !pmd_trans_huge(*pmd) && !pmd_devmap(*pmd) - && pmd_none_or_clear_bad(pmd)) + + /* + * Automatic NUMA balancing walks the tables with mmap_sem + * held for read. It's possible a parallel update to occur + * between pmd_trans_huge() and a pmd_none_or_clear_bad() + * check leading to a false positive and clearing. + * Hence, it's necessary to atomically read the PMD value + * for all the checks. + */ + if (!is_swap_pmd(*pmd) && !pmd_devmap(*pmd) && + pmd_none_or_clear_bad_unless_trans_huge(pmd)) goto next; /* invoke the mmu notifier if the pmd is populated */ diff --git a/mm/mremap.c b/mm/mremap.c index 122938dcec15c9a8359d62ceec5801bd74177b3f..af363063ea23bc45430bf5658ca526dd7e053cb7 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -607,7 +607,6 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, LIST_HEAD(uf_unmap); addr = untagged_addr(addr); - new_addr = untagged_addr(new_addr); if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE)) return ret; diff --git a/mm/nommu.c b/mm/nommu.c index bd2b4e5ef14457eab36c1905ee558eea5e33f213..318df4e236c99003e81880e8619c111a3138dcdf 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -370,10 +370,14 @@ void vm_unmap_aliases(void) EXPORT_SYMBOL_GPL(vm_unmap_aliases); /* - * Implement a stub for vmalloc_sync_all() if the architecture chose not to - * have one. + * Implement a stub for vmalloc_sync_[un]mapping() if the architecture + * chose not to have one. */ -void __weak vmalloc_sync_all(void) +void __weak vmalloc_sync_mappings(void) +{ +} + +void __weak vmalloc_sync_unmappings(void) { } diff --git a/mm/shmem.c b/mm/shmem.c index c8f7540ef048ebc5b425ed640999acf361819cd7..aad3ba74b0e9d121bd774e795460d5f2f73ac119 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -3386,8 +3386,6 @@ static const struct constant_table shmem_param_enums_huge[] = { {"always", SHMEM_HUGE_ALWAYS }, {"within_size", SHMEM_HUGE_WITHIN_SIZE }, {"advise", SHMEM_HUGE_ADVISE }, - {"deny", SHMEM_HUGE_DENY }, - {"force", SHMEM_HUGE_FORCE }, {} }; diff --git a/mm/slub.c b/mm/slub.c index 17dc00e33115b73736bfb687a271e7539464b20a..6589b41d5a6056013a2f31270ad21476bcecb477 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1973,8 +1973,6 @@ static void *get_partial(struct kmem_cache *s, gfp_t flags, int node, if (node == NUMA_NO_NODE) searchnode = numa_mem_id(); - else if (!node_present_pages(node)) - searchnode = node_to_mem_node(node); object = get_partial_node(s, get_node(s, searchnode), c, flags); if (object || node != NUMA_NO_NODE) @@ -2563,17 +2561,27 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, struct page *page; page = c->page; - if (!page) + if (!page) { + /* + * if the node is not online or has no normal memory, just + * ignore the node constraint + */ + if (unlikely(node != NUMA_NO_NODE && + !node_state(node, N_NORMAL_MEMORY))) + node = NUMA_NO_NODE; goto new_slab; + } redo: if (unlikely(!node_match(page, node))) { - int searchnode = node; - - if (node != NUMA_NO_NODE && !node_present_pages(node)) - searchnode = node_to_mem_node(node); - - if (unlikely(!node_match(page, searchnode))) { + /* + * same as above but node_match() being false already + * implies node != NUMA_NO_NODE + */ + if (!node_state(node, N_NORMAL_MEMORY)) { + node = NUMA_NO_NODE; + goto redo; + } else { stat(s, ALLOC_NODE_MISMATCH); deactivate_slab(s, page, c->freelist, c); goto new_slab; @@ -2997,11 +3005,13 @@ static __always_inline void do_slab_free(struct kmem_cache *s, barrier(); if (likely(page == c->page)) { - set_freepointer(s, tail_obj, c->freelist); + void **freelist = READ_ONCE(c->freelist); + + set_freepointer(s, tail_obj, freelist); if (unlikely(!this_cpu_cmpxchg_double( s->cpu_slab->freelist, s->cpu_slab->tid, - c->freelist, tid, + freelist, tid, head, next_tid(tid)))) { note_cmpxchg_failure("slab_free", s, tid); @@ -3174,6 +3184,15 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, void *object = c->freelist; if (unlikely(!object)) { + /* + * We may have removed an object from c->freelist using + * the fastpath in the previous iteration; in that case, + * c->tid has not been bumped yet. + * Since ___slab_alloc() may reenable interrupts while + * allocating memory, we should bump c->tid now. + */ + c->tid = next_tid(c->tid); + /* * Invoking slow path likely have side-effect * of re-populating per CPU c->freelist diff --git a/mm/sparse.c b/mm/sparse.c index c184b69460b7bd53198a5e31cfd56bf39b0016e5..aadb7298dcefda4b6212e9b47c2ec36db4cea605 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -734,6 +734,7 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages, struct mem_section *ms = __pfn_to_section(pfn); bool section_is_early = early_section(ms); struct page *memmap = NULL; + bool empty; unsigned long *subsection_map = ms->usage ? &ms->usage->subsection_map[0] : NULL; @@ -764,7 +765,8 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages, * For 2/ and 3/ the SPARSEMEM_VMEMMAP={y,n} cases are unified */ bitmap_xor(subsection_map, map, subsection_map, SUBSECTIONS_PER_SECTION); - if (bitmap_empty(subsection_map, SUBSECTIONS_PER_SECTION)) { + empty = bitmap_empty(subsection_map, SUBSECTIONS_PER_SECTION); + if (empty) { unsigned long section_nr = pfn_to_section_nr(pfn); /* @@ -779,13 +781,15 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages, ms->usage = NULL; } memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr); - ms->section_mem_map = (unsigned long)NULL; } if (section_is_early && memmap) free_map_bootmem(memmap); else depopulate_section_memmap(pfn, nr_pages, altmap); + + if (empty) + ms->section_mem_map = (unsigned long)NULL; } static struct page * __meminit section_activate(int nid, unsigned long pfn, @@ -876,7 +880,7 @@ int __meminit sparse_add_section(int nid, unsigned long start_pfn, * Poison uninitialized struct pages in order to catch invalid flags * combinations. */ - page_init_poison(pfn_to_page(start_pfn), sizeof(struct page) * nr_pages); + page_init_poison(memmap, sizeof(struct page) * nr_pages); ms = __nr_to_section(section_nr); set_section_nid(section_nr, nid); diff --git a/mm/swapfile.c b/mm/swapfile.c index 2c33ff456ed5e228510e02becb6e722f6e6603f0..b2a2e45c9a36f15dee49301aabb9343fe76c36cd 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -3157,7 +3157,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) mapping = swap_file->f_mapping; inode = mapping->host; - /* If S_ISREG(inode->i_mode) will do inode_lock(inode); */ + /* will take i_rwsem; */ error = claim_swapfile(p, inode); if (unlikely(error)) goto bad_swap; diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 1f46c3b86f9f7ded21837f7a3e26e6072af46b98..6b8eeb0ecee518a46c1a62c8b884ec9be56e89b7 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1295,7 +1295,7 @@ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end) * First make sure the mappings are removed from all page-tables * before they are freed. */ - vmalloc_sync_all(); + vmalloc_sync_unmappings(); /* * TODO: to calculate a flush range without looping. @@ -3128,16 +3128,19 @@ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, EXPORT_SYMBOL(remap_vmalloc_range); /* - * Implement a stub for vmalloc_sync_all() if the architecture chose not to - * have one. + * Implement stubs for vmalloc_sync_[un]mappings () if the architecture chose + * not to have one. * * The purpose of this function is to make sure the vmalloc area * mappings are identical in all page-tables in the system. */ -void __weak vmalloc_sync_all(void) +void __weak vmalloc_sync_mappings(void) { } +void __weak vmalloc_sync_unmappings(void) +{ +} static int f(pte_t *pte, unsigned long addr, void *data) { diff --git a/mm/vmscan.c b/mm/vmscan.c index c05eb9efec07f369296756dbd035ed4e59961b98..876370565455e275828d8cde8e8f9cd1819fd759 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2415,10 +2415,13 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, /* * Scan types proportional to swappiness and * their relative recent reclaim efficiency. - * Make sure we don't miss the last page - * because of a round-off error. + * Make sure we don't miss the last page on + * the offlined memory cgroups because of a + * round-off error. */ - scan = DIV64_U64_ROUND_UP(scan * fraction[file], + scan = mem_cgroup_online(memcg) ? + div64_u64(scan * fraction[file], denominator) : + DIV64_U64_ROUND_UP(scan * fraction[file], denominator); break; case SCAN_FILE: diff --git a/mm/z3fold.c b/mm/z3fold.c index 43754d8ebce8fc941cc809afbb89bace1c907657..42f31c4b53ad43e4204874fb20d3d901d9ef921a 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -41,7 +41,6 @@ #include #include #include -#include #include #include diff --git a/net/Kconfig b/net/Kconfig index b0937a700f018323e5b1e8f0421ee42c825a02d7..2eeb0e55f7c9342dc45f9eb99d438988e1a625dc 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -189,7 +189,6 @@ config BRIDGE_NETFILTER depends on NETFILTER_ADVANCED select NETFILTER_FAMILY_BRIDGE select SKB_EXTENSIONS - default m ---help--- Enabling this option will let arptables resp. iptables see bridged ARP resp. IP traffic. If you want a bridging firewall, you probably diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index f0209505e41ae1a4bba6989dc571906dc46f432d..a7c8dd7ae51314f3fd729484300b0796238a87c8 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -789,6 +789,10 @@ static void batadv_iv_ogm_schedule_buff(struct batadv_hard_iface *hard_iface) lockdep_assert_held(&hard_iface->bat_iv.ogm_buff_mutex); + /* interface already disabled by batadv_iv_ogm_iface_disable */ + if (!*ogm_buff) + return; + /* the interface gets activated here to avoid race conditions between * the moment of activating the interface in * hardif_activate_interface() where the originator mac is set and diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index dc3d2c1dd9d54ca0a2a9a888b53996bb844b03f9..0e3dbc5f3c34f83203ffafcb944a89fed8043b25 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -34,7 +34,6 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) const struct nf_br_ops *nf_ops; u8 state = BR_STATE_FORWARDING; const unsigned char *dest; - struct ethhdr *eth; u16 vid = 0; rcu_read_lock(); @@ -54,15 +53,14 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) BR_INPUT_SKB_CB(skb)->frag_max_size = 0; skb_reset_mac_header(skb); - eth = eth_hdr(skb); skb_pull(skb, ETH_HLEN); if (!br_allowed_ingress(br, br_vlan_group_rcu(br), skb, &vid, &state)) goto out; if (IS_ENABLED(CONFIG_INET) && - (eth->h_proto == htons(ETH_P_ARP) || - eth->h_proto == htons(ETH_P_RARP)) && + (eth_hdr(skb)->h_proto == htons(ETH_P_ARP) || + eth_hdr(skb)->h_proto == htons(ETH_P_RARP)) && br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED)) { br_do_proxy_suppress_arp(skb, br, vid, NULL); } else if (IS_ENABLED(CONFIG_IPV6) && diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index 6856a6d9282b830fce00cce256d671c17c08638f..1f14b84553457053479d2019f2ec9d8e6e2c41b1 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -63,7 +63,8 @@ struct net_bridge_port *br_get_port(struct net_bridge *br, u16 port_no) { struct net_bridge_port *p; - list_for_each_entry_rcu(p, &br->port_list, list) { + list_for_each_entry_rcu(p, &br->port_list, list, + lockdep_is_held(&br->lock)) { if (p->port_no == port_no) return p; } diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index 03c7cdd8e4cbfcfcbb9a1c66cae3f6803bde24a9..195d2d67be8a3043c48027a0a6e897660bd74072 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -112,7 +112,8 @@ static struct caif_device_entry *caif_get(struct net_device *dev) caif_device_list(dev_net(dev)); struct caif_device_entry *caifd; - list_for_each_entry_rcu(caifd, &caifdevs->list, list) { + list_for_each_entry_rcu(caifd, &caifdevs->list, list, + lockdep_rtnl_is_held()) { if (caifd->netdev == dev) return caifd; } diff --git a/net/core/dev.c b/net/core/dev.c index a69e8bd7ed74f1c8c34eab5ffa792e4096761072..c6c985fe7b1bcf784cedde2b2a86e26356471bee 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -146,7 +146,6 @@ #include "net-sysfs.h" #define MAX_GRO_SKBS 8 -#define MAX_NEST_DEV 8 /* This should be increased if a protocol with a bigger head is added. */ #define GRO_MAX_HEAD (MAX_HEADER + 128) @@ -331,6 +330,12 @@ int netdev_name_node_alt_destroy(struct net_device *dev, const char *name) name_node = netdev_name_node_lookup(net, name); if (!name_node) return -ENOENT; + /* lookup might have found our primary name or a name belonging + * to another device. + */ + if (name_node == dev->name_node || name_node->dev != dev) + return -EINVAL; + __netdev_name_node_alt_destroy(name_node); return 0; @@ -3071,6 +3076,8 @@ static u16 skb_tx_hash(const struct net_device *dev, if (skb_rx_queue_recorded(skb)) { hash = skb_get_rx_queue(skb); + if (hash >= qoffset) + hash -= qoffset; while (unlikely(hash >= qcount)) hash -= qcount; return hash + qoffset; @@ -3657,26 +3664,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, qdisc_calculate_pkt_len(skb, q); if (q->flags & TCQ_F_NOLOCK) { - if ((q->flags & TCQ_F_CAN_BYPASS) && READ_ONCE(q->empty) && - qdisc_run_begin(q)) { - if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, - &q->state))) { - __qdisc_drop(skb, &to_free); - rc = NET_XMIT_DROP; - goto end_run; - } - qdisc_bstats_cpu_update(q, skb); - - rc = NET_XMIT_SUCCESS; - if (sch_direct_xmit(skb, q, dev, txq, NULL, true)) - __qdisc_run(q); - -end_run: - qdisc_run_end(q); - } else { - rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; - qdisc_run(q); - } + rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; + qdisc_run(q); if (unlikely(to_free)) kfree_skb_list(to_free); @@ -4527,14 +4516,14 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, /* Reinjected packets coming from act_mirred or similar should * not get XDP generic processing. */ - if (skb_cloned(skb) || skb_is_tc_redirected(skb)) + if (skb_is_tc_redirected(skb)) return XDP_PASS; /* XDP packets must be linear and must have sufficient headroom * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also * native XDP provides, thus we need to do it here as well. */ - if (skb_is_nonlinear(skb) || + if (skb_cloned(skb) || skb_is_nonlinear(skb) || skb_headroom(skb) < XDP_PACKET_HEADROOM) { int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb); int troom = skb->tail + skb->data_len - skb->end; @@ -7201,8 +7190,8 @@ static int __netdev_walk_all_lower_dev(struct net_device *dev, return 0; } -static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, - struct list_head **iter) +struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, + struct list_head **iter) { struct netdev_adjacent *lower; @@ -7214,6 +7203,7 @@ static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, return lower->dev; } +EXPORT_SYMBOL(netdev_next_lower_dev_rcu); static u8 __netdev_upper_depth(struct net_device *dev) { diff --git a/net/core/devlink.c b/net/core/devlink.c index 549ee56b7a21b72a9d721c66f04c667db12b822a..b831c5545d6a95d049db968418d7d8ff6cb81767 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -2103,11 +2103,11 @@ static int devlink_dpipe_entry_put(struct sk_buff *skb, static struct devlink_dpipe_table * devlink_dpipe_table_find(struct list_head *dpipe_tables, - const char *table_name) + const char *table_name, struct devlink *devlink) { struct devlink_dpipe_table *table; - - list_for_each_entry_rcu(table, dpipe_tables, list) { + list_for_each_entry_rcu(table, dpipe_tables, list, + lockdep_is_held(&devlink->lock)) { if (!strcmp(table->name, table_name)) return table; } @@ -2226,7 +2226,7 @@ static int devlink_nl_cmd_dpipe_entries_get(struct sk_buff *skb, table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]); table = devlink_dpipe_table_find(&devlink->dpipe_table_list, - table_name); + table_name, devlink); if (!table) return -EINVAL; @@ -2382,7 +2382,7 @@ static int devlink_dpipe_table_counters_set(struct devlink *devlink, struct devlink_dpipe_table *table; table = devlink_dpipe_table_find(&devlink->dpipe_table_list, - table_name); + table_name, devlink); if (!table) return -EINVAL; @@ -3352,34 +3352,41 @@ devlink_param_value_get_from_info(const struct devlink_param *param, struct genl_info *info, union devlink_param_value *value) { + struct nlattr *param_data; int len; - if (param->type != DEVLINK_PARAM_TYPE_BOOL && - !info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]) + param_data = info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]; + + if (param->type != DEVLINK_PARAM_TYPE_BOOL && !param_data) return -EINVAL; switch (param->type) { case DEVLINK_PARAM_TYPE_U8: - value->vu8 = nla_get_u8(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]); + if (nla_len(param_data) != sizeof(u8)) + return -EINVAL; + value->vu8 = nla_get_u8(param_data); break; case DEVLINK_PARAM_TYPE_U16: - value->vu16 = nla_get_u16(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]); + if (nla_len(param_data) != sizeof(u16)) + return -EINVAL; + value->vu16 = nla_get_u16(param_data); break; case DEVLINK_PARAM_TYPE_U32: - value->vu32 = nla_get_u32(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]); + if (nla_len(param_data) != sizeof(u32)) + return -EINVAL; + value->vu32 = nla_get_u32(param_data); break; case DEVLINK_PARAM_TYPE_STRING: - len = strnlen(nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]), - nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA])); - if (len == nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]) || + len = strnlen(nla_data(param_data), nla_len(param_data)); + if (len == nla_len(param_data) || len >= __DEVLINK_PARAM_MAX_STRING_VALUE) return -EINVAL; - strcpy(value->vstr, - nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA])); + strcpy(value->vstr, nla_data(param_data)); break; case DEVLINK_PARAM_TYPE_BOOL: - value->vbool = info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA] ? - true : false; + if (param_data && nla_len(param_data)) + return -EINVAL; + value->vbool = nla_get_flag(param_data); break; } return 0; @@ -5951,6 +5958,8 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_PARAM_VALUE_CMODE] = { .type = NLA_U8 }, [DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32 }, + [DEVLINK_ATTR_REGION_CHUNK_ADDR] = { .type = NLA_U64 }, + [DEVLINK_ATTR_REGION_CHUNK_LEN] = { .type = NLA_U64 }, [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] = { .type = NLA_U64 }, [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .type = NLA_U8 }, @@ -6854,7 +6863,7 @@ bool devlink_dpipe_table_counter_enabled(struct devlink *devlink, rcu_read_lock(); table = devlink_dpipe_table_find(&devlink->dpipe_table_list, - table_name); + table_name, devlink); enabled = false; if (table) enabled = table->counters_enabled; @@ -6878,26 +6887,34 @@ int devlink_dpipe_table_register(struct devlink *devlink, void *priv, bool counter_control_extern) { struct devlink_dpipe_table *table; - - if (devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name)) - return -EEXIST; + int err = 0; if (WARN_ON(!table_ops->size_get)) return -EINVAL; + mutex_lock(&devlink->lock); + + if (devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name, + devlink)) { + err = -EEXIST; + goto unlock; + } + table = kzalloc(sizeof(*table), GFP_KERNEL); - if (!table) - return -ENOMEM; + if (!table) { + err = -ENOMEM; + goto unlock; + } table->name = table_name; table->table_ops = table_ops; table->priv = priv; table->counter_control_extern = counter_control_extern; - mutex_lock(&devlink->lock); list_add_tail_rcu(&table->list, &devlink->dpipe_table_list); +unlock: mutex_unlock(&devlink->lock); - return 0; + return err; } EXPORT_SYMBOL_GPL(devlink_dpipe_table_register); @@ -6914,7 +6931,7 @@ void devlink_dpipe_table_unregister(struct devlink *devlink, mutex_lock(&devlink->lock); table = devlink_dpipe_table_find(&devlink->dpipe_table_list, - table_name); + table_name, devlink); if (!table) goto unlock; list_del_rcu(&table->list); @@ -7071,7 +7088,7 @@ int devlink_dpipe_table_resource_set(struct devlink *devlink, mutex_lock(&devlink->lock); table = devlink_dpipe_table_find(&devlink->dpipe_table_list, - table_name); + table_name, devlink); if (!table) { err = -EINVAL; goto out; diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 3e7e15278c46847e9d6d25ad960d015fbaa8b6fa..bd7eba9066f8d6b39d04be38611535f238bf5cd0 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -974,7 +974,7 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, frh = nlmsg_data(nlh); frh->family = ops->family; - frh->table = rule->table; + frh->table = rule->table < 256 ? rule->table : RT_TABLE_COMPAT; if (nla_put_u32(skb, FRA_TABLE, rule->table)) goto nla_put_failure; if (nla_put_u32(skb, FRA_SUPPRESS_PREFIXLEN, rule->suppress_prefixlen)) diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c index 0642f91c4038d5b97b3820c3a16669583177fc0b..b4c87fe31be2e860db70a9840ce88d8c82fe2efb 100644 --- a/net/core/netclassid_cgroup.c +++ b/net/core/netclassid_cgroup.c @@ -53,30 +53,60 @@ static void cgrp_css_free(struct cgroup_subsys_state *css) kfree(css_cls_state(css)); } +/* + * To avoid freezing of sockets creation for tasks with big number of threads + * and opened sockets lets release file_lock every 1000 iterated descriptors. + * New sockets will already have been created with new classid. + */ + +struct update_classid_context { + u32 classid; + unsigned int batch; +}; + +#define UPDATE_CLASSID_BATCH 1000 + static int update_classid_sock(const void *v, struct file *file, unsigned n) { int err; + struct update_classid_context *ctx = (void *)v; struct socket *sock = sock_from_file(file, &err); if (sock) { spin_lock(&cgroup_sk_update_lock); - sock_cgroup_set_classid(&sock->sk->sk_cgrp_data, - (unsigned long)v); + sock_cgroup_set_classid(&sock->sk->sk_cgrp_data, ctx->classid); spin_unlock(&cgroup_sk_update_lock); } + if (--ctx->batch == 0) { + ctx->batch = UPDATE_CLASSID_BATCH; + return n + 1; + } return 0; } +static void update_classid_task(struct task_struct *p, u32 classid) +{ + struct update_classid_context ctx = { + .classid = classid, + .batch = UPDATE_CLASSID_BATCH + }; + unsigned int fd = 0; + + do { + task_lock(p); + fd = iterate_fd(p->files, fd, update_classid_sock, &ctx); + task_unlock(p); + cond_resched(); + } while (fd); +} + static void cgrp_attach(struct cgroup_taskset *tset) { struct cgroup_subsys_state *css; struct task_struct *p; cgroup_taskset_for_each(p, css, tset) { - task_lock(p); - iterate_fd(p->files, 0, update_classid_sock, - (void *)(unsigned long)css_cls_state(css)->classid); - task_unlock(p); + update_classid_task(p, css_cls_state(css)->classid); } } @@ -98,10 +128,7 @@ static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft, css_task_iter_start(css, 0, &it); while ((p = css_task_iter_next(&it))) { - task_lock(p); - iterate_fd(p->files, 0, update_classid_sock, - (void *)(unsigned long)cs->classid); - task_unlock(p); + update_classid_task(p, cs->classid); cond_resched(); } css_task_iter_end(&it); diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 9b7cbe35df37d30bdfdd50819a8c30dee66e6e7d..10d2b255df5eccade8feb8f73d8fc657b604e9a4 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -99,8 +99,7 @@ EXPORT_SYMBOL(page_pool_create); static void __page_pool_return_page(struct page_pool *pool, struct page *page); noinline -static struct page *page_pool_refill_alloc_cache(struct page_pool *pool, - bool refill) +static struct page *page_pool_refill_alloc_cache(struct page_pool *pool) { struct ptr_ring *r = &pool->ring; struct page *page; @@ -141,8 +140,7 @@ static struct page *page_pool_refill_alloc_cache(struct page_pool *pool, page = NULL; break; } - } while (pool->alloc.count < PP_ALLOC_CACHE_REFILL && - refill); + } while (pool->alloc.count < PP_ALLOC_CACHE_REFILL); /* Return last page */ if (likely(pool->alloc.count > 0)) @@ -155,20 +153,16 @@ static struct page *page_pool_refill_alloc_cache(struct page_pool *pool, /* fast path */ static struct page *__page_pool_get_cached(struct page_pool *pool) { - bool refill = false; struct page *page; - /* Test for safe-context, caller should provide this guarantee */ - if (likely(in_serving_softirq())) { - if (likely(pool->alloc.count)) { - /* Fast-path */ - page = pool->alloc.cache[--pool->alloc.count]; - return page; - } - refill = true; + /* Caller MUST guarantee safe non-concurrent access, e.g. softirq */ + if (likely(pool->alloc.count)) { + /* Fast-path */ + page = pool->alloc.cache[--pool->alloc.count]; + } else { + page = page_pool_refill_alloc_cache(pool); } - page = page_pool_refill_alloc_cache(pool, refill); return page; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 09c44bf2e1d28842d77b4ed442ef2c051a25ad21..e1152f4ffe33efb0a69f17a1f5940baa04942e5b 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3504,27 +3504,25 @@ static int rtnl_alt_ifname(int cmd, struct net_device *dev, struct nlattr *attr, if (err) return err; - alt_ifname = nla_data(attr); + alt_ifname = nla_strdup(attr, GFP_KERNEL); + if (!alt_ifname) + return -ENOMEM; + if (cmd == RTM_NEWLINKPROP) { - alt_ifname = kstrdup(alt_ifname, GFP_KERNEL); - if (!alt_ifname) - return -ENOMEM; err = netdev_name_node_alt_create(dev, alt_ifname); - if (err) { - kfree(alt_ifname); - return err; - } + if (!err) + alt_ifname = NULL; } else if (cmd == RTM_DELLINKPROP) { err = netdev_name_node_alt_destroy(dev, alt_ifname); - if (err) - return err; } else { - WARN_ON(1); - return 0; + WARN_ON_ONCE(1); + err = -EINVAL; } - *changed = true; - return 0; + kfree(alt_ifname); + if (!err) + *changed = true; + return err; } static int rtnl_linkprop(int cmd, struct sk_buff *skb, struct nlmsghdr *nlh, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 864cb9e9622f539c14fdeeffd597a6b697e84d26..e1101a4f90a6353038fac59de8a193c91c7d8874 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -467,7 +467,6 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, return NULL; } - /* use OR instead of assignment to avoid clearing of bits in mask */ if (pfmemalloc) skb->pfmemalloc = 1; skb->head_frag = 1; @@ -527,7 +526,6 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, return NULL; } - /* use OR instead of assignment to avoid clearing of bits in mask */ if (nc->page.pfmemalloc) skb->pfmemalloc = 1; skb->head_frag = 1; @@ -4805,9 +4803,9 @@ static __sum16 *skb_checksum_setup_ip(struct sk_buff *skb, typeof(IPPROTO_IP) proto, unsigned int off) { - switch (proto) { - int err; + int err; + switch (proto) { case IPPROTO_TCP: err = skb_maybe_pull_tail(skb, off + sizeof(struct tcphdr), off + MAX_TCP_HDR_LEN); diff --git a/net/core/sock.c b/net/core/sock.c index a4c8fac781ff3ceba7fb6c85f636e18a0de66891..8f71684305c398195a1c18e2c12d0f26b440adbb 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1830,7 +1830,10 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) atomic_set(&newsk->sk_zckey, 0); sock_reset_flag(newsk, SOCK_DONE); - mem_cgroup_sk_alloc(newsk); + + /* sk->sk_memcg will be populated at accept() time */ + newsk->sk_memcg = NULL; + cgroup_sk_alloc(&newsk->sk_cgrp_data); rcu_read_lock(); diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index a7662e7a691d385d3f493d9e7814560e51a2b76a..760e6ea3178a7e34b787c33660aa66aa8c0cb384 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -117,7 +117,9 @@ static inline struct net_device *dsa_master_find_slave(struct net_device *dev, /* port.c */ int dsa_port_set_state(struct dsa_port *dp, u8 state, struct switchdev_trans *trans); +int dsa_port_enable_rt(struct dsa_port *dp, struct phy_device *phy); int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy); +void dsa_port_disable_rt(struct dsa_port *dp); void dsa_port_disable(struct dsa_port *dp); int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br); void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br); diff --git a/net/dsa/port.c b/net/dsa/port.c index 774facb8d54754e13765611ebc0c421906de674d..ec13dc6667884f154c1fd76c823d11894860d11e 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -63,7 +63,7 @@ static void dsa_port_set_state_now(struct dsa_port *dp, u8 state) pr_err("DSA: failed to set STP state %u (%d)\n", state, err); } -int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy) +int dsa_port_enable_rt(struct dsa_port *dp, struct phy_device *phy) { struct dsa_switch *ds = dp->ds; int port = dp->index; @@ -78,14 +78,31 @@ int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy) if (!dp->bridge_dev) dsa_port_set_state_now(dp, BR_STATE_FORWARDING); + if (dp->pl) + phylink_start(dp->pl); + return 0; } -void dsa_port_disable(struct dsa_port *dp) +int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy) +{ + int err; + + rtnl_lock(); + err = dsa_port_enable_rt(dp, phy); + rtnl_unlock(); + + return err; +} + +void dsa_port_disable_rt(struct dsa_port *dp) { struct dsa_switch *ds = dp->ds; int port = dp->index; + if (dp->pl) + phylink_stop(dp->pl); + if (!dp->bridge_dev) dsa_port_set_state_now(dp, BR_STATE_DISABLED); @@ -93,6 +110,13 @@ void dsa_port_disable(struct dsa_port *dp) ds->ops->port_disable(ds, port); } +void dsa_port_disable(struct dsa_port *dp) +{ + rtnl_lock(); + dsa_port_disable_rt(dp); + rtnl_unlock(); +} + int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br) { struct dsa_notifier_bridge_info info = { @@ -614,10 +638,6 @@ static int dsa_port_phylink_register(struct dsa_port *dp) goto err_phy_connect; } - rtnl_lock(); - phylink_start(dp->pl); - rtnl_unlock(); - return 0; err_phy_connect: @@ -628,9 +648,14 @@ static int dsa_port_phylink_register(struct dsa_port *dp) int dsa_port_link_register_of(struct dsa_port *dp) { struct dsa_switch *ds = dp->ds; + struct device_node *phy_np; - if (!ds->ops->adjust_link) - return dsa_port_phylink_register(dp); + if (!ds->ops->adjust_link) { + phy_np = of_parse_phandle(dp->dn, "phy-handle", 0); + if (of_phy_is_fixed_link(dp->dn) || phy_np) + return dsa_port_phylink_register(dp); + return 0; + } dev_warn(ds->dev, "Using legacy PHYLIB callbacks. Please migrate to PHYLINK!\n"); @@ -645,11 +670,12 @@ void dsa_port_link_unregister_of(struct dsa_port *dp) { struct dsa_switch *ds = dp->ds; - if (!ds->ops->adjust_link) { + if (!ds->ops->adjust_link && dp->pl) { rtnl_lock(); phylink_disconnect_phy(dp->pl); rtnl_unlock(); phylink_destroy(dp->pl); + dp->pl = NULL; return; } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 088c886e609ee78d15aa139aad469471b833e057..ddc0f9236928891ffbb2f417df66ef4daf4950d6 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -88,12 +88,10 @@ static int dsa_slave_open(struct net_device *dev) goto clear_allmulti; } - err = dsa_port_enable(dp, dev->phydev); + err = dsa_port_enable_rt(dp, dev->phydev); if (err) goto clear_promisc; - phylink_start(dp->pl); - return 0; clear_promisc: @@ -114,9 +112,7 @@ static int dsa_slave_close(struct net_device *dev) struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); - phylink_stop(dp->pl); - - dsa_port_disable(dp); + dsa_port_disable_rt(dp); dev_mc_unsync(master, dev); dev_uc_unsync(master, dev); diff --git a/net/dsa/tag_ar9331.c b/net/dsa/tag_ar9331.c index 466ffa92a4746f0ac0b2860d5af68f3399c35054..55b00694cdba1e75154f4b0f6af0e2f0a14fe9af 100644 --- a/net/dsa/tag_ar9331.c +++ b/net/dsa/tag_ar9331.c @@ -31,7 +31,7 @@ static struct sk_buff *ar9331_tag_xmit(struct sk_buff *skb, __le16 *phdr; u16 hdr; - if (skb_cow_head(skb, 0) < 0) + if (skb_cow_head(skb, AR9331_HDR_LEN) < 0) return NULL; phdr = skb_push(skb, AR9331_HDR_LEN); diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c index c8a128c9e5e0f6c8ab048ae6f90aa12e1087cdd6..70db7c909f74efeec7d3b4aa2812fab118bcff3c 100644 --- a/net/dsa/tag_qca.c +++ b/net/dsa/tag_qca.c @@ -33,7 +33,7 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev) struct dsa_port *dp = dsa_slave_to_port(dev); u16 *phdr, hdr; - if (skb_cow_head(skb, 0) < 0) + if (skb_cow_head(skb, QCA_HDR_LEN) < 0) return NULL; skb_push(skb, QCA_HDR_LEN); diff --git a/net/ethtool/bitset.c b/net/ethtool/bitset.c index fce45dac42056b26a61ca71d527dfb70e3d16b33..ef9197541cb3ba4eadb65aa453df0d29a07747b2 100644 --- a/net/ethtool/bitset.c +++ b/net/ethtool/bitset.c @@ -305,7 +305,8 @@ int ethnl_put_bitset32(struct sk_buff *skb, int attrtype, const u32 *val, static const struct nla_policy bitset_policy[ETHTOOL_A_BITSET_MAX + 1] = { [ETHTOOL_A_BITSET_UNSPEC] = { .type = NLA_REJECT }, [ETHTOOL_A_BITSET_NOMASK] = { .type = NLA_FLAG }, - [ETHTOOL_A_BITSET_SIZE] = { .type = NLA_U32 }, + [ETHTOOL_A_BITSET_SIZE] = NLA_POLICY_MAX(NLA_U32, + ETHNL_MAX_BITSET_SIZE), [ETHTOOL_A_BITSET_BITS] = { .type = NLA_NESTED }, [ETHTOOL_A_BITSET_VALUE] = { .type = NLA_BINARY }, [ETHTOOL_A_BITSET_MASK] = { .type = NLA_BINARY }, @@ -447,7 +448,10 @@ ethnl_update_bitset32_verbose(u32 *bitmap, unsigned int nbits, "mask only allowed in compact bitset"); return -EINVAL; } + no_mask = tb[ETHTOOL_A_BITSET_NOMASK]; + if (no_mask) + ethnl_bitmap32_clear(bitmap, 0, nbits, mod); nla_for_each_nested(bit_attr, tb[ETHTOOL_A_BITSET_BITS], rem) { bool old_val, new_val; diff --git a/net/ethtool/bitset.h b/net/ethtool/bitset.h index b8247e34109d0272a96dd3e261b9da473f0a306b..b849f9d1967699c017a1b3e201f4a2b1e33c166c 100644 --- a/net/ethtool/bitset.h +++ b/net/ethtool/bitset.h @@ -3,6 +3,8 @@ #ifndef _NET_ETHTOOL_BITSET_H #define _NET_ETHTOOL_BITSET_H +#define ETHNL_MAX_BITSET_SIZE S16_MAX + typedef const char (*const ethnl_string_array_t)[ETH_GSTRING_LEN]; int ethnl_bitset_is_compact(const struct nlattr *bitset, bool *compact); diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 364ea2cc028e9a0ccb1a9d409961943cae8e1b3f..3ba7f61be10784a6bb5c814dfe669c320edbc8dd 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -155,7 +155,8 @@ static struct hsr_node *hsr_add_node(struct hsr_priv *hsr, new_node->seq_out[i] = seq_out; spin_lock_bh(&hsr->list_lock); - list_for_each_entry_rcu(node, node_db, mac_list) { + list_for_each_entry_rcu(node, node_db, mac_list, + lockdep_is_held(&hsr->list_lock)) { if (ether_addr_equal(node->macaddress_A, addr)) goto out; if (ether_addr_equal(node->macaddress_B, addr)) diff --git a/net/ieee802154/nl_policy.c b/net/ieee802154/nl_policy.c index 2c7a38d76a3a6dbfcdb2f827e7fb0b8654850d96..0672b2f01586f195e1439610b3154b15282cdd2b 100644 --- a/net/ieee802154/nl_policy.c +++ b/net/ieee802154/nl_policy.c @@ -21,7 +21,13 @@ const struct nla_policy ieee802154_policy[IEEE802154_ATTR_MAX + 1] = { [IEEE802154_ATTR_HW_ADDR] = { .type = NLA_HW_ADDR, }, [IEEE802154_ATTR_PAN_ID] = { .type = NLA_U16, }, [IEEE802154_ATTR_CHANNEL] = { .type = NLA_U8, }, + [IEEE802154_ATTR_BCN_ORD] = { .type = NLA_U8, }, + [IEEE802154_ATTR_SF_ORD] = { .type = NLA_U8, }, + [IEEE802154_ATTR_PAN_COORD] = { .type = NLA_U8, }, + [IEEE802154_ATTR_BAT_EXT] = { .type = NLA_U8, }, + [IEEE802154_ATTR_COORD_REALIGN] = { .type = NLA_U8, }, [IEEE802154_ATTR_PAGE] = { .type = NLA_U8, }, + [IEEE802154_ATTR_DEV_TYPE] = { .type = NLA_U8, }, [IEEE802154_ATTR_COORD_SHORT_ADDR] = { .type = NLA_U16, }, [IEEE802154_ATTR_COORD_HW_ADDR] = { .type = NLA_HW_ADDR, }, [IEEE802154_ATTR_COORD_PAN_ID] = { .type = NLA_U16, }, diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 3768822159192b919f33e8174003369ca235cde1..0bd10a1f477fdfd6bdc8b6c4a14f132280faedcf 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1724,6 +1724,7 @@ void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway) { unsigned char optbuf[sizeof(struct ip_options) + 40]; struct ip_options *opt = (struct ip_options *)optbuf; + int res; if (ip_hdr(skb)->protocol == IPPROTO_ICMP || error != -EACCES) return; @@ -1735,7 +1736,11 @@ void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway) memset(opt, 0, sizeof(struct ip_options)); opt->optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr); - if (__ip_options_compile(dev_net(skb->dev), opt, skb, NULL)) + rcu_read_lock(); + res = __ip_options_compile(dev_net(skb->dev), opt, skb, NULL); + rcu_read_unlock(); + + if (res) return; if (gateway) diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c index 5fd6e8ed02b5d5c201ff8dc8cf31db3994fcdcf7..66fdbfe5447cdb93e06fe85d94646a6806401e98 100644 --- a/net/ipv4/gre_demux.c +++ b/net/ipv4/gre_demux.c @@ -56,7 +56,9 @@ int gre_del_protocol(const struct gre_protocol *proto, u8 version) } EXPORT_SYMBOL_GPL(gre_del_protocol); -/* Fills in tpi and returns header length to be pulled. */ +/* Fills in tpi and returns header length to be pulled. + * Note that caller must use pskb_may_pull() before pulling GRE header. + */ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, bool *csum_err, __be16 proto, int nhs) { @@ -110,8 +112,14 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header */ if (greh->flags == 0 && tpi->proto == htons(ETH_P_WCCP)) { + u8 _val, *val; + + val = skb_header_pointer(skb, nhs + hdr_len, + sizeof(_val), &_val); + if (!val) + return -EINVAL; tpi->proto = proto; - if ((*(u8 *)options & 0xF0) != 0x40) + if ((*val & 0xF0) != 0x40) hdr_len += 4; } tpi->hdr_len = hdr_len; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 18068ed42f258349a07248a85acdf93b8c2f1749..f369e7ce685b8374eae04d0ca0c5508463c5e72f 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -748,6 +748,39 @@ out:; } EXPORT_SYMBOL(__icmp_send); +#if IS_ENABLED(CONFIG_NF_NAT) +#include +void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info) +{ + struct sk_buff *cloned_skb = NULL; + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + __be32 orig_ip; + + ct = nf_ct_get(skb_in, &ctinfo); + if (!ct || !(ct->status & IPS_SRC_NAT)) { + icmp_send(skb_in, type, code, info); + return; + } + + if (skb_shared(skb_in)) + skb_in = cloned_skb = skb_clone(skb_in, GFP_ATOMIC); + + if (unlikely(!skb_in || skb_network_header(skb_in) < skb_in->head || + (skb_network_header(skb_in) + sizeof(struct iphdr)) > + skb_tail_pointer(skb_in) || skb_ensure_writable(skb_in, + skb_network_offset(skb_in) + sizeof(struct iphdr)))) + goto out; + + orig_ip = ip_hdr(skb_in)->saddr; + ip_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.ip; + icmp_send(skb_in, type, code, info); + ip_hdr(skb_in)->saddr = orig_ip; +out: + consume_skb(cloned_skb); +} +EXPORT_SYMBOL(icmp_ndo_send); +#endif static void icmp_socket_deliver(struct sk_buff *skb, u32 info) { diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index a4db79b1b64301c4d7d172f7c2673a30d4307196..d545fb99a8a1c84153c4a42226d15754c1f52ca0 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -482,8 +482,28 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern) } spin_unlock_bh(&queue->fastopenq.lock); } + out: release_sock(sk); + if (newsk && mem_cgroup_sockets_enabled) { + int amt; + + /* atomically get the memory usage, set and charge the + * newsk->sk_memcg. + */ + lock_sock(newsk); + + /* The socket has not been accepted yet, no need to look at + * newsk->sk_wmem_queued. + */ + amt = sk_mem_pages(newsk->sk_forward_alloc + + atomic_read(&newsk->sk_rmem_alloc)); + mem_cgroup_sk_alloc(newsk); + if (newsk->sk_memcg && amt) + mem_cgroup_charge_skmem(newsk->sk_memcg, amt); + + release_sock(newsk); + } if (req) reqsk_put(req); return newsk; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index f11e997e517b6652479acd892ffea6cdeb940e33..8c8377568a787c80540aac7e9ed6f122068010ca 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -100,13 +100,9 @@ static size_t inet_sk_attr_size(struct sock *sk, aux = handler->idiag_get_aux_size(sk, net_admin); return nla_total_size(sizeof(struct tcp_info)) - + nla_total_size(1) /* INET_DIAG_SHUTDOWN */ - + nla_total_size(1) /* INET_DIAG_TOS */ - + nla_total_size(1) /* INET_DIAG_TCLASS */ - + nla_total_size(4) /* INET_DIAG_MARK */ - + nla_total_size(4) /* INET_DIAG_CLASS_ID */ - + nla_total_size(sizeof(struct inet_diag_meminfo)) + nla_total_size(sizeof(struct inet_diag_msg)) + + inet_diag_msg_attrs_size() + + nla_total_size(sizeof(struct inet_diag_meminfo)) + nla_total_size(SK_MEMINFO_VARS * sizeof(u32)) + nla_total_size(TCP_CA_NAME_MAX) + nla_total_size(sizeof(struct tcpvegas_info)) @@ -147,6 +143,24 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, sk->sk_mark)) goto errout; + if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) || + ext & (1 << (INET_DIAG_TCLASS - 1))) { + u32 classid = 0; + +#ifdef CONFIG_SOCK_CGROUP_DATA + classid = sock_cgroup_classid(&sk->sk_cgrp_data); +#endif + /* Fallback to socket priority if class id isn't set. + * Classful qdiscs use it as direct reference to class. + * For cgroup2 classid is always zero. + */ + if (!classid) + classid = sk->sk_priority; + + if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid)) + goto errout; + } + r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk)); r->idiag_inode = sock_i_ino(sk); @@ -284,24 +298,6 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, goto errout; } - if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) || - ext & (1 << (INET_DIAG_TCLASS - 1))) { - u32 classid = 0; - -#ifdef CONFIG_SOCK_CGROUP_DATA - classid = sock_cgroup_classid(&sk->sk_cgrp_data); -#endif - /* Fallback to socket priority if class id isn't set. - * Classful qdiscs use it as direct reference to class. - * For cgroup2 classid is always zero. - */ - if (!classid) - classid = sk->sk_priority; - - if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid)) - goto errout; - } - out: nlmsg_end(skb, nlh); return 0; diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c index e35736b993003253614de79a6c83e4fd1a0a0a73..a93e7d1e125154e7afa0a7f162429a233de64a95 100644 --- a/net/ipv4/raw_diag.c +++ b/net/ipv4/raw_diag.c @@ -100,8 +100,9 @@ static int raw_diag_dump_one(struct sk_buff *in_skb, if (IS_ERR(sk)) return PTR_ERR(sk); - rep = nlmsg_new(sizeof(struct inet_diag_msg) + - sizeof(struct inet_diag_meminfo) + 64, + rep = nlmsg_new(nla_total_size(sizeof(struct inet_diag_msg)) + + inet_diag_msg_attrs_size() + + nla_total_size(sizeof(struct inet_diag_meminfo)) + 64, GFP_KERNEL); if (!rep) { sock_put(sk); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 316ebdf8151d6e836fcd68e6063ab3302fae779a..6b6b57000dad879996310717eeb016d2aad46541 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6124,7 +6124,11 @@ static void tcp_rcv_synrecv_state_fastopen(struct sock *sk) { struct request_sock *req; - tcp_try_undo_loss(sk, false); + /* If we are still handling the SYNACK RTO, see if timestamp ECR allows + * undo. If peer SACKs triggered fast recovery, we can't undo here. + */ + if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss) + tcp_try_undo_loss(sk, false); /* Reset rtx states to prevent spurious retransmits_timed_out() */ tcp_sk(sk)->retrans_stamp = 0; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index db76b96092991cb3f0057035e0e051141511acd5..08a41f1e1cd22478b9ea7740fa34e3979373ac6f 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1857,8 +1857,12 @@ int __udp_disconnect(struct sock *sk, int flags) inet->inet_dport = 0; sock_rps_reset_rxhash(sk); sk->sk_bound_dev_if = 0; - if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) + if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) { inet_reset_saddr(sk); + if (sk->sk_prot->rehash && + (sk->sk_userlocks & SOCK_BINDPORT_LOCK)) + sk->sk_prot->rehash(sk); + } if (!(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) { sk->sk_prot->unhash(sk); diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index 910555a4d9fe2dcc1465421afac904d20147dd06..dccd2286bc2849458417956f7340ab5e06105e49 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -64,8 +64,9 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, goto out; err = -ENOMEM; - rep = nlmsg_new(sizeof(struct inet_diag_msg) + - sizeof(struct inet_diag_meminfo) + 64, + rep = nlmsg_new(nla_total_size(sizeof(struct inet_diag_msg)) + + inet_diag_msg_attrs_size() + + nla_total_size(sizeof(struct inet_diag_meminfo)) + 64, GFP_KERNEL); if (!rep) goto out; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index cb493e15959c4d1bb68cf30f4099a8daa785bb84..46d614b611db260d6566c7d6b4d45111a6a027ec 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1226,11 +1226,13 @@ check_cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long *expires) } static void -cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, bool del_rt) +cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, + bool del_rt, bool del_peer) { struct fib6_info *f6i; - f6i = addrconf_get_prefix_route(&ifp->addr, ifp->prefix_len, + f6i = addrconf_get_prefix_route(del_peer ? &ifp->peer_addr : &ifp->addr, + ifp->prefix_len, ifp->idev->dev, 0, RTF_DEFAULT, true); if (f6i) { if (del_rt) @@ -1293,7 +1295,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) if (action != CLEANUP_PREFIX_RT_NOP) { cleanup_prefix_route(ifp, expires, - action == CLEANUP_PREFIX_RT_DEL); + action == CLEANUP_PREFIX_RT_DEL, false); } /* clean up prefsrc entries */ @@ -3345,6 +3347,10 @@ static void addrconf_dev_config(struct net_device *dev) (dev->type != ARPHRD_NONE) && (dev->type != ARPHRD_RAWIP)) { /* Alas, we support only Ethernet autoconfiguration. */ + idev = __in6_dev_get(dev); + if (!IS_ERR_OR_NULL(idev) && dev->flags & IFF_UP && + dev->flags & IFF_MULTICAST) + ipv6_mc_up(idev); return; } @@ -4586,12 +4592,14 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, } static int modify_prefix_route(struct inet6_ifaddr *ifp, - unsigned long expires, u32 flags) + unsigned long expires, u32 flags, + bool modify_peer) { struct fib6_info *f6i; u32 prio; - f6i = addrconf_get_prefix_route(&ifp->addr, ifp->prefix_len, + f6i = addrconf_get_prefix_route(modify_peer ? &ifp->peer_addr : &ifp->addr, + ifp->prefix_len, ifp->idev->dev, 0, RTF_DEFAULT, true); if (!f6i) return -ENOENT; @@ -4602,7 +4610,8 @@ static int modify_prefix_route(struct inet6_ifaddr *ifp, ip6_del_rt(dev_net(ifp->idev->dev), f6i); /* add new one */ - addrconf_prefix_route(&ifp->addr, ifp->prefix_len, + addrconf_prefix_route(modify_peer ? &ifp->peer_addr : &ifp->addr, + ifp->prefix_len, ifp->rt_priority, ifp->idev->dev, expires, flags, GFP_KERNEL); } else { @@ -4624,6 +4633,7 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg) unsigned long timeout; bool was_managetempaddr; bool had_prefixroute; + bool new_peer = false; ASSERT_RTNL(); @@ -4655,6 +4665,13 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg) cfg->preferred_lft = timeout; } + if (cfg->peer_pfx && + memcmp(&ifp->peer_addr, cfg->peer_pfx, sizeof(struct in6_addr))) { + if (!ipv6_addr_any(&ifp->peer_addr)) + cleanup_prefix_route(ifp, expires, true, true); + new_peer = true; + } + spin_lock_bh(&ifp->lock); was_managetempaddr = ifp->flags & IFA_F_MANAGETEMPADDR; had_prefixroute = ifp->flags & IFA_F_PERMANENT && @@ -4670,6 +4687,9 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg) if (cfg->rt_priority && cfg->rt_priority != ifp->rt_priority) ifp->rt_priority = cfg->rt_priority; + if (new_peer) + ifp->peer_addr = *cfg->peer_pfx; + spin_unlock_bh(&ifp->lock); if (!(ifp->flags&IFA_F_TENTATIVE)) ipv6_ifa_notify(0, ifp); @@ -4678,7 +4698,7 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg) int rc = -ENOENT; if (had_prefixroute) - rc = modify_prefix_route(ifp, expires, flags); + rc = modify_prefix_route(ifp, expires, flags, false); /* prefix route could have been deleted; if so restore it */ if (rc == -ENOENT) { @@ -4686,6 +4706,15 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg) ifp->rt_priority, ifp->idev->dev, expires, flags, GFP_KERNEL); } + + if (had_prefixroute && !ipv6_addr_any(&ifp->peer_addr)) + rc = modify_prefix_route(ifp, expires, flags, true); + + if (rc == -ENOENT && !ipv6_addr_any(&ifp->peer_addr)) { + addrconf_prefix_route(&ifp->peer_addr, ifp->prefix_len, + ifp->rt_priority, ifp->idev->dev, + expires, flags, GFP_KERNEL); + } } else if (had_prefixroute) { enum cleanup_prefix_rt_t action; unsigned long rt_expires; @@ -4696,7 +4725,7 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg) if (action != CLEANUP_PREFIX_RT_NOP) { cleanup_prefix_route(ifp, rt_expires, - action == CLEANUP_PREFIX_RT_DEL); + action == CLEANUP_PREFIX_RT_DEL, false); } } @@ -5983,9 +6012,9 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) if (ifp->idev->cnf.forwarding) addrconf_join_anycast(ifp); if (!ipv6_addr_any(&ifp->peer_addr)) - addrconf_prefix_route(&ifp->peer_addr, 128, 0, - ifp->idev->dev, 0, 0, - GFP_ATOMIC); + addrconf_prefix_route(&ifp->peer_addr, 128, + ifp->rt_priority, ifp->idev->dev, + 0, 0, GFP_ATOMIC); break; case RTM_DELADDR: if (ifp->idev->cnf.forwarding) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 58fbde24438116950c11e7cf8e0ca6f59fec23d9..72abf892302f27fd50179b1b5b6d6e0f974a06b9 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1102,8 +1102,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, found++; break; } - if (rt_can_ecmp) - fallback_ins = fallback_ins ?: ins; + fallback_ins = fallback_ins ?: ins; goto next_iter; } @@ -1146,7 +1145,9 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, } if (fallback_ins && !found) { - /* No ECMP-able route found, replace first non-ECMP one */ + /* No matching route with same ecmp-able-ness found, replace + * first matching route + */ ins = fallback_ins; iter = rcu_dereference_protected(*ins, lockdep_is_held(&rt->fib6_table->tb6_lock)); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 55bfc5149d0c5b5a6063dbdf19c2055a3b9aea93..781ca8c07a0da3619d31f8ddd06c8ae69a7a17eb 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -437,8 +437,6 @@ static int ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, return -ENOENT; switch (type) { - struct ipv6_tlv_tnl_enc_lim *tel; - __u32 teli; case ICMPV6_DEST_UNREACH: net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n", t->parms.name); @@ -452,7 +450,10 @@ static int ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, break; } return 0; - case ICMPV6_PARAMPROB: + case ICMPV6_PARAMPROB: { + struct ipv6_tlv_tnl_enc_lim *tel; + __u32 teli; + teli = 0; if (code == ICMPV6_HDR_FIELD) teli = ip6_tnl_parse_tlv_enc_lim(skb, skb->data); @@ -468,6 +469,7 @@ static int ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, t->parms.name); } return 0; + } case ICMPV6_PKT_TOOBIG: ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL)); return 0; diff --git a/net/ipv6/ip6_icmp.c b/net/ipv6/ip6_icmp.c index 02045494c24cccaa8b50af839aae975695319922..e0086758b6ee3c3e91568e59028838c770fac795 100644 --- a/net/ipv6/ip6_icmp.c +++ b/net/ipv6/ip6_icmp.c @@ -45,4 +45,38 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) rcu_read_unlock(); } EXPORT_SYMBOL(icmpv6_send); + +#if IS_ENABLED(CONFIG_NF_NAT) +#include +void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) +{ + struct sk_buff *cloned_skb = NULL; + enum ip_conntrack_info ctinfo; + struct in6_addr orig_ip; + struct nf_conn *ct; + + ct = nf_ct_get(skb_in, &ctinfo); + if (!ct || !(ct->status & IPS_SRC_NAT)) { + icmpv6_send(skb_in, type, code, info); + return; + } + + if (skb_shared(skb_in)) + skb_in = cloned_skb = skb_clone(skb_in, GFP_ATOMIC); + + if (unlikely(!skb_in || skb_network_header(skb_in) < skb_in->head || + (skb_network_header(skb_in) + sizeof(struct ipv6hdr)) > + skb_tail_pointer(skb_in) || skb_ensure_writable(skb_in, + skb_network_offset(skb_in) + sizeof(struct ipv6hdr)))) + goto out; + + orig_ip = ipv6_hdr(skb_in)->saddr; + ipv6_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.in6; + icmpv6_send(skb_in, type, code, info); + ipv6_hdr(skb_in)->saddr = orig_ip; +out: + consume_skb(cloned_skb); +} +EXPORT_SYMBOL(icmpv6_ndo_send); +#endif #endif diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index b5dd20c4599bb1fc2515f6a78b8a6ee3287d03e5..4703b09808d0af016ae566a5be5cb490c7179d38 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -121,6 +121,7 @@ static struct net_device_stats *ip6_get_stats(struct net_device *dev) /** * ip6_tnl_lookup - fetch tunnel matching the end-point addresses + * @link: ifindex of underlying interface * @remote: the address of the tunnel exit-point * @local: the address of the tunnel entry-point * @@ -134,37 +135,56 @@ static struct net_device_stats *ip6_get_stats(struct net_device *dev) for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) static struct ip6_tnl * -ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_addr *local) +ip6_tnl_lookup(struct net *net, int link, + const struct in6_addr *remote, const struct in6_addr *local) { unsigned int hash = HASH(remote, local); - struct ip6_tnl *t; + struct ip6_tnl *t, *cand = NULL; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); struct in6_addr any; for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) { - if (ipv6_addr_equal(local, &t->parms.laddr) && - ipv6_addr_equal(remote, &t->parms.raddr) && - (t->dev->flags & IFF_UP)) + if (!ipv6_addr_equal(local, &t->parms.laddr) || + !ipv6_addr_equal(remote, &t->parms.raddr) || + !(t->dev->flags & IFF_UP)) + continue; + + if (link == t->parms.link) return t; + else + cand = t; } memset(&any, 0, sizeof(any)); hash = HASH(&any, local); for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) { - if (ipv6_addr_equal(local, &t->parms.laddr) && - ipv6_addr_any(&t->parms.raddr) && - (t->dev->flags & IFF_UP)) + if (!ipv6_addr_equal(local, &t->parms.laddr) || + !ipv6_addr_any(&t->parms.raddr) || + !(t->dev->flags & IFF_UP)) + continue; + + if (link == t->parms.link) return t; + else if (!cand) + cand = t; } hash = HASH(remote, &any); for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) { - if (ipv6_addr_equal(remote, &t->parms.raddr) && - ipv6_addr_any(&t->parms.laddr) && - (t->dev->flags & IFF_UP)) + if (!ipv6_addr_equal(remote, &t->parms.raddr) || + !ipv6_addr_any(&t->parms.laddr) || + !(t->dev->flags & IFF_UP)) + continue; + + if (link == t->parms.link) return t; + else if (!cand) + cand = t; } + if (cand) + return cand; + t = rcu_dereference(ip6n->collect_md_tun); if (t && t->dev->flags & IFF_UP) return t; @@ -351,7 +371,8 @@ static struct ip6_tnl *ip6_tnl_locate(struct net *net, (t = rtnl_dereference(*tp)) != NULL; tp = &t->next) { if (ipv6_addr_equal(local, &t->parms.laddr) && - ipv6_addr_equal(remote, &t->parms.raddr)) { + ipv6_addr_equal(remote, &t->parms.raddr) && + p->link == t->parms.link) { if (create) return ERR_PTR(-EEXIST); @@ -485,7 +506,7 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, processing of the error. */ rcu_read_lock(); - t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->daddr, &ipv6h->saddr); + t = ip6_tnl_lookup(dev_net(skb->dev), skb->dev->ifindex, &ipv6h->daddr, &ipv6h->saddr); if (!t) goto out; @@ -496,8 +517,6 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, err = 0; switch (*type) { - struct ipv6_tlv_tnl_enc_lim *tel; - __u32 mtu, teli; case ICMPV6_DEST_UNREACH: net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n", t->parms.name); @@ -510,7 +529,10 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, rel_msg = 1; } break; - case ICMPV6_PARAMPROB: + case ICMPV6_PARAMPROB: { + struct ipv6_tlv_tnl_enc_lim *tel; + __u32 teli; + teli = 0; if ((*code) == ICMPV6_HDR_FIELD) teli = ip6_tnl_parse_tlv_enc_lim(skb, skb->data); @@ -527,7 +549,10 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, t->parms.name); } break; - case ICMPV6_PKT_TOOBIG: + } + case ICMPV6_PKT_TOOBIG: { + __u32 mtu; + ip6_update_pmtu(skb, net, htonl(*info), 0, 0, sock_net_uid(net, NULL)); mtu = *info - offset; @@ -541,6 +566,7 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, rel_msg = 1; } break; + } case NDISC_REDIRECT: ip6_redirect(skb, net, skb->dev->ifindex, 0, sock_net_uid(net, NULL)); @@ -887,7 +913,7 @@ static int ipxip6_rcv(struct sk_buff *skb, u8 ipproto, int ret = -1; rcu_read_lock(); - t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, &ipv6h->daddr); + t = ip6_tnl_lookup(dev_net(skb->dev), skb->dev->ifindex, &ipv6h->saddr, &ipv6h->daddr); if (t) { u8 tproto = READ_ONCE(t->parms.proto); @@ -1420,8 +1446,10 @@ ip6_tnl_start_xmit(struct sk_buff *skb, struct net_device *dev) static void ip6_tnl_link_config(struct ip6_tnl *t) { struct net_device *dev = t->dev; + struct net_device *tdev = NULL; struct __ip6_tnl_parm *p = &t->parms; struct flowi6 *fl6 = &t->fl.u.ip6; + unsigned int mtu; int t_hlen; memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr)); @@ -1457,22 +1485,25 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) struct rt6_info *rt = rt6_lookup(t->net, &p->raddr, &p->laddr, p->link, NULL, strict); + if (rt) { + tdev = rt->dst.dev; + ip6_rt_put(rt); + } - if (!rt) - return; + if (!tdev && p->link) + tdev = __dev_get_by_index(t->net, p->link); - if (rt->dst.dev) { - dev->hard_header_len = rt->dst.dev->hard_header_len + - t_hlen; + if (tdev) { + dev->hard_header_len = tdev->hard_header_len + t_hlen; + mtu = min_t(unsigned int, tdev->mtu, IP6_MAX_MTU); - dev->mtu = rt->dst.dev->mtu - t_hlen; + dev->mtu = mtu - t_hlen; if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) dev->mtu -= 8; if (dev->mtu < IPV6_MIN_MTU) dev->mtu = IPV6_MIN_MTU; } - ip6_rt_put(rt); } } diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 79fc012dd2cae44b69057c168037b018775d1f49..debdaeba5d8c130dbf7dd099bc29fbed80a7ac75 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -183,9 +183,15 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, retv = -EBUSY; break; } - } else if (sk->sk_protocol != IPPROTO_TCP) + } else if (sk->sk_protocol == IPPROTO_TCP) { + if (sk->sk_prot != &tcpv6_prot) { + retv = -EBUSY; + break; + } break; - + } else { + break; + } if (sk->sk_state != TCP_ESTABLISHED) { retv = -ENOTCONN; break; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 4fbdc60b4e070802fcd6905dce800641816a79fa..2931224b674e81e1608cbf5b6a08a31cb6f99415 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5198,6 +5198,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, */ cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL | NLM_F_REPLACE); + cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_CREATE; nhn++; } diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index ab7f124ff5d7e8a69e84fae0c72c581a716266f5..8c52efe299cced6c79575033814c62d82d1f7295 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -268,7 +268,7 @@ static int seg6_do_srh(struct sk_buff *skb) skb_mac_header_rebuild(skb); skb_push(skb, skb->mac_len); - err = seg6_do_srh_encap(skb, tinfo->srh, NEXTHDR_NONE); + err = seg6_do_srh_encap(skb, tinfo->srh, IPPROTO_ETHERNET); if (err) return err; diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 7cbc19731997969bf7eec4ea5e1e8dd20d9e3da1..8165802d8e05dea47225264f20f995b5962565ae 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -282,7 +282,7 @@ static int input_action_end_dx2(struct sk_buff *skb, struct net_device *odev; struct ethhdr *eth; - if (!decap_and_validate(skb, NEXTHDR_NONE)) + if (!decap_and_validate(skb, IPPROTO_ETHERNET)) goto drop; if (!pskb_may_pull(skb, ETH_HLEN)) diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 000c742d05279a8bebb23b54b061e47669b5a4ae..6aee699deb289bbbaa50eb14b5cfb8a728857666 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -3450,7 +3450,7 @@ int ieee80211_attach_ack_skb(struct ieee80211_local *local, struct sk_buff *skb, spin_lock_irqsave(&local->ack_status_lock, spin_flags); id = idr_alloc(&local->ack_status_frames, ack_skb, - 1, 0x40, GFP_ATOMIC); + 1, 0x2000, GFP_ATOMIC); spin_unlock_irqrestore(&local->ack_status_lock, spin_flags); if (id < 0) { diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index d699833703819af130c54803528aa7808e4f2c54..38a0383dfbcfaee991f9bbc05cc5d5dfabd76a90 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -1152,7 +1152,8 @@ int mesh_nexthop_resolve(struct ieee80211_sub_if_data *sdata, } } - if (!(mpath->flags & MESH_PATH_RESOLVING)) + if (!(mpath->flags & MESH_PATH_RESOLVING) && + mesh_path_sel_is_hwmp(sdata)) mesh_queue_preq(mpath, PREQ_Q_F_START); if (skb_queue_len(&mpath->frame_queue) >= MESH_FRAME_QUEUE_LEN) diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 5fa13176036f4f3d9d9edeff6a903580597e11f0..88d7a692a9658137f06128c7a7c98b2a358d12b2 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -8,7 +8,7 @@ * Copyright 2007, Michael Wu * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015 - 2017 Intel Deutschland GmbH - * Copyright (C) 2018 - 2019 Intel Corporation + * Copyright (C) 2018 - 2020 Intel Corporation */ #include @@ -1311,7 +1311,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, if (!res) { ch_switch.timestamp = timestamp; ch_switch.device_timestamp = device_timestamp; - ch_switch.block_tx = beacon ? csa_ie.mode : 0; + ch_switch.block_tx = csa_ie.mode; ch_switch.chandef = csa_ie.chandef; ch_switch.count = csa_ie.count; ch_switch.delay = csa_ie.max_switch_time; @@ -1404,7 +1404,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, sdata->vif.csa_active = true; sdata->csa_chandef = csa_ie.chandef; - sdata->csa_block_tx = ch_switch.block_tx; + sdata->csa_block_tx = csa_ie.mode; ifmgd->csa_ignored_same_chan = false; if (sdata->csa_block_tx) @@ -1438,7 +1438,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, * reset when the disconnection worker runs. */ sdata->vif.csa_active = true; - sdata->csa_block_tx = ch_switch.block_tx; + sdata->csa_block_tx = csa_ie.mode; ieee80211_queue_work(&local->hw, &ifmgd->csa_connection_drop_work); mutex_unlock(&local->chanctx_mtx); @@ -2959,7 +2959,7 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, (auth_transaction == 2 && ifmgd->auth_data->expected_transaction == 2)) { if (!ieee80211_mark_sta_auth(sdata, bssid)) - goto out_err; + return; /* ignore frame -- wait for timeout */ } else if (ifmgd->auth_data->algorithm == WLAN_AUTH_SAE && auth_transaction == 2) { sdata_info(sdata, "SAE peer confirmed\n"); @@ -2967,10 +2967,6 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, } cfg80211_rx_mlme_mgmt(sdata->dev, (u8 *)mgmt, len); - return; - out_err: - mutex_unlock(&sdata->local->sta_mtx); - /* ignore frame -- wait for timeout */ } #define case_WLAN(type) \ diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 0e05ff0376726ddbaf80f05d9f90f6f086225b88..0ba98ad9bc854800fad0c90cc594bc6d98b12508 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -4114,7 +4114,7 @@ void __ieee80211_check_fast_rx_iface(struct ieee80211_sub_if_data *sdata) lockdep_assert_held(&local->sta_mtx); - list_for_each_entry_rcu(sta, &local->sta_list, list) { + list_for_each_entry(sta, &local->sta_list, list) { if (sdata != sta->sdata && (!sta->sdata->bss || sta->sdata->bss != sdata->bss)) continue; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 4bd1faf4f779fb821579f9cea77c32c8e1007a2e..87def9cb91fffb462a47bac7112a513f74a98401 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -2442,7 +2442,7 @@ static int ieee80211_store_ack_skb(struct ieee80211_local *local, spin_lock_irqsave(&local->ack_status_lock, flags); id = idr_alloc(&local->ack_status_frames, ack_skb, - 1, 0x40, GFP_ATOMIC); + 1, 0x2000, GFP_ATOMIC); spin_unlock_irqrestore(&local->ack_status_lock, flags); if (id >= 0) { diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 32a7a53833c01d1ea760646440f54009ae9c4544..decd46b3839380d5e0897f3063ceb4e27d625fe2 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1063,16 +1063,22 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, elem_parse_failed = true; break; case WLAN_EID_VHT_OPERATION: - if (elen >= sizeof(struct ieee80211_vht_operation)) + if (elen >= sizeof(struct ieee80211_vht_operation)) { elems->vht_operation = (void *)pos; - else - elem_parse_failed = true; + if (calc_crc) + crc = crc32_be(crc, pos - 2, elen + 2); + break; + } + elem_parse_failed = true; break; case WLAN_EID_OPMODE_NOTIF: - if (elen > 0) + if (elen > 0) { elems->opmode_notif = pos; - else - elem_parse_failed = true; + if (calc_crc) + crc = crc32_be(crc, pos - 2, elen + 2); + break; + } + elem_parse_failed = true; break; case WLAN_EID_MESH_ID: elems->mesh_id = pos; @@ -2987,10 +2993,22 @@ bool ieee80211_chandef_vht_oper(struct ieee80211_hw *hw, int cf0, cf1; int ccfs0, ccfs1, ccfs2; int ccf0, ccf1; + u32 vht_cap; + bool support_80_80 = false; + bool support_160 = false; if (!oper || !htop) return false; + vht_cap = hw->wiphy->bands[chandef->chan->band]->vht_cap.cap; + support_160 = (vht_cap & (IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK | + IEEE80211_VHT_CAP_EXT_NSS_BW_MASK)); + support_80_80 = ((vht_cap & + IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) || + (vht_cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ && + vht_cap & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) || + ((vht_cap & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) >> + IEEE80211_VHT_CAP_EXT_NSS_BW_SHIFT > 1)); ccfs0 = oper->center_freq_seg0_idx; ccfs1 = oper->center_freq_seg1_idx; ccfs2 = (le16_to_cpu(htop->operation_mode) & @@ -3018,10 +3036,10 @@ bool ieee80211_chandef_vht_oper(struct ieee80211_hw *hw, unsigned int diff; diff = abs(ccf1 - ccf0); - if (diff == 8) { + if ((diff == 8) && support_160) { new.width = NL80211_CHAN_WIDTH_160; new.center_freq1 = cf1; - } else if (diff > 8) { + } else if ((diff > 8) && support_80_80) { new.width = NL80211_CHAN_WIDTH_80P80; new.center_freq2 = cf1; } diff --git a/net/mptcp/Kconfig b/net/mptcp/Kconfig index 49f6054e7f4ebc15837ad7f0c61420063ea00104..a9ed3bf1d93faaf6ca3f2597e2bde6ff3a5f3487 100644 --- a/net/mptcp/Kconfig +++ b/net/mptcp/Kconfig @@ -4,6 +4,7 @@ config MPTCP depends on INET select SKB_EXTENSIONS select CRYPTO_LIB_SHA256 + select CRYPTO help Multipath TCP (MPTCP) connections send and receive data over multiple subflows in order to utilize multiple network paths. Each subflow diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 45acd877bef345259ca2a84c58cd0d375f88386f..fd2c3150e59193e189a5e85f901d21c2bfca0115 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -334,6 +334,8 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, struct mptcp_sock *msk; unsigned int ack_size; bool ret = false; + bool can_ack; + u64 ack_seq; u8 tcp_fin; if (skb) { @@ -360,9 +362,22 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, ret = true; } + /* passive sockets msk will set the 'can_ack' after accept(), even + * if the first subflow may have the already the remote key handy + */ + can_ack = true; opts->ext_copy.use_ack = 0; msk = mptcp_sk(subflow->conn); - if (!msk || !READ_ONCE(msk->can_ack)) { + if (likely(msk && READ_ONCE(msk->can_ack))) { + ack_seq = msk->ack_seq; + } else if (subflow->can_ack) { + mptcp_crypto_key_sha(subflow->remote_key, NULL, &ack_seq); + ack_seq++; + } else { + can_ack = false; + } + + if (unlikely(!can_ack)) { *size = ALIGN(dss_size, 4); return ret; } @@ -375,7 +390,7 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, dss_size += ack_size; - opts->ext_copy.data_ack = msk->ack_seq; + opts->ext_copy.data_ack = ack_seq; opts->ext_copy.ack64 = 1; opts->ext_copy.use_ack = 1; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 73780b4cb10813e203ba9bebad3f6553a49dfa83..3c19a8efdceadcde707150a33bc03c31dc8a0b84 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -543,6 +543,11 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, } } +static unsigned int mptcp_sync_mss(struct sock *sk, u32 pmtu) +{ + return 0; +} + static int __mptcp_init_sock(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); @@ -551,6 +556,7 @@ static int __mptcp_init_sock(struct sock *sk) __set_bit(MPTCP_SEND_SPACE, &msk->flags); msk->first = NULL; + inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss; return 0; } @@ -643,7 +649,7 @@ static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk) } #endif -struct sock *mptcp_sk_clone_lock(const struct sock *sk) +static struct sock *mptcp_sk_clone_lock(const struct sock *sk) { struct sock *nsk = sk_clone_lock(sk, GFP_ATOMIC); @@ -755,60 +761,50 @@ static int mptcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen) { struct mptcp_sock *msk = mptcp_sk(sk); - int ret = -EOPNOTSUPP; struct socket *ssock; - struct sock *ssk; pr_debug("msk=%p", msk); /* @@ the meaning of setsockopt() when the socket is connected and - * there are multiple subflows is not defined. + * there are multiple subflows is not yet defined. It is up to the + * MPTCP-level socket to configure the subflows until the subflow + * is in TCP fallback, when TCP socket options are passed through + * to the one remaining subflow. */ lock_sock(sk); - ssock = __mptcp_socket_create(msk, MPTCP_SAME_STATE); - if (IS_ERR(ssock)) { - release_sock(sk); - return ret; - } + ssock = __mptcp_tcp_fallback(msk); + if (ssock) + return tcp_setsockopt(ssock->sk, level, optname, optval, + optlen); - ssk = ssock->sk; - sock_hold(ssk); release_sock(sk); - ret = tcp_setsockopt(ssk, level, optname, optval, optlen); - sock_put(ssk); - - return ret; + return -EOPNOTSUPP; } static int mptcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *option) { struct mptcp_sock *msk = mptcp_sk(sk); - int ret = -EOPNOTSUPP; struct socket *ssock; - struct sock *ssk; pr_debug("msk=%p", msk); - /* @@ the meaning of getsockopt() when the socket is connected and - * there are multiple subflows is not defined. + /* @@ the meaning of setsockopt() when the socket is connected and + * there are multiple subflows is not yet defined. It is up to the + * MPTCP-level socket to configure the subflows until the subflow + * is in TCP fallback, when socket options are passed through + * to the one remaining subflow. */ lock_sock(sk); - ssock = __mptcp_socket_create(msk, MPTCP_SAME_STATE); - if (IS_ERR(ssock)) { - release_sock(sk); - return ret; - } + ssock = __mptcp_tcp_fallback(msk); + if (ssock) + return tcp_getsockopt(ssock->sk, level, optname, optval, + option); - ssk = ssock->sk; - sock_hold(ssk); release_sock(sk); - ret = tcp_getsockopt(ssk, level, optname, optval, option); - sock_put(ssk); - - return ret; + return -EOPNOTSUPP; } static int mptcp_get_port(struct sock *sk, unsigned short snum) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 8a99a29302846fdc2b21d225daffa7e44adb067c..9f8663b30456256bfdd0e8e4d89061bc90e5281a 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -56,8 +56,8 @@ #define MPTCP_DSS_FLAG_MASK (0x1F) /* MPTCP socket flags */ -#define MPTCP_DATA_READY BIT(0) -#define MPTCP_SEND_SPACE BIT(1) +#define MPTCP_DATA_READY 0 +#define MPTCP_SEND_SPACE 1 /* MPTCP connection sock */ struct mptcp_sock { diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 69c107f9ba8db06ebb0b332a7fb91e2514d5831e..8dd17589217d71e4e38f6d442434130cadd290e0 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -723,6 +723,20 @@ ip_set_rcu_get(struct net *net, ip_set_id_t index) return set; } +static inline void +ip_set_lock(struct ip_set *set) +{ + if (!set->variant->region_lock) + spin_lock_bh(&set->lock); +} + +static inline void +ip_set_unlock(struct ip_set *set) +{ + if (!set->variant->region_lock) + spin_unlock_bh(&set->lock); +} + int ip_set_test(ip_set_id_t index, const struct sk_buff *skb, const struct xt_action_param *par, struct ip_set_adt_opt *opt) @@ -744,9 +758,9 @@ ip_set_test(ip_set_id_t index, const struct sk_buff *skb, if (ret == -EAGAIN) { /* Type requests element to be completed */ pr_debug("element must be completed, ADD is triggered\n"); - spin_lock_bh(&set->lock); + ip_set_lock(set); set->variant->kadt(set, skb, par, IPSET_ADD, opt); - spin_unlock_bh(&set->lock); + ip_set_unlock(set); ret = 1; } else { /* --return-nomatch: invert matched element */ @@ -775,9 +789,9 @@ ip_set_add(ip_set_id_t index, const struct sk_buff *skb, !(opt->family == set->family || set->family == NFPROTO_UNSPEC)) return -IPSET_ERR_TYPE_MISMATCH; - spin_lock_bh(&set->lock); + ip_set_lock(set); ret = set->variant->kadt(set, skb, par, IPSET_ADD, opt); - spin_unlock_bh(&set->lock); + ip_set_unlock(set); return ret; } @@ -797,9 +811,9 @@ ip_set_del(ip_set_id_t index, const struct sk_buff *skb, !(opt->family == set->family || set->family == NFPROTO_UNSPEC)) return -IPSET_ERR_TYPE_MISMATCH; - spin_lock_bh(&set->lock); + ip_set_lock(set); ret = set->variant->kadt(set, skb, par, IPSET_DEL, opt); - spin_unlock_bh(&set->lock); + ip_set_unlock(set); return ret; } @@ -1264,9 +1278,9 @@ ip_set_flush_set(struct ip_set *set) { pr_debug("set: %s\n", set->name); - spin_lock_bh(&set->lock); + ip_set_lock(set); set->variant->flush(set); - spin_unlock_bh(&set->lock); + ip_set_unlock(set); } static int ip_set_flush(struct net *net, struct sock *ctnl, struct sk_buff *skb, @@ -1713,9 +1727,9 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set, bool eexist = flags & IPSET_FLAG_EXIST, retried = false; do { - spin_lock_bh(&set->lock); + ip_set_lock(set); ret = set->variant->uadt(set, tb, adt, &lineno, flags, retried); - spin_unlock_bh(&set->lock); + ip_set_unlock(set); retried = true; } while (ret == -EAGAIN && set->variant->resize && diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 7480ce55b5c856feba27bc47341ff8158068e11f..e52d7b7597a0d8f3d6cfed5d2af6544ae1ad2e5d 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -7,13 +7,21 @@ #include #include #include +#include #include -#define __ipset_dereference_protected(p, c) rcu_dereference_protected(p, c) -#define ipset_dereference_protected(p, set) \ - __ipset_dereference_protected(p, lockdep_is_held(&(set)->lock)) - -#define rcu_dereference_bh_nfnl(p) rcu_dereference_bh_check(p, 1) +#define __ipset_dereference(p) \ + rcu_dereference_protected(p, 1) +#define ipset_dereference_nfnl(p) \ + rcu_dereference_protected(p, \ + lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET)) +#define ipset_dereference_set(p, set) \ + rcu_dereference_protected(p, \ + lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET) || \ + lockdep_is_held(&(set)->lock)) +#define ipset_dereference_bh_nfnl(p) \ + rcu_dereference_bh_check(p, \ + lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET)) /* Hashing which uses arrays to resolve clashing. The hash table is resized * (doubled) when searching becomes too long. @@ -72,11 +80,35 @@ struct hbucket { __aligned(__alignof__(u64)); }; +/* Region size for locking == 2^HTABLE_REGION_BITS */ +#define HTABLE_REGION_BITS 10 +#define ahash_numof_locks(htable_bits) \ + ((htable_bits) < HTABLE_REGION_BITS ? 1 \ + : jhash_size((htable_bits) - HTABLE_REGION_BITS)) +#define ahash_sizeof_regions(htable_bits) \ + (ahash_numof_locks(htable_bits) * sizeof(struct ip_set_region)) +#define ahash_region(n, htable_bits) \ + ((n) % ahash_numof_locks(htable_bits)) +#define ahash_bucket_start(h, htable_bits) \ + ((htable_bits) < HTABLE_REGION_BITS ? 0 \ + : (h) * jhash_size(HTABLE_REGION_BITS)) +#define ahash_bucket_end(h, htable_bits) \ + ((htable_bits) < HTABLE_REGION_BITS ? jhash_size(htable_bits) \ + : ((h) + 1) * jhash_size(HTABLE_REGION_BITS)) + +struct htable_gc { + struct delayed_work dwork; + struct ip_set *set; /* Set the gc belongs to */ + u32 region; /* Last gc run position */ +}; + /* The hash table: the table size stored here in order to make resizing easy */ struct htable { atomic_t ref; /* References for resizing */ - atomic_t uref; /* References for dumping */ + atomic_t uref; /* References for dumping and gc */ u8 htable_bits; /* size of hash table == 2^htable_bits */ + u32 maxelem; /* Maxelem per region */ + struct ip_set_region *hregion; /* Region locks and ext sizes */ struct hbucket __rcu *bucket[0]; /* hashtable buckets */ }; @@ -162,6 +194,10 @@ htable_bits(u32 hashsize) #define NLEN 0 #endif /* IP_SET_HASH_WITH_NETS */ +#define SET_ELEM_EXPIRED(set, d) \ + (SET_WITH_TIMEOUT(set) && \ + ip_set_timeout_expired(ext_timeout(d, set))) + #endif /* _IP_SET_HASH_GEN_H */ #ifndef MTYPE @@ -205,10 +241,12 @@ htable_bits(u32 hashsize) #undef mtype_test_cidrs #undef mtype_test #undef mtype_uref -#undef mtype_expire #undef mtype_resize +#undef mtype_ext_size +#undef mtype_resize_ad #undef mtype_head #undef mtype_list +#undef mtype_gc_do #undef mtype_gc #undef mtype_gc_init #undef mtype_variant @@ -247,10 +285,12 @@ htable_bits(u32 hashsize) #define mtype_test_cidrs IPSET_TOKEN(MTYPE, _test_cidrs) #define mtype_test IPSET_TOKEN(MTYPE, _test) #define mtype_uref IPSET_TOKEN(MTYPE, _uref) -#define mtype_expire IPSET_TOKEN(MTYPE, _expire) #define mtype_resize IPSET_TOKEN(MTYPE, _resize) +#define mtype_ext_size IPSET_TOKEN(MTYPE, _ext_size) +#define mtype_resize_ad IPSET_TOKEN(MTYPE, _resize_ad) #define mtype_head IPSET_TOKEN(MTYPE, _head) #define mtype_list IPSET_TOKEN(MTYPE, _list) +#define mtype_gc_do IPSET_TOKEN(MTYPE, _gc_do) #define mtype_gc IPSET_TOKEN(MTYPE, _gc) #define mtype_gc_init IPSET_TOKEN(MTYPE, _gc_init) #define mtype_variant IPSET_TOKEN(MTYPE, _variant) @@ -275,8 +315,7 @@ htable_bits(u32 hashsize) /* The generic hash structure */ struct htype { struct htable __rcu *table; /* the hash table */ - struct timer_list gc; /* garbage collection when timeout enabled */ - struct ip_set *set; /* attached to this ip_set */ + struct htable_gc gc; /* gc workqueue */ u32 maxelem; /* max elements in the hash */ u32 initval; /* random jhash init value */ #ifdef IP_SET_HASH_WITH_MARKMASK @@ -288,21 +327,33 @@ struct htype { #ifdef IP_SET_HASH_WITH_NETMASK u8 netmask; /* netmask value for subnets to store */ #endif + struct list_head ad; /* Resize add|del backlist */ struct mtype_elem next; /* temporary storage for uadd */ #ifdef IP_SET_HASH_WITH_NETS struct net_prefixes nets[NLEN]; /* book-keeping of prefixes */ #endif }; +/* ADD|DEL entries saved during resize */ +struct mtype_resize_ad { + struct list_head list; + enum ipset_adt ad; /* ADD|DEL element */ + struct mtype_elem d; /* Element value */ + struct ip_set_ext ext; /* Extensions for ADD */ + struct ip_set_ext mext; /* Target extensions for ADD */ + u32 flags; /* Flags for ADD */ +}; + #ifdef IP_SET_HASH_WITH_NETS /* Network cidr size book keeping when the hash stores different * sized networks. cidr == real cidr + 1 to support /0. */ static void -mtype_add_cidr(struct htype *h, u8 cidr, u8 n) +mtype_add_cidr(struct ip_set *set, struct htype *h, u8 cidr, u8 n) { int i, j; + spin_lock_bh(&set->lock); /* Add in increasing prefix order, so larger cidr first */ for (i = 0, j = -1; i < NLEN && h->nets[i].cidr[n]; i++) { if (j != -1) { @@ -311,7 +362,7 @@ mtype_add_cidr(struct htype *h, u8 cidr, u8 n) j = i; } else if (h->nets[i].cidr[n] == cidr) { h->nets[CIDR_POS(cidr)].nets[n]++; - return; + goto unlock; } } if (j != -1) { @@ -320,24 +371,29 @@ mtype_add_cidr(struct htype *h, u8 cidr, u8 n) } h->nets[i].cidr[n] = cidr; h->nets[CIDR_POS(cidr)].nets[n] = 1; +unlock: + spin_unlock_bh(&set->lock); } static void -mtype_del_cidr(struct htype *h, u8 cidr, u8 n) +mtype_del_cidr(struct ip_set *set, struct htype *h, u8 cidr, u8 n) { u8 i, j, net_end = NLEN - 1; + spin_lock_bh(&set->lock); for (i = 0; i < NLEN; i++) { if (h->nets[i].cidr[n] != cidr) continue; h->nets[CIDR_POS(cidr)].nets[n]--; if (h->nets[CIDR_POS(cidr)].nets[n] > 0) - return; + goto unlock; for (j = i; j < net_end && h->nets[j].cidr[n]; j++) h->nets[j].cidr[n] = h->nets[j + 1].cidr[n]; h->nets[j].cidr[n] = 0; - return; + goto unlock; } +unlock: + spin_unlock_bh(&set->lock); } #endif @@ -345,7 +401,7 @@ mtype_del_cidr(struct htype *h, u8 cidr, u8 n) static size_t mtype_ahash_memsize(const struct htype *h, const struct htable *t) { - return sizeof(*h) + sizeof(*t); + return sizeof(*h) + sizeof(*t) + ahash_sizeof_regions(t->htable_bits); } /* Get the ith element from the array block n */ @@ -369,24 +425,29 @@ mtype_flush(struct ip_set *set) struct htype *h = set->data; struct htable *t; struct hbucket *n; - u32 i; - - t = ipset_dereference_protected(h->table, set); - for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = __ipset_dereference_protected(hbucket(t, i), 1); - if (!n) - continue; - if (set->extensions & IPSET_EXT_DESTROY) - mtype_ext_cleanup(set, n); - /* FIXME: use slab cache */ - rcu_assign_pointer(hbucket(t, i), NULL); - kfree_rcu(n, rcu); + u32 r, i; + + t = ipset_dereference_nfnl(h->table); + for (r = 0; r < ahash_numof_locks(t->htable_bits); r++) { + spin_lock_bh(&t->hregion[r].lock); + for (i = ahash_bucket_start(r, t->htable_bits); + i < ahash_bucket_end(r, t->htable_bits); i++) { + n = __ipset_dereference(hbucket(t, i)); + if (!n) + continue; + if (set->extensions & IPSET_EXT_DESTROY) + mtype_ext_cleanup(set, n); + /* FIXME: use slab cache */ + rcu_assign_pointer(hbucket(t, i), NULL); + kfree_rcu(n, rcu); + } + t->hregion[r].ext_size = 0; + t->hregion[r].elements = 0; + spin_unlock_bh(&t->hregion[r].lock); } #ifdef IP_SET_HASH_WITH_NETS memset(h->nets, 0, sizeof(h->nets)); #endif - set->elements = 0; - set->ext_size = 0; } /* Destroy the hashtable part of the set */ @@ -397,7 +458,7 @@ mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy) u32 i; for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = __ipset_dereference_protected(hbucket(t, i), 1); + n = __ipset_dereference(hbucket(t, i)); if (!n) continue; if (set->extensions & IPSET_EXT_DESTROY && ext_destroy) @@ -406,6 +467,7 @@ mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy) kfree(n); } + ip_set_free(t->hregion); ip_set_free(t); } @@ -414,28 +476,21 @@ static void mtype_destroy(struct ip_set *set) { struct htype *h = set->data; + struct list_head *l, *lt; if (SET_WITH_TIMEOUT(set)) - del_timer_sync(&h->gc); + cancel_delayed_work_sync(&h->gc.dwork); - mtype_ahash_destroy(set, - __ipset_dereference_protected(h->table, 1), true); + mtype_ahash_destroy(set, ipset_dereference_nfnl(h->table), true); + list_for_each_safe(l, lt, &h->ad) { + list_del(l); + kfree(l); + } kfree(h); set->data = NULL; } -static void -mtype_gc_init(struct ip_set *set, void (*gc)(struct timer_list *t)) -{ - struct htype *h = set->data; - - timer_setup(&h->gc, gc, 0); - mod_timer(&h->gc, jiffies + IPSET_GC_PERIOD(set->timeout) * HZ); - pr_debug("gc initialized, run in every %u\n", - IPSET_GC_PERIOD(set->timeout)); -} - static bool mtype_same_set(const struct ip_set *a, const struct ip_set *b) { @@ -454,11 +509,9 @@ mtype_same_set(const struct ip_set *a, const struct ip_set *b) a->extensions == b->extensions; } -/* Delete expired elements from the hashtable */ static void -mtype_expire(struct ip_set *set, struct htype *h) +mtype_gc_do(struct ip_set *set, struct htype *h, struct htable *t, u32 r) { - struct htable *t; struct hbucket *n, *tmp; struct mtype_elem *data; u32 i, j, d; @@ -466,10 +519,12 @@ mtype_expire(struct ip_set *set, struct htype *h) #ifdef IP_SET_HASH_WITH_NETS u8 k; #endif + u8 htable_bits = t->htable_bits; - t = ipset_dereference_protected(h->table, set); - for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = __ipset_dereference_protected(hbucket(t, i), 1); + spin_lock_bh(&t->hregion[r].lock); + for (i = ahash_bucket_start(r, htable_bits); + i < ahash_bucket_end(r, htable_bits); i++) { + n = __ipset_dereference(hbucket(t, i)); if (!n) continue; for (j = 0, d = 0; j < n->pos; j++) { @@ -485,58 +540,100 @@ mtype_expire(struct ip_set *set, struct htype *h) smp_mb__after_atomic(); #ifdef IP_SET_HASH_WITH_NETS for (k = 0; k < IPSET_NET_COUNT; k++) - mtype_del_cidr(h, + mtype_del_cidr(set, h, NCIDR_PUT(DCIDR_GET(data->cidr, k)), k); #endif + t->hregion[r].elements--; ip_set_ext_destroy(set, data); - set->elements--; d++; } if (d >= AHASH_INIT_SIZE) { if (d >= n->size) { + t->hregion[r].ext_size -= + ext_size(n->size, dsize); rcu_assign_pointer(hbucket(t, i), NULL); kfree_rcu(n, rcu); continue; } tmp = kzalloc(sizeof(*tmp) + - (n->size - AHASH_INIT_SIZE) * dsize, - GFP_ATOMIC); + (n->size - AHASH_INIT_SIZE) * dsize, + GFP_ATOMIC); if (!tmp) - /* Still try to delete expired elements */ + /* Still try to delete expired elements. */ continue; tmp->size = n->size - AHASH_INIT_SIZE; for (j = 0, d = 0; j < n->pos; j++) { if (!test_bit(j, n->used)) continue; data = ahash_data(n, j, dsize); - memcpy(tmp->value + d * dsize, data, dsize); + memcpy(tmp->value + d * dsize, + data, dsize); set_bit(d, tmp->used); d++; } tmp->pos = d; - set->ext_size -= ext_size(AHASH_INIT_SIZE, dsize); + t->hregion[r].ext_size -= + ext_size(AHASH_INIT_SIZE, dsize); rcu_assign_pointer(hbucket(t, i), tmp); kfree_rcu(n, rcu); } } + spin_unlock_bh(&t->hregion[r].lock); } static void -mtype_gc(struct timer_list *t) +mtype_gc(struct work_struct *work) { - struct htype *h = from_timer(h, t, gc); - struct ip_set *set = h->set; + struct htable_gc *gc; + struct ip_set *set; + struct htype *h; + struct htable *t; + u32 r, numof_locks; + unsigned int next_run; + + gc = container_of(work, struct htable_gc, dwork.work); + set = gc->set; + h = set->data; - pr_debug("called\n"); spin_lock_bh(&set->lock); - mtype_expire(set, h); + t = ipset_dereference_set(h->table, set); + atomic_inc(&t->uref); + numof_locks = ahash_numof_locks(t->htable_bits); + r = gc->region++; + if (r >= numof_locks) { + r = gc->region = 0; + } + next_run = (IPSET_GC_PERIOD(set->timeout) * HZ) / numof_locks; + if (next_run < HZ/10) + next_run = HZ/10; spin_unlock_bh(&set->lock); - h->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ; - add_timer(&h->gc); + mtype_gc_do(set, h, t, r); + + if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { + pr_debug("Table destroy after resize by expire: %p\n", t); + mtype_ahash_destroy(set, t, false); + } + + queue_delayed_work(system_power_efficient_wq, &gc->dwork, next_run); + +} + +static void +mtype_gc_init(struct htable_gc *gc) +{ + INIT_DEFERRABLE_WORK(&gc->dwork, mtype_gc); + queue_delayed_work(system_power_efficient_wq, &gc->dwork, HZ); } +static int +mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, + struct ip_set_ext *mext, u32 flags); +static int +mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, + struct ip_set_ext *mext, u32 flags); + /* Resize a hash: create a new hash table with doubling the hashsize * and inserting the elements to it. Repeat until we succeed or * fail due to memory pressures. @@ -547,7 +644,7 @@ mtype_resize(struct ip_set *set, bool retried) struct htype *h = set->data; struct htable *t, *orig; u8 htable_bits; - size_t extsize, dsize = set->dsize; + size_t dsize = set->dsize; #ifdef IP_SET_HASH_WITH_NETS u8 flags; struct mtype_elem *tmp; @@ -555,7 +652,9 @@ mtype_resize(struct ip_set *set, bool retried) struct mtype_elem *data; struct mtype_elem *d; struct hbucket *n, *m; - u32 i, j, key; + struct list_head *l, *lt; + struct mtype_resize_ad *x; + u32 i, j, r, nr, key; int ret; #ifdef IP_SET_HASH_WITH_NETS @@ -563,10 +662,8 @@ mtype_resize(struct ip_set *set, bool retried) if (!tmp) return -ENOMEM; #endif - rcu_read_lock_bh(); - orig = rcu_dereference_bh_nfnl(h->table); + orig = ipset_dereference_bh_nfnl(h->table); htable_bits = orig->htable_bits; - rcu_read_unlock_bh(); retry: ret = 0; @@ -583,88 +680,124 @@ mtype_resize(struct ip_set *set, bool retried) ret = -ENOMEM; goto out; } + t->hregion = ip_set_alloc(ahash_sizeof_regions(htable_bits)); + if (!t->hregion) { + kfree(t); + ret = -ENOMEM; + goto out; + } t->htable_bits = htable_bits; + t->maxelem = h->maxelem / ahash_numof_locks(htable_bits); + for (i = 0; i < ahash_numof_locks(htable_bits); i++) + spin_lock_init(&t->hregion[i].lock); - spin_lock_bh(&set->lock); - orig = __ipset_dereference_protected(h->table, 1); - /* There can't be another parallel resizing, but dumping is possible */ + /* There can't be another parallel resizing, + * but dumping, gc, kernel side add/del are possible + */ + orig = ipset_dereference_bh_nfnl(h->table); atomic_set(&orig->ref, 1); atomic_inc(&orig->uref); - extsize = 0; pr_debug("attempt to resize set %s from %u to %u, t %p\n", set->name, orig->htable_bits, htable_bits, orig); - for (i = 0; i < jhash_size(orig->htable_bits); i++) { - n = __ipset_dereference_protected(hbucket(orig, i), 1); - if (!n) - continue; - for (j = 0; j < n->pos; j++) { - if (!test_bit(j, n->used)) + for (r = 0; r < ahash_numof_locks(orig->htable_bits); r++) { + /* Expire may replace a hbucket with another one */ + rcu_read_lock_bh(); + for (i = ahash_bucket_start(r, orig->htable_bits); + i < ahash_bucket_end(r, orig->htable_bits); i++) { + n = __ipset_dereference(hbucket(orig, i)); + if (!n) continue; - data = ahash_data(n, j, dsize); + for (j = 0; j < n->pos; j++) { + if (!test_bit(j, n->used)) + continue; + data = ahash_data(n, j, dsize); + if (SET_ELEM_EXPIRED(set, data)) + continue; #ifdef IP_SET_HASH_WITH_NETS - /* We have readers running parallel with us, - * so the live data cannot be modified. - */ - flags = 0; - memcpy(tmp, data, dsize); - data = tmp; - mtype_data_reset_flags(data, &flags); + /* We have readers running parallel with us, + * so the live data cannot be modified. + */ + flags = 0; + memcpy(tmp, data, dsize); + data = tmp; + mtype_data_reset_flags(data, &flags); #endif - key = HKEY(data, h->initval, htable_bits); - m = __ipset_dereference_protected(hbucket(t, key), 1); - if (!m) { - m = kzalloc(sizeof(*m) + + key = HKEY(data, h->initval, htable_bits); + m = __ipset_dereference(hbucket(t, key)); + nr = ahash_region(key, htable_bits); + if (!m) { + m = kzalloc(sizeof(*m) + AHASH_INIT_SIZE * dsize, GFP_ATOMIC); - if (!m) { - ret = -ENOMEM; - goto cleanup; - } - m->size = AHASH_INIT_SIZE; - extsize += ext_size(AHASH_INIT_SIZE, dsize); - RCU_INIT_POINTER(hbucket(t, key), m); - } else if (m->pos >= m->size) { - struct hbucket *ht; - - if (m->size >= AHASH_MAX(h)) { - ret = -EAGAIN; - } else { - ht = kzalloc(sizeof(*ht) + + if (!m) { + ret = -ENOMEM; + goto cleanup; + } + m->size = AHASH_INIT_SIZE; + t->hregion[nr].ext_size += + ext_size(AHASH_INIT_SIZE, + dsize); + RCU_INIT_POINTER(hbucket(t, key), m); + } else if (m->pos >= m->size) { + struct hbucket *ht; + + if (m->size >= AHASH_MAX(h)) { + ret = -EAGAIN; + } else { + ht = kzalloc(sizeof(*ht) + (m->size + AHASH_INIT_SIZE) * dsize, GFP_ATOMIC); - if (!ht) - ret = -ENOMEM; + if (!ht) + ret = -ENOMEM; + } + if (ret < 0) + goto cleanup; + memcpy(ht, m, sizeof(struct hbucket) + + m->size * dsize); + ht->size = m->size + AHASH_INIT_SIZE; + t->hregion[nr].ext_size += + ext_size(AHASH_INIT_SIZE, + dsize); + kfree(m); + m = ht; + RCU_INIT_POINTER(hbucket(t, key), ht); } - if (ret < 0) - goto cleanup; - memcpy(ht, m, sizeof(struct hbucket) + - m->size * dsize); - ht->size = m->size + AHASH_INIT_SIZE; - extsize += ext_size(AHASH_INIT_SIZE, dsize); - kfree(m); - m = ht; - RCU_INIT_POINTER(hbucket(t, key), ht); - } - d = ahash_data(m, m->pos, dsize); - memcpy(d, data, dsize); - set_bit(m->pos++, m->used); + d = ahash_data(m, m->pos, dsize); + memcpy(d, data, dsize); + set_bit(m->pos++, m->used); + t->hregion[nr].elements++; #ifdef IP_SET_HASH_WITH_NETS - mtype_data_reset_flags(d, &flags); + mtype_data_reset_flags(d, &flags); #endif + } } + rcu_read_unlock_bh(); } - rcu_assign_pointer(h->table, t); - set->ext_size = extsize; - spin_unlock_bh(&set->lock); + /* There can't be any other writer. */ + rcu_assign_pointer(h->table, t); /* Give time to other readers of the set */ synchronize_rcu(); pr_debug("set %s resized from %u (%p) to %u (%p)\n", set->name, orig->htable_bits, orig, t->htable_bits, t); - /* If there's nobody else dumping the table, destroy it */ + /* Add/delete elements processed by the SET target during resize. + * Kernel-side add cannot trigger a resize and userspace actions + * are serialized by the mutex. + */ + list_for_each_safe(l, lt, &h->ad) { + x = list_entry(l, struct mtype_resize_ad, list); + if (x->ad == IPSET_ADD) { + mtype_add(set, &x->d, &x->ext, &x->mext, x->flags); + } else { + mtype_del(set, &x->d, NULL, NULL, 0); + } + list_del(l); + kfree(l); + } + /* If there's nobody else using the table, destroy it */ if (atomic_dec_and_test(&orig->uref)) { pr_debug("Table destroy by resize %p\n", orig); mtype_ahash_destroy(set, orig, false); @@ -677,15 +810,44 @@ mtype_resize(struct ip_set *set, bool retried) return ret; cleanup: + rcu_read_unlock_bh(); atomic_set(&orig->ref, 0); atomic_dec(&orig->uref); - spin_unlock_bh(&set->lock); mtype_ahash_destroy(set, t, false); if (ret == -EAGAIN) goto retry; goto out; } +/* Get the current number of elements and ext_size in the set */ +static void +mtype_ext_size(struct ip_set *set, u32 *elements, size_t *ext_size) +{ + struct htype *h = set->data; + const struct htable *t; + u32 i, j, r; + struct hbucket *n; + struct mtype_elem *data; + + t = rcu_dereference_bh(h->table); + for (r = 0; r < ahash_numof_locks(t->htable_bits); r++) { + for (i = ahash_bucket_start(r, t->htable_bits); + i < ahash_bucket_end(r, t->htable_bits); i++) { + n = rcu_dereference_bh(hbucket(t, i)); + if (!n) + continue; + for (j = 0; j < n->pos; j++) { + if (!test_bit(j, n->used)) + continue; + data = ahash_data(n, j, set->dsize); + if (!SET_ELEM_EXPIRED(set, data)) + (*elements)++; + } + } + *ext_size += t->hregion[r].ext_size; + } +} + /* Add an element to a hash and update the internal counters when succeeded, * otherwise report the proper error code. */ @@ -698,32 +860,49 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, const struct mtype_elem *d = value; struct mtype_elem *data; struct hbucket *n, *old = ERR_PTR(-ENOENT); - int i, j = -1; + int i, j = -1, ret; bool flag_exist = flags & IPSET_FLAG_EXIST; bool deleted = false, forceadd = false, reuse = false; - u32 key, multi = 0; + u32 r, key, multi = 0, elements, maxelem; - if (set->elements >= h->maxelem) { - if (SET_WITH_TIMEOUT(set)) - /* FIXME: when set is full, we slow down here */ - mtype_expire(set, h); - if (set->elements >= h->maxelem && SET_WITH_FORCEADD(set)) + rcu_read_lock_bh(); + t = rcu_dereference_bh(h->table); + key = HKEY(value, h->initval, t->htable_bits); + r = ahash_region(key, t->htable_bits); + atomic_inc(&t->uref); + elements = t->hregion[r].elements; + maxelem = t->maxelem; + if (elements >= maxelem) { + u32 e; + if (SET_WITH_TIMEOUT(set)) { + rcu_read_unlock_bh(); + mtype_gc_do(set, h, t, r); + rcu_read_lock_bh(); + } + maxelem = h->maxelem; + elements = 0; + for (e = 0; e < ahash_numof_locks(t->htable_bits); e++) + elements += t->hregion[e].elements; + if (elements >= maxelem && SET_WITH_FORCEADD(set)) forceadd = true; } + rcu_read_unlock_bh(); - t = ipset_dereference_protected(h->table, set); - key = HKEY(value, h->initval, t->htable_bits); - n = __ipset_dereference_protected(hbucket(t, key), 1); + spin_lock_bh(&t->hregion[r].lock); + n = rcu_dereference_bh(hbucket(t, key)); if (!n) { - if (forceadd || set->elements >= h->maxelem) + if (forceadd || elements >= maxelem) goto set_full; old = NULL; n = kzalloc(sizeof(*n) + AHASH_INIT_SIZE * set->dsize, GFP_ATOMIC); - if (!n) - return -ENOMEM; + if (!n) { + ret = -ENOMEM; + goto unlock; + } n->size = AHASH_INIT_SIZE; - set->ext_size += ext_size(AHASH_INIT_SIZE, set->dsize); + t->hregion[r].ext_size += + ext_size(AHASH_INIT_SIZE, set->dsize); goto copy_elem; } for (i = 0; i < n->pos; i++) { @@ -737,38 +916,37 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, } data = ahash_data(n, i, set->dsize); if (mtype_data_equal(data, d, &multi)) { - if (flag_exist || - (SET_WITH_TIMEOUT(set) && - ip_set_timeout_expired(ext_timeout(data, set)))) { + if (flag_exist || SET_ELEM_EXPIRED(set, data)) { /* Just the extensions could be overwritten */ j = i; goto overwrite_extensions; } - return -IPSET_ERR_EXIST; + ret = -IPSET_ERR_EXIST; + goto unlock; } /* Reuse first timed out entry */ - if (SET_WITH_TIMEOUT(set) && - ip_set_timeout_expired(ext_timeout(data, set)) && - j == -1) { + if (SET_ELEM_EXPIRED(set, data) && j == -1) { j = i; reuse = true; } } if (reuse || forceadd) { + if (j == -1) + j = 0; data = ahash_data(n, j, set->dsize); if (!deleted) { #ifdef IP_SET_HASH_WITH_NETS for (i = 0; i < IPSET_NET_COUNT; i++) - mtype_del_cidr(h, + mtype_del_cidr(set, h, NCIDR_PUT(DCIDR_GET(data->cidr, i)), i); #endif ip_set_ext_destroy(set, data); - set->elements--; + t->hregion[r].elements--; } goto copy_data; } - if (set->elements >= h->maxelem) + if (elements >= maxelem) goto set_full; /* Create a new slot */ if (n->pos >= n->size) { @@ -776,28 +954,32 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, if (n->size >= AHASH_MAX(h)) { /* Trigger rehashing */ mtype_data_next(&h->next, d); - return -EAGAIN; + ret = -EAGAIN; + goto resize; } old = n; n = kzalloc(sizeof(*n) + (old->size + AHASH_INIT_SIZE) * set->dsize, GFP_ATOMIC); - if (!n) - return -ENOMEM; + if (!n) { + ret = -ENOMEM; + goto unlock; + } memcpy(n, old, sizeof(struct hbucket) + old->size * set->dsize); n->size = old->size + AHASH_INIT_SIZE; - set->ext_size += ext_size(AHASH_INIT_SIZE, set->dsize); + t->hregion[r].ext_size += + ext_size(AHASH_INIT_SIZE, set->dsize); } copy_elem: j = n->pos++; data = ahash_data(n, j, set->dsize); copy_data: - set->elements++; + t->hregion[r].elements++; #ifdef IP_SET_HASH_WITH_NETS for (i = 0; i < IPSET_NET_COUNT; i++) - mtype_add_cidr(h, NCIDR_PUT(DCIDR_GET(d->cidr, i)), i); + mtype_add_cidr(set, h, NCIDR_PUT(DCIDR_GET(d->cidr, i)), i); #endif memcpy(data, d, sizeof(struct mtype_elem)); overwrite_extensions: @@ -820,13 +1002,41 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, if (old) kfree_rcu(old, rcu); } + ret = 0; +resize: + spin_unlock_bh(&t->hregion[r].lock); + if (atomic_read(&t->ref) && ext->target) { + /* Resize is in process and kernel side add, save values */ + struct mtype_resize_ad *x; + + x = kzalloc(sizeof(struct mtype_resize_ad), GFP_ATOMIC); + if (!x) + /* Don't bother */ + goto out; + x->ad = IPSET_ADD; + memcpy(&x->d, value, sizeof(struct mtype_elem)); + memcpy(&x->ext, ext, sizeof(struct ip_set_ext)); + memcpy(&x->mext, mext, sizeof(struct ip_set_ext)); + x->flags = flags; + spin_lock_bh(&set->lock); + list_add_tail(&x->list, &h->ad); + spin_unlock_bh(&set->lock); + } + goto out; - return 0; set_full: if (net_ratelimit()) pr_warn("Set %s is full, maxelem %u reached\n", - set->name, h->maxelem); - return -IPSET_ERR_HASH_FULL; + set->name, maxelem); + ret = -IPSET_ERR_HASH_FULL; +unlock: + spin_unlock_bh(&t->hregion[r].lock); +out: + if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { + pr_debug("Table destroy after resize by add: %p\n", t); + mtype_ahash_destroy(set, t, false); + } + return ret; } /* Delete an element from the hash and free up space if possible. @@ -840,13 +1050,23 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, const struct mtype_elem *d = value; struct mtype_elem *data; struct hbucket *n; - int i, j, k, ret = -IPSET_ERR_EXIST; + struct mtype_resize_ad *x = NULL; + int i, j, k, r, ret = -IPSET_ERR_EXIST; u32 key, multi = 0; size_t dsize = set->dsize; - t = ipset_dereference_protected(h->table, set); + /* Userspace add and resize is excluded by the mutex. + * Kernespace add does not trigger resize. + */ + rcu_read_lock_bh(); + t = rcu_dereference_bh(h->table); key = HKEY(value, h->initval, t->htable_bits); - n = __ipset_dereference_protected(hbucket(t, key), 1); + r = ahash_region(key, t->htable_bits); + atomic_inc(&t->uref); + rcu_read_unlock_bh(); + + spin_lock_bh(&t->hregion[r].lock); + n = rcu_dereference_bh(hbucket(t, key)); if (!n) goto out; for (i = 0, k = 0; i < n->pos; i++) { @@ -857,8 +1077,7 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, data = ahash_data(n, i, dsize); if (!mtype_data_equal(data, d, &multi)) continue; - if (SET_WITH_TIMEOUT(set) && - ip_set_timeout_expired(ext_timeout(data, set))) + if (SET_ELEM_EXPIRED(set, data)) goto out; ret = 0; @@ -866,20 +1085,33 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, smp_mb__after_atomic(); if (i + 1 == n->pos) n->pos--; - set->elements--; + t->hregion[r].elements--; #ifdef IP_SET_HASH_WITH_NETS for (j = 0; j < IPSET_NET_COUNT; j++) - mtype_del_cidr(h, NCIDR_PUT(DCIDR_GET(d->cidr, j)), - j); + mtype_del_cidr(set, h, + NCIDR_PUT(DCIDR_GET(d->cidr, j)), j); #endif ip_set_ext_destroy(set, data); + if (atomic_read(&t->ref) && ext->target) { + /* Resize is in process and kernel side del, + * save values + */ + x = kzalloc(sizeof(struct mtype_resize_ad), + GFP_ATOMIC); + if (x) { + x->ad = IPSET_DEL; + memcpy(&x->d, value, + sizeof(struct mtype_elem)); + x->flags = flags; + } + } for (; i < n->pos; i++) { if (!test_bit(i, n->used)) k++; } if (n->pos == 0 && k == 0) { - set->ext_size -= ext_size(n->size, dsize); + t->hregion[r].ext_size -= ext_size(n->size, dsize); rcu_assign_pointer(hbucket(t, key), NULL); kfree_rcu(n, rcu); } else if (k >= AHASH_INIT_SIZE) { @@ -898,7 +1130,8 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, k++; } tmp->pos = k; - set->ext_size -= ext_size(AHASH_INIT_SIZE, dsize); + t->hregion[r].ext_size -= + ext_size(AHASH_INIT_SIZE, dsize); rcu_assign_pointer(hbucket(t, key), tmp); kfree_rcu(n, rcu); } @@ -906,6 +1139,16 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, } out: + spin_unlock_bh(&t->hregion[r].lock); + if (x) { + spin_lock_bh(&set->lock); + list_add(&x->list, &h->ad); + spin_unlock_bh(&set->lock); + } + if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { + pr_debug("Table destroy after resize by del: %p\n", t); + mtype_ahash_destroy(set, t, false); + } return ret; } @@ -991,6 +1234,7 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext, int i, ret = 0; u32 key, multi = 0; + rcu_read_lock_bh(); t = rcu_dereference_bh(h->table); #ifdef IP_SET_HASH_WITH_NETS /* If we test an IP address and not a network address, @@ -1022,6 +1266,7 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext, goto out; } out: + rcu_read_unlock_bh(); return ret; } @@ -1033,23 +1278,14 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) const struct htable *t; struct nlattr *nested; size_t memsize; + u32 elements = 0; + size_t ext_size = 0; u8 htable_bits; - /* If any members have expired, set->elements will be wrong - * mytype_expire function will update it with the right count. - * we do not hold set->lock here, so grab it first. - * set->elements can still be incorrect in the case of a huge set, - * because elements might time out during the listing. - */ - if (SET_WITH_TIMEOUT(set)) { - spin_lock_bh(&set->lock); - mtype_expire(set, h); - spin_unlock_bh(&set->lock); - } - rcu_read_lock_bh(); - t = rcu_dereference_bh_nfnl(h->table); - memsize = mtype_ahash_memsize(h, t) + set->ext_size; + t = rcu_dereference_bh(h->table); + mtype_ext_size(set, &elements, &ext_size); + memsize = mtype_ahash_memsize(h, t) + ext_size + set->ext_size; htable_bits = t->htable_bits; rcu_read_unlock_bh(); @@ -1071,7 +1307,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) #endif if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref)) || nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)) || - nla_put_net32(skb, IPSET_ATTR_ELEMENTS, htonl(set->elements))) + nla_put_net32(skb, IPSET_ATTR_ELEMENTS, htonl(elements))) goto nla_put_failure; if (unlikely(ip_set_put_flags(skb, set))) goto nla_put_failure; @@ -1091,15 +1327,15 @@ mtype_uref(struct ip_set *set, struct netlink_callback *cb, bool start) if (start) { rcu_read_lock_bh(); - t = rcu_dereference_bh_nfnl(h->table); + t = ipset_dereference_bh_nfnl(h->table); atomic_inc(&t->uref); cb->args[IPSET_CB_PRIVATE] = (unsigned long)t; rcu_read_unlock_bh(); } else if (cb->args[IPSET_CB_PRIVATE]) { t = (struct htable *)cb->args[IPSET_CB_PRIVATE]; if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { - /* Resizing didn't destroy the hash table */ - pr_debug("Table destroy by dump: %p\n", t); + pr_debug("Table destroy after resize " + " by dump: %p\n", t); mtype_ahash_destroy(set, t, false); } cb->args[IPSET_CB_PRIVATE] = 0; @@ -1141,8 +1377,7 @@ mtype_list(const struct ip_set *set, if (!test_bit(i, n->used)) continue; e = ahash_data(n, i, set->dsize); - if (SET_WITH_TIMEOUT(set) && - ip_set_timeout_expired(ext_timeout(e, set))) + if (SET_ELEM_EXPIRED(set, e)) continue; pr_debug("list hash %lu hbucket %p i %u, data %p\n", cb->args[IPSET_CB_ARG0], n, i, e); @@ -1208,6 +1443,7 @@ static const struct ip_set_type_variant mtype_variant = { .uref = mtype_uref, .resize = mtype_resize, .same_set = mtype_same_set, + .region_lock = true, }; #ifdef IP_SET_EMIT_CREATE @@ -1226,6 +1462,7 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, size_t hsize; struct htype *h; struct htable *t; + u32 i; pr_debug("Create set %s with family %s\n", set->name, set->family == NFPROTO_IPV4 ? "inet" : "inet6"); @@ -1294,6 +1531,15 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, kfree(h); return -ENOMEM; } + t->hregion = ip_set_alloc(ahash_sizeof_regions(hbits)); + if (!t->hregion) { + kfree(t); + kfree(h); + return -ENOMEM; + } + h->gc.set = set; + for (i = 0; i < ahash_numof_locks(hbits); i++) + spin_lock_init(&t->hregion[i].lock); h->maxelem = maxelem; #ifdef IP_SET_HASH_WITH_NETMASK h->netmask = netmask; @@ -1304,9 +1550,10 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, get_random_bytes(&h->initval, sizeof(h->initval)); t->htable_bits = hbits; + t->maxelem = h->maxelem / ahash_numof_locks(hbits); RCU_INIT_POINTER(h->table, t); - h->set = set; + INIT_LIST_HEAD(&h->ad); set->data = h; #ifndef IP_SET_PROTO_UNDEF if (set->family == NFPROTO_IPV4) { @@ -1329,12 +1576,10 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, #ifndef IP_SET_PROTO_UNDEF if (set->family == NFPROTO_IPV4) #endif - IPSET_TOKEN(HTYPE, 4_gc_init)(set, - IPSET_TOKEN(HTYPE, 4_gc)); + IPSET_TOKEN(HTYPE, 4_gc_init)(&h->gc); #ifndef IP_SET_PROTO_UNDEF else - IPSET_TOKEN(HTYPE, 6_gc_init)(set, - IPSET_TOKEN(HTYPE, 6_gc)); + IPSET_TOKEN(HTYPE, 6_gc_init)(&h->gc); #endif } pr_debug("create %s hashsize %u (%u) maxelem %u: %p(%p)\n", diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index d1305423640f3abfcaf7e3295022c765d31d82e5..1927fc296f9514bcd5866d340c6f659bea0fdb3e 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -894,32 +894,175 @@ static void nf_ct_acct_merge(struct nf_conn *ct, enum ip_conntrack_info ctinfo, } } -/* Resolve race on insertion if this protocol allows this. */ +static void __nf_conntrack_insert_prepare(struct nf_conn *ct) +{ + struct nf_conn_tstamp *tstamp; + + atomic_inc(&ct->ct_general.use); + ct->status |= IPS_CONFIRMED; + + /* set conntrack timestamp, if enabled. */ + tstamp = nf_conn_tstamp_find(ct); + if (tstamp) + tstamp->start = ktime_get_real_ns(); +} + +static int __nf_ct_resolve_clash(struct sk_buff *skb, + struct nf_conntrack_tuple_hash *h) +{ + /* This is the conntrack entry already in hashes that won race. */ + struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); + enum ip_conntrack_info ctinfo; + struct nf_conn *loser_ct; + + loser_ct = nf_ct_get(skb, &ctinfo); + + if (nf_ct_is_dying(ct)) + return NF_DROP; + + if (!atomic_inc_not_zero(&ct->ct_general.use)) + return NF_DROP; + + if (((ct->status & IPS_NAT_DONE_MASK) == 0) || + nf_ct_match(ct, loser_ct)) { + struct net *net = nf_ct_net(ct); + + nf_ct_acct_merge(ct, ctinfo, loser_ct); + nf_ct_add_to_dying_list(loser_ct); + nf_conntrack_put(&loser_ct->ct_general); + nf_ct_set(skb, ct, ctinfo); + + NF_CT_STAT_INC(net, insert_failed); + return NF_ACCEPT; + } + + nf_ct_put(ct); + return NF_DROP; +} + +/** + * nf_ct_resolve_clash_harder - attempt to insert clashing conntrack entry + * + * @skb: skb that causes the collision + * @repl_idx: hash slot for reply direction + * + * Called when origin or reply direction had a clash. + * The skb can be handled without packet drop provided the reply direction + * is unique or there the existing entry has the identical tuple in both + * directions. + * + * Caller must hold conntrack table locks to prevent concurrent updates. + * + * Returns NF_DROP if the clash could not be handled. + */ +static int nf_ct_resolve_clash_harder(struct sk_buff *skb, u32 repl_idx) +{ + struct nf_conn *loser_ct = (struct nf_conn *)skb_nfct(skb); + const struct nf_conntrack_zone *zone; + struct nf_conntrack_tuple_hash *h; + struct hlist_nulls_node *n; + struct net *net; + + zone = nf_ct_zone(loser_ct); + net = nf_ct_net(loser_ct); + + /* Reply direction must never result in a clash, unless both origin + * and reply tuples are identical. + */ + hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[repl_idx], hnnode) { + if (nf_ct_key_equal(h, + &loser_ct->tuplehash[IP_CT_DIR_REPLY].tuple, + zone, net)) + return __nf_ct_resolve_clash(skb, h); + } + + /* We want the clashing entry to go away real soon: 1 second timeout. */ + loser_ct->timeout = nfct_time_stamp + HZ; + + /* IPS_NAT_CLASH removes the entry automatically on the first + * reply. Also prevents UDP tracker from moving the entry to + * ASSURED state, i.e. the entry can always be evicted under + * pressure. + */ + loser_ct->status |= IPS_FIXED_TIMEOUT | IPS_NAT_CLASH; + + __nf_conntrack_insert_prepare(loser_ct); + + /* fake add for ORIGINAL dir: we want lookups to only find the entry + * already in the table. This also hides the clashing entry from + * ctnetlink iteration, i.e. conntrack -L won't show them. + */ + hlist_nulls_add_fake(&loser_ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode); + + hlist_nulls_add_head_rcu(&loser_ct->tuplehash[IP_CT_DIR_REPLY].hnnode, + &nf_conntrack_hash[repl_idx]); + return NF_ACCEPT; +} + +/** + * nf_ct_resolve_clash - attempt to handle clash without packet drop + * + * @skb: skb that causes the clash + * @h: tuplehash of the clashing entry already in table + * @hash_reply: hash slot for reply direction + * + * A conntrack entry can be inserted to the connection tracking table + * if there is no existing entry with an identical tuple. + * + * If there is one, @skb (and the assocated, unconfirmed conntrack) has + * to be dropped. In case @skb is retransmitted, next conntrack lookup + * will find the already-existing entry. + * + * The major problem with such packet drop is the extra delay added by + * the packet loss -- it will take some time for a retransmit to occur + * (or the sender to time out when waiting for a reply). + * + * This function attempts to handle the situation without packet drop. + * + * If @skb has no NAT transformation or if the colliding entries are + * exactly the same, only the to-be-confirmed conntrack entry is discarded + * and @skb is associated with the conntrack entry already in the table. + * + * Failing that, the new, unconfirmed conntrack is still added to the table + * provided that the collision only occurs in the ORIGINAL direction. + * The new entry will be added after the existing one in the hash list, + * so packets in the ORIGINAL direction will continue to match the existing + * entry. The new entry will also have a fixed timeout so it expires -- + * due to the collision, it will not see bidirectional traffic. + * + * Returns NF_DROP if the clash could not be resolved. + */ static __cold noinline int -nf_ct_resolve_clash(struct net *net, struct sk_buff *skb, - enum ip_conntrack_info ctinfo, - struct nf_conntrack_tuple_hash *h) +nf_ct_resolve_clash(struct sk_buff *skb, struct nf_conntrack_tuple_hash *h, + u32 reply_hash) { /* This is the conntrack entry already in hashes that won race. */ struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); const struct nf_conntrack_l4proto *l4proto; - enum ip_conntrack_info oldinfo; - struct nf_conn *loser_ct = nf_ct_get(skb, &oldinfo); + enum ip_conntrack_info ctinfo; + struct nf_conn *loser_ct; + struct net *net; + int ret; + + loser_ct = nf_ct_get(skb, &ctinfo); + net = nf_ct_net(loser_ct); l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct)); - if (l4proto->allow_clash && - !nf_ct_is_dying(ct) && - atomic_inc_not_zero(&ct->ct_general.use)) { - if (((ct->status & IPS_NAT_DONE_MASK) == 0) || - nf_ct_match(ct, loser_ct)) { - nf_ct_acct_merge(ct, ctinfo, loser_ct); - nf_conntrack_put(&loser_ct->ct_general); - nf_ct_set(skb, ct, oldinfo); - return NF_ACCEPT; - } - nf_ct_put(ct); - } + if (!l4proto->allow_clash) + goto drop; + + ret = __nf_ct_resolve_clash(skb, h); + if (ret == NF_ACCEPT) + return ret; + + ret = nf_ct_resolve_clash_harder(skb, reply_hash); + if (ret == NF_ACCEPT) + return ret; + +drop: + nf_ct_add_to_dying_list(loser_ct); NF_CT_STAT_INC(net, drop); + NF_CT_STAT_INC(net, insert_failed); return NF_DROP; } @@ -932,7 +1075,6 @@ __nf_conntrack_confirm(struct sk_buff *skb) struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; struct nf_conn_help *help; - struct nf_conn_tstamp *tstamp; struct hlist_nulls_node *n; enum ip_conntrack_info ctinfo; struct net *net; @@ -989,6 +1131,7 @@ __nf_conntrack_confirm(struct sk_buff *skb) if (unlikely(nf_ct_is_dying(ct))) { nf_ct_add_to_dying_list(ct); + NF_CT_STAT_INC(net, insert_failed); goto dying; } @@ -1009,13 +1152,8 @@ __nf_conntrack_confirm(struct sk_buff *skb) setting time, otherwise we'd get timer wrap in weird delay cases. */ ct->timeout += nfct_time_stamp; - atomic_inc(&ct->ct_general.use); - ct->status |= IPS_CONFIRMED; - /* set conntrack timestamp, if enabled. */ - tstamp = nf_conn_tstamp_find(ct); - if (tstamp) - tstamp->start = ktime_get_real_ns(); + __nf_conntrack_insert_prepare(ct); /* Since the lookup is lockless, hash insertion must be done after * starting the timer and setting the CONFIRMED bit. The RCU barriers @@ -1035,11 +1173,9 @@ __nf_conntrack_confirm(struct sk_buff *skb) return NF_ACCEPT; out: - nf_ct_add_to_dying_list(ct); - ret = nf_ct_resolve_clash(net, skb, ctinfo, h); + ret = nf_ct_resolve_clash(skb, h, reply_hash); dying: nf_conntrack_double_unlock(hash, reply_hash); - NF_CT_STAT_INC(net, insert_failed); local_bh_enable(); return ret; } diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 7365b43f8f980edb267835006c8d7388ab450336..760ca242281655590ddf0a20ec25c8b73930e06f 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -81,6 +81,18 @@ static bool udp_error(struct sk_buff *skb, return false; } +static void nf_conntrack_udp_refresh_unreplied(struct nf_conn *ct, + struct sk_buff *skb, + enum ip_conntrack_info ctinfo, + u32 extra_jiffies) +{ + if (unlikely(ctinfo == IP_CT_ESTABLISHED_REPLY && + ct->status & IPS_NAT_CLASH)) + nf_ct_kill(ct); + else + nf_ct_refresh_acct(ct, ctinfo, skb, extra_jiffies); +} + /* Returns verdict for packet, and may modify conntracktype */ int nf_conntrack_udp_packet(struct nf_conn *ct, struct sk_buff *skb, @@ -116,8 +128,8 @@ int nf_conntrack_udp_packet(struct nf_conn *ct, if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) nf_conntrack_event_cache(IPCT_ASSURED, ct); } else { - nf_ct_refresh_acct(ct, ctinfo, skb, - timeouts[UDP_CT_UNREPLIED]); + nf_conntrack_udp_refresh_unreplied(ct, skb, ctinfo, + timeouts[UDP_CT_UNREPLIED]); } return NF_ACCEPT; } @@ -198,8 +210,8 @@ int nf_conntrack_udplite_packet(struct nf_conn *ct, if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) nf_conntrack_event_cache(IPCT_ASSURED, ct); } else { - nf_ct_refresh_acct(ct, ctinfo, skb, - timeouts[UDP_CT_UNREPLIED]); + nf_conntrack_udp_refresh_unreplied(ct, skb, ctinfo, + timeouts[UDP_CT_UNREPLIED]); } return NF_ACCEPT; } diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 410809c669e119d9f8e84c54e9a3cc782e7b7196..4912069627b651fcad837f40eb208553bf55cdc5 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -411,7 +411,7 @@ static void *ct_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos) *pos = cpu + 1; return per_cpu_ptr(net->ct.stat, cpu); } - + (*pos)++; return NULL; } diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index 83e1db37c3b041f7872624d05dddd78a8b980404..06f00cdc389100fb197abba44e7fd208d4da23b8 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -847,9 +847,6 @@ static int nf_flow_table_offload_cmd(struct flow_block_offload *bo, { int err; - if (!nf_flowtable_hw_offload(flowtable)) - return 0; - if (!dev->netdev_ops->ndo_setup_tc) return -EOPNOTSUPP; @@ -876,6 +873,9 @@ int nf_flow_table_offload_setup(struct nf_flowtable *flowtable, struct flow_block_offload bo; int err; + if (!nf_flowtable_hw_offload(flowtable)) + return 0; + err = nf_flow_table_offload_cmd(&bo, flowtable, dev, cmd, &extack); if (err < 0) return err; diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index b0930d4aba228bdf63eeb15ac521bfad482b51ea..b9cbe1e2453e82b5040b2309c9a67dda49da64d8 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -267,7 +267,7 @@ static void *synproxy_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos) *pos = cpu + 1; return per_cpu_ptr(snet->stats, cpu); } - + (*pos)++; return NULL; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index d1318bdf49ca97bcdc0b4dd9ff209fdb6cb183f2..38c680f28f157f1346e6047c661d93170de0f8cf 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1405,6 +1405,11 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, lockdep_commit_lock_is_held(net)); if (nft_dump_stats(skb, stats)) goto nla_put_failure; + + if ((chain->flags & NFT_CHAIN_HW_OFFLOAD) && + nla_put_be32(skb, NFTA_CHAIN_FLAGS, + htonl(NFT_CHAIN_HW_OFFLOAD))) + goto nla_put_failure; } if (nla_put_be32(skb, NFTA_CHAIN_USE, htonl(chain->use))) @@ -6300,8 +6305,13 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, goto err4; err = nft_register_flowtable_net_hooks(ctx.net, table, flowtable); - if (err < 0) + if (err < 0) { + list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) { + list_del_rcu(&hook->list); + kfree_rcu(hook, rcu); + } goto err4; + } err = nft_trans_flowtable_add(&ctx, NFT_MSG_NEWFLOWTABLE, flowtable); if (err < 0) @@ -7378,13 +7388,8 @@ static void nf_tables_module_autoload(struct net *net) list_splice_init(&net->nft.module_list, &module_list); mutex_unlock(&net->nft.commit_mutex); list_for_each_entry_safe(req, next, &module_list, list) { - if (req->done) { - list_del(&req->list); - kfree(req); - } else { - request_module("%s", req->module); - req->done = true; - } + request_module("%s", req->module); + req->done = true; } mutex_lock(&net->nft.commit_mutex); list_splice(&module_list, &net->nft.module_list); @@ -8167,6 +8172,7 @@ static void __net_exit nf_tables_exit_net(struct net *net) __nft_release_tables(net); mutex_unlock(&net->nft.commit_mutex); WARN_ON_ONCE(!list_empty(&net->nft.tables)); + WARN_ON_ONCE(!list_empty(&net->nft.module_list)); } static struct pernet_operations nf_tables_net_ops = { diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index de3a9596b7f1bca045b8683bc48f66230fb65e75..a5f294aa8e4cf9c3ef361d775de6f8707d2f1143 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -742,6 +742,8 @@ static const struct nla_policy nfnl_cthelper_policy[NFCTH_MAX+1] = { [NFCTH_NAME] = { .type = NLA_NUL_STRING, .len = NF_CT_HELPER_NAME_LEN-1 }, [NFCTH_QUEUE_NUM] = { .type = NLA_U32, }, + [NFCTH_PRIV_DATA_LEN] = { .type = NLA_U32, }, + [NFCTH_STATUS] = { .type = NLA_U32, }, }; static const struct nfnl_callback nfnl_cthelper_cb[NFNL_MSG_CTHELPER_MAX] = { diff --git a/net/netfilter/nft_chain_nat.c b/net/netfilter/nft_chain_nat.c index ff9ac8ae0031f037efe5ce1061ceabf79fde925a..eac4a901233f24d8fab7392efa36204d1ffab909 100644 --- a/net/netfilter/nft_chain_nat.c +++ b/net/netfilter/nft_chain_nat.c @@ -89,6 +89,7 @@ static const struct nft_chain_type nft_chain_nat_inet = { .name = "nat", .type = NFT_CHAIN_T_NAT, .family = NFPROTO_INET, + .owner = THIS_MODULE, .hook_mask = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_LOCAL_OUT) | diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 1993af3a2979527362bfa419a73c65f71a789363..a7de3a58f553d57885876ba730b5ab2877422101 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -129,6 +129,7 @@ static const struct nla_policy nft_payload_policy[NFTA_PAYLOAD_MAX + 1] = { [NFTA_PAYLOAD_LEN] = { .type = NLA_U32 }, [NFTA_PAYLOAD_CSUM_TYPE] = { .type = NLA_U32 }, [NFTA_PAYLOAD_CSUM_OFFSET] = { .type = NLA_U32 }, + [NFTA_PAYLOAD_CSUM_FLAGS] = { .type = NLA_U32 }, }; static int nft_payload_init(const struct nft_ctx *ctx, diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index f0cb1e13af5081216d799057ed5da4a314e0c4c7..4fc0c924ed5da0cc7adb99d4ba1c0ec8df636f1c 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -203,7 +203,7 @@ * :: * * rule indices in last field: 0 1 - * map to elements: 0x42 0x66 + * map to elements: 0x66 0x42 * * * Matching @@ -298,7 +298,7 @@ * :: * * rule indices in last field: 0 1 - * map to elements: 0x42 0x66 + * map to elements: 0x66 0x42 * * the matching element is at 0x42. * @@ -503,7 +503,7 @@ static int pipapo_refill(unsigned long *map, int len, int rules, return -1; } - if (unlikely(match_only)) { + if (match_only) { bitmap_clear(map, i, 1); return i; } @@ -1766,11 +1766,13 @@ static bool pipapo_match_field(struct nft_pipapo_field *f, static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem) { - const u8 *data = (const u8 *)elem->key.val.data; struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *m = priv->clone; + struct nft_pipapo_elem *e = elem->priv; int rules_f0, first_rule = 0; - struct nft_pipapo_elem *e; + const u8 *data; + + data = (const u8 *)nft_set_ext_key(&e->ext); e = pipapo_get(net, set, data, 0); if (IS_ERR(e)) diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index 4c3f2e24c7cba9e19f096d0c429904949c6f93ae..764e88682a81f25c4fb840a700780f65d23aaebb 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -339,6 +339,8 @@ static const struct nla_policy nft_tunnel_key_policy[NFTA_TUNNEL_KEY_MAX + 1] = [NFTA_TUNNEL_KEY_FLAGS] = { .type = NLA_U32, }, [NFTA_TUNNEL_KEY_TOS] = { .type = NLA_U8, }, [NFTA_TUNNEL_KEY_TTL] = { .type = NLA_U8, }, + [NFTA_TUNNEL_KEY_SPORT] = { .type = NLA_U16, }, + [NFTA_TUNNEL_KEY_DPORT] = { .type = NLA_U16, }, [NFTA_TUNNEL_KEY_OPTS] = { .type = NLA_NESTED, }, }; diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index e27c6c5ba9df880e4604a032130b057bc8c023ab..cd2b034eef59aa96fe5c4e218e4897bac8f9aae6 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1551,6 +1551,9 @@ static void *xt_mttg_seq_next(struct seq_file *seq, void *v, loff_t *ppos, uint8_t nfproto = (unsigned long)PDE_DATA(file_inode(seq->file)); struct nf_mttg_trav *trav = seq->private; + if (ppos != NULL) + ++(*ppos); + switch (trav->class) { case MTTG_TRAV_INIT: trav->class = MTTG_TRAV_NFP_UNSPEC; @@ -1576,9 +1579,6 @@ static void *xt_mttg_seq_next(struct seq_file *seq, void *v, loff_t *ppos, default: return NULL; } - - if (ppos != NULL) - ++*ppos; return trav; } diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index bccd47cd7190810af06dea672842be7f58f72a4e..8c835ad637290efc7505bcfd64507c731a94e364 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -36,6 +36,7 @@ #include #include #include +#include #include #define XT_HASHLIMIT_ALL (XT_HASHLIMIT_HASH_DIP | XT_HASHLIMIT_HASH_DPT | \ @@ -114,7 +115,7 @@ struct dsthash_ent { struct xt_hashlimit_htable { struct hlist_node node; /* global list of all htables */ - int use; + refcount_t use; u_int8_t family; bool rnd_initialized; @@ -315,7 +316,7 @@ static int htable_create(struct net *net, struct hashlimit_cfg3 *cfg, for (i = 0; i < hinfo->cfg.size; i++) INIT_HLIST_HEAD(&hinfo->hash[i]); - hinfo->use = 1; + refcount_set(&hinfo->use, 1); hinfo->count = 0; hinfo->family = family; hinfo->rnd_initialized = false; @@ -401,15 +402,6 @@ static void htable_remove_proc_entry(struct xt_hashlimit_htable *hinfo) remove_proc_entry(hinfo->name, parent); } -static void htable_destroy(struct xt_hashlimit_htable *hinfo) -{ - cancel_delayed_work_sync(&hinfo->gc_work); - htable_remove_proc_entry(hinfo); - htable_selective_cleanup(hinfo, true); - kfree(hinfo->name); - vfree(hinfo); -} - static struct xt_hashlimit_htable *htable_find_get(struct net *net, const char *name, u_int8_t family) @@ -420,7 +412,7 @@ static struct xt_hashlimit_htable *htable_find_get(struct net *net, hlist_for_each_entry(hinfo, &hashlimit_net->htables, node) { if (!strcmp(name, hinfo->name) && hinfo->family == family) { - hinfo->use++; + refcount_inc(&hinfo->use); return hinfo; } } @@ -429,12 +421,16 @@ static struct xt_hashlimit_htable *htable_find_get(struct net *net, static void htable_put(struct xt_hashlimit_htable *hinfo) { - mutex_lock(&hashlimit_mutex); - if (--hinfo->use == 0) { + if (refcount_dec_and_mutex_lock(&hinfo->use, &hashlimit_mutex)) { hlist_del(&hinfo->node); - htable_destroy(hinfo); + htable_remove_proc_entry(hinfo); + mutex_unlock(&hashlimit_mutex); + + cancel_delayed_work_sync(&hinfo->gc_work); + htable_selective_cleanup(hinfo, true); + kfree(hinfo->name); + vfree(hinfo); } - mutex_unlock(&hashlimit_mutex); } /* The algorithm used is the Simple Token Bucket Filter (TBF) @@ -837,6 +833,8 @@ hashlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) return hashlimit_mt_common(skb, par, hinfo, &info->cfg, 3); } +#define HASHLIMIT_MAX_SIZE 1048576 + static int hashlimit_mt_check_common(const struct xt_mtchk_param *par, struct xt_hashlimit_htable **hinfo, struct hashlimit_cfg3 *cfg, @@ -847,6 +845,14 @@ static int hashlimit_mt_check_common(const struct xt_mtchk_param *par, if (cfg->gc_interval == 0 || cfg->expire == 0) return -EINVAL; + if (cfg->size > HASHLIMIT_MAX_SIZE) { + cfg->size = HASHLIMIT_MAX_SIZE; + pr_info_ratelimited("size too large, truncated to %u\n", cfg->size); + } + if (cfg->max > HASHLIMIT_MAX_SIZE) { + cfg->max = HASHLIMIT_MAX_SIZE; + pr_info_ratelimited("max too large, truncated to %u\n", cfg->max); + } if (par->family == NFPROTO_IPV4) { if (cfg->srcmask > 32 || cfg->dstmask > 32) return -EINVAL; diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index 0a9708004e205cf52f391f1b1729b06504eba207..225a7ab6d79a9480b70ded6dc4a774e0c7b9a409 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -492,12 +492,12 @@ static void *recent_seq_next(struct seq_file *seq, void *v, loff_t *pos) const struct recent_entry *e = v; const struct list_head *head = e->list.next; + (*pos)++; while (head == &t->iphash[st->bucket]) { if (++st->bucket >= ip_list_hash_size) return NULL; head = t->iphash[st->bucket].next; } - (*pos)++; return list_entry(head, struct recent_entry, list); } diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c index f5d34da0646eda1647a39300252ff1249c8b01eb..a1f2320ecc16d1450525123fe6f217ddb8203b76 100644 --- a/net/netlabel/netlabel_domainhash.c +++ b/net/netlabel/netlabel_domainhash.c @@ -143,7 +143,8 @@ static struct netlbl_dom_map *netlbl_domhsh_search(const char *domain, if (domain != NULL) { bkt = netlbl_domhsh_hash(domain); bkt_list = &netlbl_domhsh_rcu_deref(netlbl_domhsh)->tbl[bkt]; - list_for_each_entry_rcu(iter, bkt_list, list) + list_for_each_entry_rcu(iter, bkt_list, list, + lockdep_is_held(&netlbl_domhsh_lock)) if (iter->valid && netlbl_family_match(iter->family, family) && strcmp(iter->domain, domain) == 0) diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index d2e4ab8d1cb1008da0a9577667d1206d4c0bb309..77bb1bb22c3bfced3a6302d4241f5a0cdbd5d069 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -207,7 +207,8 @@ static struct netlbl_unlhsh_iface *netlbl_unlhsh_search_iface(int ifindex) bkt = netlbl_unlhsh_hash(ifindex); bkt_list = &netlbl_unlhsh_rcu_deref(netlbl_unlhsh)->tbl[bkt]; - list_for_each_entry_rcu(iter, bkt_list, list) + list_for_each_entry_rcu(iter, bkt_list, list, + lockdep_is_held(&netlbl_unlhsh_lock)) if (iter->valid && iter->ifindex == ifindex) return iter; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 4e31721e729360c8bf555186ab6d4aa67cb00280..5313f1cec17063fb048ad80fdf0a567c4dc7357f 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1014,7 +1014,8 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, if (nlk->netlink_bind && groups) { int group; - for (group = 0; group < nlk->ngroups; group++) { + /* nl_groups is a u32, so cap the maximum groups we can bind */ + for (group = 0; group < BITS_PER_TYPE(u32); group++) { if (!test_bit(group, &groups)) continue; err = nlk->netlink_bind(net, group + 1); @@ -1033,7 +1034,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, netlink_insert(sk, nladdr->nl_pid) : netlink_autobind(sock); if (err) { - netlink_undo_bind(nlk->ngroups, groups, sk); + netlink_undo_bind(BITS_PER_TYPE(u32), groups, sk); goto unlock; } } @@ -2433,7 +2434,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, in_skb->len)) WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_OFFS, (u8 *)extack->bad_attr - - in_skb->data)); + (u8 *)nlh)); } else { if (extack->cookie_len) WARN_ON(nla_put(skb, NLMSGERR_ATTR_COOKIE, diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 0522b2b1fd958ce17de51163df8505d2b754d988..9f357aa22b9452d17f5c391a159d263c4f3df552 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -497,8 +497,9 @@ genl_family_rcv_msg_attrs_parse(const struct genl_family *family, err = __nlmsg_parse(nlh, hdrlen, attrbuf, family->maxattr, family->policy, validate, extack); - if (err && parallel) { - kfree(attrbuf); + if (err) { + if (parallel) + kfree(attrbuf); return ERR_PTR(err); } return attrbuf; diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c index 6f1b096e601c7e4c4744afc84c8dc7788935c8fa..43811b5219b5b6276663f7d527a24cf964c1665f 100644 --- a/net/nfc/hci/core.c +++ b/net/nfc/hci/core.c @@ -181,13 +181,20 @@ void nfc_hci_resp_received(struct nfc_hci_dev *hdev, u8 result, void nfc_hci_cmd_received(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd, struct sk_buff *skb) { - u8 gate = hdev->pipes[pipe].gate; u8 status = NFC_HCI_ANY_OK; struct hci_create_pipe_resp *create_info; struct hci_delete_pipe_noti *delete_info; struct hci_all_pipe_cleared_noti *cleared_info; + u8 gate; - pr_debug("from gate %x pipe %x cmd %x\n", gate, pipe, cmd); + pr_debug("from pipe %x cmd %x\n", pipe, cmd); + + if (pipe >= NFC_HCI_MAX_PIPES) { + status = NFC_HCI_ANY_E_NOK; + goto exit; + } + + gate = hdev->pipes[pipe].gate; switch (cmd) { case NFC_HCI_ADM_NOTIFY_PIPE_CREATED: @@ -375,8 +382,14 @@ void nfc_hci_event_received(struct nfc_hci_dev *hdev, u8 pipe, u8 event, struct sk_buff *skb) { int r = 0; - u8 gate = hdev->pipes[pipe].gate; + u8 gate; + + if (pipe >= NFC_HCI_MAX_PIPES) { + pr_err("Discarded event %x to invalid pipe %x\n", event, pipe); + goto exit; + } + gate = hdev->pipes[pipe].gate; if (gate == NFC_HCI_INVALID_GATE) { pr_err("Discarded event %x to unopened pipe %x\n", event, pipe); goto exit; diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index eee0dddb7749e0c9dec121ea29a047226b9e4473..e894254c17d430f7055a7a333e454af6d942a913 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -32,6 +32,7 @@ static const struct nla_policy nfc_genl_policy[NFC_ATTR_MAX + 1] = { [NFC_ATTR_DEVICE_NAME] = { .type = NLA_STRING, .len = NFC_DEVICE_NAME_MAXSIZE }, [NFC_ATTR_PROTOCOLS] = { .type = NLA_U32 }, + [NFC_ATTR_TARGET_INDEX] = { .type = NLA_U32 }, [NFC_ATTR_COMM_MODE] = { .type = NLA_U8 }, [NFC_ATTR_RF_MODE] = { .type = NLA_U8 }, [NFC_ATTR_DEVICE_POWERED] = { .type = NLA_U8 }, @@ -43,7 +44,10 @@ static const struct nla_policy nfc_genl_policy[NFC_ATTR_MAX + 1] = { [NFC_ATTR_LLC_SDP] = { .type = NLA_NESTED }, [NFC_ATTR_FIRMWARE_NAME] = { .type = NLA_STRING, .len = NFC_FIRMWARE_NAME_MAXSIZE }, + [NFC_ATTR_SE_INDEX] = { .type = NLA_U32 }, [NFC_ATTR_SE_APDU] = { .type = NLA_BINARY }, + [NFC_ATTR_VENDOR_ID] = { .type = NLA_U32 }, + [NFC_ATTR_VENDOR_SUBCMD] = { .type = NLA_U32 }, [NFC_ATTR_VENDOR_DATA] = { .type = NLA_BINARY }, }; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 659c2a790fe7cf919d3b5b6af3bd41ffde1211c7..07a7dd185995454b86f441cca819772cce9bcef0 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -179,7 +179,8 @@ struct vport *ovs_lookup_vport(const struct datapath *dp, u16 port_no) struct hlist_head *head; head = vport_hash_bucket(dp, port_no); - hlist_for_each_entry_rcu(vport, head, dp_hash_node) { + hlist_for_each_entry_rcu(vport, head, dp_hash_node, + lockdep_ovsl_is_held()) { if (vport->port_no == port_no) return vport; } @@ -644,6 +645,7 @@ static const struct nla_policy packet_policy[OVS_PACKET_ATTR_MAX + 1] = { [OVS_PACKET_ATTR_ACTIONS] = { .type = NLA_NESTED }, [OVS_PACKET_ATTR_PROBE] = { .type = NLA_FLAG }, [OVS_PACKET_ATTR_MRU] = { .type = NLA_U16 }, + [OVS_PACKET_ATTR_HASH] = { .type = NLA_U64 }, }; static const struct genl_ops dp_packet_genl_ops[] = { @@ -2042,7 +2044,8 @@ static unsigned int ovs_get_max_headroom(struct datapath *dp) int i; for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) { - hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node) { + hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node, + lockdep_ovsl_is_held()) { dev = vport->dev; dev_headroom = netdev_get_fwd_headroom(dev); if (dev_headroom > max_headroom) @@ -2061,7 +2064,8 @@ static void ovs_update_headroom(struct datapath *dp, unsigned int new_headroom) dp->max_headroom = new_headroom; for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) - hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node) + hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node, + lockdep_ovsl_is_held()) netdev_set_rx_headroom(vport->dev, new_headroom); } diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 7da4230627f51489707fc199c4333702c344282e..288122eec7c838abcadcd0c106a719675c84471e 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2708,10 +2708,6 @@ static int validate_set(const struct nlattr *a, return -EINVAL; switch (key_type) { - const struct ovs_key_ipv4 *ipv4_key; - const struct ovs_key_ipv6 *ipv6_key; - int err; - case OVS_KEY_ATTR_PRIORITY: case OVS_KEY_ATTR_SKB_MARK: case OVS_KEY_ATTR_CT_MARK: @@ -2723,7 +2719,9 @@ static int validate_set(const struct nlattr *a, return -EINVAL; break; - case OVS_KEY_ATTR_TUNNEL: + case OVS_KEY_ATTR_TUNNEL: { + int err; + if (masked) return -EINVAL; /* Masked tunnel set not supported. */ @@ -2732,8 +2730,10 @@ static int validate_set(const struct nlattr *a, if (err) return err; break; + } + case OVS_KEY_ATTR_IPV4: { + const struct ovs_key_ipv4 *ipv4_key; - case OVS_KEY_ATTR_IPV4: if (eth_type != htons(ETH_P_IP)) return -EINVAL; @@ -2753,8 +2753,10 @@ static int validate_set(const struct nlattr *a, return -EINVAL; } break; + } + case OVS_KEY_ATTR_IPV6: { + const struct ovs_key_ipv6 *ipv6_key; - case OVS_KEY_ATTR_IPV6: if (eth_type != htons(ETH_P_IPV6)) return -EINVAL; @@ -2781,7 +2783,7 @@ static int validate_set(const struct nlattr *a, return -EINVAL; break; - + } case OVS_KEY_ATTR_TCP: if ((eth_type != htons(ETH_P_IP) && eth_type != htons(ETH_P_IPV6)) || diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index 5904e93e57656d80632b00e288292706e8597ef9..fd8a01ca7a2d53d72766d5234e1f133caf4be68e 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -585,7 +585,8 @@ static struct sw_flow *masked_flow_lookup(struct table_instance *ti, head = find_bucket(ti, hash); (*n_mask_hit)++; - hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver]) { + hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver], + lockdep_ovsl_is_held()) { if (flow->mask == mask && flow->flow_table.hash == hash && flow_cmp_masked_key(flow, &masked_key, &mask->range)) return flow; @@ -769,7 +770,8 @@ struct sw_flow *ovs_flow_tbl_lookup_ufid(struct flow_table *tbl, hash = ufid_hash(ufid); head = find_bucket(ti, hash); - hlist_for_each_entry_rcu(flow, head, ufid_table.node[ti->node_ver]) { + hlist_for_each_entry_rcu(flow, head, ufid_table.node[ti->node_ver], + lockdep_ovsl_is_held()) { if (flow->ufid_table.hash == hash && ovs_flow_cmp_ufid(flow, ufid)) return flow; diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index 3323b79ff548dfbf7842b3ac3b825b7d0f7dcfde..5010d1ddd4bdb1f8b5fd34dbc97c7b3803552563 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -61,7 +61,8 @@ static struct dp_meter *lookup_meter(const struct datapath *dp, struct hlist_head *head; head = meter_hash_bucket(dp, meter_id); - hlist_for_each_entry_rcu(meter, head, dp_hash_node) { + hlist_for_each_entry_rcu(meter, head, dp_hash_node, + lockdep_ovsl_is_held()) { if (meter->id == meter_id) return meter; } diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 5da9392b03d624c2ae56b67366d3922e0000b079..47febb4504f098d2be91a1072fdd1daac71a9462 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -96,7 +96,8 @@ struct vport *ovs_vport_locate(const struct net *net, const char *name) struct hlist_head *bucket = hash_bucket(net, name); struct vport *vport; - hlist_for_each_entry_rcu(vport, bucket, hash_node) + hlist_for_each_entry_rcu(vport, bucket, hash_node, + lockdep_ovsl_is_held()) if (!strcmp(name, ovs_vport_name(vport)) && net_eq(ovs_dp_get_net(vport->dp), net)) return vport; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 30c6879d67748eb9c3275fb755aabe99e6073e4a..e5b0986215d25ee7d646c4de027bab4ecf897fcc 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2274,6 +2274,13 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, TP_STATUS_KERNEL, (macoff+snaplen)); if (!h.raw) goto drop_n_account; + + if (do_vnet && + virtio_net_hdr_from_skb(skb, h.raw + macoff - + sizeof(struct virtio_net_hdr), + vio_le(), true, 0)) + goto drop_n_account; + if (po->tp_version <= TPACKET_V2) { packet_increment_rx_head(po, &po->rx_ring); /* @@ -2286,12 +2293,6 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, status |= TP_STATUS_LOSING; } - if (do_vnet && - virtio_net_hdr_from_skb(skb, h.raw + macoff - - sizeof(struct virtio_net_hdr), - vio_le(), true, 0)) - goto drop_n_account; - po->stats.stats1.tp_packets++; if (copy_skb) { status |= TP_STATUS_COPY; diff --git a/net/rds/rdma.c b/net/rds/rdma.c index 3341eee87bf9b3c8bad89b88ca0e8fcd74186539..585e6b3b69ce4c32ec9404ee5ad88065b0979f75 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -162,10 +162,9 @@ static int rds_pin_pages(unsigned long user_addr, unsigned int nr_pages, if (write) gup_flags |= FOLL_WRITE; - ret = get_user_pages_fast(user_addr, nr_pages, gup_flags, pages); + ret = pin_user_pages_fast(user_addr, nr_pages, gup_flags, pages); if (ret >= 0 && ret < nr_pages) { - while (ret--) - put_page(pages[ret]); + unpin_user_pages(pages, ret); ret = -EFAULT; } @@ -300,8 +299,7 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, * to release anything. */ if (!need_odp) { - for (i = 0 ; i < nents; i++) - put_page(sg_page(&sg[i])); + unpin_user_pages(pages, nr_pages); kfree(sg); } ret = PTR_ERR(trans_private); @@ -325,7 +323,12 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, if (cookie_ret) *cookie_ret = cookie; - if (args->cookie_addr && put_user(cookie, (u64 __user *)(unsigned long) args->cookie_addr)) { + if (args->cookie_addr && + put_user(cookie, (u64 __user *)(unsigned long)args->cookie_addr)) { + if (!need_odp) { + unpin_user_pages(pages, nr_pages); + kfree(sg); + } ret = -EFAULT; goto out; } @@ -496,9 +499,7 @@ void rds_rdma_free_op(struct rm_rdma_op *ro) * is the case for a RDMA_READ which copies from remote * to local memory */ - if (!ro->op_write) - set_page_dirty(page); - put_page(page); + unpin_user_pages_dirty_lock(&page, 1, !ro->op_write); } } @@ -515,8 +516,7 @@ void rds_atomic_free_op(struct rm_atomic_op *ao) /* Mark page dirty if it was possibly modified, which * is the case for a RDMA_READ which copies from remote * to local memory */ - set_page_dirty(page); - put_page(page); + unpin_user_pages_dirty_lock(&page, 1, true); kfree(ao->op_notifier); ao->op_notifier = NULL; @@ -944,7 +944,7 @@ int rds_cmsg_atomic(struct rds_sock *rs, struct rds_message *rm, return ret; err: if (page) - put_page(page); + unpin_user_page(page); rm->atomic.op_active = 0; kfree(rm->atomic.op_notifier); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 90a31b15585f61a5a3c406eb3e3985679164e044..8c466a712cda047001973652603c4f0e0c4e2b4d 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -186,6 +186,7 @@ static size_t tcf_action_shared_attrs_size(const struct tc_action *act) + nla_total_size(IFNAMSIZ) /* TCA_ACT_KIND */ + cookie_len /* TCA_ACT_COOKIE */ + nla_total_size(0) /* TCA_ACT_STATS nested */ + + nla_total_size(sizeof(struct nla_bitfield32)) /* TCA_ACT_FLAGS */ /* TCA_STATS_BASIC */ + nla_total_size_64bit(sizeof(struct gnet_stats_basic)) /* TCA_STATS_PKT64 */ diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index f9c0d1e8d380152e4900e78e98c3edfca5deda29..d32d4233d33748c302600a229d207dcab3644266 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -305,6 +305,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct cls_fl_filter *f; list_for_each_entry_rcu(mask, &head->masks, list) { + flow_dissector_init_keys(&skb_key.control, &skb_key.basic); fl_clear_masked_range(&skb_key, mask); skb_flow_dissect_meta(skb, &mask->dissector, &skb_key); @@ -691,6 +692,7 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { .len = 128 / BITS_PER_BYTE }, [TCA_FLOWER_KEY_CT_LABELS_MASK] = { .type = NLA_BINARY, .len = 128 / BITS_PER_BYTE }, + [TCA_FLOWER_FLAGS] = { .type = NLA_U32 }, }; static const struct nla_policy diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index 039cc86974f4583472583c0260031ace609501b2..610a0b728161a32385465aff9e35903c302341a7 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -157,6 +157,7 @@ static void *mall_get(struct tcf_proto *tp, u32 handle) static const struct nla_policy mall_policy[TCA_MATCHALL_MAX + 1] = { [TCA_MATCHALL_UNSPEC] = { .type = NLA_UNSPEC }, [TCA_MATCHALL_CLASSID] = { .type = NLA_U32 }, + [TCA_MATCHALL_FLAGS] = { .type = NLA_U32 }, }; static int mall_set_parms(struct net *net, struct tcf_proto *tp, diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index a5a295477eccd52952e26e2ce121315341dddd0f..371ad84def3b6f1b5f0d0704b67723d0a8af22c6 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -744,6 +744,7 @@ static const struct nla_policy fq_policy[TCA_FQ_MAX + 1] = { [TCA_FQ_FLOW_MAX_RATE] = { .type = NLA_U32 }, [TCA_FQ_BUCKETS_LOG] = { .type = NLA_U32 }, [TCA_FQ_FLOW_REFILL_DELAY] = { .type = NLA_U32 }, + [TCA_FQ_ORPHAN_MASK] = { .type = NLA_U32 }, [TCA_FQ_LOW_RATE_THRESHOLD] = { .type = NLA_U32 }, [TCA_FQ_CE_THRESHOLD] = { .type = NLA_U32 }, }; diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 660fc45ee40fc0036996f701d8c1c3184f713640..b1eb12d33b9a6ca9d608d03684d884adc257f0ec 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -564,8 +564,10 @@ static struct sk_buff *taprio_dequeue_soft(struct Qdisc *sch) prio = skb->priority; tc = netdev_get_prio_tc_map(dev, prio); - if (!(gate_mask & BIT(tc))) + if (!(gate_mask & BIT(tc))) { + skb = NULL; continue; + } len = qdisc_pkt_len(skb); guard = ktime_add_ns(taprio_get_time(q), @@ -575,13 +577,17 @@ static struct sk_buff *taprio_dequeue_soft(struct Qdisc *sch) * guard band ... */ if (gate_mask != TAPRIO_ALL_GATES_OPEN && - ktime_after(guard, entry->close_time)) + ktime_after(guard, entry->close_time)) { + skb = NULL; continue; + } /* ... and no budget. */ if (gate_mask != TAPRIO_ALL_GATES_OPEN && - atomic_sub_return(len, &entry->budget) < 0) + atomic_sub_return(len, &entry->budget) < 0) { + skb = NULL; continue; + } skb = child->ops->dequeue(child); if (unlikely(!skb)) @@ -768,6 +774,7 @@ static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = { [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME] = { .type = NLA_S64 }, [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION] = { .type = NLA_S64 }, [TCA_TAPRIO_ATTR_FLAGS] = { .type = NLA_U32 }, + [TCA_TAPRIO_ATTR_TXTIME_DELAY] = { .type = NLA_U32 }, }; static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry, diff --git a/net/sctp/diag.c b/net/sctp/diag.c index 8a15146faaebdcb869233a08318e4fb5a1e1129b..1069d7af367290a42df7a52b2b0a3638c5b55f21 100644 --- a/net/sctp/diag.c +++ b/net/sctp/diag.c @@ -237,15 +237,11 @@ static size_t inet_assoc_attr_size(struct sctp_association *asoc) addrcnt++; return nla_total_size(sizeof(struct sctp_info)) - + nla_total_size(1) /* INET_DIAG_SHUTDOWN */ - + nla_total_size(1) /* INET_DIAG_TOS */ - + nla_total_size(1) /* INET_DIAG_TCLASS */ - + nla_total_size(4) /* INET_DIAG_MARK */ - + nla_total_size(4) /* INET_DIAG_CLASS_ID */ + nla_total_size(addrlen * asoc->peer.transport_count) + nla_total_size(addrlen * addrcnt) - + nla_total_size(sizeof(struct inet_diag_meminfo)) + nla_total_size(sizeof(struct inet_diag_msg)) + + inet_diag_msg_attrs_size() + + nla_total_size(sizeof(struct inet_diag_meminfo)) + 64; } diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 748e3b19ec1dc2c7d8ed1dbc83193b7f077c7eb2..6a16af4b1ef61810fed8a04169109f311b070575 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -170,6 +170,16 @@ static inline bool sctp_chunk_length_valid(struct sctp_chunk *chunk, return true; } +/* Check for format error in an ABORT chunk */ +static inline bool sctp_err_chunk_valid(struct sctp_chunk *chunk) +{ + struct sctp_errhdr *err; + + sctp_walk_errors(err, chunk->chunk_hdr); + + return (void *)err == (void *)chunk->chunk_end; +} + /********************************************************** * These are the state functions for handling chunk events. **********************************************************/ @@ -2255,6 +2265,9 @@ enum sctp_disposition sctp_sf_shutdown_pending_abort( sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + if (!sctp_err_chunk_valid(chunk)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + return __sctp_sf_do_9_1_abort(net, ep, asoc, type, arg, commands); } @@ -2298,6 +2311,9 @@ enum sctp_disposition sctp_sf_shutdown_sent_abort( sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + if (!sctp_err_chunk_valid(chunk)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + /* Stop the T2-shutdown timer. */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T2_SHUTDOWN)); @@ -2565,6 +2581,9 @@ enum sctp_disposition sctp_sf_do_9_1_abort( sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + if (!sctp_err_chunk_valid(chunk)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + return __sctp_sf_do_9_1_abort(net, ep, asoc, type, arg, commands); } @@ -2582,16 +2601,8 @@ static enum sctp_disposition __sctp_sf_do_9_1_abort( /* See if we have an error cause code in the chunk. */ len = ntohs(chunk->chunk_hdr->length); - if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr)) { - struct sctp_errhdr *err; - - sctp_walk_errors(err, chunk->chunk_hdr); - if ((void *)err != (void *)chunk->chunk_end) - return sctp_sf_pdiscard(net, ep, asoc, type, arg, - commands); - + if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr)) error = ((struct sctp_errhdr *)chunk->skb->data)->cause; - } sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNRESET)); /* ASSOC_FAILED will DELETE_TCB. */ diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index cee5bf4a9bb95a517861ddebc0c4deaf603da245..6fd44bdb0fc3ebb8d9b32e5aebbb494267d71b27 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -470,6 +470,8 @@ static void smc_switch_to_fallback(struct smc_sock *smc) if (smc->sk.sk_socket && smc->sk.sk_socket->file) { smc->clcsock->file = smc->sk.sk_socket->file; smc->clcsock->file->private_data = smc->clcsock; + smc->clcsock->wq.fasync_list = + smc->sk.sk_socket->wq.fasync_list; } } @@ -510,15 +512,18 @@ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code) static int smc_connect_abort(struct smc_sock *smc, int reason_code, int local_contact) { + bool is_smcd = smc->conn.lgr->is_smcd; + if (local_contact == SMC_FIRST_CONTACT) - smc_lgr_forget(smc->conn.lgr); - if (smc->conn.lgr->is_smcd) + smc_lgr_cleanup_early(&smc->conn); + else + smc_conn_free(&smc->conn); + if (is_smcd) /* there is only one lgr role for SMC-D; use server lock */ mutex_unlock(&smc_server_lgr_pending); else mutex_unlock(&smc_client_lgr_pending); - smc_conn_free(&smc->conn); smc->connect_nonblock = 0; return reason_code; } @@ -1089,7 +1094,6 @@ static void smc_listen_out_err(struct smc_sock *new_smc) if (newsmcsk->sk_state == SMC_INIT) sock_put(&new_smc->sk); /* passive closing */ newsmcsk->sk_state = SMC_CLOSED; - smc_conn_free(&new_smc->conn); smc_listen_out(new_smc); } @@ -1100,12 +1104,13 @@ static void smc_listen_decline(struct smc_sock *new_smc, int reason_code, { /* RDMA setup failed, switch back to TCP */ if (local_contact == SMC_FIRST_CONTACT) - smc_lgr_forget(new_smc->conn.lgr); + smc_lgr_cleanup_early(&new_smc->conn); + else + smc_conn_free(&new_smc->conn); if (reason_code < 0) { /* error, no fallback possible */ smc_listen_out_err(new_smc); return; } - smc_conn_free(&new_smc->conn); smc_switch_to_fallback(new_smc); new_smc->fallback_rsn = reason_code; if (reason_code && reason_code != SMC_CLC_DECL_PEERDECL) { @@ -1168,16 +1173,18 @@ static int smc_listen_ism_init(struct smc_sock *new_smc, new_smc->conn.lgr->vlan_id, new_smc->conn.lgr->smcd)) { if (ini->cln_first_contact == SMC_FIRST_CONTACT) - smc_lgr_forget(new_smc->conn.lgr); - smc_conn_free(&new_smc->conn); + smc_lgr_cleanup_early(&new_smc->conn); + else + smc_conn_free(&new_smc->conn); return SMC_CLC_DECL_SMCDNOTALK; } /* Create send and receive buffers */ if (smc_buf_create(new_smc, true)) { if (ini->cln_first_contact == SMC_FIRST_CONTACT) - smc_lgr_forget(new_smc->conn.lgr); - smc_conn_free(&new_smc->conn); + smc_lgr_cleanup_early(&new_smc->conn); + else + smc_conn_free(&new_smc->conn); return SMC_CLC_DECL_MEM; } diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 0879f7bed96752c6832d1777a31ff633ae4b1aec..86cccc24e52e2d047c5617af4421902e8dd6c747 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -372,7 +372,9 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info) dclc.hdr.length = htons(sizeof(struct smc_clc_msg_decline)); dclc.hdr.version = SMC_CLC_V1; dclc.hdr.flag = (peer_diag_info == SMC_CLC_DECL_SYNCERR) ? 1 : 0; - memcpy(dclc.id_for_peer, local_systemid, sizeof(local_systemid)); + if (smc->conn.lgr && !smc->conn.lgr->is_smcd) + memcpy(dclc.id_for_peer, local_systemid, + sizeof(local_systemid)); dclc.peer_diagnosis = htonl(peer_diag_info); memcpy(dclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 2249de5379ee900301cc9fc34cf84b51085399f5..5b085efa3bce49e4cc10185c90d61ef1ece7c5c0 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -162,6 +162,18 @@ static void smc_lgr_unregister_conn(struct smc_connection *conn) conn->lgr = NULL; } +void smc_lgr_cleanup_early(struct smc_connection *conn) +{ + struct smc_link_group *lgr = conn->lgr; + + if (!lgr) + return; + + smc_conn_free(conn); + smc_lgr_forget(lgr); + smc_lgr_schedule_free_work_fast(lgr); +} + /* Send delete link, either as client to request the initiation * of the DELETE LINK sequence from server; or as server to * initiate the delete processing. See smc_llc_rx_delete_link(). diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index c472e12951d1abbf52c8ab44f041b3042605b5e6..234ae25f0025f1ea641ce20868d0dd9e9bf8e814 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -296,6 +296,7 @@ struct smc_clc_msg_accept_confirm; struct smc_clc_msg_local; void smc_lgr_forget(struct smc_link_group *lgr); +void smc_lgr_cleanup_early(struct smc_connection *conn); void smc_lgr_terminate(struct smc_link_group *lgr, bool soft); void smc_port_terminate(struct smc_ib_device *smcibdev, u8 ibport); void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid, @@ -316,7 +317,6 @@ int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini); void smc_conn_free(struct smc_connection *conn); int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini); -void smcd_conn_free(struct smc_connection *conn); void smc_lgr_schedule_free_work_fast(struct smc_link_group *lgr); int smc_core_init(void); void smc_core_exit(void); diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index f38727ecf8b220b398f3ef622df1eccd03da1c56..e1f64f4ba2361432a58ce1d19ec0ecd41462971e 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -39,16 +39,15 @@ static void smc_diag_msg_common_fill(struct smc_diag_msg *r, struct sock *sk) { struct smc_sock *smc = smc_sk(sk); + memset(r, 0, sizeof(*r)); r->diag_family = sk->sk_family; + sock_diag_save_cookie(sk, r->id.idiag_cookie); if (!smc->clcsock) return; r->id.idiag_sport = htons(smc->clcsock->sk->sk_num); r->id.idiag_dport = smc->clcsock->sk->sk_dport; r->id.idiag_if = smc->clcsock->sk->sk_bound_dev_if; - sock_diag_save_cookie(sk, r->id.idiag_cookie); if (sk->sk_protocol == SMCPROTO_SMC) { - memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src)); - memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst)); r->id.idiag_src[0] = smc->clcsock->sk->sk_rcv_saddr; r->id.idiag_dst[0] = smc->clcsock->sk->sk_daddr; #if IS_ENABLED(CONFIG_IPV6) diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 548632621f4bc952b973c920af68f6477f0acc2b..05b825b3cfa4861cd0ab24b4ac9ad4476a75aabf 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -573,6 +573,8 @@ static void smc_ib_remove_dev(struct ib_device *ibdev, void *client_data) struct smc_ib_device *smcibdev; smcibdev = ib_get_client_data(ibdev, &smc_ib_client); + if (!smcibdev || smcibdev->ibdev != ibdev) + return; ib_set_client_data(ibdev, &smc_ib_client, NULL); spin_lock(&smc_ib_devices.lock); list_del_init(&smcibdev->list); /* remove from smc_ib_devices */ @@ -580,6 +582,7 @@ static void smc_ib_remove_dev(struct ib_device *ibdev, void *client_data) smc_smcr_terminate_all(smcibdev); smc_ib_cleanup_per_ibdev(smcibdev); ib_unregister_event_handler(&smcibdev->event_handler); + cancel_work_sync(&smcibdev->port_event_work); kfree(smcibdev); } diff --git a/net/socket.c b/net/socket.c index b79a05de7c6e9091df65f4aa4816af329cf2c0c8..2eecf1517f766bef06fbbd4fab0a60847f178e74 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1707,7 +1707,8 @@ SYSCALL_DEFINE2(listen, int, fd, int, backlog) int __sys_accept4_file(struct file *file, unsigned file_flags, struct sockaddr __user *upeer_sockaddr, - int __user *upeer_addrlen, int flags) + int __user *upeer_addrlen, int flags, + unsigned long nofile) { struct socket *sock, *newsock; struct file *newfile; @@ -1738,7 +1739,7 @@ int __sys_accept4_file(struct file *file, unsigned file_flags, */ __module_get(newsock->ops->owner); - newfd = get_unused_fd_flags(flags); + newfd = __get_unused_fd_flags(flags, nofile); if (unlikely(newfd < 0)) { err = newfd; sock_release(newsock); @@ -1807,7 +1808,8 @@ int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, f = fdget(fd); if (f.file) { ret = __sys_accept4_file(f.file, 0, upeer_sockaddr, - upeer_addrlen, flags); + upeer_addrlen, flags, + rlimit(RLIMIT_NOFILE)); if (f.flags) fput(f.file); } diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 095be887753e026035ee25381b47528cf41d40ac..125297c9aa3e761185b3ddee8d681a5841ede944 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -288,8 +288,8 @@ struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt, { struct rpcrdma_ia *ia = &r_xprt->rx_ia; struct ib_reg_wr *reg_wr; + int i, n, dma_nents; struct ib_mr *ibmr; - int i, n; u8 key; if (nsegs > ia->ri_max_frwr_depth) @@ -313,15 +313,16 @@ struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt, break; } mr->mr_dir = rpcrdma_data_dir(writing); + mr->mr_nents = i; - mr->mr_nents = - ib_dma_map_sg(ia->ri_id->device, mr->mr_sg, i, mr->mr_dir); - if (!mr->mr_nents) + dma_nents = ib_dma_map_sg(ia->ri_id->device, mr->mr_sg, mr->mr_nents, + mr->mr_dir); + if (!dma_nents) goto out_dmamap_err; ibmr = mr->frwr.fr_mr; - n = ib_map_mr_sg(ibmr, mr->mr_sg, mr->mr_nents, NULL, PAGE_SIZE); - if (unlikely(n != mr->mr_nents)) + n = ib_map_mr_sg(ibmr, mr->mr_sg, dma_nents, NULL, PAGE_SIZE); + if (n != dma_nents) goto out_mapmr_err; ibmr->iova &= 0x00000000ffffffff; diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index 7c35094c20b8b7af139a05220745af9d0fe61e04..bb9862410e689e992ccd22bb6b598ff2bdba17b2 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -116,6 +116,7 @@ const struct nla_policy tipc_nl_prop_policy[TIPC_NLA_PROP_MAX + 1] = { [TIPC_NLA_PROP_PRIO] = { .type = NLA_U32 }, [TIPC_NLA_PROP_TOL] = { .type = NLA_U32 }, [TIPC_NLA_PROP_WIN] = { .type = NLA_U32 }, + [TIPC_NLA_PROP_MTU] = { .type = NLA_U32 }, [TIPC_NLA_PROP_BROADCAST] = { .type = NLA_U32 }, [TIPC_NLA_PROP_BROADCAST_RATIO] = { .type = NLA_U32 } }; diff --git a/net/tipc/node.c b/net/tipc/node.c index 99b28b69fc174a09cd6a73db84e7149ba673d51a..0c88778c88b5f142772330123998978fc50284a8 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -278,7 +278,7 @@ struct tipc_crypto *tipc_node_crypto_rx_by_list(struct list_head *pos) } #endif -void tipc_node_free(struct rcu_head *rp) +static void tipc_node_free(struct rcu_head *rp) { struct tipc_node *n = container_of(rp, struct tipc_node, rcu); @@ -2798,7 +2798,7 @@ static int tipc_nl_retrieve_nodeid(struct nlattr **attrs, u8 **node_id) return 0; } -int __tipc_nl_node_set_key(struct sk_buff *skb, struct genl_info *info) +static int __tipc_nl_node_set_key(struct sk_buff *skb, struct genl_info *info) { struct nlattr *attrs[TIPC_NLA_NODE_MAX + 1]; struct net *net = sock_net(skb->sk); @@ -2875,7 +2875,8 @@ int tipc_nl_node_set_key(struct sk_buff *skb, struct genl_info *info) return err; } -int __tipc_nl_node_flush_key(struct sk_buff *skb, struct genl_info *info) +static int __tipc_nl_node_flush_key(struct sk_buff *skb, + struct genl_info *info) { struct net *net = sock_net(skb->sk); struct tipc_net *tn = tipc_net(net); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index f9b4fb92c0b1c98f373bc2346e5d5e77c86d48f8..693e8902161efaa35f918dae4731a5c3a081c5fd 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2441,6 +2441,8 @@ static int tipc_wait_for_connect(struct socket *sock, long *timeo_p) return -ETIMEDOUT; if (signal_pending(current)) return sock_intr_errno(*timeo_p); + if (sk->sk_state == TIPC_DISCONNECTING) + break; add_wait_queue(sk_sleep(sk), &wait); done = sk_wait_event(sk, timeo_p, tipc_sk_connected(sk), diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 1ba5a92832bb0e065e0e9b8ac6f742b24d1d13c5..1c5574e2e05825140fd4b2ffc2ecd636147aba63 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -593,7 +593,7 @@ struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context, u32 seq, u64 *p_record_sn) { u64 record_sn = context->hint_record_sn; - struct tls_record_info *info; + struct tls_record_info *info, *last; info = context->retransmit_hint; if (!info || @@ -605,6 +605,24 @@ struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context, struct tls_record_info, list); if (!info) return NULL; + /* send the start_marker record if seq number is before the + * tls offload start marker sequence number. This record is + * required to handle TCP packets which are before TLS offload + * started. + * And if it's not start marker, look if this seq number + * belongs to the list. + */ + if (likely(!tls_record_is_start_marker(info))) { + /* we have the first record, get the last record to see + * if this seq number belongs to the list. + */ + last = list_last_entry(&context->records_list, + struct tls_record_info, list); + + if (!between(seq, tls_record_start_seq(info), + last->end_seq)) + return NULL; + } record_sn = context->unacked_record_sn; } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 62c12cb5763e6d0ec4ef7daefd6836b6588b7185..68debcb28fa4c46eb2b75b0ec262958299eda960 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -682,6 +682,7 @@ static int unix_set_peek_off(struct sock *sk, int val) return 0; } +#ifdef CONFIG_PROC_FS static void unix_show_fdinfo(struct seq_file *m, struct socket *sock) { struct sock *sk = sock->sk; @@ -692,6 +693,9 @@ static void unix_show_fdinfo(struct seq_file *m, struct socket *sock) seq_printf(m, "scm_fds: %u\n", READ_ONCE(u->scm_stat.nr_fds)); } } +#else +#define unix_show_fdinfo NULL +#endif static const struct proto_ops unix_stream_ops = { .family = PF_UNIX, diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 9c5b2a91baad60945cd06881c57d1b0c56810a58..a5f28708e0e75402e595a38ee91c57e9637e0289 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -451,6 +451,12 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) if (vsk->transport == new_transport) return 0; + /* transport->release() must be called with sock lock acquired. + * This path can only be taken during vsock_stream_connect(), + * where we have already held the sock lock. + * In the other cases, this function is called on a new socket + * which is not assigned to any transport. + */ vsk->transport->release(vsk); vsock_deassign_transport(vsk); } @@ -753,20 +759,18 @@ static void __vsock_release(struct sock *sk, int level) vsk = vsock_sk(sk); pending = NULL; /* Compiler warning. */ - /* The release call is supposed to use lock_sock_nested() - * rather than lock_sock(), if a sock lock should be acquired. - */ - if (vsk->transport) - vsk->transport->release(vsk); - else if (sk->sk_type == SOCK_STREAM) - vsock_remove_sock(vsk); - /* When "level" is SINGLE_DEPTH_NESTING, use the nested * version to avoid the warning "possible recursive locking * detected". When "level" is 0, lock_sock_nested(sk, level) * is the same as lock_sock(sk). */ lock_sock_nested(sk, level); + + if (vsk->transport) + vsk->transport->release(vsk); + else if (sk->sk_type == SOCK_STREAM) + vsock_remove_sock(vsk); + sock_orphan(sk); sk->sk_shutdown = SHUTDOWN_MASK; diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c index 3492c021925f4b2163ff5aff46d334ae64bbdc41..630b851f8150fd2e67eac5187d75a1771b82f068 100644 --- a/net/vmw_vsock/hyperv_transport.c +++ b/net/vmw_vsock/hyperv_transport.c @@ -526,12 +526,9 @@ static bool hvs_close_lock_held(struct vsock_sock *vsk) static void hvs_release(struct vsock_sock *vsk) { - struct sock *sk = sk_vsock(vsk); bool remove_sock; - lock_sock_nested(sk, SINGLE_DEPTH_NESTING); remove_sock = hvs_close_lock_held(vsk); - release_sock(sk); if (remove_sock) vsock_remove_sock(vsk); } diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index d9f0c9c5425a424c2c54e7794cd97764a9735ee1..f3c4bab2f737c97c08e38237b8108209f45eccad 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -829,7 +829,6 @@ void virtio_transport_release(struct vsock_sock *vsk) struct sock *sk = &vsk->sk; bool remove_sock = true; - lock_sock_nested(sk, SINGLE_DEPTH_NESTING); if (sk->sk_type == SOCK_STREAM) remove_sock = virtio_transport_close(vsk); @@ -837,7 +836,6 @@ void virtio_transport_release(struct vsock_sock *vsk) list_del(&pkt->list); virtio_transport_free_pkt(pkt); } - release_sock(sk); if (remove_sock) vsock_remove_sock(vsk); diff --git a/net/wireless/ethtool.c b/net/wireless/ethtool.c index a9c0f368db5d27ed72159a2395a4a4ec60234ed0..24e18405cdb48fff6090831f656b4f883c926109 100644 --- a/net/wireless/ethtool.c +++ b/net/wireless/ethtool.c @@ -7,9 +7,13 @@ void cfg80211_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { struct wireless_dev *wdev = dev->ieee80211_ptr; + struct device *pdev = wiphy_dev(wdev->wiphy); - strlcpy(info->driver, wiphy_dev(wdev->wiphy)->driver->name, - sizeof(info->driver)); + if (pdev->driver) + strlcpy(info->driver, pdev->driver->name, + sizeof(info->driver)); + else + strlcpy(info->driver, "N/A", sizeof(info->driver)); strlcpy(info->version, init_utsname()->release, sizeof(info->version)); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 123b8d720a596d31cf7abff3b450cc1c64ee8441..ec5d67794aab67a2f7c56a880c7fd8510860dada 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -437,6 +438,7 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_CONTROL_PORT_NO_ENCRYPT] = { .type = NLA_FLAG }, [NL80211_ATTR_CONTROL_PORT_OVER_NL80211] = { .type = NLA_FLAG }, [NL80211_ATTR_PRIVACY] = { .type = NLA_FLAG }, + [NL80211_ATTR_STATUS_CODE] = { .type = NLA_U16 }, [NL80211_ATTR_CIPHER_SUITE_GROUP] = { .type = NLA_U32 }, [NL80211_ATTR_WPA_VERSIONS] = { .type = NLA_U32 }, [NL80211_ATTR_PID] = { .type = NLA_U32 }, @@ -468,6 +470,8 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_WOWLAN_TRIGGERS] = { .type = NLA_NESTED }, [NL80211_ATTR_STA_PLINK_STATE] = NLA_POLICY_MAX(NLA_U8, NUM_NL80211_PLINK_STATES - 1), + [NL80211_ATTR_MEASUREMENT_DURATION] = { .type = NLA_U16 }, + [NL80211_ATTR_MEASUREMENT_DURATION_MANDATORY] = { .type = NLA_FLAG }, [NL80211_ATTR_MESH_PEER_AID] = NLA_POLICY_RANGE(NLA_U16, 1, IEEE80211_MAX_AID), [NL80211_ATTR_SCHED_SCAN_INTERVAL] = { .type = NLA_U32 }, @@ -529,6 +533,8 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_MDID] = { .type = NLA_U16 }, [NL80211_ATTR_IE_RIC] = { .type = NLA_BINARY, .len = IEEE80211_MAX_DATA_LEN }, + [NL80211_ATTR_CRIT_PROT_ID] = { .type = NLA_U16 }, + [NL80211_ATTR_MAX_CRIT_PROT_DURATION] = { .type = NLA_U16 }, [NL80211_ATTR_PEER_AID] = NLA_POLICY_RANGE(NLA_U16, 1, IEEE80211_MAX_AID), [NL80211_ATTR_CH_SWITCH_COUNT] = { .type = NLA_U32 }, @@ -559,6 +565,7 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { NLA_POLICY_MAX(NLA_U8, IEEE80211_NUM_UPS - 1), [NL80211_ATTR_ADMITTED_TIME] = { .type = NLA_U16 }, [NL80211_ATTR_SMPS_MODE] = { .type = NLA_U8 }, + [NL80211_ATTR_OPER_CLASS] = { .type = NLA_U8 }, [NL80211_ATTR_MAC_MASK] = { .type = NLA_EXACT_LEN_WARN, .len = ETH_ALEN @@ -4799,8 +4806,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) err = nl80211_parse_he_obss_pd( info->attrs[NL80211_ATTR_HE_OBSS_PD], ¶ms.he_obss_pd); - if (err) - return err; + goto out; } nl80211_calculate_ap_params(¶ms); @@ -4822,6 +4828,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) } wdev_unlock(wdev); +out: kfree(params.acl); return err; diff --git a/net/wireless/reg.c b/net/wireless/reg.c index fff9a74891fc433e5ac05970b23aa7f13adaad78..1a8218f1bbe075457441e39da8e14220e375701d 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2276,7 +2276,7 @@ static void handle_channel_custom(struct wiphy *wiphy, break; } - if (IS_ERR(reg_rule)) { + if (IS_ERR_OR_NULL(reg_rule)) { pr_debug("Disabling freq %d MHz as custom regd has no rule that fits it\n", chan->center_freq); if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) { diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index df600487a68d513c3f7abcb1b584d2f4c229a7dd..356f90e4522b4cc39bf05ae4765d0517c43e5dc4 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -217,6 +217,7 @@ static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) static void xsk_flush(struct xdp_sock *xs) { xskq_prod_submit(xs->rx); + __xskq_cons_release(xs->umem->fq); sock_def_readable(&xs->sk); } @@ -304,6 +305,7 @@ void xsk_umem_consume_tx_done(struct xdp_umem *umem) rcu_read_lock(); list_for_each_entry_rcu(xs, &umem->xsk_list, list) { + __xskq_cons_release(xs->tx); xs->sk.sk_write_space(&xs->sk); } rcu_read_unlock(); diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index bec2af11853addb48c658b7e046383ef8025169f..89a01ac4e07965cfafc342d205fbf21edc366c0b 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -271,7 +271,8 @@ static inline void xskq_cons_release(struct xsk_queue *q) { /* To improve performance, only update local state here. * Reflect this to global state when we get new entries - * from the ring in xskq_cons_get_entries(). + * from the ring in xskq_cons_get_entries() and whenever + * Rx or Tx processing are completed in the NAPI loop. */ q->cached_cons++; } diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index dc651a628dcf07df229ff85878c744a257f01f49..3361e3ac5714cc6c751afe3eed996f8956180696 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@ -300,10 +300,10 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); } else { - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, - htonl(mtu)); + icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, + htonl(mtu)); } dst_release(dst); diff --git a/scripts/Kconfig.include b/scripts/Kconfig.include index 85334dc8c997e62182446ea4aa3dd57bd944de21..496d11c92c97e75843a9ba3a99390f55261f1add 100644 --- a/scripts/Kconfig.include +++ b/scripts/Kconfig.include @@ -44,3 +44,10 @@ $(error-if,$(success, $(LD) -v | grep -q gold), gold linker '$(LD)' not supporte # gcc version including patch level gcc-version := $(shell,$(srctree)/scripts/gcc-version.sh $(CC)) + +# machine bit flags +# $(m32-flag): -m32 if the compiler supports it, or an empty string otherwise. +# $(m64-flag): -m64 if the compiler supports it, or an empty string otherwise. +cc-option-bit = $(if-success,$(CC) -Werror $(1) -E -x c /dev/null -o /dev/null,$(1)) +m32-flag := $(cc-option-bit,-m32) +m64-flag := $(cc-option-bit,-m64) diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn index ecddf83ac14291408e38967cac787d27c1c2e1d6..ca08f2fe7c344b1678c795575ddedc9ec088394d 100644 --- a/scripts/Makefile.extrawarn +++ b/scripts/Makefile.extrawarn @@ -48,6 +48,7 @@ KBUILD_CFLAGS += -Wno-initializer-overrides KBUILD_CFLAGS += -Wno-format KBUILD_CFLAGS += -Wno-sign-compare KBUILD_CFLAGS += -Wno-format-zero-length +KBUILD_CFLAGS += $(call cc-disable-warning, pointer-to-enum-cast) endif endif diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index bae62549e3d2a3308b1683f375fd4d9004cbe6f2..752ff0a225a9d3d4caaf824ac7a2272743234451 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -300,15 +300,15 @@ DT_BINDING_DIR := Documentation/devicetree/bindings DT_TMP_SCHEMA := $(objtree)/$(DT_BINDING_DIR)/processed-schema.yaml quiet_cmd_dtb_check = CHECK $@ - cmd_dtb_check = $(DT_CHECKER) -u $(srctree)/$(DT_BINDING_DIR) -p $(DT_TMP_SCHEMA) $@ ; + cmd_dtb_check = $(DT_CHECKER) -u $(srctree)/$(DT_BINDING_DIR) -p $(DT_TMP_SCHEMA) $@ -define rule_dtc_dt_yaml +define rule_dtc $(call cmd_and_fixdep,dtc,yaml) $(call cmd,dtb_check) endef $(obj)/%.dt.yaml: $(src)/%.dts $(DTC) $(DT_TMP_SCHEMA) FORCE - $(call if_changed_rule,dtc_dt_yaml) + $(call if_changed_rule,dtc) dtc-tmp = $(subst $(comma),_,$(dot-target).dts.tmp) diff --git a/scripts/export_report.pl b/scripts/export_report.pl index 548330e8c4e7a35028b7f60bf58708d02a853bd7..feb3d5542a62d90b7af4f041d98a3c4b5ac386c0 100755 --- a/scripts/export_report.pl +++ b/scripts/export_report.pl @@ -94,7 +94,7 @@ if (defined $opt{'o'}) { # while ( <$module_symvers> ) { chomp; - my (undef, $symbol, $namespace, $module, $gpl) = split('\t'); + my (undef, $symbol, $module, $gpl, $namespace) = split('\t'); $SYMBOL { $symbol } = [ $module , "0" , $symbol, $gpl]; } close($module_symvers); diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index 34085d146fa2cadb0a92353c0f6cc0d89303af29..6cbcd1a3e113c1f5866fc02ae4f8b40f16276be0 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -932,10 +932,6 @@ sub get_maintainers { } } - foreach my $fix (@fixes) { - vcs_add_commit_signers($fix, "blamed_fixes"); - } - foreach my $email (@email_to, @list_to) { $email->[0] = deduplicate_email($email->[0]); } @@ -974,6 +970,10 @@ sub get_maintainers { } } + foreach my $fix (@fixes) { + vcs_add_commit_signers($fix, "blamed_fixes"); + } + my @to = (); if ($email || $email_list) { if ($email) { @@ -1341,35 +1341,11 @@ sub add_categories { } } } elsif ($ptype eq "M") { - my ($name, $address) = parse_email($pvalue); - if ($name eq "") { - if ($i > 0) { - my $tv = $typevalue[$i - 1]; - if ($tv =~ m/^([A-Z]):\s*(.*)/) { - if ($1 eq "P") { - $name = $2; - $pvalue = format_email($name, $address, $email_usename); - } - } - } - } if ($email_maintainer) { my $role = get_maintainer_role($i); push_email_addresses($pvalue, $role); } } elsif ($ptype eq "R") { - my ($name, $address) = parse_email($pvalue); - if ($name eq "") { - if ($i > 0) { - my $tv = $typevalue[$i - 1]; - if ($tv =~ m/^([A-Z]):\s*(.*)/) { - if ($1 eq "P") { - $name = $2; - $pvalue = format_email($name, $address, $email_usename); - } - } - } - } if ($email_reviewer) { my $subsystem = get_subsystem_name($i); push_email_addresses($pvalue, "reviewer:$subsystem"); diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index a566d8201b56c530d93cee048d9a45a6a3ab26a9..3e8dea6e0a9572c21b719b8ac111ed8097bab77e 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -195,13 +195,13 @@ static struct sym_entry *read_symbol(FILE *in) return NULL; } - if (is_ignored_symbol(name, type)) - return NULL; - - /* Ignore most absolute/undefined (?) symbols. */ if (strcmp(name, "_text") == 0) _text = addr; + /* Ignore most absolute/undefined (?) symbols. */ + if (is_ignored_symbol(name, type)) + return NULL; + check_symbol_range(name, addr, text_ranges, ARRAY_SIZE(text_ranges)); check_symbol_range(name, addr, &percpu_range, 1); @@ -210,7 +210,7 @@ static struct sym_entry *read_symbol(FILE *in) len = strlen(name) + 1; - sym = malloc(sizeof(*sym) + len); + sym = malloc(sizeof(*sym) + len + 1); if (!sym) { fprintf(stderr, "kallsyms failure: " "unable to allocate required amount of memory\n"); @@ -219,7 +219,7 @@ static struct sym_entry *read_symbol(FILE *in) sym->addr = addr; sym->len = len; sym->sym[0] = type; - memcpy(sym_name(sym), name, len); + strcpy(sym_name(sym), name); sym->percpu_absolute = 0; return sym; diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 1919c311c1491af4027ebdccc3b998308da4043f..dd484e92752edf3509e2e8b74ff0e395e46e4470 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -239,7 +239,7 @@ else fi; # final build of init/ -${MAKE} -f "${srctree}/scripts/Makefile.build" obj=init +${MAKE} -f "${srctree}/scripts/Makefile.build" obj=init need-builtin=1 #link vmlinux.o info LD vmlinux.o diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 7edfdb2f4497ac471b116733c48165699a015f0c..55a0a2eccbd2bce1948009dfa51c40344fd1f22c 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -308,7 +308,8 @@ static const char *sec_name(struct elf_info *elf, int secindex) static void *sym_get_data(const struct elf_info *info, const Elf_Sym *sym) { - Elf_Shdr *sechdr = &info->sechdrs[sym->st_shndx]; + unsigned int secindex = get_secindex(info, sym); + Elf_Shdr *sechdr = &info->sechdrs[secindex]; unsigned long offset; offset = sym->st_value; @@ -2427,7 +2428,7 @@ static void write_if_changed(struct buffer *b, const char *fname) } /* parse Module.symvers file. line format: - * 0x12345678symbolmodule[[export]something] + * 0x12345678symbolmoduleexportnamespace **/ static void read_dump(const char *fname, unsigned int kernel) { @@ -2440,7 +2441,7 @@ static void read_dump(const char *fname, unsigned int kernel) return; while ((line = get_next_line(&pos, file, size))) { - char *symname, *namespace, *modname, *d, *export, *end; + char *symname, *namespace, *modname, *d, *export; unsigned int crc; struct module *mod; struct symbol *s; @@ -2448,16 +2449,16 @@ static void read_dump(const char *fname, unsigned int kernel) if (!(symname = strchr(line, '\t'))) goto fail; *symname++ = '\0'; - if (!(namespace = strchr(symname, '\t'))) - goto fail; - *namespace++ = '\0'; - if (!(modname = strchr(namespace, '\t'))) + if (!(modname = strchr(symname, '\t'))) goto fail; *modname++ = '\0'; - if ((export = strchr(modname, '\t')) != NULL) - *export++ = '\0'; - if (export && ((end = strchr(export, '\t')) != NULL)) - *end = '\0'; + if (!(export = strchr(modname, '\t'))) + goto fail; + *export++ = '\0'; + if (!(namespace = strchr(export, '\t'))) + goto fail; + *namespace++ = '\0'; + crc = strtoul(line, &d, 16); if (*symname == '\0' || *modname == '\0' || *d != '\0') goto fail; @@ -2508,9 +2509,9 @@ static void write_dump(const char *fname) namespace = symbol->namespace; buf_printf(&buf, "0x%08x\t%s\t%s\t%s\t%s\n", symbol->crc, symbol->name, - namespace ? namespace : "", symbol->module->name, - export_str(symbol->export)); + export_str(symbol->export), + namespace ? namespace : ""); } symbol = symbol->next; } diff --git a/scripts/parse-maintainers.pl b/scripts/parse-maintainers.pl old mode 100644 new mode 100755 diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig index 711ff10fa36eca6ad201deca04abc41ff2858339..3f3ee4e2eb0d1c739ca57f93ad1dd7fe421157ff 100644 --- a/security/integrity/ima/Kconfig +++ b/security/integrity/ima/Kconfig @@ -112,6 +112,10 @@ choice config IMA_DEFAULT_HASH_WP512 bool "WP512" depends on CRYPTO_WP512=y && !IMA_TEMPLATE + + config IMA_DEFAULT_HASH_SM3 + bool "SM3" + depends on CRYPTO_SM3=y && !IMA_TEMPLATE endchoice config IMA_DEFAULT_HASH @@ -121,6 +125,7 @@ config IMA_DEFAULT_HASH default "sha256" if IMA_DEFAULT_HASH_SHA256 default "sha512" if IMA_DEFAULT_HASH_SHA512 default "wp512" if IMA_DEFAULT_HASH_WP512 + default "sm3" if IMA_DEFAULT_HASH_SM3 config IMA_WRITE_POLICY bool "Enable multiple writes to the IMA policy" diff --git a/security/integrity/platform_certs/load_uefi.c b/security/integrity/platform_certs/load_uefi.c index 111898aad56e48b99d93d55411adedbc82ad8670..f0c908241966ae3f387a55d4ddc813150135b91b 100644 --- a/security/integrity/platform_certs/load_uefi.c +++ b/security/integrity/platform_certs/load_uefi.c @@ -35,16 +35,18 @@ static __init bool uefi_check_ignore_db(void) * Get a certificate list blob from the named EFI variable. */ static __init void *get_cert_list(efi_char16_t *name, efi_guid_t *guid, - unsigned long *size) + unsigned long *size, efi_status_t *status) { - efi_status_t status; unsigned long lsize = 4; unsigned long tmpdb[4]; void *db; - status = efi.get_variable(name, guid, NULL, &lsize, &tmpdb); - if (status != EFI_BUFFER_TOO_SMALL) { - pr_err("Couldn't get size: 0x%lx\n", status); + *status = efi.get_variable(name, guid, NULL, &lsize, &tmpdb); + if (*status == EFI_NOT_FOUND) + return NULL; + + if (*status != EFI_BUFFER_TOO_SMALL) { + pr_err("Couldn't get size: 0x%lx\n", *status); return NULL; } @@ -52,10 +54,10 @@ static __init void *get_cert_list(efi_char16_t *name, efi_guid_t *guid, if (!db) return NULL; - status = efi.get_variable(name, guid, NULL, &lsize, db); - if (status != EFI_SUCCESS) { + *status = efi.get_variable(name, guid, NULL, &lsize, db); + if (*status != EFI_SUCCESS) { kfree(db); - pr_err("Error reading db var: 0x%lx\n", status); + pr_err("Error reading db var: 0x%lx\n", *status); return NULL; } @@ -74,6 +76,7 @@ static int __init load_uefi_certs(void) efi_guid_t mok_var = EFI_SHIM_LOCK_GUID; void *db = NULL, *dbx = NULL, *mok = NULL; unsigned long dbsize = 0, dbxsize = 0, moksize = 0; + efi_status_t status; int rc = 0; if (!efi.get_variable) @@ -83,9 +86,12 @@ static int __init load_uefi_certs(void) * an error if we can't get them. */ if (!uefi_check_ignore_db()) { - db = get_cert_list(L"db", &secure_var, &dbsize); + db = get_cert_list(L"db", &secure_var, &dbsize, &status); if (!db) { - pr_err("MODSIGN: Couldn't get UEFI db list\n"); + if (status == EFI_NOT_FOUND) + pr_debug("MODSIGN: db variable wasn't found\n"); + else + pr_err("MODSIGN: Couldn't get UEFI db list\n"); } else { rc = parse_efi_signature_list("UEFI:db", db, dbsize, get_handler_for_db); @@ -96,9 +102,12 @@ static int __init load_uefi_certs(void) } } - mok = get_cert_list(L"MokListRT", &mok_var, &moksize); + mok = get_cert_list(L"MokListRT", &mok_var, &moksize, &status); if (!mok) { - pr_info("Couldn't get UEFI MokListRT\n"); + if (status == EFI_NOT_FOUND) + pr_debug("MokListRT variable wasn't found\n"); + else + pr_info("Couldn't get UEFI MokListRT\n"); } else { rc = parse_efi_signature_list("UEFI:MokListRT", mok, moksize, get_handler_for_db); @@ -107,9 +116,12 @@ static int __init load_uefi_certs(void) kfree(mok); } - dbx = get_cert_list(L"dbx", &secure_var, &dbxsize); + dbx = get_cert_list(L"dbx", &secure_var, &dbxsize, &status); if (!dbx) { - pr_info("Couldn't get UEFI dbx list\n"); + if (status == EFI_NOT_FOUND) + pr_debug("dbx variable wasn't found\n"); + else + pr_info("Couldn't get UEFI dbx list\n"); } else { rc = parse_efi_signature_list("UEFI:dbx", dbx, dbxsize, diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 4b6991e178d37e5916f33bb6ec3911aa550985c7..1659b59fb5d77d10736cb2aa6f63c7c90aebdaaa 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -698,7 +698,7 @@ static int selinux_set_mnt_opts(struct super_block *sb, if (!strcmp(sb->s_type->name, "debugfs") || !strcmp(sb->s_type->name, "tracefs") || - !strcmp(sb->s_type->name, "binderfs") || + !strcmp(sb->s_type->name, "binder") || !strcmp(sb->s_type->name, "pstore")) sbsec->flags |= SE_SBGENFS; diff --git a/security/selinux/ss/sidtab.c b/security/selinux/ss/sidtab.c index a308ce1e6a13b2af9a9342c75df8ede272614461..f511ffccb131cbe533a733a176f5a17ff22de3fc 100644 --- a/security/selinux/ss/sidtab.c +++ b/security/selinux/ss/sidtab.c @@ -518,19 +518,13 @@ void sidtab_sid2str_put(struct sidtab *s, struct sidtab_entry *entry, const char *str, u32 str_len) { struct sidtab_str_cache *cache, *victim = NULL; + unsigned long flags; /* do not cache invalid contexts */ if (entry->context.len) return; - /* - * Skip the put operation when in non-task context to avoid the need - * to disable interrupts while holding s->cache_lock. - */ - if (!in_task()) - return; - - spin_lock(&s->cache_lock); + spin_lock_irqsave(&s->cache_lock, flags); cache = rcu_dereference_protected(entry->cache, lockdep_is_held(&s->cache_lock)); @@ -561,7 +555,7 @@ void sidtab_sid2str_put(struct sidtab *s, struct sidtab_entry *entry, rcu_assign_pointer(entry->cache, cache); out_unlock: - spin_unlock(&s->cache_lock); + spin_unlock_irqrestore(&s->cache_lock, flags); kfree_rcu(victim, rcu_member); } diff --git a/sound/core/oss/pcm_plugin.c b/sound/core/oss/pcm_plugin.c index 240e4702c09881409cd3de59306bae2409d5258f..752d078908e9d017ad633da45c052e22c6ba9b25 100644 --- a/sound/core/oss/pcm_plugin.c +++ b/sound/core/oss/pcm_plugin.c @@ -111,7 +111,7 @@ int snd_pcm_plug_alloc(struct snd_pcm_substream *plug, snd_pcm_uframes_t frames) while (plugin->next) { if (plugin->dst_frames) frames = plugin->dst_frames(plugin, frames); - if (snd_BUG_ON((snd_pcm_sframes_t)frames <= 0)) + if ((snd_pcm_sframes_t)frames <= 0) return -ENXIO; plugin = plugin->next; err = snd_pcm_plugin_alloc(plugin, frames); @@ -123,7 +123,7 @@ int snd_pcm_plug_alloc(struct snd_pcm_substream *plug, snd_pcm_uframes_t frames) while (plugin->prev) { if (plugin->src_frames) frames = plugin->src_frames(plugin, frames); - if (snd_BUG_ON((snd_pcm_sframes_t)frames <= 0)) + if ((snd_pcm_sframes_t)frames <= 0) return -ENXIO; plugin = plugin->prev; err = snd_pcm_plugin_alloc(plugin, frames); @@ -209,6 +209,8 @@ snd_pcm_sframes_t snd_pcm_plug_client_size(struct snd_pcm_substream *plug, snd_p if (stream == SNDRV_PCM_STREAM_PLAYBACK) { plugin = snd_pcm_plug_last(plug); while (plugin && drv_frames > 0) { + if (drv_frames > plugin->buf_frames) + drv_frames = plugin->buf_frames; plugin_prev = plugin->prev; if (plugin->src_frames) drv_frames = plugin->src_frames(plugin, drv_frames); @@ -220,6 +222,8 @@ snd_pcm_sframes_t snd_pcm_plug_client_size(struct snd_pcm_substream *plug, snd_p plugin_next = plugin->next; if (plugin->dst_frames) drv_frames = plugin->dst_frames(plugin, drv_frames); + if (drv_frames > plugin->buf_frames) + drv_frames = plugin->buf_frames; plugin = plugin_next; } } else @@ -248,11 +252,15 @@ snd_pcm_sframes_t snd_pcm_plug_slave_size(struct snd_pcm_substream *plug, snd_pc if (frames < 0) return frames; } + if (frames > plugin->buf_frames) + frames = plugin->buf_frames; plugin = plugin_next; } } else if (stream == SNDRV_PCM_STREAM_CAPTURE) { plugin = snd_pcm_plug_last(plug); while (plugin) { + if (frames > plugin->buf_frames) + frames = plugin->buf_frames; plugin_prev = plugin->prev; if (plugin->src_frames) { frames = plugin->src_frames(plugin, frames); diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 336406bcb59e2cd3ded45db70449d390deac2850..d5443eeb8b6338a2a51d7a1c158e4d87c0184e16 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -2594,7 +2594,8 @@ void snd_pcm_release_substream(struct snd_pcm_substream *substream) snd_pcm_drop(substream); if (substream->hw_opened) { - do_hw_free(substream); + if (substream->runtime->status->state != SNDRV_PCM_STATE_OPEN) + do_hw_free(substream); substream->ops->close(substream); substream->hw_opened = 0; } diff --git a/sound/core/seq/oss/seq_oss_midi.c b/sound/core/seq/oss/seq_oss_midi.c index a88c235b2ea365edcbf07727d01b1e4c33fadbd9..2ddfe22266517ced0b06f3e14cce137d16ef1fe6 100644 --- a/sound/core/seq/oss/seq_oss_midi.c +++ b/sound/core/seq/oss/seq_oss_midi.c @@ -602,6 +602,7 @@ send_midi_event(struct seq_oss_devinfo *dp, struct snd_seq_event *ev, struct seq len = snd_seq_oss_timer_start(dp->timer); if (ev->type == SNDRV_SEQ_EVENT_SYSEX) { snd_seq_oss_readq_sysex(dp->readq, mdev->seq_device, ev); + snd_midi_event_reset_decode(mdev->coder); } else { len = snd_midi_event_decode(mdev->coder, msg, sizeof(msg), ev); if (len > 0) diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 6d9592f0ae1d53c42b3d7d59bfdc462f39a34f77..cc93157fa950045b8d74e2fc4a6b1dc4e7753a5d 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -580,7 +580,7 @@ static int update_timestamp_of_queue(struct snd_seq_event *event, event->queue = queue; event->flags &= ~SNDRV_SEQ_TIME_STAMP_MASK; if (real_time) { - event->time.time = snd_seq_timer_get_cur_time(q->timer); + event->time.time = snd_seq_timer_get_cur_time(q->timer, true); event->flags |= SNDRV_SEQ_TIME_STAMP_REAL; } else { event->time.tick = snd_seq_timer_get_cur_tick(q->timer); @@ -1659,7 +1659,7 @@ static int snd_seq_ioctl_get_queue_status(struct snd_seq_client *client, tmr = queue->timer; status->events = queue->tickq->cells + queue->timeq->cells; - status->time = snd_seq_timer_get_cur_time(tmr); + status->time = snd_seq_timer_get_cur_time(tmr, true); status->tick = snd_seq_timer_get_cur_tick(tmr); status->running = tmr->running; diff --git a/sound/core/seq/seq_queue.c b/sound/core/seq/seq_queue.c index caf68bf42f134be3e802c976b6b824f38d64c82d..71a6ea62c3be7c8a0a1885da0b32b2b527ef8644 100644 --- a/sound/core/seq/seq_queue.c +++ b/sound/core/seq/seq_queue.c @@ -238,6 +238,8 @@ void snd_seq_check_queue(struct snd_seq_queue *q, int atomic, int hop) { unsigned long flags; struct snd_seq_event_cell *cell; + snd_seq_tick_time_t cur_tick; + snd_seq_real_time_t cur_time; if (q == NULL) return; @@ -254,17 +256,18 @@ void snd_seq_check_queue(struct snd_seq_queue *q, int atomic, int hop) __again: /* Process tick queue... */ + cur_tick = snd_seq_timer_get_cur_tick(q->timer); for (;;) { - cell = snd_seq_prioq_cell_out(q->tickq, - &q->timer->tick.cur_tick); + cell = snd_seq_prioq_cell_out(q->tickq, &cur_tick); if (!cell) break; snd_seq_dispatch_event(cell, atomic, hop); } /* Process time queue... */ + cur_time = snd_seq_timer_get_cur_time(q->timer, false); for (;;) { - cell = snd_seq_prioq_cell_out(q->timeq, &q->timer->cur_time); + cell = snd_seq_prioq_cell_out(q->timeq, &cur_time); if (!cell) break; snd_seq_dispatch_event(cell, atomic, hop); @@ -392,6 +395,7 @@ int snd_seq_queue_check_access(int queueid, int client) int snd_seq_queue_set_owner(int queueid, int client, int locked) { struct snd_seq_queue *q = queueptr(queueid); + unsigned long flags; if (q == NULL) return -EINVAL; @@ -401,8 +405,10 @@ int snd_seq_queue_set_owner(int queueid, int client, int locked) return -EPERM; } + spin_lock_irqsave(&q->owner_lock, flags); q->locked = locked ? 1 : 0; q->owner = client; + spin_unlock_irqrestore(&q->owner_lock, flags); queue_access_unlock(q); queuefree(q); @@ -539,15 +545,17 @@ void snd_seq_queue_client_termination(int client) unsigned long flags; int i; struct snd_seq_queue *q; + bool matched; for (i = 0; i < SNDRV_SEQ_MAX_QUEUES; i++) { if ((q = queueptr(i)) == NULL) continue; spin_lock_irqsave(&q->owner_lock, flags); - if (q->owner == client) + matched = (q->owner == client); + if (matched) q->klocked = 1; spin_unlock_irqrestore(&q->owner_lock, flags); - if (q->owner == client) { + if (matched) { if (q->timer->running) snd_seq_timer_stop(q->timer); snd_seq_timer_reset(q->timer); @@ -739,6 +747,8 @@ void snd_seq_info_queues_read(struct snd_info_entry *entry, int i, bpm; struct snd_seq_queue *q; struct snd_seq_timer *tmr; + bool locked; + int owner; for (i = 0; i < SNDRV_SEQ_MAX_QUEUES; i++) { if ((q = queueptr(i)) == NULL) @@ -750,9 +760,14 @@ void snd_seq_info_queues_read(struct snd_info_entry *entry, else bpm = 0; + spin_lock_irq(&q->owner_lock); + locked = q->locked; + owner = q->owner; + spin_unlock_irq(&q->owner_lock); + snd_iprintf(buffer, "queue %d: [%s]\n", q->queue, q->name); - snd_iprintf(buffer, "owned by client : %d\n", q->owner); - snd_iprintf(buffer, "lock status : %s\n", q->locked ? "Locked" : "Free"); + snd_iprintf(buffer, "owned by client : %d\n", owner); + snd_iprintf(buffer, "lock status : %s\n", locked ? "Locked" : "Free"); snd_iprintf(buffer, "queued time events : %d\n", snd_seq_prioq_avail(q->timeq)); snd_iprintf(buffer, "queued tick events : %d\n", snd_seq_prioq_avail(q->tickq)); snd_iprintf(buffer, "timer state : %s\n", tmr->running ? "Running" : "Stopped"); diff --git a/sound/core/seq/seq_timer.c b/sound/core/seq/seq_timer.c index be59b59c9be40c233995817f3ddb3e5d71fbb6d7..1645e4142e30246dc30af69857d1dc8e9f736219 100644 --- a/sound/core/seq/seq_timer.c +++ b/sound/core/seq/seq_timer.c @@ -428,14 +428,15 @@ int snd_seq_timer_continue(struct snd_seq_timer *tmr) } /* return current 'real' time. use timeofday() to get better granularity. */ -snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr) +snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr, + bool adjust_ktime) { snd_seq_real_time_t cur_time; unsigned long flags; spin_lock_irqsave(&tmr->lock, flags); cur_time = tmr->cur_time; - if (tmr->running) { + if (adjust_ktime && tmr->running) { struct timespec64 tm; ktime_get_ts64(&tm); @@ -452,7 +453,13 @@ snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr) high PPQ values) */ snd_seq_tick_time_t snd_seq_timer_get_cur_tick(struct snd_seq_timer *tmr) { - return tmr->tick.cur_tick; + snd_seq_tick_time_t cur_tick; + unsigned long flags; + + spin_lock_irqsave(&tmr->lock, flags); + cur_tick = tmr->tick.cur_tick; + spin_unlock_irqrestore(&tmr->lock, flags); + return cur_tick; } diff --git a/sound/core/seq/seq_timer.h b/sound/core/seq/seq_timer.h index 66c3e344eae37f9285e90ab3b8d607f6d1f4bb02..4bec57df8158caf81e6cdba3248d7e252bd34643 100644 --- a/sound/core/seq/seq_timer.h +++ b/sound/core/seq/seq_timer.h @@ -120,7 +120,8 @@ int snd_seq_timer_set_tempo_ppq(struct snd_seq_timer *tmr, int tempo, int ppq); int snd_seq_timer_set_position_tick(struct snd_seq_timer *tmr, snd_seq_tick_time_t position); int snd_seq_timer_set_position_time(struct snd_seq_timer *tmr, snd_seq_real_time_t position); int snd_seq_timer_set_skew(struct snd_seq_timer *tmr, unsigned int skew, unsigned int base); -snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr); +snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr, + bool adjust_ktime); snd_seq_tick_time_t snd_seq_timer_get_cur_tick(struct snd_seq_timer *tmr); extern int seq_default_timer_class; diff --git a/sound/core/seq/seq_virmidi.c b/sound/core/seq/seq_virmidi.c index 626d87c1539b5fb1619520f8ec2de5567c1e29db..77d7037d1476fab4c9a12c98a332285b0d40ebee 100644 --- a/sound/core/seq/seq_virmidi.c +++ b/sound/core/seq/seq_virmidi.c @@ -81,6 +81,7 @@ static int snd_virmidi_dev_receive_event(struct snd_virmidi_dev *rdev, if ((ev->flags & SNDRV_SEQ_EVENT_LENGTH_MASK) != SNDRV_SEQ_EVENT_LENGTH_VARIABLE) continue; snd_seq_dump_var_event(ev, (snd_seq_dump_func_t)snd_rawmidi_receive, vmidi->substream); + snd_midi_event_reset_decode(vmidi->parser); } else { len = snd_midi_event_decode(vmidi->parser, msg, sizeof(msg), ev); if (len > 0) diff --git a/sound/hda/ext/hdac_ext_controller.c b/sound/hda/ext/hdac_ext_controller.c index a684f0520b4b982f71897967641d05ce0dca5128..4d060d5b1db6dc7eabfd5d44c3ef965792925537 100644 --- a/sound/hda/ext/hdac_ext_controller.c +++ b/sound/hda/ext/hdac_ext_controller.c @@ -254,6 +254,7 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_link_power_down_all); int snd_hdac_ext_bus_link_get(struct hdac_bus *bus, struct hdac_ext_link *link) { + unsigned long codec_mask; int ret = 0; mutex_lock(&bus->lock); @@ -280,9 +281,11 @@ int snd_hdac_ext_bus_link_get(struct hdac_bus *bus, * HDA spec section 4.3 - Codec Discovery */ udelay(521); - bus->codec_mask = snd_hdac_chip_readw(bus, STATESTS); - dev_dbg(bus->dev, "codec_mask = 0x%lx\n", bus->codec_mask); - snd_hdac_chip_writew(bus, STATESTS, bus->codec_mask); + codec_mask = snd_hdac_chip_readw(bus, STATESTS); + dev_dbg(bus->dev, "codec_mask = 0x%lx\n", codec_mask); + snd_hdac_chip_writew(bus, STATESTS, codec_mask); + if (!bus->codec_mask) + bus->codec_mask = codec_mask; } mutex_unlock(&bus->lock); diff --git a/sound/hda/hdmi_chmap.c b/sound/hda/hdmi_chmap.c index 5fd6d575e123b0e4cb20a986ecf8010d1795023c..aad5c4bf4d3441754b0ec1d5d046b438b1ee6c5e 100644 --- a/sound/hda/hdmi_chmap.c +++ b/sound/hda/hdmi_chmap.c @@ -250,7 +250,7 @@ void snd_hdac_print_channel_allocation(int spk_alloc, char *buf, int buflen) for (i = 0, j = 0; i < ARRAY_SIZE(cea_speaker_allocation_names); i++) { if (spk_alloc & (1 << i)) - j += snprintf(buf + j, buflen - j, " %s", + j += scnprintf(buf + j, buflen - j, " %s", cea_speaker_allocation_names[i]); } buf[j] = '\0'; /* necessary when j == 0 */ diff --git a/sound/mips/sgio2audio.c b/sound/mips/sgio2audio.c index 9f60a5037f8bc36d2d53c09e0c813d2f02ef6f8e..5bf1ea150f26478791014bef55da611f1780a924 100644 --- a/sound/mips/sgio2audio.c +++ b/sound/mips/sgio2audio.c @@ -649,8 +649,6 @@ snd_sgio2audio_pcm_pointer(struct snd_pcm_substream *substream) static const struct snd_pcm_ops snd_sgio2audio_playback1_ops = { .open = snd_sgio2audio_playback1_open, .close = snd_sgio2audio_pcm_close, - .hw_params = snd_sgio2audio_pcm_hw_params, - .hw_free = snd_sgio2audio_pcm_hw_free, .prepare = snd_sgio2audio_pcm_prepare, .trigger = snd_sgio2audio_pcm_trigger, .pointer = snd_sgio2audio_pcm_pointer, @@ -659,8 +657,6 @@ static const struct snd_pcm_ops snd_sgio2audio_playback1_ops = { static const struct snd_pcm_ops snd_sgio2audio_playback2_ops = { .open = snd_sgio2audio_playback2_open, .close = snd_sgio2audio_pcm_close, - .hw_params = snd_sgio2audio_pcm_hw_params, - .hw_free = snd_sgio2audio_pcm_hw_free, .prepare = snd_sgio2audio_pcm_prepare, .trigger = snd_sgio2audio_pcm_trigger, .pointer = snd_sgio2audio_pcm_pointer, @@ -669,8 +665,6 @@ static const struct snd_pcm_ops snd_sgio2audio_playback2_ops = { static const struct snd_pcm_ops snd_sgio2audio_capture_ops = { .open = snd_sgio2audio_capture_open, .close = snd_sgio2audio_pcm_close, - .hw_params = snd_sgio2audio_pcm_hw_params, - .hw_free = snd_sgio2audio_pcm_hw_free, .prepare = snd_sgio2audio_pcm_prepare, .trigger = snd_sgio2audio_pcm_trigger, .pointer = snd_sgio2audio_pcm_pointer, diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index 5dc42f932739f3b385f826cb4431e0ed85731a0f..53e7732ef75209b63617ecc700c55cf994064bf8 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -4022,7 +4022,7 @@ void snd_print_pcm_bits(int pcm, char *buf, int buflen) for (i = 0, j = 0; i < ARRAY_SIZE(bits); i++) if (pcm & (AC_SUPPCM_BITS_8 << i)) - j += snprintf(buf + j, buflen - j, " %d", bits[i]); + j += scnprintf(buf + j, buflen - j, " %d", bits[i]); buf[j] = '\0'; /* necessary when j == 0 */ } diff --git a/sound/pci/hda/hda_eld.c b/sound/pci/hda/hda_eld.c index bb46c89b7f63d9c06e8500065170bbabbc8205e7..136477ed46ae2673db07fcd200b61871063dab07 100644 --- a/sound/pci/hda/hda_eld.c +++ b/sound/pci/hda/hda_eld.c @@ -360,7 +360,7 @@ static void hdmi_print_pcm_rates(int pcm, char *buf, int buflen) for (i = 0, j = 0; i < ARRAY_SIZE(alsa_rates); i++) if (pcm & (1 << i)) - j += snprintf(buf + j, buflen - j, " %d", + j += scnprintf(buf + j, buflen - j, " %d", alsa_rates[i]); buf[j] = '\0'; /* necessary when j == 0 */ diff --git a/sound/pci/hda/hda_sysfs.c b/sound/pci/hda/hda_sysfs.c index 0607ed5d1959958da12647ba6b4b165c5683d4da..eb8ec109d7adb5ce187567b2a5a8c10bdc3eec05 100644 --- a/sound/pci/hda/hda_sysfs.c +++ b/sound/pci/hda/hda_sysfs.c @@ -222,7 +222,7 @@ static ssize_t init_verbs_show(struct device *dev, int i, len = 0; mutex_lock(&codec->user_mutex); snd_array_for_each(&codec->init_verbs, i, v) { - len += snprintf(buf + len, PAGE_SIZE - len, + len += scnprintf(buf + len, PAGE_SIZE - len, "0x%02x 0x%03x 0x%04x\n", v->nid, v->verb, v->param); } @@ -272,7 +272,7 @@ static ssize_t hints_show(struct device *dev, int i, len = 0; mutex_lock(&codec->user_mutex); snd_array_for_each(&codec->hints, i, hint) { - len += snprintf(buf + len, PAGE_SIZE - len, + len += scnprintf(buf + len, PAGE_SIZE - len, "%s = %s\n", hint->key, hint->val); } mutex_unlock(&codec->user_mutex); diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 4770fb3f51fb4c641dd5cdab254420c733154174..63e1a56f705b7de38f36b1abd7c69c3aa88728e7 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -2447,6 +2447,10 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x1071, 0x8258, "Evesham Voyaeger", ALC882_FIXUP_EAPD), SND_PCI_QUIRK(0x1458, 0xa002, "Gigabyte EP45-DS3/Z87X-UD3H", ALC889_FIXUP_FRONT_HP_NO_PRESENCE), SND_PCI_QUIRK(0x1458, 0xa0b8, "Gigabyte AZ370-Gaming", ALC1220_FIXUP_GB_DUAL_CODECS), + SND_PCI_QUIRK(0x1458, 0xa0cd, "Gigabyte X570 Aorus Master", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1462, 0x1228, "MSI-GP63", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1462, 0x1276, "MSI-GL73", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1462, 0x1293, "MSI-GP65", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1462, 0x7350, "MSI-7350", ALC889_FIXUP_CD), SND_PCI_QUIRK(0x1462, 0xda57, "MSI Z270-Gaming", ALC1220_FIXUP_GB_DUAL_CODECS), SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3), @@ -5701,8 +5705,11 @@ static void alc_fixup_headset_jack(struct hda_codec *codec, break; case HDA_FIXUP_ACT_INIT: switch (codec->core.vendor_id) { + case 0x10ec0215: case 0x10ec0225: + case 0x10ec0285: case 0x10ec0295: + case 0x10ec0289: case 0x10ec0299: alc_write_coef_idx(codec, 0x48, 0xd011); alc_update_coef_idx(codec, 0x49, 0x007f, 0x0045); @@ -5914,7 +5921,8 @@ enum { ALC289_FIXUP_DUAL_SPK, ALC294_FIXUP_SPK2_TO_DAC1, ALC294_FIXUP_ASUS_DUAL_SPK, - + ALC285_FIXUP_THINKPAD_HEADSET_JACK, + ALC294_FIXUP_ASUS_HPE, }; static const struct hda_fixup alc269_fixups[] = { @@ -6678,6 +6686,8 @@ static const struct hda_fixup alc269_fixups[] = { [ALC285_FIXUP_SPEAKER2_TO_DAC1] = { .type = HDA_FIXUP_FUNC, .v.func = alc285_fixup_speaker2_to_dac1, + .chained = true, + .chain_id = ALC269_FIXUP_THINKPAD_ACPI }, [ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER] = { .type = HDA_FIXUP_PINS, @@ -7034,7 +7044,23 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC294_FIXUP_SPK2_TO_DAC1 }, - + [ALC285_FIXUP_THINKPAD_HEADSET_JACK] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_headset_jack, + .chained = true, + .chain_id = ALC285_FIXUP_SPEAKER2_TO_DAC1 + }, + [ALC294_FIXUP_ASUS_HPE] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + /* Set EAPD high */ + { 0x20, AC_VERB_SET_COEF_INDEX, 0x0f }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x7774 }, + { } + }, + .chained = true, + .chain_id = ALC294_FIXUP_ASUS_HEADSET_MIC + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -7109,6 +7135,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0935, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB), SND_PCI_QUIRK(0x1028, 0x097e, "Dell Precision", ALC289_FIXUP_DUAL_SPK), SND_PCI_QUIRK(0x1028, 0x097d, "Dell Precision", ALC289_FIXUP_DUAL_SPK), + SND_PCI_QUIRK(0x1028, 0x098d, "Dell Precision", ALC233_FIXUP_ASUS_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1028, 0x09bf, "Dell Precision", ALC233_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2), @@ -7198,6 +7226,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x16e3, "ASUS UX50", ALC269_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x1043, 0x17d1, "ASUS UX431FL", ALC294_FIXUP_ASUS_DUAL_SPK), SND_PCI_QUIRK(0x1043, 0x18b1, "Asus MJ401TA", ALC256_FIXUP_ASUS_HEADSET_MIC), + SND_PCI_QUIRK(0x1043, 0x19ce, "ASUS B9450FA", ALC294_FIXUP_ASUS_HPE), SND_PCI_QUIRK(0x1043, 0x1a13, "Asus G73Jw", ALC269_FIXUP_ASUS_G73JW), SND_PCI_QUIRK(0x1043, 0x1a30, "ASUS X705UD", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x1b13, "Asus U41SV", ALC269_FIXUP_INV_DMIC), @@ -7268,8 +7297,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x224c, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x224d, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x225d, "Thinkpad T480", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), - SND_PCI_QUIRK(0x17aa, 0x2292, "Thinkpad X1 Yoga 7th", ALC285_FIXUP_SPEAKER2_TO_DAC1), - SND_PCI_QUIRK(0x17aa, 0x2293, "Thinkpad X1 Carbon 7th", ALC285_FIXUP_SPEAKER2_TO_DAC1), + SND_PCI_QUIRK(0x17aa, 0x2292, "Thinkpad X1 Yoga 7th", ALC285_FIXUP_THINKPAD_HEADSET_JACK), + SND_PCI_QUIRK(0x17aa, 0x2293, "Thinkpad X1 Carbon 7th", ALC285_FIXUP_THINKPAD_HEADSET_JACK), SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION), @@ -8022,6 +8051,8 @@ static int patch_alc269(struct hda_codec *codec) spec->gen.mixer_nid = 0; break; case 0x10ec0225: + codec->power_save_node = 1; + /* fall through */ case 0x10ec0295: case 0x10ec0299: spec->codec_variant = ALC269_TYPE_ALC225; @@ -8581,6 +8612,8 @@ enum { ALC669_FIXUP_ACER_ASPIRE_ETHOS, ALC669_FIXUP_ACER_ASPIRE_ETHOS_HEADSET, ALC671_FIXUP_HP_HEADSET_MIC2, + ALC662_FIXUP_ACER_X2660G_HEADSET_MODE, + ALC662_FIXUP_ACER_NITRO_HEADSET_MODE, }; static const struct hda_fixup alc662_fixups[] = { @@ -8926,6 +8959,25 @@ static const struct hda_fixup alc662_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc671_fixup_hp_headset_mic2, }, + [ALC662_FIXUP_ACER_X2660G_HEADSET_MODE] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x1a, 0x02a1113c }, /* use as headset mic, without its own jack detect */ + { } + }, + .chained = true, + .chain_id = ALC662_FIXUP_USI_FUNC + }, + [ALC662_FIXUP_ACER_NITRO_HEADSET_MODE] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x1a, 0x01a11140 }, /* use as headset mic, without its own jack detect */ + { 0x1b, 0x0221144f }, + { } + }, + .chained = true, + .chain_id = ALC662_FIXUP_USI_FUNC + }, }; static const struct snd_pci_quirk alc662_fixup_tbl[] = { @@ -8937,6 +8989,8 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x0349, "eMachines eM250", ALC662_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x1025, 0x034a, "Gateway LT27", ALC662_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x1025, 0x038b, "Acer Aspire 8943G", ALC662_FIXUP_ASPIRE), + SND_PCI_QUIRK(0x1025, 0x123c, "Acer Nitro N50-600", ALC662_FIXUP_ACER_NITRO_HEADSET_MODE), + SND_PCI_QUIRK(0x1025, 0x124e, "Acer 2660G", ALC662_FIXUP_ACER_X2660G_HEADSET_MODE), SND_PCI_QUIRK(0x1028, 0x05d8, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x05db, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x05fe, "Dell XPS 15", ALC668_FIXUP_DELL_XPS13), diff --git a/sound/soc/amd/raven/acp3x-i2s.c b/sound/soc/amd/raven/acp3x-i2s.c index 31cd4008e33ff88d9b61085133d12755a60f1724..91a388184e525d66f0953effc36f0b6204a04972 100644 --- a/sound/soc/amd/raven/acp3x-i2s.c +++ b/sound/soc/amd/raven/acp3x-i2s.c @@ -170,6 +170,7 @@ static int acp3x_i2s_trigger(struct snd_pcm_substream *substream, struct snd_soc_card *card; struct acp3x_platform_info *pinfo; u32 ret, val, period_bytes, reg_val, ier_val, water_val; + u32 buf_size, buf_reg; prtd = substream->private_data; rtd = substream->runtime->private_data; @@ -183,6 +184,8 @@ static int acp3x_i2s_trigger(struct snd_pcm_substream *substream, } period_bytes = frames_to_bytes(substream->runtime, substream->runtime->period_size); + buf_size = frames_to_bytes(substream->runtime, + substream->runtime->buffer_size); switch (cmd) { case SNDRV_PCM_TRIGGER_START: case SNDRV_PCM_TRIGGER_RESUME: @@ -196,6 +199,7 @@ static int acp3x_i2s_trigger(struct snd_pcm_substream *substream, mmACP_BT_TX_INTR_WATERMARK_SIZE; reg_val = mmACP_BTTDM_ITER; ier_val = mmACP_BTTDM_IER; + buf_reg = mmACP_BT_TX_RINGBUFSIZE; break; case I2S_SP_INSTANCE: default: @@ -203,6 +207,7 @@ static int acp3x_i2s_trigger(struct snd_pcm_substream *substream, mmACP_I2S_TX_INTR_WATERMARK_SIZE; reg_val = mmACP_I2STDM_ITER; ier_val = mmACP_I2STDM_IER; + buf_reg = mmACP_I2S_TX_RINGBUFSIZE; } } else { switch (rtd->i2s_instance) { @@ -211,6 +216,7 @@ static int acp3x_i2s_trigger(struct snd_pcm_substream *substream, mmACP_BT_RX_INTR_WATERMARK_SIZE; reg_val = mmACP_BTTDM_IRER; ier_val = mmACP_BTTDM_IER; + buf_reg = mmACP_BT_RX_RINGBUFSIZE; break; case I2S_SP_INSTANCE: default: @@ -218,9 +224,11 @@ static int acp3x_i2s_trigger(struct snd_pcm_substream *substream, mmACP_I2S_RX_INTR_WATERMARK_SIZE; reg_val = mmACP_I2STDM_IRER; ier_val = mmACP_I2STDM_IER; + buf_reg = mmACP_I2S_RX_RINGBUFSIZE; } } rv_writel(period_bytes, rtd->acp3x_base + water_val); + rv_writel(buf_size, rtd->acp3x_base + buf_reg); val = rv_readl(rtd->acp3x_base + reg_val); val = val | BIT(0); rv_writel(val, rtd->acp3x_base + reg_val); diff --git a/sound/soc/amd/raven/acp3x-pcm-dma.c b/sound/soc/amd/raven/acp3x-pcm-dma.c index aecc3c06167907a00634559a25dea93c04fa0f8a..d62c0d90c41e34d99421f840312c8c77c04c793b 100644 --- a/sound/soc/amd/raven/acp3x-pcm-dma.c +++ b/sound/soc/amd/raven/acp3x-pcm-dma.c @@ -110,7 +110,7 @@ static void config_acp3x_dma(struct i2s_stream_instance *rtd, int direction) { u16 page_idx; u32 low, high, val, acp_fifo_addr, reg_fifo_addr; - u32 reg_ringbuf_size, reg_dma_size, reg_fifo_size; + u32 reg_dma_size, reg_fifo_size; dma_addr_t addr; addr = rtd->dma_addr; @@ -157,7 +157,6 @@ static void config_acp3x_dma(struct i2s_stream_instance *rtd, int direction) if (direction == SNDRV_PCM_STREAM_PLAYBACK) { switch (rtd->i2s_instance) { case I2S_BT_INSTANCE: - reg_ringbuf_size = mmACP_BT_TX_RINGBUFSIZE; reg_dma_size = mmACP_BT_TX_DMA_SIZE; acp_fifo_addr = ACP_SRAM_PTE_OFFSET + BT_PB_FIFO_ADDR_OFFSET; @@ -169,7 +168,6 @@ static void config_acp3x_dma(struct i2s_stream_instance *rtd, int direction) case I2S_SP_INSTANCE: default: - reg_ringbuf_size = mmACP_I2S_TX_RINGBUFSIZE; reg_dma_size = mmACP_I2S_TX_DMA_SIZE; acp_fifo_addr = ACP_SRAM_PTE_OFFSET + SP_PB_FIFO_ADDR_OFFSET; @@ -181,7 +179,6 @@ static void config_acp3x_dma(struct i2s_stream_instance *rtd, int direction) } else { switch (rtd->i2s_instance) { case I2S_BT_INSTANCE: - reg_ringbuf_size = mmACP_BT_RX_RINGBUFSIZE; reg_dma_size = mmACP_BT_RX_DMA_SIZE; acp_fifo_addr = ACP_SRAM_PTE_OFFSET + BT_CAPT_FIFO_ADDR_OFFSET; @@ -193,7 +190,6 @@ static void config_acp3x_dma(struct i2s_stream_instance *rtd, int direction) case I2S_SP_INSTANCE: default: - reg_ringbuf_size = mmACP_I2S_RX_RINGBUFSIZE; reg_dma_size = mmACP_I2S_RX_DMA_SIZE; acp_fifo_addr = ACP_SRAM_PTE_OFFSET + SP_CAPT_FIFO_ADDR_OFFSET; @@ -203,7 +199,6 @@ static void config_acp3x_dma(struct i2s_stream_instance *rtd, int direction) rtd->acp3x_base + mmACP_I2S_RX_RINGBUFADDR); } } - rv_writel(MAX_BUFFER, rtd->acp3x_base + reg_ringbuf_size); rv_writel(DMA_SIZE, rtd->acp3x_base + reg_dma_size); rv_writel(acp_fifo_addr, rtd->acp3x_base + reg_fifo_addr); rv_writel(FIFO_SIZE, rtd->acp3x_base + reg_fifo_size); diff --git a/sound/soc/amd/raven/pci-acp3x.c b/sound/soc/amd/raven/pci-acp3x.c index 65330bb50e74c991e8b0abed3d7e584a10785e15..da60e2ec5535172710229db1d461bff899a965b1 100644 --- a/sound/soc/amd/raven/pci-acp3x.c +++ b/sound/soc/amd/raven/pci-acp3x.c @@ -45,23 +45,6 @@ static int acp3x_power_on(void __iomem *acp3x_base) return -ETIMEDOUT; } -static int acp3x_power_off(void __iomem *acp3x_base) -{ - u32 val; - int timeout; - - rv_writel(ACP_PGFSM_CNTL_POWER_OFF_MASK, - acp3x_base + mmACP_PGFSM_CONTROL); - timeout = 0; - while (++timeout < 500) { - val = rv_readl(acp3x_base + mmACP_PGFSM_STATUS); - if ((val & ACP_PGFSM_STATUS_MASK) == ACP_POWERED_OFF) - return 0; - udelay(1); - } - return -ETIMEDOUT; -} - static int acp3x_reset(void __iomem *acp3x_base) { u32 val; @@ -115,12 +98,6 @@ static int acp3x_deinit(void __iomem *acp3x_base) pr_err("ACP3x reset failed\n"); return ret; } - /* power off */ - ret = acp3x_power_off(acp3x_base); - if (ret) { - pr_err("ACP3x power off failed\n"); - return ret; - } return 0; } diff --git a/sound/soc/atmel/Kconfig b/sound/soc/atmel/Kconfig index d1dc8e6366dcbd3356cb39dafb2cc41753bd4896..71f2d42188c461a4169af85cac84511851f122ac 100644 --- a/sound/soc/atmel/Kconfig +++ b/sound/soc/atmel/Kconfig @@ -10,11 +10,11 @@ config SND_ATMEL_SOC if SND_ATMEL_SOC config SND_ATMEL_SOC_PDC - tristate + bool depends on HAS_DMA config SND_ATMEL_SOC_DMA - tristate + bool select SND_SOC_GENERIC_DMAENGINE_PCM config SND_ATMEL_SOC_SSC diff --git a/sound/soc/atmel/Makefile b/sound/soc/atmel/Makefile index 1f6890ed373826fbad9432df6e6c14eebb2924b7..c7d2989791be1a2db9f4100246d8414ecea67d68 100644 --- a/sound/soc/atmel/Makefile +++ b/sound/soc/atmel/Makefile @@ -6,8 +6,14 @@ snd-soc-atmel_ssc_dai-objs := atmel_ssc_dai.o snd-soc-atmel-i2s-objs := atmel-i2s.o snd-soc-mchp-i2s-mcc-objs := mchp-i2s-mcc.o -obj-$(CONFIG_SND_ATMEL_SOC_PDC) += snd-soc-atmel-pcm-pdc.o -obj-$(CONFIG_SND_ATMEL_SOC_DMA) += snd-soc-atmel-pcm-dma.o +# pdc and dma need to both be built-in if any user of +# ssc is built-in. +ifdef CONFIG_SND_ATMEL_SOC_PDC +obj-$(CONFIG_SND_ATMEL_SOC_SSC) += snd-soc-atmel-pcm-pdc.o +endif +ifdef CONFIG_SND_ATMEL_SOC_DMA +obj-$(CONFIG_SND_ATMEL_SOC_SSC) += snd-soc-atmel-pcm-dma.o +endif obj-$(CONFIG_SND_ATMEL_SOC_SSC) += snd-soc-atmel_ssc_dai.o obj-$(CONFIG_SND_ATMEL_SOC_I2S) += snd-soc-atmel-i2s.o obj-$(CONFIG_SND_MCHP_SOC_I2S_MCC) += snd-soc-mchp-i2s-mcc.o diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig index 7e90f5d83097130945718686d1a2f0715cd5cfef..ea912439e446787204316aecbe893877ce4d1f4c 100644 --- a/sound/soc/codecs/Kconfig +++ b/sound/soc/codecs/Kconfig @@ -1406,7 +1406,7 @@ config SND_SOC_WM8737 depends on SND_SOC_I2C_AND_SPI config SND_SOC_WM8741 - tristate "Wolfson Microelectronics WM8737 DAC" + tristate "Wolfson Microelectronics WM8741 DAC" depends on SND_SOC_I2C_AND_SPI config SND_SOC_WM8750 diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c index 444cc4e3374e17eb8b0dc988664d0d04914b3025..f005751da2ccb39abd42adb029c0f5fa0e4e3eac 100644 --- a/sound/soc/codecs/hdmi-codec.c +++ b/sound/soc/codecs/hdmi-codec.c @@ -779,7 +779,17 @@ static int hdmi_of_xlate_dai_id(struct snd_soc_component *component, return ret; } +static void hdmi_remove(struct snd_soc_component *component) +{ + struct hdmi_codec_priv *hcp = snd_soc_component_get_drvdata(component); + + if (hcp->hcd.ops->hook_plugged_cb) + hcp->hcd.ops->hook_plugged_cb(component->dev->parent, + hcp->hcd.data, NULL, NULL); +} + static const struct snd_soc_component_driver hdmi_driver = { + .remove = hdmi_remove, .dapm_widgets = hdmi_widgets, .num_dapm_widgets = ARRAY_SIZE(hdmi_widgets), .of_xlate_dai_id = hdmi_of_xlate_dai_id, diff --git a/sound/soc/codecs/max98090.c b/sound/soc/codecs/max98090.c index 5bc2c6411b33bfbd4747a6b836375039bfdc1885..032adc14562d24c54b4933c0c4818f0537ebb1f4 100644 --- a/sound/soc/codecs/max98090.c +++ b/sound/soc/codecs/max98090.c @@ -5,150 +5,24 @@ * Copyright 2011-2012 Maxim Integrated Products */ -#include -#include #include #include #include -#include #include #include #include #include #include +#include +#include #include -#include #include #include #include #include +#include #include "max98090.h" -static void max98090_shdn_save_locked(struct max98090_priv *max98090) -{ - int shdn = 0; - - /* saved_shdn, saved_count, SHDN are protected by card->dapm_mutex */ - regmap_read(max98090->regmap, M98090_REG_DEVICE_SHUTDOWN, &shdn); - max98090->saved_shdn |= shdn; - ++max98090->saved_count; - - if (shdn) - regmap_write(max98090->regmap, M98090_REG_DEVICE_SHUTDOWN, 0x0); -} - -static void max98090_shdn_restore_locked(struct max98090_priv *max98090) -{ - /* saved_shdn, saved_count, SHDN are protected by card->dapm_mutex */ - if (--max98090->saved_count == 0) { - if (max98090->saved_shdn) { - regmap_write(max98090->regmap, - M98090_REG_DEVICE_SHUTDOWN, - M98090_SHDNN_MASK); - max98090->saved_shdn = 0; - } - } -} - -static void max98090_shdn_save(struct max98090_priv *max98090) -{ - mutex_lock_nested(&max98090->component->card->dapm_mutex, - SND_SOC_DAPM_CLASS_RUNTIME); - max98090_shdn_save_locked(max98090); -} - -static void max98090_shdn_restore(struct max98090_priv *max98090) -{ - max98090_shdn_restore_locked(max98090); - mutex_unlock(&max98090->component->card->dapm_mutex); -} - -static int max98090_put_volsw(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) -{ - struct snd_soc_component *component = - snd_soc_kcontrol_component(kcontrol); - struct max98090_priv *max98090 = - snd_soc_component_get_drvdata(component); - int ret; - - max98090_shdn_save(max98090); - ret = snd_soc_put_volsw(kcontrol, ucontrol); - max98090_shdn_restore(max98090); - - return ret; -} - -static int max98090_dapm_put_enum_double(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) -{ - struct snd_soc_component *component = - snd_soc_dapm_kcontrol_component(kcontrol); - struct max98090_priv *max98090 = - snd_soc_component_get_drvdata(component); - int ret; - - max98090_shdn_save(max98090); - ret = snd_soc_dapm_put_enum_double_locked(kcontrol, ucontrol); - max98090_shdn_restore(max98090); - - return ret; -} - -static int max98090_put_enum_double(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) -{ - struct snd_soc_component *component = - snd_soc_kcontrol_component(kcontrol); - struct max98090_priv *max98090 = - snd_soc_component_get_drvdata(component); - int ret; - - max98090_shdn_save(max98090); - ret = snd_soc_put_enum_double(kcontrol, ucontrol); - max98090_shdn_restore(max98090); - - return ret; -} - -static int max98090_bytes_put(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) -{ - struct snd_soc_component *component = - snd_soc_kcontrol_component(kcontrol); - struct max98090_priv *max98090 = - snd_soc_component_get_drvdata(component); - int ret; - - max98090_shdn_save(max98090); - ret = snd_soc_bytes_put(kcontrol, ucontrol); - max98090_shdn_restore(max98090); - - return ret; -} - -static int max98090_dapm_event(struct snd_soc_dapm_widget *w, - struct snd_kcontrol *kcontrol, int event) -{ - struct snd_soc_component *component = - snd_soc_dapm_to_component(w->dapm); - struct max98090_priv *max98090 = - snd_soc_component_get_drvdata(component); - - switch (event) { - case SND_SOC_DAPM_PRE_PMU: - case SND_SOC_DAPM_PRE_PMD: - max98090_shdn_save_locked(max98090); - break; - case SND_SOC_DAPM_POST_PMU: - case SND_SOC_DAPM_POST_PMD: - max98090_shdn_restore_locked(max98090); - break; - } - - return 0; -} - /* Allows for sparsely populated register maps */ static const struct reg_default max98090_reg[] = { { 0x00, 0x00 }, /* 00 Software Reset */ @@ -632,13 +506,10 @@ static SOC_ENUM_SINGLE_DECL(max98090_adchp_enum, max98090_pwr_perf_text); static const struct snd_kcontrol_new max98090_snd_controls[] = { - SOC_ENUM_EXT("MIC Bias VCM Bandgap", max98090_vcmbandgap_enum, - snd_soc_get_enum_double, max98090_put_enum_double), + SOC_ENUM("MIC Bias VCM Bandgap", max98090_vcmbandgap_enum), - SOC_SINGLE_EXT("DMIC MIC Comp Filter Config", - M98090_REG_DIGITAL_MIC_CONFIG, - M98090_DMIC_COMP_SHIFT, M98090_DMIC_COMP_NUM - 1, 0, - snd_soc_get_volsw, max98090_put_volsw), + SOC_SINGLE("DMIC MIC Comp Filter Config", M98090_REG_DIGITAL_MIC_CONFIG, + M98090_DMIC_COMP_SHIFT, M98090_DMIC_COMP_NUM - 1, 0), SOC_SINGLE_EXT_TLV("MIC1 Boost Volume", M98090_REG_MIC1_INPUT_LEVEL, M98090_MIC_PA1EN_SHIFT, @@ -693,34 +564,24 @@ static const struct snd_kcontrol_new max98090_snd_controls[] = { M98090_AVR_SHIFT, M98090_AVR_NUM - 1, 1, max98090_av_tlv), - SOC_ENUM_EXT("ADC Oversampling Rate", max98090_osr128_enum, - snd_soc_get_enum_double, max98090_put_enum_double), - SOC_SINGLE_EXT("ADC Quantizer Dither", M98090_REG_ADC_CONTROL, - M98090_ADCDITHER_SHIFT, M98090_ADCDITHER_NUM - 1, 0, - snd_soc_get_volsw, max98090_put_volsw), - SOC_ENUM_EXT("ADC High Performance Mode", max98090_adchp_enum, - snd_soc_get_enum_double, max98090_put_enum_double), - - SOC_SINGLE_EXT("DAC Mono Mode", M98090_REG_IO_CONFIGURATION, - M98090_DMONO_SHIFT, M98090_DMONO_NUM - 1, 0, - snd_soc_get_volsw, max98090_put_volsw), - SOC_SINGLE_EXT("SDIN Mode", M98090_REG_IO_CONFIGURATION, - M98090_SDIEN_SHIFT, M98090_SDIEN_NUM - 1, 0, - snd_soc_get_volsw, max98090_put_volsw), - SOC_SINGLE_EXT("SDOUT Mode", M98090_REG_IO_CONFIGURATION, - M98090_SDOEN_SHIFT, M98090_SDOEN_NUM - 1, 0, - snd_soc_get_volsw, max98090_put_volsw), - SOC_SINGLE_EXT("SDOUT Hi-Z Mode", M98090_REG_IO_CONFIGURATION, - M98090_HIZOFF_SHIFT, M98090_HIZOFF_NUM - 1, 1, - snd_soc_get_volsw, max98090_put_volsw), - SOC_ENUM_EXT("Filter Mode", max98090_mode_enum, - snd_soc_get_enum_double, max98090_put_enum_double), - SOC_SINGLE_EXT("Record Path DC Blocking", M98090_REG_FILTER_CONFIG, - M98090_AHPF_SHIFT, M98090_AHPF_NUM - 1, 0, - snd_soc_get_volsw, max98090_put_volsw), - SOC_SINGLE_EXT("Playback Path DC Blocking", M98090_REG_FILTER_CONFIG, - M98090_DHPF_SHIFT, M98090_DHPF_NUM - 1, 0, - snd_soc_get_volsw, max98090_put_volsw), + SOC_ENUM("ADC Oversampling Rate", max98090_osr128_enum), + SOC_SINGLE("ADC Quantizer Dither", M98090_REG_ADC_CONTROL, + M98090_ADCDITHER_SHIFT, M98090_ADCDITHER_NUM - 1, 0), + SOC_ENUM("ADC High Performance Mode", max98090_adchp_enum), + + SOC_SINGLE("DAC Mono Mode", M98090_REG_IO_CONFIGURATION, + M98090_DMONO_SHIFT, M98090_DMONO_NUM - 1, 0), + SOC_SINGLE("SDIN Mode", M98090_REG_IO_CONFIGURATION, + M98090_SDIEN_SHIFT, M98090_SDIEN_NUM - 1, 0), + SOC_SINGLE("SDOUT Mode", M98090_REG_IO_CONFIGURATION, + M98090_SDOEN_SHIFT, M98090_SDOEN_NUM - 1, 0), + SOC_SINGLE("SDOUT Hi-Z Mode", M98090_REG_IO_CONFIGURATION, + M98090_HIZOFF_SHIFT, M98090_HIZOFF_NUM - 1, 1), + SOC_ENUM("Filter Mode", max98090_mode_enum), + SOC_SINGLE("Record Path DC Blocking", M98090_REG_FILTER_CONFIG, + M98090_AHPF_SHIFT, M98090_AHPF_NUM - 1, 0), + SOC_SINGLE("Playback Path DC Blocking", M98090_REG_FILTER_CONFIG, + M98090_DHPF_SHIFT, M98090_DHPF_NUM - 1, 0), SOC_SINGLE_TLV("Digital BQ Volume", M98090_REG_ADC_BIQUAD_LEVEL, M98090_AVBQ_SHIFT, M98090_AVBQ_NUM - 1, 1, max98090_dv_tlv), SOC_SINGLE_EXT_TLV("Digital Sidetone Volume", @@ -733,17 +594,13 @@ static const struct snd_kcontrol_new max98090_snd_controls[] = { SOC_SINGLE_TLV("Digital Volume", M98090_REG_DAI_PLAYBACK_LEVEL, M98090_DV_SHIFT, M98090_DV_NUM - 1, 1, max98090_dv_tlv), - SND_SOC_BYTES_E("EQ Coefficients", M98090_REG_EQUALIZER_BASE, 105, - snd_soc_bytes_get, max98090_bytes_put), - SOC_SINGLE_EXT("Digital EQ 3 Band Switch", M98090_REG_DSP_FILTER_ENABLE, - M98090_EQ3BANDEN_SHIFT, M98090_EQ3BANDEN_NUM - 1, 0, - snd_soc_get_volsw, max98090_put_volsw), - SOC_SINGLE_EXT("Digital EQ 5 Band Switch", M98090_REG_DSP_FILTER_ENABLE, - M98090_EQ5BANDEN_SHIFT, M98090_EQ5BANDEN_NUM - 1, 0, - snd_soc_get_volsw, max98090_put_volsw), - SOC_SINGLE_EXT("Digital EQ 7 Band Switch", M98090_REG_DSP_FILTER_ENABLE, - M98090_EQ7BANDEN_SHIFT, M98090_EQ7BANDEN_NUM - 1, 0, - snd_soc_get_volsw, max98090_put_volsw), + SND_SOC_BYTES("EQ Coefficients", M98090_REG_EQUALIZER_BASE, 105), + SOC_SINGLE("Digital EQ 3 Band Switch", M98090_REG_DSP_FILTER_ENABLE, + M98090_EQ3BANDEN_SHIFT, M98090_EQ3BANDEN_NUM - 1, 0), + SOC_SINGLE("Digital EQ 5 Band Switch", M98090_REG_DSP_FILTER_ENABLE, + M98090_EQ5BANDEN_SHIFT, M98090_EQ5BANDEN_NUM - 1, 0), + SOC_SINGLE("Digital EQ 7 Band Switch", M98090_REG_DSP_FILTER_ENABLE, + M98090_EQ7BANDEN_SHIFT, M98090_EQ7BANDEN_NUM - 1, 0), SOC_SINGLE("Digital EQ Clipping Detection", M98090_REG_DAI_PLAYBACK_LEVEL_EQ, M98090_EQCLPN_SHIFT, M98090_EQCLPN_NUM - 1, 1), @@ -751,34 +608,25 @@ static const struct snd_kcontrol_new max98090_snd_controls[] = { M98090_DVEQ_SHIFT, M98090_DVEQ_NUM - 1, 1, max98090_dv_tlv), - SOC_SINGLE_EXT("ALC Enable", M98090_REG_DRC_TIMING, - M98090_DRCEN_SHIFT, M98090_DRCEN_NUM - 1, 0, - snd_soc_get_volsw, max98090_put_volsw), - SOC_ENUM_EXT("ALC Attack Time", max98090_drcatk_enum, - snd_soc_get_enum_double, max98090_put_enum_double), - SOC_ENUM_EXT("ALC Release Time", max98090_drcrls_enum, - snd_soc_get_enum_double, max98090_put_enum_double), + SOC_SINGLE("ALC Enable", M98090_REG_DRC_TIMING, + M98090_DRCEN_SHIFT, M98090_DRCEN_NUM - 1, 0), + SOC_ENUM("ALC Attack Time", max98090_drcatk_enum), + SOC_ENUM("ALC Release Time", max98090_drcrls_enum), SOC_SINGLE_TLV("ALC Make Up Volume", M98090_REG_DRC_GAIN, M98090_DRCG_SHIFT, M98090_DRCG_NUM - 1, 0, max98090_alcmakeup_tlv), - SOC_ENUM_EXT("ALC Compression Ratio", max98090_alccmp_enum, - snd_soc_get_enum_double, max98090_put_enum_double), - SOC_ENUM_EXT("ALC Expansion Ratio", max98090_drcexp_enum, - snd_soc_get_enum_double, max98090_put_enum_double), - SOC_SINGLE_EXT_TLV("ALC Compression Threshold Volume", + SOC_ENUM("ALC Compression Ratio", max98090_alccmp_enum), + SOC_ENUM("ALC Expansion Ratio", max98090_drcexp_enum), + SOC_SINGLE_TLV("ALC Compression Threshold Volume", M98090_REG_DRC_COMPRESSOR, M98090_DRCTHC_SHIFT, - M98090_DRCTHC_NUM - 1, 1, - snd_soc_get_volsw, max98090_put_volsw, max98090_alccomp_tlv), - SOC_SINGLE_EXT_TLV("ALC Expansion Threshold Volume", + M98090_DRCTHC_NUM - 1, 1, max98090_alccomp_tlv), + SOC_SINGLE_TLV("ALC Expansion Threshold Volume", M98090_REG_DRC_EXPANDER, M98090_DRCTHE_SHIFT, - M98090_DRCTHE_NUM - 1, 1, - snd_soc_get_volsw, max98090_put_volsw, max98090_drcexp_tlv), + M98090_DRCTHE_NUM - 1, 1, max98090_drcexp_tlv), - SOC_ENUM_EXT("DAC HP Playback Performance Mode", - max98090_dac_perfmode_enum, - snd_soc_get_enum_double, max98090_put_enum_double), - SOC_ENUM_EXT("DAC High Performance Mode", max98090_dachp_enum, - snd_soc_get_enum_double, max98090_put_enum_double), + SOC_ENUM("DAC HP Playback Performance Mode", + max98090_dac_perfmode_enum), + SOC_ENUM("DAC High Performance Mode", max98090_dachp_enum), SOC_SINGLE_TLV("Headphone Left Mixer Volume", M98090_REG_HP_CONTROL, M98090_MIXHPLG_SHIFT, @@ -836,12 +684,9 @@ static const struct snd_kcontrol_new max98090_snd_controls[] = { SOC_SINGLE("Volume Adjustment Smoothing", M98090_REG_LEVEL_CONTROL, M98090_VSENN_SHIFT, M98090_VSENN_NUM - 1, 1), - SND_SOC_BYTES_E("Biquad Coefficients", - M98090_REG_RECORD_BIQUAD_BASE, 15, - snd_soc_bytes_get, max98090_bytes_put), - SOC_SINGLE_EXT("Biquad Switch", M98090_REG_DSP_FILTER_ENABLE, - M98090_ADCBQEN_SHIFT, M98090_ADCBQEN_NUM - 1, 0, - snd_soc_get_volsw, max98090_put_volsw), + SND_SOC_BYTES("Biquad Coefficients", M98090_REG_RECORD_BIQUAD_BASE, 15), + SOC_SINGLE("Biquad Switch", M98090_REG_DSP_FILTER_ENABLE, + M98090_ADCBQEN_SHIFT, M98090_ADCBQEN_NUM - 1, 0), }; static const struct snd_kcontrol_new max98091_snd_controls[] = { @@ -850,12 +695,10 @@ static const struct snd_kcontrol_new max98091_snd_controls[] = { M98090_DMIC34_ZEROPAD_SHIFT, M98090_DMIC34_ZEROPAD_NUM - 1, 0), - SOC_ENUM_EXT("Filter DMIC34 Mode", max98090_filter_dmic34mode_enum, - snd_soc_get_enum_double, max98090_put_enum_double), - SOC_SINGLE_EXT("DMIC34 DC Blocking", M98090_REG_FILTER_CONFIG, + SOC_ENUM("Filter DMIC34 Mode", max98090_filter_dmic34mode_enum), + SOC_SINGLE("DMIC34 DC Blocking", M98090_REG_FILTER_CONFIG, M98090_FLT_DMIC34HPF_SHIFT, - M98090_FLT_DMIC34HPF_NUM - 1, 0, - snd_soc_get_volsw, max98090_put_volsw), + M98090_FLT_DMIC34HPF_NUM - 1, 0), SOC_SINGLE_TLV("DMIC3 Boost Volume", M98090_REG_DMIC3_VOLUME, M98090_DMIC_AV3G_SHIFT, M98090_DMIC_AV3G_NUM - 1, 0, @@ -873,9 +716,8 @@ static const struct snd_kcontrol_new max98091_snd_controls[] = { SND_SOC_BYTES("DMIC34 Biquad Coefficients", M98090_REG_DMIC34_BIQUAD_BASE, 15), - SOC_SINGLE_EXT("DMIC34 Biquad Switch", M98090_REG_DSP_FILTER_ENABLE, - M98090_DMIC34BQEN_SHIFT, M98090_DMIC34BQEN_NUM - 1, 0, - snd_soc_get_volsw, max98090_put_volsw), + SOC_SINGLE("DMIC34 Biquad Switch", M98090_REG_DSP_FILTER_ENABLE, + M98090_DMIC34BQEN_SHIFT, M98090_DMIC34BQEN_NUM - 1, 0), SOC_SINGLE_TLV("DMIC34 BQ PreAttenuation Volume", M98090_REG_DMIC34_BQ_PREATTEN, M98090_AV34BQ_SHIFT, @@ -929,6 +771,19 @@ static int max98090_micinput_event(struct snd_soc_dapm_widget *w, return 0; } +static int max98090_shdn_event(struct snd_soc_dapm_widget *w, + struct snd_kcontrol *kcontrol, int event) +{ + struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm); + struct max98090_priv *max98090 = snd_soc_component_get_drvdata(component); + + if (event & SND_SOC_DAPM_POST_PMU) + max98090->shdn_pending = true; + + return 0; + +} + static const char *mic1_mux_text[] = { "IN12", "IN56" }; static SOC_ENUM_SINGLE_DECL(mic1_mux_enum, @@ -1029,14 +884,10 @@ static SOC_ENUM_SINGLE_DECL(ltenr_mux_enum, lten_mux_text); static const struct snd_kcontrol_new max98090_ltenl_mux = - SOC_DAPM_ENUM_EXT("LTENL Mux", ltenl_mux_enum, - snd_soc_dapm_get_enum_double, - max98090_dapm_put_enum_double); + SOC_DAPM_ENUM("LTENL Mux", ltenl_mux_enum); static const struct snd_kcontrol_new max98090_ltenr_mux = - SOC_DAPM_ENUM_EXT("LTENR Mux", ltenr_mux_enum, - snd_soc_dapm_get_enum_double, - max98090_dapm_put_enum_double); + SOC_DAPM_ENUM("LTENR Mux", ltenr_mux_enum); static const char *lben_mux_text[] = { "Normal", "Loopback" }; @@ -1051,14 +902,10 @@ static SOC_ENUM_SINGLE_DECL(lbenr_mux_enum, lben_mux_text); static const struct snd_kcontrol_new max98090_lbenl_mux = - SOC_DAPM_ENUM_EXT("LBENL Mux", lbenl_mux_enum, - snd_soc_dapm_get_enum_double, - max98090_dapm_put_enum_double); + SOC_DAPM_ENUM("LBENL Mux", lbenl_mux_enum); static const struct snd_kcontrol_new max98090_lbenr_mux = - SOC_DAPM_ENUM_EXT("LBENR Mux", lbenr_mux_enum, - snd_soc_dapm_get_enum_double, - max98090_dapm_put_enum_double); + SOC_DAPM_ENUM("LBENR Mux", lbenr_mux_enum); static const char *stenl_mux_text[] = { "Normal", "Sidetone Left" }; @@ -1225,25 +1072,21 @@ static const struct snd_soc_dapm_widget max98090_dapm_widgets[] = { SND_SOC_DAPM_INPUT("IN56"), SND_SOC_DAPM_SUPPLY("MICBIAS", M98090_REG_INPUT_ENABLE, - M98090_MBEN_SHIFT, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), + M98090_MBEN_SHIFT, 0, NULL, 0), SND_SOC_DAPM_SUPPLY("SHDN", M98090_REG_DEVICE_SHUTDOWN, M98090_SHDNN_SHIFT, 0, NULL, 0), SND_SOC_DAPM_SUPPLY("SDIEN", M98090_REG_IO_CONFIGURATION, - M98090_SDIEN_SHIFT, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), + M98090_SDIEN_SHIFT, 0, NULL, 0), SND_SOC_DAPM_SUPPLY("SDOEN", M98090_REG_IO_CONFIGURATION, - M98090_SDOEN_SHIFT, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), + M98090_SDOEN_SHIFT, 0, NULL, 0), SND_SOC_DAPM_SUPPLY("DMICL_ENA", M98090_REG_DIGITAL_MIC_ENABLE, - M98090_DIGMICL_SHIFT, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), + M98090_DIGMICL_SHIFT, 0, max98090_shdn_event, + SND_SOC_DAPM_POST_PMU), SND_SOC_DAPM_SUPPLY("DMICR_ENA", M98090_REG_DIGITAL_MIC_ENABLE, - M98090_DIGMICR_SHIFT, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), + M98090_DIGMICR_SHIFT, 0, max98090_shdn_event, + SND_SOC_DAPM_POST_PMU), SND_SOC_DAPM_SUPPLY("AHPF", M98090_REG_FILTER_CONFIG, - M98090_AHPF_SHIFT, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), + M98090_AHPF_SHIFT, 0, NULL, 0), /* * Note: Sysclk and misc power supplies are taken care of by SHDN @@ -1273,12 +1116,10 @@ static const struct snd_soc_dapm_widget max98090_dapm_widgets[] = { &max98090_lineb_mixer_controls[0], ARRAY_SIZE(max98090_lineb_mixer_controls)), - SND_SOC_DAPM_PGA_E("LINEA Input", M98090_REG_INPUT_ENABLE, - M98090_LINEAEN_SHIFT, 0, NULL, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), - SND_SOC_DAPM_PGA_E("LINEB Input", M98090_REG_INPUT_ENABLE, - M98090_LINEBEN_SHIFT, 0, NULL, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), + SND_SOC_DAPM_PGA("LINEA Input", M98090_REG_INPUT_ENABLE, + M98090_LINEAEN_SHIFT, 0, NULL, 0), + SND_SOC_DAPM_PGA("LINEB Input", M98090_REG_INPUT_ENABLE, + M98090_LINEBEN_SHIFT, 0, NULL, 0), SND_SOC_DAPM_MIXER("Left ADC Mixer", SND_SOC_NOPM, 0, 0, &max98090_left_adc_mixer_controls[0], @@ -1289,11 +1130,11 @@ static const struct snd_soc_dapm_widget max98090_dapm_widgets[] = { ARRAY_SIZE(max98090_right_adc_mixer_controls)), SND_SOC_DAPM_ADC_E("ADCL", NULL, M98090_REG_INPUT_ENABLE, - M98090_ADLEN_SHIFT, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), + M98090_ADLEN_SHIFT, 0, max98090_shdn_event, + SND_SOC_DAPM_POST_PMU), SND_SOC_DAPM_ADC_E("ADCR", NULL, M98090_REG_INPUT_ENABLE, - M98090_ADREN_SHIFT, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), + M98090_ADREN_SHIFT, 0, max98090_shdn_event, + SND_SOC_DAPM_POST_PMU), SND_SOC_DAPM_AIF_OUT("AIFOUTL", "HiFi Capture", 0, SND_SOC_NOPM, 0, 0), @@ -1321,12 +1162,10 @@ static const struct snd_soc_dapm_widget max98090_dapm_widgets[] = { SND_SOC_DAPM_AIF_IN("AIFINL", "HiFi Playback", 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("AIFINR", "HiFi Playback", 1, SND_SOC_NOPM, 0, 0), - SND_SOC_DAPM_DAC_E("DACL", NULL, M98090_REG_OUTPUT_ENABLE, - M98090_DALEN_SHIFT, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), - SND_SOC_DAPM_DAC_E("DACR", NULL, M98090_REG_OUTPUT_ENABLE, - M98090_DAREN_SHIFT, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), + SND_SOC_DAPM_DAC("DACL", NULL, M98090_REG_OUTPUT_ENABLE, + M98090_DALEN_SHIFT, 0), + SND_SOC_DAPM_DAC("DACR", NULL, M98090_REG_OUTPUT_ENABLE, + M98090_DAREN_SHIFT, 0), SND_SOC_DAPM_MIXER("Left Headphone Mixer", SND_SOC_NOPM, 0, 0, &max98090_left_hp_mixer_controls[0], @@ -1361,26 +1200,20 @@ static const struct snd_soc_dapm_widget max98090_dapm_widgets[] = { SND_SOC_DAPM_MUX("MIXHPRSEL Mux", SND_SOC_NOPM, 0, 0, &max98090_mixhprsel_mux), - SND_SOC_DAPM_PGA_E("HP Left Out", M98090_REG_OUTPUT_ENABLE, - M98090_HPLEN_SHIFT, 0, NULL, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), - SND_SOC_DAPM_PGA_E("HP Right Out", M98090_REG_OUTPUT_ENABLE, - M98090_HPREN_SHIFT, 0, NULL, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), - - SND_SOC_DAPM_PGA_E("SPK Left Out", M98090_REG_OUTPUT_ENABLE, - M98090_SPLEN_SHIFT, 0, NULL, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), - SND_SOC_DAPM_PGA_E("SPK Right Out", M98090_REG_OUTPUT_ENABLE, - M98090_SPREN_SHIFT, 0, NULL, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), - - SND_SOC_DAPM_PGA_E("RCV Left Out", M98090_REG_OUTPUT_ENABLE, - M98090_RCVLEN_SHIFT, 0, NULL, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), - SND_SOC_DAPM_PGA_E("RCV Right Out", M98090_REG_OUTPUT_ENABLE, - M98090_RCVREN_SHIFT, 0, NULL, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), + SND_SOC_DAPM_PGA("HP Left Out", M98090_REG_OUTPUT_ENABLE, + M98090_HPLEN_SHIFT, 0, NULL, 0), + SND_SOC_DAPM_PGA("HP Right Out", M98090_REG_OUTPUT_ENABLE, + M98090_HPREN_SHIFT, 0, NULL, 0), + + SND_SOC_DAPM_PGA("SPK Left Out", M98090_REG_OUTPUT_ENABLE, + M98090_SPLEN_SHIFT, 0, NULL, 0), + SND_SOC_DAPM_PGA("SPK Right Out", M98090_REG_OUTPUT_ENABLE, + M98090_SPREN_SHIFT, 0, NULL, 0), + + SND_SOC_DAPM_PGA("RCV Left Out", M98090_REG_OUTPUT_ENABLE, + M98090_RCVLEN_SHIFT, 0, NULL, 0), + SND_SOC_DAPM_PGA("RCV Right Out", M98090_REG_OUTPUT_ENABLE, + M98090_RCVREN_SHIFT, 0, NULL, 0), SND_SOC_DAPM_OUTPUT("HPL"), SND_SOC_DAPM_OUTPUT("HPR"), @@ -1395,11 +1228,9 @@ static const struct snd_soc_dapm_widget max98091_dapm_widgets[] = { SND_SOC_DAPM_INPUT("DMIC4"), SND_SOC_DAPM_SUPPLY("DMIC3_ENA", M98090_REG_DIGITAL_MIC_ENABLE, - M98090_DIGMIC3_SHIFT, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), + M98090_DIGMIC3_SHIFT, 0, NULL, 0), SND_SOC_DAPM_SUPPLY("DMIC4_ENA", M98090_REG_DIGITAL_MIC_ENABLE, - M98090_DIGMIC4_SHIFT, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), + M98090_DIGMIC4_SHIFT, 0, NULL, 0), }; static const struct snd_soc_dapm_route max98090_dapm_routes[] = { @@ -1670,11 +1501,6 @@ static void max98090_configure_bclk(struct snd_soc_component *component) return; } - /* - * Master mode: no need to save and restore SHDN for the following - * sensitive registers. - */ - /* Check for supported PCLK to LRCLK ratios */ for (i = 0; i < ARRAY_SIZE(pclk_rates); i++) { if ((pclk_rates[i] == max98090->sysclk) && @@ -1761,14 +1587,12 @@ static int max98090_dai_set_fmt(struct snd_soc_dai *codec_dai, switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) { case SND_SOC_DAIFMT_CBS_CFS: /* Set to slave mode PLL - MAS mode off */ - max98090_shdn_save(max98090); snd_soc_component_write(component, M98090_REG_CLOCK_RATIO_NI_MSB, 0x00); snd_soc_component_write(component, M98090_REG_CLOCK_RATIO_NI_LSB, 0x00); snd_soc_component_update_bits(component, M98090_REG_CLOCK_MODE, M98090_USE_M1_MASK, 0); - max98090_shdn_restore(max98090); max98090->master = false; break; case SND_SOC_DAIFMT_CBM_CFM: @@ -1794,9 +1618,7 @@ static int max98090_dai_set_fmt(struct snd_soc_dai *codec_dai, dev_err(component->dev, "DAI clock mode unsupported"); return -EINVAL; } - max98090_shdn_save(max98090); snd_soc_component_write(component, M98090_REG_MASTER_MODE, regval); - max98090_shdn_restore(max98090); regval = 0; switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) { @@ -1841,10 +1663,8 @@ static int max98090_dai_set_fmt(struct snd_soc_dai *codec_dai, if (max98090->tdm_slots > 1) regval ^= M98090_BCI_MASK; - max98090_shdn_save(max98090); snd_soc_component_write(component, M98090_REG_INTERFACE_FORMAT, regval); - max98090_shdn_restore(max98090); } return 0; @@ -1856,7 +1676,6 @@ static int max98090_set_tdm_slot(struct snd_soc_dai *codec_dai, struct snd_soc_component *component = codec_dai->component; struct max98090_priv *max98090 = snd_soc_component_get_drvdata(component); struct max98090_cdata *cdata; - cdata = &max98090->dai[0]; if (slots < 0 || slots > 4) @@ -1866,7 +1685,6 @@ static int max98090_set_tdm_slot(struct snd_soc_dai *codec_dai, max98090->tdm_width = slot_width; if (max98090->tdm_slots > 1) { - max98090_shdn_save(max98090); /* SLOTL SLOTR SLOTDLY */ snd_soc_component_write(component, M98090_REG_TDM_FORMAT, 0 << M98090_TDM_SLOTL_SHIFT | @@ -1877,7 +1695,6 @@ static int max98090_set_tdm_slot(struct snd_soc_dai *codec_dai, snd_soc_component_update_bits(component, M98090_REG_TDM_CONTROL, M98090_TDM_MASK, M98090_TDM_MASK); - max98090_shdn_restore(max98090); } /* @@ -2077,7 +1894,6 @@ static int max98090_configure_dmic(struct max98090_priv *max98090, dmic_freq = dmic_table[pclk_index].settings[micclk_index].freq; dmic_comp = dmic_table[pclk_index].settings[micclk_index].comp[i]; - max98090_shdn_save(max98090); regmap_update_bits(max98090->regmap, M98090_REG_DIGITAL_MIC_ENABLE, M98090_MICCLK_MASK, micclk_index << M98090_MICCLK_SHIFT); @@ -2086,7 +1902,6 @@ static int max98090_configure_dmic(struct max98090_priv *max98090, M98090_DMIC_COMP_MASK | M98090_DMIC_FREQ_MASK, dmic_comp << M98090_DMIC_COMP_SHIFT | dmic_freq << M98090_DMIC_FREQ_SHIFT); - max98090_shdn_restore(max98090); return 0; } @@ -2123,10 +1938,8 @@ static int max98090_dai_hw_params(struct snd_pcm_substream *substream, switch (params_width(params)) { case 16: - max98090_shdn_save(max98090); snd_soc_component_update_bits(component, M98090_REG_INTERFACE_FORMAT, M98090_WS_MASK, 0); - max98090_shdn_restore(max98090); break; default: return -EINVAL; @@ -2137,7 +1950,6 @@ static int max98090_dai_hw_params(struct snd_pcm_substream *substream, cdata->rate = max98090->lrclk; - max98090_shdn_save(max98090); /* Update filter mode */ if (max98090->lrclk < 24000) snd_soc_component_update_bits(component, M98090_REG_FILTER_CONFIG, @@ -2153,7 +1965,6 @@ static int max98090_dai_hw_params(struct snd_pcm_substream *substream, else snd_soc_component_update_bits(component, M98090_REG_FILTER_CONFIG, M98090_DHF_MASK, M98090_DHF_MASK); - max98090_shdn_restore(max98090); max98090_configure_dmic(max98090, max98090->dmic_freq, max98090->pclk, max98090->lrclk); @@ -2184,7 +1995,6 @@ static int max98090_dai_set_sysclk(struct snd_soc_dai *dai, * 0x02 (when master clk is 20MHz to 40MHz).. * 0x03 (when master clk is 40MHz to 60MHz).. */ - max98090_shdn_save(max98090); if ((freq >= 10000000) && (freq <= 20000000)) { snd_soc_component_write(component, M98090_REG_SYSTEM_CLOCK, M98090_PSCLK_DIV1); @@ -2199,10 +2009,8 @@ static int max98090_dai_set_sysclk(struct snd_soc_dai *dai, max98090->pclk = freq >> 2; } else { dev_err(component->dev, "Invalid master clock frequency\n"); - max98090_shdn_restore(max98090); return -EINVAL; } - max98090_shdn_restore(max98090); max98090->sysclk = freq; @@ -2314,12 +2122,10 @@ static void max98090_pll_work(struct max98090_priv *max98090) */ /* Toggle shutdown OFF then ON */ - mutex_lock(&component->card->dapm_mutex); snd_soc_component_update_bits(component, M98090_REG_DEVICE_SHUTDOWN, M98090_SHDNN_MASK, 0); snd_soc_component_update_bits(component, M98090_REG_DEVICE_SHUTDOWN, M98090_SHDNN_MASK, M98090_SHDNN_MASK); - mutex_unlock(&component->card->dapm_mutex); for (i = 0; i < 10; ++i) { /* Give PLL time to lock */ @@ -2642,12 +2448,7 @@ static int max98090_probe(struct snd_soc_component *component) */ snd_soc_component_read32(component, M98090_REG_DEVICE_STATUS); - /* - * SHDN should be 0 at the point, no need to save/restore for the - * following registers. - * - * High Performance is default - */ + /* High Performance is default */ snd_soc_component_update_bits(component, M98090_REG_DAC_CONTROL, M98090_DACHP_MASK, 1 << M98090_DACHP_SHIFT); @@ -2658,12 +2459,7 @@ static int max98090_probe(struct snd_soc_component *component) M98090_ADCHP_MASK, 1 << M98090_ADCHP_SHIFT); - /* - * SHDN should be 0 at the point, no need to save/restore for the - * following registers. - * - * Turn on VCM bandgap reference - */ + /* Turn on VCM bandgap reference */ snd_soc_component_write(component, M98090_REG_BIAS_CONTROL, M98090_VCM_MODE_MASK); @@ -2695,9 +2491,25 @@ static void max98090_remove(struct snd_soc_component *component) max98090->component = NULL; } +static void max98090_seq_notifier(struct snd_soc_component *component, + enum snd_soc_dapm_type event, int subseq) +{ + struct max98090_priv *max98090 = snd_soc_component_get_drvdata(component); + + if (max98090->shdn_pending) { + snd_soc_component_update_bits(component, M98090_REG_DEVICE_SHUTDOWN, + M98090_SHDNN_MASK, 0); + msleep(40); + snd_soc_component_update_bits(component, M98090_REG_DEVICE_SHUTDOWN, + M98090_SHDNN_MASK, M98090_SHDNN_MASK); + max98090->shdn_pending = false; + } +} + static const struct snd_soc_component_driver soc_component_dev_max98090 = { .probe = max98090_probe, .remove = max98090_remove, + .seq_notifier = max98090_seq_notifier, .set_bias_level = max98090_set_bias_level, .idle_bias_on = 1, .use_pmdown_time = 1, diff --git a/sound/soc/codecs/max98090.h b/sound/soc/codecs/max98090.h index 0a31708b7df7f7ad19083d360e4b23fb347c610c..a197114b0dad3fc648952b8f272fb8b87c1a77c1 100644 --- a/sound/soc/codecs/max98090.h +++ b/sound/soc/codecs/max98090.h @@ -1539,8 +1539,7 @@ struct max98090_priv { unsigned int pa2en; unsigned int sidetone; bool master; - int saved_count; - int saved_shdn; + bool shdn_pending; }; int max98090_mic_detect(struct snd_soc_component *component, diff --git a/sound/soc/codecs/pcm512x.c b/sound/soc/codecs/pcm512x.c index 861210f6bf4fda8516011d481e8c4f2031b4922d..4cbef9affffda95ce6af991a40d8310cf11ed13d 100644 --- a/sound/soc/codecs/pcm512x.c +++ b/sound/soc/codecs/pcm512x.c @@ -1564,13 +1564,15 @@ int pcm512x_probe(struct device *dev, struct regmap *regmap) } pcm512x->sclk = devm_clk_get(dev, NULL); - if (PTR_ERR(pcm512x->sclk) == -EPROBE_DEFER) - return -EPROBE_DEFER; + if (PTR_ERR(pcm512x->sclk) == -EPROBE_DEFER) { + ret = -EPROBE_DEFER; + goto err; + } if (!IS_ERR(pcm512x->sclk)) { ret = clk_prepare_enable(pcm512x->sclk); if (ret != 0) { dev_err(dev, "Failed to enable SCLK: %d\n", ret); - return ret; + goto err; } } diff --git a/sound/soc/codecs/rt1015.c b/sound/soc/codecs/rt1015.c index 6d490e2dbc259b9442e92103010d979ba4eea58c..66eb55b4ffd4c75e979f80a22f05343d4d460cf1 100644 --- a/sound/soc/codecs/rt1015.c +++ b/sound/soc/codecs/rt1015.c @@ -664,7 +664,7 @@ static int rt1015_hw_params(struct snd_pcm_substream *substream, snd_soc_component_update_bits(component, RT1015_TDM_MASTER, RT1015_I2S_DL_MASK, val_len); snd_soc_component_update_bits(component, RT1015_CLK2, - RT1015_FS_PD_MASK, pre_div); + RT1015_FS_PD_MASK, pre_div << RT1015_FS_PD_SFT); return 0; } @@ -857,6 +857,7 @@ struct snd_soc_dai_driver rt1015_dai[] = { .rates = RT1015_STEREO_RATES, .formats = RT1015_FORMATS, }, + .ops = &rt1015_aif_dai_ops, } }; diff --git a/sound/soc/codecs/tas2562.c b/sound/soc/codecs/tas2562.c index 729acd874c485cebd0826fa269430a3a57330878..be52886a5edb21435c4448b22e65b2214e6172d5 100644 --- a/sound/soc/codecs/tas2562.c +++ b/sound/soc/codecs/tas2562.c @@ -215,7 +215,8 @@ static int tas2562_set_bitwidth(struct tas2562_data *tas2562, int bitwidth) break; default: - dev_info(tas2562->dev, "Not supported params format\n"); + dev_info(tas2562->dev, "Unsupported bitwidth format\n"); + return -EINVAL; } ret = snd_soc_component_update_bits(tas2562->component, @@ -251,7 +252,7 @@ static int tas2562_hw_params(struct snd_pcm_substream *substream, ret = tas2562_set_samplerate(tas2562, params_rate(params)); if (ret) - dev_err(tas2562->dev, "set bitwidth failed, %d\n", ret); + dev_err(tas2562->dev, "set sample rate failed, %d\n", ret); return ret; } diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c index 8c3ea73009721f8fb89c8e4d54ca47b8b0fb50a8..9d436b0c5718a2531049e7e8ba7d025b6f1fe4c6 100644 --- a/sound/soc/fsl/fsl_sai.c +++ b/sound/soc/fsl/fsl_sai.c @@ -1020,12 +1020,24 @@ static int fsl_sai_probe(struct platform_device *pdev) ret = devm_snd_soc_register_component(&pdev->dev, &fsl_component, &fsl_sai_dai, 1); if (ret) - return ret; + goto err_pm_disable; - if (sai->soc_data->use_imx_pcm) - return imx_pcm_dma_init(pdev, IMX_SAI_DMABUF_SIZE); - else - return devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, 0); + if (sai->soc_data->use_imx_pcm) { + ret = imx_pcm_dma_init(pdev, IMX_SAI_DMABUF_SIZE); + if (ret) + goto err_pm_disable; + } else { + ret = devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, 0); + if (ret) + goto err_pm_disable; + } + + return ret; + +err_pm_disable: + pm_runtime_disable(&pdev->dev); + + return ret; } static int fsl_sai_remove(struct platform_device *pdev) diff --git a/sound/soc/intel/skylake/skl-debug.c b/sound/soc/intel/skylake/skl-debug.c index 3466675f26785572db1b73ec0a38a4423b005407..a15aa2ffa681082f2b142184e4e0bdeb243efbfe 100644 --- a/sound/soc/intel/skylake/skl-debug.c +++ b/sound/soc/intel/skylake/skl-debug.c @@ -34,8 +34,8 @@ static ssize_t skl_print_pins(struct skl_module_pin *m_pin, char *buf, int i; ssize_t ret = 0; - for (i = 0; i < max_pin; i++) - ret += snprintf(buf + size, MOD_BUF - size, + for (i = 0; i < max_pin; i++) { + ret += scnprintf(buf + size, MOD_BUF - size, "%s %d\n\tModule %d\n\tInstance %d\n\t" "In-used %s\n\tType %s\n" "\tState %d\n\tIndex %d\n", @@ -45,13 +45,15 @@ static ssize_t skl_print_pins(struct skl_module_pin *m_pin, char *buf, m_pin[i].in_use ? "Used" : "Unused", m_pin[i].is_dynamic ? "Dynamic" : "Static", m_pin[i].pin_state, i); + size += ret; + } return ret; } static ssize_t skl_print_fmt(struct skl_module_fmt *fmt, char *buf, ssize_t size, bool direction) { - return snprintf(buf + size, MOD_BUF - size, + return scnprintf(buf + size, MOD_BUF - size, "%s\n\tCh %d\n\tFreq %d\n\tBit depth %d\n\t" "Valid bit depth %d\n\tCh config %#x\n\tInterleaving %d\n\t" "Sample Type %d\n\tCh Map %#x\n", @@ -75,16 +77,16 @@ static ssize_t module_read(struct file *file, char __user *user_buf, if (!buf) return -ENOMEM; - ret = snprintf(buf, MOD_BUF, "Module:\n\tUUID %pUL\n\tModule id %d\n" + ret = scnprintf(buf, MOD_BUF, "Module:\n\tUUID %pUL\n\tModule id %d\n" "\tInstance id %d\n\tPvt_id %d\n", mconfig->guid, mconfig->id.module_id, mconfig->id.instance_id, mconfig->id.pvt_id); - ret += snprintf(buf + ret, MOD_BUF - ret, + ret += scnprintf(buf + ret, MOD_BUF - ret, "Resources:\n\tCPC %#x\n\tIBS %#x\n\tOBS %#x\t\n", res->cpc, res->ibs, res->obs); - ret += snprintf(buf + ret, MOD_BUF - ret, + ret += scnprintf(buf + ret, MOD_BUF - ret, "Module data:\n\tCore %d\n\tIn queue %d\n\t" "Out queue %d\n\tType %s\n", mconfig->core_id, mconfig->max_in_queue, @@ -94,38 +96,38 @@ static ssize_t module_read(struct file *file, char __user *user_buf, ret += skl_print_fmt(mconfig->in_fmt, buf, ret, true); ret += skl_print_fmt(mconfig->out_fmt, buf, ret, false); - ret += snprintf(buf + ret, MOD_BUF - ret, + ret += scnprintf(buf + ret, MOD_BUF - ret, "Fixup:\n\tParams %#x\n\tConverter %#x\n", mconfig->params_fixup, mconfig->converter); - ret += snprintf(buf + ret, MOD_BUF - ret, + ret += scnprintf(buf + ret, MOD_BUF - ret, "Module Gateway:\n\tType %#x\n\tVbus %#x\n\tHW conn %#x\n\tSlot %#x\n", mconfig->dev_type, mconfig->vbus_id, mconfig->hw_conn_type, mconfig->time_slot); - ret += snprintf(buf + ret, MOD_BUF - ret, + ret += scnprintf(buf + ret, MOD_BUF - ret, "Pipeline:\n\tID %d\n\tPriority %d\n\tConn Type %d\n\t" "Pages %#x\n", mconfig->pipe->ppl_id, mconfig->pipe->pipe_priority, mconfig->pipe->conn_type, mconfig->pipe->memory_pages); - ret += snprintf(buf + ret, MOD_BUF - ret, + ret += scnprintf(buf + ret, MOD_BUF - ret, "\tParams:\n\t\tHost DMA %d\n\t\tLink DMA %d\n", mconfig->pipe->p_params->host_dma_id, mconfig->pipe->p_params->link_dma_id); - ret += snprintf(buf + ret, MOD_BUF - ret, + ret += scnprintf(buf + ret, MOD_BUF - ret, "\tPCM params:\n\t\tCh %d\n\t\tFreq %d\n\t\tFormat %d\n", mconfig->pipe->p_params->ch, mconfig->pipe->p_params->s_freq, mconfig->pipe->p_params->s_fmt); - ret += snprintf(buf + ret, MOD_BUF - ret, + ret += scnprintf(buf + ret, MOD_BUF - ret, "\tLink %#x\n\tStream %#x\n", mconfig->pipe->p_params->linktype, mconfig->pipe->p_params->stream); - ret += snprintf(buf + ret, MOD_BUF - ret, + ret += scnprintf(buf + ret, MOD_BUF - ret, "\tState %d\n\tPassthru %s\n", mconfig->pipe->state, mconfig->pipe->passthru ? "true" : "false"); @@ -135,7 +137,7 @@ static ssize_t module_read(struct file *file, char __user *user_buf, ret += skl_print_pins(mconfig->m_out_pin, buf, mconfig->max_out_queue, ret, false); - ret += snprintf(buf + ret, MOD_BUF - ret, + ret += scnprintf(buf + ret, MOD_BUF - ret, "Other:\n\tDomain %d\n\tHomogeneous Input %s\n\t" "Homogeneous Output %s\n\tIn Queue Mask %d\n\t" "Out Queue Mask %d\n\tDMA ID %d\n\tMem Pages %d\n\t" @@ -191,7 +193,7 @@ static ssize_t fw_softreg_read(struct file *file, char __user *user_buf, __ioread32_copy(d->fw_read_buff, fw_reg_addr, w0_stat_sz >> 2); for (offset = 0; offset < FW_REG_SIZE; offset += 16) { - ret += snprintf(tmp + ret, FW_REG_BUF - ret, "%#.4x: ", offset); + ret += scnprintf(tmp + ret, FW_REG_BUF - ret, "%#.4x: ", offset); hex_dump_to_buffer(d->fw_read_buff + offset, 16, 16, 4, tmp + ret, FW_REG_BUF - ret, 0); ret += strlen(tmp + ret); diff --git a/sound/soc/intel/skylake/skl-ssp-clk.c b/sound/soc/intel/skylake/skl-ssp-clk.c index 1c0e5226cb5b6b18c72c3f75721a6f38426fb43c..bd43885f38052c99e5c97ba127c64c47efc2974f 100644 --- a/sound/soc/intel/skylake/skl-ssp-clk.c +++ b/sound/soc/intel/skylake/skl-ssp-clk.c @@ -384,9 +384,11 @@ static int skl_clk_dev_probe(struct platform_device *pdev) &clks[i], clk_pdata, i); if (IS_ERR(data->clk[data->avail_clk_cnt])) { - ret = PTR_ERR(data->clk[data->avail_clk_cnt++]); + ret = PTR_ERR(data->clk[data->avail_clk_cnt]); goto err_unreg_skl_clk; } + + data->avail_clk_cnt++; } platform_set_drvdata(pdev, data); diff --git a/sound/soc/meson/g12a-tohdmitx.c b/sound/soc/meson/g12a-tohdmitx.c index 9cfbd343a00c86c1d3e80b72dc0ad799c4423f72..8a0db28a6a40680eea90fdcacac7f4580b0fef0e 100644 --- a/sound/soc/meson/g12a-tohdmitx.c +++ b/sound/soc/meson/g12a-tohdmitx.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include @@ -378,6 +379,11 @@ static int g12a_tohdmitx_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; void __iomem *regs; struct regmap *map; + int ret; + + ret = device_reset(dev); + if (ret) + return ret; regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(regs)) diff --git a/sound/soc/soc-component.c b/sound/soc/soc-component.c index 14e175cdeeb84b0336218c4fd190faf38947f04f..785a0385cc7f5da3f0e83d6b963cfeacdb98c718 100644 --- a/sound/soc/soc-component.c +++ b/sound/soc/soc-component.c @@ -451,7 +451,7 @@ int snd_soc_pcm_component_sync_stop(struct snd_pcm_substream *substream) int i, ret; for_each_rtd_components(rtd, i, component) { - if (component->driver->ioctl) { + if (component->driver->sync_stop) { ret = component->driver->sync_stop(component, substream); if (ret < 0) diff --git a/sound/soc/soc-compress.c b/sound/soc/soc-compress.c index 223cd045719e8df10dbd71221391387b3f378fe2..392a1c5b15d3240e9afa17550c2bb35d100c8b36 100644 --- a/sound/soc/soc-compress.c +++ b/sound/soc/soc-compress.c @@ -299,7 +299,7 @@ static int soc_compr_free_fe(struct snd_compr_stream *cstream) for_each_dpcm_be(fe, stream, dpcm) dpcm->state = SND_SOC_DPCM_LINK_STATE_FREE; - snd_soc_dapm_stream_stop(fe, stream); + dpcm_dapm_stream_event(fe, stream, SND_SOC_DAPM_STREAM_STOP); fe->dpcm[stream].state = SND_SOC_DPCM_STATE_CLOSE; fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO; diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index bc20ad9abf8bddc119381f1ddbf010b766f7fc8d..9fb54e6fe25432e0f3014a8fcb4943999c073a86 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -3441,8 +3441,17 @@ int snd_soc_dapm_get_enum_double(struct snd_kcontrol *kcontrol, } EXPORT_SYMBOL_GPL(snd_soc_dapm_get_enum_double); -static int __snd_soc_dapm_put_enum_double(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol, int locked) +/** + * snd_soc_dapm_put_enum_double - dapm enumerated double mixer set callback + * @kcontrol: mixer control + * @ucontrol: control element information + * + * Callback to set the value of a dapm enumerated double mixer control. + * + * Returns 0 for success. + */ +int snd_soc_dapm_put_enum_double(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) { struct snd_soc_dapm_context *dapm = snd_soc_dapm_kcontrol_dapm(kcontrol); struct snd_soc_card *card = dapm->card; @@ -3465,9 +3474,7 @@ static int __snd_soc_dapm_put_enum_double(struct snd_kcontrol *kcontrol, mask |= e->mask << e->shift_r; } - if (!locked) - mutex_lock_nested(&card->dapm_mutex, - SND_SOC_DAPM_CLASS_RUNTIME); + mutex_lock_nested(&card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME); change = dapm_kcontrol_set_value(kcontrol, val); @@ -3489,50 +3496,15 @@ static int __snd_soc_dapm_put_enum_double(struct snd_kcontrol *kcontrol, card->update = NULL; } - if (!locked) - mutex_unlock(&card->dapm_mutex); + mutex_unlock(&card->dapm_mutex); if (ret > 0) soc_dpcm_runtime_update(card); return change; } - -/** - * snd_soc_dapm_put_enum_double - dapm enumerated double mixer set callback - * @kcontrol: mixer control - * @ucontrol: control element information - * - * Callback to set the value of a dapm enumerated double mixer control. - * - * Returns 0 for success. - */ -int snd_soc_dapm_put_enum_double(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) -{ - return __snd_soc_dapm_put_enum_double(kcontrol, ucontrol, 0); -} EXPORT_SYMBOL_GPL(snd_soc_dapm_put_enum_double); -/** - * snd_soc_dapm_put_enum_double_locked - dapm enumerated double mixer set - * callback - * @kcontrol: mixer control - * @ucontrol: control element information - * - * Callback to set the value of a dapm enumerated double mixer control. - * Must acquire dapm_mutex before calling the function. - * - * Returns 0 for success. - */ -int snd_soc_dapm_put_enum_double_locked(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) -{ - dapm_assert_locked(snd_soc_dapm_kcontrol_dapm(kcontrol)); - return __snd_soc_dapm_put_enum_double(kcontrol, ucontrol, 1); -} -EXPORT_SYMBOL_GPL(snd_soc_dapm_put_enum_double_locked); - /** * snd_soc_dapm_info_pin_switch - Info for a pin switch * @@ -3916,9 +3888,6 @@ snd_soc_dai_link_event_pre_pmu(struct snd_soc_dapm_widget *w, runtime->rate = params_rate(params); out: - if (ret < 0) - kfree(runtime); - kfree(params); return ret; } @@ -4803,7 +4772,7 @@ static void soc_dapm_shutdown_dapm(struct snd_soc_dapm_context *dapm) continue; if (w->power) { dapm_seq_insert(w, &down_list, false); - w->power = 0; + w->new_power = 0; powerdown = 1; } } diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index ff1b7c7078e5f1d01db793fbe6484476eeb60cf9..2c59b3688ca01b90223d79f6e2d809feca052aa5 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -2006,7 +2006,7 @@ static int dpcm_fe_dai_shutdown(struct snd_pcm_substream *substream) soc_pcm_close(substream); /* run the stream event for each BE */ - snd_soc_dapm_stream_stop(fe, stream); + dpcm_dapm_stream_event(fe, stream, SND_SOC_DAPM_STREAM_STOP); fe->dpcm[stream].state = SND_SOC_DPCM_STATE_CLOSE; dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_NO); @@ -3171,16 +3171,16 @@ static ssize_t dpcm_show_state(struct snd_soc_pcm_runtime *fe, unsigned long flags; /* FE state */ - offset += snprintf(buf + offset, size - offset, + offset += scnprintf(buf + offset, size - offset, "[%s - %s]\n", fe->dai_link->name, stream ? "Capture" : "Playback"); - offset += snprintf(buf + offset, size - offset, "State: %s\n", + offset += scnprintf(buf + offset, size - offset, "State: %s\n", dpcm_state_string(fe->dpcm[stream].state)); if ((fe->dpcm[stream].state >= SND_SOC_DPCM_STATE_HW_PARAMS) && (fe->dpcm[stream].state <= SND_SOC_DPCM_STATE_STOP)) - offset += snprintf(buf + offset, size - offset, + offset += scnprintf(buf + offset, size - offset, "Hardware Params: " "Format = %s, Channels = %d, Rate = %d\n", snd_pcm_format_name(params_format(params)), @@ -3188,10 +3188,10 @@ static ssize_t dpcm_show_state(struct snd_soc_pcm_runtime *fe, params_rate(params)); /* BEs state */ - offset += snprintf(buf + offset, size - offset, "Backends:\n"); + offset += scnprintf(buf + offset, size - offset, "Backends:\n"); if (list_empty(&fe->dpcm[stream].be_clients)) { - offset += snprintf(buf + offset, size - offset, + offset += scnprintf(buf + offset, size - offset, " No active DSP links\n"); goto out; } @@ -3201,16 +3201,16 @@ static ssize_t dpcm_show_state(struct snd_soc_pcm_runtime *fe, struct snd_soc_pcm_runtime *be = dpcm->be; params = &dpcm->hw_params; - offset += snprintf(buf + offset, size - offset, + offset += scnprintf(buf + offset, size - offset, "- %s\n", be->dai_link->name); - offset += snprintf(buf + offset, size - offset, + offset += scnprintf(buf + offset, size - offset, " State: %s\n", dpcm_state_string(be->dpcm[stream].state)); if ((be->dpcm[stream].state >= SND_SOC_DPCM_STATE_HW_PARAMS) && (be->dpcm[stream].state <= SND_SOC_DPCM_STATE_STOP)) - offset += snprintf(buf + offset, size - offset, + offset += scnprintf(buf + offset, size - offset, " Hardware Params: " "Format = %s, Channels = %d, Rate = %d\n", snd_pcm_format_name(params_format(params)), diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index d2ee6ad20e83478c030975f30fe155274917b48c..575da6aba807553b87f727047dc8c41d86e3b405 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -2377,8 +2377,11 @@ static int soc_tplg_link_elems_load(struct soc_tplg *tplg, } ret = soc_tplg_link_config(tplg, _link); - if (ret < 0) + if (ret < 0) { + if (!abi_match) + kfree(_link); return ret; + } /* offset by version-specific struct size and * real priv data size @@ -2542,7 +2545,7 @@ static int soc_tplg_manifest_load(struct soc_tplg *tplg, { struct snd_soc_tplg_manifest *manifest, *_manifest; bool abi_match; - int err; + int ret = 0; if (tplg->pass != SOC_TPLG_PASS_MANIFEST) return 0; @@ -2555,19 +2558,19 @@ static int soc_tplg_manifest_load(struct soc_tplg *tplg, _manifest = manifest; } else { abi_match = false; - err = manifest_new_ver(tplg, manifest, &_manifest); - if (err < 0) - return err; + ret = manifest_new_ver(tplg, manifest, &_manifest); + if (ret < 0) + return ret; } /* pass control to component driver for optional further init */ if (tplg->comp && tplg->ops && tplg->ops->manifest) - return tplg->ops->manifest(tplg->comp, tplg->index, _manifest); + ret = tplg->ops->manifest(tplg->comp, tplg->index, _manifest); if (!abi_match) /* free the duplicated one */ kfree(_manifest); - return 0; + return ret; } /* validate header magic, size and type */ diff --git a/sound/soc/sof/intel/hda-codec.c b/sound/soc/sof/intel/hda-codec.c index 9106ab8dac6f62d6efc0251c5b26770ff1e856fb..ff45075ef7203809acb355a6f6c6b028e9daf94f 100644 --- a/sound/soc/sof/intel/hda-codec.c +++ b/sound/soc/sof/intel/hda-codec.c @@ -174,8 +174,10 @@ void hda_codec_i915_display_power(struct snd_sof_dev *sdev, bool enable) { struct hdac_bus *bus = sof_to_bus(sdev); - dev_dbg(bus->dev, "Turning i915 HDAC power %d\n", enable); - snd_hdac_display_power(bus, HDA_CODEC_IDX_CONTROLLER, enable); + if (HDA_IDISP_CODEC(bus->codec_mask)) { + dev_dbg(bus->dev, "Turning i915 HDAC power %d\n", enable); + snd_hdac_display_power(bus, HDA_CODEC_IDX_CONTROLLER, enable); + } } EXPORT_SYMBOL_NS(hda_codec_i915_display_power, SND_SOC_SOF_HDA_AUDIO_CODEC_I915); @@ -189,7 +191,8 @@ int hda_codec_i915_init(struct snd_sof_dev *sdev) if (ret < 0) return ret; - hda_codec_i915_display_power(sdev, true); + /* codec_mask not yet known, power up for probe */ + snd_hdac_display_power(bus, HDA_CODEC_IDX_CONTROLLER, true); return 0; } @@ -200,7 +203,8 @@ int hda_codec_i915_exit(struct snd_sof_dev *sdev) struct hdac_bus *bus = sof_to_bus(sdev); int ret; - hda_codec_i915_display_power(sdev, false); + /* power down unconditionally */ + snd_hdac_display_power(bus, HDA_CODEC_IDX_CONTROLLER, false); ret = snd_hdac_i915_exit(bus); diff --git a/sound/soc/sof/intel/hda-dsp.c b/sound/soc/sof/intel/hda-dsp.c index 4a4d318f97ffa5698217c0282bb24321f94d4b4b..0848b79967a9f426e4c7d6124906eb51fe25bed9 100644 --- a/sound/soc/sof/intel/hda-dsp.c +++ b/sound/soc/sof/intel/hda-dsp.c @@ -428,6 +428,9 @@ static int hda_suspend(struct snd_sof_dev *sdev, bool runtime_suspend) return ret; } + /* display codec can powered off after link reset */ + hda_codec_i915_display_power(sdev, false); + return 0; } @@ -439,6 +442,9 @@ static int hda_resume(struct snd_sof_dev *sdev, bool runtime_resume) #endif int ret; + /* display codec must be powered before link reset */ + hda_codec_i915_display_power(sdev, true); + /* * clear TCSEL to clear playback on some HD Audio * codecs. PCI TCSEL is defined in the Intel manuals. @@ -482,6 +488,8 @@ int hda_dsp_resume(struct snd_sof_dev *sdev) struct pci_dev *pci = to_pci_dev(sdev->dev); if (sdev->s0_suspend) { + hda_codec_i915_display_power(sdev, true); + /* restore L1SEN bit */ if (hda->l1_support_changed) snd_sof_dsp_update_bits(sdev, HDA_DSP_HDA_BAR, @@ -531,6 +539,9 @@ int hda_dsp_suspend(struct snd_sof_dev *sdev) int ret; if (sdev->s0_suspend) { + /* we can't keep a wakeref to display driver at suspend */ + hda_codec_i915_display_power(sdev, false); + /* enable L1SEN to make sure the system can enter S0Ix */ hda->l1_support_changed = snd_sof_dsp_update_bits(sdev, HDA_DSP_HDA_BAR, diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c index 65b86dd044f101b0255c9be51d01961469e37407..25946a1c28224c69e2925a4b477a854769e47d62 100644 --- a/sound/soc/sof/intel/hda.c +++ b/sound/soc/sof/intel/hda.c @@ -286,6 +286,13 @@ static int hda_init(struct snd_sof_dev *sdev) /* HDA base */ sdev->bar[HDA_DSP_HDA_BAR] = bus->remap_addr; + /* init i915 and HDMI codecs */ + ret = hda_codec_i915_init(sdev); + if (ret < 0) { + dev_err(sdev->dev, "error: init i915 and HDMI codec failed\n"); + return ret; + } + /* get controller capabilities */ ret = hda_dsp_ctrl_get_caps(sdev); if (ret < 0) @@ -353,15 +360,6 @@ static int hda_init_caps(struct snd_sof_dev *sdev) if (bus->ppcap) dev_dbg(sdev->dev, "PP capability, will probe DSP later.\n"); -#if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA) - /* init i915 and HDMI codecs */ - ret = hda_codec_i915_init(sdev); - if (ret < 0) { - dev_err(sdev->dev, "error: init i915 and HDMI codec failed\n"); - return ret; - } -#endif - /* Init HDA controller after i915 init */ ret = hda_dsp_ctrl_init_chip(sdev, true); if (ret < 0) { @@ -381,7 +379,7 @@ static int hda_init_caps(struct snd_sof_dev *sdev) hda_codec_probe_bus(sdev, hda_codec_use_common_hdmi); if (!HDA_IDISP_CODEC(bus->codec_mask)) - hda_codec_i915_display_power(sdev, false); + hda_codec_i915_exit(sdev); /* * we are done probing so decrement link counts @@ -611,6 +609,7 @@ int hda_dsp_probe(struct snd_sof_dev *sdev) iounmap(sdev->bar[HDA_DSP_BAR]); hdac_bus_unmap: iounmap(bus->remap_addr); + hda_codec_i915_exit(sdev); err: return ret; } diff --git a/sound/soc/sof/ipc.c b/sound/soc/sof/ipc.c index b63fc529b4568e476cf6d22b4176189c74d97313..78aa1da7c7a9564dd5a5e606edd1759fd2fce6bb 100644 --- a/sound/soc/sof/ipc.c +++ b/sound/soc/sof/ipc.c @@ -499,7 +499,7 @@ int snd_sof_ipc_stream_posn(struct snd_soc_component *scomp, /* send IPC to the DSP */ err = sof_ipc_tx_message(sdev->ipc, - stream.hdr.cmd, &stream, sizeof(stream), &posn, + stream.hdr.cmd, &stream, sizeof(stream), posn, sizeof(*posn)); if (err < 0) { dev_err(sdev->dev, "error: failed to get stream %d position\n", diff --git a/sound/soc/stm/stm32_sai_sub.c b/sound/soc/stm/stm32_sai_sub.c index 30bcd5d3a32a8ffe4bcda256200c0ecbc7f4832b..10eb4b8e8e7eea2ae3c8567594bc95b42388a3d8 100644 --- a/sound/soc/stm/stm32_sai_sub.c +++ b/sound/soc/stm/stm32_sai_sub.c @@ -1543,20 +1543,20 @@ static int stm32_sai_sub_probe(struct platform_device *pdev) return ret; } - ret = devm_snd_soc_register_component(&pdev->dev, &stm32_component, - &sai->cpu_dai_drv, 1); + ret = snd_dmaengine_pcm_register(&pdev->dev, conf, 0); + if (ret) { + dev_err(&pdev->dev, "Could not register pcm dma\n"); + return ret; + } + + ret = snd_soc_register_component(&pdev->dev, &stm32_component, + &sai->cpu_dai_drv, 1); if (ret) return ret; if (STM_SAI_PROTOCOL_IS_SPDIF(sai)) conf = &stm32_sai_pcm_config_spdif; - ret = devm_snd_dmaengine_pcm_register(&pdev->dev, conf, 0); - if (ret) { - dev_err(&pdev->dev, "Could not register pcm dma\n"); - return ret; - } - return 0; } @@ -1565,6 +1565,8 @@ static int stm32_sai_sub_remove(struct platform_device *pdev) struct stm32_sai_sub_data *sai = dev_get_drvdata(&pdev->dev); clk_unprepare(sai->pdata->pclk); + snd_dmaengine_pcm_unregister(&pdev->dev); + snd_soc_unregister_component(&pdev->dev); return 0; } diff --git a/sound/soc/sunxi/sun8i-codec.c b/sound/soc/sunxi/sun8i-codec.c index 55798bc8eae29d27c9b85d548b4fb8d8ef355ecc..686561df8e13b30ef1672d7b7aa3c80926e7e479 100644 --- a/sound/soc/sunxi/sun8i-codec.c +++ b/sound/soc/sunxi/sun8i-codec.c @@ -80,6 +80,7 @@ #define SUN8I_SYS_SR_CTRL_AIF1_FS_MASK GENMASK(15, 12) #define SUN8I_SYS_SR_CTRL_AIF2_FS_MASK GENMASK(11, 8) +#define SUN8I_AIF1CLK_CTRL_AIF1_DATA_FMT_MASK GENMASK(3, 2) #define SUN8I_AIF1CLK_CTRL_AIF1_WORD_SIZ_MASK GENMASK(5, 4) #define SUN8I_AIF1CLK_CTRL_AIF1_LRCK_DIV_MASK GENMASK(8, 6) #define SUN8I_AIF1CLK_CTRL_AIF1_BCLK_DIV_MASK GENMASK(12, 9) @@ -241,7 +242,7 @@ static int sun8i_set_fmt(struct snd_soc_dai *dai, unsigned int fmt) return -EINVAL; } regmap_update_bits(scodec->regmap, SUN8I_AIF1CLK_CTRL, - BIT(SUN8I_AIF1CLK_CTRL_AIF1_DATA_FMT), + SUN8I_AIF1CLK_CTRL_AIF1_DATA_FMT_MASK, value << SUN8I_AIF1CLK_CTRL_AIF1_DATA_FMT); return 0; diff --git a/sound/usb/clock.c b/sound/usb/clock.c index 018b1ecb5404655e327b35ca10c420f965383d3d..a48313dfa967a15836785b9961ffb7df346e5f7a 100644 --- a/sound/usb/clock.c +++ b/sound/usb/clock.c @@ -151,8 +151,34 @@ static int uac_clock_selector_set_val(struct snd_usb_audio *chip, int selector_i return ret; } +/* + * Assume the clock is valid if clock source supports only one single sample + * rate, the terminal is connected directly to it (there is no clock selector) + * and clock type is internal. This is to deal with some Denon DJ controllers + * that always reports that clock is invalid. + */ +static bool uac_clock_source_is_valid_quirk(struct snd_usb_audio *chip, + struct audioformat *fmt, + int source_id) +{ + if (fmt->protocol == UAC_VERSION_2) { + struct uac_clock_source_descriptor *cs_desc = + snd_usb_find_clock_source(chip->ctrl_intf, source_id); + + if (!cs_desc) + return false; + + return (fmt->nr_rates == 1 && + (fmt->clock & 0xff) == cs_desc->bClockID && + (cs_desc->bmAttributes & 0x3) != + UAC_CLOCK_SOURCE_TYPE_EXT); + } + + return false; +} + static bool uac_clock_source_is_valid(struct snd_usb_audio *chip, - int protocol, + struct audioformat *fmt, int source_id) { int err; @@ -160,7 +186,7 @@ static bool uac_clock_source_is_valid(struct snd_usb_audio *chip, struct usb_device *dev = chip->dev; u32 bmControls; - if (protocol == UAC_VERSION_3) { + if (fmt->protocol == UAC_VERSION_3) { struct uac3_clock_source_descriptor *cs_desc = snd_usb_find_clock_source_v3(chip->ctrl_intf, source_id); @@ -194,10 +220,14 @@ static bool uac_clock_source_is_valid(struct snd_usb_audio *chip, return false; } - return data ? true : false; + if (data) + return true; + else + return uac_clock_source_is_valid_quirk(chip, fmt, source_id); } -static int __uac_clock_find_source(struct snd_usb_audio *chip, int entity_id, +static int __uac_clock_find_source(struct snd_usb_audio *chip, + struct audioformat *fmt, int entity_id, unsigned long *visited, bool validate) { struct uac_clock_source_descriptor *source; @@ -217,7 +247,7 @@ static int __uac_clock_find_source(struct snd_usb_audio *chip, int entity_id, source = snd_usb_find_clock_source(chip->ctrl_intf, entity_id); if (source) { entity_id = source->bClockID; - if (validate && !uac_clock_source_is_valid(chip, UAC_VERSION_2, + if (validate && !uac_clock_source_is_valid(chip, fmt, entity_id)) { usb_audio_err(chip, "clock source %d is not valid, cannot use\n", @@ -248,8 +278,9 @@ static int __uac_clock_find_source(struct snd_usb_audio *chip, int entity_id, } cur = ret; - ret = __uac_clock_find_source(chip, selector->baCSourceID[ret - 1], - visited, validate); + ret = __uac_clock_find_source(chip, fmt, + selector->baCSourceID[ret - 1], + visited, validate); if (!validate || ret > 0 || !chip->autoclock) return ret; @@ -260,8 +291,9 @@ static int __uac_clock_find_source(struct snd_usb_audio *chip, int entity_id, if (i == cur) continue; - ret = __uac_clock_find_source(chip, selector->baCSourceID[i - 1], - visited, true); + ret = __uac_clock_find_source(chip, fmt, + selector->baCSourceID[i - 1], + visited, true); if (ret < 0) continue; @@ -281,14 +313,16 @@ static int __uac_clock_find_source(struct snd_usb_audio *chip, int entity_id, /* FIXME: multipliers only act as pass-thru element for now */ multiplier = snd_usb_find_clock_multiplier(chip->ctrl_intf, entity_id); if (multiplier) - return __uac_clock_find_source(chip, multiplier->bCSourceID, - visited, validate); + return __uac_clock_find_source(chip, fmt, + multiplier->bCSourceID, + visited, validate); return -EINVAL; } -static int __uac3_clock_find_source(struct snd_usb_audio *chip, int entity_id, - unsigned long *visited, bool validate) +static int __uac3_clock_find_source(struct snd_usb_audio *chip, + struct audioformat *fmt, int entity_id, + unsigned long *visited, bool validate) { struct uac3_clock_source_descriptor *source; struct uac3_clock_selector_descriptor *selector; @@ -307,7 +341,7 @@ static int __uac3_clock_find_source(struct snd_usb_audio *chip, int entity_id, source = snd_usb_find_clock_source_v3(chip->ctrl_intf, entity_id); if (source) { entity_id = source->bClockID; - if (validate && !uac_clock_source_is_valid(chip, UAC_VERSION_3, + if (validate && !uac_clock_source_is_valid(chip, fmt, entity_id)) { usb_audio_err(chip, "clock source %d is not valid, cannot use\n", @@ -338,7 +372,8 @@ static int __uac3_clock_find_source(struct snd_usb_audio *chip, int entity_id, } cur = ret; - ret = __uac3_clock_find_source(chip, selector->baCSourceID[ret - 1], + ret = __uac3_clock_find_source(chip, fmt, + selector->baCSourceID[ret - 1], visited, validate); if (!validate || ret > 0 || !chip->autoclock) return ret; @@ -350,8 +385,9 @@ static int __uac3_clock_find_source(struct snd_usb_audio *chip, int entity_id, if (i == cur) continue; - ret = __uac3_clock_find_source(chip, selector->baCSourceID[i - 1], - visited, true); + ret = __uac3_clock_find_source(chip, fmt, + selector->baCSourceID[i - 1], + visited, true); if (ret < 0) continue; @@ -372,7 +408,8 @@ static int __uac3_clock_find_source(struct snd_usb_audio *chip, int entity_id, multiplier = snd_usb_find_clock_multiplier_v3(chip->ctrl_intf, entity_id); if (multiplier) - return __uac3_clock_find_source(chip, multiplier->bCSourceID, + return __uac3_clock_find_source(chip, fmt, + multiplier->bCSourceID, visited, validate); return -EINVAL; @@ -389,18 +426,18 @@ static int __uac3_clock_find_source(struct snd_usb_audio *chip, int entity_id, * * Returns the clock source UnitID (>=0) on success, or an error. */ -int snd_usb_clock_find_source(struct snd_usb_audio *chip, int protocol, - int entity_id, bool validate) +int snd_usb_clock_find_source(struct snd_usb_audio *chip, + struct audioformat *fmt, bool validate) { DECLARE_BITMAP(visited, 256); memset(visited, 0, sizeof(visited)); - switch (protocol) { + switch (fmt->protocol) { case UAC_VERSION_2: - return __uac_clock_find_source(chip, entity_id, visited, + return __uac_clock_find_source(chip, fmt, fmt->clock, visited, validate); case UAC_VERSION_3: - return __uac3_clock_find_source(chip, entity_id, visited, + return __uac3_clock_find_source(chip, fmt, fmt->clock, visited, validate); default: return -EINVAL; @@ -501,8 +538,7 @@ static int set_sample_rate_v2v3(struct snd_usb_audio *chip, int iface, * automatic clock selection if the current clock is not * valid. */ - clock = snd_usb_clock_find_source(chip, fmt->protocol, - fmt->clock, true); + clock = snd_usb_clock_find_source(chip, fmt, true); if (clock < 0) { /* We did not find a valid clock, but that might be * because the current sample rate does not match an @@ -510,8 +546,7 @@ static int set_sample_rate_v2v3(struct snd_usb_audio *chip, int iface, * and we will do another validation after setting the * rate. */ - clock = snd_usb_clock_find_source(chip, fmt->protocol, - fmt->clock, false); + clock = snd_usb_clock_find_source(chip, fmt, false); if (clock < 0) return clock; } @@ -577,7 +612,7 @@ static int set_sample_rate_v2v3(struct snd_usb_audio *chip, int iface, validation: /* validate clock after rate change */ - if (!uac_clock_source_is_valid(chip, fmt->protocol, clock)) + if (!uac_clock_source_is_valid(chip, fmt, clock)) return -ENXIO; return 0; } diff --git a/sound/usb/clock.h b/sound/usb/clock.h index 076e31b79ee0ff69a137d8367af1041d12686e66..68df0fbe09d0073c681dd521a8164ab15e518d7d 100644 --- a/sound/usb/clock.h +++ b/sound/usb/clock.h @@ -6,7 +6,7 @@ int snd_usb_init_sample_rate(struct snd_usb_audio *chip, int iface, struct usb_host_interface *alts, struct audioformat *fmt, int rate); -int snd_usb_clock_find_source(struct snd_usb_audio *chip, int protocol, - int entity_id, bool validate); +int snd_usb_clock_find_source(struct snd_usb_audio *chip, + struct audioformat *fmt, bool validate); #endif /* __USBAUDIO_CLOCK_H */ diff --git a/sound/usb/format.c b/sound/usb/format.c index 9260136e4c9bb77dd3b79562c842e921ad469c4c..9f5cb4ed3a0c4466b24f59b3d59beff216c62947 100644 --- a/sound/usb/format.c +++ b/sound/usb/format.c @@ -151,6 +151,19 @@ static u64 parse_audio_format_i_type(struct snd_usb_audio *chip, return pcm_formats; } +static int set_fixed_rate(struct audioformat *fp, int rate, int rate_bits) +{ + kfree(fp->rate_table); + fp->rate_table = kmalloc(sizeof(int), GFP_KERNEL); + if (!fp->rate_table) + return -ENOMEM; + fp->nr_rates = 1; + fp->rate_min = rate; + fp->rate_max = rate; + fp->rates = rate_bits; + fp->rate_table[0] = rate; + return 0; +} /* * parse the format descriptor and stores the possible sample rates @@ -223,6 +236,14 @@ static int parse_audio_format_rates_v1(struct snd_usb_audio *chip, struct audiof fp->rate_min = combine_triple(&fmt[offset + 1]); fp->rate_max = combine_triple(&fmt[offset + 4]); } + + /* Jabra Evolve 65 headset */ + if (chip->usb_id == USB_ID(0x0b0e, 0x030b)) { + /* only 48kHz for playback while keeping 16kHz for capture */ + if (fp->nr_rates != 1) + return set_fixed_rate(fp, 48000, SNDRV_PCM_RATE_48000); + } + return 0; } @@ -299,17 +320,7 @@ static int line6_parse_audio_format_rates_quirk(struct snd_usb_audio *chip, case USB_ID(0x0e41, 0x4248): /* Line6 Helix >= fw 2.82 */ case USB_ID(0x0e41, 0x4249): /* Line6 Helix Rack >= fw 2.82 */ case USB_ID(0x0e41, 0x424a): /* Line6 Helix LT >= fw 2.82 */ - /* supported rates: 48Khz */ - kfree(fp->rate_table); - fp->rate_table = kmalloc(sizeof(int), GFP_KERNEL); - if (!fp->rate_table) - return -ENOMEM; - fp->nr_rates = 1; - fp->rate_min = 48000; - fp->rate_max = 48000; - fp->rates = SNDRV_PCM_RATE_48000; - fp->rate_table[0] = 48000; - return 0; + return set_fixed_rate(fp, 48000, SNDRV_PCM_RATE_48000); } return -ENODEV; @@ -325,8 +336,7 @@ static int parse_audio_format_rates_v2v3(struct snd_usb_audio *chip, struct usb_device *dev = chip->dev; unsigned char tmp[2], *data; int nr_triplets, data_size, ret = 0, ret_l6; - int clock = snd_usb_clock_find_source(chip, fp->protocol, - fp->clock, false); + int clock = snd_usb_clock_find_source(chip, fp, false); if (clock < 0) { dev_err(&dev->dev, diff --git a/sound/usb/line6/driver.c b/sound/usb/line6/driver.c index b5a3f754a4f13e145e42172be822a2a4a1190dc7..4f096685ed6543fd892d473d2f02896ed292260a 100644 --- a/sound/usb/line6/driver.c +++ b/sound/usb/line6/driver.c @@ -305,7 +305,7 @@ static void line6_data_received(struct urb *urb) line6_midibuf_read(mb, line6->buffer_message, LINE6_MIDI_MESSAGE_MAXLEN); - if (done == 0) + if (done <= 0) break; line6->message_length = done; diff --git a/sound/usb/line6/midibuf.c b/sound/usb/line6/midibuf.c index 8d6eefa0d9362a1c6c64d7b5cac955f9bc94bc5c..6a70463f82c4efcbd533c192844e072cae497cc2 100644 --- a/sound/usb/line6/midibuf.c +++ b/sound/usb/line6/midibuf.c @@ -159,7 +159,7 @@ int line6_midibuf_read(struct midi_buffer *this, unsigned char *data, int midi_length_prev = midibuf_message_length(this->command_prev); - if (midi_length_prev > 0) { + if (midi_length_prev > 1) { midi_length = midi_length_prev - 1; repeat = 1; } else diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index d659fdb475e2bc373941df884b0404364cfb534b..81b2db0edd5f43bcbd8406f533c6732da7e84326 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -897,6 +897,15 @@ static int parse_term_proc_unit(struct mixer_build *state, return 0; } +static int parse_term_effect_unit(struct mixer_build *state, + struct usb_audio_term *term, + void *p1, int id) +{ + term->type = UAC3_EFFECT_UNIT << 16; /* virtual type */ + term->id = id; + return 0; +} + static int parse_term_uac2_clock_source(struct mixer_build *state, struct usb_audio_term *term, void *p1, int id) @@ -981,8 +990,7 @@ static int __check_input_term(struct mixer_build *state, int id, UAC3_PROCESSING_UNIT); case PTYPE(UAC_VERSION_2, UAC2_EFFECT_UNIT): case PTYPE(UAC_VERSION_3, UAC3_EFFECT_UNIT): - return parse_term_proc_unit(state, term, p1, id, - UAC3_EFFECT_UNIT); + return parse_term_effect_unit(state, term, p1, id); case PTYPE(UAC_VERSION_1, UAC1_EXTENSION_UNIT): case PTYPE(UAC_VERSION_2, UAC2_EXTENSION_UNIT_V2): case PTYPE(UAC_VERSION_3, UAC3_EXTENSION_UNIT): diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 3a5242e383b24ad21652f98aa3396567417043ca..7f558f4b452045f07700f0dc95fea50746eb600b 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1440,6 +1440,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip) case USB_ID(0x1395, 0x740a): /* Sennheiser DECT */ case USB_ID(0x1901, 0x0191): /* GE B850V3 CP2114 audio interface */ case USB_ID(0x21b4, 0x0081): /* AudioQuest DragonFly */ + case USB_ID(0x2912, 0x30c8): /* Audioengine D1 */ return true; } diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index 820e5751ada71ab1ce0e08b90e026d4a9231dd36..ba85bb23f06017b4ed401da32167c057d526b1d0 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -220,10 +220,18 @@ struct kvm_vcpu_events { #define KVM_REG_ARM_PTIMER_CVAL ARM64_SYS_REG(3, 3, 14, 2, 2) #define KVM_REG_ARM_PTIMER_CNT ARM64_SYS_REG(3, 3, 14, 0, 1) -/* EL0 Virtual Timer Registers */ +/* + * EL0 Virtual Timer Registers + * + * WARNING: + * KVM_REG_ARM_TIMER_CVAL and KVM_REG_ARM_TIMER_CNT are not defined + * with the appropriate register encodings. Their values have been + * accidentally swapped. As this is set API, the definitions here + * must be used, rather than ones derived from the encodings. + */ #define KVM_REG_ARM_TIMER_CTL ARM64_SYS_REG(3, 3, 14, 3, 1) -#define KVM_REG_ARM_TIMER_CNT ARM64_SYS_REG(3, 3, 14, 3, 2) #define KVM_REG_ARM_TIMER_CVAL ARM64_SYS_REG(3, 3, 14, 0, 2) +#define KVM_REG_ARM_TIMER_CNT ARM64_SYS_REG(3, 3, 14, 3, 2) /* KVM-as-firmware specific pseudo-registers */ #define KVM_REG_ARM_FW (0x0014 << KVM_REG_ARM_COPROC_SHIFT) diff --git a/tools/arch/arm64/include/uapi/asm/unistd.h b/tools/arch/arm64/include/uapi/asm/unistd.h index 4703d218663a2ad81e7c8d4fd0749bed8199ef4f..f83a70e07df85ca5029a1e91cde93b8e0dd9fb7e 100644 --- a/tools/arch/arm64/include/uapi/asm/unistd.h +++ b/tools/arch/arm64/include/uapi/asm/unistd.h @@ -19,5 +19,6 @@ #define __ARCH_WANT_NEW_STAT #define __ARCH_WANT_SET_GET_RLIMIT #define __ARCH_WANT_TIME32_SYSCALLS +#define __ARCH_WANT_SYS_CLONE3 #include diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index e9b62498fe75a3f3fce3692678e5ff28bbb28880..f3327cb56edfe163d1a8fc0a45b89fb324573243 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -220,6 +220,7 @@ #define X86_FEATURE_ZEN ( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */ #define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* "" L1TF workaround PTE inversion */ #define X86_FEATURE_IBRS_ENHANCED ( 7*32+30) /* Enhanced IBRS */ +#define X86_FEATURE_MSR_IA32_FEAT_CTL ( 7*32+31) /* "" MSR IA32_FEAT_CTL configured */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ @@ -357,6 +358,7 @@ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ #define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_FSRM (18*32+ 4) /* Fast Short Rep Mov */ #define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* AVX-512 Intersect for D/Q */ #define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */ #define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */ diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 8e1d0bb463611026f80589660c7ea16c850fecf1..4ea8584682f9982662e34db1f9df77377f4a3662 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -10,12 +10,6 @@ * cpu_feature_enabled(). */ -#ifdef CONFIG_X86_INTEL_MPX -# define DISABLE_MPX 0 -#else -# define DISABLE_MPX (1<<(X86_FEATURE_MPX & 31)) -#endif - #ifdef CONFIG_X86_SMAP # define DISABLE_SMAP 0 #else @@ -74,7 +68,7 @@ #define DISABLED_MASK6 0 #define DISABLED_MASK7 (DISABLE_PTI) #define DISABLED_MASK8 0 -#define DISABLED_MASK9 (DISABLE_MPX|DISABLE_SMAP) +#define DISABLED_MASK9 (DISABLE_SMAP) #define DISABLED_MASK10 0 #define DISABLED_MASK11 0 #define DISABLED_MASK12 0 diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index ebe1685e92dda2bfd6795b45a92924de8a8f9451..d5e517d1c3ddc5c9ac6e594500d87524168b143d 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -512,6 +512,8 @@ #define MSR_K7_HWCR 0xc0010015 #define MSR_K7_HWCR_SMMLOCK_BIT 0 #define MSR_K7_HWCR_SMMLOCK BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT) +#define MSR_K7_HWCR_IRPERF_EN_BIT 30 +#define MSR_K7_HWCR_IRPERF_EN BIT_ULL(MSR_K7_HWCR_IRPERF_EN_BIT) #define MSR_K7_FID_VID_CTL 0xc0010041 #define MSR_K7_FID_VID_STATUS 0xc0010042 diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 503d3f42da1676791d2c4f4a70bfad35743daf4c..3f3f780c8c6500e1a1ea52bc0585af93699572fe 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -390,6 +390,7 @@ struct kvm_sync_regs { #define KVM_STATE_NESTED_GUEST_MODE 0x00000001 #define KVM_STATE_NESTED_RUN_PENDING 0x00000002 #define KVM_STATE_NESTED_EVMCS 0x00000004 +#define KVM_STATE_NESTED_MTF_PENDING 0x00000008 #define KVM_STATE_NESTED_SMM_GUEST_MODE 0x00000001 #define KVM_STATE_NESTED_SMM_VMXON 0x00000002 diff --git a/tools/bootconfig/include/linux/memblock.h b/tools/bootconfig/include/linux/memblock.h new file mode 100644 index 0000000000000000000000000000000000000000..7862f217d85d37d234d4679c32ebe7e988a0580b --- /dev/null +++ b/tools/bootconfig/include/linux/memblock.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _XBC_LINUX_MEMBLOCK_H +#define _XBC_LINUX_MEMBLOCK_H + +#include + +#define __pa(addr) (addr) +#define SMP_CACHE_BYTES 0 +#define memblock_alloc(size, align) malloc(size) +#define memblock_free(paddr, size) free(paddr) + +#endif diff --git a/tools/bootconfig/include/linux/printk.h b/tools/bootconfig/include/linux/printk.h index 017bcd6912a5cbc0c830e001abed2f9e17f2863e..036e667596eb17c383e46cdc331961b9ed3c2ab2 100644 --- a/tools/bootconfig/include/linux/printk.h +++ b/tools/bootconfig/include/linux/printk.h @@ -4,10 +4,7 @@ #include -/* controllable printf */ -extern int pr_output; -#define printk(fmt, ...) \ - (pr_output ? printf(fmt, __VA_ARGS__) : 0) +#define printk(fmt, ...) printf(fmt, ##__VA_ARGS__) #define pr_err printk #define pr_warn printk diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c index 47f4884583289debf08d2033276a45e4f7e62d71..a9b97814d1a937b139893076fbdcb47b9bd05d50 100644 --- a/tools/bootconfig/main.c +++ b/tools/bootconfig/main.c @@ -14,8 +14,6 @@ #include #include -int pr_output = 1; - static int xbc_show_array(struct xbc_node *node) { const char *val; @@ -131,16 +129,27 @@ int load_xbc_from_initrd(int fd, char **buf) struct stat stat; int ret; u32 size = 0, csum = 0, rcsum; + char magic[BOOTCONFIG_MAGIC_LEN]; ret = fstat(fd, &stat); if (ret < 0) return -errno; - if (stat.st_size < 8) + if (stat.st_size < 8 + BOOTCONFIG_MAGIC_LEN) return 0; - if (lseek(fd, -8, SEEK_END) < 0) { - printf("Failed to lseek: %d\n", -errno); + if (lseek(fd, -BOOTCONFIG_MAGIC_LEN, SEEK_END) < 0) { + pr_err("Failed to lseek: %d\n", -errno); + return -errno; + } + if (read(fd, magic, BOOTCONFIG_MAGIC_LEN) < 0) + return -errno; + /* Check the bootconfig magic bytes */ + if (memcmp(magic, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN) != 0) + return 0; + + if (lseek(fd, -(8 + BOOTCONFIG_MAGIC_LEN), SEEK_END) < 0) { + pr_err("Failed to lseek: %d\n", -errno); return -errno; } @@ -150,12 +159,15 @@ int load_xbc_from_initrd(int fd, char **buf) if (read(fd, &csum, sizeof(u32)) < 0) return -errno; - /* Wrong size, maybe no boot config here */ - if (stat.st_size < size + 8) - return 0; + /* Wrong size error */ + if (stat.st_size < size + 8 + BOOTCONFIG_MAGIC_LEN) { + pr_err("bootconfig size is too big\n"); + return -E2BIG; + } - if (lseek(fd, stat.st_size - 8 - size, SEEK_SET) < 0) { - printf("Failed to lseek: %d\n", -errno); + if (lseek(fd, stat.st_size - (size + 8 + BOOTCONFIG_MAGIC_LEN), + SEEK_SET) < 0) { + pr_err("Failed to lseek: %d\n", -errno); return -errno; } @@ -163,17 +175,17 @@ int load_xbc_from_initrd(int fd, char **buf) if (ret < 0) return ret; - /* Wrong Checksum, maybe no boot config here */ + /* Wrong Checksum */ rcsum = checksum((unsigned char *)*buf, size); if (csum != rcsum) { - printf("checksum error: %d != %d\n", csum, rcsum); - return 0; + pr_err("checksum error: %d != %d\n", csum, rcsum); + return -EINVAL; } ret = xbc_init(*buf); - /* Wrong data, maybe no boot config here */ + /* Wrong data */ if (ret < 0) - return 0; + return ret; return size; } @@ -185,13 +197,13 @@ int show_xbc(const char *path) fd = open(path, O_RDONLY); if (fd < 0) { - printf("Failed to open initrd %s: %d\n", path, fd); + pr_err("Failed to open initrd %s: %d\n", path, fd); return -errno; } ret = load_xbc_from_initrd(fd, &buf); if (ret < 0) - printf("Failed to load a boot config from initrd: %d\n", ret); + pr_err("Failed to load a boot config from initrd: %d\n", ret); else xbc_show_compact_tree(); @@ -209,24 +221,19 @@ int delete_xbc(const char *path) fd = open(path, O_RDWR); if (fd < 0) { - printf("Failed to open initrd %s: %d\n", path, fd); + pr_err("Failed to open initrd %s: %d\n", path, fd); return -errno; } - /* - * Suppress error messages in xbc_init() because it can be just a - * data which concidentally matches the size and checksum footer. - */ - pr_output = 0; size = load_xbc_from_initrd(fd, &buf); - pr_output = 1; if (size < 0) { ret = size; - printf("Failed to load a boot config from initrd: %d\n", ret); + pr_err("Failed to load a boot config from initrd: %d\n", ret); } else if (size > 0) { ret = fstat(fd, &stat); if (!ret) - ret = ftruncate(fd, stat.st_size - size - 8); + ret = ftruncate(fd, stat.st_size + - size - 8 - BOOTCONFIG_MAGIC_LEN); if (ret) ret = -errno; } /* Ignore if there is no boot config in initrd */ @@ -245,7 +252,7 @@ int apply_xbc(const char *path, const char *xbc_path) ret = load_xbc_file(xbc_path, &buf); if (ret < 0) { - printf("Failed to load %s : %d\n", xbc_path, ret); + pr_err("Failed to load %s : %d\n", xbc_path, ret); return ret; } size = strlen(buf) + 1; @@ -262,7 +269,7 @@ int apply_xbc(const char *path, const char *xbc_path) /* Check the data format */ ret = xbc_init(buf); if (ret < 0) { - printf("Failed to parse %s: %d\n", xbc_path, ret); + pr_err("Failed to parse %s: %d\n", xbc_path, ret); free(data); free(buf); return ret; @@ -279,20 +286,26 @@ int apply_xbc(const char *path, const char *xbc_path) /* Remove old boot config if exists */ ret = delete_xbc(path); if (ret < 0) { - printf("Failed to delete previous boot config: %d\n", ret); + pr_err("Failed to delete previous boot config: %d\n", ret); return ret; } /* Apply new one */ fd = open(path, O_RDWR | O_APPEND); if (fd < 0) { - printf("Failed to open %s: %d\n", path, fd); + pr_err("Failed to open %s: %d\n", path, fd); return fd; } /* TODO: Ensure the @path is initramfs/initrd image */ ret = write(fd, data, size + 8); if (ret < 0) { - printf("Failed to apply a boot config: %d\n", ret); + pr_err("Failed to apply a boot config: %d\n", ret); + return ret; + } + /* Write a magic word of the bootconfig */ + ret = write(fd, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN); + if (ret < 0) { + pr_err("Failed to apply a boot config magic: %d\n", ret); return ret; } close(fd); @@ -334,12 +347,12 @@ int main(int argc, char **argv) } if (apply && delete) { - printf("Error: You can not specify both -a and -d at once.\n"); + pr_err("Error: You can not specify both -a and -d at once.\n"); return usage(); } if (optind >= argc) { - printf("Error: No initrd is specified.\n"); + pr_err("Error: No initrd is specified.\n"); return usage(); } diff --git a/tools/bootconfig/samples/bad-mixed-kv1.bconf b/tools/bootconfig/samples/bad-mixed-kv1.bconf new file mode 100644 index 0000000000000000000000000000000000000000..1761547dd05caee6ea1d04bddfb2d4d332d5d78e --- /dev/null +++ b/tools/bootconfig/samples/bad-mixed-kv1.bconf @@ -0,0 +1,3 @@ +# value -> subkey pattern +key = value +key.subkey = another-value diff --git a/tools/bootconfig/samples/bad-mixed-kv2.bconf b/tools/bootconfig/samples/bad-mixed-kv2.bconf new file mode 100644 index 0000000000000000000000000000000000000000..6b32e0c3878c00db123cdd8c5ecc68353cc4be58 --- /dev/null +++ b/tools/bootconfig/samples/bad-mixed-kv2.bconf @@ -0,0 +1,3 @@ +# subkey -> value pattern +key.subkey = value +key = another-value diff --git a/tools/bootconfig/samples/bad-samekey.bconf b/tools/bootconfig/samples/bad-samekey.bconf new file mode 100644 index 0000000000000000000000000000000000000000..e8d983a4563cd532a4b9502473bca247c39d5b4a --- /dev/null +++ b/tools/bootconfig/samples/bad-samekey.bconf @@ -0,0 +1,6 @@ +# Same key value is not allowed +key { + foo = value + bar = value2 +} +key.foo = value diff --git a/tools/bootconfig/test-bootconfig.sh b/tools/bootconfig/test-bootconfig.sh index 87725e8723f87c74f5f1b5340f2e08ce47b3e160..1411f4c3454fbdb55cb1e290f71fc9849fa931ce 100755 --- a/tools/bootconfig/test-bootconfig.sh +++ b/tools/bootconfig/test-bootconfig.sh @@ -9,7 +9,7 @@ TEMPCONF=`mktemp temp-XXXX.bconf` NG=0 cleanup() { - rm -f $INITRD $TEMPCONF + rm -f $INITRD $TEMPCONF $OUTFILE exit $NG } @@ -49,7 +49,7 @@ xpass $BOOTCONF -a $TEMPCONF $INITRD new_size=$(stat -c %s $INITRD) echo "File size check" -xpass test $new_size -eq $(expr $bconf_size + $initrd_size + 9) +xpass test $new_size -eq $(expr $bconf_size + $initrd_size + 9 + 12) echo "Apply command repeat test" xpass $BOOTCONF -a $TEMPCONF $INITRD @@ -64,6 +64,14 @@ echo "File size check" new_size=$(stat -c %s $INITRD) xpass test $new_size -eq $initrd_size +echo "No error messge while applying" +OUTFILE=`mktemp tempout-XXXX` +dd if=/dev/zero of=$INITRD bs=4096 count=1 +printf " \0\0\0 \0\0\0" >> $INITRD +$BOOTCONF -a $TEMPCONF $INITRD > $OUTFILE 2>&1 +xfail grep -i "failed" $OUTFILE +xfail grep -i "error" $OUTFILE + echo "Max node number check" echo -n > $TEMPCONF @@ -87,6 +95,19 @@ truncate -s 32764 $TEMPCONF echo "\"" >> $TEMPCONF # add 2 bytes + terminal ('\"\n\0') xpass $BOOTCONF -a $TEMPCONF $INITRD +echo "Adding same-key values" +cat > $TEMPCONF << EOF +key = bar, baz +key += qux +EOF +echo > $INITRD + +xpass $BOOTCONF -a $TEMPCONF $INITRD +$BOOTCONF $INITRD > $OUTFILE +xpass grep -q "bar" $OUTFILE +xpass grep -q "baz" $OUTFILE +xpass grep -q "qux" $OUTFILE + echo "=== expected failure cases ===" for i in samples/bad-* ; do xfail $BOOTCONF -a $i $INITRD diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h index c160a5354eb62b3b17de564be439451c812470ae..f94f65d429bea3c26bdcdc3197376916399089e9 100644 --- a/tools/include/uapi/asm-generic/mman-common.h +++ b/tools/include/uapi/asm-generic/mman-common.h @@ -11,6 +11,8 @@ #define PROT_WRITE 0x2 /* page can be written */ #define PROT_EXEC 0x4 /* page can be executed */ #define PROT_SEM 0x8 /* page may be used for atomic ops */ +/* 0x10 reserved for arch-specific use */ +/* 0x20 reserved for arch-specific use */ #define PROT_NONE 0x0 /* page can not be accessed */ #define PROT_GROWSDOWN 0x01000000 /* mprotect flag: extend change to start of growsdown vma */ #define PROT_GROWSUP 0x02000000 /* mprotect flag: extend change to end of growsup vma */ diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index 1fc8faa6e97306dfa95335ecba91b3777a843aa9..3a3201e4618ef8c7445895b26f6eebbaea1574f9 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -851,8 +851,13 @@ __SYSCALL(__NR_pidfd_open, sys_pidfd_open) __SYSCALL(__NR_clone3, sys_clone3) #endif +#define __NR_openat2 437 +__SYSCALL(__NR_openat2, sys_openat2) +#define __NR_pidfd_getfd 438 +__SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd) + #undef __NR_syscalls -#define __NR_syscalls 436 +#define __NR_syscalls 439 /* * 32 bit systems traditionally used different diff --git a/tools/include/uapi/asm/errno.h b/tools/include/uapi/asm/errno.h index ce3c5945a1c48ebb793b83080fc5225706148d66..637189ec1ab992e5a5313a8d71c8c499ffb27411 100644 --- a/tools/include/uapi/asm/errno.h +++ b/tools/include/uapi/asm/errno.h @@ -1,18 +1,18 @@ /* SPDX-License-Identifier: GPL-2.0 */ #if defined(__i386__) || defined(__x86_64__) -#include "../../arch/x86/include/uapi/asm/errno.h" +#include "../../../arch/x86/include/uapi/asm/errno.h" #elif defined(__powerpc__) -#include "../../arch/powerpc/include/uapi/asm/errno.h" +#include "../../../arch/powerpc/include/uapi/asm/errno.h" #elif defined(__sparc__) -#include "../../arch/sparc/include/uapi/asm/errno.h" +#include "../../../arch/sparc/include/uapi/asm/errno.h" #elif defined(__alpha__) -#include "../../arch/alpha/include/uapi/asm/errno.h" +#include "../../../arch/alpha/include/uapi/asm/errno.h" #elif defined(__mips__) -#include "../../arch/mips/include/uapi/asm/errno.h" +#include "../../../arch/mips/include/uapi/asm/errno.h" #elif defined(__ia64__) -#include "../../arch/ia64/include/uapi/asm/errno.h" +#include "../../../arch/ia64/include/uapi/asm/errno.h" #elif defined(__xtensa__) -#include "../../arch/xtensa/include/uapi/asm/errno.h" +#include "../../../arch/xtensa/include/uapi/asm/errno.h" #else #include #endif diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 5400d7e057f143abdeb124c229ccfe7cdeb58196..829c0a48577f8b942b7efbf4d7a6438c7d72a670 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -395,6 +395,7 @@ typedef struct _drm_i915_sarea { #define DRM_IOCTL_I915_GEM_PWRITE DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_PWRITE, struct drm_i915_gem_pwrite) #define DRM_IOCTL_I915_GEM_MMAP DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP, struct drm_i915_gem_mmap) #define DRM_IOCTL_I915_GEM_MMAP_GTT DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP_GTT, struct drm_i915_gem_mmap_gtt) +#define DRM_IOCTL_I915_GEM_MMAP_OFFSET DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP_GTT, struct drm_i915_gem_mmap_offset) #define DRM_IOCTL_I915_GEM_SET_DOMAIN DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SET_DOMAIN, struct drm_i915_gem_set_domain) #define DRM_IOCTL_I915_GEM_SW_FINISH DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SW_FINISH, struct drm_i915_gem_sw_finish) #define DRM_IOCTL_I915_GEM_SET_TILING DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_SET_TILING, struct drm_i915_gem_set_tiling) @@ -793,6 +794,37 @@ struct drm_i915_gem_mmap_gtt { __u64 offset; }; +struct drm_i915_gem_mmap_offset { + /** Handle for the object being mapped. */ + __u32 handle; + __u32 pad; + /** + * Fake offset to use for subsequent mmap call + * + * This is a fixed-size type for 32/64 compatibility. + */ + __u64 offset; + + /** + * Flags for extended behaviour. + * + * It is mandatory that one of the MMAP_OFFSET types + * (GTT, WC, WB, UC, etc) should be included. + */ + __u64 flags; +#define I915_MMAP_OFFSET_GTT 0 +#define I915_MMAP_OFFSET_WC 1 +#define I915_MMAP_OFFSET_WB 2 +#define I915_MMAP_OFFSET_UC 3 + + /* + * Zero-terminated chain of extensions. + * + * No current extensions defined; mbz. + */ + __u64 extensions; +}; + struct drm_i915_gem_set_domain { /** Handle for the object */ __u32 handle; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index f1d74a2bd23493635afcbd6a7336c2fd2806f471..22f235260a3a352cf4223249fc1d26f2fce62f34 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1045,9 +1045,9 @@ union bpf_attr { * supports redirection to the egress interface, and accepts no * flag at all. * - * The same effect can be attained with the more generic - * **bpf_redirect_map**\ (), which requires specific maps to be - * used but offers better performance. + * The same effect can also be attained with the more generic + * **bpf_redirect_map**\ (), which uses a BPF map to store the + * redirect target instead of providing it directly to the helper. * Return * For XDP, the helper returns **XDP_REDIRECT** on success or * **XDP_ABORTED** on error. For other program types, the values @@ -1611,13 +1611,11 @@ union bpf_attr { * the caller. Any higher bits in the *flags* argument must be * unset. * - * When used to redirect packets to net devices, this helper - * provides a high performance increase over **bpf_redirect**\ (). - * This is due to various implementation details of the underlying - * mechanisms, one of which is the fact that **bpf_redirect_map**\ - * () tries to send packet as a "bulk" to the device. + * See also bpf_redirect(), which only supports redirecting to an + * ifindex, but doesn't require a map to do so. * Return - * **XDP_REDIRECT** on success, or **XDP_ABORTED** on error. + * **XDP_REDIRECT** on success, or the value of the two lower bits + * of the **flags* argument on error. * * int bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags) * Description diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h index 1f97b33c840e09936fb92b6a13d82e333d0e8151..ca88b7bce55385b41203284196923d09250f2ea3 100644 --- a/tools/include/uapi/linux/fcntl.h +++ b/tools/include/uapi/linux/fcntl.h @@ -3,6 +3,7 @@ #define _UAPI_LINUX_FCNTL_H #include +#include #define F_SETLEASE (F_LINUX_SPECIFIC_BASE + 0) #define F_GETLEASE (F_LINUX_SPECIFIC_BASE + 1) @@ -100,5 +101,4 @@ #define AT_RECURSIVE 0x8000 /* Apply to the entire subtree */ - #endif /* _UAPI_LINUX_FCNTL_H */ diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h index 1beb174ad9505634151c5ac2896ae63bcced028e..0d8a6f47711c32eef4701ad9d9d6936f3a01d9c9 100644 --- a/tools/include/uapi/linux/fscrypt.h +++ b/tools/include/uapi/linux/fscrypt.h @@ -8,6 +8,7 @@ #ifndef _UAPI_LINUX_FSCRYPT_H #define _UAPI_LINUX_FSCRYPT_H +#include #include /* Encryption policy flags */ @@ -109,11 +110,22 @@ struct fscrypt_key_specifier { } u; }; +/* + * Payload of Linux keyring key of type "fscrypt-provisioning", referenced by + * fscrypt_add_key_arg::key_id as an alternative to fscrypt_add_key_arg::raw. + */ +struct fscrypt_provisioning_key_payload { + __u32 type; + __u32 __reserved; + __u8 raw[]; +}; + /* Struct passed to FS_IOC_ADD_ENCRYPTION_KEY */ struct fscrypt_add_key_arg { struct fscrypt_key_specifier key_spec; __u32 raw_size; - __u32 __reserved[9]; + __u32 key_id; + __u32 __reserved[8]; __u8 raw[]; }; diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index f0a16b4adbbd63c421006f6ca9b0fd9a892f7a5d..4b95f9a31a2f5e227f57f4cbba907c0508c5e3a9 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -1009,6 +1009,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_PPC_GUEST_DEBUG_SSTEP 176 #define KVM_CAP_ARM_NISV_TO_USER 177 #define KVM_CAP_ARM_INJECT_EXT_DABT 178 +#define KVM_CAP_S390_VCPU_RESETS 179 #ifdef KVM_CAP_IRQ_ROUTING @@ -1473,6 +1474,10 @@ struct kvm_enc_region { /* Available with KVM_CAP_ARM_SVE */ #define KVM_ARM_VCPU_FINALIZE _IOW(KVMIO, 0xc2, int) +/* Available with KVM_CAP_S390_VCPU_RESETS */ +#define KVM_S390_NORMAL_RESET _IO(KVMIO, 0xc3) +#define KVM_S390_CLEAR_RESET _IO(KVMIO, 0xc4) + /* Secure Encrypted Virtualization command */ enum sev_cmd_id { /* Guest initialization commands */ diff --git a/tools/include/uapi/linux/openat2.h b/tools/include/uapi/linux/openat2.h new file mode 100644 index 0000000000000000000000000000000000000000..58b1eb71136007727e8535eaeb19e2ea4a00fb9a --- /dev/null +++ b/tools/include/uapi/linux/openat2.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_OPENAT2_H +#define _UAPI_LINUX_OPENAT2_H + +#include + +/* + * Arguments for how openat2(2) should open the target path. If only @flags and + * @mode are non-zero, then openat2(2) operates very similarly to openat(2). + * + * However, unlike openat(2), unknown or invalid bits in @flags result in + * -EINVAL rather than being silently ignored. @mode must be zero unless one of + * {O_CREAT, O_TMPFILE} are set. + * + * @flags: O_* flags. + * @mode: O_CREAT/O_TMPFILE file mode. + * @resolve: RESOLVE_* flags. + */ +struct open_how { + __u64 flags; + __u64 mode; + __u64 resolve; +}; + +/* how->resolve flags for openat2(2). */ +#define RESOLVE_NO_XDEV 0x01 /* Block mount-point crossings + (includes bind-mounts). */ +#define RESOLVE_NO_MAGICLINKS 0x02 /* Block traversal through procfs-style + "magic-links". */ +#define RESOLVE_NO_SYMLINKS 0x04 /* Block traversal through all symlinks + (implies OEXT_NO_MAGICLINKS) */ +#define RESOLVE_BENEATH 0x08 /* Block "lexical" trickery like + "..", symlinks, and absolute + paths which escape the dirfd. */ +#define RESOLVE_IN_ROOT 0x10 /* Make all jumps to "/" and ".." + be scoped inside the dirfd + (similar to chroot(2)). */ + +#endif /* _UAPI_LINUX_OPENAT2_H */ diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index 7da1b37b27aa5b75fb89b79f0d9f193e5021a911..07b4f8131e362bdc815f37cea0c9067a9464f256 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -234,4 +234,8 @@ struct prctl_mm_map { #define PR_GET_TAGGED_ADDR_CTRL 56 # define PR_TAGGED_ADDR_ENABLE (1UL << 0) +/* Control reclaim behavior when allocating memory */ +#define PR_SET_IO_FLUSHER 57 +#define PR_GET_IO_FLUSHER 58 + #endif /* _LINUX_PRCTL_H */ diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h index 4a02178324641f555336164316ba2e30805c3719..2e3bc22c6f202f6280ef7279de60fa966b84d3ed 100644 --- a/tools/include/uapi/linux/sched.h +++ b/tools/include/uapi/linux/sched.h @@ -36,6 +36,12 @@ /* Flags for the clone3() syscall. */ #define CLONE_CLEAR_SIGHAND 0x100000000ULL /* Clear any signal handler and reset to SIG_DFL. */ +/* + * cloning flags intersect with CSIGNAL so can be used with unshare and clone3 + * syscalls only: + */ +#define CLONE_NEWTIME 0x00000080 /* New time namespace */ + #ifndef __ASSEMBLY__ /** * struct clone_args - arguments for the clone3 syscall diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h index df1153cea0b7ee2a27e19682837f81922fef353e..535a7229e1d94a706dd8f91d9fdfdf0e0f66caa4 100644 --- a/tools/include/uapi/sound/asound.h +++ b/tools/include/uapi/sound/asound.h @@ -26,7 +26,9 @@ #if defined(__KERNEL__) || defined(__linux__) #include +#include #else +#include #include #endif @@ -154,7 +156,7 @@ struct snd_hwdep_dsp_image { * * *****************************************************************************/ -#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 14) +#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 15) typedef unsigned long snd_pcm_uframes_t; typedef signed long snd_pcm_sframes_t; @@ -301,7 +303,9 @@ typedef int __bitwise snd_pcm_subformat_t; #define SNDRV_PCM_INFO_DRAIN_TRIGGER 0x40000000 /* internal kernel flag - trigger in drain */ #define SNDRV_PCM_INFO_FIFO_IN_FRAMES 0x80000000 /* internal kernel flag - FIFO size is in frames */ - +#if (__BITS_PER_LONG == 32 && defined(__USE_TIME_BITS64)) || defined __KERNEL__ +#define __SND_STRUCT_TIME64 +#endif typedef int __bitwise snd_pcm_state_t; #define SNDRV_PCM_STATE_OPEN ((__force snd_pcm_state_t) 0) /* stream is open */ @@ -317,8 +321,17 @@ typedef int __bitwise snd_pcm_state_t; enum { SNDRV_PCM_MMAP_OFFSET_DATA = 0x00000000, - SNDRV_PCM_MMAP_OFFSET_STATUS = 0x80000000, - SNDRV_PCM_MMAP_OFFSET_CONTROL = 0x81000000, + SNDRV_PCM_MMAP_OFFSET_STATUS_OLD = 0x80000000, + SNDRV_PCM_MMAP_OFFSET_CONTROL_OLD = 0x81000000, + SNDRV_PCM_MMAP_OFFSET_STATUS_NEW = 0x82000000, + SNDRV_PCM_MMAP_OFFSET_CONTROL_NEW = 0x83000000, +#ifdef __SND_STRUCT_TIME64 + SNDRV_PCM_MMAP_OFFSET_STATUS = SNDRV_PCM_MMAP_OFFSET_STATUS_NEW, + SNDRV_PCM_MMAP_OFFSET_CONTROL = SNDRV_PCM_MMAP_OFFSET_CONTROL_NEW, +#else + SNDRV_PCM_MMAP_OFFSET_STATUS = SNDRV_PCM_MMAP_OFFSET_STATUS_OLD, + SNDRV_PCM_MMAP_OFFSET_CONTROL = SNDRV_PCM_MMAP_OFFSET_CONTROL_OLD, +#endif }; union snd_pcm_sync_id { @@ -456,8 +469,13 @@ enum { SNDRV_PCM_AUDIO_TSTAMP_TYPE_LAST = SNDRV_PCM_AUDIO_TSTAMP_TYPE_LINK_SYNCHRONIZED }; +#ifndef __KERNEL__ +/* explicit padding avoids incompatibility between i386 and x86-64 */ +typedef struct { unsigned char pad[sizeof(time_t) - sizeof(int)]; } __time_pad; + struct snd_pcm_status { snd_pcm_state_t state; /* stream state */ + __time_pad pad1; /* align to timespec */ struct timespec trigger_tstamp; /* time when stream was started/stopped/paused */ struct timespec tstamp; /* reference timestamp */ snd_pcm_uframes_t appl_ptr; /* appl ptr */ @@ -473,17 +491,48 @@ struct snd_pcm_status { __u32 audio_tstamp_accuracy; /* in ns units, only valid if indicated in audio_tstamp_data */ unsigned char reserved[52-2*sizeof(struct timespec)]; /* must be filled with zero */ }; +#endif + +/* + * For mmap operations, we need the 64-bit layout, both for compat mode, + * and for y2038 compatibility. For 64-bit applications, the two definitions + * are identical, so we keep the traditional version. + */ +#ifdef __SND_STRUCT_TIME64 +#define __snd_pcm_mmap_status64 snd_pcm_mmap_status +#define __snd_pcm_mmap_control64 snd_pcm_mmap_control +#define __snd_pcm_sync_ptr64 snd_pcm_sync_ptr +#ifdef __KERNEL__ +#define __snd_timespec64 __kernel_timespec +#else +#define __snd_timespec64 timespec +#endif +struct __snd_timespec { + __s32 tv_sec; + __s32 tv_nsec; +}; +#else +#define __snd_pcm_mmap_status snd_pcm_mmap_status +#define __snd_pcm_mmap_control snd_pcm_mmap_control +#define __snd_pcm_sync_ptr snd_pcm_sync_ptr +#define __snd_timespec timespec +struct __snd_timespec64 { + __s64 tv_sec; + __s64 tv_nsec; +}; -struct snd_pcm_mmap_status { +#endif + +struct __snd_pcm_mmap_status { snd_pcm_state_t state; /* RO: state - SNDRV_PCM_STATE_XXXX */ int pad1; /* Needed for 64 bit alignment */ snd_pcm_uframes_t hw_ptr; /* RO: hw ptr (0...boundary-1) */ - struct timespec tstamp; /* Timestamp */ + struct __snd_timespec tstamp; /* Timestamp */ snd_pcm_state_t suspended_state; /* RO: suspended stream state */ - struct timespec audio_tstamp; /* from sample counter or wall clock */ + struct __snd_timespec audio_tstamp; /* from sample counter or wall clock */ }; -struct snd_pcm_mmap_control { +struct __snd_pcm_mmap_control { snd_pcm_uframes_t appl_ptr; /* RW: appl ptr (0...boundary-1) */ snd_pcm_uframes_t avail_min; /* RW: min available frames for wakeup */ }; @@ -492,14 +541,59 @@ struct snd_pcm_mmap_control { #define SNDRV_PCM_SYNC_PTR_APPL (1<<1) /* get appl_ptr from driver (r/w op) */ #define SNDRV_PCM_SYNC_PTR_AVAIL_MIN (1<<2) /* get avail_min from driver */ -struct snd_pcm_sync_ptr { +struct __snd_pcm_sync_ptr { unsigned int flags; union { - struct snd_pcm_mmap_status status; + struct __snd_pcm_mmap_status status; + unsigned char reserved[64]; + } s; + union { + struct __snd_pcm_mmap_control control; + unsigned char reserved[64]; + } c; +}; + +#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __BIG_ENDIAN : defined(__BIG_ENDIAN) +typedef char __pad_before_uframe[sizeof(__u64) - sizeof(snd_pcm_uframes_t)]; +typedef char __pad_after_uframe[0]; +#endif + +#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN) +typedef char __pad_before_uframe[0]; +typedef char __pad_after_uframe[sizeof(__u64) - sizeof(snd_pcm_uframes_t)]; +#endif + +struct __snd_pcm_mmap_status64 { + snd_pcm_state_t state; /* RO: state - SNDRV_PCM_STATE_XXXX */ + __u32 pad1; /* Needed for 64 bit alignment */ + __pad_before_uframe __pad1; + snd_pcm_uframes_t hw_ptr; /* RO: hw ptr (0...boundary-1) */ + __pad_after_uframe __pad2; + struct __snd_timespec64 tstamp; /* Timestamp */ + snd_pcm_state_t suspended_state;/* RO: suspended stream state */ + __u32 pad3; /* Needed for 64 bit alignment */ + struct __snd_timespec64 audio_tstamp; /* sample counter or wall clock */ +}; + +struct __snd_pcm_mmap_control64 { + __pad_before_uframe __pad1; + snd_pcm_uframes_t appl_ptr; /* RW: appl ptr (0...boundary-1) */ + __pad_before_uframe __pad2; + + __pad_before_uframe __pad3; + snd_pcm_uframes_t avail_min; /* RW: min available frames for wakeup */ + __pad_after_uframe __pad4; +}; + +struct __snd_pcm_sync_ptr64 { + __u32 flags; + __u32 pad1; + union { + struct __snd_pcm_mmap_status64 status; unsigned char reserved[64]; } s; union { - struct snd_pcm_mmap_control control; + struct __snd_pcm_mmap_control64 control; unsigned char reserved[64]; } c; }; @@ -584,6 +678,8 @@ enum { #define SNDRV_PCM_IOCTL_STATUS _IOR('A', 0x20, struct snd_pcm_status) #define SNDRV_PCM_IOCTL_DELAY _IOR('A', 0x21, snd_pcm_sframes_t) #define SNDRV_PCM_IOCTL_HWSYNC _IO('A', 0x22) +#define __SNDRV_PCM_IOCTL_SYNC_PTR _IOWR('A', 0x23, struct __snd_pcm_sync_ptr) +#define __SNDRV_PCM_IOCTL_SYNC_PTR64 _IOWR('A', 0x23, struct __snd_pcm_sync_ptr64) #define SNDRV_PCM_IOCTL_SYNC_PTR _IOWR('A', 0x23, struct snd_pcm_sync_ptr) #define SNDRV_PCM_IOCTL_STATUS_EXT _IOWR('A', 0x24, struct snd_pcm_status) #define SNDRV_PCM_IOCTL_CHANNEL_INFO _IOR('A', 0x32, struct snd_pcm_channel_info) @@ -614,7 +710,7 @@ enum { * Raw MIDI section - /dev/snd/midi?? */ -#define SNDRV_RAWMIDI_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 0) +#define SNDRV_RAWMIDI_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 1) enum { SNDRV_RAWMIDI_STREAM_OUTPUT = 0, @@ -648,13 +744,16 @@ struct snd_rawmidi_params { unsigned char reserved[16]; /* reserved for future use */ }; +#ifndef __KERNEL__ struct snd_rawmidi_status { int stream; + __time_pad pad1; struct timespec tstamp; /* Timestamp */ size_t avail; /* available bytes */ size_t xruns; /* count of overruns since last status (in bytes) */ unsigned char reserved[16]; /* reserved for future use */ }; +#endif #define SNDRV_RAWMIDI_IOCTL_PVERSION _IOR('W', 0x00, int) #define SNDRV_RAWMIDI_IOCTL_INFO _IOR('W', 0x01, struct snd_rawmidi_info) @@ -667,7 +766,7 @@ struct snd_rawmidi_status { * Timer section - /dev/snd/timer */ -#define SNDRV_TIMER_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 6) +#define SNDRV_TIMER_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 7) enum { SNDRV_TIMER_CLASS_NONE = -1, @@ -761,6 +860,7 @@ struct snd_timer_params { unsigned char reserved[60]; /* reserved */ }; +#ifndef __KERNEL__ struct snd_timer_status { struct timespec tstamp; /* Timestamp - last update */ unsigned int resolution; /* current period resolution in ns */ @@ -769,10 +869,11 @@ struct snd_timer_status { unsigned int queue; /* used queue size */ unsigned char reserved[64]; /* reserved */ }; +#endif #define SNDRV_TIMER_IOCTL_PVERSION _IOR('T', 0x00, int) #define SNDRV_TIMER_IOCTL_NEXT_DEVICE _IOWR('T', 0x01, struct snd_timer_id) -#define SNDRV_TIMER_IOCTL_TREAD _IOW('T', 0x02, int) +#define SNDRV_TIMER_IOCTL_TREAD_OLD _IOW('T', 0x02, int) #define SNDRV_TIMER_IOCTL_GINFO _IOWR('T', 0x03, struct snd_timer_ginfo) #define SNDRV_TIMER_IOCTL_GPARAMS _IOW('T', 0x04, struct snd_timer_gparams) #define SNDRV_TIMER_IOCTL_GSTATUS _IOWR('T', 0x05, struct snd_timer_gstatus) @@ -785,6 +886,15 @@ struct snd_timer_status { #define SNDRV_TIMER_IOCTL_STOP _IO('T', 0xa1) #define SNDRV_TIMER_IOCTL_CONTINUE _IO('T', 0xa2) #define SNDRV_TIMER_IOCTL_PAUSE _IO('T', 0xa3) +#define SNDRV_TIMER_IOCTL_TREAD64 _IOW('T', 0xa4, int) + +#if __BITS_PER_LONG == 64 +#define SNDRV_TIMER_IOCTL_TREAD SNDRV_TIMER_IOCTL_TREAD_OLD +#else +#define SNDRV_TIMER_IOCTL_TREAD ((sizeof(__kernel_long_t) >= sizeof(time_t)) ? \ + SNDRV_TIMER_IOCTL_TREAD_OLD : \ + SNDRV_TIMER_IOCTL_TREAD64) +#endif struct snd_timer_read { unsigned int resolution; @@ -810,11 +920,15 @@ enum { SNDRV_TIMER_EVENT_MRESUME = SNDRV_TIMER_EVENT_RESUME + 10, }; +#ifndef __KERNEL__ struct snd_timer_tread { int event; + __time_pad pad1; struct timespec tstamp; unsigned int val; + __time_pad pad2; }; +#endif /**************************************************************************** * * @@ -822,7 +936,7 @@ struct snd_timer_tread { * * ****************************************************************************/ -#define SNDRV_CTL_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 7) +#define SNDRV_CTL_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 8) struct snd_ctl_card_info { int card; /* card number */ @@ -860,7 +974,7 @@ typedef int __bitwise snd_ctl_elem_iface_t; #define SNDRV_CTL_ELEM_ACCESS_WRITE (1<<1) #define SNDRV_CTL_ELEM_ACCESS_READWRITE (SNDRV_CTL_ELEM_ACCESS_READ|SNDRV_CTL_ELEM_ACCESS_WRITE) #define SNDRV_CTL_ELEM_ACCESS_VOLATILE (1<<2) /* control value may be changed without a notification */ -#define SNDRV_CTL_ELEM_ACCESS_TIMESTAMP (1<<3) /* when was control changed */ +// (1 << 3) is unused. #define SNDRV_CTL_ELEM_ACCESS_TLV_READ (1<<4) /* TLV read is possible */ #define SNDRV_CTL_ELEM_ACCESS_TLV_WRITE (1<<5) /* TLV write is possible */ #define SNDRV_CTL_ELEM_ACCESS_TLV_READWRITE (SNDRV_CTL_ELEM_ACCESS_TLV_READ|SNDRV_CTL_ELEM_ACCESS_TLV_WRITE) @@ -926,11 +1040,7 @@ struct snd_ctl_elem_info { } enumerated; unsigned char reserved[128]; } value; - union { - unsigned short d[4]; /* dimensions */ - unsigned short *d_ptr; /* indirect - obsoleted */ - } dimen; - unsigned char reserved[64-4*sizeof(unsigned short)]; + unsigned char reserved[64]; }; struct snd_ctl_elem_value { @@ -955,8 +1065,7 @@ struct snd_ctl_elem_value { } bytes; struct snd_aes_iec958 iec958; } value; /* RO */ - struct timespec tstamp; - unsigned char reserved[128-sizeof(struct timespec)]; + unsigned char reserved[128]; }; struct snd_ctl_tlv { diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 514b1a524abbc0ff49bfe25fa2244eb50b860e1c..7469c7dcc15e71fb82e0c8d0a1426cce7b7e2127 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include @@ -1283,7 +1284,7 @@ static size_t bpf_map_mmap_sz(const struct bpf_map *map) static char *internal_map_name(struct bpf_object *obj, enum libbpf_map_type type) { - char map_name[BPF_OBJ_NAME_LEN]; + char map_name[BPF_OBJ_NAME_LEN], *p; const char *sfx = libbpf_type_to_btf_name[type]; int sfx_len = max((size_t)7, strlen(sfx)); int pfx_len = min((size_t)BPF_OBJ_NAME_LEN - sfx_len - 1, @@ -1292,6 +1293,11 @@ static char *internal_map_name(struct bpf_object *obj, snprintf(map_name, sizeof(map_name), "%.*s%.*s", pfx_len, obj->name, sfx_len, libbpf_type_to_btf_name[type]); + /* sanitise map name to characters allowed by kernel */ + for (p = map_name; *p && p < map_name + sizeof(map_name); p++) + if (!isalnum(*p) && *p != '_' && *p != '.') + *p = '_'; + return strdup(map_name); } diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index c4dd23c4b47811e7c896fe90532bdc11ac2580b9..8ead55593984fd7022938442459addf565dd1d91 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -239,7 +239,6 @@ buildid.*:: set buildid.dir to /dev/null. The default is $HOME/.debug annotate.*:: - These options work only for TUI. These are in control of addresses, jump function, source code in lines of assembly code from a specific program. @@ -269,6 +268,8 @@ annotate.*:: │ mov (%rdi),%rdx │ return n; + This option works with tui, stdio2 browsers. + annotate.use_offset:: Basing on a first address of a loaded function, offset can be used. Instead of using original addresses of assembly code, @@ -287,6 +288,8 @@ annotate.*:: 368:│ mov 0x8(%r14),%rdi + This option works with tui, stdio2 browsers. + annotate.jump_arrows:: There can be jump instruction among assembly code. Depending on a boolean value of jump_arrows, @@ -306,6 +309,8 @@ annotate.*:: │1330: mov %r15,%r10 │1333: cmp %r15,%r14 + This option works with tui browser. + annotate.show_linenr:: When showing source code if this option is 'true', line numbers are printed as below. @@ -325,6 +330,8 @@ annotate.*:: │ array++; │ } + This option works with tui, stdio2 browsers. + annotate.show_nr_jumps:: Let's see a part of assembly code. @@ -335,6 +342,8 @@ annotate.*:: │1 1382: movb $0x1,-0x270(%rbp) + This option works with tui, stdio2 browsers. + annotate.show_total_period:: To compare two records on an instruction base, with this option provided, display total number of samples that belong to a line @@ -348,11 +357,30 @@ annotate.*:: 99.93 │ mov %eax,%eax + This option works with tui, stdio2, stdio browsers. + + annotate.show_nr_samples:: + By default perf annotate shows percentage of samples. This option + can be used to print absolute number of samples. Ex, when set as + false: + + Percent│ + 74.03 │ mov %fs:0x28,%rax + + When set as true: + + Samples│ + 6 │ mov %fs:0x28,%rax + + This option works with tui, stdio2, stdio browsers. + annotate.offset_level:: Default is '1', meaning just jump targets will have offsets show right beside the instruction. When set to '2' 'call' instructions will also have its offsets shown, 3 or higher will show offsets for all instructions. + This option works with tui, stdio2 browsers. + hist.*:: hist.percentage:: This option control the way to calculate overhead of filtered entries - @@ -490,6 +518,12 @@ top.*:: column by default. The default is 'true'. + top.call-graph:: + This is identical to 'call-graph.record-mode', except it is + applicable only for 'top' subcommand. This option ONLY setup + the unwind method. To enable 'perf top' to actually use it, + the command line option -g must be specified. + man.*:: man.viewer:: This option can assign a tool to view manual pages when 'help' @@ -517,6 +551,16 @@ record.*:: But if this option is 'no-cache', it will not update the build-id cache. 'skip' skips post-processing and does not update the cache. + record.call-graph:: + This is identical to 'call-graph.record-mode', except it is + applicable only for 'record' subcommand. This option ONLY setup + the unwind method. To enable 'perf record' to actually use it, + the command line option -g must be specified. + + record.aio:: + Use 'n' control blocks in asynchronous (Posix AIO) trace writing + mode ('n' default: 1, max: 4). + diff.*:: diff.order:: This option sets the number of columns to sort the result. @@ -566,6 +610,11 @@ trace.*:: "libbeauty", the default, to use the same argument beautifiers used in the strace-like sys_enter+sys_exit lines. +ftrace.*:: + ftrace.tracer:: + Can be used to select the default tracer. Possible values are + 'function' and 'function_graph'. + llvm.*:: llvm.clang-path:: Path to clang. If omit, search it from $PATH. @@ -610,6 +659,29 @@ scripts.*:: The script gets the same options passed as a full perf script, in particular -i perfdata file, --cpu, --tid +convert.*:: + + convert.queue-size:: + Limit the size of ordered_events queue, so we could control + allocation size of perf data files without proper finished + round events. + +intel-pt.*:: + + intel-pt.cache-divisor:: + + intel-pt.mispred-all:: + If set, Intel PT decoder will set the mispred flag on all + branches. + +auxtrace.*:: + + auxtrace.dumpdir:: + s390 only. The directory to save the auxiliary trace buffer + can be changed using this option. Ex, auxtrace.dumpdir=/tmp. + If the directory does not exist or has the wrong file type, + the current directory is used. + SEE ALSO -------- linkperf:perf[1] diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 2898cfdf8fe18f3640351329a920a2f04df35aca..941f814820b8c653930e03d690ac6647227ef552 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -858,21 +858,6 @@ static void cs_etm_recording_free(struct auxtrace_record *itr) free(ptr); } -static int cs_etm_read_finish(struct auxtrace_record *itr, int idx) -{ - struct cs_etm_recording *ptr = - container_of(itr, struct cs_etm_recording, itr); - struct evsel *evsel; - - evlist__for_each_entry(ptr->evlist, evsel) { - if (evsel->core.attr.type == ptr->cs_etm_pmu->type) - return perf_evlist__enable_event_idx(ptr->evlist, - evsel, idx); - } - - return -EINVAL; -} - struct auxtrace_record *cs_etm_record_init(int *err) { struct perf_pmu *cs_etm_pmu; @@ -892,6 +877,7 @@ struct auxtrace_record *cs_etm_record_init(int *err) } ptr->cs_etm_pmu = cs_etm_pmu; + ptr->itr.pmu = cs_etm_pmu; ptr->itr.parse_snapshot_options = cs_etm_parse_snapshot_options; ptr->itr.recording_options = cs_etm_recording_options; ptr->itr.info_priv_size = cs_etm_info_priv_size; @@ -901,7 +887,7 @@ struct auxtrace_record *cs_etm_record_init(int *err) ptr->itr.snapshot_finish = cs_etm_snapshot_finish; ptr->itr.reference = cs_etm_reference; ptr->itr.free = cs_etm_recording_free; - ptr->itr.read_finish = cs_etm_read_finish; + ptr->itr.read_finish = auxtrace_record__read_finish; *err = 0; return &ptr->itr; diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c index eba6541ec0f12ca8250c3c7d6e33aab1ecf89c1b..27653be244473b08701a917dad2ff72c871e1081 100644 --- a/tools/perf/arch/arm64/util/arm-spe.c +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -11,17 +11,17 @@ #include #include -#include "../../util/cpumap.h" -#include "../../util/event.h" -#include "../../util/evsel.h" -#include "../../util/evlist.h" -#include "../../util/session.h" +#include "../../../util/cpumap.h" +#include "../../../util/event.h" +#include "../../../util/evsel.h" +#include "../../../util/evlist.h" +#include "../../../util/session.h" #include // page_size -#include "../../util/pmu.h" -#include "../../util/debug.h" -#include "../../util/auxtrace.h" -#include "../../util/record.h" -#include "../../util/arm-spe.h" +#include "../../../util/pmu.h" +#include "../../../util/debug.h" +#include "../../../util/auxtrace.h" +#include "../../../util/record.h" +#include "../../../util/arm-spe.h" #define KiB(x) ((x) * 1024) #define MiB(x) ((x) * 1024 * 1024) @@ -158,20 +158,6 @@ static void arm_spe_recording_free(struct auxtrace_record *itr) free(sper); } -static int arm_spe_read_finish(struct auxtrace_record *itr, int idx) -{ - struct arm_spe_recording *sper = - container_of(itr, struct arm_spe_recording, itr); - struct evsel *evsel; - - evlist__for_each_entry(sper->evlist, evsel) { - if (evsel->core.attr.type == sper->arm_spe_pmu->type) - return perf_evlist__enable_event_idx(sper->evlist, - evsel, idx); - } - return -EINVAL; -} - struct auxtrace_record *arm_spe_recording_init(int *err, struct perf_pmu *arm_spe_pmu) { @@ -189,12 +175,13 @@ struct auxtrace_record *arm_spe_recording_init(int *err, } sper->arm_spe_pmu = arm_spe_pmu; + sper->itr.pmu = arm_spe_pmu; sper->itr.recording_options = arm_spe_recording_options; sper->itr.info_priv_size = arm_spe_info_priv_size; sper->itr.info_fill = arm_spe_info_fill; sper->itr.free = arm_spe_recording_free; sper->itr.reference = arm_spe_reference; - sper->itr.read_finish = arm_spe_read_finish; + sper->itr.read_finish = auxtrace_record__read_finish; sper->itr.alignment = 0; *err = 0; diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c index a32e4b72a98f0f615fa6cc237e681e2ee0776441..d730666ab95d21c4d2b834776d552980e9c6fa27 100644 --- a/tools/perf/arch/arm64/util/header.c +++ b/tools/perf/arch/arm64/util/header.c @@ -1,8 +1,10 @@ #include #include #include +#include #include #include +#include #include "debug.h" #include "header.h" @@ -12,26 +14,21 @@ #define MIDR_VARIANT_SHIFT 20 #define MIDR_VARIANT_MASK (0xf << MIDR_VARIANT_SHIFT) -char *get_cpuid_str(struct perf_pmu *pmu) +static int _get_cpuid(char *buf, size_t sz, struct perf_cpu_map *cpus) { - char *buf = NULL; - char path[PATH_MAX]; const char *sysfs = sysfs__mountpoint(); - int cpu; u64 midr = 0; - struct perf_cpu_map *cpus; - FILE *file; + int cpu; - if (!sysfs || !pmu || !pmu->cpus) - return NULL; + if (!sysfs || sz < MIDR_SIZE) + return EINVAL; - buf = malloc(MIDR_SIZE); - if (!buf) - return NULL; + cpus = perf_cpu_map__get(cpus); - /* read midr from list of cpus mapped to this pmu */ - cpus = perf_cpu_map__get(pmu->cpus); for (cpu = 0; cpu < perf_cpu_map__nr(cpus); cpu++) { + char path[PATH_MAX]; + FILE *file; + scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d"MIDR, sysfs, cpus->map[cpu]); @@ -57,12 +54,48 @@ char *get_cpuid_str(struct perf_pmu *pmu) break; } - if (!midr) { + perf_cpu_map__put(cpus); + + if (!midr) + return EINVAL; + + return 0; +} + +int get_cpuid(char *buf, size_t sz) +{ + struct perf_cpu_map *cpus = perf_cpu_map__new(NULL); + int ret; + + if (!cpus) + return EINVAL; + + ret = _get_cpuid(buf, sz, cpus); + + perf_cpu_map__put(cpus); + + return ret; +} + +char *get_cpuid_str(struct perf_pmu *pmu) +{ + char *buf = NULL; + int res; + + if (!pmu || !pmu->cpus) + return NULL; + + buf = malloc(MIDR_SIZE); + if (!buf) + return NULL; + + /* read midr from list of cpus mapped to this pmu */ + res = _get_cpuid(buf, MIDR_SIZE, pmu->cpus); + if (res) { pr_err("failed to get cpuid string for PMU %s\n", pmu->name); free(buf); buf = NULL; } - perf_cpu_map__put(cpus); return buf; } diff --git a/tools/perf/arch/arm64/util/perf_regs.c b/tools/perf/arch/arm64/util/perf_regs.c index 2864e2e3776d5105d39f83f4de94d306df4a07ac..2833e101a7c6407263130e9948a06a2caa32bc4b 100644 --- a/tools/perf/arch/arm64/util/perf_regs.c +++ b/tools/perf/arch/arm64/util/perf_regs.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -#include "../../util/perf_regs.h" +#include "../../../util/perf_regs.h" const struct sample_reg sample_reg_masks[] = { SMPL_REG_END diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index 43f736ed47f28a1dff42ffb7ae7b3e19613e0211..35b61bfc1b1ae928158dee422a150c19c8d30e4e 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -517,3 +517,5 @@ 433 common fspick sys_fspick 434 common pidfd_open sys_pidfd_open 435 nospu clone3 ppc_clone3 +437 common openat2 sys_openat2 +438 common pidfd_getfd sys_pidfd_getfd diff --git a/tools/perf/arch/powerpc/util/perf_regs.c b/tools/perf/arch/powerpc/util/perf_regs.c index e9c436eeffc9d8f390eb564619283e49897c0adf..0a5242900248504530b760a60886d68cb1208df9 100644 --- a/tools/perf/arch/powerpc/util/perf_regs.c +++ b/tools/perf/arch/powerpc/util/perf_regs.c @@ -4,8 +4,8 @@ #include #include -#include "../../util/perf_regs.h" -#include "../../util/debug.h" +#include "../../../util/perf_regs.h" +#include "../../../util/debug.h" #include diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index c29976eca4a8a86bdd2fc062b3e521afc0338301..44d510bc9b7877a18c082ceb168f01e94db0417b 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -357,6 +357,8 @@ 433 common fspick __x64_sys_fspick 434 common pidfd_open __x64_sys_pidfd_open 435 common clone3 __x64_sys_clone3/ptregs +437 common openat2 __x64_sys_openat2 +438 common pidfd_getfd __x64_sys_pidfd_getfd # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/tools/perf/arch/x86/util/auxtrace.c b/tools/perf/arch/x86/util/auxtrace.c index 7abc9fd4cbec444032c5ddf3b1c6eae69b477ab6..3da506e13f49ddd002a0c6dc8dc4e6da9d61757a 100644 --- a/tools/perf/arch/x86/util/auxtrace.c +++ b/tools/perf/arch/x86/util/auxtrace.c @@ -7,13 +7,13 @@ #include #include -#include "../../util/header.h" -#include "../../util/debug.h" -#include "../../util/pmu.h" -#include "../../util/auxtrace.h" -#include "../../util/intel-pt.h" -#include "../../util/intel-bts.h" -#include "../../util/evlist.h" +#include "../../../util/header.h" +#include "../../../util/debug.h" +#include "../../../util/pmu.h" +#include "../../../util/auxtrace.h" +#include "../../../util/intel-pt.h" +#include "../../../util/intel-bts.h" +#include "../../../util/evlist.h" static struct auxtrace_record *auxtrace_record__init_intel(struct evlist *evlist, diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c index ac45015cc6bae1c5c89dd6035a0c6aaec6bd4dd0..047dc00eafa6ec099fda74e794ebcd378525ef2b 100644 --- a/tools/perf/arch/x86/util/event.c +++ b/tools/perf/arch/x86/util/event.c @@ -3,12 +3,12 @@ #include #include -#include "../../util/event.h" -#include "../../util/synthetic-events.h" -#include "../../util/machine.h" -#include "../../util/tool.h" -#include "../../util/map.h" -#include "../../util/debug.h" +#include "../../../util/event.h" +#include "../../../util/synthetic-events.h" +#include "../../../util/machine.h" +#include "../../../util/tool.h" +#include "../../../util/map.h" +#include "../../../util/debug.h" #if defined(__x86_64__) diff --git a/tools/perf/arch/x86/util/header.c b/tools/perf/arch/x86/util/header.c index aa6deb463bf3c7407fd47cde1edcd933c68c42ff..578c8c568ffd6f1210a421052fd2ad5ba5242879 100644 --- a/tools/perf/arch/x86/util/header.c +++ b/tools/perf/arch/x86/util/header.c @@ -7,8 +7,8 @@ #include #include -#include "../../util/debug.h" -#include "../../util/header.h" +#include "../../../util/debug.h" +#include "../../../util/header.h" static inline void cpuid(unsigned int op, unsigned int *a, unsigned int *b, unsigned int *c, diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c index 27d9e214d068074d37ff0e5287bfba047819ea56..09f93800bffd0cbdc5bddc6406fb7eebca7acc3c 100644 --- a/tools/perf/arch/x86/util/intel-bts.c +++ b/tools/perf/arch/x86/util/intel-bts.c @@ -11,18 +11,18 @@ #include #include -#include "../../util/cpumap.h" -#include "../../util/event.h" -#include "../../util/evsel.h" -#include "../../util/evlist.h" -#include "../../util/mmap.h" -#include "../../util/session.h" -#include "../../util/pmu.h" -#include "../../util/debug.h" -#include "../../util/record.h" -#include "../../util/tsc.h" -#include "../../util/auxtrace.h" -#include "../../util/intel-bts.h" +#include "../../../util/cpumap.h" +#include "../../../util/event.h" +#include "../../../util/evsel.h" +#include "../../../util/evlist.h" +#include "../../../util/mmap.h" +#include "../../../util/session.h" +#include "../../../util/pmu.h" +#include "../../../util/debug.h" +#include "../../../util/record.h" +#include "../../../util/tsc.h" +#include "../../../util/auxtrace.h" +#include "../../../util/intel-bts.h" #include // page_size #define KiB(x) ((x) * 1024) @@ -413,20 +413,6 @@ static int intel_bts_find_snapshot(struct auxtrace_record *itr, int idx, return err; } -static int intel_bts_read_finish(struct auxtrace_record *itr, int idx) -{ - struct intel_bts_recording *btsr = - container_of(itr, struct intel_bts_recording, itr); - struct evsel *evsel; - - evlist__for_each_entry(btsr->evlist, evsel) { - if (evsel->core.attr.type == btsr->intel_bts_pmu->type) - return perf_evlist__enable_event_idx(btsr->evlist, - evsel, idx); - } - return -EINVAL; -} - struct auxtrace_record *intel_bts_recording_init(int *err) { struct perf_pmu *intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME); @@ -447,6 +433,7 @@ struct auxtrace_record *intel_bts_recording_init(int *err) } btsr->intel_bts_pmu = intel_bts_pmu; + btsr->itr.pmu = intel_bts_pmu; btsr->itr.recording_options = intel_bts_recording_options; btsr->itr.info_priv_size = intel_bts_info_priv_size; btsr->itr.info_fill = intel_bts_info_fill; @@ -456,7 +443,7 @@ struct auxtrace_record *intel_bts_recording_init(int *err) btsr->itr.find_snapshot = intel_bts_find_snapshot; btsr->itr.parse_snapshot_options = intel_bts_parse_snapshot_options; btsr->itr.reference = intel_bts_reference; - btsr->itr.read_finish = intel_bts_read_finish; + btsr->itr.read_finish = auxtrace_record__read_finish; btsr->itr.alignment = sizeof(struct branch); return &btsr->itr; } diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index 20df442fdf36d930e603122bb19acbf578a93765..1643aed8c4c8ee319206916ad9f1ebfc772a7784 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -13,23 +13,23 @@ #include #include -#include "../../util/session.h" -#include "../../util/event.h" -#include "../../util/evlist.h" -#include "../../util/evsel.h" -#include "../../util/evsel_config.h" -#include "../../util/cpumap.h" -#include "../../util/mmap.h" +#include "../../../util/session.h" +#include "../../../util/event.h" +#include "../../../util/evlist.h" +#include "../../../util/evsel.h" +#include "../../../util/evsel_config.h" +#include "../../../util/cpumap.h" +#include "../../../util/mmap.h" #include -#include "../../util/parse-events.h" -#include "../../util/pmu.h" -#include "../../util/debug.h" -#include "../../util/auxtrace.h" -#include "../../util/record.h" -#include "../../util/target.h" -#include "../../util/tsc.h" +#include "../../../util/parse-events.h" +#include "../../../util/pmu.h" +#include "../../../util/debug.h" +#include "../../../util/auxtrace.h" +#include "../../../util/record.h" +#include "../../../util/target.h" +#include "../../../util/tsc.h" #include // page_size -#include "../../util/intel-pt.h" +#include "../../../util/intel-pt.h" #define KiB(x) ((x) * 1024) #define MiB(x) ((x) * 1024 * 1024) @@ -1166,20 +1166,6 @@ static u64 intel_pt_reference(struct auxtrace_record *itr __maybe_unused) return rdtsc(); } -static int intel_pt_read_finish(struct auxtrace_record *itr, int idx) -{ - struct intel_pt_recording *ptr = - container_of(itr, struct intel_pt_recording, itr); - struct evsel *evsel; - - evlist__for_each_entry(ptr->evlist, evsel) { - if (evsel->core.attr.type == ptr->intel_pt_pmu->type) - return perf_evlist__enable_event_idx(ptr->evlist, evsel, - idx); - } - return -EINVAL; -} - struct auxtrace_record *intel_pt_recording_init(int *err) { struct perf_pmu *intel_pt_pmu = perf_pmu__find(INTEL_PT_PMU_NAME); @@ -1200,6 +1186,7 @@ struct auxtrace_record *intel_pt_recording_init(int *err) } ptr->intel_pt_pmu = intel_pt_pmu; + ptr->itr.pmu = intel_pt_pmu; ptr->itr.recording_options = intel_pt_recording_options; ptr->itr.info_priv_size = intel_pt_info_priv_size; ptr->itr.info_fill = intel_pt_info_fill; @@ -1209,7 +1196,7 @@ struct auxtrace_record *intel_pt_recording_init(int *err) ptr->itr.find_snapshot = intel_pt_find_snapshot; ptr->itr.parse_snapshot_options = intel_pt_parse_snapshot_options; ptr->itr.reference = intel_pt_reference; - ptr->itr.read_finish = intel_pt_read_finish; + ptr->itr.read_finish = auxtrace_record__read_finish; /* * Decoding starts at a PSB packet. Minimum PSB period is 2K so 4K * should give at least 1 PSB per sample. diff --git a/tools/perf/arch/x86/util/machine.c b/tools/perf/arch/x86/util/machine.c index e17e080e76f49b1ed1bcf3415f473e2d1b21ebb1..31679c35d493e87d10af534fa1c5fc9732d8191d 100644 --- a/tools/perf/arch/x86/util/machine.c +++ b/tools/perf/arch/x86/util/machine.c @@ -5,9 +5,9 @@ #include #include // page_size -#include "../../util/machine.h" -#include "../../util/map.h" -#include "../../util/symbol.h" +#include "../../../util/machine.h" +#include "../../../util/map.h" +#include "../../../util/symbol.h" #include #include diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c index c218b83e063b52510697a41c047b328d1e17f36f..fca81b39b09f4f65a2f4d64d05264197e8893388 100644 --- a/tools/perf/arch/x86/util/perf_regs.c +++ b/tools/perf/arch/x86/util/perf_regs.c @@ -5,10 +5,10 @@ #include #include -#include "../../perf-sys.h" -#include "../../util/perf_regs.h" -#include "../../util/debug.h" -#include "../../util/event.h" +#include "../../../perf-sys.h" +#include "../../../util/perf_regs.h" +#include "../../../util/debug.h" +#include "../../../util/event.h" const struct sample_reg sample_reg_masks[] = { SMPL_REG(AX, PERF_REG_X86_AX), diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c index e33ef5bc31c57f08aa40ac682b4ca8931aba7751..d48d608517fd273212b0c8c0da310aa8075085a4 100644 --- a/tools/perf/arch/x86/util/pmu.c +++ b/tools/perf/arch/x86/util/pmu.c @@ -4,9 +4,9 @@ #include #include -#include "../../util/intel-pt.h" -#include "../../util/intel-bts.h" -#include "../../util/pmu.h" +#include "../../../util/intel-pt.h" +#include "../../../util/intel-bts.h" +#include "../../../util/pmu.h" struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused) { diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h index fddb3ced9db620f8700faa82494d80c5b2ee1c24..4aa6de1aa67dc6a7f095d135e95f8b406cc7f5c1 100644 --- a/tools/perf/bench/bench.h +++ b/tools/perf/bench/bench.h @@ -2,6 +2,10 @@ #ifndef BENCH_H #define BENCH_H +#include + +extern struct timeval bench__start, bench__end, bench__runtime; + /* * The madvise transparent hugepage constants were added in glibc * 2.13. For compatibility with older versions of glibc, define these diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c index bb617e56884129ce83bf4f7db4f79fb0c7f1a95a..cadc18d42aa4af3eab7b190f9a95b8c761d6ddf4 100644 --- a/tools/perf/bench/epoll-ctl.c +++ b/tools/perf/bench/epoll-ctl.c @@ -35,7 +35,6 @@ static unsigned int nthreads = 0; static unsigned int nsecs = 8; -struct timeval start, end, runtime; static bool done, __verbose, randomize; /* @@ -94,8 +93,8 @@ static void toggle_done(int sig __maybe_unused, { /* inform all threads that we're done for the day */ done = true; - gettimeofday(&end, NULL); - timersub(&end, &start, &runtime); + gettimeofday(&bench__end, NULL); + timersub(&bench__end, &bench__start, &bench__runtime); } static void nest_epollfd(void) @@ -313,6 +312,7 @@ int bench_epoll_ctl(int argc, const char **argv) exit(EXIT_FAILURE); } + memset(&act, 0, sizeof(act)); sigfillset(&act.sa_mask); act.sa_sigaction = toggle_done; sigaction(SIGINT, &act, NULL); @@ -361,7 +361,7 @@ int bench_epoll_ctl(int argc, const char **argv) threads_starting = nthreads; - gettimeofday(&start, NULL); + gettimeofday(&bench__start, NULL); do_threads(worker, cpu); diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c index 7af694437f4ead2adce1cb9079291bd2d134dfcc..f938c585d51248ddfc3277383098c05f5a8df60f 100644 --- a/tools/perf/bench/epoll-wait.c +++ b/tools/perf/bench/epoll-wait.c @@ -90,7 +90,6 @@ static unsigned int nthreads = 0; static unsigned int nsecs = 8; -struct timeval start, end, runtime; static bool wdone, done, __verbose, randomize, nonblocking; /* @@ -276,8 +275,8 @@ static void toggle_done(int sig __maybe_unused, { /* inform all threads that we're done for the day */ done = true; - gettimeofday(&end, NULL); - timersub(&end, &start, &runtime); + gettimeofday(&bench__end, NULL); + timersub(&bench__end, &bench__start, &bench__runtime); } static void print_summary(void) @@ -287,7 +286,7 @@ static void print_summary(void) printf("\nAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n", avg, rel_stddev_stats(stddev, avg), - (int) runtime.tv_sec); + (int)bench__runtime.tv_sec); } static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) @@ -427,6 +426,7 @@ int bench_epoll_wait(int argc, const char **argv) exit(EXIT_FAILURE); } + memset(&act, 0, sizeof(act)); sigfillset(&act.sa_mask); act.sa_sigaction = toggle_done; sigaction(SIGINT, &act, NULL); @@ -479,7 +479,7 @@ int bench_epoll_wait(int argc, const char **argv) threads_starting = nthreads; - gettimeofday(&start, NULL); + gettimeofday(&bench__start, NULL); do_threads(worker, cpu); @@ -519,7 +519,7 @@ int bench_epoll_wait(int argc, const char **argv) qsort(worker, nthreads, sizeof(struct worker), cmpworker); for (i = 0; i < nthreads; i++) { - unsigned long t = worker[i].ops/runtime.tv_sec; + unsigned long t = worker[i].ops / bench__runtime.tv_sec; update_stats(&throughput_stats, t); diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c index 8ba0c3330a9a2af7a3483d2ad13e85d71350e046..65eebe06c04d406b2fa11c5c43d443675af12b88 100644 --- a/tools/perf/bench/futex-hash.c +++ b/tools/perf/bench/futex-hash.c @@ -37,7 +37,7 @@ static unsigned int nfutexes = 1024; static bool fshared = false, done = false, silent = false; static int futex_flag = 0; -struct timeval start, end, runtime; +struct timeval bench__start, bench__end, bench__runtime; static pthread_mutex_t thread_lock; static unsigned int threads_starting; static struct stats throughput_stats; @@ -103,8 +103,8 @@ static void toggle_done(int sig __maybe_unused, { /* inform all threads that we're done for the day */ done = true; - gettimeofday(&end, NULL); - timersub(&end, &start, &runtime); + gettimeofday(&bench__end, NULL); + timersub(&bench__end, &bench__start, &bench__runtime); } static void print_summary(void) @@ -114,7 +114,7 @@ static void print_summary(void) printf("%sAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n", !silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg), - (int) runtime.tv_sec); + (int)bench__runtime.tv_sec); } int bench_futex_hash(int argc, const char **argv) @@ -137,6 +137,7 @@ int bench_futex_hash(int argc, const char **argv) if (!cpu) goto errmem; + memset(&act, 0, sizeof(act)); sigfillset(&act.sa_mask); act.sa_sigaction = toggle_done; sigaction(SIGINT, &act, NULL); @@ -161,7 +162,7 @@ int bench_futex_hash(int argc, const char **argv) threads_starting = nthreads; pthread_attr_init(&thread_attr); - gettimeofday(&start, NULL); + gettimeofday(&bench__start, NULL); for (i = 0; i < nthreads; i++) { worker[i].tid = i; worker[i].futex = calloc(nfutexes, sizeof(*worker[i].futex)); @@ -204,7 +205,7 @@ int bench_futex_hash(int argc, const char **argv) pthread_mutex_destroy(&thread_lock); for (i = 0; i < nthreads; i++) { - unsigned long t = worker[i].ops/runtime.tv_sec; + unsigned long t = worker[i].ops / bench__runtime.tv_sec; update_stats(&throughput_stats, t); if (!silent) { if (nfutexes == 1) diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c index d0cae8125423f69a76f2435c6c8ee01e926f69ea..89fd8f325f384eeac2f5e71c246b1e9aff2f28eb 100644 --- a/tools/perf/bench/futex-lock-pi.c +++ b/tools/perf/bench/futex-lock-pi.c @@ -37,7 +37,6 @@ static bool silent = false, multi = false; static bool done = false, fshared = false; static unsigned int nthreads = 0; static int futex_flag = 0; -struct timeval start, end, runtime; static pthread_mutex_t thread_lock; static unsigned int threads_starting; static struct stats throughput_stats; @@ -64,7 +63,7 @@ static void print_summary(void) printf("%sAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n", !silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg), - (int) runtime.tv_sec); + (int)bench__runtime.tv_sec); } static void toggle_done(int sig __maybe_unused, @@ -73,8 +72,8 @@ static void toggle_done(int sig __maybe_unused, { /* inform all threads that we're done for the day */ done = true; - gettimeofday(&end, NULL); - timersub(&end, &start, &runtime); + gettimeofday(&bench__end, NULL); + timersub(&bench__end, &bench__start, &bench__runtime); } static void *workerfn(void *arg) @@ -161,6 +160,7 @@ int bench_futex_lock_pi(int argc, const char **argv) if (!cpu) err(EXIT_FAILURE, "calloc"); + memset(&act, 0, sizeof(act)); sigfillset(&act.sa_mask); act.sa_sigaction = toggle_done; sigaction(SIGINT, &act, NULL); @@ -185,7 +185,7 @@ int bench_futex_lock_pi(int argc, const char **argv) threads_starting = nthreads; pthread_attr_init(&thread_attr); - gettimeofday(&start, NULL); + gettimeofday(&bench__start, NULL); create_threads(worker, thread_attr, cpu); pthread_attr_destroy(&thread_attr); @@ -211,7 +211,7 @@ int bench_futex_lock_pi(int argc, const char **argv) pthread_mutex_destroy(&thread_lock); for (i = 0; i < nthreads; i++) { - unsigned long t = worker[i].ops/runtime.tv_sec; + unsigned long t = worker[i].ops / bench__runtime.tv_sec; update_stats(&throughput_stats, t); if (!silent) diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c index a00a6891447ab3dcf3595f82b5526c6cea64ee7c..7a15c2e610228f081d8a3e5b8da2e5e283a8a427 100644 --- a/tools/perf/bench/futex-requeue.c +++ b/tools/perf/bench/futex-requeue.c @@ -128,6 +128,7 @@ int bench_futex_requeue(int argc, const char **argv) if (!cpu) err(EXIT_FAILURE, "cpu_map__new"); + memset(&act, 0, sizeof(act)); sigfillset(&act.sa_mask); act.sa_sigaction = toggle_done; sigaction(SIGINT, &act, NULL); diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c index a053cf2b703974353ce0456e5c1e2a3a5b454259..cd2b81a845acb0537f8841fb914b006c69c17772 100644 --- a/tools/perf/bench/futex-wake-parallel.c +++ b/tools/perf/bench/futex-wake-parallel.c @@ -234,6 +234,7 @@ int bench_futex_wake_parallel(int argc, const char **argv) exit(EXIT_FAILURE); } + memset(&act, 0, sizeof(act)); sigfillset(&act.sa_mask); act.sa_sigaction = toggle_done; sigaction(SIGINT, &act, NULL); diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c index df810096abfef9f9173818f8eaa052f3769d9a35..2dfcef3e371e4b15b9dead17bfa348b00e2a79d1 100644 --- a/tools/perf/bench/futex-wake.c +++ b/tools/perf/bench/futex-wake.c @@ -43,7 +43,7 @@ static bool done = false, silent = false, fshared = false; static pthread_mutex_t thread_lock; static pthread_cond_t thread_parent, thread_worker; static struct stats waketime_stats, wakeup_stats; -static unsigned int ncpus, threads_starting, nthreads = 0; +static unsigned int threads_starting, nthreads = 0; static int futex_flag = 0; static const struct option options[] = { @@ -136,12 +136,13 @@ int bench_futex_wake(int argc, const char **argv) if (!cpu) err(EXIT_FAILURE, "calloc"); + memset(&act, 0, sizeof(act)); sigfillset(&act.sa_mask); act.sa_sigaction = toggle_done; sigaction(SIGINT, &act, NULL); if (!nthreads) - nthreads = ncpus; + nthreads = cpu->nr; worker = calloc(nthreads, sizeof(*worker)); if (!worker) diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index ff61795a4d13783011cd25682e4894b61da21643..6c0a0412502ebb5e731156f47fcf87ccb2b9b55b 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -566,6 +566,8 @@ int cmd_annotate(int argc, const char **argv) if (ret < 0) return ret; + annotation_config__init(&annotate.opts); + argc = parse_options(argc, argv, options, annotate_usage, 0); if (argc) { /* @@ -605,8 +607,6 @@ int cmd_annotate(int argc, const char **argv) if (ret < 0) goto out_delete; - annotation_config__init(); - symbol_conf.try_vmlinux_path = true; ret = symbol__init(&annotate.session->header.env); diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index f8b6ae557d8bd7b7750a8fccf53ae338059ef91e..c03c36fde7e2f3a0d31146c948a38268560227f9 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -1312,7 +1312,8 @@ static int cycles_printf(struct hist_entry *he, struct hist_entry *pair, end_line = map__srcline(he->ms.map, bi->sym->start + bi->end, he->ms.sym); - if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) { + if ((strncmp(start_line, SRCLINE_UNKNOWN, strlen(SRCLINE_UNKNOWN)) != 0) && + (strncmp(end_line, SRCLINE_UNKNOWN, strlen(SRCLINE_UNKNOWN)) != 0)) { scnprintf(buf, sizeof(buf), "[%s -> %s] %4ld", start_line, end_line, block_he->diff.cycles); } else { diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index 26bc5923e6b56c0a3959212de58de8b36a8832e8..70548df2abb92f797721684e9a687a5b0fdacbf3 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -449,7 +449,8 @@ static int perf_del_probe_events(struct strfilter *filter) ret = probe_file__del_strlist(kfd, klist); if (ret < 0) goto error; - } + } else if (ret == -ENOMEM) + goto error; ret2 = probe_file__get_events(ufd, filter, ulist); if (ret2 == 0) { @@ -459,7 +460,8 @@ static int perf_del_probe_events(struct strfilter *filter) ret2 = probe_file__del_strlist(ufd, ulist); if (ret2 < 0) goto error; - } + } else if (ret2 == -ENOMEM) + goto error; if (ret == -ENOENT && ret2 == -ENOENT) pr_warning("\"%s\" does not hit any event.\n", str); diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 9483b3f0cae3f50004d0a6ea9e4ede717d185627..72a12b69f120b959b0d20e6441eb7197e8852f32 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -1507,7 +1507,7 @@ int cmd_report(int argc, const char **argv) symbol_conf.priv_size += sizeof(u32); symbol_conf.sort_by_name = true; } - annotation_config__init(); + annotation_config__init(&report.annotation_opts); } if (symbol__init(&session->header.env) < 0) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 8affcab756043dc4c31c43ccc43443446afaf37a..d2539b793f9d4fb8ae7299f0183217529d5525d9 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -143,7 +143,7 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he) return err; } - err = symbol__annotate(&he->ms, evsel, 0, &top->annotation_opts, NULL); + err = symbol__annotate(&he->ms, evsel, &top->annotation_opts, NULL); if (err == 0) { top->sym_filter_entry = he; } else { @@ -684,7 +684,9 @@ static void *display_thread(void *arg) delay_msecs = top->delay_secs * MSEC_PER_SEC; set_term_quiet_input(&save); /* trash return*/ - getc(stdin); + clearerr(stdin); + if (poll(&stdin_poll, 1, 0) > 0) + getc(stdin); while (!done) { perf_top__print_sym_table(top); @@ -1683,7 +1685,7 @@ int cmd_top(int argc, const char **argv) if (status < 0) goto out_delete_evlist; - annotation_config__init(); + annotation_config__init(&top.annotation_opts); symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL); status = symbol__init(NULL); diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 46a72ecac427f33a16d0d7d0ff7d713a306b8464..01d542007c8b1210b9fbf348bfb8ccafb849c645 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1065,7 +1065,9 @@ static struct syscall_fmt syscall_fmts[] = { { .name = "poll", .timeout = true, }, { .name = "ppoll", .timeout = true, }, { .name = "prctl", - .arg = { [0] = { .scnprintf = SCA_PRCTL_OPTION, /* option */ }, + .arg = { [0] = { .scnprintf = SCA_PRCTL_OPTION, /* option */ + .strtoul = STUL_STRARRAY, + .parm = &strarray__prctl_options, }, [1] = { .scnprintf = SCA_PRCTL_ARG2, /* arg2 */ }, [2] = { .scnprintf = SCA_PRCTL_ARG3, /* arg3 */ }, }, }, { .name = "pread", .alias = "pread64", }, diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 68039a96c1dcaa7a2b9c5f54882ce39b98c71b0e..bfb21d049e6ce1569c301ac8813c7b3488cd2244 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -13,6 +13,7 @@ include/uapi/linux/kcmp.h include/uapi/linux/kvm.h include/uapi/linux/in.h include/uapi/linux/mount.h +include/uapi/linux/openat2.h include/uapi/linux/perf_event.h include/uapi/linux/prctl.h include/uapi/linux/sched.h diff --git a/tools/perf/include/bpf/pid_filter.h b/tools/perf/include/bpf/pid_filter.h index 607189a315b2cbd32f36878d0fcdfb97b1001685..6e61c4bdf54826ce6538c98984f2751d6ddff755 100644 --- a/tools/perf/include/bpf/pid_filter.h +++ b/tools/perf/include/bpf/pid_filter.h @@ -3,7 +3,7 @@ #ifndef _PERF_BPF_PID_FILTER_ #define _PERF_BPF_PID_FILTER_ -#include +#include #define pid_filter(name) pid_map(name, bool) diff --git a/tools/perf/include/bpf/stdio.h b/tools/perf/include/bpf/stdio.h index 7ca6fa5463eea9faebb2dda6e561e98654da9692..316af5b2ff3516b3aba5365423c69e24f3f5dee5 100644 --- a/tools/perf/include/bpf/stdio.h +++ b/tools/perf/include/bpf/stdio.h @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 -#include +#include struct bpf_map SEC("maps") __bpf_stdout__ = { .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, diff --git a/tools/perf/include/bpf/unistd.h b/tools/perf/include/bpf/unistd.h index d1a35b6c649dc7b860ccb661f3e71ba0b595ce69..ca7877f9a976fbcaf55beb5196eedcc8eed9351b 100644 --- a/tools/perf/include/bpf/unistd.h +++ b/tools/perf/include/bpf/unistd.h @@ -1,6 +1,6 @@ // SPDX-License-Identifier: LGPL-2.1 -#include +#include static int (*bpf_get_current_pid_tgid)(void) = (void *)BPF_FUNC_get_current_pid_tgid; diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index 079c77b6a2fdfd236ca57fe424a6e04059291236..27b4da80f751177968848ff1656caaa5e91dfb1c 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -1082,10 +1082,9 @@ static int process_one_file(const char *fpath, const struct stat *sb, */ int main(int argc, char *argv[]) { - int rc; + int rc, ret = 0; int maxfds; char ldirname[PATH_MAX]; - const char *arch; const char *output_file; const char *start_dirname; @@ -1156,7 +1155,8 @@ int main(int argc, char *argv[]) /* Make build fail */ fclose(eventsfp); free_arch_std_events(); - return 1; + ret = 1; + goto out_free_mapfile; } else if (rc) { goto empty_map; } @@ -1174,14 +1174,17 @@ int main(int argc, char *argv[]) /* Make build fail */ fclose(eventsfp); free_arch_std_events(); - return 1; + ret = 1; } - return 0; + + goto out_free_mapfile; empty_map: fclose(eventsfp); create_empty_mapping(output_file); free_arch_std_events(); - return 0; +out_free_mapfile: + free(mapfile); + return ret; } diff --git a/tools/perf/tests/bp_account.c b/tools/perf/tests/bp_account.c index d0b935356274b2297970f28ca319dd9205602284..489b50604cf274046b879c54eb0e2a9037236ff8 100644 --- a/tools/perf/tests/bp_account.c +++ b/tools/perf/tests/bp_account.c @@ -19,7 +19,7 @@ #include "../perf-sys.h" #include "cloexec.h" -volatile long the_var; +static volatile long the_var; static noinline int test_function(void) { diff --git a/tools/perf/tests/shell/lib/probe_vfs_getname.sh b/tools/perf/tests/shell/lib/probe_vfs_getname.sh index 7cb99b433888b80d1b56b6331748b3db8414c0ca..c2cc42daf924235762a7528b89c858c7ebb9d062 100644 --- a/tools/perf/tests/shell/lib/probe_vfs_getname.sh +++ b/tools/perf/tests/shell/lib/probe_vfs_getname.sh @@ -14,7 +14,7 @@ add_probe_vfs_getname() { if [ $had_vfs_getname -eq 1 ] ; then line=$(perf probe -L getname_flags 2>&1 | egrep 'result.*=.*filename;' | sed -r 's/[[:space:]]+([[:digit:]]+)[[:space:]]+result->uptr.*/\1/') perf probe -q "vfs_getname=getname_flags:${line} pathname=result->name:string" || \ - perf probe $verbose "vfs_getname=getname_flags:${line} pathname=filename:string" + perf probe $verbose "vfs_getname=getname_flags:${line} pathname=filename:ustring" fi } diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h index 5a61043c2ff732e483ae57ad5ca40c5a86811b40..d6dfe68a7612552ab0eebb2022064c660737566a 100644 --- a/tools/perf/trace/beauty/beauty.h +++ b/tools/perf/trace/beauty/beauty.h @@ -213,6 +213,8 @@ size_t syscall_arg__scnprintf_x86_arch_prctl_code(char *bf, size_t size, struct size_t syscall_arg__scnprintf_prctl_option(char *bf, size_t size, struct syscall_arg *arg); #define SCA_PRCTL_OPTION syscall_arg__scnprintf_prctl_option +extern struct strarray strarray__prctl_options; + size_t syscall_arg__scnprintf_prctl_arg2(char *bf, size_t size, struct syscall_arg *arg); #define SCA_PRCTL_ARG2 syscall_arg__scnprintf_prctl_arg2 diff --git a/tools/perf/trace/beauty/prctl.c b/tools/perf/trace/beauty/prctl.c index ba2179abed00982e0f3fce9a7c66bc9780a083b3..6fe5ad5f5d3a4e4b8c043518215075874fe09892 100644 --- a/tools/perf/trace/beauty/prctl.c +++ b/tools/perf/trace/beauty/prctl.c @@ -11,9 +11,10 @@ #include "trace/beauty/generated/prctl_option_array.c" +DEFINE_STRARRAY(prctl_options, "PR_"); + static size_t prctl__scnprintf_option(int option, char *bf, size_t size, bool show_prefix) { - static DEFINE_STRARRAY(prctl_options, "PR_"); return strarray__scnprintf(&strarray__prctl_options, bf, size, "%d", show_prefix, option); } diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index badbddbb30f813b997bc43d8ce5744a55674dce9..9023267e564335ce9005288e35e60a9a86703b71 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -754,10 +754,9 @@ static int annotate_browser__run(struct annotate_browser *browser, "? Search string backwards\n"); continue; case 'r': - { - script_browse(NULL, NULL); - continue; - } + script_browse(NULL, NULL); + annotate_browser__show(&browser->b, title, help); + continue; case 'k': notes->options->show_linenr = !notes->options->show_linenr; break; @@ -834,13 +833,13 @@ static int annotate_browser__run(struct annotate_browser *browser, map_symbol__annotation_dump(ms, evsel, browser->opts); continue; case 't': - if (notes->options->show_total_period) { - notes->options->show_total_period = false; - notes->options->show_nr_samples = true; - } else if (notes->options->show_nr_samples) - notes->options->show_nr_samples = false; + if (symbol_conf.show_total_period) { + symbol_conf.show_total_period = false; + symbol_conf.show_nr_samples = true; + } else if (symbol_conf.show_nr_samples) + symbol_conf.show_nr_samples = false; else - notes->options->show_total_period = true; + symbol_conf.show_total_period = true; annotation__update_column_widths(notes); continue; case 'c': diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c index 22cc240f73713852342d75ea96249eeea2a339db..35f9641bf670cb5bc9103efffa8f060e9d8d4627 100644 --- a/tools/perf/ui/gtk/annotate.c +++ b/tools/perf/ui/gtk/annotate.c @@ -174,7 +174,7 @@ static int symbol__gtk_annotate(struct map_symbol *ms, struct evsel *evsel, if (ms->map->dso->annotate_warned) return -1; - err = symbol__annotate(ms, evsel, 0, &annotation__default_options, NULL); + err = symbol__annotate(ms, evsel, &annotation__default_options, NULL); if (err) { char msg[BUFSIZ]; symbol__strerror_disassemble(ms, err, msg, sizeof(msg)); diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index ca73fb74ad03273464abe6bb86455140495542ca..0ea95be84b3bd32d488491dd5f2272623d928085 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1143,93 +1143,70 @@ static int disasm_line__parse(char *line, const char **namep, char **rawp) } struct annotate_args { - size_t privsize; - struct arch *arch; - struct map_symbol ms; - struct evsel *evsel; + struct arch *arch; + struct map_symbol ms; + struct evsel *evsel; struct annotation_options *options; - s64 offset; - char *line; - int line_nr; + s64 offset; + char *line; + int line_nr; }; -static void annotation_line__delete(struct annotation_line *al) +static void annotation_line__init(struct annotation_line *al, + struct annotate_args *args, + int nr) { - void *ptr = (void *) al - al->privsize; + al->offset = args->offset; + al->line = strdup(args->line); + al->line_nr = args->line_nr; + al->data_nr = nr; +} +static void annotation_line__exit(struct annotation_line *al) +{ free_srcline(al->path); zfree(&al->line); - free(ptr); } -/* - * Allocating the annotation line data with following - * structure: - * - * -------------------------------------- - * private space | struct annotation_line - * -------------------------------------- - * - * Size of the private space is stored in 'struct annotation_line'. - * - */ -static struct annotation_line * -annotation_line__new(struct annotate_args *args, size_t privsize) +static size_t disasm_line_size(int nr) { struct annotation_line *al; - struct evsel *evsel = args->evsel; - size_t size = privsize + sizeof(*al); - int nr = 1; - - if (perf_evsel__is_group_event(evsel)) - nr = evsel->core.nr_members; - size += sizeof(al->data[0]) * nr; - - al = zalloc(size); - if (al) { - al = (void *) al + privsize; - al->privsize = privsize; - al->offset = args->offset; - al->line = strdup(args->line); - al->line_nr = args->line_nr; - al->data_nr = nr; - } - - return al; + return (sizeof(struct disasm_line) + (sizeof(al->data[0]) * nr)); } /* * Allocating the disasm annotation line data with * following structure: * - * ------------------------------------------------------------ - * privsize space | struct disasm_line | struct annotation_line - * ------------------------------------------------------------ + * ------------------------------------------- + * struct disasm_line | struct annotation_line + * ------------------------------------------- * * We have 'struct annotation_line' member as last member * of 'struct disasm_line' to have an easy access. - * */ static struct disasm_line *disasm_line__new(struct annotate_args *args) { struct disasm_line *dl = NULL; - struct annotation_line *al; - size_t privsize = args->privsize + offsetof(struct disasm_line, al); + int nr = 1; - al = annotation_line__new(args, privsize); - if (al != NULL) { - dl = disasm_line(al); + if (perf_evsel__is_group_event(args->evsel)) + nr = args->evsel->core.nr_members; - if (dl->al.line == NULL) - goto out_delete; + dl = zalloc(disasm_line_size(nr)); + if (!dl) + return NULL; - if (args->offset != -1) { - if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0) - goto out_free_line; + annotation_line__init(&dl->al, args, nr); + if (dl->al.line == NULL) + goto out_delete; - disasm_line__init_ins(dl, args->arch, &args->ms); - } + if (args->offset != -1) { + if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0) + goto out_free_line; + + disasm_line__init_ins(dl, args->arch, &args->ms); } return dl; @@ -1248,7 +1225,8 @@ void disasm_line__free(struct disasm_line *dl) else ins__delete(&dl->ops); zfree(&dl->ins.name); - annotation_line__delete(&dl->al); + annotation_line__exit(&dl->al); + free(dl); } int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw, int max_ins_name) @@ -2149,13 +2127,12 @@ void symbol__calc_percent(struct symbol *sym, struct evsel *evsel) annotation__calc_percent(notes, evsel, symbol__size(sym)); } -int symbol__annotate(struct map_symbol *ms, struct evsel *evsel, size_t privsize, +int symbol__annotate(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *options, struct arch **parch) { struct symbol *sym = ms->sym; struct annotation *notes = symbol__annotation(sym); struct annotate_args args = { - .privsize = privsize, .evsel = evsel, .options = options, }; @@ -2644,6 +2621,8 @@ void annotation__set_offsets(struct annotation *notes, s64 size) struct annotation_line *al; notes->max_line_len = 0; + notes->nr_entries = 0; + notes->nr_asm_entries = 0; list_for_each_entry(al, ¬es->src->source, node) { size_t line_len = strlen(al->line); @@ -2790,7 +2769,7 @@ int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel, struct symbol *sym = ms->sym; struct rb_root source_line = RB_ROOT; - if (symbol__annotate(ms, evsel, 0, opts, NULL) < 0) + if (symbol__annotate(ms, evsel, opts, NULL) < 0) return -1; symbol__calc_percent(sym, evsel); @@ -2915,9 +2894,9 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati percent = annotation_data__percent(&al->data[i], percent_type); obj__set_percent_color(obj, percent, current_entry); - if (notes->options->show_total_period) { + if (symbol_conf.show_total_period) { obj__printf(obj, "%11" PRIu64 " ", al->data[i].he.period); - } else if (notes->options->show_nr_samples) { + } else if (symbol_conf.show_nr_samples) { obj__printf(obj, "%6" PRIu64 " ", al->data[i].he.nr_samples); } else { @@ -2931,8 +2910,8 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati obj__printf(obj, "%-*s", pcnt_width, " "); else { obj__printf(obj, "%-*s", pcnt_width, - notes->options->show_total_period ? "Period" : - notes->options->show_nr_samples ? "Samples" : "Percent"); + symbol_conf.show_total_period ? "Period" : + symbol_conf.show_nr_samples ? "Samples" : "Percent"); } } @@ -3070,7 +3049,7 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel, if (perf_evsel__is_group_event(evsel)) nr_pcnt = evsel->core.nr_members; - err = symbol__annotate(ms, evsel, 0, options, parch); + err = symbol__annotate(ms, evsel, options, parch); if (err) goto out_free_offsets; @@ -3094,69 +3073,46 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel, return err; } -#define ANNOTATION__CFG(n) \ - { .name = #n, .value = &annotation__default_options.n, } - -/* - * Keep the entries sorted, they are bsearch'ed - */ -static struct annotation_config { - const char *name; - void *value; -} annotation__configs[] = { - ANNOTATION__CFG(hide_src_code), - ANNOTATION__CFG(jump_arrows), - ANNOTATION__CFG(offset_level), - ANNOTATION__CFG(show_linenr), - ANNOTATION__CFG(show_nr_jumps), - ANNOTATION__CFG(show_nr_samples), - ANNOTATION__CFG(show_total_period), - ANNOTATION__CFG(use_offset), -}; - -#undef ANNOTATION__CFG - -static int annotation_config__cmp(const void *name, const void *cfgp) -{ - const struct annotation_config *cfg = cfgp; - - return strcmp(name, cfg->name); -} - -static int annotation__config(const char *var, const char *value, - void *data __maybe_unused) +static int annotation__config(const char *var, const char *value, void *data) { - struct annotation_config *cfg; - const char *name; + struct annotation_options *opt = data; if (!strstarts(var, "annotate.")) return 0; - name = var + 9; - cfg = bsearch(name, annotation__configs, ARRAY_SIZE(annotation__configs), - sizeof(struct annotation_config), annotation_config__cmp); - - if (cfg == NULL) - pr_debug("%s variable unknown, ignoring...", var); - else if (strcmp(var, "annotate.offset_level") == 0) { - perf_config_int(cfg->value, name, value); - - if (*(int *)cfg->value > ANNOTATION__MAX_OFFSET_LEVEL) - *(int *)cfg->value = ANNOTATION__MAX_OFFSET_LEVEL; - else if (*(int *)cfg->value < ANNOTATION__MIN_OFFSET_LEVEL) - *(int *)cfg->value = ANNOTATION__MIN_OFFSET_LEVEL; + if (!strcmp(var, "annotate.offset_level")) { + perf_config_u8(&opt->offset_level, "offset_level", value); + + if (opt->offset_level > ANNOTATION__MAX_OFFSET_LEVEL) + opt->offset_level = ANNOTATION__MAX_OFFSET_LEVEL; + else if (opt->offset_level < ANNOTATION__MIN_OFFSET_LEVEL) + opt->offset_level = ANNOTATION__MIN_OFFSET_LEVEL; + } else if (!strcmp(var, "annotate.hide_src_code")) { + opt->hide_src_code = perf_config_bool("hide_src_code", value); + } else if (!strcmp(var, "annotate.jump_arrows")) { + opt->jump_arrows = perf_config_bool("jump_arrows", value); + } else if (!strcmp(var, "annotate.show_linenr")) { + opt->show_linenr = perf_config_bool("show_linenr", value); + } else if (!strcmp(var, "annotate.show_nr_jumps")) { + opt->show_nr_jumps = perf_config_bool("show_nr_jumps", value); + } else if (!strcmp(var, "annotate.show_nr_samples")) { + symbol_conf.show_nr_samples = perf_config_bool("show_nr_samples", + value); + } else if (!strcmp(var, "annotate.show_total_period")) { + symbol_conf.show_total_period = perf_config_bool("show_total_period", + value); + } else if (!strcmp(var, "annotate.use_offset")) { + opt->use_offset = perf_config_bool("use_offset", value); } else { - *(bool *)cfg->value = perf_config_bool(name, value); + pr_debug("%s variable unknown, ignoring...", var); } + return 0; } -void annotation_config__init(void) +void annotation_config__init(struct annotation_options *opt) { - perf_config(annotation__config, NULL); - - annotation__default_options.show_total_period = symbol_conf.show_total_period; - annotation__default_options.show_nr_samples = symbol_conf.show_nr_samples; + perf_config(annotation__config, opt); } static unsigned int parse_percent_type(char *str1, char *str2) diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 455403e8feded864661094b4c5fbb26fe8626492..001258601a371babdb13a1c47d1702a8e9e3e992 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -83,8 +83,6 @@ struct annotation_options { full_path, show_linenr, show_nr_jumps, - show_nr_samples, - show_total_period, show_minmax_cycle, show_asm_raw, annotate_src; @@ -141,7 +139,6 @@ struct annotation_line { u64 cycles; u64 cycles_max; u64 cycles_min; - size_t privsize; char *path; u32 idx; int idx_asm; @@ -309,7 +306,7 @@ static inline int annotation__cycles_width(struct annotation *notes) static inline int annotation__pcnt_width(struct annotation *notes) { - return (notes->options->show_total_period ? 12 : 7) * notes->nr_events; + return (symbol_conf.show_total_period ? 12 : 7) * notes->nr_events; } static inline bool annotation_line__filter(struct annotation_line *al, struct annotation *notes) @@ -352,7 +349,7 @@ struct annotated_source *symbol__hists(struct symbol *sym, int nr_hists); void symbol__annotate_zero_histograms(struct symbol *sym); int symbol__annotate(struct map_symbol *ms, - struct evsel *evsel, size_t privsize, + struct evsel *evsel, struct annotation_options *options, struct arch **parch); int symbol__annotate2(struct map_symbol *ms, @@ -413,7 +410,7 @@ static inline int symbol__tui_annotate(struct map_symbol *ms __maybe_unused, } #endif -void annotation_config__init(void); +void annotation_config__init(struct annotation_options *opt); int annotate_parse_percent_type(const struct option *opt, const char *_str, int unset); diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index eb087e7df6f4bc1c98398a9e98b12dfd64761f0e..3571ce72ca28e7e6ee68adcab72ef3398d88350d 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -629,8 +629,10 @@ int auxtrace_record__options(struct auxtrace_record *itr, struct evlist *evlist, struct record_opts *opts) { - if (itr) + if (itr) { + itr->evlist = evlist; return itr->recording_options(itr, evlist, opts); + } return 0; } @@ -664,6 +666,24 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr, return -EINVAL; } +int auxtrace_record__read_finish(struct auxtrace_record *itr, int idx) +{ + struct evsel *evsel; + + if (!itr->evlist || !itr->pmu) + return -EINVAL; + + evlist__for_each_entry(itr->evlist, evsel) { + if (evsel->core.attr.type == itr->pmu->type) { + if (evsel->disabled) + return 0; + return perf_evlist__enable_event_idx(itr->evlist, evsel, + idx); + } + } + return -EINVAL; +} + /* * Event record size is 16-bit which results in a maximum size of about 64KiB. * Allow about 4KiB for the rest of the sample record, to give a maximum diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index 749d72cd9c7b0eaaf6f82ea1fc63ee71d6ca8b50..e58ef160b59992602fd89c6c48260b3ceafd5890 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -29,6 +29,7 @@ struct record_opts; struct perf_record_auxtrace_error; struct perf_record_auxtrace_info; struct events_stats; +struct perf_pmu; enum auxtrace_error_type { PERF_AUXTRACE_ERROR_ITRACE = 1, @@ -322,6 +323,8 @@ struct auxtrace_mmap_params { * @read_finish: called after reading from an auxtrace mmap * @alignment: alignment (if any) for AUX area data * @default_aux_sample_size: default sample size for --aux sample option + * @pmu: associated pmu + * @evlist: selected events list */ struct auxtrace_record { int (*recording_options)(struct auxtrace_record *itr, @@ -346,6 +349,8 @@ struct auxtrace_record { int (*read_finish)(struct auxtrace_record *itr, int idx); unsigned int alignment; unsigned int default_aux_sample_size; + struct perf_pmu *pmu; + struct evlist *evlist; }; /** @@ -537,6 +542,7 @@ int auxtrace_record__find_snapshot(struct auxtrace_record *itr, int idx, struct auxtrace_mmap *mm, unsigned char *data, u64 *head, u64 *old); u64 auxtrace_record__reference(struct auxtrace_record *itr); +int auxtrace_record__read_finish(struct auxtrace_record *itr, int idx); int auxtrace_index__auxtrace_event(struct list_head *head, union perf_event *event, off_t file_offset); diff --git a/tools/perf/util/block-info.c b/tools/perf/util/block-info.c index c4b030bf6ec2d258da7fecac94d7154b859fb580..fbbb6d640dadcff16ad08083148fdfc9b4598e06 100644 --- a/tools/perf/util/block-info.c +++ b/tools/perf/util/block-info.c @@ -295,7 +295,8 @@ static int block_range_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, end_line = map__srcline(he->ms.map, bi->sym->start + bi->end, he->ms.sym); - if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) { + if ((strncmp(start_line, SRCLINE_UNKNOWN, strlen(SRCLINE_UNKNOWN)) != 0) && + (strncmp(end_line, SRCLINE_UNKNOWN, strlen(SRCLINE_UNKNOWN)) != 0)) { scnprintf(buf, sizeof(buf), "[%s -> %s]", start_line, end_line); } else { diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 0bc9c4d7fdc5d2239dc6c68dff690e9460d17a2e..ef38eba56ed0cb7629263c5132ec1bf0f7d8349f 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -374,6 +374,18 @@ int perf_config_int(int *dest, const char *name, const char *value) return 0; } +int perf_config_u8(u8 *dest, const char *name, const char *value) +{ + long ret = 0; + + if (!perf_parse_long(value, &ret)) { + bad_config(name); + return -1; + } + *dest = ret; + return 0; +} + static int perf_config_bool_or_int(const char *name, const char *value, int *is_bool) { int ret; diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h index bd0a5897c76a5daad5f68f6b561d1a744f029b76..c10b66dde2f35e407ce0b7a5431551c1cc40afdd 100644 --- a/tools/perf/util/config.h +++ b/tools/perf/util/config.h @@ -29,6 +29,7 @@ typedef int (*config_fn_t)(const char *, const char *, void *); int perf_default_config(const char *, const char *, void *); int perf_config(config_fn_t fn, void *); int perf_config_int(int *dest, const char *, const char *); +int perf_config_u8(u8 *dest, const char *name, const char *value); int perf_config_u64(u64 *dest, const char *, const char *); int perf_config_bool(const char *, const char *); int config_error_nonbool(const char *); diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 6242a9215df7ee325265646dd9ce71acbc0c73b8..4154f944f474a4152d4469c652a040db4b05a78a 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -343,11 +343,11 @@ static const char *normalize_arch(char *arch) const char *perf_env__arch(struct perf_env *env) { - struct utsname uts; char *arch_name; if (!env || !env->arch) { /* Assume local operation */ - if (uname(&uts) < 0) + static struct utsname uts = { .machine[0] = '\0', }; + if (uts.machine[0] == '\0' && uname(&uts) < 0) return NULL; arch_name = uts.machine; } else diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c index eae47c2509eb6fd6023855c816a1200723e97d56..b5af680fc667cc2ebbe5dc6447564cf90f15e7b7 100644 --- a/tools/perf/util/llvm-utils.c +++ b/tools/perf/util/llvm-utils.c @@ -288,6 +288,7 @@ static const char *kinc_fetch_script = "obj-y := dummy.o\n" "\\$(obj)/%.o: \\$(src)/%.c\n" "\t@echo -n \"\\$(NOSTDINC_FLAGS) \\$(LINUXINCLUDE) \\$(EXTRA_CFLAGS)\"\n" +"\t\\$(CC) -c -o \\$@ \\$<\n" "EOF\n" "touch $TMPDIR/dummy.c\n" "make -s -C $KBUILD_DIR M=$TMPDIR $KBUILD_OPTS dummy.o 2>/dev/null\n" diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index c8c5410315e817c2b9533eb8df718dc1bf98915f..fb5c2cd44d3003ac1c0dc1621d8cbb718ab1bdd0 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -686,6 +686,7 @@ static struct dso *machine__findnew_module_dso(struct machine *machine, dso__set_module_info(dso, m, machine); dso__set_long_name(dso, strdup(filename), true); + dso->kernel = DSO_TYPE_KERNEL; } dso__get(dso); @@ -726,9 +727,17 @@ static int machine__process_ksymbol_register(struct machine *machine, struct map *map = maps__find(&machine->kmaps, event->ksymbol.addr); if (!map) { - map = dso__new_map(event->ksymbol.name); - if (!map) + struct dso *dso = dso__new(event->ksymbol.name); + + if (dso) { + dso->kernel = DSO_TYPE_KERNEL; + map = map__new2(0, dso); + } + + if (!dso || !map) { + dso__put(dso); return -ENOMEM; + } map->start = event->ksymbol.addr; map->end = map->start + event->ksymbol.len; @@ -972,7 +981,6 @@ int machine__create_extra_kernel_map(struct machine *machine, kmap = map__kmap(map); - kmap->kmaps = &machine->kmaps; strlcpy(kmap->name, xm->name, KMAP_NAME_LEN); maps__insert(&machine->kmaps, map); @@ -1082,9 +1090,6 @@ int __weak machine__create_extra_kernel_maps(struct machine *machine __maybe_unu static int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel) { - struct kmap *kmap; - struct map *map; - /* In case of renewal the kernel map, destroy previous one */ machine__destroy_kernel_maps(machine); @@ -1093,14 +1098,7 @@ __machine__create_kernel_maps(struct machine *machine, struct dso *kernel) return -1; machine->vmlinux_map->map_ip = machine->vmlinux_map->unmap_ip = identity__map_ip; - map = machine__kernel_map(machine); - kmap = map__kmap(map); - if (!kmap) - return -1; - - kmap->kmaps = &machine->kmaps; - maps__insert(&machine->kmaps, map); - + maps__insert(&machine->kmaps, machine->vmlinux_map); return 0; } diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index f67960bedebba63663f573f28df9f746aa106910..95428511300d1e371c756846fbdfd3b415e94782 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -375,8 +375,13 @@ struct symbol *map__find_symbol_by_name(struct map *map, const char *name) struct map *map__clone(struct map *from) { - struct map *map = memdup(from, sizeof(*map)); + size_t size = sizeof(struct map); + struct map *map; + + if (from->dso && from->dso->kernel) + size += sizeof(struct kmap); + map = memdup(from, size); if (map != NULL) { refcount_set(&map->refcnt, 1); RB_CLEAR_NODE(&map->rb_node); @@ -426,7 +431,7 @@ int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix, if (map && map->dso) { char *srcline = map__srcline(map, addr, NULL); - if (srcline != SRCLINE_UNKNOWN) + if (strncmp(srcline, SRCLINE_UNKNOWN, strlen(SRCLINE_UNKNOWN)) != 0) ret = fprintf(fp, "%s%s", prefix, srcline); free_srcline(srcline); } @@ -538,6 +543,16 @@ void maps__insert(struct maps *maps, struct map *map) __maps__insert(maps, map); ++maps->nr_maps; + if (map->dso && map->dso->kernel) { + struct kmap *kmap = map__kmap(map); + + if (kmap) + kmap->kmaps = maps; + else + pr_err("Internal error: kernel dso with non kernel map\n"); + } + + /* * If we already performed some search by name, then we need to add the just * inserted map and resort. diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index c01ba6f8fdad3a3662662267d0941a7bd3b6db04..a14995835d85980f8ac86725ea9f197499d8b6d1 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -257,21 +257,15 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) path = zalloc(sizeof(*path)); if (!path) return NULL; - path->system = malloc(MAX_EVENT_LENGTH); - if (!path->system) { + if (asprintf(&path->system, "%.*s", MAX_EVENT_LENGTH, sys_dirent->d_name) < 0) { free(path); return NULL; } - path->name = malloc(MAX_EVENT_LENGTH); - if (!path->name) { + if (asprintf(&path->name, "%.*s", MAX_EVENT_LENGTH, evt_dirent->d_name) < 0) { zfree(&path->system); free(path); return NULL; } - strncpy(path->system, sys_dirent->d_name, - MAX_EVENT_LENGTH); - strncpy(path->name, evt_dirent->d_name, - MAX_EVENT_LENGTH); return path; } } diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index 5003ba4033454f813c420bdeafe44ad8b718751b..0f5fda11675fbd46256e5a46c8c61eb3a121f125 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -301,10 +301,15 @@ int probe_file__get_events(int fd, struct strfilter *filter, p = strchr(ent->s, ':'); if ((p && strfilter__compare(filter, p + 1)) || strfilter__compare(filter, ent->s)) { - strlist__add(plist, ent->s); + ret = strlist__add(plist, ent->s); + if (ret == -ENOMEM) { + pr_err("strlist__add failed with -ENOMEM\n"); + goto out; + } ret = 0; } } +out: strlist__delete(namelist); return ret; @@ -511,7 +516,11 @@ static int probe_cache__load(struct probe_cache *pcache) ret = -EINVAL; goto out; } - strlist__add(entry->tevlist, buf); + ret = strlist__add(entry->tevlist, buf); + if (ret == -ENOMEM) { + pr_err("strlist__add failed with -ENOMEM\n"); + goto out; + } } } out: @@ -672,7 +681,12 @@ int probe_cache__add_entry(struct probe_cache *pcache, command = synthesize_probe_trace_command(&tevs[i]); if (!command) goto out_err; - strlist__add(entry->tevlist, command); + ret = strlist__add(entry->tevlist, command); + if (ret == -ENOMEM) { + pr_err("strlist__add failed with -ENOMEM\n"); + goto out_err; + } + free(command); } list_add_tail(&entry->node, &pcache->entries); @@ -853,9 +867,15 @@ int probe_cache__scan_sdt(struct probe_cache *pcache, const char *pathname) break; } - strlist__add(entry->tevlist, buf); + ret = strlist__add(entry->tevlist, buf); + free(buf); entry = NULL; + + if (ret == -ENOMEM) { + pr_err("strlist__add failed with -ENOMEM\n"); + break; + } } if (entry) { list_del_init(&entry->node); diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 2c41d47f6f83e6b27d417bd690e0edc4b762961f..90d23cc3c8d492dd515d491166438742bd2b5a70 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -18,7 +18,6 @@ * AGGR_NONE: Use matching CPU * AGGR_THREAD: Not supported? */ -static bool have_frontend_stalled; struct runtime_stat rt_stat; struct stats walltime_nsecs_stats; @@ -144,7 +143,6 @@ void runtime_stat__exit(struct runtime_stat *st) void perf_stat__init_shadow_stats(void) { - have_frontend_stalled = pmu_have_event("cpu", "stalled-cycles-frontend"); runtime_stat__init(&rt_stat); } @@ -853,10 +851,6 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric(config, ctxp, NULL, "%7.2f ", "stalled cycles per insn", ratio); - } else if (have_frontend_stalled) { - out->new_line(config, ctxp); - print_metric(config, ctxp, NULL, "%7.2f ", - "stalled cycles per insn", 0); } } else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) { if (runtime_stat_n(st, STAT_BRANCHES, ctx, cpu) != 0) diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 3b379b1296f1077beb2e1242823eb15cbe4a6729..26bc6a0096ce568bd4e9e70fa910063f1633787b 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -635,9 +635,12 @@ int modules__parse(const char *filename, void *arg, static bool symbol__is_idle(const char *name) { const char * const idle_symbols[] = { + "acpi_idle_do_entry", + "acpi_processor_ffh_cstate_enter", "arch_cpu_idle", "cpu_idle", "cpu_startup_entry", + "idle_cpu", "intel_idle", "default_idle", "native_safe_halt", @@ -651,13 +654,17 @@ static bool symbol__is_idle(const char *name) NULL }; int i; + static struct strlist *idle_symbols_list; - for (i = 0; idle_symbols[i]; i++) { - if (!strcmp(idle_symbols[i], name)) - return true; - } + if (idle_symbols_list) + return strlist__has_entry(idle_symbols_list, name); - return false; + idle_symbols_list = strlist__new(NULL, NULL); + + for (i = 0; idle_symbols[i]; i++) + strlist__add(idle_symbols_list, idle_symbols[i]); + + return strlist__has_entry(idle_symbols_list, name); } static int map__process_kallsym_symbol(void *arg, const char *name, @@ -1615,7 +1622,12 @@ int dso__load(struct dso *dso, struct map *map) goto out; } - if (dso->kernel) { + kmod = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE || + dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP || + dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE || + dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP; + + if (dso->kernel && !kmod) { if (dso->kernel == DSO_TYPE_KERNEL) ret = dso__load_kernel_sym(dso, map); else if (dso->kernel == DSO_TYPE_GUEST_KERNEL) @@ -1643,12 +1655,6 @@ int dso__load(struct dso *dso, struct map *map) if (!name) goto out; - kmod = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE || - dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP || - dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE || - dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP; - - /* * Read the build id if possible. This is required for * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work diff --git a/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c b/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c index 33dc34db4f3cc62c956676466fbab7eb78f0f140..20f46348271b1b9dcdadfff8918150a5944de4d8 100644 --- a/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c +++ b/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c @@ -82,7 +82,7 @@ static struct pci_access *pci_acc; static struct pci_dev *amd_fam14h_pci_dev; static int nbp1_entered; -struct timespec start_time; +static struct timespec start_time; static unsigned long long timediff; #ifdef DEBUG diff --git a/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c b/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c index 3c4cee160b0e69a91f8bb8dbf5527ed32cd442fa..a65f7d011513a3f3d311790cf6b9c81aee99fb1d 100644 --- a/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c +++ b/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c @@ -19,7 +19,7 @@ struct cpuidle_monitor cpuidle_sysfs_monitor; static unsigned long long **previous_count; static unsigned long long **current_count; -struct timespec start_time; +static struct timespec start_time; static unsigned long long timediff; static int cpuidle_get_count_percent(unsigned int id, double *percent, diff --git a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c index 6d44fec55ad5ac230874fd7bc6d86d84be8800c9..7c77045fef52f1d20c2e1c71602cbd7da8dab168 100644 --- a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c +++ b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c @@ -27,6 +27,8 @@ struct cpuidle_monitor *all_monitors[] = { 0 }; +int cpu_count; + static struct cpuidle_monitor *monitors[MONITORS_MAX]; static unsigned int avail_monitors; diff --git a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h index 5b5eb1da0cce39257275cbe73d20581ae4e6926e..c559d3115330a41e4c31d22876175b4490c85413 100644 --- a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h +++ b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h @@ -25,7 +25,7 @@ #endif #define CSTATE_DESC_LEN 60 -int cpu_count; +extern int cpu_count; /* Hard to define the right names ...: */ enum power_range_e { diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile index 13f1e8b9ac525ddf44793541551acde4f8432e1c..2b6551269e431f0aa4e7688b81a585f7b470cdc4 100644 --- a/tools/power/x86/turbostat/Makefile +++ b/tools/power/x86/turbostat/Makefile @@ -16,7 +16,7 @@ override CFLAGS += -D_FORTIFY_SOURCE=2 %: %.c @mkdir -p $(BUILD_OUTPUT) - $(CC) $(CFLAGS) $< -o $(BUILD_OUTPUT)/$@ $(LDFLAGS) + $(CC) $(CFLAGS) $< -o $(BUILD_OUTPUT)/$@ $(LDFLAGS) -lcap .PHONY : clean clean : diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 31c1ca0bb3ee1d6e98250cc24c7de2dbbd016f13..33b370865d16da6f2d6c966183d39a6cecbeed8d 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -30,7 +30,7 @@ #include #include #include -#include +#include #include #include @@ -304,6 +304,10 @@ int *irqs_per_cpu; /* indexed by cpu_num */ void setup_all_buffers(void); +char *sys_lpi_file; +char *sys_lpi_file_sysfs = "/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us"; +char *sys_lpi_file_debugfs = "/sys/kernel/debug/pmc_core/slp_s0_residency_usec"; + int cpu_is_not_present(int cpu) { return !CPU_ISSET_S(cpu, cpu_present_setsize, cpu_present_set); @@ -2916,8 +2920,6 @@ int snapshot_gfx_mhz(void) * * record snapshot of * /sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us - * - * return 1 if config change requires a restart, else return 0 */ int snapshot_cpu_lpi_us(void) { @@ -2941,17 +2943,14 @@ int snapshot_cpu_lpi_us(void) /* * snapshot_sys_lpi() * - * record snapshot of - * /sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us - * - * return 1 if config change requires a restart, else return 0 + * record snapshot of sys_lpi_file */ int snapshot_sys_lpi_us(void) { FILE *fp; int retval; - fp = fopen_or_die("/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us", "r"); + fp = fopen_or_die(sys_lpi_file, "r"); retval = fscanf(fp, "%lld", &cpuidle_cur_sys_lpi_us); if (retval != 1) { @@ -3151,28 +3150,42 @@ void check_dev_msr() err(-5, "no /dev/cpu/0/msr, Try \"# modprobe msr\" "); } -void check_permissions() +/* + * check for CAP_SYS_RAWIO + * return 0 on success + * return 1 on fail + */ +int check_for_cap_sys_rawio(void) { - struct __user_cap_header_struct cap_header_data; - cap_user_header_t cap_header = &cap_header_data; - struct __user_cap_data_struct cap_data_data; - cap_user_data_t cap_data = &cap_data_data; - extern int capget(cap_user_header_t hdrp, cap_user_data_t datap); - int do_exit = 0; - char pathname[32]; + cap_t caps; + cap_flag_value_t cap_flag_value; - /* check for CAP_SYS_RAWIO */ - cap_header->pid = getpid(); - cap_header->version = _LINUX_CAPABILITY_VERSION; - if (capget(cap_header, cap_data) < 0) - err(-6, "capget(2) failed"); + caps = cap_get_proc(); + if (caps == NULL) + err(-6, "cap_get_proc\n"); - if ((cap_data->effective & (1 << CAP_SYS_RAWIO)) == 0) { - do_exit++; + if (cap_get_flag(caps, CAP_SYS_RAWIO, CAP_EFFECTIVE, &cap_flag_value)) + err(-6, "cap_get\n"); + + if (cap_flag_value != CAP_SET) { warnx("capget(CAP_SYS_RAWIO) failed," " try \"# setcap cap_sys_rawio=ep %s\"", progname); + return 1; } + if (cap_free(caps) == -1) + err(-6, "cap_free\n"); + + return 0; +} +void check_permissions(void) +{ + int do_exit = 0; + char pathname[32]; + + /* check for CAP_SYS_RAWIO */ + do_exit += check_for_cap_sys_rawio(); + /* test file permissions */ sprintf(pathname, "/dev/cpu/%d/msr", base_cpu); if (euidaccess(pathname, R_OK)) { @@ -3265,6 +3278,7 @@ int probe_nhm_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ case INTEL_FAM6_ATOM_GOLDMONT_PLUS: case INTEL_FAM6_ATOM_GOLDMONT_D: /* DNV */ + case INTEL_FAM6_ATOM_TREMONT: /* EHL */ pkg_cstate_limits = glm_pkg_cstate_limits; break; default: @@ -3336,6 +3350,17 @@ int is_skx(unsigned int family, unsigned int model) } return 0; } +int is_ehl(unsigned int family, unsigned int model) +{ + if (!genuine_intel) + return 0; + + switch (model) { + case INTEL_FAM6_ATOM_TREMONT: + return 1; + } + return 0; +} int has_turbo_ratio_limit(unsigned int family, unsigned int model) { @@ -3478,6 +3503,23 @@ dump_cstate_pstate_config_info(unsigned int family, unsigned int model) dump_nhm_cst_cfg(); } +static void dump_sysfs_file(char *path) +{ + FILE *input; + char cpuidle_buf[64]; + + input = fopen(path, "r"); + if (input == NULL) { + if (debug) + fprintf(outf, "NSFOD %s\n", path); + return; + } + if (!fgets(cpuidle_buf, sizeof(cpuidle_buf), input)) + err(1, "%s: failed to read file", path); + fclose(input); + + fprintf(outf, "%s: %s", strrchr(path, '/') + 1, cpuidle_buf); +} static void dump_sysfs_cstate_config(void) { @@ -3491,6 +3533,15 @@ dump_sysfs_cstate_config(void) if (!DO_BIC(BIC_sysfs)) return; + if (access("/sys/devices/system/cpu/cpuidle", R_OK)) { + fprintf(outf, "cpuidle not loaded\n"); + return; + } + + dump_sysfs_file("/sys/devices/system/cpu/cpuidle/current_driver"); + dump_sysfs_file("/sys/devices/system/cpu/cpuidle/current_governor"); + dump_sysfs_file("/sys/devices/system/cpu/cpuidle/current_governor_ro"); + for (state = 0; state < 10; ++state) { sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/name", @@ -3894,6 +3945,20 @@ void rapl_probe_intel(unsigned int family, unsigned int model) else BIC_PRESENT(BIC_PkgWatt); break; + case INTEL_FAM6_ATOM_TREMONT: /* EHL */ + do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_GFX | RAPL_PKG_POWER_INFO; + if (rapl_joules) { + BIC_PRESENT(BIC_Pkg_J); + BIC_PRESENT(BIC_Cor_J); + BIC_PRESENT(BIC_RAM_J); + BIC_PRESENT(BIC_GFX_J); + } else { + BIC_PRESENT(BIC_PkgWatt); + BIC_PRESENT(BIC_CorWatt); + BIC_PRESENT(BIC_RAMWatt); + BIC_PRESENT(BIC_GFXWatt); + } + break; case INTEL_FAM6_SKYLAKE_L: /* SKL */ case INTEL_FAM6_CANNONLAKE_L: /* CNL */ do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_GFX | RAPL_PKG_POWER_INFO; @@ -4295,6 +4360,7 @@ int has_snb_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ case INTEL_FAM6_ATOM_GOLDMONT_PLUS: case INTEL_FAM6_ATOM_GOLDMONT_D: /* DNV */ + case INTEL_FAM6_ATOM_TREMONT: /* EHL */ return 1; } return 0; @@ -4324,6 +4390,7 @@ int has_c8910_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_CANNONLAKE_L: /* CNL */ case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ case INTEL_FAM6_ATOM_GOLDMONT_PLUS: + case INTEL_FAM6_ATOM_TREMONT: /* EHL */ return 1; } return 0; @@ -4610,14 +4677,24 @@ unsigned int intel_model_duplicates(unsigned int model) case INTEL_FAM6_SKYLAKE: case INTEL_FAM6_KABYLAKE_L: case INTEL_FAM6_KABYLAKE: + case INTEL_FAM6_COMETLAKE_L: + case INTEL_FAM6_COMETLAKE: return INTEL_FAM6_SKYLAKE_L; case INTEL_FAM6_ICELAKE_L: case INTEL_FAM6_ICELAKE_NNPI: + case INTEL_FAM6_TIGERLAKE_L: + case INTEL_FAM6_TIGERLAKE: return INTEL_FAM6_CANNONLAKE_L; case INTEL_FAM6_ATOM_TREMONT_D: return INTEL_FAM6_ATOM_GOLDMONT_D; + + case INTEL_FAM6_ATOM_TREMONT_L: + return INTEL_FAM6_ATOM_TREMONT; + + case INTEL_FAM6_ICELAKE_X: + return INTEL_FAM6_SKYLAKE_X; } return model; } @@ -4872,7 +4949,8 @@ void process_cpuid() do_slm_cstates = is_slm(family, model); do_knl_cstates = is_knl(family, model); - if (do_slm_cstates || do_knl_cstates || is_cnl(family, model)) + if (do_slm_cstates || do_knl_cstates || is_cnl(family, model) || + is_ehl(family, model)) BIC_NOT_PRESENT(BIC_CPU_c3); if (!quiet) @@ -4907,10 +4985,16 @@ void process_cpuid() else BIC_NOT_PRESENT(BIC_CPU_LPI); - if (!access("/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us", R_OK)) + if (!access(sys_lpi_file_sysfs, R_OK)) { + sys_lpi_file = sys_lpi_file_sysfs; BIC_PRESENT(BIC_SYS_LPI); - else + } else if (!access(sys_lpi_file_debugfs, R_OK)) { + sys_lpi_file = sys_lpi_file_debugfs; + BIC_PRESENT(BIC_SYS_LPI); + } else { + sys_lpi_file_sysfs = NULL; BIC_NOT_PRESENT(BIC_SYS_LPI); + } if (!quiet) decode_misc_feature_control(); @@ -5306,7 +5390,7 @@ int get_and_dump_counters(void) } void print_version() { - fprintf(outf, "turbostat version 19.08.31" + fprintf(outf, "turbostat version 20.03.20" " - Len Brown \n"); } @@ -5323,9 +5407,9 @@ int add_counter(unsigned int msr_num, char *path, char *name, } msrp->msr_num = msr_num; - strncpy(msrp->name, name, NAME_BYTES); + strncpy(msrp->name, name, NAME_BYTES - 1); if (path) - strncpy(msrp->path, path, PATH_BYTES); + strncpy(msrp->path, path, PATH_BYTES - 1); msrp->width = width; msrp->type = type; msrp->format = format; diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index 220d04f958a628948d62409afc2c3c2ce35d874b..7570e36d636d833670253881fc501444d2bfcba1 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -30,7 +30,7 @@ my %default = ( "EMAIL_WHEN_STARTED" => 0, "NUM_TESTS" => 1, "TEST_TYPE" => "build", - "BUILD_TYPE" => "randconfig", + "BUILD_TYPE" => "oldconfig", "MAKE_CMD" => "make", "CLOSE_CONSOLE_SIGNAL" => "INT", "TIMEOUT" => 120, @@ -1030,7 +1030,7 @@ sub __read_config { } if (!$skip && $rest !~ /^\s*$/) { - die "$name: $.: Gargbage found after $type\n$_"; + die "$name: $.: Garbage found after $type\n$_"; } if ($skip && $type eq "TEST_START") { @@ -1063,7 +1063,7 @@ sub __read_config { } if ($rest !~ /^\s*$/) { - die "$name: $.: Gargbage found after DEFAULTS\n$_"; + die "$name: $.: Garbage found after DEFAULTS\n$_"; } } elsif (/^\s*INCLUDE\s+(\S+)/) { @@ -1154,7 +1154,7 @@ sub __read_config { # on of these sections that have SKIP defined. # The save variable can be # defined multiple times and the new one simply overrides - # the prevous one. + # the previous one. set_variable($lvalue, $rvalue); } else { @@ -1234,7 +1234,7 @@ sub read_config { foreach my $option (keys %not_used) { print "$option\n"; } - print "Set IGRNORE_UNUSED = 1 to have ktest ignore unused variables\n"; + print "Set IGNORE_UNUSED = 1 to have ktest ignore unused variables\n"; if (!read_yn "Do you want to continue?") { exit -1; } @@ -1345,7 +1345,7 @@ sub eval_option { # Check for recursive evaluations. # 100 deep should be more than enough. if ($r++ > 100) { - die "Over 100 evaluations accurred with $option\n" . + die "Over 100 evaluations occurred with $option\n" . "Check for recursive variables\n"; } $prev = $option; @@ -1383,7 +1383,7 @@ sub reboot { } else { # Make sure everything has been written to disk - run_ssh("sync"); + run_ssh("sync", 10); if (defined($time)) { start_monitor; @@ -1461,7 +1461,7 @@ sub get_test_name() { sub dodie { - # avoid recusion + # avoid recursion return if ($in_die); $in_die = 1; diff --git a/tools/testing/ktest/sample.conf b/tools/testing/ktest/sample.conf index c3bc933d437b34d3f9e77029908517d6a53b0e32..27666b8007edbb596085ebfb49441be8ad160c2e 100644 --- a/tools/testing/ktest/sample.conf +++ b/tools/testing/ktest/sample.conf @@ -10,7 +10,7 @@ # # Options set in the beginning of the file are considered to be -# default options. These options can be overriden by test specific +# default options. These options can be overridden by test specific # options, with the following exceptions: # # LOG_FILE @@ -204,7 +204,7 @@ # # This config file can also contain "config variables". # These are assigned with ":=" instead of the ktest option -# assigment "=". +# assignment "=". # # The difference between ktest options and config variables # is that config variables can be used multiple times, @@ -263,7 +263,7 @@ #### Using options in other options #### # # Options that are defined in the config file may also be used -# by other options. All options are evaulated at time of +# by other options. All options are evaluated at time of # use (except that config variables are evaluated at config # processing time). # @@ -505,7 +505,7 @@ #TEST = ssh user@machine /root/run_test # The build type is any make config type or special command -# (default randconfig) +# (default oldconfig) # nobuild - skip the clean and build step # useconfig:/path/to/config - use the given config and run # oldconfig on it. @@ -707,7 +707,7 @@ # Line to define a successful boot up in console output. # This is what the line contains, not the entire line. If you need -# the entire line to match, then use regural expression syntax like: +# the entire line to match, then use regular expression syntax like: # (do not add any quotes around it) # # SUCCESS_LINE = ^MyBox Login:$ @@ -839,7 +839,7 @@ # (ignored if POWEROFF_ON_SUCCESS is set) #REBOOT_ON_SUCCESS = 1 -# In case there are isses with rebooting, you can specify this +# In case there are issues with rebooting, you can specify this # to always powercycle after this amount of time after calling # reboot. # Note, POWERCYCLE_AFTER_REBOOT = 0 does NOT disable it. It just @@ -848,7 +848,7 @@ # (default undefined) #POWERCYCLE_AFTER_REBOOT = 5 -# In case there's isses with halting, you can specify this +# In case there's issues with halting, you can specify this # to always poweroff after this amount of time after calling # halt. # Note, POWEROFF_AFTER_HALT = 0 does NOT disable it. It just @@ -972,7 +972,7 @@ # # PATCHCHECK_START is required and is the first patch to # test (the SHA1 of the commit). You may also specify anything -# that git checkout allows (branch name, tage, HEAD~3). +# that git checkout allows (branch name, tag, HEAD~3). # # PATCHCHECK_END is the last patch to check (default HEAD) # @@ -994,7 +994,7 @@ # IGNORE_WARNINGS is set for the given commit's sha1 # # IGNORE_WARNINGS can be used to disable the failure of patchcheck -# on a particuler commit (SHA1). You can add more than one commit +# on a particular commit (SHA1). You can add more than one commit # by adding a list of SHA1s that are space delimited. # # If BUILD_NOCLEAN is set, then make mrproper will not be run on @@ -1093,7 +1093,7 @@ # whatever reason. (Can't reboot, want to inspect each iteration) # Doing a BISECT_MANUAL will have the test wait for you to # tell it if the test passed or failed after each iteration. -# This is basicall the same as running git bisect yourself +# This is basically the same as running git bisect yourself # but ktest will rebuild and install the kernel for you. # # BISECT_CHECK = 1 (optional, default 0) @@ -1239,7 +1239,7 @@ # # CONFIG_BISECT_EXEC (optional) # The config bisect is a separate program that comes with ktest.pl. -# By befault, it will look for: +# By default, it will look for: # `pwd`/config-bisect.pl # the location ktest.pl was executed from. # If it does not find it there, it will look for: # `dirname `/config-bisect.pl # The directory that holds ktest.pl diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index e59eb9e7f9236b5dc872b270b21b072b4886b6ef..180ad1e1b04f91a4f5e7a956436d872a54d5384c 100755 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -24,6 +24,8 @@ KunitResult = namedtuple('KunitResult', ['status','result']) KunitRequest = namedtuple('KunitRequest', ['raw_output','timeout', 'jobs', 'build_dir', 'defconfig']) +KernelDirectoryPath = sys.argv[0].split('tools/testing/kunit/')[0] + class KunitStatus(Enum): SUCCESS = auto() CONFIG_FAILURE = auto() @@ -35,6 +37,13 @@ def create_default_kunitconfig(): shutil.copyfile('arch/um/configs/kunit_defconfig', kunit_kernel.kunitconfig_path) +def get_kernel_root_path(): + parts = sys.argv[0] if not __file__ else __file__ + parts = os.path.realpath(parts).split('tools/testing/kunit') + if len(parts) != 2: + sys.exit(1) + return parts[0] + def run_tests(linux: kunit_kernel.LinuxSourceTree, request: KunitRequest) -> KunitResult: config_start = time.time() @@ -114,6 +123,9 @@ def main(argv, linux=None): cli_args = parser.parse_args(argv) if cli_args.subcommand == 'run': + if get_kernel_root_path(): + os.chdir(get_kernel_root_path()) + if cli_args.build_dir: if not os.path.exists(cli_args.build_dir): os.mkdir(cli_args.build_dir) diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index cc5d844ecca13bfe57f69f13b9c3180834e90a79..d99ae75ef72fa0b7d8193f890875e33c7fb63dce 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -93,6 +93,20 @@ class LinuxSourceTree(object): return False return True + def validate_config(self, build_dir): + kconfig_path = get_kconfig_path(build_dir) + validated_kconfig = kunit_config.Kconfig() + validated_kconfig.read_from_file(kconfig_path) + if not self._kconfig.is_subset_of(validated_kconfig): + invalid = self._kconfig.entries() - validated_kconfig.entries() + message = 'Provided Kconfig is not contained in validated .config. Following fields found in kunitconfig, ' \ + 'but not in .config: %s' % ( + ', '.join([str(e) for e in invalid]) + ) + logging.error(message) + return False + return True + def build_config(self, build_dir): kconfig_path = get_kconfig_path(build_dir) if build_dir and not os.path.exists(build_dir): @@ -103,12 +117,7 @@ class LinuxSourceTree(object): except ConfigError as e: logging.error(e) return False - validated_kconfig = kunit_config.Kconfig() - validated_kconfig.read_from_file(kconfig_path) - if not self._kconfig.is_subset_of(validated_kconfig): - logging.error('Provided Kconfig is not contained in validated .config!') - return False - return True + return self.validate_config(build_dir) def build_reconfig(self, build_dir): """Creates a new .config if it is not a subset of the .kunitconfig.""" @@ -133,12 +142,7 @@ class LinuxSourceTree(object): except (ConfigError, BuildError) as e: logging.error(e) return False - used_kconfig = kunit_config.Kconfig() - used_kconfig.read_from_file(get_kconfig_path(build_dir)) - if not self._kconfig.is_subset_of(used_kconfig): - logging.error('Provided Kconfig is not contained in final config!') - return False - return True + return self.validate_config(build_dir) def run_kernel(self, args=[], timeout=None, build_dir=''): args.extend(['mem=256M']) diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 63430e2664c2eaf4942f855bead786b05bf8e785..6ec503912bea1e5547235ecdedd5bde9fc87f85d 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -77,6 +77,12 @@ ifneq ($(SKIP_TARGETS),) override TARGETS := $(TMP) endif +# User can set FORCE_TARGETS to 1 to require all targets to be successfully +# built; make will fail if any of the targets cannot be built. If +# FORCE_TARGETS is not set (the default), make will succeed if at least one +# of the targets gets built. +FORCE_TARGETS ?= + # Clear LDFLAGS and MAKEFLAGS if called from main # Makefile to avoid test build failures when test # Makefile doesn't have explicit build rules. @@ -151,7 +157,8 @@ all: khdr for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ mkdir $$BUILD_TARGET -p; \ - $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET; \ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET \ + $(if $(FORCE_TARGETS),|| exit); \ ret=$$((ret * $$?)); \ done; exit $$ret; @@ -205,7 +212,8 @@ ifdef INSTALL_PATH @ret=1; \ for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ - $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install; \ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install \ + $(if $(FORCE_TARGETS),|| exit); \ ret=$$((ret * $$?)); \ done; exit $$ret; diff --git a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c index 098bcae5f827e949610d702349d386a89a5f6ddd..0800036ed6547d26efc5b89d7fe109f2fcf7c604 100644 --- a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c +++ b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c @@ -506,8 +506,10 @@ static void test_syncookie(int type, sa_family_t family) .pass_on_failure = 0, }; - if (type != SOCK_STREAM) + if (type != SOCK_STREAM) { + test__skip(); return; + } /* * +1 for TCP-SYN and @@ -822,8 +824,10 @@ void test_select_reuseport(void) goto out; saved_tcp_fo = read_int_sysctl(TCP_FO_SYSCTL); + if (saved_tcp_fo < 0) + goto out; saved_tcp_syncookie = read_int_sysctl(TCP_SYNCOOKIE_SYSCTL); - if (saved_tcp_syncookie < 0 || saved_tcp_syncookie < 0) + if (saved_tcp_syncookie < 0) goto out; if (enable_fastopen()) diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index 07f5b462c2ef5bc11aee156e442b3ac565272d89..aa43e0bd210c3182fe7ebce2f62c5f2def0548de 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -3,6 +3,11 @@ #include "test_progs.h" +#define TCP_REPAIR 19 /* TCP sock is under repair right now */ + +#define TCP_REPAIR_ON 1 +#define TCP_REPAIR_OFF_NO_WP -1 /* Turn off without window probes */ + static int connected_socket_v4(void) { struct sockaddr_in addr = { diff --git a/tools/testing/selftests/ftrace/Makefile b/tools/testing/selftests/ftrace/Makefile index cd1f5b3a777461b89b25c9783d54aeadcc4d66d0..d6e106fbce11c7706e061cf23a920b8d0cb03459 100644 --- a/tools/testing/selftests/ftrace/Makefile +++ b/tools/testing/selftests/ftrace/Makefile @@ -2,7 +2,7 @@ all: TEST_PROGS := ftracetest -TEST_FILES := test.d +TEST_FILES := test.d settings EXTRA_CLEAN := $(OUTPUT)/logs/* include ../lib.mk diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc index 64cfcc75e3c10dc8016f2678f3d06f14863c9f81..f2ee1e889e1350e2c77c0c33b713de96afabc86d 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc @@ -1,6 +1,7 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 # description: ftrace - function pid filters +# flags: instance # Make sure that function pid matching filter works. # Also test it on an instance directory @@ -96,13 +97,6 @@ do_test() { } do_test - -mkdir instances/foo -cd instances/foo -do_test -cd ../../ -rmdir instances/foo - do_reset exit 0 diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile index 30996306cabcfe89a47977643e529b122893bb7e..23207829ec752b52a56577a679f5baf3f3f51a46 100644 --- a/tools/testing/selftests/futex/functional/Makefile +++ b/tools/testing/selftests/futex/functional/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 INCLUDES := -I../include -I../../ CFLAGS := $(CFLAGS) -g -O2 -Wall -D_GNU_SOURCE -pthread $(INCLUDES) -LDFLAGS := $(LDFLAGS) -pthread -lrt +LDLIBS := -lpthread -lrt HEADERS := \ ../include/futextest.h \ diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 67abc1dd50ee6aeaf082445a9fe78ad103dacf90..d91c53b726e60c3f36698930c4e59a4388da74c5 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -8,7 +8,7 @@ KSFT_KHDR_INSTALL := 1 UNAME_M := $(shell uname -m) LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c -LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/ucall.c +LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c @@ -26,6 +26,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/vmx_dirty_log_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test +TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test TEST_GEN_PROGS_x86_64 += clear_dirty_log_test TEST_GEN_PROGS_x86_64 += dirty_log_test TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index aa6451b3f740baa24a2afb90e85365af99f02e81..7428513a4c687f0061d0feb310f6af5abc8dcc9d 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -36,24 +36,24 @@ #define X86_CR4_SMAP (1ul << 21) #define X86_CR4_PKE (1ul << 22) -/* The enum values match the intruction encoding of each register */ -enum x86_register { - RAX = 0, - RCX, - RDX, - RBX, - RSP, - RBP, - RSI, - RDI, - R8, - R9, - R10, - R11, - R12, - R13, - R14, - R15, +/* General Registers in 64-Bit Mode */ +struct gpr64_regs { + u64 rax; + u64 rcx; + u64 rdx; + u64 rbx; + u64 rsp; + u64 rbp; + u64 rsi; + u64 rdi; + u64 r8; + u64 r9; + u64 r10; + u64 r11; + u64 r12; + u64 r13; + u64 r14; + u64 r15; }; struct desc64 { @@ -220,20 +220,20 @@ static inline void set_cr4(uint64_t val) __asm__ __volatile__("mov %0, %%cr4" : : "r" (val) : "memory"); } -static inline uint64_t get_gdt_base(void) +static inline struct desc_ptr get_gdt(void) { struct desc_ptr gdt; __asm__ __volatile__("sgdt %[gdt]" : /* output */ [gdt]"=m"(gdt)); - return gdt.address; + return gdt; } -static inline uint64_t get_idt_base(void) +static inline struct desc_ptr get_idt(void) { struct desc_ptr idt; __asm__ __volatile__("sidt %[idt]" : /* output */ [idt]"=m"(idt)); - return idt.address; + return idt; } #define SET_XMM(__var, __xmm) \ diff --git a/tools/testing/selftests/kvm/include/x86_64/svm.h b/tools/testing/selftests/kvm/include/x86_64/svm.h new file mode 100644 index 0000000000000000000000000000000000000000..f4ea2355dbc2e7b5af3360467c8ddd6451f9e73a --- /dev/null +++ b/tools/testing/selftests/kvm/include/x86_64/svm.h @@ -0,0 +1,297 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * tools/testing/selftests/kvm/include/x86_64/svm.h + * This is a copy of arch/x86/include/asm/svm.h + * + */ + +#ifndef SELFTEST_KVM_SVM_H +#define SELFTEST_KVM_SVM_H + +enum { + INTERCEPT_INTR, + INTERCEPT_NMI, + INTERCEPT_SMI, + INTERCEPT_INIT, + INTERCEPT_VINTR, + INTERCEPT_SELECTIVE_CR0, + INTERCEPT_STORE_IDTR, + INTERCEPT_STORE_GDTR, + INTERCEPT_STORE_LDTR, + INTERCEPT_STORE_TR, + INTERCEPT_LOAD_IDTR, + INTERCEPT_LOAD_GDTR, + INTERCEPT_LOAD_LDTR, + INTERCEPT_LOAD_TR, + INTERCEPT_RDTSC, + INTERCEPT_RDPMC, + INTERCEPT_PUSHF, + INTERCEPT_POPF, + INTERCEPT_CPUID, + INTERCEPT_RSM, + INTERCEPT_IRET, + INTERCEPT_INTn, + INTERCEPT_INVD, + INTERCEPT_PAUSE, + INTERCEPT_HLT, + INTERCEPT_INVLPG, + INTERCEPT_INVLPGA, + INTERCEPT_IOIO_PROT, + INTERCEPT_MSR_PROT, + INTERCEPT_TASK_SWITCH, + INTERCEPT_FERR_FREEZE, + INTERCEPT_SHUTDOWN, + INTERCEPT_VMRUN, + INTERCEPT_VMMCALL, + INTERCEPT_VMLOAD, + INTERCEPT_VMSAVE, + INTERCEPT_STGI, + INTERCEPT_CLGI, + INTERCEPT_SKINIT, + INTERCEPT_RDTSCP, + INTERCEPT_ICEBP, + INTERCEPT_WBINVD, + INTERCEPT_MONITOR, + INTERCEPT_MWAIT, + INTERCEPT_MWAIT_COND, + INTERCEPT_XSETBV, + INTERCEPT_RDPRU, +}; + + +struct __attribute__ ((__packed__)) vmcb_control_area { + u32 intercept_cr; + u32 intercept_dr; + u32 intercept_exceptions; + u64 intercept; + u8 reserved_1[40]; + u16 pause_filter_thresh; + u16 pause_filter_count; + u64 iopm_base_pa; + u64 msrpm_base_pa; + u64 tsc_offset; + u32 asid; + u8 tlb_ctl; + u8 reserved_2[3]; + u32 int_ctl; + u32 int_vector; + u32 int_state; + u8 reserved_3[4]; + u32 exit_code; + u32 exit_code_hi; + u64 exit_info_1; + u64 exit_info_2; + u32 exit_int_info; + u32 exit_int_info_err; + u64 nested_ctl; + u64 avic_vapic_bar; + u8 reserved_4[8]; + u32 event_inj; + u32 event_inj_err; + u64 nested_cr3; + u64 virt_ext; + u32 clean; + u32 reserved_5; + u64 next_rip; + u8 insn_len; + u8 insn_bytes[15]; + u64 avic_backing_page; /* Offset 0xe0 */ + u8 reserved_6[8]; /* Offset 0xe8 */ + u64 avic_logical_id; /* Offset 0xf0 */ + u64 avic_physical_id; /* Offset 0xf8 */ + u8 reserved_7[768]; +}; + + +#define TLB_CONTROL_DO_NOTHING 0 +#define TLB_CONTROL_FLUSH_ALL_ASID 1 +#define TLB_CONTROL_FLUSH_ASID 3 +#define TLB_CONTROL_FLUSH_ASID_LOCAL 7 + +#define V_TPR_MASK 0x0f + +#define V_IRQ_SHIFT 8 +#define V_IRQ_MASK (1 << V_IRQ_SHIFT) + +#define V_GIF_SHIFT 9 +#define V_GIF_MASK (1 << V_GIF_SHIFT) + +#define V_INTR_PRIO_SHIFT 16 +#define V_INTR_PRIO_MASK (0x0f << V_INTR_PRIO_SHIFT) + +#define V_IGN_TPR_SHIFT 20 +#define V_IGN_TPR_MASK (1 << V_IGN_TPR_SHIFT) + +#define V_INTR_MASKING_SHIFT 24 +#define V_INTR_MASKING_MASK (1 << V_INTR_MASKING_SHIFT) + +#define V_GIF_ENABLE_SHIFT 25 +#define V_GIF_ENABLE_MASK (1 << V_GIF_ENABLE_SHIFT) + +#define AVIC_ENABLE_SHIFT 31 +#define AVIC_ENABLE_MASK (1 << AVIC_ENABLE_SHIFT) + +#define LBR_CTL_ENABLE_MASK BIT_ULL(0) +#define VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK BIT_ULL(1) + +#define SVM_INTERRUPT_SHADOW_MASK 1 + +#define SVM_IOIO_STR_SHIFT 2 +#define SVM_IOIO_REP_SHIFT 3 +#define SVM_IOIO_SIZE_SHIFT 4 +#define SVM_IOIO_ASIZE_SHIFT 7 + +#define SVM_IOIO_TYPE_MASK 1 +#define SVM_IOIO_STR_MASK (1 << SVM_IOIO_STR_SHIFT) +#define SVM_IOIO_REP_MASK (1 << SVM_IOIO_REP_SHIFT) +#define SVM_IOIO_SIZE_MASK (7 << SVM_IOIO_SIZE_SHIFT) +#define SVM_IOIO_ASIZE_MASK (7 << SVM_IOIO_ASIZE_SHIFT) + +#define SVM_VM_CR_VALID_MASK 0x001fULL +#define SVM_VM_CR_SVM_LOCK_MASK 0x0008ULL +#define SVM_VM_CR_SVM_DIS_MASK 0x0010ULL + +#define SVM_NESTED_CTL_NP_ENABLE BIT(0) +#define SVM_NESTED_CTL_SEV_ENABLE BIT(1) + +struct __attribute__ ((__packed__)) vmcb_seg { + u16 selector; + u16 attrib; + u32 limit; + u64 base; +}; + +struct __attribute__ ((__packed__)) vmcb_save_area { + struct vmcb_seg es; + struct vmcb_seg cs; + struct vmcb_seg ss; + struct vmcb_seg ds; + struct vmcb_seg fs; + struct vmcb_seg gs; + struct vmcb_seg gdtr; + struct vmcb_seg ldtr; + struct vmcb_seg idtr; + struct vmcb_seg tr; + u8 reserved_1[43]; + u8 cpl; + u8 reserved_2[4]; + u64 efer; + u8 reserved_3[112]; + u64 cr4; + u64 cr3; + u64 cr0; + u64 dr7; + u64 dr6; + u64 rflags; + u64 rip; + u8 reserved_4[88]; + u64 rsp; + u8 reserved_5[24]; + u64 rax; + u64 star; + u64 lstar; + u64 cstar; + u64 sfmask; + u64 kernel_gs_base; + u64 sysenter_cs; + u64 sysenter_esp; + u64 sysenter_eip; + u64 cr2; + u8 reserved_6[32]; + u64 g_pat; + u64 dbgctl; + u64 br_from; + u64 br_to; + u64 last_excp_from; + u64 last_excp_to; +}; + +struct __attribute__ ((__packed__)) vmcb { + struct vmcb_control_area control; + struct vmcb_save_area save; +}; + +#define SVM_CPUID_FUNC 0x8000000a + +#define SVM_VM_CR_SVM_DISABLE 4 + +#define SVM_SELECTOR_S_SHIFT 4 +#define SVM_SELECTOR_DPL_SHIFT 5 +#define SVM_SELECTOR_P_SHIFT 7 +#define SVM_SELECTOR_AVL_SHIFT 8 +#define SVM_SELECTOR_L_SHIFT 9 +#define SVM_SELECTOR_DB_SHIFT 10 +#define SVM_SELECTOR_G_SHIFT 11 + +#define SVM_SELECTOR_TYPE_MASK (0xf) +#define SVM_SELECTOR_S_MASK (1 << SVM_SELECTOR_S_SHIFT) +#define SVM_SELECTOR_DPL_MASK (3 << SVM_SELECTOR_DPL_SHIFT) +#define SVM_SELECTOR_P_MASK (1 << SVM_SELECTOR_P_SHIFT) +#define SVM_SELECTOR_AVL_MASK (1 << SVM_SELECTOR_AVL_SHIFT) +#define SVM_SELECTOR_L_MASK (1 << SVM_SELECTOR_L_SHIFT) +#define SVM_SELECTOR_DB_MASK (1 << SVM_SELECTOR_DB_SHIFT) +#define SVM_SELECTOR_G_MASK (1 << SVM_SELECTOR_G_SHIFT) + +#define SVM_SELECTOR_WRITE_MASK (1 << 1) +#define SVM_SELECTOR_READ_MASK SVM_SELECTOR_WRITE_MASK +#define SVM_SELECTOR_CODE_MASK (1 << 3) + +#define INTERCEPT_CR0_READ 0 +#define INTERCEPT_CR3_READ 3 +#define INTERCEPT_CR4_READ 4 +#define INTERCEPT_CR8_READ 8 +#define INTERCEPT_CR0_WRITE (16 + 0) +#define INTERCEPT_CR3_WRITE (16 + 3) +#define INTERCEPT_CR4_WRITE (16 + 4) +#define INTERCEPT_CR8_WRITE (16 + 8) + +#define INTERCEPT_DR0_READ 0 +#define INTERCEPT_DR1_READ 1 +#define INTERCEPT_DR2_READ 2 +#define INTERCEPT_DR3_READ 3 +#define INTERCEPT_DR4_READ 4 +#define INTERCEPT_DR5_READ 5 +#define INTERCEPT_DR6_READ 6 +#define INTERCEPT_DR7_READ 7 +#define INTERCEPT_DR0_WRITE (16 + 0) +#define INTERCEPT_DR1_WRITE (16 + 1) +#define INTERCEPT_DR2_WRITE (16 + 2) +#define INTERCEPT_DR3_WRITE (16 + 3) +#define INTERCEPT_DR4_WRITE (16 + 4) +#define INTERCEPT_DR5_WRITE (16 + 5) +#define INTERCEPT_DR6_WRITE (16 + 6) +#define INTERCEPT_DR7_WRITE (16 + 7) + +#define SVM_EVTINJ_VEC_MASK 0xff + +#define SVM_EVTINJ_TYPE_SHIFT 8 +#define SVM_EVTINJ_TYPE_MASK (7 << SVM_EVTINJ_TYPE_SHIFT) + +#define SVM_EVTINJ_TYPE_INTR (0 << SVM_EVTINJ_TYPE_SHIFT) +#define SVM_EVTINJ_TYPE_NMI (2 << SVM_EVTINJ_TYPE_SHIFT) +#define SVM_EVTINJ_TYPE_EXEPT (3 << SVM_EVTINJ_TYPE_SHIFT) +#define SVM_EVTINJ_TYPE_SOFT (4 << SVM_EVTINJ_TYPE_SHIFT) + +#define SVM_EVTINJ_VALID (1 << 31) +#define SVM_EVTINJ_VALID_ERR (1 << 11) + +#define SVM_EXITINTINFO_VEC_MASK SVM_EVTINJ_VEC_MASK +#define SVM_EXITINTINFO_TYPE_MASK SVM_EVTINJ_TYPE_MASK + +#define SVM_EXITINTINFO_TYPE_INTR SVM_EVTINJ_TYPE_INTR +#define SVM_EXITINTINFO_TYPE_NMI SVM_EVTINJ_TYPE_NMI +#define SVM_EXITINTINFO_TYPE_EXEPT SVM_EVTINJ_TYPE_EXEPT +#define SVM_EXITINTINFO_TYPE_SOFT SVM_EVTINJ_TYPE_SOFT + +#define SVM_EXITINTINFO_VALID SVM_EVTINJ_VALID +#define SVM_EXITINTINFO_VALID_ERR SVM_EVTINJ_VALID_ERR + +#define SVM_EXITINFOSHIFT_TS_REASON_IRET 36 +#define SVM_EXITINFOSHIFT_TS_REASON_JMP 38 +#define SVM_EXITINFOSHIFT_TS_HAS_ERROR_CODE 44 + +#define SVM_EXITINFO_REG_MASK 0x0F + +#define SVM_CR0_SELECTIVE_MASK (X86_CR0_TS | X86_CR0_MP) + +#endif /* SELFTEST_KVM_SVM_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/svm_util.h b/tools/testing/selftests/kvm/include/x86_64/svm_util.h new file mode 100644 index 0000000000000000000000000000000000000000..cd037917feceda21dbbf27bc78d1b0c80c7576d6 --- /dev/null +++ b/tools/testing/selftests/kvm/include/x86_64/svm_util.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * tools/testing/selftests/kvm/include/x86_64/svm_utils.h + * Header for nested SVM testing + * + * Copyright (C) 2020, Red Hat, Inc. + */ + +#ifndef SELFTEST_KVM_SVM_UTILS_H +#define SELFTEST_KVM_SVM_UTILS_H + +#include +#include "svm.h" +#include "processor.h" + +#define CPUID_SVM_BIT 2 +#define CPUID_SVM BIT_ULL(CPUID_SVM_BIT) + +#define SVM_EXIT_VMMCALL 0x081 + +struct svm_test_data { + /* VMCB */ + struct vmcb *vmcb; /* gva */ + void *vmcb_hva; + uint64_t vmcb_gpa; + + /* host state-save area */ + struct vmcb_save_area *save_area; /* gva */ + void *save_area_hva; + uint64_t save_area_gpa; +}; + +struct svm_test_data *vcpu_alloc_svm(struct kvm_vm *vm, vm_vaddr_t *p_svm_gva); +void generic_svm_setup(struct svm_test_data *svm, void *guest_rip, void *guest_rsp); +void run_guest(struct vmcb *vmcb, uint64_t vmcb_gpa); +void nested_svm_check_supported(void); + +#endif /* SELFTEST_KVM_SVM_UTILS_H */ diff --git a/tools/testing/selftests/kvm/lib/x86_64/svm.c b/tools/testing/selftests/kvm/lib/x86_64/svm.c new file mode 100644 index 0000000000000000000000000000000000000000..6e05a8fc3fe0694fb6ab805745c841943b0e8604 --- /dev/null +++ b/tools/testing/selftests/kvm/lib/x86_64/svm.c @@ -0,0 +1,161 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * tools/testing/selftests/kvm/lib/x86_64/svm.c + * Helpers used for nested SVM testing + * Largely inspired from KVM unit test svm.c + * + * Copyright (C) 2020, Red Hat, Inc. + */ + +#include "test_util.h" +#include "kvm_util.h" +#include "../kvm_util_internal.h" +#include "processor.h" +#include "svm_util.h" + +struct gpr64_regs guest_regs; +u64 rflags; + +/* Allocate memory regions for nested SVM tests. + * + * Input Args: + * vm - The VM to allocate guest-virtual addresses in. + * + * Output Args: + * p_svm_gva - The guest virtual address for the struct svm_test_data. + * + * Return: + * Pointer to structure with the addresses of the SVM areas. + */ +struct svm_test_data * +vcpu_alloc_svm(struct kvm_vm *vm, vm_vaddr_t *p_svm_gva) +{ + vm_vaddr_t svm_gva = vm_vaddr_alloc(vm, getpagesize(), + 0x10000, 0, 0); + struct svm_test_data *svm = addr_gva2hva(vm, svm_gva); + + svm->vmcb = (void *)vm_vaddr_alloc(vm, getpagesize(), + 0x10000, 0, 0); + svm->vmcb_hva = addr_gva2hva(vm, (uintptr_t)svm->vmcb); + svm->vmcb_gpa = addr_gva2gpa(vm, (uintptr_t)svm->vmcb); + + svm->save_area = (void *)vm_vaddr_alloc(vm, getpagesize(), + 0x10000, 0, 0); + svm->save_area_hva = addr_gva2hva(vm, (uintptr_t)svm->save_area); + svm->save_area_gpa = addr_gva2gpa(vm, (uintptr_t)svm->save_area); + + *p_svm_gva = svm_gva; + return svm; +} + +static void vmcb_set_seg(struct vmcb_seg *seg, u16 selector, + u64 base, u32 limit, u32 attr) +{ + seg->selector = selector; + seg->attrib = attr; + seg->limit = limit; + seg->base = base; +} + +void generic_svm_setup(struct svm_test_data *svm, void *guest_rip, void *guest_rsp) +{ + struct vmcb *vmcb = svm->vmcb; + uint64_t vmcb_gpa = svm->vmcb_gpa; + struct vmcb_save_area *save = &vmcb->save; + struct vmcb_control_area *ctrl = &vmcb->control; + u32 data_seg_attr = 3 | SVM_SELECTOR_S_MASK | SVM_SELECTOR_P_MASK + | SVM_SELECTOR_DB_MASK | SVM_SELECTOR_G_MASK; + u32 code_seg_attr = 9 | SVM_SELECTOR_S_MASK | SVM_SELECTOR_P_MASK + | SVM_SELECTOR_L_MASK | SVM_SELECTOR_G_MASK; + uint64_t efer; + + efer = rdmsr(MSR_EFER); + wrmsr(MSR_EFER, efer | EFER_SVME); + wrmsr(MSR_VM_HSAVE_PA, svm->save_area_gpa); + + memset(vmcb, 0, sizeof(*vmcb)); + asm volatile ("vmsave\n\t" : : "a" (vmcb_gpa) : "memory"); + vmcb_set_seg(&save->es, get_es(), 0, -1U, data_seg_attr); + vmcb_set_seg(&save->cs, get_cs(), 0, -1U, code_seg_attr); + vmcb_set_seg(&save->ss, get_ss(), 0, -1U, data_seg_attr); + vmcb_set_seg(&save->ds, get_ds(), 0, -1U, data_seg_attr); + vmcb_set_seg(&save->gdtr, 0, get_gdt().address, get_gdt().size, 0); + vmcb_set_seg(&save->idtr, 0, get_idt().address, get_idt().size, 0); + + ctrl->asid = 1; + save->cpl = 0; + save->efer = rdmsr(MSR_EFER); + asm volatile ("mov %%cr4, %0" : "=r"(save->cr4) : : "memory"); + asm volatile ("mov %%cr3, %0" : "=r"(save->cr3) : : "memory"); + asm volatile ("mov %%cr0, %0" : "=r"(save->cr0) : : "memory"); + asm volatile ("mov %%dr7, %0" : "=r"(save->dr7) : : "memory"); + asm volatile ("mov %%dr6, %0" : "=r"(save->dr6) : : "memory"); + asm volatile ("mov %%cr2, %0" : "=r"(save->cr2) : : "memory"); + save->g_pat = rdmsr(MSR_IA32_CR_PAT); + save->dbgctl = rdmsr(MSR_IA32_DEBUGCTLMSR); + ctrl->intercept = (1ULL << INTERCEPT_VMRUN) | + (1ULL << INTERCEPT_VMMCALL); + + vmcb->save.rip = (u64)guest_rip; + vmcb->save.rsp = (u64)guest_rsp; + guest_regs.rdi = (u64)svm; +} + +/* + * save/restore 64-bit general registers except rax, rip, rsp + * which are directly handed through the VMCB guest processor state + */ +#define SAVE_GPR_C \ + "xchg %%rbx, guest_regs+0x20\n\t" \ + "xchg %%rcx, guest_regs+0x10\n\t" \ + "xchg %%rdx, guest_regs+0x18\n\t" \ + "xchg %%rbp, guest_regs+0x30\n\t" \ + "xchg %%rsi, guest_regs+0x38\n\t" \ + "xchg %%rdi, guest_regs+0x40\n\t" \ + "xchg %%r8, guest_regs+0x48\n\t" \ + "xchg %%r9, guest_regs+0x50\n\t" \ + "xchg %%r10, guest_regs+0x58\n\t" \ + "xchg %%r11, guest_regs+0x60\n\t" \ + "xchg %%r12, guest_regs+0x68\n\t" \ + "xchg %%r13, guest_regs+0x70\n\t" \ + "xchg %%r14, guest_regs+0x78\n\t" \ + "xchg %%r15, guest_regs+0x80\n\t" + +#define LOAD_GPR_C SAVE_GPR_C + +/* + * selftests do not use interrupts so we dropped clgi/sti/cli/stgi + * for now. registers involved in LOAD/SAVE_GPR_C are eventually + * unmodified so they do not need to be in the clobber list. + */ +void run_guest(struct vmcb *vmcb, uint64_t vmcb_gpa) +{ + asm volatile ( + "vmload\n\t" + "mov rflags, %%r15\n\t" // rflags + "mov %%r15, 0x170(%[vmcb])\n\t" + "mov guest_regs, %%r15\n\t" // rax + "mov %%r15, 0x1f8(%[vmcb])\n\t" + LOAD_GPR_C + "vmrun\n\t" + SAVE_GPR_C + "mov 0x170(%[vmcb]), %%r15\n\t" // rflags + "mov %%r15, rflags\n\t" + "mov 0x1f8(%[vmcb]), %%r15\n\t" // rax + "mov %%r15, guest_regs\n\t" + "vmsave\n\t" + : : [vmcb] "r" (vmcb), [vmcb_gpa] "a" (vmcb_gpa) + : "r15", "memory"); +} + +void nested_svm_check_supported(void) +{ + struct kvm_cpuid_entry2 *entry = + kvm_get_supported_cpuid_entry(0x80000001); + + if (!(entry->ecx & CPUID_SVM)) { + fprintf(stderr, "nested SVM not enabled, skipping test\n"); + exit(KSFT_SKIP); + } +} + diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c index 85064baf5e97c2fe363c4f662ca2e0f274e4fa21..7aaa99ca4dbc3a34aabfbcda41239742be46f3b6 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c +++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c @@ -288,9 +288,9 @@ static inline void init_vmcs_host_state(void) vmwrite(HOST_FS_BASE, rdmsr(MSR_FS_BASE)); vmwrite(HOST_GS_BASE, rdmsr(MSR_GS_BASE)); vmwrite(HOST_TR_BASE, - get_desc64_base((struct desc64 *)(get_gdt_base() + get_tr()))); - vmwrite(HOST_GDTR_BASE, get_gdt_base()); - vmwrite(HOST_IDTR_BASE, get_idt_base()); + get_desc64_base((struct desc64 *)(get_gdt().address + get_tr()))); + vmwrite(HOST_GDTR_BASE, get_gdt().address); + vmwrite(HOST_IDTR_BASE, get_idt().address); vmwrite(HOST_IA32_SYSENTER_ESP, rdmsr(MSR_IA32_SYSENTER_ESP)); vmwrite(HOST_IA32_SYSENTER_EIP, rdmsr(MSR_IA32_SYSENTER_EIP)); } diff --git a/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c new file mode 100644 index 0000000000000000000000000000000000000000..e280f68f6365b4b23a5912ae1a74a995feb7034c --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c @@ -0,0 +1,79 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * svm_vmcall_test + * + * Copyright (C) 2020, Red Hat, Inc. + * + * Nested SVM testing: VMCALL + */ + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" +#include "svm_util.h" + +#define VCPU_ID 5 + +static struct kvm_vm *vm; + +static void l2_guest_code(struct svm_test_data *svm) +{ + __asm__ __volatile__("vmcall"); +} + +static void l1_guest_code(struct svm_test_data *svm) +{ + #define L2_GUEST_STACK_SIZE 64 + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + struct vmcb *vmcb = svm->vmcb; + + /* Prepare for L2 execution. */ + generic_svm_setup(svm, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + run_guest(vmcb, svm->vmcb_gpa); + + GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL); + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + vm_vaddr_t svm_gva; + + nested_svm_check_supported(); + + vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); + vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + + vcpu_alloc_svm(vm, &svm_gva); + vcpu_args_set(vm, VCPU_ID, 1, svm_gva); + + for (;;) { + volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct ucall uc; + + vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_ABORT: + TEST_ASSERT(false, "%s", + (const char *)uc.args[0]); + /* NOT REACHED */ + case UCALL_SYNC: + break; + case UCALL_DONE: + goto done; + default: + TEST_ASSERT(false, + "Unknown ucall 0x%x.", uc.cmd); + } + } +done: + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 1c8a1963d03f8acf349ae209e5db03ab79e2614e..3ed0134a764d494f6b451fddfa45fee58f11611a 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -83,17 +83,20 @@ else $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS)) endif +define INSTALL_SINGLE_RULE + $(if $(INSTALL_LIST),@mkdir -p $(INSTALL_PATH)) + $(if $(INSTALL_LIST),@echo rsync -a $(INSTALL_LIST) $(INSTALL_PATH)/) + $(if $(INSTALL_LIST),@rsync -a $(INSTALL_LIST) $(INSTALL_PATH)/) +endef + define INSTALL_RULE - @if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then \ - mkdir -p ${INSTALL_PATH}; \ - echo "rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/"; \ - rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/; \ - fi - @if [ "X$(TEST_GEN_PROGS)$(TEST_CUSTOM_PROGS)$(TEST_GEN_PROGS_EXTENDED)$(TEST_GEN_FILES)" != "X" ]; then \ - mkdir -p ${INSTALL_PATH}; \ - echo "rsync -a $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/"; \ - rsync -a $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/; \ - fi + $(eval INSTALL_LIST = $(TEST_PROGS)) $(INSTALL_SINGLE_RULE) + $(eval INSTALL_LIST = $(TEST_PROGS_EXTENDED)) $(INSTALL_SINGLE_RULE) + $(eval INSTALL_LIST = $(TEST_FILES)) $(INSTALL_SINGLE_RULE) + $(eval INSTALL_LIST = $(TEST_GEN_PROGS)) $(INSTALL_SINGLE_RULE) + $(eval INSTALL_LIST = $(TEST_CUSTOM_PROGS)) $(INSTALL_SINGLE_RULE) + $(eval INSTALL_LIST = $(TEST_GEN_PROGS_EXTENDED)) $(INSTALL_SINGLE_RULE) + $(eval INSTALL_LIST = $(TEST_GEN_FILES)) $(INSTALL_SINGLE_RULE) endef install: all diff --git a/tools/testing/selftests/livepatch/Makefile b/tools/testing/selftests/livepatch/Makefile index 3876d8d62494443297b0da55cb88bbe5f2da5210..1acc9e1fa3fbca78db5fca858f01c042a2fe62ff 100644 --- a/tools/testing/selftests/livepatch/Makefile +++ b/tools/testing/selftests/livepatch/Makefile @@ -8,4 +8,6 @@ TEST_PROGS := \ test-state.sh \ test-ftrace.sh +TEST_FILES := settings + include ../lib.mk diff --git a/tools/testing/selftests/lkdtm/.gitignore b/tools/testing/selftests/lkdtm/.gitignore new file mode 100644 index 0000000000000000000000000000000000000000..f26212605b6b7592b1b255e11e6e165b9e975705 --- /dev/null +++ b/tools/testing/selftests/lkdtm/.gitignore @@ -0,0 +1,2 @@ +*.sh +!run.sh diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index b5694196430ae2334b83cdeb465bf3e7d36080f5..287ae916ec0b4b8e22b886ec65ac0c21fdedc72a 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -27,5 +27,5 @@ KSFT_KHDR_INSTALL := 1 include ../lib.mk $(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma -$(OUTPUT)/tcp_mmap: LDFLAGS += -lpthread -$(OUTPUT)/tcp_inq: LDFLAGS += -lpthread +$(OUTPUT)/tcp_mmap: LDLIBS += -lpthread +$(OUTPUT)/tcp_inq: LDLIBS += -lpthread diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 6dd4031038008bef871a66ea1e3ebfdf7d8b964f..b7616704b55e982f20d55c768def568f54e0efc1 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -910,6 +910,12 @@ ipv6_rt_replace_mpath() check_route6 "2001:db8:104::/64 via 2001:db8:101::3 dev veth1 metric 1024" log_test $? 0 "Multipath with single path via multipath attribute" + # multipath with dev-only + add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 dev veth1" + check_route6 "2001:db8:104::/64 dev veth1 metric 1024" + log_test $? 0 "Multipath with dev-only" + # route replace fails - invalid nexthop 1 add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:111::3 nexthop via 2001:db8:103::3" @@ -1035,6 +1041,27 @@ ipv6_addr_metric_test() fi log_test $rc 0 "Prefix route with metric on link up" + # verify peer metric added correctly + set -e + run_cmd "$IP -6 addr flush dev dummy2" + run_cmd "$IP -6 addr add dev dummy2 2001:db8:104::1 peer 2001:db8:104::2 metric 260" + set +e + + check_route6 "2001:db8:104::1 dev dummy2 proto kernel metric 260" + log_test $? 0 "Set metric with peer route on local side" + log_test $? 0 "User specified metric on local address" + check_route6 "2001:db8:104::2 dev dummy2 proto kernel metric 260" + log_test $? 0 "Set metric with peer route on peer side" + + set -e + run_cmd "$IP -6 addr change dev dummy2 2001:db8:104::1 peer 2001:db8:104::3 metric 261" + set +e + + check_route6 "2001:db8:104::1 dev dummy2 proto kernel metric 261" + log_test $? 0 "Modify metric and peer address on local side" + check_route6 "2001:db8:104::3 dev dummy2 proto kernel metric 261" + log_test $? 0 "Modify metric and peer address on peer side" + $IP li del dummy1 $IP li del dummy2 cleanup @@ -1451,13 +1478,20 @@ ipv4_addr_metric_test() run_cmd "$IP addr flush dev dummy2" run_cmd "$IP addr add dev dummy2 172.16.104.1/32 peer 172.16.104.2 metric 260" - run_cmd "$IP addr change dev dummy2 172.16.104.1/32 peer 172.16.104.2 metric 261" rc=$? if [ $rc -eq 0 ]; then - check_route "172.16.104.2 dev dummy2 proto kernel scope link src 172.16.104.1 metric 261" + check_route "172.16.104.2 dev dummy2 proto kernel scope link src 172.16.104.1 metric 260" + rc=$? + fi + log_test $rc 0 "Set metric of address with peer route" + + run_cmd "$IP addr change dev dummy2 172.16.104.1/32 peer 172.16.104.3 metric 261" + rc=$? + if [ $rc -eq 0 ]; then + check_route "172.16.104.3 dev dummy2 proto kernel scope link src 172.16.104.1 metric 261" rc=$? fi - log_test $rc 0 "Modify metric of address with peer route" + log_test $rc 0 "Modify metric and peer address for peer route" $IP li del dummy1 $IP li del dummy2 diff --git a/tools/testing/selftests/net/forwarding/mirror_gre.sh b/tools/testing/selftests/net/forwarding/mirror_gre.sh index e6fd7a18c655ff32e4f4d5ffd033acd866a70c96..0266443601bc0bb90504132a1c1b57aced95089b 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre.sh @@ -63,22 +63,23 @@ test_span_gre_mac() { local tundev=$1; shift local direction=$1; shift - local prot=$1; shift local what=$1; shift - local swp3mac=$(mac_get $swp3) - local h3mac=$(mac_get $h3) + case "$direction" in + ingress) local src_mac=$(mac_get $h1); local dst_mac=$(mac_get $h2) + ;; + egress) local src_mac=$(mac_get $h2); local dst_mac=$(mac_get $h1) + ;; + esac RET=0 mirror_install $swp1 $direction $tundev "matchall $tcflags" - tc filter add dev $h3 ingress pref 77 prot $prot \ - flower ip_proto 0x2f src_mac $swp3mac dst_mac $h3mac \ - action pass + icmp_capture_install h3-${tundev} "src_mac $src_mac dst_mac $dst_mac" - mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 10 + mirror_test v$h1 192.0.2.1 192.0.2.2 h3-${tundev} 100 10 - tc filter del dev $h3 ingress pref 77 + icmp_capture_uninstall h3-${tundev} mirror_uninstall $swp1 $direction log_test "$direction $what: envelope MAC ($tcflags)" @@ -120,14 +121,14 @@ test_ip6gretap() test_gretap_mac() { - test_span_gre_mac gt4 ingress ip "mirror to gretap" - test_span_gre_mac gt4 egress ip "mirror to gretap" + test_span_gre_mac gt4 ingress "mirror to gretap" + test_span_gre_mac gt4 egress "mirror to gretap" } test_ip6gretap_mac() { - test_span_gre_mac gt6 ingress ipv6 "mirror to ip6gretap" - test_span_gre_mac gt6 egress ipv6 "mirror to ip6gretap" + test_span_gre_mac gt6 ingress "mirror to ip6gretap" + test_span_gre_mac gt6 egress "mirror to ip6gretap" } test_all() diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh index bb10e33690b25a763d3de18cce207a098baf7351..ce6bea9675c074587ca1ebc51a3402cdcf782ee0 100755 --- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh @@ -516,9 +516,9 @@ test_tos() RET=0 tc filter add dev v1 egress pref 77 prot ip \ - flower ip_tos 0x40 action pass - vxlan_ping_test $h1 192.0.2.3 "-Q 0x40" v1 egress 77 10 - vxlan_ping_test $h1 192.0.2.3 "-Q 0x30" v1 egress 77 0 + flower ip_tos 0x14 action pass + vxlan_ping_test $h1 192.0.2.3 "-Q 0x14" v1 egress 77 10 + vxlan_ping_test $h1 192.0.2.3 "-Q 0x18" v1 egress 77 0 tc filter del dev v1 egress pref 77 prot ip log_test "VXLAN: envelope TOS inheritance" diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index 93de52016ddee400e64ae3ed9eceac8a3b10834b..ba450e62dc5be5e5bccd5f36753ca81c1a74dff7 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -8,6 +8,8 @@ TEST_PROGS := mptcp_connect.sh TEST_GEN_FILES = mptcp_connect +TEST_FILES := settings + EXTRA_CLEAN := *.pcap include ../../lib.mk diff --git a/tools/testing/selftests/netfilter/nft_concat_range.sh b/tools/testing/selftests/netfilter/nft_concat_range.sh index aca21dde102abbb05294594d8b3f7483873b87f5..5a4938d6dcf25a3f8137be799091f4f0d16ad7fd 100755 --- a/tools/testing/selftests/netfilter/nft_concat_range.sh +++ b/tools/testing/selftests/netfilter/nft_concat_range.sh @@ -13,11 +13,12 @@ KSELFTEST_SKIP=4 # Available test groups: +# - reported_issues: check for issues that were reported in the past # - correctness: check that packets match given entries, and only those # - concurrency: attempt races between insertion, deletion and lookup # - timeout: check that packets match entries until they expire # - performance: estimate matching rate, compare with rbtree and hash baselines -TESTS="correctness concurrency timeout" +TESTS="reported_issues correctness concurrency timeout" [ "${quicktest}" != "1" ] && TESTS="${TESTS} performance" # Set types, defined by TYPE_ variables below @@ -25,6 +26,9 @@ TYPES="net_port port_net net6_port port_proto net6_port_mac net6_port_mac_proto net_port_net net_mac net_mac_icmp net6_mac_icmp net6_port_net6_port net_port_mac_proto_net" +# Reported bugs, also described by TYPE_ variables below +BUGS="flush_remove_add" + # List of possible paths to pktgen script from kernel tree for performance tests PKTGEN_SCRIPT_PATHS=" ../../../samples/pktgen/pktgen_bench_xmit_mode_netif_receive.sh @@ -327,6 +331,12 @@ flood_spec ip daddr . tcp dport . meta l4proto . ip saddr perf_duration 0 " +# Definition of tests for bugs reported in the past: +# display display text for test report +TYPE_flush_remove_add=" +display Add two elements, flush, re-add +" + # Set template for all tests, types and rules are filled in depending on test set_template=' flush ruleset @@ -440,6 +450,8 @@ setup_set() { # Check that at least one of the needed tools is available check_tools() { + [ -z "${tools}" ] && return 0 + __tools= for tool in ${tools}; do if [ "${tool}" = "nc" ] && [ "${proto}" = "udp6" ] && \ @@ -1025,7 +1037,7 @@ format_noconcat() { add() { if ! nft add element inet filter test "${1}"; then err "Failed to add ${1} given ruleset:" - err "$(nft list ruleset -a)" + err "$(nft -a list ruleset)" return 1 fi } @@ -1045,7 +1057,7 @@ add_perf() { add_perf_norange() { if ! nft add element netdev perf norange "${1}"; then err "Failed to add ${1} given ruleset:" - err "$(nft list ruleset -a)" + err "$(nft -a list ruleset)" return 1 fi } @@ -1054,7 +1066,7 @@ add_perf_norange() { add_perf_noconcat() { if ! nft add element netdev perf noconcat "${1}"; then err "Failed to add ${1} given ruleset:" - err "$(nft list ruleset -a)" + err "$(nft -a list ruleset)" return 1 fi } @@ -1063,7 +1075,7 @@ add_perf_noconcat() { del() { if ! nft delete element inet filter test "${1}"; then err "Failed to delete ${1} given ruleset:" - err "$(nft list ruleset -a)" + err "$(nft -a list ruleset)" return 1 fi } @@ -1134,7 +1146,7 @@ send_match() { err " $(for f in ${src}; do eval format_\$f "${2}"; printf ' '; done)" err "should have matched ruleset:" - err "$(nft list ruleset -a)" + err "$(nft -a list ruleset)" return 1 fi nft reset counter inet filter test >/dev/null @@ -1160,7 +1172,7 @@ send_nomatch() { err " $(for f in ${src}; do eval format_\$f "${2}"; printf ' '; done)" err "should not have matched ruleset:" - err "$(nft list ruleset -a)" + err "$(nft -a list ruleset)" return 1 fi } @@ -1430,6 +1442,23 @@ test_performance() { kill "${perf_pid}" } +test_bug_flush_remove_add() { + set_cmd='{ set s { type ipv4_addr . inet_service; flags interval; }; }' + elem1='{ 10.0.0.1 . 22-25, 10.0.0.1 . 10-20 }' + elem2='{ 10.0.0.1 . 10-20, 10.0.0.1 . 22-25 }' + for i in `seq 1 100`; do + nft add table t ${set_cmd} || return ${KSELFTEST_SKIP} + nft add element t s ${elem1} 2>/dev/null || return 1 + nft flush set t s 2>/dev/null || return 1 + nft add element t s ${elem2} 2>/dev/null || return 1 + done + nft flush ruleset +} + +test_reported_issues() { + eval test_bug_"${subtest}" +} + # Run everything in a separate network namespace [ "${1}" != "run" ] && { unshare -n "${0}" run; exit $?; } tmp="$(mktemp)" @@ -1438,9 +1467,15 @@ trap cleanup EXIT # Entry point for test runs passed=0 for name in ${TESTS}; do - printf "TEST: %s\n" "${name}" - for type in ${TYPES}; do - eval desc=\$TYPE_"${type}" + printf "TEST: %s\n" "$(echo ${name} | tr '_' ' ')" + if [ "${name}" = "reported_issues" ]; then + SUBTESTS="${BUGS}" + else + SUBTESTS="${TYPES}" + fi + + for subtest in ${SUBTESTS}; do + eval desc=\$TYPE_"${subtest}" IFS=' ' for __line in ${desc}; do diff --git a/tools/testing/selftests/openat2/helpers.c b/tools/testing/selftests/openat2/helpers.c index e9a6557ab16f3b347d98d84d80d008f2488c7bdd..5074681ffdc995dbe3cc903550ef63f3385ba25a 100644 --- a/tools/testing/selftests/openat2/helpers.c +++ b/tools/testing/selftests/openat2/helpers.c @@ -46,7 +46,7 @@ int sys_renameat2(int olddirfd, const char *oldpath, int touchat(int dfd, const char *path) { - int fd = openat(dfd, path, O_CREAT); + int fd = openat(dfd, path, O_CREAT, 0700); if (fd >= 0) close(fd); return fd; diff --git a/tools/testing/selftests/openat2/resolve_test.c b/tools/testing/selftests/openat2/resolve_test.c index 7a94b1da8e7bcf2a8413bad5abb3a2cb2de6ed8d..bbafad440893cba427168d42fe3e1620a8dc00e5 100644 --- a/tools/testing/selftests/openat2/resolve_test.c +++ b/tools/testing/selftests/openat2/resolve_test.c @@ -230,7 +230,7 @@ void test_openat2_opath_tests(void) { .name = "[in_root] garbage link to /root", .path = "cheeky/garbageself", .how.resolve = RESOLVE_IN_ROOT, .out.path = "root", .pass = true }, - { .name = "[in_root] chainged garbage links to /root", + { .name = "[in_root] chained garbage links to /root", .path = "abscheeky/garbageself", .how.resolve = RESOLVE_IN_ROOT, .out.path = "root", .pass = true }, { .name = "[in_root] relative path to 'root'", diff --git a/tools/testing/selftests/pidfd/.gitignore b/tools/testing/selftests/pidfd/.gitignore index 3a779c084d965087a0e08d7ffd88b5c39a0c8119..39559d723c41808a4bdce9662c9b0de721f12e92 100644 --- a/tools/testing/selftests/pidfd/.gitignore +++ b/tools/testing/selftests/pidfd/.gitignore @@ -2,4 +2,5 @@ pidfd_open_test pidfd_poll_test pidfd_test pidfd_wait +pidfd_fdinfo_test pidfd_getfd_test diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index d6469535630af888051a9c50e8059a8a2abfac8a..2af9d39a97168c14dc4c008d59017d45146ff5bf 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -4,7 +4,7 @@ ifneq ($(shell $(CC) --version 2>&1 | head -n 1 | grep clang),) CLANG_FLAGS += -no-integrated-as endif -CFLAGS += -O2 -Wall -g -I./ -I../../../../usr/include/ -L./ -Wl,-rpath=./ \ +CFLAGS += -O2 -Wall -g -I./ -I../../../../usr/include/ -L$(OUTPUT) -Wl,-rpath=./ \ $(CLANG_FLAGS) LDLIBS += -lpthread @@ -19,6 +19,8 @@ TEST_GEN_PROGS_EXTENDED = librseq.so TEST_PROGS = run_param_test.sh +TEST_FILES := settings + include ../lib.mk $(OUTPUT)/librseq.so: rseq.c rseq.h rseq-*.h diff --git a/tools/testing/selftests/rtc/Makefile b/tools/testing/selftests/rtc/Makefile index de9c8566672ae7e4bd7d6d7c321455ff5525b5a2..55198ecc04dbea93c4fb358ebac715527e2755d4 100644 --- a/tools/testing/selftests/rtc/Makefile +++ b/tools/testing/selftests/rtc/Makefile @@ -1,9 +1,11 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS += -O3 -Wl,-no-as-needed -Wall -LDFLAGS += -lrt -lpthread -lm +LDLIBS += -lrt -lpthread -lm TEST_GEN_PROGS = rtctest TEST_GEN_PROGS_EXTENDED = setdate +TEST_FILES := settings + include ../lib.mk diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config index 477bc61b374a5e4e4cdfb31f1b750d512e7c84f0..c03af46002818234020d58a55bf9a7ac116acfd1 100644 --- a/tools/testing/selftests/tc-testing/config +++ b/tools/testing/selftests/tc-testing/config @@ -57,3 +57,4 @@ CONFIG_NET_IFE_SKBMARK=m CONFIG_NET_IFE_SKBPRIO=m CONFIG_NET_IFE_SKBTCINDEX=m CONFIG_NET_SCH_FIFO=y +CONFIG_NET_SCH_ETS=m diff --git a/tools/testing/selftests/timens/Makefile b/tools/testing/selftests/timens/Makefile index e9fb30bd8aeb3c0ed846ccdd2aeaf18cb6723592..b4fd9a9346547c71e8331d0ccb165ada9200d15e 100644 --- a/tools/testing/selftests/timens/Makefile +++ b/tools/testing/selftests/timens/Makefile @@ -2,6 +2,6 @@ TEST_GEN_PROGS := timens timerfd timer clock_nanosleep procfs exec TEST_GEN_PROGS_EXTENDED := gettime_perf CFLAGS := -Wall -Werror -pthread -LDFLAGS := -lrt -ldl +LDLIBS := -lrt -ldl include ../lib.mk diff --git a/tools/testing/selftests/tpm2/test_smoke.sh b/tools/testing/selftests/tpm2/test_smoke.sh index 8155c2ea7ccbb6ed1b9685f3c602105eb2c26173..b630c7b5950a960b95a9bb0aeda79e41924ca989 100755 --- a/tools/testing/selftests/tpm2/test_smoke.sh +++ b/tools/testing/selftests/tpm2/test_smoke.sh @@ -1,8 +1,17 @@ #!/bin/bash # SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) +self.flags = flags -python -m unittest -v tpm2_tests.SmokeTest -python -m unittest -v tpm2_tests.AsyncTest +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + + +if [ -f /dev/tpm0 ] ; then + python -m unittest -v tpm2_tests.SmokeTest + python -m unittest -v tpm2_tests.AsyncTest +else + exit $ksft_skip +fi CLEAR_CMD=$(which tpm2_clear) if [ -n $CLEAR_CMD ]; then diff --git a/tools/testing/selftests/tpm2/test_space.sh b/tools/testing/selftests/tpm2/test_space.sh index a6f5e346635e560db7c7767b22f32f760922600a..180b469c53b47d4e0e2e3d7c6bb2ecc7331065e2 100755 --- a/tools/testing/selftests/tpm2/test_space.sh +++ b/tools/testing/selftests/tpm2/test_space.sh @@ -1,4 +1,11 @@ #!/bin/bash # SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) -python -m unittest -v tpm2_tests.SpaceTest +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +if [ -f /dev/tpmrm0 ] ; then + python -m unittest -v tpm2_tests.SpaceTest +else + exit $ksft_skip +fi diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests index a692ea8283177dc8716ae6af24c2b7684471e4c4..f337148431980b821b058a87fb73bd3679d0b316 100755 --- a/tools/testing/selftests/vm/run_vmtests +++ b/tools/testing/selftests/vm/run_vmtests @@ -112,6 +112,17 @@ echo "NOTE: The above hugetlb tests provide minimal coverage. Use" echo " https://github.com/libhugetlbfs/libhugetlbfs.git for" echo " hugetlb regression testing." +echo "---------------------------" +echo "running map_fixed_noreplace" +echo "---------------------------" +./map_fixed_noreplace +if [ $? -ne 0 ]; then + echo "[FAIL]" + exitcode=1 +else + echo "[PASS]" +fi + echo "-------------------" echo "running userfaultfd" echo "-------------------" @@ -186,6 +197,17 @@ else echo "[PASS]" fi +echo "-------------------------" +echo "running mlock-random-test" +echo "-------------------------" +./mlock-random-test +if [ $? -ne 0 ]; then + echo "[FAIL]" + exitcode=1 +else + echo "[PASS]" +fi + echo "--------------------" echo "running mlock2-tests" echo "--------------------" @@ -197,6 +219,17 @@ else echo "[PASS]" fi +echo "-----------------" +echo "running thuge-gen" +echo "-----------------" +./thuge-gen +if [ $? -ne 0 ]; then + echo "[FAIL]" + exitcode=1 +else + echo "[PASS]" +fi + if [ $VADDR64 -ne 0 ]; then echo "-----------------------------" echo "running virtual_address_range" diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh index f5ab1cda8bb55c49ae30ae91919b33922d5f240e..138d46b3f3306bce463da910cd2f37066655f24b 100755 --- a/tools/testing/selftests/wireguard/netns.sh +++ b/tools/testing/selftests/wireguard/netns.sh @@ -24,6 +24,7 @@ set -e exec 3>&1 +export LANG=C export WG_HIDE_KEYS=never netns0="wg-test-$$-0" netns1="wg-test-$$-1" @@ -297,7 +298,17 @@ ip1 -4 rule add table main suppress_prefixlength 0 n1 ping -W 1 -c 100 -f 192.168.99.7 n1 ping -W 1 -c 100 -f abab::1111 +# Have ns2 NAT into wg0 packets from ns0, but return an icmp error along the right route. +n2 iptables -t nat -A POSTROUTING -s 10.0.0.0/24 -d 192.168.241.0/24 -j SNAT --to 192.168.241.2 +n0 iptables -t filter -A INPUT \! -s 10.0.0.0/24 -i vethrs -j DROP # Manual rpfilter just to be explicit. +n2 bash -c 'printf 1 > /proc/sys/net/ipv4/ip_forward' +ip0 -4 route add 192.168.241.1 via 10.0.0.100 +n2 wg set wg0 peer "$pub1" remove +[[ $(! n0 ping -W 1 -c 1 192.168.241.1 || false) == *"From 10.0.0.100 icmp_seq=1 Destination Host Unreachable"* ]] + n0 iptables -t nat -F +n0 iptables -t filter -F +n2 iptables -t nat -F ip0 link del vethrc ip0 link del vethrs ip1 link del wg0 diff --git a/tools/testing/selftests/wireguard/qemu/Makefile b/tools/testing/selftests/wireguard/qemu/Makefile index f10aa3590adc425b4d564eb91adfe4a77250e1bd..28d477683e8abe3c492274f7a71c8b48f9bda00e 100644 --- a/tools/testing/selftests/wireguard/qemu/Makefile +++ b/tools/testing/selftests/wireguard/qemu/Makefile @@ -38,19 +38,17 @@ endef define file_download = $(DISTFILES_PATH)/$(1): mkdir -p $(DISTFILES_PATH) - flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp' - if echo "$(3) $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi + flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp; [ -f $$@.tmp ] || exit 1; if echo "$(3) $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi' endef $(eval $(call tar_download,MUSL,musl,1.1.24,.tar.gz,https://www.musl-libc.org/releases/,1370c9a812b2cf2a7d92802510cca0058cc37e66a7bedd70051f0a34015022a3)) -$(eval $(call tar_download,LIBMNL,libmnl,1.0.4,.tar.bz2,https://www.netfilter.org/projects/libmnl/files/,171f89699f286a5854b72b91d06e8f8e3683064c5901fb09d954a9ab6f551f81)) $(eval $(call tar_download,IPERF,iperf,3.7,.tar.gz,https://downloads.es.net/pub/iperf/,d846040224317caf2f75c843d309a950a7db23f9b44b94688ccbe557d6d1710c)) $(eval $(call tar_download,BASH,bash,5.0,.tar.gz,https://ftp.gnu.org/gnu/bash/,b4a80f2ac66170b2913efbfb9f2594f1f76c7b1afd11f799e22035d63077fb4d)) $(eval $(call tar_download,IPROUTE2,iproute2,5.4.0,.tar.xz,https://www.kernel.org/pub/linux/utils/net/iproute2/,fe97aa60a0d4c5ac830be18937e18dc3400ca713a33a89ad896ff1e3d46086ae)) $(eval $(call tar_download,IPTABLES,iptables,1.8.4,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,993a3a5490a544c2cbf2ef15cf7e7ed21af1845baf228318d5c36ef8827e157c)) $(eval $(call tar_download,NMAP,nmap,7.80,.tar.bz2,https://nmap.org/dist/,fcfa5a0e42099e12e4bf7a68ebe6fde05553383a682e816a7ec9256ab4773faa)) $(eval $(call tar_download,IPUTILS,iputils,s20190709,.tar.gz,https://github.com/iputils/iputils/archive/s20190709.tar.gz/#,a15720dd741d7538dd2645f9f516d193636ae4300ff7dbc8bfca757bf166490a)) -$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20191226,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,aa8af0fdc9872d369d8c890a84dbc2a2466b55795dccd5b47721b2d97644b04f)) +$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20200206,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,f5207248c6a3c3e3bfc9ab30b91c1897b00802ed861e1f9faaed873366078c64)) KERNEL_BUILD_PATH := $(BUILD_PATH)/kernel$(if $(findstring yes,$(DEBUG_KERNEL)),-debug) rwildcard=$(foreach d,$(wildcard $1*),$(call rwildcard,$d/,$2) $(filter $(subst *,%,$2),$d)) @@ -295,21 +293,13 @@ $(IPERF_PATH)/src/iperf3: | $(IPERF_PATH)/.installed $(USERSPACE_DEPS) $(MAKE) -C $(IPERF_PATH) $(STRIP) -s $@ -$(LIBMNL_PATH)/.installed: $(LIBMNL_TAR) - flock -s $<.lock tar -C $(BUILD_PATH) -xf $< - touch $@ - -$(LIBMNL_PATH)/src/.libs/libmnl.a: | $(LIBMNL_PATH)/.installed $(USERSPACE_DEPS) - cd $(LIBMNL_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared - $(MAKE) -C $(LIBMNL_PATH) - sed -i 's:prefix=.*:prefix=$(LIBMNL_PATH):' $(LIBMNL_PATH)/libmnl.pc - $(WIREGUARD_TOOLS_PATH)/.installed: $(WIREGUARD_TOOLS_TAR) + mkdir -p $(BUILD_PATH) flock -s $<.lock tar -C $(BUILD_PATH) -xf $< touch $@ -$(WIREGUARD_TOOLS_PATH)/src/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) - LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src LIBMNL_CFLAGS="-I$(LIBMNL_PATH)/include" LIBMNL_LDLIBS="-lmnl" wg +$(WIREGUARD_TOOLS_PATH)/src/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(USERSPACE_DEPS) + $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src wg $(STRIP) -s $@ $(BUILD_PATH)/init: init.c | $(USERSPACE_DEPS) @@ -340,17 +330,17 @@ $(BASH_PATH)/bash: | $(BASH_PATH)/.installed $(USERSPACE_DEPS) $(IPROUTE2_PATH)/.installed: $(IPROUTE2_TAR) mkdir -p $(BUILD_PATH) flock -s $<.lock tar -C $(BUILD_PATH) -xf $< - printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=y\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS -DHAVE_LIBMNL -I$(LIBMNL_PATH)/include\nLDLIBS+=-lmnl' > $(IPROUTE2_PATH)/config.mk + printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=n\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS\n' > $(IPROUTE2_PATH)/config.mk printf 'lib: snapshot\n\t$$(MAKE) -C lib\nip/ip: lib\n\t$$(MAKE) -C ip ip\nmisc/ss: lib\n\t$$(MAKE) -C misc ss\n' >> $(IPROUTE2_PATH)/Makefile touch $@ -$(IPROUTE2_PATH)/ip/ip: | $(IPROUTE2_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) - LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ ip/ip - $(STRIP) -s $(IPROUTE2_PATH)/ip/ip +$(IPROUTE2_PATH)/ip/ip: | $(IPROUTE2_PATH)/.installed $(USERSPACE_DEPS) + $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ ip/ip + $(STRIP) -s $@ -$(IPROUTE2_PATH)/misc/ss: | $(IPROUTE2_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) - LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ misc/ss - $(STRIP) -s $(IPROUTE2_PATH)/misc/ss +$(IPROUTE2_PATH)/misc/ss: | $(IPROUTE2_PATH)/.installed $(USERSPACE_DEPS) + $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ misc/ss + $(STRIP) -s $@ $(IPTABLES_PATH)/.installed: $(IPTABLES_TAR) mkdir -p $(BUILD_PATH) @@ -358,8 +348,8 @@ $(IPTABLES_PATH)/.installed: $(IPTABLES_TAR) sed -i -e "/nfnetlink=[01]/s:=[01]:=0:" -e "/nfconntrack=[01]/s:=[01]:=0:" $(IPTABLES_PATH)/configure touch $@ -$(IPTABLES_PATH)/iptables/xtables-legacy-multi: | $(IPTABLES_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) - cd $(IPTABLES_PATH) && PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --disable-nftables --disable-bpf-compiler --disable-nfsynproxy --disable-libipq --with-kernel=$(BUILD_PATH)/include +$(IPTABLES_PATH)/iptables/xtables-legacy-multi: | $(IPTABLES_PATH)/.installed $(USERSPACE_DEPS) + cd $(IPTABLES_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --disable-nftables --disable-bpf-compiler --disable-nfsynproxy --disable-libipq --disable-connlabel --with-kernel=$(BUILD_PATH)/include $(MAKE) -C $(IPTABLES_PATH) $(STRIP) -s $@ diff --git a/usr/Kconfig b/usr/Kconfig index bdf5bbd40727e7bd3af324ea8c37894c732d5993..96afb03b65f97db76091de047b98b1ba409c92ea 100644 --- a/usr/Kconfig +++ b/usr/Kconfig @@ -124,17 +124,6 @@ choice If in doubt, select 'None' -config INITRAMFS_COMPRESSION_NONE - bool "None" - help - Do not compress the built-in initramfs at all. This may sound wasteful - in space, but, you should be aware that the built-in initramfs will be - compressed at a later stage anyways along with the rest of the kernel, - on those architectures that support this. However, not compressing the - initramfs may lead to slightly higher memory consumption during a - short time at boot, while both the cpio image and the unpacked - filesystem image will be present in memory simultaneously - config INITRAMFS_COMPRESSION_GZIP bool "Gzip" depends on RD_GZIP @@ -207,4 +196,15 @@ config INITRAMFS_COMPRESSION_LZ4 If you choose this, keep in mind that most distros don't provide lz4 by default which could cause a build failure. +config INITRAMFS_COMPRESSION_NONE + bool "None" + help + Do not compress the built-in initramfs at all. This may sound wasteful + in space, but, you should be aware that the built-in initramfs will be + compressed at a later stage anyways along with the rest of the kernel, + on those architectures that support this. However, not compressing the + initramfs may lead to slightly higher memory consumption during a + short time at boot, while both the cpio image and the unpacked + filesystem image will be present in memory simultaneously + endchoice diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index d65a0faa46d8977e4ecfa3e36a722bb506ab3924..eda7b624eab8c46250789267a2118c50affab453 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -742,9 +742,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) guest_enter_irqoff(); if (has_vhe()) { - kvm_arm_vhe_guest_enter(); ret = kvm_vcpu_run_vhe(vcpu); - kvm_arm_vhe_guest_exit(); } else { ret = kvm_call_hyp_ret(__kvm_vcpu_run_nvhe, vcpu); } diff --git a/virt/kvm/arm/trace.h b/virt/kvm/arm/trace.h index 204d210d01c29a3282e16ec7c6ed21d25dc315c3..cc94ccc688217c7fa337e01d74ca1378f31699c1 100644 --- a/virt/kvm/arm/trace.h +++ b/virt/kvm/arm/trace.h @@ -4,6 +4,7 @@ #include #include +#include #undef TRACE_SYSTEM #define TRACE_SYSTEM kvm diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c index d656ebd5f9d4614deab7668c2c091c8ab644c038..97fb2a40e6ba193efc51fa1cf0c05bb0815db648 100644 --- a/virt/kvm/arm/vgic/vgic-mmio.c +++ b/virt/kvm/arm/vgic/vgic-mmio.c @@ -179,18 +179,6 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, return value; } -/* - * This function will return the VCPU that performed the MMIO access and - * trapped from within the VM, and will return NULL if this is a userspace - * access. - * - * We can disable preemption locally around accessing the per-CPU variable, - * and use the resolved vcpu pointer after enabling preemption again, because - * even if the current thread is migrated to another CPU, reading the per-CPU - * value later will give us the same value as we update the per-CPU variable - * in the preempt notifier handlers. - */ - /* Must be called with irq->irq_lock held */ static void vgic_hw_irq_spending(struct kvm_vcpu *vcpu, struct vgic_irq *irq, bool is_uaccess) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 67ae2d5c37b238749aa153485d6bbbe855f8f108..70f03ce0e5c1d547beaa2d206ce6687f292a3b48 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -4409,12 +4409,22 @@ static void kvm_sched_out(struct preempt_notifier *pn, /** * kvm_get_running_vcpu - get the vcpu running on the current CPU. - * Thanks to preempt notifiers, this can also be called from - * preemptible context. + * + * We can disable preemption locally around accessing the per-CPU variable, + * and use the resolved vcpu pointer after enabling preemption again, + * because even if the current thread is migrated to another CPU, reading + * the per-CPU value later will give us the same value as we update the + * per-CPU variable in the preempt notifier handlers. */ struct kvm_vcpu *kvm_get_running_vcpu(void) { - return __this_cpu_read(kvm_running_vcpu); + struct kvm_vcpu *vcpu; + + preempt_disable(); + vcpu = __this_cpu_read(kvm_running_vcpu); + preempt_enable(); + + return vcpu; } /**