- Kernel - mailweb.openeuler.org

[PATCH openEuler-26.09] tools: Add maio-utils tool
by Hongbo Li 16 Mar '26

16 Mar '26

hulk inclusion category: feature bugzilla: https://atomgit.com/openeuler/kernel/issues/8613 -------------------------------- This is a userspace tool for MFS to provide: programmable strategy framework. Some basic strategies have added in test, and more flexible strategies can be written based on this framework. Signed-off-by: Hongbo Li <lihongbo22(a)huawei.com> --- tools/mfs/maio-utils/CMakeLists.txt | 101 ++++ tools/mfs/maio-utils/README.md | 17 + tools/mfs/maio-utils/build/build.sh | 91 +++ .../mfs/maio-utils/include/client/fs_client.h | 17 + tools/mfs/maio-utils/include/inner/inner.h | 37 ++ tools/mfs/maio-utils/include/loader/loader.h | 10 + tools/mfs/maio-utils/include/maio.h | 53 ++ .../maio-utils/include/parser/req_parser.h | 13 + tools/mfs/maio-utils/include/policy/policy.h | 17 + tools/mfs/maio-utils/include/uapi/mfs.h | 62 ++ tools/mfs/maio-utils/src/CMakeLists.txt | 42 ++ .../mfs/maio-utils/src/client/CMakeLists.txt | 17 + tools/mfs/maio-utils/src/client/fs_client.c | 359 ++++++++++++ .../mfs/maio-utils/src/loader/CMakeLists.txt | 18 + tools/mfs/maio-utils/src/loader/loader.c | 144 +++++ tools/mfs/maio-utils/src/main.c | 156 +++++ .../mfs/maio-utils/src/parser/CMakeLists.txt | 16 + tools/mfs/maio-utils/src/parser/req_parser.c | 313 ++++++++++ .../mfs/maio-utils/src/policy/CMakeLists.txt | 16 + tools/mfs/maio-utils/src/policy/policy.c | 114 ++++ tools/mfs/maio-utils/test/Makefile | 26 + tools/mfs/maio-utils/test/README.md | 61 ++ tools/mfs/maio-utils/test/strategy_demo.c | 45 ++ .../mfs/maio-utils/test/strategy_generate.cpp | 296 ++++++++++ .../mfs/maio-utils/test/strategy_prefetch.cpp | 150 +++++ tools/mfs/maio-utils/test/strategy_prefetch.h | 21 + tools/mfs/maio-utils/test/strategy_replay.cpp | 540 ++++++++++++++++++ tools/mfs/maio-utils/test/strategy_template.h | 21 + tools/mfs/maio-utils/test/strategy_toend.c | 46 ++ tools/mfs/maio-utils/test/trace_analyse.py | 87 +++ tools/mfs/maio-utils/test/trace_gen.py | 116 ++++ 31 files changed, 3022 insertions(+) create mode 100644 tools/mfs/maio-utils/CMakeLists.txt create mode 100644 tools/mfs/maio-utils/README.md create mode 100644 tools/mfs/maio-utils/build/build.sh create mode 100644 tools/mfs/maio-utils/include/client/fs_client.h create mode 100644 tools/mfs/maio-utils/include/inner/inner.h create mode 100644 tools/mfs/maio-utils/include/loader/loader.h create mode 100644 tools/mfs/maio-utils/include/maio.h create mode 100644 tools/mfs/maio-utils/include/parser/req_parser.h create mode 100644 tools/mfs/maio-utils/include/policy/policy.h create mode 100644 tools/mfs/maio-utils/include/uapi/mfs.h create mode 100644 tools/mfs/maio-utils/src/CMakeLists.txt create mode 100644 tools/mfs/maio-utils/src/client/CMakeLists.txt create mode 100644 tools/mfs/maio-utils/src/client/fs_client.c create mode 100644 tools/mfs/maio-utils/src/loader/CMakeLists.txt create mode 100644 tools/mfs/maio-utils/src/loader/loader.c create mode 100644 tools/mfs/maio-utils/src/main.c create mode 100644 tools/mfs/maio-utils/src/parser/CMakeLists.txt create mode 100644 tools/mfs/maio-utils/src/parser/req_parser.c create mode 100644 tools/mfs/maio-utils/src/policy/CMakeLists.txt create mode 100644 tools/mfs/maio-utils/src/policy/policy.c create mode 100644 tools/mfs/maio-utils/test/Makefile create mode 100644 tools/mfs/maio-utils/test/README.md create mode 100644 tools/mfs/maio-utils/test/strategy_demo.c create mode 100644 tools/mfs/maio-utils/test/strategy_generate.cpp create mode 100644 tools/mfs/maio-utils/test/strategy_prefetch.cpp create mode 100644 tools/mfs/maio-utils/test/strategy_prefetch.h create mode 100644 tools/mfs/maio-utils/test/strategy_replay.cpp create mode 100644 tools/mfs/maio-utils/test/strategy_template.h create mode 100644 tools/mfs/maio-utils/test/strategy_toend.c create mode 100644 tools/mfs/maio-utils/test/trace_analyse.py create mode 100644 tools/mfs/maio-utils/test/trace_gen.py diff --git a/tools/mfs/maio-utils/CMakeLists.txt b/tools/mfs/maio-utils/CMakeLists.txt new file mode 100644 index 000000000000..f710e6c15f79 --- /dev/null +++ b/tools/mfs/maio-utils/CMakeLists.txt @@ -0,0 +1,101 @@ +#******************************************************************************* +#******************************************************************************* + +cmake_minimum_required(VERSION 3.0) +cmake_policy(SET CMP0057 NEW) + +project(maio) + +#******************************************************************************* +#******************************************************************************* + +add_definitions(-D__LINUX_USR__) +add_definitions(-D__USE_GNU) +add_definitions(-D__POSIX_SOURCE) +add_definitions(-D_GNU_SOURCE) +add_definitions(-D_FILE_OFFSET_BITS=64) + +#******************************************************************************* +#******************************************************************************* + +include(TestBigEndian) + +TEST_BIG_ENDIAN(BIGENDIAN) + if (${BIGENDIAN}) + message(">>> Big Endian") + add_definitions(-D_CMAKE_BIGENDIAN) + else() + message(">>> Little Endian") + endif(${BIGENDIAN}) + +#******************************************************************************* +#******************************************************************************* + +EXECUTE_PROCESS(COMMAND uname -m COMMAND tr -d '\n' OUTPUT_VARIABLE ARCH) +if(${ARCH} STREQUAL "x86_64" OR ${ARCH} STREQUAL "aarch64") + message(STATUS "Architecture: ${ARCH}") +else() + message(STATUS "Invaild Architecture: ${ARCH}") + return() +endif() + +#******************************************************************************* +#******************************************************************************* + +set(BASE_FLAGS "-g -Wall -Werror -fno-strict-overflow -rdynamic") +set(SP_C_FLAGS "-std=gnu99") +set(SP_C++_FLAGS "-std=c++11") +set(SP_RELEASE_FLAGS "-O2") +set(SP_DEBUG_FLAGS "-O0") +set(SEC_REQ_FLAGS "-fstack-protector-all -fPIE -pie -fPIC -Wl,-z,relro,-z,now,-z,noexecstack") +set(SEC_SUG_BASE_FLAGS "-Wformat=2") +set(SEC_SUG_SP_C_FLAGS "-Wshadow") + +set(C_FLAGS "${BASE_FLAGS} ${SP_C_FLAGS}") +set(C++_FLAGS "${BASE_FLAGS} ${SP_C++_FLAGS}") +set(SEC_C_FLAGS "${SEC_REQ_FLAGS} ${SEC_SUG_BASE_FLAGS} ${SEC_SUG_SP_C_FLAGS}") +set(SEC_C++_FLAGS "${SEC_REQ_FLAGS} ${SEC_SUG_BASE_FLAGS}") +set(DEPC_FLAGS "-Wno-error=deprecated-declarations -Wno-deprecated-declarations") + +if(CMAKE_BUILD_TYPE MATCHES "Release") + message(">>> Release Mode") + set(CMAKE_C_FLAGS "${C_FLAGS} ${SP_RELEASE_FLAGS} ${SEC_C_FLAGS}") + set(CMAKE_CXX_FLAGS "${C++_FLAGS} ${SP_RELEASE_FLAGS} ${SEC_C++_FLAGS} ${DEPC_FLAGS}") +else() + message(">>> Debug Mode") + add_definitions(-D_DEBUG) + set(CMAKE_C_FLAGS "${C_FLAGS} ${SP_DEBUG_FLAGS} ${SEC_C_FLAGS}") + set(CMAKE_CXX_FLAGS "${C++_FLAGS} ${SP_DEBUG_FLAGS} ${SEC_C++_FLAGS} ${DEPC_FLAGS}") + set(COVERAGE_FLAGS "-coverage") + set(COVERAGE_LINK "gcov") +endif() + +message(STATUS ">>> Source Dir: " ${PROJECT_SOURCE_DIR}) +message(STATUS ">>> Binary Dir: " ${PROJECT_BINARY_DIR}) +message(STATUS ">>> C_FLAGS : " ${CMAKE_C_FLAGS}) +message(STATUS ">>> CXX_FLAGS : " ${CMAKE_CXX_FLAGS}) + +#******************************************************************************* +#******************************************************************************* + +set(EXECUTABLE_OUTPUT_PATH ${PROJECT_BINARY_DIR}/bin) + +#******************************************************************************* +#******************************************************************************* + +if(DEFINED THIRD_PARTY) + message(">>> third_party: ${THIRD_PARTY}") +else() + set(THIRD_PARTY ${PROJECT_SOURCE_DIR}/lib) +endif() + +set(INFRA_DIR ${PROJECT_SOURCE_DIR}/infrastructure) +set(SECUREC_DIR ${THIRD_PARTY}/securec) +set(ZLOG_DIR ${THIRD_PARTY}/zlog) +set(LIBNUMA_DIR ${THIRD_PARTY}/libnuma) + +#******************************************************************************* +#******************************************************************************* + +add_subdirectory(infrastructure) +add_subdirectory(src) diff --git a/tools/mfs/maio-utils/README.md b/tools/mfs/maio-utils/README.md new file mode 100644 index 000000000000..4c5a66a83c60 --- /dev/null +++ b/tools/mfs/maio-utils/README.md @@ -0,0 +1,17 @@ +# maio-utils + +#### How to build + +1. prepare thirdparty by using: +``` +git clone -b threadpool_bind https://github.com/hb-lee/infrastructure.git infrastructure +git clone -b 1.2.18 https://github.com/HardySimpson/zlog.git thirdparty/zlog +git clone https://github.com/chriszt/securec.git thirdparty/securec +git clone -b v2.0.19 https://github.com/numactl/numactl.git thirdparty/libnuma +``` +2. cd build +3. bash build.sh prepare # only once. +4. bash build.sh build + +#### How to run +Run with `./maio -m ${MNTPOINT}`, here ${MNTPOINT} means the mfs mount point. If you want to use some strategies, you can run with `./maio -m ${MNTPOINT} -s ${STRATEGYLIB}` where ${STRATEGYLIB} is your strategy library. Some examples are provided in `test` directory. diff --git a/tools/mfs/maio-utils/build/build.sh b/tools/mfs/maio-utils/build/build.sh new file mode 100644 index 000000000000..91b49d3d6bf8 --- /dev/null +++ b/tools/mfs/maio-utils/build/build.sh @@ -0,0 +1,91 @@ +#!/bin/bash + +LOCAL_PATH="$(readlink -e "$(dirname "$0")")" +PRJ_PATH="$(readlink -e "${LOCAL_PATH}/..")" +THIRD_SUB="${PRJ_PATH}/thirdparty" +Lib_PATH="${PRJ_PATH}/lib" + +ARCH=$(uname -m) + +function build_zlog() { + local zlog_dir=${THIRD_SUB}/zlog + local build_path=${zlog_dir}/build + mkdir ${build_path} + mkdir -p ${Lib_PATH}/zlog + cd ${zlog_dir} + make PREFIX=`pwd`/build/zlog + make PREFIX=`pwd`/build/zlog install + cp -rdp ${build_path}/zlog/include ${Lib_PATH}/zlog + cp -rdp ${build_path}/zlog/lib ${Lib_PATH}/zlog + cd - +} + +function build_securec() { + local securec_dir=${THIRD_SUB}/securec + local securec_lib=${securec_dir}/build/securec/lib + mkdir -p ${securec_lib} + mkdir -p ${Lib_PATH}/securec + cd ${securec_dir} + if [ "${ARCH}" = "aarch64" ]; then + make -f aarch64-so.mk + else + make -f x86-so.mk + fi + cp -rdp include build/securec + cp libsecurec.so build/securec/lib + cp -rdp build/securec/include ${Lib_PATH}/securec + cp -rdp build/securec/lib ${Lib_PATH}/securec + cd - +} + +function build_libnuma() { + local libnuma_dir=${THIRD_SUB}/libnuma + local build_path=${libnuma_dir}/build + mkdir ${build_path} + mkdir -p ${Lib_PATH}/libnuma + cd ${libnuma_dir} + ./autogen.sh + ./configure --prefix=`pwd`/build + make -j4 + make install + cp -rdp build/include ${Lib_PATH}/libnuma + cp -rdp build/lib ${Lib_PATH}/libnuma + cd - +} + +function prepare_thirdparty() { + build_jsoncpp + build_zlog + build_securec + build_libnuma +} + +function build_program() { + local BUILD_TYPE=$1 + + set -x + if [ "${BUILD_TYPE}" == "release" ]; then + cmake .. -DCMAKE_BUILD_TYPE=Release + else + cmake .. -DCMAKE_BUILD_TYPE=Debug + fi + set +x + + make clean + make VERBOSE=1 -j +} + +function main() { + local ACTION="$1" + local PARAMETER="$2" + + if [ "${ACTION}" == "prepare" ]; then + prepare_thirdparty + fi + if [ "$ACTION" == "build" ]; then + build_program $PARAMETER + fi +} + +main $@ +exit $? diff --git a/tools/mfs/maio-utils/include/client/fs_client.h b/tools/mfs/maio-utils/include/client/fs_client.h new file mode 100644 index 000000000000..803179ade14c --- /dev/null +++ b/tools/mfs/maio-utils/include/client/fs_client.h @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2025 Huawei Technologies Co., Ltd + */ +#ifndef _FS_CLIENT_H_ +#define _FS_CLIENT_H_ + +#include <stdint.h> + +int fs_evict_by_path(const char*path, uint64_t off, uint64_t len); +int fs_load_by_path(const char *path, uint64_t off, uint64_t len); +int fs_load_by_fd(int fd, uint64_t off, uint64_t len); +int fs_sync_by_path(const char *path, void *buf, uint64_t off, uint64_t len); + +int fs_client_init(const char *source); +void fs_client_exit(); + +#endif diff --git a/tools/mfs/maio-utils/include/inner/inner.h b/tools/mfs/maio-utils/include/inner/inner.h new file mode 100644 index 000000000000..c10f40a3712c --- /dev/null +++ b/tools/mfs/maio-utils/include/inner/inner.h @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2025 Huawei Technologies Co., Ltd + */ +#ifndef _INNER_H_ +#define _INNER_H_ + +#include <time.h> +#include <stdint.h> + +static inline uint64_t _get_ts() +{ + struct timespec now = {0}; + (void)clock_gettime(CLOCK_MONOTONIC_COARSE, &now); + return (uint64_t)now.tv_sec; +} + +/* io context for loader and writeback */ +struct io_context { + uint32_t id; /* msg id */ + uint64_t off; /* io offset in fd */ + uint64_t len; /* io length */ + uint16_t numaid; /* numa node of this io, -1 means non-bind */ + int fd; /* io file handle */ + char *path; /* fullpath of this io */ + void *buf; /* flighting buffer for writeback */ + + uint64_t seq; + + void *private; + void (*end_io)(int ret, void *private); +}; + +void loader_update_curseq(uint64_t seq); +int loader_evict_submit(struct io_context *ioctx); +int loader_io_submit(struct io_context *ioctx); + +#endif diff --git a/tools/mfs/maio-utils/include/loader/loader.h b/tools/mfs/maio-utils/include/loader/loader.h new file mode 100644 index 000000000000..ff280989f9f9 --- /dev/null +++ b/tools/mfs/maio-utils/include/loader/loader.h @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2025 Huawei Technologies Co., Ltd + */ +#ifndef _LOADER_H_ +#define _LOADER_H_ + +int loader_init(); +void loader_exit(); + +#endif diff --git a/tools/mfs/maio-utils/include/maio.h b/tools/mfs/maio-utils/include/maio.h new file mode 100644 index 000000000000..a508d5b1fa27 --- /dev/null +++ b/tools/mfs/maio-utils/include/maio.h @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2025 Huawei Technologies Co., Ltd + */ +#ifndef _MAIO_H_ +#define _MAIO_H_ + +#ifdef __cplusplus +extern "C" { +#endif + +#include <stdint.h> + +struct maio_entry { + char *fpath; + uint64_t toff; + uint64_t tlen; + uint8_t tnuma; + uint64_t seq; +}; + +struct maio { + /* IN */ + int fd; + uint64_t off; + uint64_t len; + int pid; + uint8_t op; + uint64_t ts; + uint32_t cksz; + + /* OUT */ + uint16_t flags; +#define MAIO_WITH_SEQ 0x0001 + uint64_t curseq; + struct maio_entry entries[]; +}; + +struct maio_operation { + int max_io; + int (*init) (void); + void (*exit) (void); + int (*load) (struct maio **io); + int (*evict) (struct maio **io); +}; + +char *_get_fullpath(char *fpath, int fd); +void maio_preload(struct maio *maio, int nio); + +#ifdef __cplusplus +} +#endif + +#endif diff --git a/tools/mfs/maio-utils/include/parser/req_parser.h b/tools/mfs/maio-utils/include/parser/req_parser.h new file mode 100644 index 000000000000..908e7297558a --- /dev/null +++ b/tools/mfs/maio-utils/include/parser/req_parser.h @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2025 Huawei Technologies Co., Ltd + */ +#ifndef __REQ_PARSER_H__ +#define __REQ_PARSER_H__ + +#include <stdint.h> + +int parser_init(uint32_t fs_mode, const char *mntpoint); +void parser_destory(); +int maio_parse_req(void *buf, int size); + +#endif diff --git a/tools/mfs/maio-utils/include/policy/policy.h b/tools/mfs/maio-utils/include/policy/policy.h new file mode 100644 index 000000000000..aef05c956b3b --- /dev/null +++ b/tools/mfs/maio-utils/include/policy/policy.h @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2025 Huawei Technologies Co., Ltd + */ +#ifndef _POLICY_H_ +#define _POLICY_H_ + +#include "maio.h" + +int policy_max_io(); +int policy_load(struct maio **io); +int policy_evict(struct maio **io); +int policy_register(const char *path); +void policy_unregister(); +int policy_init(); +void policy_exit(); + +#endif diff --git a/tools/mfs/maio-utils/include/uapi/mfs.h b/tools/mfs/maio-utils/include/uapi/mfs.h new file mode 100644 index 000000000000..a7d5882b5e50 --- /dev/null +++ b/tools/mfs/maio-utils/include/uapi/mfs.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ + +#ifndef _UAPI_LINUX_MFS_H +#define _UAPI_LINUX_MFS_H + +#include <linux/types.h> +#include <linux/ioctl.h> + +enum mfs_opcode { + MFS_OP_READ = 0, + MFS_OP_FAULT, + MFS_OP_FAROUND, +}; + +enum { + MFS_MODE_NONE = 0, + MFS_MODE_LOCAL, + MFS_MODE_REMOTE, +}; + +struct mfs_ioc_ra { + __u64 off; + __u64 len; +}; + +struct mfs_ioc_done { + __u32 id; + __u32 ret; +}; + +struct mfs_ioc_rpath { + __u16 max; + __u16 len; + __u8 d[]; +}; + +#define MFS_IOC_RA _IOW(0xbc, 1, struct mfs_ioc_ra) +#define MFS_IOC_DONE _IOW(0xbc, 2, struct mfs_ioc_done) +#define MFS_IOC_RPATH _IOWR(0xbc, 3, struct mfs_ioc_rpath) + +struct mfs_ioc_fsinfo { + __u8 mode; /* 0: none, 1: local, 2: remote */ +}; + +#define MFS_IOC_FSINFO _IOR(0xbd, 1, struct mfs_ioc_fsinfo) + +struct mfs_msg { + __u8 version; + __u8 opcode; + __u16 len; + __u32 fd; + __u32 id; + __u8 data[]; +}; + +struct mfs_read { + __u64 off; + __u64 len; + __s32 pid; +}; + +#endif /* _UAPI_LINUX_MFS_H */ diff --git a/tools/mfs/maio-utils/src/CMakeLists.txt b/tools/mfs/maio-utils/src/CMakeLists.txt new file mode 100644 index 000000000000..fd053a8bd081 --- /dev/null +++ b/tools/mfs/maio-utils/src/CMakeLists.txt @@ -0,0 +1,42 @@ +#******************************************************************************* +#******************************************************************************* + +include_directories(${PROJECT_SOURCE_DIR}/include) +include_directories(${PROJECT_SOURCE_DIR}/include/inner) +include_directories(${PROJECT_SOURCE_DIR}/include/uapi) +include_directories(${PROJECT_SOURCE_DIR}/include/client) +include_directories(${PROJECT_SOURCE_DIR}/include/loader) +include_directories(${PROJECT_SOURCE_DIR}/include/policy) +include_directories(${PROJECT_SOURCE_DIR}/include/monitor) +include_directories(${PROJECT_SOURCE_DIR}/include/parser) + +include_directories(${INFRA_DIR}/include) +include_directories(${SECUREC_DIR}/include) +include_directories(${ZLOG_DIR}/include) +include_directories(${LIBNUMA_DIR}/include) + +#******************************************************************************* +#******************************************************************************* + +link_directories(${PROJECT_BINARY_DIR}/lib) +link_directories(${SECUREC_DIR}/lib) +link_directories(${ZLOG_DIR}/lib) +link_directories(${LIBNUMA_DIR}/lib) + +#******************************************************************************* +#******************************************************************************* + +add_subdirectory(client) +add_subdirectory(loader) +add_subdirectory(policy) +add_subdirectory(parser) + +add_executable(maio-utils main.c) +target_link_libraries(maio-utils "-Wl,--whole-archive" + client + loader + policy + parser + "-Wl,--no-whole-archive" + infra + dl) diff --git a/tools/mfs/maio-utils/src/client/CMakeLists.txt b/tools/mfs/maio-utils/src/client/CMakeLists.txt new file mode 100644 index 000000000000..0fb67d64eb03 --- /dev/null +++ b/tools/mfs/maio-utils/src/client/CMakeLists.txt @@ -0,0 +1,17 @@ +#******************************************************************************* +#******************************************************************************* + +include_directories(${CMAKE_CURRENT_SOURCE_DIR}) + +#******************************************************************************* +#******************************************************************************* + +#aux_source_directory(. CLIENT_SRC) +set(CLIENT_SRC fs_client.c) + +#******************************************************************************* +#******************************************************************************* + +add_library(client ${CLIENT_SRC}) +target_link_libraries(client infra + securec) diff --git a/tools/mfs/maio-utils/src/client/fs_client.c b/tools/mfs/maio-utils/src/client/fs_client.c new file mode 100644 index 000000000000..5d359b8f22e1 --- /dev/null +++ b/tools/mfs/maio-utils/src/client/fs_client.c @@ -0,0 +1,359 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2025 Huawei Technologies Co., Ltd + */ +#include "fs_client.h" +#include "mfs.h" +#include "inner.h" +#include "hashmap.h" +#include "hashfunc.h" +#include "stimer.h" +#include "atomic.h" +#include "log.h" +#include "list.h" +#include "spinlock.h" +#include "sysdef.h" +#include "securec.h" + +#include <fcntl.h> +#include <errno.h> +#include <string.h> +#include <unistd.h> +#include <sys/ioctl.h> + +#define TIMER_CYCLE 10000 /* 10s */ +#define FD_TMOUT 3600 /* 60s */ + +struct fs_client { + int rootfd; + hashmap_t *map; + stimer_t *timer; + list_head_t head; + spinlock_t lock; + uint64_t tmout; +}; + +struct fs_client g_client = {0}; + +typedef struct { + uint32_t plen; + char *path; +} fdkey_t; + +typedef struct { + fdkey_t key; + int fd; + int ref; + uint64_t ts; + list_head_t link; + hashlink_t hash; +} fd_t; + +static inline int fd_cmp(void *first, void *second) +{ + fdkey_t *key1 = (fdkey_t *)first; + fdkey_t *key2 = (fdkey_t *)second; + + if (key1->plen != key2->plen) + return -1; + + return strcmp(key1->path, key2->path); +} + +static inline uint32_t fd_hash(void *args) +{ + fdkey_t *key = (fdkey_t *)args; + uint64_t hash = hashstr(key->path, key->plen); + + return (uint32_t)hash; +} + +static inline void fd_inc(void *args, hashlink_t *link) +{ + fd_t *f = container_of(link, fd_t, hash); + int ref = atomic_s32_inc(&f->ref); + if (ref <= 0) { + log_error("fd(%d) for path(%s) with invalid ref(%d)", + f->fd, f->key.path, ref); + sys_assert(0); + } +} + +static inline int fd_dec(void *args, hashlink_t *link) +{ + fd_t *f = container_of(link, fd_t, hash); + int ref = atomic_s32_dec(&f->ref); + + if (ref < 0) { + log_error("fd(%d) for path(%s) with invalid ref(%d)", + f->fd, f->key.path, ref); + sys_assert(0); + } + /* update access timestamp for the last one */ + if (ref == 0) + f->ts = _get_ts(); + return -1; +} + +static inline int fd_expire(void *args, hashlink_t *link) +{ + fd_t *f = container_of(link, fd_t, hash); + int ref = atomic_s32_fetch(&f->ref); + uint64_t cur; + + if (ref > 0) + return -1; + if (ref < 0) { + log_error("fd(%d) for path(%s) with invalid ref(%d)", + f->fd, f->key.path, ref); + sys_assert(0); + } + cur = _get_ts(); + return ((cur - f->ts) >= g_client.tmout) ? 0: -1; +} + +static fd_t *fd_alloc(const char *path) +{ + fd_t *f = (fd_t *)malloc(sizeof(fd_t)); + if (!f) { + log_error("alloc fd_t fail"); + return NULL; + } + + f->key.path = strdup(path); + if (!f->key.path) { + log_error("strdup(%s) fail", path); + free(f); + return NULL; + } + + f->key.plen = strlen(path) + 1; + f->fd = -1; + f->ref = 1; + f->hash.key = &f->key; + list_init(&f->link); + return f; +} + +static void fd_free(fd_t *f) +{ + if (f->fd > 0) { + int ret = close(f->fd); + if (ret != 0) { + log_error("close(%d) fail, err(%s)", f->fd, strerror(errno)); + } + f->fd = -1; + } + + if (f->key.path) { + free(f->key.path); + f->key.path = NULL; + } + list_del(&f->link); + free(f); +} + +static int fd_fetch(const char *path, fd_t **f_res, int dirfd) +{ + fdkey_t key; + key.plen = strlen(path) + 1; + key.path = (char *)path; + + /* fd in cache */ + hashlink_t *data = NULL; + if (EEXIST == hashmap_search(g_client.map, &key, &data, NULL, fd_inc)) { + *f_res = container_of(data, fd_t, hash); + (*f_res)->ts = _get_ts(); + return 0; + } + + /* new fd */ + fd_t *f = fd_alloc(path); + if (!f) + return -ENOMEM; + + /* open file */ + if (dirfd > 0) + f->fd = openat(dirfd, path, O_RDONLY, S_IRUSR | S_IRGRP); + else + f->fd = open(path, O_RDONLY, S_IRUSR | S_IRGRP); + if (f->fd < 0) { + if (errno != ENOENT) + log_error("open(%d,%s) fail, err(%s)", dirfd, path, strerror(errno)); + fd_free(f); + return errno; + } + + /* add to fd cache */ + hashlink_t *old = NULL; + if (EEXIST == hashmap_insert(g_client.map, &f->hash, &old, NULL, fd_inc)) { + fd_free(f); + f = container_of(old, fd_t, hash); + } + + spinlock_lock(&g_client.lock); + list_add_tail(&f->link, &g_client.head); + spinlock_unlock(&g_client.lock); + f->ts = _get_ts(); + *f_res = f; + return 0; +} + +static inline void fd_restore(fd_t *f) +{ + (void)hashmap_protect(g_client.map, &f->key, NULL, fd_dec); +} + +static void _fd_gc(void *args) +{ + list_head_t head, *curr, *next; + hashlink_t *data = NULL; + + list_init(&head); + spinlock_lock(&g_client.lock); + list_splice(&g_client.head, &head); + spinlock_unlock(&g_client.lock); + + list_foreach_safe(curr, next, &head) + { + fd_t *f = container_of(curr, fd_t, link); + if (atomic_s32_fetch(&f->ref) != 0) + continue; + /* try to destroy */ + if (0 != hashmap_delete(g_client.map, &f->key, &data, NULL, fd_expire)) + continue; + list_del(&f->link); + log_info("path:%s with fd:%d is expire.", f->key.path, f->fd); + fd_free(f); + } + + spinlock_lock(&g_client.lock); + list_splice(&head, &g_client.head); + spinlock_unlock(&g_client.lock); +} + +int fs_evict_by_path(const char*path, uint64_t off, uint64_t len) +{ + int ret; + fd_t *f; + uint64_t step = 4096 * 4; + + ret = fd_fetch(path, &f, 0); + if (ret) + return ret; + + while (len) { + if (step > len) + step = len; + ret = posix_fadvise(f->fd, off, len, POSIX_FADV_DONTNEED); + if (ret < 0) + break; + len -= step; + off += step; + } + + fd_restore(f); + return ret; +} + +int fs_load_by_path(const char *path, uint64_t off, uint64_t len) +{ + int ret; + fd_t *f; + uint64_t step = 16 * 4096; + char *buf = NULL; + + ret = fd_fetch(path, &f, 0); + if (ret) + return ret; + + buf = (char *)malloc(step); + + while (len) { + if (step > len) + step = len; + ret = pread(f->fd, buf, step, off); + if (ret <= 0) + break; + len -= step; + off += step; + } + free(buf); + fd_restore(f); + return ret; +} + +int fs_load_by_fd(int fd, uint64_t off, uint64_t len) +{ + struct mfs_ioc_ra ra; + + ra.off = off; + ra.len = len; + return ioctl(fd, MFS_IOC_RA, &ra); +} + +int fs_sync_by_path(const char *path, void *buf, uint64_t off, uint64_t len) +{ + ssize_t rsize = 0, ret; + uint64_t pos = 0; + fd_t *f; + + ret = fd_fetch(path + 1, &f, g_client.rootfd); + if (ret) + return ret; + + do { + ret = pread(f->fd, buf + pos, len - pos, off + pos); + if (ret == 0) + break; + if (ret < 0) { + log_error("failed to read:%s", strerror(errno)); + fd_restore(f); + return -1; + } + pos += ret; + rsize += ret; + } while (rsize < len); + fd_restore(f); + return 0; +} + +int fs_client_init(const char *source) +{ + int ret; + + g_client.rootfd = -1; + if (source) { + g_client.rootfd = open(source, O_RDONLY | O_DIRECTORY); + if (g_client.rootfd <= 0) { + log_error("open %s failed", source); + return -1; + } + } + ret = hashmap_create(1024, fd_cmp, fd_hash, &g_client.map); + if (ret) { + log_error("client fd map alloc failed"); + close(g_client.rootfd); + return ret; + } + + g_client.timer = stimer_create("LfsGc", TIMER_CYCLE, NULL, _fd_gc); + if (!g_client.timer) { + log_error("timer create failed"); + hashmap_destroy(g_client.map, NULL, NULL); + close(g_client.rootfd); + return -1; + } + list_init(&g_client.head); + spinlock_init(&g_client.lock); + g_client.tmout = FD_TMOUT; + return 0; +} + +void fs_client_exit() +{ + spinlock_destroy(&g_client.lock); + stimer_destroy(g_client.timer); + hashmap_destroy(g_client.map, NULL, NULL); + close(g_client.rootfd); +} + diff --git a/tools/mfs/maio-utils/src/loader/CMakeLists.txt b/tools/mfs/maio-utils/src/loader/CMakeLists.txt new file mode 100644 index 000000000000..08e1b637be26 --- /dev/null +++ b/tools/mfs/maio-utils/src/loader/CMakeLists.txt @@ -0,0 +1,18 @@ +#******************************************************************************* +#******************************************************************************* + +include_directories(${CMAKE_CURRENT_SOURCE_DIR}) + +#******************************************************************************* +#******************************************************************************* + +aux_source_directory(. LOADER_SRC) + +#******************************************************************************* +#******************************************************************************* + +add_library(loader ${LOADER_SRC}) +target_link_libraries(loader infra + numa + securec) + diff --git a/tools/mfs/maio-utils/src/loader/loader.c b/tools/mfs/maio-utils/src/loader/loader.c new file mode 100644 index 000000000000..61c5302204fc --- /dev/null +++ b/tools/mfs/maio-utils/src/loader/loader.c @@ -0,0 +1,144 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2025 Huawei Technologies Co., Ltd + */ +#include "loader.h" + +#include "fs_client.h" +#include "threadpool.h" +#include "log.h" +#include "atomic.h" +#include "inner.h" +#include "sysdef.h" + +#include "securec.h" +#include "numa.h" +#include <errno.h> + +struct loader_mgr { + int numa_num; + threadpool_t **numa_thp; + uint64_t curseq; +}; + +struct loader_mgr g_local_mgr; + +static threadpool_t *choose_worker_pool(struct io_context *ioctx) +{ + static uint64_t cid = 0; + int nid; + + if (ioctx->numaid == (uint16_t)-1) + nid = cid++ % g_local_mgr.numa_num; + else + nid = ioctx->numaid % g_local_mgr.numa_num; + return g_local_mgr.numa_thp[nid]; +} + +static void handle_io(void *args) +{ + struct io_context *ioctx = (struct io_context *)args; + int ret; + + if (g_local_mgr.curseq > ioctx->seq) { + if (ioctx->end_io) + ioctx->end_io(0, ioctx->private); + return; + } + ret = ioctx->path ? fs_load_by_path(ioctx->path, ioctx->off, ioctx->len) + : fs_load_by_fd(ioctx->fd, ioctx->off, ioctx->len); + if (ioctx->end_io) + ioctx->end_io(ret, ioctx->private); +} + +int loader_io_submit(struct io_context *ioctx) +{ + threadpool_t *worker_pools = choose_worker_pool(ioctx); + + threadpool_submit(worker_pools, ioctx, handle_io); + return 0; +} + +void loader_update_curseq(uint64_t seq) +{ + uint64_t curseq = atomic_u64_fetch(&g_local_mgr.curseq); + uint64_t old; + + while (seq > curseq) { + if (atomic_u64_cas(&g_local_mgr.curseq, curseq, seq, &old)) + break; + curseq = old; + } +} + +static void handle_evict(void *args) +{ + struct io_context *ioctx = (struct io_context *)args; + int ret; + + ret = ioctx->path ? fs_evict_by_path(ioctx->path, ioctx->off, ioctx->len) : 0; + if (ioctx->end_io) + ioctx->end_io(ret, ioctx->private); +} + +int loader_evict_submit(struct io_context *ioctx) +{ + threadpool_t *worker_pools = choose_worker_pool(ioctx); + + threadpool_submit(worker_pools, ioctx, handle_evict); + return 0; +} + +static void _free_loader() +{ + int i; + + if (!g_local_mgr.numa_thp) + return; + + for (i = 0; i < g_local_mgr.numa_num; i++) + threadpool_destroy(g_local_mgr.numa_thp[i]); + free(g_local_mgr.numa_thp); + g_local_mgr.numa_thp = NULL; +} + +int loader_init() +{ + int i, ret, wnum = 8; + char name[THD_NAME + 1] = {0}; + + if (numa_available() < 0) { + log_error("Current system does not support NUAM api"); + return -1; + } + + g_local_mgr.numa_num = numa_max_node() + 1; + g_local_mgr.curseq = 0; + ret = 0; + do { + g_local_mgr.numa_thp = + calloc(g_local_mgr.numa_num, sizeof(threadpool_t *)); + if (!g_local_mgr.numa_thp) { + log_error("alloc for numa threadpool failed"); + ret = -1; + break; + } + for (i = 0; i < g_local_mgr.numa_num; i++) { + sprintf_s(name, sizeof(name), "Loader-%d", i); + g_local_mgr.numa_thp[i] = threadpool_create(name, wnum, i); + if (!g_local_mgr.numa_thp[i]) { + log_error("alloc Loader-%d failed", i); + ret = -1; + break; + } + } + } while (0); + + if (ret != 0) + _free_loader(); + return ret; +} + +void loader_exit() +{ + _free_loader(); +} diff --git a/tools/mfs/maio-utils/src/main.c b/tools/mfs/maio-utils/src/main.c new file mode 100644 index 000000000000..854c5b298521 --- /dev/null +++ b/tools/mfs/maio-utils/src/main.c @@ -0,0 +1,156 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2025 Huawei Technologies Co., Ltd + */ +#include <stdlib.h> +#include <unistd.h> +#include <string.h> +#include <getopt.h> +#include <errno.h> +#include <fcntl.h> +#include <poll.h> + +#include "loader.h" +#include "log.h" +#include "maio.h" +#include "policy.h" +#include "req_parser.h" +#include "fs_client.h" +#include "mfs.h" +#include "securec.h" + +#include <sys/ioctl.h> +#include <sys/statfs.h> + +#define MAX_BUF_SIZE 1024 +#define MFS_SUPER_MAGIC 0x85428370 + +static int read_req(int fd) +{ + char *buf; + int ret; + + buf = calloc(MAX_BUF_SIZE, sizeof(char)); + if (!buf) { + log_error("failed to alloc buf\n"); + return -1; + } + ret = read(fd, buf, MAX_BUF_SIZE); + if (ret <= 0) { + if (ret < 0) + log_error("failed to read, ret:%d\n", ret); + return -1; + } + return maio_parse_req(buf, ret); +} + +static void dev_monitor(int dfd) +{ + struct pollfd pfd; + int ret; + + pfd.fd = dfd; + pfd.events = POLLIN; + while (1) { + ret = poll(&pfd, 1, -1); + if (ret < 0) { + log_error("poll failed\n"); + return; + } + if (ret == 0 || !(pfd.revents & POLLIN)) { + log_error("poll events error, ret:%d, revents:%x\n", ret, pfd.revents); + continue; + } + while(!read_req(pfd.fd)) {} + } +} + +int main(int argc, char *argv[]) +{ + const char *mntpoint = NULL, *strategylib = NULL; + struct mfs_ioc_fsinfo fsinfo = {0}; + int dfd, ret, opt; + struct statfs buf; + char devname[10]; + + while ((opt = getopt(argc, argv, "m:s:")) != -1) { + switch (opt) { + case 'm': + mntpoint = optarg; + break; + case 's': + strategylib = optarg; + break; + default: + fprintf(stderr, "Usage: %s -m ${mnt} [-s ${strategylib}]\n", argv[0]); + return -EINVAL; + } + } + if (!mntpoint) { + fprintf(stderr, "mount point should specify\n"); + fprintf(stderr, "Usage: %s -m ${mnt} [-s ${strategylib}]\n", argv[0]); + return -1; + } + + ret = statfs(mntpoint, &buf); + if (ret) { + log_error("statfs %s failed, errstr:%s\n", mntpoint, strerror(errno)); + return -1; + } + if (buf.f_type != MFS_SUPER_MAGIC) { + log_error("fstype(%x) is invalid, please check the mountpoint", buf.f_type); + return -1; + } + + sprintf_s(devname, sizeof(devname), "/dev/mfs%ld", buf.f_spare[0]); + /* Open with O_CLOEXEC to avoid potential fd leaks */ + dfd = open(devname, O_RDWR | O_CLOEXEC); + if (dfd < 0) { + log_error("open %s failed errstr:%s\n", devname, strerror(errno)); + return -1; + } + + ret = ioctl(dfd, MFS_IOC_FSINFO, (unsigned long)&fsinfo); + if (ret < 0) { + log_error("ioctl get fsinfo failed, ret:%d\n", ret); + goto close_fd; + } + if (fsinfo.mode != 1) { + log_error("fs runing mode(%d) is not supported", fsinfo.mode); + goto close_fd; + } + ret = loader_init(); + if (ret) { + log_error("loader init failed"); + goto close_fd; + } + ret = fs_client_init(NULL); + if (ret) { + log_error("clients init failed"); + goto free_loader; + } + ret = parser_init(fsinfo.mode, mntpoint); + if (ret) { + log_error("parser init failed"); + goto free_client; + } + ret = policy_init(); + if (ret) { + log_error("policy init failed"); + goto free_parser; + } + ret = policy_register(strategylib); + if (ret) { + log_info("register new policy failed, use default policy"); + } + + dev_monitor(dfd); +free_parser: + parser_destory(); +free_client: + fs_client_exit(); +free_loader: + loader_exit(); +close_fd: + close(dfd); + return ret; +} diff --git a/tools/mfs/maio-utils/src/parser/CMakeLists.txt b/tools/mfs/maio-utils/src/parser/CMakeLists.txt new file mode 100644 index 000000000000..72e5849da8e4 --- /dev/null +++ b/tools/mfs/maio-utils/src/parser/CMakeLists.txt @@ -0,0 +1,16 @@ +#******************************************************************************* +#******************************************************************************* + +include_directories(${CMAKE_CURRENT_SOURCE_DIR}) + +#******************************************************************************* +#******************************************************************************* + +aux_source_directory(. PARSER_SRC) + +#******************************************************************************* +#******************************************************************************* + +add_library(parser ${PARSER_SRC}) +target_link_libraries(parser infra + securec) diff --git a/tools/mfs/maio-utils/src/parser/req_parser.c b/tools/mfs/maio-utils/src/parser/req_parser.c new file mode 100644 index 000000000000..83a975276bc2 --- /dev/null +++ b/tools/mfs/maio-utils/src/parser/req_parser.c @@ -0,0 +1,313 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2025 Huawei Technologies Co., Ltd + */ + +#include "inner.h" +#include "log.h" +#include "mfs.h" +#include "policy.h" +#include "securec.h" +#include "threadpool.h" + +#include <stdbool.h> +#include <errno.h> +#include <sys/ioctl.h> +#include <sys/stat.h> + +struct parser_mgr { + uint32_t fs_mode; + uint32_t chunk_size; + const char *mntpoint; + threadpool_t *parser; +}; + +struct parser_mgr g_parser_mgr; + +#define PARSER_NUM 8 +#define MAX_PATH_SIZE 1024 + +#define __round_mask(x, y) ((__typeof__(x))((y)-1)) +#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1) +#define round_down(x, y) ((x) & ~__round_mask(x, y)) + +#define DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) +#define MIN(x, y) ((x) < (y) ? (x) : (y)) + +bool is_power_of_2(unsigned long n) +{ + return (n != 0 && ((n & (n - 1)) == 0)); +} + +void ctx_cb(int ret, void *args) +{ + struct io_context *ctx = (struct io_context *)args; + + if (ctx->path) + free(ctx->path); + if (ctx->buf) + free(ctx->buf); + free(ctx); +} + +void _submit_local_io(int fd, struct maio_entry *entry) +{ + struct io_context *ioctx; + + ioctx = calloc(1, sizeof(struct io_context)); + if (!ioctx) { + log_error("ioctx alloc failed"); + return; + } + ioctx->off = entry->toff; + ioctx->len = entry->tlen; + ioctx->numaid = entry->tnuma; + ioctx->fd = fd; + ioctx->path = entry->fpath; + ioctx->seq = entry->seq; + ioctx->private = ioctx; + ioctx->end_io = ctx_cb; + loader_io_submit(ioctx); +} + +char *get_file_path(int fd) +{ + struct mfs_ioc_rpath *rp; + char *path; + int ret; + + rp = malloc(sizeof(struct mfs_ioc_rpath) + MAX_PATH_SIZE); + if (!rp) { + log_error("rpath alloc failed"); + return NULL; + } + rp->max = MAX_PATH_SIZE; + ret = ioctl(fd, MFS_IOC_RPATH, (unsigned long)rp); + if (ret) { + log_error("realpath failed for fd:%d, ret:%d", fd, ret); + free(rp); + return NULL; + } + rp->d[rp->len] = '\0'; + + path = malloc(strlen(g_parser_mgr.mntpoint) + rp->len); + if (!path) { + log_error("malloc path %s %s failed", g_parser_mgr.mntpoint, (const char *)rp->d); + return NULL; + } + sprintf(path, "%s%s", g_parser_mgr.mntpoint, (const char *)rp->d); + free(rp); + return path; +} + +char *_get_fullpath(char *fpath, int fd) +{ + struct mfs_ioc_rpath *rp; + char *path; + int ret; + + if (fpath) + return fpath; + rp = malloc(sizeof(struct mfs_ioc_rpath) + MAX_PATH_SIZE); + if (!rp) { + log_error("rpath alloc failed"); + return NULL; + } + rp->max = MAX_PATH_SIZE; + ret = ioctl(fd, MFS_IOC_RPATH, (unsigned long)rp); + if (ret) { + log_error("realpath failed for fd:%d, ret:%d", fd, ret); + free(rp); + return NULL; + } + rp->d[rp->len] = '\0'; + path = strdup((const char *)rp->d); + if (!path) + log_error("strdup path(%s) failed", (const char *)rp->d); + free(rp); + return path; +} + +void maio_preload(struct maio *maio, int nio) +{ + struct maio_entry *entry; + + for (int i = 0; i < nio; ++i) { + entry = &maio->entries[i]; + _submit_local_io(0, entry); + } +} + +uint8_t pid_to_numaid(int pid) +{ + return (uint8_t)-1; +} + +void _process_read_io(uint32_t id, struct maio *maio, int nio) +{ + struct maio_entry *entry; + int i; + + /* process the successor io */ + for (i = 0; i < nio; i++) { + entry = &maio->entries[i]; + _submit_local_io(maio->fd, entry); + } +} + +void _submit_evict(struct maio_entry *entry) +{ + struct io_context *ioctx; + + ioctx = calloc(1, sizeof(struct io_context)); + if (!ioctx) { + log_error("ioctx alloc failed"); + return; + } + ioctx->off = entry->toff; + ioctx->len = entry->tlen; + ioctx->numaid = -1; + ioctx->path = entry->fpath; + ioctx->private = ioctx; + ioctx->end_io = ctx_cb; + loader_evict_submit(ioctx); +} + +void _process_evict(struct mfs_msg *msg) +{ + struct maio_entry *entry; + struct mfs_read *read; + uint64_t soff, eoff; + struct maio *maio; + int ret; + + if (g_parser_mgr.fs_mode != MFS_MODE_LOCAL) + return; + + maio = calloc(1, sizeof(struct maio)); + if (!maio) { + log_error("failed to alloc maio"); + return; + } + + read = (void*)msg->data; + maio->cksz = g_parser_mgr.chunk_size; + soff = round_down(read->off, maio->cksz); + eoff = round_up(read->off + read->len, maio->cksz); + maio->fd = msg->fd; + maio->off = read->off; + maio->len = eoff - soff; + maio->pid = read->pid; + maio->op = msg->opcode; + + ret = policy_evict(&maio); + if (ret <= 0) + goto out; + + for (int i = 0; i < ret; ++i) { + entry = &maio->entries[i]; + _submit_evict(entry); + } +out: + free(maio); +} + +void _parse_read_req(struct mfs_msg *msg) +{ + struct mfs_read *read; + struct maio *maio; + uint64_t soff, eoff, ts; + int ret, io_num = policy_max_io(); + + _process_evict(msg); + + /* alloc maio slots */ + maio = calloc(1, sizeof(struct maio) + io_num * sizeof(struct maio_entry)); + if (!maio) { + log_error("failed to alloc maio, num:%d", io_num); + return; + } + read = (void *)msg->data; + maio->cksz = g_parser_mgr.chunk_size; + soff = round_down(read->off, maio->cksz); + eoff = round_up(read->off + read->len, maio->cksz); + ts = _get_ts(); + maio->fd = msg->fd; + maio->off = soff; + maio->len = eoff - soff; + maio->pid = read->pid; + maio->op = msg->opcode; + maio->ts = ts; + + /* fill slots from policy */ + ret = policy_load(&maio); + if (ret < 0) { + char *path = _get_fullpath(NULL, maio->fd); + if (path) { + log_warn("io on path:%s%s offset:%lu length:%lu dropped", + g_parser_mgr.mntpoint, path, read->off, read->len); + free(path); + } + free(maio); + return; + } + + if (maio->flags & MAIO_WITH_SEQ) + loader_update_curseq(maio->curseq); + + /* keep the input parameter */ + maio->fd = msg->fd; + maio->off = soff; + maio->len = eoff - soff; + maio->cksz = g_parser_mgr.chunk_size; + maio->pid = read->pid; + maio->op = msg->opcode; + maio->ts = ts; + + /* process each maio in slots */ + _process_read_io(msg->id, maio, ret); + free(maio); +} + +void _parse_one_req(void *buf) +{ + struct mfs_msg *msg = (struct mfs_msg *)buf; + + if (msg->opcode == MFS_OP_READ || msg->opcode == MFS_OP_FAULT) + _parse_read_req(msg); + + free(buf); +} + +int maio_parse_req(void *buf, int size) +{ + struct mfs_msg *msg = (struct mfs_msg *)buf; + + if (msg->len != size) + return -1; + + threadpool_submit(g_parser_mgr.parser, buf, _parse_one_req); + return 0; +} + +int parser_init(uint32_t fs_mode, const char *mntpoint) +{ + g_parser_mgr.fs_mode = fs_mode; + g_parser_mgr.mntpoint = strdup(mntpoint); + g_parser_mgr.chunk_size = 4096; + if (!is_power_of_2(g_parser_mgr.chunk_size)) { + log_error("chunk size must be power of 2"); + return -1; + } + g_parser_mgr.parser = threadpool_create("ReqParser", PARSER_NUM, -1); + if (!g_parser_mgr.parser) { + log_error("failed to alloc parser threadpool"); + return -1; + } + + return 0; +} + +void parser_destory() +{ + threadpool_destroy(g_parser_mgr.parser); +} diff --git a/tools/mfs/maio-utils/src/policy/CMakeLists.txt b/tools/mfs/maio-utils/src/policy/CMakeLists.txt new file mode 100644 index 000000000000..714023475e07 --- /dev/null +++ b/tools/mfs/maio-utils/src/policy/CMakeLists.txt @@ -0,0 +1,16 @@ +#******************************************************************************* +#******************************************************************************* + +include_directories(${CMAKE_CURRENT_SOURCE_DIR}) + +#******************************************************************************* +#******************************************************************************* + +aux_source_directory(. POLICY_SRC) + +#******************************************************************************* +#******************************************************************************* + +add_library(policy ${POLICY_SRC}) +target_link_libraries(policy infra + securec) diff --git a/tools/mfs/maio-utils/src/policy/policy.c b/tools/mfs/maio-utils/src/policy/policy.c new file mode 100644 index 000000000000..404358ff9b46 --- /dev/null +++ b/tools/mfs/maio-utils/src/policy/policy.c @@ -0,0 +1,114 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2025 Huawei Technologies Co., Ltd + */ +#include "policy.h" + +#include "maio.h" +#include "log.h" +#include "securec.h" +#include <dlfcn.h> + +typedef struct maio_operation* (*strategy_init)(); + +struct policy_mgr { + void *handle; + struct maio_operation *strategy; +}; + +struct policy_mgr g_policy; + +static int default_init(void) +{ + return 0; +} + +static void default_exit(void) +{ +} + +static int default_load(struct maio **io) +{ + return 0; +} + +static int default_evict(struct maio **io) +{ + return 0; +} + +struct maio_operation default_ops = { + .max_io = 1, + .init = default_init, + .exit = default_exit, + .load = default_load, + .evict = default_evict, +}; + +static void set_default_strategy() +{ + g_policy.strategy = &default_ops; +} + +int policy_max_io(void) +{ + return g_policy.strategy->max_io; +} + +/* return the filled num of io */ +int policy_load(struct maio **io) +{ + return g_policy.strategy->load(io); +} + +int policy_evict(struct maio **io) +{ + return g_policy.strategy->evict(io); +} + +int policy_register(const char *path) +{ + strategy_init sinit; + + if (!path || strlen(path) == 0) + return -1; + + g_policy.handle = dlopen(path, RTLD_LAZY); + if (!g_policy.handle) { + log_error("dlopen failed:%s", dlerror()); + return -1; + } + + sinit = dlsym(g_policy.handle, "register_strategy"); + if (!sinit) { + log_error("dlsym failed:%s", dlerror()); + dlclose(g_policy.handle); + g_policy.handle = NULL; + return -1; + } + g_policy.strategy = sinit(); + if (g_policy.strategy->init()) + return -1; + log_info("register strategy:%s done.", path); + return 0; +} + +void policy_unregister() +{ + if (g_policy.handle) { + g_policy.strategy->exit(); + dlclose(g_policy.handle); + g_policy.handle = NULL; + } + set_default_strategy(); +} + +int policy_init() +{ + g_policy.handle = NULL; + set_default_strategy(); + return 0; +} + +void policy_exit() +{ +} diff --git a/tools/mfs/maio-utils/test/Makefile b/tools/mfs/maio-utils/test/Makefile new file mode 100644 index 000000000000..6c87247aafa0 --- /dev/null +++ b/tools/mfs/maio-utils/test/Makefile @@ -0,0 +1,26 @@ +# SPDX-License-Identifier: GPL-2.0 + +CC := gcc +CFLAGS := -fPIC -Wall -Werror -O2 +CPPFLAGS := -fPIC -Wall -Werror -O2 -std=c++11 -g +LDFLAGS := -shared + +CFLAGS += $(addprefix -I,../include) +CPPFLAGS += $(addprefix -I,../include) + +C_SRCS := $(wildcard *.c) +CPP_SRCS := $(wildcard *.cpp) +TARGETS := $(C_SRCS:.c=.so) $(CPP_SRCS:.cpp=.so) + +all: $(TARGETS) + +%.so: %.c + $(CC) $(CFLAGS) $(LDFLAGS) -o $@ $< + +%.so: %.cpp + $(CC) $(CPPFLAGS) $(LDFLAGS) -o $@ $< + +clean: + rm -f $(TARGETS) + +.PHONY: all clean diff --git a/tools/mfs/maio-utils/test/README.md b/tools/mfs/maio-utils/test/README.md new file mode 100644 index 000000000000..a7b7980de933 --- /dev/null +++ b/tools/mfs/maio-utils/test/README.md @@ -0,0 +1,61 @@ +Here, we provide some strategies library for some cases. + +- strategy_demo +A simple strategy library shows how to write a demo. + +- strategy_prefetch +A prefetch strategy library to prefetch data. + +- strategy_toend +A readahead strategy until the end. + +- strategy_generate +A tools using maio-util to generate the io trace. + +- strategy_replay +A strategy to replay the io trace. + +### How to build + +Using `make -j` to build the libraries. + +### How to use + +Set the library path as the `-s` parameter's value to run with maio-utils. Here we show usage of the advanced replay strategy: + +- generate the io trace + +> assume you have mounted the mfs at /mnt/mfs + +This is the tracing period. + +``` +export MAIO_TRACE_FILE=trace.txt +export MAIO_MNTPOINT=/mnt/mfs # /mnt/mfs is the MFS mountpoint +./bin/maio-utils -m /mnt/mfs -s /home/lihb/workspace/hulk-6.6/maio-utils/test/strategy_generate.so +``` +Then, you can trigger the io. After finishing, you would get the trace file with the content likes: + +``` +xxx/model-00001-of-000008.safetensors 0 32768 0 +xxx/model-00001-of-000008.safetensors 32768 32768 0 +xxx/model-00001-of-000008.safetensors 65536 32768 0 +xxx/model-00001-of-000008.safetensors 98304 32768 0 +xxx/model-00001-of-000008.safetensors 131072 32768 0 +... + +``` + +The format is "<path> <offset> <length> <numaid>". + +- replay the io trace + +> assume you have mounted the mfs at /mnt/mfs and begin to launch the model. + +This is the running period. + +``` +export MAIO_TRACE_FILE=trace.txt +export MAIO_MNTPOINT=/mnt/mfs # /mnt/mfs is the MFS mountpoint +./bin/maio-utils -m /mnt/mfs -s /home/lihb/workspace/hulk-6.6/maio-utils/test/replay.so +``` diff --git a/tools/mfs/maio-utils/test/strategy_demo.c b/tools/mfs/maio-utils/test/strategy_demo.c new file mode 100644 index 000000000000..54554b609f85 --- /dev/null +++ b/tools/mfs/maio-utils/test/strategy_demo.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2025 Huawei Technologies Co., Ltd + */ +#include "maio.h" +#include <stddef.h> + +int demo_init(void) +{ + return 0; +} + +void demo_exit(void) +{ +} + +int demo_load(struct maio **io) +{ + struct maio_entry *entry; + + entry = (*io)->entries; + entry[0].toff = (*io)->off + (*io)->len; + entry[0].tlen = (*io)->cksz; + entry[0].fpath = NULL; + entry[0].tnuma = -1; + return 1; +} + +int demo_evict(struct maio **io) +{ + ((void)io); + return 0; +} + +const struct maio_operation demo_strategy = { + .max_io = 1, + .init = demo_init, + .exit = demo_exit, + .load = demo_load, + .evict = demo_evict, +}; + +struct maio_operation *register_strategy() +{ + return (struct maio_operation *)&demo_strategy; +} diff --git a/tools/mfs/maio-utils/test/strategy_generate.cpp b/tools/mfs/maio-utils/test/strategy_generate.cpp new file mode 100644 index 000000000000..929be30e6a42 --- /dev/null +++ b/tools/mfs/maio-utils/test/strategy_generate.cpp @@ -0,0 +1,296 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2025 Huawei Technologies Co., Ltd + */ +#include "maio.h" +#include "strategy_template.h" + +#include <array> +#include <atomic> +#include <cstring> +#include <condition_variable> +#include <fstream> +#include <sstream> +#include <iostream> +#include <mutex> +#include <queue> +#include <thread> +#include <unordered_map> +#include <vector> +#include <unistd.h> + +using namespace std; + +#define MAIO_MNTPOINT "MAIO_MNTPOINT" +#define MAIO_TRACE_FILE "MAIO_TRACE_FILE" +#define CACHEDIR "cachedir" + +#define MAXLINE 1024 + +/* Data struct definition */ +template<typename T> +class SafeQueue { +private: + queue<T> data_queue; + mutex mtx; + condition_variable cv; + +public: + // 添加数据到队列 + void push(T item) { + lock_guard<mutex> lock(mtx); + data_queue.push(move(item)); + cv.notify_one(); + } + + // 从队列取出数据（阻塞直到有数据） + T pop() { + unique_lock<mutex> lock(mtx); + cv.wait(lock, [this]{ return !data_queue.empty(); }); + T item = move(data_queue.front()); + data_queue.pop(); + return item; + } + + // 检查队列是否为空 + bool empty() { + lock_guard<mutex> lock(mtx); + return data_queue.empty(); + } +}; + +struct io { + string name; + uint64_t off; + uint64_t len; + uint8_t npu; + + io(const string& _name, uint64_t _off, uint64_t _len, uint8_t _npu) + : name(_name), off(_off), len(_len), npu(_npu) {} +}; + +/* Global variable definition */ +unordered_map<int, char*> fd_map; /* map fd to path */ +mutex fd_mutex; +string cachedir; + +vector<io> iovec; /* io traces */ +mutex iovec_mutex; +SafeQueue<vector<io>> iovec_queue; + +ofstream tfile; /* trace file */ + +thread writer; + +unordered_map<int, int> process_npu_map; +mutex pnpu_mutex; + +atomic<int> npu_smi_enable(-1); + +/* fd_map helper function */ +char* fd_path_find(int iofd) { + lock_guard<mutex> lock(fd_mutex); + auto it = fd_map.find(iofd); + if (it != fd_map.end()) { + return it->second; + } else { + char *path = _get_fullpath(NULL, iofd); + fd_map.insert({iofd, path}); + return path; + } +} + +/* iovec helper function */ +void io_insert_data(string name, uint64_t off, uint64_t len, uint8_t npu) +{ + lock_guard<mutex> lock(iovec_mutex); + iovec.emplace_back(name, off, len, npu); + + vector<io> copy_iovec = move(iovec); + iovec.clear(); + + iovec_queue.push(move(copy_iovec)); +} + +void get_mount_option(const char* mntpoint, const char* option) +{ + ifstream mounts("/proc/mounts"); + string line, target_mp; + + if (!mounts.is_open()) { + cerr << "Error: could not open /proc/mounts" << endl; + return; + } + + while (getline(mounts, line)) { + istringstream iss(line); + string device, mp, fs_type, options; + + if (!(iss >> device >> mp >> fs_type >> options)) + continue; + + if (mp.back() != '/') + mp += '/'; + target_mp = mntpoint; + if (target_mp.back() != '/') + target_mp += '/'; + + if (target_mp == mp) { + istringstream opt_stream(options); + string opt; + + while (getline(opt_stream, opt, ',')) { + if (opt.find(option) == 0) { + if (opt[strlen(option)] == '=') { + cachedir = opt.substr(strlen(option) + 1); + } + } + } + break; + } + } +} + +void writer_thread() { + while (true) { + vector<io> iovec_to_write = iovec_queue.pop(); + + for (const auto &item : iovec_to_write) + tfile << cachedir << item.name << " " << item.off << " " << item.len << " " << (unsigned int)item.npu << endl; + tfile.flush(); + } +} + +string exec_cmd(const char* cmd) { + array<char, 128> buffer; + string result; + unique_ptr<FILE, decltype(&pclose)> pipe(popen(cmd, "r"), pclose); + + if (!pipe) { + throw std::runtime_error("popen() failed!"); + } + while (fgets(buffer.data(), buffer.size(), pipe.get()) != nullptr) { + result += buffer.data(); + } + return result; +} + +bool isNumber(const std::string& str) { + return !str.empty() && str.find_first_not_of("0123456789") == std::string::npos; +} + +void get_npu_info(string &npuinfo) +{ + istringstream iss(npuinfo); + string line; + + while (getline(iss, line)) { + istringstream lineStream(line); + string token; + vector<string> tokens; + while (getline(lineStream, token, ' ')) { + if (!token.empty()) { + tokens.push_back(token); + } + } + if (tokens.size() >= 3) { + if (!isNumber(tokens[1]) || !isNumber(tokens[4])) + continue; + int npuId = stoi(tokens[1]); + int processId = stoi(tokens[4]); + process_npu_map[processId] = npuId; + } + } +} + +int process_npu_find(int processid) { + lock_guard<mutex> lock(pnpu_mutex); + auto it = process_npu_map.find(processid); + + if (npu_smi_enable.load() == -1) { + if (exec_cmd("command -v npu-smi").empty()) + npu_smi_enable.store(0); + else + npu_smi_enable.store(1); + } + + if (npu_smi_enable.load() == 0) + return 0; + + if (it != process_npu_map.end()) { + return it->second; + } else { + string result = exec_cmd("npu-smi info"); + get_npu_info(result); + auto it = process_npu_map.find(processid); + if (it != process_npu_map.end()) + return it->second; + else + return 0; + } +} + +int strategy_init(void) +{ + char *tfilename = getenv(MAIO_TRACE_FILE); + char *mntpoint = getenv(MAIO_MNTPOINT); + + if(!tfilename || !mntpoint) { + printf("no MAIO_TRACE_FILE or MAIO_MNTPOINT env variable\n"); + return -1; + } + get_mount_option(mntpoint, CACHEDIR); + string stfilename = tfilename; + tfile.open(stfilename, ios::trunc); + writer = thread(writer_thread); + if (!tfile.is_open()) { + cerr << "Error: could not open" << stfilename << endl; + return -1; + } + return 0; +} + +void strategy_exit(void) +{ + lock_guard<mutex> lock(iovec_mutex); + vector<io> copy_iovec = move(iovec); + iovec.clear(); + iovec_queue.push(move(copy_iovec)); + + tfile.close(); + writer.join(); +} + +int strategy_load(struct maio **io) +{ + char *path; + string pathStr; + int ret = 0; + + if (!tfile.is_open()) + return -1; + + path = fd_path_find((*io)->fd); + pathStr.assign(path); + io_insert_data(pathStr, (*io)->off, (*io)->len, process_npu_find((*io)->pid)); + + return ret; +} + +int strategy_evict(struct maio **io) +{ + ((void)io); + return 0; +} + +const struct maio_operation maio_strategy = { + .max_io = 1, + .init = strategy_init, + .exit = strategy_exit, + .load = strategy_load, + .evict = strategy_evict, +}; + +struct maio_operation *register_strategy() +{ + return (struct maio_operation *)&maio_strategy; +} diff --git a/tools/mfs/maio-utils/test/strategy_prefetch.cpp b/tools/mfs/maio-utils/test/strategy_prefetch.cpp new file mode 100644 index 000000000000..9ba205931cdc --- /dev/null +++ b/tools/mfs/maio-utils/test/strategy_prefetch.cpp @@ -0,0 +1,150 @@ +#include "strategy_prefetch.h" +#include "maio.h" +#include <iostream> +#include <map> +#include <cstring> +#include <string> +#include <stdint.h> +#include <sys/stat.h> +#include <sys/mman.h> +#include <dirent.h> +#include <fcntl.h> +#include <unistd.h> + +using namespace std; + +struct prefetch_mgr { + map<string, uint64_t> files; +}; + +struct prefetch_mgr g_prefetch; + +int get_files(const char *parent) +{ + DIR *dir; + struct dirent *entry; + string filepath; + struct stat buf; + + if ((dir = opendir(parent)) == NULL) { + cout<<"opening directory failed"<<endl; + return -1; + } + + while ((entry = readdir(dir)) != NULL) { + if (strcmp(entry->d_name, ".") == 0 || strcmp(entry->d_name, "..") == 0) + continue; + + filepath = string(parent) + "/" + string(entry->d_name); + if (stat(filepath.c_str(), &buf) == -1) { + cout<<"stat path:"<<filepath<<" failed"<<endl; + continue; + } + if (S_ISDIR(buf.st_mode)) + continue; + cout<<"Find file:"<<filepath<<" size:"<<buf.st_size<<endl; + g_prefetch.files.insert(pair<string, uint64_t>(filepath, buf.st_size)); + } + + map<string, uint64_t>::iterator it; + for (it = g_prefetch.files.begin(); it != g_prefetch.files.end(); ++it) { + cout<<"path:"<<it->first<<" size:"<<it->second<<endl; + } + return 0; +} + +int prefetch_init(void) +{ + char *parent = getenv("MODEL_WEIGHT_DIR"); + if (!parent) { + cout<<"please set the env MODEL_WEIGHT_DIR"<<endl; + return -1; + } + + if (get_files(parent) != 0) { + cout<<"get all files failed"<<endl; + return -1; + } + return 0; +} + +void prefetch_exit(void) +{ +} + +struct thread_ctx { + char *path; + uint64_t off; + uint64_t len; +}; + +void *fault(void *arg) +{ + struct thread_ctx *ctx = (struct thread_ctx *)arg; + int fd = open(ctx->path, O_RDONLY); + if (fd < 0) { + cout<<"open file:%s"<<ctx->path<<" failed"<<endl; + free(ctx); + return NULL; + } + + cout<<"FAULT path:"<<ctx->path<<" fd:"<<fd<<" off:"<<ctx->off<<" len:"<<ctx->len<<endl; + void *addr = mmap(NULL, ctx->len, PROT_READ, MAP_SHARED, fd, 0); + uint64_t idx; + char tmp, total, *buffer = (char *)addr; + total = 'B'; + for (idx = 0; idx < ctx->len; idx += 4096) { + tmp = buffer[idx]; + total += tmp; + } + cout<<"Fault calculate total:"<<total<<endl; + munmap(addr, ctx->len); + close(fd); + free(ctx); + return NULL; +} + +int prefetch_load(struct maio **io) +{ + map<string, uint64_t>::iterator it; + struct thread_ctx *ctx; + pthread_t t0; + int ret; + + for (it = g_prefetch.files.begin(); it != g_prefetch.files.end(); ++it) { + ctx = (struct thread_ctx *)malloc(sizeof(struct thread_ctx)); + if (!ctx) { + cout<<"malloc ctx failed"<<endl; + continue; + } + ctx->path = strdup(it->first.c_str()); + ctx->off = 0; + ctx->len = it->second; + ret = pthread_create(&t0, NULL, fault, ctx); + if (ret == 0) + pthread_detach(t0); + } + g_prefetch.files.clear(); + + return 0; +} + +int prefetch_evict(struct maio **io) +{ + ((void)io); + return 0; +} + +const struct maio_operation prefetch_strategy = { + .max_io = 1, + .init = prefetch_init, + .exit = prefetch_exit, + .load = prefetch_load, + .evict = prefetch_evict, +}; + +struct maio_operation *register_strategy() +{ + return (struct maio_operation *)&prefetch_strategy; +} + diff --git a/tools/mfs/maio-utils/test/strategy_prefetch.h b/tools/mfs/maio-utils/test/strategy_prefetch.h new file mode 100644 index 000000000000..2c2475dc91f0 --- /dev/null +++ b/tools/mfs/maio-utils/test/strategy_prefetch.h @@ -0,0 +1,21 @@ +#ifndef STRATEGY_PREFETCH_H +#define STRATEGY_PREFETCH_H + +#ifdef __cplusplus +extern "C" { +#endif + +int prefetch_init(void); +void prefetch_exit(void); +int prefetch_load(struct maio *io); +int prefetch_evict(struct maio **io); + +extern const struct maio_operation prefetch_strategy; + +struct maio_operation *register_strategy(); + +#ifdef __cplusplus +} +#endif + +#endif diff --git a/tools/mfs/maio-utils/test/strategy_replay.cpp b/tools/mfs/maio-utils/test/strategy_replay.cpp new file mode 100644 index 000000000000..85c1c7defedd --- /dev/null +++ b/tools/mfs/maio-utils/test/strategy_replay.cpp @@ -0,0 +1,540 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2025 Huawei Technologies Co., Ltd + */ +#include "maio.h" +#include "strategy_template.h" + +#include <atomic> +#include <array> +#include <cstring> +#include <fstream> +#include <iostream> +#include <map> +#include <mutex> +#include <sstream> +#include <string> +#include <thread> +#include <unordered_map> +#include <vector> +#include <pthread.h> +#include <fcntl.h> +#include <unistd.h> + +using namespace std; + +#define MAIO_MNTPOINT "MAIO_MNTPOINT" +#define MAIO_TRACE_FILE "MAIO_TRACE_FILE" +#define CACHEDIR "cachedir" +#define MAXLINE 1024 + +/* Data structure definition */ +enum { + IO_NONE = 0, + IO_LOADED, + IO_EVICTED, +}; + +struct io { + string name; + uint64_t off; + uint64_t len; + uint8_t npu; + int flag; + + explicit io(const string& _name, uint64_t _off, uint64_t _len, uint8_t _npu) + : name(_name), off(_off), len(_len), npu(_npu), flag(IO_NONE) {} +}; + + +struct ioKey { + string name; + uint64_t off; + uint64_t len; + uint8_t npu; + + ioKey(const string& _name, uint64_t _off, uint64_t _len, uint8_t _npu) + : name(_name), off(_off), len(_len), npu(_npu) {} + + bool operator<(const ioKey &other) const { + return name < other.name || (name == other.name && off < other.off) || + (name == other.name && off == other.off && len < other.len); + } +}; + +vector<io> iovec; /* io traces */ +map<ioKey, int> io_to_index; +unordered_map<int, char*> fd_map; +mutex fd_mutex; +string cachedir; + +unordered_map<int, int> npu_numa_map; + +unordered_map<int, int> process_npu_map; +mutex pnpu_mutex; + +/* for evict */ +#define EVICT_DIST 10000 +#define EVICT_IO_MAX 5000 +thread_local size_t evict_idx = 0; + +atomic<int> npu_smi_enable(-1); +atomic<uint64_t> memory_usage(0); + +uint64_t memory_limit; +uint64_t memory_limit_bound; +string usage_in_bytes_path = "memory.usage_in_bytes"; +string limit_in_bytes_path = "memory.limit_in_bytes"; +string cgroup_mem=""; + +string get_cgroup_path() +{ + fstream cgroup_file("/proc/self/cgroup"); + if (!cgroup_file.is_open()) { + cerr << "Failed to open /proc/self/cgroup" << endl; + return ""; + } + + string line; + string cgroup_path; + while (getline(cgroup_file, line)) { + istringstream iss(line); + string hierarchy, controller, path; + if (!getline(iss, hierarchy, ':')) + continue; + if (!getline(iss, controller, ':')) + continue; + if (!getline(iss, path, ':')) + continue; + if (controller == "memory") { + cgroup_path = path; + break; + } + } + cgroup_file.close(); + return cgroup_path; +} + +/* read from /sys/fs/cgroup/memory/memory.[usage_in_bytes|limit_in_bytes] */ +uint64_t read_cgroup_memory(const string &file_path) +{ + if (cgroup_mem == "") + return -1; + string whole_path = "/sys/fs/cgroup/memory"+cgroup_mem+"/"+file_path; + ifstream cgroup_file(whole_path); + + if(!cgroup_file.is_open()) { + cerr << "Failed to open " << file_path << endl; + return -1; + } + + string line; + while(getline(cgroup_file, line)) { + try { + return stoll(line); + } catch (...) { + cerr << "Failed to parse line" << line << endl; + } + } + + cgroup_file.close(); + return -1; +} + +/* mount helper */ +void get_mount_option(const char* mntpoint, const char* option) +{ + ifstream mounts("/proc/mounts"); + string line, target_mp; + + if (!mounts.is_open()) { + cerr << "Error: could not open /proc/mounts" << endl; + return; + } + + while (getline(mounts, line)) { + istringstream iss(line); + string device, mp, fs_type, options; + + if (!(iss >> device >> mp >> fs_type >> options)) + continue; + + if (mp.back() != '/') + mp += '/'; + target_mp = mntpoint; + if (target_mp.back() != '/') + target_mp += '/'; + + if (target_mp == mp) { + istringstream opt_stream(options); + string opt; + + while (getline(opt_stream, opt, ',')) { + if (opt.find(option) == 0) { + if (opt[strlen(option)] == '=') { + cachedir = opt.substr(strlen(option) + 1); + } + } + } + break; + } + } +} + +/* fd_map helper function */ +char* fd_path_find(int iofd) { + lock_guard<mutex> lock(fd_mutex); + auto it = fd_map.find(iofd); + if (it != fd_map.end()) { + return it->second; + } else { + char *path = _get_fullpath(NULL, iofd); + size_t len = strlen(path) + cachedir.length() + 1; + char *realpath = (char*)malloc(len); + snprintf(realpath, len, "%s%s", cachedir.c_str(), path); + fd_map.insert({iofd, realpath}); + return realpath; + } +} + +string exec_cmd(const char* cmd) { + array<char, 128> buffer; + string result = ""; + unique_ptr<FILE, decltype(&pclose)> pipe(popen(cmd, "r"), pclose); + + if (!pipe) { + throw std::runtime_error("popen() failed!"); + } + while (fgets(buffer.data(), buffer.size(), pipe.get()) != nullptr) { + result += buffer.data(); + } + return result; +} + +bool isNumber(const std::string& str) { + return !str.empty() && str.find_first_not_of("0123456789") == std::string::npos; +} + +/* cpu_numa_map builder from lscpu */ +unordered_map<string, int> build_cpu_numa_map() { + unordered_map<string, int> cpuNumaMap; + string result = exec_cmd("lscpu"); + istringstream iss(result); + string line; + + while (getline(iss, line)) { + if (line.find("NUMA node") != string::npos) { + istringstream lineStream(line); + string key, value; + int numaNode; + getline(lineStream, value, ':'); + getline(lineStream, key); + /* what if numa is more than 10 */ + value = value.substr(value.find("NUMA node") + 9, 1); + if (!isNumber(value)) + continue; + numaNode = stoi(value); + key.erase(0, key.find_first_not_of(" \t")); + key.erase(key.find_last_not_of(" \t") + 1); + cpuNumaMap[key]=numaNode; + } + } + return cpuNumaMap; +} + +/* npu_numa_map builder, from npu-smi info -t topo */ +void build_npu_map_map() +{ + if (npu_smi_enable.load() == -1) { + if (exec_cmd("command -v npu-smi").empty()) + npu_smi_enable.store(0); + else + npu_smi_enable.store(1); + } + + if (npu_smi_enable.load() == 0) + return; + + unordered_map<string, int> cpuNumaMap = build_cpu_numa_map(); + string result = exec_cmd("npu-smi info -t topo"); + istringstream iss(result); + string line; + size_t target_token_size = 0; + + cout << "NPU\tCPU_AFFINITY\tNUMA_NODE" << endl; + while (getline(iss, line)) { + istringstream lineStream(line); + string npuStr, numaStr, token; + vector<string> tokens; + + while (lineStream >> token) { + tokens.push_back(token); + } + + if (tokens.size() >= 2 && tokens.back() == "Affinity") { + target_token_size = tokens.size() - 1 + 1; + continue; + } + + if (tokens.size() != target_token_size) + continue; + + int npuId = stoi(tokens[0].substr(3)); + + numaStr = tokens.back(); + cout << npuId << "\t" << numaStr << "\t\t" << cpuNumaMap[numaStr] << endl; + npu_numa_map[npuId] = cpuNumaMap[numaStr]; + } +} + +/* process_npu_map builder, from npu-smi info */ +void get_npu_info(string &npuinfo) +{ + istringstream iss(npuinfo); + string line; + + while (getline(iss, line)) { + istringstream lineStream(line); + string token; + vector<string> tokens; + while (getline(lineStream, token, ' ')) { + if (!token.empty()) { + tokens.push_back(token); + } + } + if (tokens.size() >= 3) { + if (!isNumber(tokens[1]) || !isNumber(tokens[4])) + continue; + int npuId = stoi(tokens[1]); + int processId = stoi(tokens[4]); + process_npu_map[processId] = npuId; + } + } +} + +/* process_npu_map helper */ +int process_npu_find(int processid) { + lock_guard<mutex> lock(pnpu_mutex); + auto it = process_npu_map.find(processid); + + if (npu_smi_enable.load() == 0) + return 0; + + if (it != process_npu_map.end()) { + return it->second; + } else { + string result = exec_cmd("npu-smi info"); + get_npu_info(result); + auto it = process_npu_map.find(processid); + if (it != process_npu_map.end()) + return it->second; + else + return 0; + } +} + +int strategy_init(void) +{ + const char *mntpoint = getenv(MAIO_MNTPOINT); + char *tfilename = getenv(MAIO_TRACE_FILE); + if(!tfilename || !mntpoint) { + fprintf(stderr, "no MAIO_TRACE_FILE or MAIO_MNTPOINT env variable\n"); + return -1; + } + ifstream tfile(tfilename); + string line; + + cgroup_mem=get_cgroup_path(); + memory_limit = read_cgroup_memory(limit_in_bytes_path); + memory_limit_bound = memory_limit * 4 / 5; + cout << "memory_limit: " << memory_limit << " memory_limit_bound: " << memory_limit_bound << endl; + get_mount_option(mntpoint, CACHEDIR); + build_npu_map_map(); + + if(!tfile.is_open()) { + cerr << "Failed to open file:" << tfilename << endl; + return -1; + } + + while(getline(tfile, line)) { + istringstream iss(line); + + string name; + uint64_t off; + uint64_t len; + unsigned int npu; + if (iss >> name >> off >> len >> npu) { + iovec.emplace_back(name, off, len, npu); + io_to_index[ioKey(name, off, len, npu)] = iovec.size() - 1; + } else { + cerr << "Failed to parse line:" << line << endl; + } + } + + tfile.close(); + return 0; +} + +void strategy_exit(void) +{ +} + +int strategy_load(struct maio **io) +{ + int npuid = process_npu_find((*io)->pid); + struct maio_entry *entry; + string pathStr; + char *path; + uint64_t idx = iovec.size(); + int ret = 0; + struct maio *new_io; + + path = fd_path_find((*io)->fd); + pathStr.assign(path); + + ioKey key(pathStr, (*io)->off, (*io)->len, npuid); + auto io_it = io_to_index.lower_bound(key); + if (io_it == io_to_index.end()) { + entry = (*io)->entries; + entry[0].toff = (*io)->off + (*io)->len; + entry[0].tlen = 0; + entry[0].fpath = NULL; + entry[0].tnuma = npu_numa_map[npuid]; + return 1; + } + if (key < io_it->first) { + if (io_it != io_to_index.begin()) { + --io_it; + if (io_it->first.name != pathStr) { + ++io_it; + } + } + } + + idx = io_it->second; + (*io)->flags |= MAIO_WITH_SEQ; + (*io)->curseq = idx; + entry = (*io)->entries; + int ios = 0; + uint64_t memory_usage = read_cgroup_memory(usage_in_bytes_path); + vector<int> io_extra; + + /* fill ios below max_io */ + while (idx < iovec.size()) { + if (iovec[idx].flag == IO_LOADED) { + idx++; + continue; + } + memory_usage += iovec[idx].len / 2; + if (memory_usage > memory_limit_bound) + break; + if (ios >= maio_strategy.max_io) { + io_extra.push_back(idx); + goto next_io; + } + entry[ios].seq = idx; + if (pathStr == iovec[idx].name) { + entry[ios].toff = iovec[idx].off; + entry[ios].tlen = iovec[idx].len; + entry[ios].tnuma = npu_numa_map[npuid]; + } else { + entry[ios].fpath = strdup(iovec[idx].name.c_str()); + entry[ios].toff = iovec[idx].off; + entry[ios].tlen = iovec[idx].len; + entry[ios].tnuma = npu_numa_map[iovec[idx].npu]; + } +next_io: + iovec[idx].flag = IO_LOADED; + idx++; + ios++; + } + + /* fill ios above max_io */ + if (ios > maio_strategy.max_io) { + new_io = (struct maio *)realloc(*io, sizeof(struct maio) + ios * sizeof(struct maio_entry)); + if (!new_io) { + printf("failed to alloc ios:%d maio\n", ios); + return -1; + } + *io = new_io; + entry = (*io)->entries; + for (int i = maio_strategy.max_io; i < ios; ++i) { + int io_idx = io_extra[i - maio_strategy.max_io]; + entry[i].seq = io_idx; + if (pathStr == iovec[io_idx].name) { + entry[i].toff = iovec[io_idx].off; + entry[i].tlen = iovec[io_idx].len; + entry[i].tnuma = npu_numa_map[npuid]; + } else { + entry[i].fpath = strdup(iovec[io_idx].name.c_str()); + entry[i].toff = iovec[io_idx].off; + entry[i].tlen = iovec[io_idx].len; + entry[i].tnuma = npu_numa_map[iovec[io_idx].npu]; + } + } + } + + // printf("file:%s off:%lu len:%lu generate_ios:%d from %d",path, (*io)->off, (*io)->len, ios, io_it->second); + ret = ios; + return ret; +} + +int strategy_evict(struct maio **io) +{ + string pathStr; + char *path; + path = fd_path_find((*io)->fd); + pathStr.assign(path); + ioKey key(pathStr, (*io)->off, (*io)->len, (*io)->pid); + auto io_it = io_to_index.lower_bound(key); + int dist = 0; + size_t i = 0, io_idx = io_it->second; + struct maio_entry *entry; + struct maio *new_io; + uint64_t evict_memory = 0; + uint64_t memory_usage = read_cgroup_memory(usage_in_bytes_path); + + if (memory_usage < (memory_limit_bound * 3 / 4)) + return 0; + dist = io_idx - evict_idx; + if (dist < 0) + return 0; + if (static_cast<size_t>(dist) < iovec.size() / 8 && io_it != io_to_index.end()) + return 0; + size_t evict_win = 0; + if (io_it != io_to_index.end()) { + evict_win = min(iovec.size() / 10, io_idx - 1); + } else { + evict_win = dist; + } + + new_io = (struct maio*)realloc(*io, sizeof(struct maio) + evict_win * sizeof(struct maio_entry)); + if (!new_io) + return -1; + *io = new_io; + entry = new_io->entries; + + for (i = 0; i < evict_win && evict_idx < iovec.size(); ++i) { + evict_memory += iovec[evict_idx].len; + if (evict_memory > memory_limit_bound / 8) + break; + entry[i].fpath = strdup(iovec[evict_idx].name.c_str()); + entry[i].toff = iovec[evict_idx].off; + entry[i].tlen = iovec[evict_idx].len; + evict_idx++; + iovec[evict_idx].flag = IO_EVICTED; + } + return i; +} + +const struct maio_operation maio_strategy = { + .max_io = 500, + .init = strategy_init, + .exit = strategy_exit, + .load = strategy_load, + .evict = strategy_evict, +}; + +struct maio_operation *register_strategy() +{ + return (struct maio_operation *)&maio_strategy; +} diff --git a/tools/mfs/maio-utils/test/strategy_template.h b/tools/mfs/maio-utils/test/strategy_template.h new file mode 100644 index 000000000000..6599b68754c9 --- /dev/null +++ b/tools/mfs/maio-utils/test/strategy_template.h @@ -0,0 +1,21 @@ +#ifndef STRATEGY_TEMPLATE_H +#define STRATEGY_TEMPLATE_H + +#ifdef __cplusplus +extern "C" { +#endif + +int strategy_init(void); +void strategy_exit(void); +int strategy_load(struct maio **io); +int strategy_evict(struct maio *io); + +extern const struct maio_operation maio_strategy; + +struct maio_operation *register_strategy(); + +#ifdef __cplusplus +} +#endif + +#endif diff --git a/tools/mfs/maio-utils/test/strategy_toend.c b/tools/mfs/maio-utils/test/strategy_toend.c new file mode 100644 index 000000000000..f2208281f8ee --- /dev/null +++ b/tools/mfs/maio-utils/test/strategy_toend.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2025 Huawei Technologies Co., Ltd + */ +#include "maio.h" +#include <stddef.h> + +int demo_init(void) +{ + return 0; +} + +void demo_exit(void) +{ +} + +int demo_load(struct maio **io) +{ + struct maio_entry *entry; + + entry = (*io)->entries; + entry[0].toff = (*io)->off + (*io)->len; + /* Read Ahead until the end */ + entry[0].tlen = 0; + entry[0].fpath = NULL; + entry[0].tnuma = -1; + return 1; +} + +int demo_evict(struct maio **io) +{ + ((void)io); + return 0; +} + +const struct maio_operation demo_strategy = { + .max_io = 1, + .init = demo_init, + .exit = demo_exit, + .load = demo_load, + .evict = demo_evict, +}; + +struct maio_operation *register_strategy() +{ + return (struct maio_operation *)&demo_strategy; +} diff --git a/tools/mfs/maio-utils/test/trace_analyse.py b/tools/mfs/maio-utils/test/trace_analyse.py new file mode 100644 index 000000000000..c25d1ce364df --- /dev/null +++ b/tools/mfs/maio-utils/test/trace_analyse.py @@ -0,0 +1,87 @@ +def merge_intervals(intervals): + """ + 合并区间 + :param intervals: 区间列表，每个区间是一个元组 (start, end) + :return: 合并后的区间列表 + """ + if not intervals: + return [] + + # 按起始位置排序 + intervals.sort(key=lambda x: x[0]) + + merged = [intervals[0]] + for current in intervals[1:]: + last_merged = merged[-1] + if current[0] <= last_merged[1]: # 有重叠 + merged[-1] = (last_merged[0], max(last_merged[1], current[1])) + else: + merged.append(current) + + return merged + +def process_file(input_file): + """ + 处理输入文件 + :param input_file: 输入文件路径 + :return: 每个文件的合并区间和总大小 + """ + from collections import defaultdict + + # 使用字典按文件名分组 + file_intervals = defaultdict(list) + + with open(input_file, 'r') as f: + for line in f: + parts = line.strip().split() + if len(parts) < 3: + print(f"跳过无效行: {line.strip()}") + continue + + # 解析文件名、起始位置、大小 + filename, start, size = parts[:3] + start = int(start) + size = int(size) + + # 计算区间 + end = start + size + file_intervals[filename].append((start, end)) + + # 合并每个文件的区间 + merged_results = {} + for filename, intervals in file_intervals.items(): + merged_intervals = merge_intervals(intervals) + # 计算合并后的区间总大小 + total_size = sum(end - start for start, end in merged_intervals) + merged_results[filename] = { + "merged_intervals": merged_intervals, + "total_size": total_size + } + + return merged_results + +def main(): + import sys + + if len(sys.argv) != 2: + print("用法: python script.py <输入文件>") + sys.exit(1) + + input_file = sys.argv[1] + + merged_results = process_file(input_file) + + whole_result=0 + + for filename, result in merged_results.items(): + print(f"文件: {filename}") + # print("合并后的区间:") + # for interval in result["merged_intervals"]: + # print(f"起始位置: {interval[0]}, 结束位置: {interval[1]}") + print(f"所有区间内数据的总大小: {result['total_size']} 字节") + print("-" * 40) + whole_result+=result['total_size'] + print(f"所有文件内数据的总大小: {whole_result} 字节") + +if __name__ == "__main__": + main() diff --git a/tools/mfs/maio-utils/test/trace_gen.py b/tools/mfs/maio-utils/test/trace_gen.py new file mode 100644 index 000000000000..d050fa48801c --- /dev/null +++ b/tools/mfs/maio-utils/test/trace_gen.py @@ -0,0 +1,116 @@ +import argparse +import os +import sys + +FILENAME_IDX = 0 +OFF_IDX = 1 +LEN_IDX = 2 +NUMA_IDX = 3 +OFF_BOUND = 1024 * 1024 * 4096 + +class ReplayHintGenerator(object): + def __init__(self, trace_file, output_file): + self.output_file = output_file + self.trace_file = trace_file + self.data_list = [] + + def generate_hint(self): + with open(self.output_file, 'w') as f: + for data in self.data_list: + data_off = data[OFF_IDX] + data_len = data[LEN_IDX] + print(data_off) + step = (512 * 1024 * 1024) + while data_len: + if data_len < step: + step = data_len + print(f"{data[FILENAME_IDX]} {data_off} {step} {data[NUMA_IDX]}", file=f) + data_len-=step + data_off+=step + + def parse_trace(self): + file_map_index={} + with open(self.trace_file, 'r') as f: + for line in f: + parts = line.strip().split(' ') + + filename, off, length, numaid = parts + off = int(off) + length = int(length) + numaid = int(numaid) + if self.data_list: + tail_data = self.data_list[-1] + ''' + 首先尝试跟末尾的数据合并: + 如若跟末尾的数据是同一个文件跟numaid, + 两者之间的距离小于设定值, + 就进行合并 + ''' + if (tail_data[FILENAME_IDX] == filename and tail_data[NUMA_IDX] == numaid): + tail_off = tail_data[OFF_IDX] + tail_end = tail_data[OFF_IDX] + tail_data[LEN_IDX] + end = off + length + abs_off = max(abs(off - tail_end), abs(tail_off - end)) + if abs_off < OFF_BOUND: + tail_data[OFF_IDX] = min(tail_off, off) + tail_data[LEN_IDX] = max(tail_end, end) - tail_data[OFF_IDX] + continue + else: + ''' + 否则跟之前同一文件和numaid的数据进行合并 + 如若两者之间距离小于设定值， + 就进行合并 + ''' + key = (filename, numaid) + if key in file_map_index: + index = file_map_index[key] + data = self.data_list[index] + data_off = data[OFF_IDX] + data_end = data[OFF_IDX] + data[LEN_IDX] + end = off + length + abs_off = max(abs(off - data_end), abs(data_off - end)) + if abs_off < OFF_BOUND: + data[OFF_IDX] = min(data_off, off) + data[LEN_IDX] = max(data_end, end) - data[OFF_IDX] + continue + self.data_list.append([filename, off, length, numaid]) + file_map_index[(filename, numaid)] = len(self.data_list) - 1 + + +def main(agrv): + """ + Parse the argument + """ + parser = argparse.ArgumentParser('model trace parser') + parser.add_argument('--trace_file', + required=True, + type=str, + help='trace source') + parser.add_argument('--output_file', + required=True, + type=str, + help='output of hint file') + try: + args = parser.parse_args() + trace_file = args.trace_file + output_file = args.output_file + if not os.path.exists(trace_file): + print("{trace_file} not exist") + return -1 + + hint_generator=ReplayHintGenerator(trace_file, output_file) + hint_generator.parse_trace() + hint_generator.generate_hint() + return 0 + except Exception as e: + print(f"Parse model trace exception:{str(e)}") + return -1 + +if __name__ == '__main__': + try: + ret = main(sys.argv[1:]) + except Exception as main_e: + print(str(main_e)) + ret = -1 + sys.exit(ret) + -- 2.34.1

2 1

[PATCH OLK-6.6 0/1] Fix TLBI broadcast optimization loss and incorrect dvmbm handling
by Tian Zheng 13 Mar '26

13 Mar '26

Fix 1 In the TLBI broadcast-optimization feature, the SYS_LSUDVM_CTRL_EL2 register controls whether the feature is enabled. When LPI low-power mode is enabled, this register is cleared as the pCPU powers down into LPI mode, causing the TLBI broadcast optimization to stop working. The fix saves and restores this control register in the callbacks for entering and exiting LPI mode. Fix 2 The current TLBI broadcast-optimization logic only supports normal VMs. If the feature is enabled globally, VMs that are not yet adapted for it, such as CCA will use an incorrect TLBI broadcast bitmap, which can cause a panic in CCA VMs. The fix moves the actual enable/disable of the dvmbm functionality into the vcpu load and vcpu put functions. Tian Zheng (1): KVM: arm64: Fix CCA guest panic when dvmbm is enabled arch/arm64/kvm/hisilicon/hisi_virt.c | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) -- 2.33.0

1 1

[PATCH v13 00/12] arm64: entry: Convert to Generic Entry
by Jinjie Ruan 13 Mar '26

13 Mar '26

Currently, x86, Riscv, Loongarch use the Generic Entry which makes maintainers' work easier and codes more elegant. arm64 has already successfully switched to the Generic IRQ Entry in commit b3cf07851b6c ("arm64: entry: Switch to generic IRQ entry"), it is time to completely convert arm64 to Generic Entry. The goal is to bring arm64 in line with other architectures that already use the generic entry infrastructure, reducing duplicated code and making it easier to share future changes in entry/exit paths, such as "Syscall User Dispatch". This patch set is rebased on v7.0-rc1. And the performance was measured on Kunpeng 920 using "perf bench basic syscall" with "arm64.nopauth selinux=0 audit=1". On the basis of optimizing el0_svc_common(), the performance are below: | Metric | W/O Generic Entry | With Generic Entry opt| Change | | ---------- | ----------------- | ------------------ | ------ | | Total time | 2.487 [sec] | 2.264 [sec] | ↓9.0% | | usecs/op | 0.248780 | 0.226481 | ↓9.0% | | ops/sec | 4,019,620 | 4,415,383 | ↑9.8% | Therefore, after the optimization, ARM64 System Call performance improved by approximately 9%. It was tested ok with following test cases on kunpeng920 and QEMU virt platform: - Stress-ng CPU stress test. - Hackbench stress test. - "sud" selftest testcase. - get_set_sud, get_syscall_info, set_syscall_info, peeksiginfo in tools/testing/selftests/ptrace. - breakpoint_test_arm64 in selftests/breakpoints. - syscall-abi and ptrace in tools/testing/selftests/arm64/abi - fp-ptrace, sve-ptrace, za-ptrace in selftests/arm64/fp. - vdso_test_getrandom in tools/testing/selftests/vDSO - Strace tests. The test QEMU configuration is as follows: qemu-system-aarch64 \ -M virt,gic-version=3,virtualization=on,mte=on \ -cpu max,pauth-impdef=on \ -kernel Image \ -smp 8,sockets=1,cores=4,threads=2 \ -m 512m \ -nographic \ -no-reboot \ -device virtio-rng-pci \ -append "root=/dev/vda rw console=ttyAMA0 kgdboc=ttyAMA0,115200 \ earlycon preempt=voluntary irqchip.gicv3_pseudo_nmi=1" \ -drive if=none,file=images/rootfs.ext4,format=raw,id=hd0 \ -device virtio-blk-device,drive=hd0 \ Changes in v13: - Rebased on v7.0-rc3, so drop the firt applied arm64 patch. - Use generic TIF bits to enables RSEQ optimization. - Update most of the commit message to make it more clear. - Link to v12: https://lore.kernel.org/all/20260203133728.848283-5-ruanjinjie@huawei.com/ Changes in v12: - Rebased on "sched/core", so remove the four generic entry patches. - Move "Expand secure_computing() in place" and "Use syscall_get_arguments() helper" patch forward, which will group all non-functional cleanups at the front. - Adjust the explanation for moving rseq_syscall() before audit_syscall_exit(). - Link to v11: https://lore.kernel.org/all/20260128031934.3906955-1-ruanjinjie@huawei.com/ Changes in v11: - Remove unused syscall in syscall_trace_enter(). - Update and provide a detailed explanation of the differences after moving rseq_syscall() before audit_syscall_exit(). - Rebased on arm64 (for-next/entry), and remove the first applied 3 patchs. - syscall_exit_to_user_mode_work() for arch reuse instead of adding new syscall_exit_to_user_mode_work_prepare() helper. - Link to v10: https://lore.kernel.org/all/20251222114737.1334364-1-ruanjinjie@huawei.com/ Changes in v10: - Rebased on v6.19-rc1, rename syscall_exit_to_user_mode_prepare() to syscall_exit_to_user_mode_work_prepare() to avoid conflict. - Also inline syscall_trace_enter(). - Support aarch64 for sud_benchmark. - Update and correct the commit message. - Add Reviewed-by. - Link to v9: https://lore.kernel.org/all/20251204082123.2792067-1-ruanjinjie@huawei.com/ Changes in v9: - Move "Return early for ptrace_report_syscall_entry() error" patch ahead to make it not introduce a regression. - Not check _TIF_SECCOMP/SYSCALL_EMU for syscall_exit_work() in a separate patch. - Do not report_syscall_exit() for PTRACE_SYSEMU_SINGLESTEP in a separate patch. - Add two performance patch to improve the arm64 performance. - Add Reviewed-by. - Link to v8: https://lore.kernel.org/all/20251126071446.3234218-1-ruanjinjie@huawei.com/ Changes in v8: - Rename "report_syscall_enter()" to "report_syscall_entry()". - Add ptrace_save_reg() to avoid duplication. - Remove unused _TIF_WORK_MASK in a standalone patch. - Align syscall_trace_enter() return value with the generic version. - Use "scno" instead of regs->syscallno in el0_svc_common(). - Move rseq_syscall() ahead in a standalone patch to clarify it clearly. - Rename "syscall_trace_exit()" to "syscall_exit_work()". - Keep the goto in el0_svc_common(). - No argument was passed to __secure_computing() and check -1 not -1L. - Remove "Add has_syscall_work() helper" patch. - Move "Add syscall_exit_to_user_mode_prepare() helper" patch later. - Add miss header for asm/entry-common.h. - Update the implementation of arch_syscall_is_vdso_sigreturn(). - Add "ARCH_SYSCALL_WORK_EXIT" to be defined as "SECCOMP | SYSCALL_EMU" to keep the behaviour unchanged. - Add more testcases test. - Add Reviewed-by. - Update the commit message. - Link to v7: https://lore.kernel.org/all/20251117133048.53182-1-ruanjinjie@huawei.com/ Jinjie Ruan (11): arm64/ptrace: Refactor syscall_trace_enter/exit() to accept flags parameter arm64/ptrace: Expand secure_computing() in place arm64/ptrace: Use syscall_get_arguments() helper for audit arm64: ptrace: Move rseq_syscall() before audit_syscall_exit() arm64: syscall: Introduce syscall_exit_to_user_mode_work() arm64/ptrace: Define and use _TIF_SYSCALL_EXIT_WORK arm64/ptrace: Skip syscall exit reporting for PTRACE_SYSEMU_SINGLESTEP arm64: entry: Convert to generic entry arm64: Inline el0_svc_common() s390: Rename TIF_SINGLE_STEP to TIF_SINGLESTEP arm64: Use generic TIF bits for common thread flags kemal (1): selftests: sud_test: Support aarch64 arch/arm64/Kconfig | 3 +- arch/arm64/include/asm/entry-common.h | 76 ++++++++++++ arch/arm64/include/asm/syscall.h | 19 ++- arch/arm64/include/asm/thread_info.h | 76 ++++-------- arch/arm64/kernel/debug-monitors.c | 7 ++ arch/arm64/kernel/ptrace.c | 115 ------------------ arch/arm64/kernel/signal.c | 2 +- arch/arm64/kernel/syscall.c | 29 ++--- arch/s390/include/asm/thread_info.h | 7 +- arch/s390/kernel/process.c | 2 +- arch/s390/kernel/ptrace.c | 20 +-- arch/s390/kernel/signal.c | 6 +- arch/x86/include/asm/thread_info.h | 6 +- include/asm-generic/thread_info_tif.h | 5 + .../syscall_user_dispatch/sud_benchmark.c | 2 +- .../syscall_user_dispatch/sud_test.c | 4 + 16 files changed, 166 insertions(+), 213 deletions(-) -- 2.34.1

1 12

[PATCH v3 00/10] arm_mpam: Introduce the Narrow-PARTID feature for MPAM driver
by Zeng Heng 13 Mar '26

13 Mar '26

The patchset is based on mpam_resctrl_glue_v5_debugfs branch of https://gitlab.arm.com/linux-arm/linux-bh.git repository. The narrow-partid feature in MPAM allows for a more efficient use of PARTIDs by enabling a many-to-one mapping of reqpartids (requested PARTIDs) to intpartids (internal PARTIDs). This mapping reduces the number of unique PARTIDs needed, thus allowing more tasks or processes to be monitored and managed with the available resources. For a mixture of MSCs system, for MSCs that do not support narrow-partid, we use the PARTIDs exceeding the number of closids as reqPARTIDs for expanding the monitoring groups. Therefore, we will expand the information contained in the RMID, so that it includes not only PMG, but also reqPARTIDs information. The new RMID would be like: RMID = reqPARTID * NUM_PMG + PMG Each control group has m (req)PARTIDs, which are used to expand the number of monitoring groups under one control group. Therefore, the number of monitoring groups is no longer limited by the range of MPAM's PMG, which enhances the extensibility of the system's monitoring capabilities. --- Compared with v2: - Add dynamic reqPARTID allocation implementation. - Patch 4 has been merged into the repository, dropped from this series. Compared with v1: - Redefine the RMID information. - Refactor the resctrl_arch_rmid_idx_decode() and resctrl_arch_rmid_idx_encode(). - Simplify closid_rmid2reqpartid() to rmid2reqpartid() and replace it accordingly. Compared with RFC-v4: - Rebase the patch set on the v6.14-rc1 branch. Compared with RFC-v3: - Add limitation of the Narrow-PARTID feature (See Patch 2). - Remove redundant reqpartid2closid() and reqpartid_pmg2rmid(). - Refactor closid_rmid2reqpartid() partially. - Merge the PARTID conversion-related patches into a single patch for bisectability. - Skip adaptation of resctrl_arch_set_rmid() which is going to be removed. Compared with RFC-v2: - Refactor closid/rmid pair translation. - Simplify the logic of synchronize configuration. - Remove reqPARTID source bitmap. Compared with RFC-v1: - Rebase this patch set on latest MPAM driver of the v6.12-rc1 branch. v2: https://lore.kernel.org/all/20250222112448.2438586-1-zengheng4@huawei.com/ v1: https://lore.kernel.org/all/20250217031852.2014939-1-zengheng4@huawei.com/ RFC-v4: https://lore.kernel.org/all/20250104101224.873926-1-zengheng4@huawei.com/ RFC-v3: https://lore.kernel.org/all/20241207092136.2488426-1-zengheng4@huawei.com/ RFC-v2: https://lore.kernel.org/all/20241119135104.595630-1-zengheng4@huawei.com/ RFC-v1: https://lore.kernel.org/all/20241114135037.918470-1-zengheng4@huawei.com/ --- Ben Horgan (1): arm64/sysreg: Add MPAMSM_EL1 register Zeng Heng (9): arm_mpam: Add intPARTID and reqPARTID support for narrow PARTID feature arm_mpam: Disable Narrow-PARTID when MBA lacks support arm_mpam: Refactor rmid to reqPARTID/PMG mapping arm_mpam: Propagate control group config to sub-monitoring groups fs/resctrl: Add rmid_entry state helpers arm_mpam: Implement dynamic reqPARTID allocation for monitoring groups fs/resctrl: Wire up rmid expansion and reclaim functions arm64/mpam: Add mpam_sync_config() for dynamic rmid expansion fs/resctrl: Prevent rmid parsing errors by flushing limbo on umount Documentation/arch/arm64/index.rst | 1 + Documentation/arch/arm64/mpam.rst | 94 + Documentation/arch/arm64/silicon-errata.rst | 9 + arch/arm64/Kconfig | 6 +- arch/arm64/include/asm/el2_setup.h | 3 +- arch/arm64/include/asm/mpam.h | 96 + arch/arm64/include/asm/resctrl.h | 2 + arch/arm64/include/asm/thread_info.h | 3 + arch/arm64/kernel/Makefile | 1 + arch/arm64/kernel/cpufeature.c | 21 +- arch/arm64/kernel/mpam.c | 62 + arch/arm64/kernel/process.c | 7 + arch/arm64/kvm/hyp/include/hyp/switch.h | 12 +- arch/arm64/kvm/hyp/nvhe/hyp-main.c | 9 + arch/arm64/kvm/hyp/vhe/sysreg-sr.c | 16 + arch/arm64/kvm/sys_regs.c | 2 + arch/arm64/tools/sysreg | 8 + arch/x86/include/asm/resctrl.h | 7 + drivers/resctrl/Kconfig | 9 +- drivers/resctrl/Makefile | 1 + drivers/resctrl/mpam_devices.c | 340 ++- drivers/resctrl/mpam_internal.h | 112 +- drivers/resctrl/mpam_resctrl.c | 2094 +++++++++++++++++++ drivers/resctrl/test_mpam_resctrl.c | 364 ++++ fs/resctrl/monitor.c | 50 +- fs/resctrl/rdtgroup.c | 24 +- include/linux/arm_mpam.h | 49 + include/linux/resctrl.h | 21 + 28 files changed, 3368 insertions(+), 55 deletions(-) create mode 100644 Documentation/arch/arm64/mpam.rst create mode 100644 arch/arm64/include/asm/mpam.h create mode 100644 arch/arm64/include/asm/resctrl.h create mode 100644 arch/arm64/kernel/mpam.c create mode 100644 drivers/resctrl/mpam_resctrl.c create mode 100644 drivers/resctrl/test_mpam_resctrl.c -- 2.25.1

1 12

[PATCH OLK-6.6] arm64/mpam: Fix warning of schedule state in resctrl_arch_mon_ctx_alloc()
by Zeng Heng 13 Mar '26

13 Mar '26

hulk inclusion category: bugfix bugzilla: https://atomgit.com/openeuler/kernel/issues/8686 ------------------ resctrl_arch_mon_ctx_alloc() triggers a scheduling state warning when calling kmalloc() while the task is in a non-running state: do not call blocking ops when !TASK_RUNNING; state=1 set at prepare_to_wait WARNING: CPU: 78 PID: 12592 at kernel/sched/core.c:10584 _might_sleep Call trace: _might_sleep+0x1cc/0xf8 _kmalloc_cache_alloc_node+0x3a0/0x4e0 kmalloc_trace+0x44/0x120 resctrl_arch_mon_ctx_alloc+0xf0/0x178 mon_event_read+0xa0/0x308 mkdir_mondata_subdir+0x24c/0x330 mkdir_mondata_all+0x17c/0x248 rdt_get_tree+0x2e8/0x680 vfs_get_tree+0x5c/0x190 do_new_mount+0x27c/0x408 path_mount+0x2ac/0x448 arm64_sys_mount+0x1d4/0x228 Ensure the allocation is performed in TASK_RUNNING state to avoid schedule state corrupted. Fixes: 9119da143939 ("arm_mpam: resctrl: Allow resctrl to allocate monitors") Signed-off-by: Zeng Heng <zengheng4(a)huawei.com> --- drivers/platform/mpam/mpam_resctrl.c | 25 +++---------------------- 1 file changed, 3 insertions(+), 22 deletions(-) diff --git a/drivers/platform/mpam/mpam_resctrl.c b/drivers/platform/mpam/mpam_resctrl.c index 1a26a0ed2cff..b6681f328aaa 100644 --- a/drivers/platform/mpam/mpam_resctrl.c +++ b/drivers/platform/mpam/mpam_resctrl.c @@ -388,11 +388,11 @@ struct rdt_resource *resctrl_arch_get_resource(enum resctrl_res_level l) return &mpam_resctrl_exports[l].resctrl_res; } -static void *resctrl_arch_mon_ctx_alloc_no_wait(struct rdt_resource *r, - int evtid) +void *resctrl_arch_mon_ctx_alloc(struct rdt_resource *r, int evtid) { - u32 *ret = kmalloc(sizeof(*ret), GFP_KERNEL); + u32 *ret; + ret = kmalloc(sizeof(*ret), GFP_KERNEL); if (!ret) return ERR_PTR(-ENOMEM); @@ -400,25 +400,6 @@ static void *resctrl_arch_mon_ctx_alloc_no_wait(struct rdt_resource *r, return ret; } -void *resctrl_arch_mon_ctx_alloc(struct rdt_resource *r, int evtid) -{ - DEFINE_WAIT(wait); - void *ret; - - might_sleep(); - - do { - prepare_to_wait(&resctrl_mon_ctx_waiters, &wait, - TASK_INTERRUPTIBLE); - ret = resctrl_arch_mon_ctx_alloc_no_wait(r, evtid); - if (PTR_ERR(ret) == -ENOSPC) - schedule(); - } while (PTR_ERR(ret) == -ENOSPC && !signal_pending(current)); - finish_wait(&resctrl_mon_ctx_waiters, &wait); - - return ret; -} - void resctrl_arch_mon_ctx_free(struct rdt_resource *r, int evtid, void *arch_mon_ctx) { -- 2.25.1

2 1

[PATCH OLK-6.6] selftests/bpf: Add cross-build support for urandom_read et al
by Pu Lehui 12 Mar '26

12 Mar '26

From: Björn Töpel <bjorn(a)rivosinc.com> mainline inclusion from mainline-v6.7-rc1 commit 97a79e502e25e27a65b0506c9fb210cb2d89b52e category: bugfix bugzilla: https://atomgit.com/openeuler/kernel/issues/8638 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Some userland programs in the BPF test suite, e.g. urandom_read, is missing cross-build support. Add cross-build support for these programs Signed-off-by: Björn Töpel <bjorn(a)rivosinc.com> Signed-off-by: Andrii Nakryiko <andrii(a)kernel.org> Link: https://lore.kernel.org/bpf/20231004122721.54525-2-bjorn@kernel.org Conflicts: tools/testing/selftests/bpf/Makefile [ctx conflicts] Signed-off-by: Pu Lehui <pulehui(a)huawei.com> --- tools/testing/selftests/bpf/Makefile | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 8ce50befca91..e97ec89fe83d 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -208,15 +208,17 @@ endif # do not fail. Static builds leave urandom_read relying on system-wide shared libraries. $(OUTPUT)/liburandom_read.so: urandom_read_lib1.c urandom_read_lib2.c $(call msg,LIB,,$@) - $(Q)$(CLANG) $(filter-out -static,$(CFLAGS) $(LDFLAGS)) \ + $(Q)$(CLANG) $(CLANG_TARGET_ARCH) \ + $(filter-out -static,$(CFLAGS) $(LDFLAGS)) \ $^ $(filter-out -static,$(LDLIBS)) \ -fuse-ld=$(LLD) -Wl,-znoseparate-code -Wl,--build-id=sha1 \ -fPIC -shared -o $@ $(OUTPUT)/urandom_read: urandom_read.c urandom_read_aux.c $(OUTPUT)/liburandom_read.so $(call msg,BINARY,,$@) - $(Q)$(CLANG) $(filter-out -static,$(CFLAGS) $(LDFLAGS)) $(filter %.c,$^) \ - -lurandom_read $(filter-out -static,$(LDLIBS)) -L$(OUTPUT) \ + $(Q)$(CLANG) $(CLANG_TARGET_ARCH) \ + $(filter-out -static,$(CFLAGS) $(LDFLAGS)) $(filter %.c,$^) \ + -lurandom_read $(filter-out -static,$(LDLIBS)) -L$(OUTPUT) \ -fuse-ld=$(LLD) -Wl,-znoseparate-code -Wl,--build-id=sha1 \ -Wl,-rpath=. -o $@ -- 2.34.1

2 1

[PATCH OLK-6.6] arm64/mpam: Fix warning of schedule state in resctrl_arch_mon_ctx_alloc()
by Zeng Heng 12 Mar '26

12 Mar '26

Offering: HULK hulk inclusion category: bugfix bugzilla: https://atomgit.com/openeuler/kernel/issues/8686 ------------------ resctrl_arch_mon_ctx_alloc() triggers a scheduling state warning when calling kmalloc() while the task is in a non-running state: do not call blocking ops when !TASK_RUNNING; state=1 set at prepare_to_wait WARNING: CPU: 78 PID: 12592 at kernel/sched/core.c:10584 _might_sleep Call trace: _might_sleep+0x1cc/0xf8 _kmalloc_cache_alloc_node+0x3a0/0x4e0 kmalloc_trace+0x44/0x120 resctrl_arch_mon_ctx_alloc+0xf0/0x178 mon_event_read+0xa0/0x308 mkdir_mondata_subdir+0x24c/0x330 mkdir_mondata_all+0x17c/0x248 rdt_get_tree+0x2e8/0x680 vfs_get_tree+0x5c/0x190 do_new_mount+0x27c/0x408 path_mount+0x2ac/0x448 arm64_sys_mount+0x1d4/0x228 Ensure the allocation is performed in TASK_RUNNING state to avoid schedule state corrupted. Fixes: 9119da143939 ("arm_mpam: resctrl: Allow resctrl to allocate monitors") Signed-off-by: Zeng Heng <zengheng4(a)huawei.com> --- drivers/platform/mpam/mpam_resctrl.c | 25 +++---------------------- 1 file changed, 3 insertions(+), 22 deletions(-) diff --git a/drivers/platform/mpam/mpam_resctrl.c b/drivers/platform/mpam/mpam_resctrl.c index 1a26a0ed2cff..b6681f328aaa 100644 --- a/drivers/platform/mpam/mpam_resctrl.c +++ b/drivers/platform/mpam/mpam_resctrl.c @@ -388,11 +388,11 @@ struct rdt_resource *resctrl_arch_get_resource(enum resctrl_res_level l) return &mpam_resctrl_exports[l].resctrl_res; } -static void *resctrl_arch_mon_ctx_alloc_no_wait(struct rdt_resource *r, - int evtid) +void *resctrl_arch_mon_ctx_alloc(struct rdt_resource *r, int evtid) { - u32 *ret = kmalloc(sizeof(*ret), GFP_KERNEL); + u32 *ret; + ret = kmalloc(sizeof(*ret), GFP_KERNEL); if (!ret) return ERR_PTR(-ENOMEM); @@ -400,25 +400,6 @@ static void *resctrl_arch_mon_ctx_alloc_no_wait(struct rdt_resource *r, return ret; } -void *resctrl_arch_mon_ctx_alloc(struct rdt_resource *r, int evtid) -{ - DEFINE_WAIT(wait); - void *ret; - - might_sleep(); - - do { - prepare_to_wait(&resctrl_mon_ctx_waiters, &wait, - TASK_INTERRUPTIBLE); - ret = resctrl_arch_mon_ctx_alloc_no_wait(r, evtid); - if (PTR_ERR(ret) == -ENOSPC) - schedule(); - } while (PTR_ERR(ret) == -ENOSPC && !signal_pending(current)); - finish_wait(&resctrl_mon_ctx_waiters, &wait); - - return ret; -} - void resctrl_arch_mon_ctx_free(struct rdt_resource *r, int evtid, void *arch_mon_ctx) { -- 2.25.1

2 1

[PATCH OLK-6.6] Revert "drivers: core: synchronize really_probe() and dev_uevent()"
by Lin Ruifeng 12 Mar '26

12 Mar '26

From: Dmitry Torokhov <dmitry.torokhov(a)gmail.com> stable inclusion from stable-v6.6.89 commit d29c2d53357fd35f24b7acba594725a5be6404d7 category: bugfix bugzilla: https://atomgit.com/openeuler/kernel/issues/8715 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit dc1771f718548f7d4b93991b174c6e7b5e1ba410 upstream. This reverts commit c0a40097f0bc81deafc15f9195d1fb54595cd6d0. Probing a device can take arbitrary long time. In the field we observed that, for example, probing a bad micro-SD cards in an external USB card reader (or maybe cards were good but cables were flaky) sometimes takes longer than 2 minutes due to multiple retries at various levels of the stack. We can not block uevent_show() method for that long because udev is reading that attribute very often and that blocks udev and interferes with booting of the system. The change that introduced locking was concerned with dev_uevent() racing with unbinding the driver. However we can handle it without locking (which will be done in subsequent patch). There was also claim that synchronization with probe() is needed to properly load USB drivers, however this is a red herring: the change adding the lock was introduced in May of last year and USB loading and probing worked properly for many years before that. Revert the harmful locking. Cc: stable(a)vger.kernel.org Signed-off-by: Dmitry Torokhov <dmitry.torokhov(a)gmail.com> Reviewed-by: Masami Hiramatsu (Google) <mhiramat(a)kernel.org> Link: https://lore.kernel.org/r/20250311052417.1846985-1-dmitry.torokhov@gmail.com Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Lin Ruifeng <linruifeng4(a)huawei.com> --- drivers/base/core.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/base/core.c b/drivers/base/core.c index 9872ce765eaa..8a4c3bc7bafa 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2707,11 +2707,8 @@ static ssize_t uevent_show(struct device *dev, struct device_attribute *attr, if (!env) return -ENOMEM; - /* Synchronize with really_probe() */ - device_lock(dev); /* let the kset specific function add its keys */ retval = kset->uevent_ops->uevent(&dev->kobj, env); - device_unlock(dev); if (retval) goto out; -- 2.43.0

2 1

[PATCH OLK-6.6 0/3] Fix RT priority Setting
by Liu Kai 12 Mar '26

12 Mar '26

Fix RT priority Setting Liu Kai (3): xsched: refactor xse_this_grp_xcu to xse_this_cfs_rq for clarity and correctness xsched: fix typo in xcu cgroup subsys released callback name xsched: initialize tgid before configuring RT priority include/linux/xsched.h | 29 ++++++++++++++--------------- kernel/xsched/cfs.c | 2 +- kernel/xsched/cgroup.c | 4 ++-- kernel/xsched/core.c | 3 +-- 4 files changed, 18 insertions(+), 20 deletions(-) -- 2.34.1

2 4

[PATCH OLK-6.6 0/3] optimize lightweight load balancing
by Chen Jinghuang 12 Mar '26

12 Mar '26

*** BLURB HERE *** Chen Jinghuang (2): sched: Fix kabi breakage of struct sched_domain for newidle_stats sched: expand sysctl_sched_features to unsigned long Peter Zijlstra (Intel) (1): sched/fair: Proportional newidle balance include/linux/sched/topology.h | 5 ++++ kernel/sched/core.c | 5 +++- kernel/sched/fair.c | 50 +++++++++++++++++++++++++++++++--- kernel/sched/features.h | 5 ++++ kernel/sched/sched.h | 9 +++++- kernel/sched/topology.c | 6 ++++ 6 files changed, 74 insertions(+), 6 deletions(-) -- 2.34.1

2 4

[PATCH OLK-5.10] scsi: hisi_sas: Change the debugfs parameters dump count default value
by Yihang Li 12 Mar '26

12 Mar '26

driver inclusion category: feature bugzilla: https://atomgit.com/openeuler/kernel/issues/8713 ----------------------------------------------------------------------------- The memory allocation time of the DFX is changed from device initialization to dump occurs, so restore the default setting hisi_sas_debugfs_dump_count to 50. Signed-off-by: Yihang Li <liyihang9(a)h-partners.com> --- drivers/scsi/hisi_sas/hisi_sas_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index a525d484d6e2..c58b77902782 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -2955,12 +2955,12 @@ EXPORT_SYMBOL_GPL(hisi_sas_remove); #if IS_ENABLED(CONFIG_SCSI_HISI_SAS_DEBUGFS_DEFAULT_ENABLE) #define DEBUGFS_ENABLE_DEFAULT "enabled" bool hisi_sas_debugfs_enable = true; +u32 hisi_sas_debugfs_dump_count = 50; #else #define DEBUGFS_ENABLE_DEFAULT "disabled" bool hisi_sas_debugfs_enable; -#endif - u32 hisi_sas_debugfs_dump_count = 1; +#endif EXPORT_SYMBOL_GPL(hisi_sas_debugfs_enable); module_param_named(debugfs_enable, hisi_sas_debugfs_enable, bool, 0444); -- 2.33.0

2 1

[PATCH OLK-5.10] nfsd: provide locking for v4_end_grace
by Li Lingfeng 12 Mar '26

12 Mar '26

From: NeilBrown <neil(a)brown.name> stable inclusion from stable-v5.10.248 commit ca97360860eb02e3ae4ba42c19b439a0fcecbf06 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13489 CVE: CVE-2026-22980 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 2857bd59feb63fcf40fe4baf55401baea6b4feb4 ] Writing to v4_end_grace can race with server shutdown and result in memory being accessed after it was freed - reclaim_str_hashtbl in particularly. We cannot hold nfsd_mutex across the nfsd4_end_grace() call as that is held while client_tracking_op->init() is called and that can wait for an upcall to nfsdcltrack which can write to v4_end_grace, resulting in a deadlock. nfsd4_end_grace() is also called by the landromat work queue and this doesn't require locking as server shutdown will stop the work and wait for it before freeing anything that nfsd4_end_grace() might access. However, we must be sure that writing to v4_end_grace doesn't restart the work item after shutdown has already waited for it. For this we add a new flag protected with nn->client_lock. It is set only while it is safe to make client tracking calls, and v4_end_grace only schedules work while the flag is set with the spinlock held. So this patch adds a nfsd_net field "client_tracking_active" which is set as described. Another field "grace_end_forced", is set when v4_end_grace is written. After this is set, and providing client_tracking_active is set, the laundromat is scheduled. This "grace_end_forced" field bypasses other checks for whether the grace period has finished. This resolves a race which can result in use-after-free. Reported-by: Li Lingfeng <lilingfeng3(a)huawei.com> Closes: https://lore.kernel.org/linux-nfs/20250623030015.2353515-1-neil@brown.name/… Fixes: 7f5ef2e900d9 ("nfsd: add a v4_end_grace file to /proc/fs/nfsd") Cc: stable(a)vger.kernel.org Signed-off-by: NeilBrown <neil(a)brown.name> Tested-by: Li Lingfeng <lilingfeng3(a)huawei.com> Reviewed-by: Jeff Layton <jlayton(a)kernel.org> Signed-off-by: Chuck Lever <chuck.lever(a)oracle.com> [ Adjust context ] Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: fs/nfsd/nfs4state.c [Commit 5aa2c4a1fe28 ("NFSD: Add a nfsd4_file_hash_remove() helper") add declaration of nfsd4_file_hash_remove(); commit ea92c0768f98 ("nfsd: simplify nfsd_renew") change the return value; commit 438ef64bbfe4 ("NFSD: register/unregister of nfsd-client shrinker at nfsd startup/shutdown time") add unregister_shrinker() in nfs4_state_shutdown_net(); commit 67ef9e5fd737 ("NFSD: add courteous server support for thread with only delegation") move the position of declaration of laundry_wq.] Signed-off-by: Li Lingfeng <lilingfeng3(a)huawei.com> --- fs/nfsd/netns.h | 2 ++ fs/nfsd/nfs4state.c | 44 +++++++++++++++++++++++++++++++++++++++++--- fs/nfsd/nfsctl.c | 3 +-- fs/nfsd/state.h | 2 +- 4 files changed, 45 insertions(+), 6 deletions(-) diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 8500acac09e0..ca5c386aafce 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -40,6 +40,8 @@ struct nfsd_net { struct lock_manager nfsd4_manager; bool grace_ended; + bool grace_end_forced; + bool client_tracking_active; time64_t boot_time; struct dentry *nfsd_client_dir; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 302bbad5cdc6..d17702a4a1ad 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -80,7 +80,7 @@ static u64 current_sessionid = 1; /* forward declarations */ static bool check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner); static void nfs4_free_ol_stateid(struct nfs4_stid *stid); -void nfsd4_end_grace(struct nfsd_net *nn); +static void nfsd4_end_grace(struct nfsd_net *nn); static void _free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps); /* Locking: */ @@ -5347,7 +5347,7 @@ nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, } void -nfsd4_end_grace(struct nfsd_net *nn) +static nfsd4_end_grace(struct nfsd_net *nn) { /* do nothing if grace period already ended */ if (nn->grace_ended) @@ -5379,6 +5379,34 @@ nfsd4_end_grace(struct nfsd_net *nn) */ } +static struct workqueue_struct *laundry_wq; +/** + * nfsd4_force_end_grace - forcibly end the NFSv4 grace period + * @nn: network namespace for the server instance to be updated + * + * Forces bypass of normal grace period completion, then schedules + * the laundromat to end the grace period immediately. Does not wait + * for the grace period to fully terminate before returning. + * + * Return values: + * %true: Grace termination schedule + * %false: No action was taken + */ +bool nfsd4_force_end_grace(struct nfsd_net *nn) +{ + if (!nn->client_tracking_ops) + return false; + spin_lock(&nn->client_lock); + if (nn->grace_ended || !nn->client_tracking_active) { + spin_unlock(&nn->client_lock); + return false; + } + WRITE_ONCE(nn->grace_end_forced, true); + mod_delayed_work(laundry_wq, &nn->laundromat_work, 0); + spin_unlock(&nn->client_lock); + return true; +} + /* * If we've waited a lease period but there are still clients trying to * reclaim, wait a little longer to give them a chance to finish. @@ -5388,6 +5416,8 @@ static bool clients_still_reclaiming(struct nfsd_net *nn) time64_t double_grace_period_end = nn->boot_time + 2 * nn->nfsd4_lease; + if (READ_ONCE(nn->grace_end_forced)) + return false; if (nn->track_reclaim_completes && atomic_read(&nn->nr_reclaim_complete) == nn->reclaim_str_hashtbl_size) @@ -5530,7 +5560,6 @@ nfs4_laundromat(struct nfsd_net *nn) return new_timeo; } -static struct workqueue_struct *laundry_wq; static void laundromat_main(struct work_struct *); static void @@ -7343,6 +7372,8 @@ static int nfs4_state_create_net(struct net *net) nn->unconf_name_tree = RB_ROOT; nn->boot_time = ktime_get_real_seconds(); nn->grace_ended = false; + nn->grace_end_forced = false; + nn->client_tracking_active = false; nn->nfsd4_manager.block_opens = true; INIT_LIST_HEAD(&nn->nfsd4_manager.list); INIT_LIST_HEAD(&nn->client_lru); @@ -7409,6 +7440,10 @@ nfs4_state_start_net(struct net *net) return ret; locks_start_grace(net, &nn->nfsd4_manager); nfsd4_client_tracking_init(net); + /* safe for laundromat to run now */ + spin_lock(&nn->client_lock); + nn->client_tracking_active = true; + spin_unlock(&nn->client_lock); if (nn->track_reclaim_completes && nn->reclaim_str_hashtbl_size == 0) goto skip_grace; printk(KERN_INFO "NFSD: starting %lld-second grace period (net %x)\n", @@ -7458,6 +7493,9 @@ nfs4_state_shutdown_net(struct net *net) struct nfsd_net *nn = net_generic(net, nfsd_net_id); cancel_delayed_work_sync(&nn->laundromat_work); + spin_lock(&nn->client_lock); + nn->client_tracking_active = false; + spin_unlock(&nn->client_lock); locks_end_grace(&nn->nfsd4_manager); INIT_LIST_HEAD(&reaplist); diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 040340080b3d..e84c8cf8e2c0 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1133,9 +1133,8 @@ static ssize_t write_v4_end_grace(struct file *file, char *buf, size_t size) case 'Y': case 'y': case '1': - if (!nn->nfsd_serv) + if (!nfsd4_force_end_grace(nn)) return -EBUSY; - nfsd4_end_grace(nn); break; default: return -EINVAL; diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 9eae11a9d21c..0e4f98b41364 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -683,7 +683,7 @@ static inline void get_nfs4_file(struct nfs4_file *fi) struct nfsd_file *find_any_file(struct nfs4_file *f); /* grace period management */ -void nfsd4_end_grace(struct nfsd_net *nn); +bool nfsd4_force_end_grace(struct nfsd_net *nn); /* nfs4recover operations */ extern int nfsd4_client_tracking_init(struct net *net); -- 2.52.0

2 1

[PATCH OLK-6.6 0/2] arm64/mpam: Fix wrong closid config access when CDP is enabled
by Zeng Heng 12 Mar '26

12 Mar '26

Zeng Heng (2): Revert "fs/resctrl: Fix configuration to wrong control group when CDP is enabled" arm64/mpam: Fix wrong closid config access when CDP is enabled arch/x86/include/asm/resctrl.h | 4 ---- drivers/platform/mpam/mpam_resctrl.c | 35 +++++++++++++++++++++------- fs/resctrl/ctrlmondata.c | 28 +++------------------- include/linux/arm_mpam.h | 1 - 4 files changed, 29 insertions(+), 39 deletions(-) -- 2.25.1

2 3

[PATCH OLK-6.6 0/2] Fix TLBI broadcast optimization loss and incorrect dvmbm handling
by Tian Zheng 11 Mar '26

11 Mar '26

Fix 1 In the TLBI broadcast-optimization feature, the SYS_LSUDVM_CTRL_EL2 register controls whether the feature is enabled. When LPI low-power mode is enabled, this register is cleared as the pCPU powers down into LPI mode, causing the TLBI broadcast optimization to stop working. The fix saves and restores this control register in the callbacks for entering and exiting LPI mode. Fix 2 The current TLBI broadcast-optimization logic only supports normal VMs. If the feature is enabled globally, VMs that are not yet adapted for it, such as CCA will use an incorrect TLBI broadcast bitmap, which can cause a panic in CCA VMs. The fix moves the actual enable/disable of the dvmbm functionality into the vcpu load and vcpu put functions. Tian Zheng (2): KVM: arm64: Fix TLBI optimization broken in LPI mode KVM: arm64: Fix CCA guest panic when dvmbm is enabled arch/arm64/kvm/arm.c | 4 +++ arch/arm64/kvm/hisilicon/hisi_virt.c | 37 +++++++++++++++++++--------- arch/arm64/kvm/hisilicon/hisi_virt.h | 4 +++ 3 files changed, 33 insertions(+), 12 deletions(-) -- 2.33.0

1 2

[PATCH OLK-6.6 0/3] optimize lightweight load balancing
by Chen Jinghuang 11 Mar '26

11 Mar '26

*** BLURB HERE *** Chen Jinghuang (2): sched: Fix kabi breakage of struct sched_domain for newidle_stats sched: expand sysctl_sched_features to unsigned long Peter Zijlstra (Intel) (1): sched/fair: Proportional newidle balance include/linux/sched/topology.h | 7 ++++- kernel/sched/core.c | 5 +++- kernel/sched/fair.c | 48 +++++++++++++++++++++++++++++++--- kernel/sched/features.h | 5 ++++ kernel/sched/sched.h | 9 ++++++- kernel/sched/topology.c | 6 +++++ 6 files changed, 73 insertions(+), 7 deletions(-) -- 2.34.1

2 4

[PATCH OLK-6.6 0/3] optimize lightweight load balancing
by Chen Jinghuang 11 Mar '26

11 Mar '26

*** BLURB HERE *** Chen Jinghuang (2): sched: Fix kabi breakage of struct sched_domain for newidle_stats sched: expand sysctl_sched_features to unsigned long Peter Zijlstra (Intel) (1): sched/fair: Proportional newidle balance include/linux/sched/topology.h | 7 ++++- kernel/sched/core.c | 5 +++- kernel/sched/fair.c | 48 +++++++++++++++++++++++++++++++--- kernel/sched/features.h | 5 ++++ kernel/sched/sched.h | 7 +++++ kernel/sched/topology.c | 6 +++++ 6 files changed, 72 insertions(+), 6 deletions(-) -- 2.34.1

2 4

[PATCH OLK-6.6 0/2] Fix TLBI broadcast optimization loss and incorrect dvmbm handling
by Tian Zheng 11 Mar '26

11 Mar '26

Fix 1 In the TLBI broadcast-optimization feature, the SYS_LSUDVM_CTRL_EL2 register controls whether the feature is enabled. When LPI low-power mode is enabled, this register is cleared as the pCPU powers down into LPI mode, causing the TLBI broadcast optimization to stop working. The fix saves and restores this control register in the callbacks for entering and exiting LPI mode. Fix 2 The current TLBI broadcast-optimization logic only supports normal VMs. If the feature is enabled globally, VMs that are not yet adapted for it, such as CCA will use an incorrect TLBI broadcast bitmap, which can cause a panic in CCA VMs. The fix moves the actual enable/disable of the dvmbm functionality into the vcpu load and vcpu put functions. Tian Zheng (2): KVM: arm64: Fix TLBI optimization broken in LPI mode KVM: arm64: Fix CCA guest panic when dvmbm is enabled arch/arm64/kvm/arm.c | 4 ++++ arch/arm64/kvm/hisilicon/hisi_virt.c | 28 ++++++++++++++++++++++------ arch/arm64/kvm/hisilicon/hisi_virt.h | 4 ++++ 3 files changed, 30 insertions(+), 6 deletions(-) -- 2.33.0

1 2

[PATCH OLK-6.6] platform/x86: classmate-laptop: Add missing NULL pointer checks
by Zeng Heng 11 Mar '26

11 Mar '26

From: "Rafael J. Wysocki" <rafael.j.wysocki(a)intel.com> mainline inclusion from mainline-v6.19 commit fe747d7112283f47169e9c16e751179a9b38611e category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13842 CVE: CVE-2026-23237 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- In a few places in the Classmate laptop driver, code using the accel object may run before that object's address is stored in the driver data of the input device using it. For example, cmpc_accel_sensitivity_store_v4() is the "show" method of cmpc_accel_sensitivity_attr_v4 which is added in cmpc_accel_add_v4(), before calling dev_set_drvdata() for inputdev->dev. If the sysfs attribute is accessed prematurely, the dev_get_drvdata(&inputdev->dev) call in in cmpc_accel_sensitivity_store_v4() returns NULL which leads to a NULL pointer dereference going forward. Moreover, sysfs attributes using the input device are added before initializing that device by cmpc_add_acpi_notify_device() and if one of them is accessed before running that function, a NULL pointer dereference will occur. For example, cmpc_accel_sensitivity_attr_v4 is added before calling cmpc_add_acpi_notify_device() and if it is read prematurely, the dev_get_drvdata(&acpi->dev) call in cmpc_accel_sensitivity_show_v4() returns NULL which leads to a NULL pointer dereference going forward. Fix this by adding NULL pointer checks in all of the relevant places. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com> Link: https://patch.msgid.link/12825381.O9o76ZdvQC@rafael.j.wysocki Reviewed-by: Ilpo Järvinen <ilpo.jarvinen(a)linux.intel.com> Signed-off-by: Ilpo Järvinen <ilpo.jarvinen(a)linux.intel.com> Conflicts: drivers/platform/x86/classmate-laptop.c [Context conflicts.] Signed-off-by: Zeng Heng <zengheng4(a)huawei.com> --- drivers/platform/x86/classmate-laptop.c | 32 +++++++++++++++++++++++++ 1 file changed, 32 insertions(+) diff --git a/drivers/platform/x86/classmate-laptop.c b/drivers/platform/x86/classmate-laptop.c index 2edaea2492df..053c8a86d5ec 100644 --- a/drivers/platform/x86/classmate-laptop.c +++ b/drivers/platform/x86/classmate-laptop.c @@ -208,7 +208,12 @@ static ssize_t cmpc_accel_sensitivity_show_v4(struct device *dev, acpi = to_acpi_device(dev); inputdev = dev_get_drvdata(&acpi->dev); + if (!inputdev) + return -ENXIO; + accel = dev_get_drvdata(&inputdev->dev); + if (!accel) + return -ENXIO; return sprintf(buf, "%d\n", accel->sensitivity); } @@ -225,7 +230,12 @@ static ssize_t cmpc_accel_sensitivity_store_v4(struct device *dev, acpi = to_acpi_device(dev); inputdev = dev_get_drvdata(&acpi->dev); + if (!inputdev) + return -ENXIO; + accel = dev_get_drvdata(&inputdev->dev); + if (!accel) + return -ENXIO; r = kstrtoul(buf, 0, &sensitivity); if (r) @@ -257,7 +267,12 @@ static ssize_t cmpc_accel_g_select_show_v4(struct device *dev, acpi = to_acpi_device(dev); inputdev = dev_get_drvdata(&acpi->dev); + if (!inputdev) + return -ENXIO; + accel = dev_get_drvdata(&inputdev->dev); + if (!accel) + return -ENXIO; return sprintf(buf, "%d\n", accel->g_select); } @@ -274,7 +289,12 @@ static ssize_t cmpc_accel_g_select_store_v4(struct device *dev, acpi = to_acpi_device(dev); inputdev = dev_get_drvdata(&acpi->dev); + if (!inputdev) + return -ENXIO; + accel = dev_get_drvdata(&inputdev->dev); + if (!accel) + return -ENXIO; r = kstrtoul(buf, 0, &g_select); if (r) @@ -303,6 +323,8 @@ static int cmpc_accel_open_v4(struct input_dev *input) acpi = to_acpi_device(input->dev.parent); accel = dev_get_drvdata(&input->dev); + if (!accel) + return -ENXIO; cmpc_accel_set_sensitivity_v4(acpi->handle, accel->sensitivity); cmpc_accel_set_g_select_v4(acpi->handle, accel->g_select); @@ -551,7 +573,12 @@ static ssize_t cmpc_accel_sensitivity_show(struct device *dev, acpi = to_acpi_device(dev); inputdev = dev_get_drvdata(&acpi->dev); + if (!inputdev) + return -ENXIO; + accel = dev_get_drvdata(&inputdev->dev); + if (!accel) + return -ENXIO; return sprintf(buf, "%d\n", accel->sensitivity); } @@ -568,7 +595,12 @@ static ssize_t cmpc_accel_sensitivity_store(struct device *dev, acpi = to_acpi_device(dev); inputdev = dev_get_drvdata(&acpi->dev); + if (!inputdev) + return -ENXIO; + accel = dev_get_drvdata(&inputdev->dev); + if (!accel) + return -ENXIO; r = kstrtoul(buf, 0, &sensitivity); if (r) -- 2.25.1

2 1

[PATCH OLK-6.6 0/2] optimize lightweight load balancing
by Chen Jinghuang 11 Mar '26

11 Mar '26

*** BLURB HERE *** Chen Jinghuang (1): sched: Fix kabi breakage of struct sched_domain for newidle_stats Peter Zijlstra (Intel) (1): sched/fair: Proportional newidle balance include/linux/sched/topology.h | 7 ++++- kernel/sched/core.c | 3 +++ kernel/sched/fair.c | 48 +++++++++++++++++++++++++++++++--- kernel/sched/features.h | 5 ++++ kernel/sched/sched.h | 7 +++++ kernel/sched/topology.c | 6 +++++ 6 files changed, 71 insertions(+), 5 deletions(-) -- 2.34.1

2 3

[PATCH OLK-6.6 0/2] optimize lightweight load balancing
by Chen Jinghuang 11 Mar '26

11 Mar '26

*** BLURB HERE *** Chen Jinghuang (1): sched: Fix kabi breakage of struct sched_domain for newidle_stats Peter Zijlstra (Intel) (1): sched/fair: Proportional newidle balance include/linux/sched/topology.h | 8 +++++- kernel/sched/core.c | 3 +++ kernel/sched/fair.c | 48 +++++++++++++++++++++++++++++++--- kernel/sched/features.h | 5 ++++ kernel/sched/sched.h | 7 +++++ kernel/sched/topology.c | 6 +++++ 6 files changed, 72 insertions(+), 5 deletions(-) -- 2.34.1

2 3

[PATCH] arch/riscv: Add bitrev.h file to support rev8 and brev8
by Jinjie Ruan 11 Mar '26

11 Mar '26

The RISC-V Bit-manipulation Extension for Cryptography (Zbkb) provides the 'brev8' instruction, which reverses the bits within each byte. Combined with the 'rev8' instruction (from Zbb or Zbkb), which reverses the byte order of a register, we can efficiently implement 16-bit, 32-bit, and (on RV64) 64-bit bit reversal. This is significantly faster than the default software table-lookup implementation in lib/bitrev.c, as it replaces memory accesses and multiple arithmetic operations with just two or three hardware instructions. Select HAVE_ARCH_BITREVERSE and provide <asm/bitrev.h> to utilize these instructions when the Zbkb extension is available at runtime via the alternatives mechanism. Signed-off-by: Jinjie Ruan <ruanjinjie(a)huawei.com> --- arch/riscv/Kconfig | 1 + arch/riscv/include/asm/bitrev.h | 46 +++++++++++++++++++++++++++++++++ lib/bitrev.c | 3 --- 3 files changed, 47 insertions(+), 3 deletions(-) create mode 100644 arch/riscv/include/asm/bitrev.h diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 90c531e6abf5..e7a04b96c0c8 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -128,6 +128,7 @@ config RISCV select HAS_IOPORT if MMU select HAVE_ALIGNED_STRUCT_PAGE select HAVE_ARCH_AUDITSYSCALL + select HAVE_ARCH_BITREVERSE select HAVE_ARCH_HUGE_VMALLOC if HAVE_ARCH_HUGE_VMAP select HAVE_ARCH_HUGE_VMAP if MMU && 64BIT select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL diff --git a/arch/riscv/include/asm/bitrev.h b/arch/riscv/include/asm/bitrev.h new file mode 100644 index 000000000000..b1977600638a --- /dev/null +++ b/arch/riscv/include/asm/bitrev.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_BITREV_H +#define __ASM_BITREV_H + +#include <linux/types.h> +#include <asm/cpufeature-macros.h> +#include <asm/hwcap.h> + +extern u8 const byte_rev_table[256]; +static __always_inline __attribute_const__ u32 __arch_bitrev32(u32 x) +{ + if (IS_ENABLED(CONFIG_RISCV_ISA_ZBKB) && + riscv_has_extension_likely(RISCV_ISA_EXT_ZBKB)) { + unsigned long result = x; + + asm volatile( + ".option push\n" + ".option arch,+zbkb\n" + "rev8 %0, %0\n" + "brev8 %0, %0\n" + ".option pop" + : "+r" (result) + ); + + if (__riscv_xlen == 64) + return (u32)(result >> 32); + + return (u32)result; + } + + return (u32)byte_rev_table[x & 0xff] << 24 | + (u32)byte_rev_table[(x >> 8) & 0xff] << 16 | + (u32)byte_rev_table[(x >> 16) & 0xff] << 8 | + (u32)byte_rev_table[x >> 24]; +} + +static __always_inline __attribute_const__ u16 __arch_bitrev16(u16 x) +{ + return __arch_bitrev32((u32)x) >> 16; +} + +static __always_inline __attribute_const__ u8 __arch_bitrev8(u8 x) +{ + return __arch_bitrev32((u32)x) >> 24; +} +#endif diff --git a/lib/bitrev.c b/lib/bitrev.c index 81b56e0a7f32..05088231f31f 100644 --- a/lib/bitrev.c +++ b/lib/bitrev.c @@ -1,5 +1,4 @@ // SPDX-License-Identifier: GPL-2.0-only -#ifndef CONFIG_HAVE_ARCH_BITREVERSE #include <linux/types.h> #include <linux/module.h> #include <linux/bitrev.h> @@ -43,5 +42,3 @@ const u8 byte_rev_table[256] = { 0x1f, 0x9f, 0x5f, 0xdf, 0x3f, 0xbf, 0x7f, 0xff, }; EXPORT_SYMBOL_GPL(byte_rev_table); - -#endif /* CONFIG_HAVE_ARCH_BITREVERSE */ -- 2.34.1

1 0

[PATCH openEuler-26.09 0/3] Fix device memory leaks in XSched
by Liu Kai 11 Mar '26

11 Mar '26

Fix device memory leaks in XSched Liu Kai (3): xsched/dmem: ensure XSched Context creation before device memory allocation xsched/dmem: add size field to xsched_dmem_pool for dmem region tracking xsched/dmem: ensure dmem region release on AI task completion to prevent memory leaks include/linux/xsched.h | 2 ++ include/uapi/linux/xcu_vstream.h | 2 +- kernel/xsched/dmem.c | 38 +++++++++++++++++++++++++++----- kernel/xsched/vstream.c | 22 +++++++++++++++--- 4 files changed, 55 insertions(+), 9 deletions(-) -- 2.34.1

2 4

[PATCH OLK-6.6 0/2] optimize lightweight load balancing
by Chen Jinghuang 11 Mar '26

11 Mar '26

*** BLURB HERE *** Chen Jinghuang (1): sched: Fix kabi breakage of struct sched_domain for newidle_stats Peter Zijlstra (Intel) (1): sched/fair: Proportional newidle balance include/linux/sched/topology.h | 4 +++ kernel/sched/core.c | 3 +++ kernel/sched/fair.c | 48 +++++++++++++++++++++++++++++++--- kernel/sched/features.h | 5 ++++ kernel/sched/sched.h | 7 +++++ kernel/sched/topology.c | 6 +++++ 6 files changed, 69 insertions(+), 4 deletions(-) -- 2.34.1

2 3

[PATCH OLK-6.6 0/2] Fix TLBI broadcast optimization loss and incorrect dvmbm handling
by Tian Zheng 11 Mar '26

11 Mar '26

Fix 1 In the TLBI broadcast-optimization feature, the SYS_LSUDVM_CTRL_EL2 register controls whether the feature is enabled. When LPI low-power mode is enabled, this register is cleared as the pCPU powers down into LPI mode, causing the TLBI broadcast optimization to stop working. The fix saves and restores this control register in the callbacks for entering and exiting LPI mode. Fix 2 The current TLBI broadcast-optimization logic only supports normal VMs. If the feature is enabled globally, VMs that are not yet adapted for it, such as CCA will use an incorrect TLBI broadcast bitmap, which can cause a panic in CCA VMs. The fix moves the actual enable/disable of the dvmbm functionality into the vcpu load and vcpu put functions. Tian Zheng (2): KVM: arm64: Fix TLBI optimization broken in LPI mode KVM: arm64: Fix CCA guest panic when dvmbm is enabled arch/arm64/kvm/arm.c | 6 ++++++ arch/arm64/kvm/hisilicon/hisi_virt.c | 9 ++++----- arch/arm64/kvm/hisilicon/hisi_virt.h | 19 +++++++++++++++++++ 3 files changed, 29 insertions(+), 5 deletions(-) -- 2.33.0

1 2

[PATCH OLK-6.6 v4 0/4] Fix CVE-2025-21696.
by Ze Zuo 10 Mar '26

10 Mar '26

Fix CVE-2025-21696. Change since v3: -- internalize struct to reduce kABI exposure. David Hildenbrand (1): mm/mremap: fix WARN with uffd that has remap events disabled Lokesh Gidra (1): userfaultfd: move userfaultfd_ctx struct to header file Ryan Roberts (1): mm: clear uffd-wp PTE/PMD state on mremap() Ze Zuo (1): userfaultfd: fix kabi breakage due to struct userfaultfd_ctx fs/userfaultfd.c | 40 +---------------- include/linux/userfaultfd_k_ext.h | 62 ++++++++++++++++++++++++++ mm/huge_memory.c | 13 ++++++ mm/hugetlb.c | 15 ++++++- mm/mremap.c | 74 +++++++++++++++++++++++-------- 5 files changed, 145 insertions(+), 59 deletions(-) create mode 100644 include/linux/userfaultfd_k_ext.h -- 2.25.1

2 5

[PATCH OLK-6.6 0/2] optimize lightweight load balancing
by Chen Jinghuang 10 Mar '26

10 Mar '26

*** BLURB HERE *** Chen Jinghuang (1): sched: Fix kabi breakage of struct sched_domain for newidle_stats Peter Zijlstra (Intel) (1): sched/fair: Proportional newidle balance include/linux/sched/topology.h | 6 +++++ kernel/sched/core.c | 3 +++ kernel/sched/fair.c | 44 ++++++++++++++++++++++++++++++---- kernel/sched/features.h | 5 ++++ kernel/sched/sched.h | 7 ++++++ kernel/sched/topology.c | 6 +++++ 6 files changed, 67 insertions(+), 4 deletions(-) -- 2.34.1

2 3

[PATCH OLK-6.6 0/2] optimize lightweight load balancing
by Chen Jinghuang 10 Mar '26

10 Mar '26

*** BLURB HERE *** Chen Jinghuang (1): sched: Fix kabi breakage pf struct sched_domain for newidle_stats Peter Zijlstra (Intel) (1): sched/fair: Proportional newidle balance include/linux/sched/topology.h | 12 ++++++ kernel/sched/core.c | 3 ++ kernel/sched/fair.c | 78 ++++++++++++++++++++++++++++++++-- kernel/sched/features.h | 5 +++ kernel/sched/sched.h | 7 +++ kernel/sched/topology.c | 11 +++++ 6 files changed, 112 insertions(+), 4 deletions(-) -- 2.34.1

2 3

[PATCH OLK-6.6 1/2] sched/fair: Proportional newidle balance
by Chen Jinghuang 10 Mar '26

10 Mar '26

From: "Peter Zijlstra (Intel)" <peterz(a)infradead.org> stable inclusion from stable-v6.6.120 commit 51445190c10a36d292e70db085d0fb6cc3bec94f category: perf bugzilla: https://atomgit.com/openeuler/kernel/issues/8555 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 33cf66d88306663d16e4759e9d24766b0aaa2e17 upstream. Add a randomized algorithm that runs newidle balancing proportional to its success rate. This improves schbench significantly: 6.18-rc4: 2.22 Mrps/s 6.18-rc4+revert: 2.04 Mrps/s 6.18-rc4+revert+random: 2.18 Mrps/S Conversely, per Adam Li this affects SpecJBB slightly, reducing it by 1%: 6.17: -6% 6.17+revert: 0% 6.17+revert+random: -1% Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Reviewed-by: Dietmar Eggemann <dietmar.eggemann(a)arm.com> Tested-by: Dietmar Eggemann <dietmar.eggemann(a)arm.com> Tested-by: Chris Mason <clm(a)meta.com> Link: https://lkml.kernel.org/r/6825c50d-7fa7-45d8-9b81-c6e7e25738e2@meta.com Link: https://patch.msgid.link/20251107161739.770122091@infradead.org [ Ajay: Modified to apply on v6.6 ] Signed-off-by: Ajay Kaher <ajay.kaher(a)broadcom.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: kernel/sched/core.c kernel/sched/fair.c [context conflicts] Signed-off-by: Chen Jinghuang <chenjinghuang2(a)huawei.com> --- include/linux/sched/topology.h | 3 +++ kernel/sched/core.c | 3 +++ kernel/sched/fair.c | 44 ++++++++++++++++++++++++++++++---- kernel/sched/features.h | 5 ++++ kernel/sched/sched.h | 7 ++++++ kernel/sched/topology.c | 6 +++++ 6 files changed, 64 insertions(+), 4 deletions(-) diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 7eee852aa384..95e5d7772800 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -130,6 +130,9 @@ struct sched_domain { unsigned int nr_balance_failed; /* initialise to 0 */ /* idle_balance() stats */ + unsigned int newidle_call; + unsigned int newidle_success; + unsigned int newidle_ratio; u64 max_newidle_lb_cost; unsigned long last_decay_max_lb_cost; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 69d10fdb84d8..cf45ea94bb05 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -119,6 +119,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_se_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp); DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); +DEFINE_PER_CPU(struct rnd_state, sched_rnd_state); #ifdef CONFIG_QOS_SCHED static void sched_change_qos_group(struct task_struct *tsk, struct task_group *tg); @@ -9976,6 +9977,8 @@ void __init sched_init_smp(void) sched_init_numa(NUMA_NO_NODE); set_sched_cluster(); + prandom_init_once(&sched_rnd_state); + /* * There's no userspace yet to cause hotplug operations; hence all the * CPU masks are stable and all blatant races in the below code cannot diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index a4592d35da8b..d16c65d5fa34 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -13651,8 +13651,24 @@ void update_max_interval(void) max_load_balance_interval = HZ*num_online_cpus()/10; } -static inline bool update_newidle_cost(struct sched_domain *sd, u64 cost) +static inline void update_newidle_stats(struct sched_domain *sd, unsigned int success) { + sd->newidle_call++; + sd->newidle_success += success; + + if (sd->newidle_call >= 1024) { + sd->newidle_ratio = sd->newidle_success; + sd->newidle_call /= 2; + sd->newidle_success /= 2; + } +} + +static inline bool +update_newidle_cost(struct sched_domain *sd, u64 cost, unsigned int success) +{ + if (cost) + update_newidle_stats(sd, success); + if (cost > sd->max_newidle_lb_cost) { /* * Track max cost of a domain to make sure to not delay the @@ -13700,7 +13716,7 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle) * Decay the newidle max times here because this is a regular * visit to all the domains. */ - need_decay = update_newidle_cost(sd, 0); + need_decay = update_newidle_cost(sd, 0, 0); max_cost += sd->max_newidle_lb_cost; /* @@ -14336,6 +14352,22 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf) break; if (sd->flags & SD_BALANCE_NEWIDLE) { + unsigned int weight = 1; + + if (sched_feat(NI_RANDOM)) { + /* + * Throw a 1k sided dice; and only run + * newidle_balance according to the success + * rate. + */ + u32 d1k = sched_rng() % 1024; + weight = 1 + sd->newidle_ratio; + if (d1k > weight) { + update_newidle_stats(sd, 0); + continue; + } + weight = (1024 + weight/2) / weight; + } pulled_task = load_balance(this_cpu, this_rq, sd, CPU_NEWLY_IDLE, @@ -14343,10 +14375,14 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf) t1 = sched_clock_cpu(this_cpu); domain_cost = t1 - t0; - update_newidle_cost(sd, domain_cost); - curr_cost += domain_cost; t0 = t1; + + /* + * Track max cost of a domain to make sure to not delay the + * next wakeup on the CPU. + */ + update_newidle_cost(sd, domain_cost, weight * !!pulled_task); } /* diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 52ea0097c513..24a0c853a8a0 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -106,6 +106,11 @@ SCHED_FEAT(UTIL_EST_FASTUP, true) SCHED_FEAT(LATENCY_WARN, false) +/* + * Do newidle balancing proportional to its success rate using randomization. + */ +SCHED_FEAT(NI_RANDOM, false) + SCHED_FEAT(HZ_BW, true) SCHED_FEAT(IRQ_AVG, false) diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index bb581cbdae8d..0c3abb44f365 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -5,6 +5,7 @@ #ifndef _KERNEL_SCHED_SCHED_H #define _KERNEL_SCHED_SCHED_H +#include <linux/prandom.h> #include <linux/sched/affinity.h> #include <linux/sched/autogroup.h> #include <linux/sched/cpufreq.h> @@ -1377,6 +1378,12 @@ static inline bool is_migration_disabled(struct task_struct *p) } DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); +DECLARE_PER_CPU(struct rnd_state, sched_rnd_state); + +static inline u32 sched_rng(void) +{ + return prandom_u32_state(this_cpu_ptr(&sched_rnd_state)); +} #define cpu_rq(cpu) (&per_cpu(runqueues, (cpu))) #define this_rq() this_cpu_ptr(&runqueues) diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 3023e67da0fd..cf847fdf1063 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1644,6 +1644,12 @@ sd_init(struct sched_domain_topology_level *tl, .last_balance = jiffies, .balance_interval = sd_weight, + + /* 50% success rate */ + .newidle_call = 512, + .newidle_success = 256, + .newidle_ratio = 512, + .max_newidle_lb_cost = 0, .last_decay_max_lb_cost = jiffies, .child = child, -- 2.34.1

2 2

[PATCH OLK-6.6 1/2] [Backport] sched/fair: Proportional newidle balance
by Chen Jinghuang 10 Mar '26

10 Mar '26

From: "Peter Zijlstra (Intel)" <peterz(a)infradead.org> stable inclusion from stable-v6.6.120 commit 51445190c10a36d292e70db085d0fb6cc3bec94f category: perf bugzilla: https://atomgit.com/openeuler/kernel/issues/8555 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 33cf66d88306663d16e4759e9d24766b0aaa2e17 upstream. Add a randomized algorithm that runs newidle balancing proportional to its success rate. This improves schbench significantly: 6.18-rc4: 2.22 Mrps/s 6.18-rc4+revert: 2.04 Mrps/s 6.18-rc4+revert+random: 2.18 Mrps/S Conversely, per Adam Li this affects SpecJBB slightly, reducing it by 1%: 6.17: -6% 6.17+revert: 0% 6.17+revert+random: -1% Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Reviewed-by: Dietmar Eggemann <dietmar.eggemann(a)arm.com> Tested-by: Dietmar Eggemann <dietmar.eggemann(a)arm.com> Tested-by: Chris Mason <clm(a)meta.com> Link: https://lkml.kernel.org/r/6825c50d-7fa7-45d8-9b81-c6e7e25738e2@meta.com Link: https://patch.msgid.link/20251107161739.770122091@infradead.org [ Ajay: Modified to apply on v6.6 ] Signed-off-by: Ajay Kaher <ajay.kaher(a)broadcom.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: kernel/sched/core.c kernel/sched/fair.c [context conflicts] Signed-off-by: Chen Jinghuang <chenjinghuang2(a)huawei.com> --- include/linux/sched/topology.h | 3 +++ kernel/sched/core.c | 3 +++ kernel/sched/fair.c | 44 ++++++++++++++++++++++++++++++---- kernel/sched/features.h | 5 ++++ kernel/sched/sched.h | 7 ++++++ kernel/sched/topology.c | 6 +++++ 6 files changed, 64 insertions(+), 4 deletions(-) diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 7eee852aa384..95e5d7772800 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -130,6 +130,9 @@ struct sched_domain { unsigned int nr_balance_failed; /* initialise to 0 */ /* idle_balance() stats */ + unsigned int newidle_call; + unsigned int newidle_success; + unsigned int newidle_ratio; u64 max_newidle_lb_cost; unsigned long last_decay_max_lb_cost; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 69d10fdb84d8..cf45ea94bb05 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -119,6 +119,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_se_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp); DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); +DEFINE_PER_CPU(struct rnd_state, sched_rnd_state); #ifdef CONFIG_QOS_SCHED static void sched_change_qos_group(struct task_struct *tsk, struct task_group *tg); @@ -9976,6 +9977,8 @@ void __init sched_init_smp(void) sched_init_numa(NUMA_NO_NODE); set_sched_cluster(); + prandom_init_once(&sched_rnd_state); + /* * There's no userspace yet to cause hotplug operations; hence all the * CPU masks are stable and all blatant races in the below code cannot diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index a4592d35da8b..d16c65d5fa34 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -13651,8 +13651,24 @@ void update_max_interval(void) max_load_balance_interval = HZ*num_online_cpus()/10; } -static inline bool update_newidle_cost(struct sched_domain *sd, u64 cost) +static inline void update_newidle_stats(struct sched_domain *sd, unsigned int success) { + sd->newidle_call++; + sd->newidle_success += success; + + if (sd->newidle_call >= 1024) { + sd->newidle_ratio = sd->newidle_success; + sd->newidle_call /= 2; + sd->newidle_success /= 2; + } +} + +static inline bool +update_newidle_cost(struct sched_domain *sd, u64 cost, unsigned int success) +{ + if (cost) + update_newidle_stats(sd, success); + if (cost > sd->max_newidle_lb_cost) { /* * Track max cost of a domain to make sure to not delay the @@ -13700,7 +13716,7 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle) * Decay the newidle max times here because this is a regular * visit to all the domains. */ - need_decay = update_newidle_cost(sd, 0); + need_decay = update_newidle_cost(sd, 0, 0); max_cost += sd->max_newidle_lb_cost; /* @@ -14336,6 +14352,22 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf) break; if (sd->flags & SD_BALANCE_NEWIDLE) { + unsigned int weight = 1; + + if (sched_feat(NI_RANDOM)) { + /* + * Throw a 1k sided dice; and only run + * newidle_balance according to the success + * rate. + */ + u32 d1k = sched_rng() % 1024; + weight = 1 + sd->newidle_ratio; + if (d1k > weight) { + update_newidle_stats(sd, 0); + continue; + } + weight = (1024 + weight/2) / weight; + } pulled_task = load_balance(this_cpu, this_rq, sd, CPU_NEWLY_IDLE, @@ -14343,10 +14375,14 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf) t1 = sched_clock_cpu(this_cpu); domain_cost = t1 - t0; - update_newidle_cost(sd, domain_cost); - curr_cost += domain_cost; t0 = t1; + + /* + * Track max cost of a domain to make sure to not delay the + * next wakeup on the CPU. + */ + update_newidle_cost(sd, domain_cost, weight * !!pulled_task); } /* diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 52ea0097c513..24a0c853a8a0 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -106,6 +106,11 @@ SCHED_FEAT(UTIL_EST_FASTUP, true) SCHED_FEAT(LATENCY_WARN, false) +/* + * Do newidle balancing proportional to its success rate using randomization. + */ +SCHED_FEAT(NI_RANDOM, false) + SCHED_FEAT(HZ_BW, true) SCHED_FEAT(IRQ_AVG, false) diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index bb581cbdae8d..0c3abb44f365 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -5,6 +5,7 @@ #ifndef _KERNEL_SCHED_SCHED_H #define _KERNEL_SCHED_SCHED_H +#include <linux/prandom.h> #include <linux/sched/affinity.h> #include <linux/sched/autogroup.h> #include <linux/sched/cpufreq.h> @@ -1377,6 +1378,12 @@ static inline bool is_migration_disabled(struct task_struct *p) } DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); +DECLARE_PER_CPU(struct rnd_state, sched_rnd_state); + +static inline u32 sched_rng(void) +{ + return prandom_u32_state(this_cpu_ptr(&sched_rnd_state)); +} #define cpu_rq(cpu) (&per_cpu(runqueues, (cpu))) #define this_rq() this_cpu_ptr(&runqueues) diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 3023e67da0fd..cf847fdf1063 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1644,6 +1644,12 @@ sd_init(struct sched_domain_topology_level *tl, .last_balance = jiffies, .balance_interval = sd_weight, + + /* 50% success rate */ + .newidle_call = 512, + .newidle_success = 256, + .newidle_ratio = 512, + .max_newidle_lb_cost = 0, .last_decay_max_lb_cost = jiffies, .child = child, -- 2.34.1

2 3

[PATCH 1/2] [Backport] sched/fair: Proportional newidle balance
by Chen Jinghuang 10 Mar '26

10 Mar '26

From: "Peter Zijlstra (Intel)" <peterz(a)infradead.org> stable inclusion from stable-v6.6.120 commit 51445190c10a36d292e70db085d0fb6cc3bec94f category: perf bugzilla: https://atomgit.com/openeuler/kernel/issues/8555 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 33cf66d88306663d16e4759e9d24766b0aaa2e17 upstream. Add a randomized algorithm that runs newidle balancing proportional to its success rate. This improves schbench significantly: 6.18-rc4: 2.22 Mrps/s 6.18-rc4+revert: 2.04 Mrps/s 6.18-rc4+revert+random: 2.18 Mrps/S Conversely, per Adam Li this affects SpecJBB slightly, reducing it by 1%: 6.17: -6% 6.17+revert: 0% 6.17+revert+random: -1% Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Reviewed-by: Dietmar Eggemann <dietmar.eggemann(a)arm.com> Tested-by: Dietmar Eggemann <dietmar.eggemann(a)arm.com> Tested-by: Chris Mason <clm(a)meta.com> Link: https://lkml.kernel.org/r/6825c50d-7fa7-45d8-9b81-c6e7e25738e2@meta.com Link: https://patch.msgid.link/20251107161739.770122091@infradead.org [ Ajay: Modified to apply on v6.6 ] Signed-off-by: Ajay Kaher <ajay.kaher(a)broadcom.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: kernel/sched/core.c kernel/sched/fair.c [context conflicts] Signed-off-by: Chen Jinghuang <chenjinghuang2(a)huawei.com> --- include/linux/sched/topology.h | 3 +++ kernel/sched/core.c | 3 +++ kernel/sched/fair.c | 44 ++++++++++++++++++++++++++++++---- kernel/sched/features.h | 5 ++++ kernel/sched/sched.h | 7 ++++++ kernel/sched/topology.c | 6 +++++ 6 files changed, 64 insertions(+), 4 deletions(-) diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 7eee852aa384..95e5d7772800 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -130,6 +130,9 @@ struct sched_domain { unsigned int nr_balance_failed; /* initialise to 0 */ /* idle_balance() stats */ + unsigned int newidle_call; + unsigned int newidle_success; + unsigned int newidle_ratio; u64 max_newidle_lb_cost; unsigned long last_decay_max_lb_cost; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 69d10fdb84d8..cf45ea94bb05 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -119,6 +119,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_se_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp); DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); +DEFINE_PER_CPU(struct rnd_state, sched_rnd_state); #ifdef CONFIG_QOS_SCHED static void sched_change_qos_group(struct task_struct *tsk, struct task_group *tg); @@ -9976,6 +9977,8 @@ void __init sched_init_smp(void) sched_init_numa(NUMA_NO_NODE); set_sched_cluster(); + prandom_init_once(&sched_rnd_state); + /* * There's no userspace yet to cause hotplug operations; hence all the * CPU masks are stable and all blatant races in the below code cannot diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index a4592d35da8b..d16c65d5fa34 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -13651,8 +13651,24 @@ void update_max_interval(void) max_load_balance_interval = HZ*num_online_cpus()/10; } -static inline bool update_newidle_cost(struct sched_domain *sd, u64 cost) +static inline void update_newidle_stats(struct sched_domain *sd, unsigned int success) { + sd->newidle_call++; + sd->newidle_success += success; + + if (sd->newidle_call >= 1024) { + sd->newidle_ratio = sd->newidle_success; + sd->newidle_call /= 2; + sd->newidle_success /= 2; + } +} + +static inline bool +update_newidle_cost(struct sched_domain *sd, u64 cost, unsigned int success) +{ + if (cost) + update_newidle_stats(sd, success); + if (cost > sd->max_newidle_lb_cost) { /* * Track max cost of a domain to make sure to not delay the @@ -13700,7 +13716,7 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle) * Decay the newidle max times here because this is a regular * visit to all the domains. */ - need_decay = update_newidle_cost(sd, 0); + need_decay = update_newidle_cost(sd, 0, 0); max_cost += sd->max_newidle_lb_cost; /* @@ -14336,6 +14352,22 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf) break; if (sd->flags & SD_BALANCE_NEWIDLE) { + unsigned int weight = 1; + + if (sched_feat(NI_RANDOM)) { + /* + * Throw a 1k sided dice; and only run + * newidle_balance according to the success + * rate. + */ + u32 d1k = sched_rng() % 1024; + weight = 1 + sd->newidle_ratio; + if (d1k > weight) { + update_newidle_stats(sd, 0); + continue; + } + weight = (1024 + weight/2) / weight; + } pulled_task = load_balance(this_cpu, this_rq, sd, CPU_NEWLY_IDLE, @@ -14343,10 +14375,14 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf) t1 = sched_clock_cpu(this_cpu); domain_cost = t1 - t0; - update_newidle_cost(sd, domain_cost); - curr_cost += domain_cost; t0 = t1; + + /* + * Track max cost of a domain to make sure to not delay the + * next wakeup on the CPU. + */ + update_newidle_cost(sd, domain_cost, weight * !!pulled_task); } /* diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 52ea0097c513..24a0c853a8a0 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -106,6 +106,11 @@ SCHED_FEAT(UTIL_EST_FASTUP, true) SCHED_FEAT(LATENCY_WARN, false) +/* + * Do newidle balancing proportional to its success rate using randomization. + */ +SCHED_FEAT(NI_RANDOM, false) + SCHED_FEAT(HZ_BW, true) SCHED_FEAT(IRQ_AVG, false) diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index bb581cbdae8d..0c3abb44f365 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -5,6 +5,7 @@ #ifndef _KERNEL_SCHED_SCHED_H #define _KERNEL_SCHED_SCHED_H +#include <linux/prandom.h> #include <linux/sched/affinity.h> #include <linux/sched/autogroup.h> #include <linux/sched/cpufreq.h> @@ -1377,6 +1378,12 @@ static inline bool is_migration_disabled(struct task_struct *p) } DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); +DECLARE_PER_CPU(struct rnd_state, sched_rnd_state); + +static inline u32 sched_rng(void) +{ + return prandom_u32_state(this_cpu_ptr(&sched_rnd_state)); +} #define cpu_rq(cpu) (&per_cpu(runqueues, (cpu))) #define this_rq() this_cpu_ptr(&runqueues) diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 3023e67da0fd..cf847fdf1063 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1644,6 +1644,12 @@ sd_init(struct sched_domain_topology_level *tl, .last_balance = jiffies, .balance_interval = sd_weight, + + /* 50% success rate */ + .newidle_call = 512, + .newidle_success = 256, + .newidle_ratio = 512, + .max_newidle_lb_cost = 0, .last_decay_max_lb_cost = jiffies, .child = child, -- 2.34.1

1 1

[PATCH 1/2] [Backport] sched/fair: Proportional newidle balance
by Chen Jinghuang 10 Mar '26

10 Mar '26

From: "Peter Zijlstra (Intel)" <peterz(a)infradead.org> stable inclusion from stable-v6.6.120 commit 51445190c10a36d292e70db085d0fb6cc3bec94f category: perf bugzilla: https://atomgit.com/openeuler/kernel/issues/8555 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 33cf66d88306663d16e4759e9d24766b0aaa2e17 upstream. Add a randomized algorithm that runs newidle balancing proportional to its success rate. This improves schbench significantly: 6.18-rc4: 2.22 Mrps/s 6.18-rc4+revert: 2.04 Mrps/s 6.18-rc4+revert+random: 2.18 Mrps/S Conversely, per Adam Li this affects SpecJBB slightly, reducing it by 1%: 6.17: -6% 6.17+revert: 0% 6.17+revert+random: -1% Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Reviewed-by: Dietmar Eggemann <dietmar.eggemann(a)arm.com> Tested-by: Dietmar Eggemann <dietmar.eggemann(a)arm.com> Tested-by: Chris Mason <clm(a)meta.com> Link: https://lkml.kernel.org/r/6825c50d-7fa7-45d8-9b81-c6e7e25738e2@meta.com Link: https://patch.msgid.link/20251107161739.770122091@infradead.org [ Ajay: Modified to apply on v6.6 ] Signed-off-by: Ajay Kaher <ajay.kaher(a)broadcom.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: kernel/sched/core.c kernel/sched/fair.c [context conflicts] Signed-off-by: Chen Jinghuang <chenjinghuang2(a)huawei.com> --- include/linux/sched/topology.h | 3 +++ kernel/sched/core.c | 3 +++ kernel/sched/fair.c | 44 ++++++++++++++++++++++++++++++---- kernel/sched/features.h | 5 ++++ kernel/sched/sched.h | 7 ++++++ kernel/sched/topology.c | 6 +++++ 6 files changed, 64 insertions(+), 4 deletions(-) diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 7eee852aa384..95e5d7772800 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -130,6 +130,9 @@ struct sched_domain { unsigned int nr_balance_failed; /* initialise to 0 */ /* idle_balance() stats */ + unsigned int newidle_call; + unsigned int newidle_success; + unsigned int newidle_ratio; u64 max_newidle_lb_cost; unsigned long last_decay_max_lb_cost; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 69d10fdb84d8..cf45ea94bb05 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -119,6 +119,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_se_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp); DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); +DEFINE_PER_CPU(struct rnd_state, sched_rnd_state); #ifdef CONFIG_QOS_SCHED static void sched_change_qos_group(struct task_struct *tsk, struct task_group *tg); @@ -9976,6 +9977,8 @@ void __init sched_init_smp(void) sched_init_numa(NUMA_NO_NODE); set_sched_cluster(); + prandom_init_once(&sched_rnd_state); + /* * There's no userspace yet to cause hotplug operations; hence all the * CPU masks are stable and all blatant races in the below code cannot diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index a4592d35da8b..d16c65d5fa34 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -13651,8 +13651,24 @@ void update_max_interval(void) max_load_balance_interval = HZ*num_online_cpus()/10; } -static inline bool update_newidle_cost(struct sched_domain *sd, u64 cost) +static inline void update_newidle_stats(struct sched_domain *sd, unsigned int success) { + sd->newidle_call++; + sd->newidle_success += success; + + if (sd->newidle_call >= 1024) { + sd->newidle_ratio = sd->newidle_success; + sd->newidle_call /= 2; + sd->newidle_success /= 2; + } +} + +static inline bool +update_newidle_cost(struct sched_domain *sd, u64 cost, unsigned int success) +{ + if (cost) + update_newidle_stats(sd, success); + if (cost > sd->max_newidle_lb_cost) { /* * Track max cost of a domain to make sure to not delay the @@ -13700,7 +13716,7 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle) * Decay the newidle max times here because this is a regular * visit to all the domains. */ - need_decay = update_newidle_cost(sd, 0); + need_decay = update_newidle_cost(sd, 0, 0); max_cost += sd->max_newidle_lb_cost; /* @@ -14336,6 +14352,22 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf) break; if (sd->flags & SD_BALANCE_NEWIDLE) { + unsigned int weight = 1; + + if (sched_feat(NI_RANDOM)) { + /* + * Throw a 1k sided dice; and only run + * newidle_balance according to the success + * rate. + */ + u32 d1k = sched_rng() % 1024; + weight = 1 + sd->newidle_ratio; + if (d1k > weight) { + update_newidle_stats(sd, 0); + continue; + } + weight = (1024 + weight/2) / weight; + } pulled_task = load_balance(this_cpu, this_rq, sd, CPU_NEWLY_IDLE, @@ -14343,10 +14375,14 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf) t1 = sched_clock_cpu(this_cpu); domain_cost = t1 - t0; - update_newidle_cost(sd, domain_cost); - curr_cost += domain_cost; t0 = t1; + + /* + * Track max cost of a domain to make sure to not delay the + * next wakeup on the CPU. + */ + update_newidle_cost(sd, domain_cost, weight * !!pulled_task); } /* diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 52ea0097c513..6cd6b5307430 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -106,6 +106,11 @@ SCHED_FEAT(UTIL_EST_FASTUP, true) SCHED_FEAT(LATENCY_WARN, false) +/* + * Do newidle balancing proportional to its success rate using randomization. + */ +SCHED_FEAT(NI_RANDOM, true) + SCHED_FEAT(HZ_BW, true) SCHED_FEAT(IRQ_AVG, false) diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index bb581cbdae8d..0c3abb44f365 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -5,6 +5,7 @@ #ifndef _KERNEL_SCHED_SCHED_H #define _KERNEL_SCHED_SCHED_H +#include <linux/prandom.h> #include <linux/sched/affinity.h> #include <linux/sched/autogroup.h> #include <linux/sched/cpufreq.h> @@ -1377,6 +1378,12 @@ static inline bool is_migration_disabled(struct task_struct *p) } DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); +DECLARE_PER_CPU(struct rnd_state, sched_rnd_state); + +static inline u32 sched_rng(void) +{ + return prandom_u32_state(this_cpu_ptr(&sched_rnd_state)); +} #define cpu_rq(cpu) (&per_cpu(runqueues, (cpu))) #define this_rq() this_cpu_ptr(&runqueues) diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 3023e67da0fd..cf847fdf1063 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1644,6 +1644,12 @@ sd_init(struct sched_domain_topology_level *tl, .last_balance = jiffies, .balance_interval = sd_weight, + + /* 50% success rate */ + .newidle_call = 512, + .newidle_success = 256, + .newidle_ratio = 512, + .max_newidle_lb_cost = 0, .last_decay_max_lb_cost = jiffies, .child = child, -- 2.34.1

1 1

[PATCH 1/2] [Backport] sched/fair: Proportional newidle balance
by Chen Jinghuang 10 Mar '26

10 Mar '26

From: "Peter Zijlstra (Intel)" <peterz(a)infradead.org> stable inclusion from stable-v6.6.120 commit 51445190c10a36d292e70db085d0fb6cc3bec94f category: perf bugzilla: https://atomgit.com/openeuler/kernel/issues/8555 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 33cf66d88306663d16e4759e9d24766b0aaa2e17 upstream. Add a randomized algorithm that runs newidle balancing proportional to its success rate. This improves schbench significantly: 6.18-rc4: 2.22 Mrps/s 6.18-rc4+revert: 2.04 Mrps/s 6.18-rc4+revert+random: 2.18 Mrps/S Conversely, per Adam Li this affects SpecJBB slightly, reducing it by 1%: 6.17: -6% 6.17+revert: 0% 6.17+revert+random: -1% Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Reviewed-by: Dietmar Eggemann <dietmar.eggemann(a)arm.com> Tested-by: Dietmar Eggemann <dietmar.eggemann(a)arm.com> Tested-by: Chris Mason <clm(a)meta.com> Link: https://lkml.kernel.org/r/6825c50d-7fa7-45d8-9b81-c6e7e25738e2@meta.com Link: https://patch.msgid.link/20251107161739.770122091@infradead.org [ Ajay: Modified to apply on v6.6 ] Signed-off-by: Ajay Kaher <ajay.kaher(a)broadcom.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: kernel/sched/core.c kernel/sched/fair.c [context conflicts] Signed-off-by: Chen Jinghuang <chenjinghuang2(a)huawei.com> --- include/linux/sched/topology.h | 3 +++ kernel/sched/core.c | 3 +++ kernel/sched/fair.c | 44 ++++++++++++++++++++++++++++++---- kernel/sched/features.h | 5 ++++ kernel/sched/sched.h | 7 ++++++ kernel/sched/topology.c | 6 +++++ 6 files changed, 64 insertions(+), 4 deletions(-) diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 7eee852aa384..95e5d7772800 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -130,6 +130,9 @@ struct sched_domain { unsigned int nr_balance_failed; /* initialise to 0 */ /* idle_balance() stats */ + unsigned int newidle_call; + unsigned int newidle_success; + unsigned int newidle_ratio; u64 max_newidle_lb_cost; unsigned long last_decay_max_lb_cost; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 69d10fdb84d8..cf45ea94bb05 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -119,6 +119,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_se_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp); DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); +DEFINE_PER_CPU(struct rnd_state, sched_rnd_state); #ifdef CONFIG_QOS_SCHED static void sched_change_qos_group(struct task_struct *tsk, struct task_group *tg); @@ -9976,6 +9977,8 @@ void __init sched_init_smp(void) sched_init_numa(NUMA_NO_NODE); set_sched_cluster(); + prandom_init_once(&sched_rnd_state); + /* * There's no userspace yet to cause hotplug operations; hence all the * CPU masks are stable and all blatant races in the below code cannot diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index a4592d35da8b..d16c65d5fa34 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -13651,8 +13651,24 @@ void update_max_interval(void) max_load_balance_interval = HZ*num_online_cpus()/10; } -static inline bool update_newidle_cost(struct sched_domain *sd, u64 cost) +static inline void update_newidle_stats(struct sched_domain *sd, unsigned int success) { + sd->newidle_call++; + sd->newidle_success += success; + + if (sd->newidle_call >= 1024) { + sd->newidle_ratio = sd->newidle_success; + sd->newidle_call /= 2; + sd->newidle_success /= 2; + } +} + +static inline bool +update_newidle_cost(struct sched_domain *sd, u64 cost, unsigned int success) +{ + if (cost) + update_newidle_stats(sd, success); + if (cost > sd->max_newidle_lb_cost) { /* * Track max cost of a domain to make sure to not delay the @@ -13700,7 +13716,7 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle) * Decay the newidle max times here because this is a regular * visit to all the domains. */ - need_decay = update_newidle_cost(sd, 0); + need_decay = update_newidle_cost(sd, 0, 0); max_cost += sd->max_newidle_lb_cost; /* @@ -14336,6 +14352,22 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf) break; if (sd->flags & SD_BALANCE_NEWIDLE) { + unsigned int weight = 1; + + if (sched_feat(NI_RANDOM)) { + /* + * Throw a 1k sided dice; and only run + * newidle_balance according to the success + * rate. + */ + u32 d1k = sched_rng() % 1024; + weight = 1 + sd->newidle_ratio; + if (d1k > weight) { + update_newidle_stats(sd, 0); + continue; + } + weight = (1024 + weight/2) / weight; + } pulled_task = load_balance(this_cpu, this_rq, sd, CPU_NEWLY_IDLE, @@ -14343,10 +14375,14 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf) t1 = sched_clock_cpu(this_cpu); domain_cost = t1 - t0; - update_newidle_cost(sd, domain_cost); - curr_cost += domain_cost; t0 = t1; + + /* + * Track max cost of a domain to make sure to not delay the + * next wakeup on the CPU. + */ + update_newidle_cost(sd, domain_cost, weight * !!pulled_task); } /* diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 52ea0097c513..6cd6b5307430 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -106,6 +106,11 @@ SCHED_FEAT(UTIL_EST_FASTUP, true) SCHED_FEAT(LATENCY_WARN, false) +/* + * Do newidle balancing proportional to its success rate using randomization. + */ +SCHED_FEAT(NI_RANDOM, true) + SCHED_FEAT(HZ_BW, true) SCHED_FEAT(IRQ_AVG, false) diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index bb581cbdae8d..0c3abb44f365 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -5,6 +5,7 @@ #ifndef _KERNEL_SCHED_SCHED_H #define _KERNEL_SCHED_SCHED_H +#include <linux/prandom.h> #include <linux/sched/affinity.h> #include <linux/sched/autogroup.h> #include <linux/sched/cpufreq.h> @@ -1377,6 +1378,12 @@ static inline bool is_migration_disabled(struct task_struct *p) } DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); +DECLARE_PER_CPU(struct rnd_state, sched_rnd_state); + +static inline u32 sched_rng(void) +{ + return prandom_u32_state(this_cpu_ptr(&sched_rnd_state)); +} #define cpu_rq(cpu) (&per_cpu(runqueues, (cpu))) #define this_rq() this_cpu_ptr(&runqueues) diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 3023e67da0fd..cf847fdf1063 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1644,6 +1644,12 @@ sd_init(struct sched_domain_topology_level *tl, .last_balance = jiffies, .balance_interval = sd_weight, + + /* 50% success rate */ + .newidle_call = 512, + .newidle_success = 256, + .newidle_ratio = 512, + .max_newidle_lb_cost = 0, .last_decay_max_lb_cost = jiffies, .child = child, -- 2.34.1

1 1

[PATCH OLK-6.6] tools/interference: add ifstool utility for kernel interference statistics
by Tengda Wu 10 Mar '26

10 Mar '26

hulk inclusion category: feature bugzilla: https://atomgit.com/openeuler/kernel/issues/7429 -------------------------------- As real-time and high-performance workloads become more sensitive to execution jitter, observability into kernel-induced "noise" is critical. The CONFIG_CGROUP_IFS infrastructure provides this telemetry, but raw data from cgroups is difficult to parse and visualize manually. Introduce ifstool, a userspace utility to monitor and analyze the interference.stat interface. Key capabilities include: 1. High-Resolution Monitoring: - Samples raw counters and latency distributions at sub-second intervals. - Outputs structured CSV data for long-term profiling and integration with external post-processing tools. 2. Interactive Offline Reporting: - Generates self-contained HTML dashboards using Plotly. - Visualizes "Total Time Delta" trends to identify temporal spikes. - Renders latency heatmaps to expose the magnitude and frequency of interference events. Signed-off-by: Tengda Wu <wutengda2(a)huawei.com> --- tools/Makefile | 11 +- tools/kspect/Makefile | 28 +++ tools/kspect/README | 65 ++++++ tools/kspect/ifstool | 409 ++++++++++++++++++++++++++++++++++ tools/kspect/ifstool.1 | 87 ++++++++ tools/kspect/requirements.txt | 2 + 6 files changed, 598 insertions(+), 4 deletions(-) create mode 100644 tools/kspect/Makefile create mode 100644 tools/kspect/README create mode 100644 tools/kspect/ifstool create mode 100644 tools/kspect/ifstool.1 create mode 100644 tools/kspect/requirements.txt diff --git a/tools/Makefile b/tools/Makefile index 37e9f6804832..153817f0cc17 100644 --- a/tools/Makefile +++ b/tools/Makefile @@ -22,6 +22,7 @@ help: @echo ' hv - tools used when in Hyper-V clients' @echo ' iio - IIO tools' @echo ' intel-speed-select - Intel Speed Select tool' + @echo ' kspect - KSPECT tools' @echo ' kvm_stat - top-like utility for displaying kvm statistics' @echo ' leds - LEDs tools' @echo ' nolibc - nolibc headers testing and installation' @@ -69,7 +70,7 @@ acpi: FORCE cpupower: FORCE $(call descend,power/$@) -cgroup counter firewire hv guest bootconfig spi usb virtio mm bpf iio gpio objtool leds wmi pci firmware debugging tracing: FORCE +cgroup counter firewire hv guest bootconfig spi usb virtio mm bpf iio gpio objtool leds wmi pci firmware debugging tracing kspect: FORCE $(call descend,$@) bpf/%: FORCE @@ -120,7 +121,8 @@ all: acpi cgroup counter cpupower gpio hv firewire \ perf selftests bootconfig spi turbostat usb \ virtio mm bpf x86_energy_perf_policy \ tmon freefall iio objtool kvm_stat wmi \ - pci debugging tracing thermal thermometer thermal-engine + pci debugging tracing thermal thermometer thermal-engine \ + kspect acpi_install: $(call descend,power/$(@:_install=),install) @@ -128,7 +130,7 @@ acpi_install: cpupower_install: $(call descend,power/$(@:_install=),install) -cgroup_install counter_install firewire_install gpio_install hv_install iio_install perf_install bootconfig_install spi_install usb_install virtio_install mm_install bpf_install objtool_install wmi_install pci_install debugging_install tracing_install: +cgroup_install counter_install firewire_install gpio_install hv_install iio_install perf_install bootconfig_install spi_install usb_install virtio_install mm_install bpf_install objtool_install wmi_install pci_install debugging_install tracing_install kspect_install: $(call descend,$(@:_install=),install) selftests_install: @@ -161,7 +163,8 @@ install: acpi_install cgroup_install counter_install cpupower_install gpio_insta virtio_install mm_install bpf_install x86_energy_perf_policy_install \ tmon_install freefall_install objtool_install kvm_stat_install \ wmi_install pci_install debugging_install intel-speed-select_install \ - tracing_install thermometer_install thermal-engine_install + tracing_install thermometer_install thermal-engine_install \ + kspect_install acpi_clean: $(call descend,power/acpi,clean) diff --git a/tools/kspect/Makefile b/tools/kspect/Makefile new file mode 100644 index 000000000000..ffb380ddc885 --- /dev/null +++ b/tools/kspect/Makefile @@ -0,0 +1,28 @@ +# SPDX-License-Identifier: GPL-2.0 + +PREFIX ?= /usr/local +BINDIR = $(PREFIX)/bin +MANDIR = $(PREFIX)/share/man/man1 + +MAN1 = ifstool.1 +TARGET = ifstool + +all: man + +man: $(MAN1) + +install-man: + install -d $(MANDIR) + install -m 0644 $(MAN1) $(MANDIR) + +install-tools: + install -d $(BINDIR) + install -m 0755 $(TARGET) $(BINDIR) + +install: install-tools install-man + +uninstall: + rm -f $(BINDIR)/$(TARGET) + rm -f $(MANDIR)/$(MAN1) + +.PHONY: all install-tools install-man install diff --git a/tools/kspect/README b/tools/kspect/README new file mode 100644 index 000000000000..618e02a202f7 --- /dev/null +++ b/tools/kspect/README @@ -0,0 +1,65 @@ +IFSTOOL - Interference Statistics Analytical Utility + +Overview +======== +IFSTOOL is a specialized userspace utility designed to facilitate the +monitoring and analysis of Interference Statistics (CONFIG_CGROUP_IFS). + +The IFS infrastructure is a kernel-level framework that provides critical +observability into execution jitter (noise) that disrupts task determinism. +It monitors and quantifies the CPU time stolen by kernel-level activities, +such as: interrupt handling, softirqs, and lock contention. The framework +exposes this telemetry via the interference.stat control file within the +cgroup hierarchy. + +IFSTOOL interfaces with the interference.stat file to export raw metrics +into structured CSV data and interactive HTML-based distribution reports. + +Setup +===== +The host environment must meet the following criteria: + +* Kernel: Compiled with `CONFIG_CGROUP_IFS=y`. +* Boot Parameters: `cgroup_ifs=1` added to the kernel command line (optional, + not needed if `CONFIG_CGROUP_IFS_DEFAULT_ENABLED=y`). +* Python Runtime: Python 3.x with `pandas` and `plotly` libraries. +* Cgroup Hierarchy: Either v2 unified or v1 with the cpu subsystem mounted. + +Build +===== +IFSTOOL provides a Makefile to streamline the installation of the +executable and its documentation. + + $ make install + +Run +=== +IFSTOOL operates via two primary functional modes: monitor and report. + +1. **Monitor:** Capture raw interference data from a target cgroup. + + $ ifstool monitor --cgroup docker/<cid> --interval 1 --output capture.csv + +2. **Report:** Transform captured CSV data into an interactive HTML dashboard. + + - Provide only --base for a single-session deep dive: + + $ ifstool report --base capture.csv + + - Provide both --base and --curr to render a differential report, + ideal for validating optimizations: + + $ ifstool report --base baseline.csv --curr current.csv + +HTML Description +================ +The generated HTML report provides a multi-dimensional view of kernel noise: + +- Total Time Delta Trend: A time-series line chart illustrating the incremental + nanoseconds of interference per category (e.g., irq, spinlock). +- Latency Heatmaps: A frequency-domain visualization of the kernel's internal + histogram. + - X-axis: Wall-clock time of the trace. + - Y-axis: Latency magnitude (logarithmic buckets from ns to s). + - Color Intensity: Represents the density (event count) of interference + within that specific latency window. diff --git a/tools/kspect/ifstool b/tools/kspect/ifstool new file mode 100644 index 000000000000..c17de045263a --- /dev/null +++ b/tools/kspect/ifstool @@ -0,0 +1,409 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0-only +# +# ifstool: A tool to monitor and report interference statistics (CONFIG_CGROUP_IFS). +# +# Copyright(c) 2026. Huawei Technologies Co., Ltd +# +# Authors: +# Tengda Wu <wutengda2(a)huawei.com> + +import os +import time +import re +import csv +import argparse +import pandas as pd +import plotly.graph_objects as go +from plotly.subplots import make_subplots +from plotly.offline import get_plotlyjs + + +class InterferenceTool: + """ + A utility class to monitor Linux cgroup interference statistics (CONFIG_CGROUP_IFS) + and generate visual comparison reports between baseline and current data. + """ + + def __init__(self): + # Default path for cgroup v2 interference stats + self.base_path = "/sys/fs/cgroup" + + def parse_stat(self, content): + """ + Parses the raw content of the interference.stat file. + + Args: + content (str): Raw string content from the stat file. + Returns: + tuple: (total_times dict, distributions dict) + """ + + total_times, distributions = {}, {} + + # Split content into sections: Top-level totals and various distributions + # Uses positive lookahead to split before a word followed by ' distribution' + sections = re.split(r"\n(?=[a-z]+ distribution)", content) + + # Parse global total times (first section) + for line in sections[0].strip().split("\n"): + match = re.match(r"^([a-z]+)\s+(\d+)$", line.strip()) + if match: + total_times[match.group(1)] = int(match.group(2)) + + # Parse histogram distributions (subsequent sections) + for section in sections[1:]: + lines = section.strip().split("\n") + # Extract header name (e.g., 'spinlock distribution') + header = lines[0].replace(" distribution", "").strip() + # Parse bucket key-value pairs (e.g., '[64 ns, 128 ns) : 143791') + dist_data = { + l.split(":")[0].strip(): int(l.split(":")[1].strip()) + for l in lines[1:] + if ":" in l + } + distributions[header] = dist_data + + return total_times, distributions + + def monitor(self, cgroup_id, interval, duration, output_csv): + """ + Periodically samples interference stats and saves results to a CSV file. + + Args: + cgroup_id (str): The specific cgroup folder name. For example, + /sys/kernel/cgroup/A/B/C, when want to monitor level B, the + cgroup_id is A/B. + interval (float): Seconds between samples. + duration (int): Total monitoring time in seconds. + output_csv (str): Filename to save sampled data. + """ + + candidates = [ + os.path.join(self.base_path, cgroup_id), + os.path.join(self.base_path, "cpu", cgroup_id), # cgroup v1 + ] + path = next((p for p in candidates if os.path.exists(p)), None) + + if not path: + print( + f"\n[!] No access to cgroup: {os.path.join(self.base_path, cgroup_id)}" + ) + print(" Hint: You can find the correct cid by executing:") + print(" cat /proc/<PID>/cgroup") + return + + path = os.path.join(path, "interference.stat") + if not os.path.exists(path): + print(f"\n[!] Interface file '{path}' not found.") + print(" This usually happens due to one of the following:") + print(" 1. Kernel is not compiled with CONFIG_CGROUP_IFS=y") + print( + " 2. CONFIG_CGROUP_IFS_DEFAULT_ENABLED is not set to y", + "and the boot parameter 'cgroup_ifs=1' is not added", + ) + print(" 3. The current cgroup is not managed by the IFS controller") + return + + print( + f"[*] Starting monitor: {cgroup_id}, interval: {interval}s, duration: {duration}s" + ) + + data_list = [] + start_time = time.time() + + try: + while (time.time() - start_time) < duration: + ts = time.strftime("%H:%M:%S") + # Using fractional seconds in timestamp for sub-second intervals + if interval < 1.0: + ts = time.strftime("%H:%M:%S") + f".{int((time.time()%1)*100):02d}" + + with open(path, "r") as f: + total_times, dists = self.parse_stat(f.read()) + + # Append total time metrics + for cat, val in total_times.items(): + data_list.append([ts, cgroup_id, cat, "total_time_ns", val]) + + # Append bucket distribution metrics + for cat, dist in dists.items(): + for b, c in dist.items(): + data_list.append([ts, cgroup_id, cat, f"bucket_{b}", c]) + + time.sleep(interval) + except KeyboardInterrupt: + print("\n[!] Monitoring interrupted by user.") + + # Write buffered data to CSV + with open(output_csv, "w", newline="") as f: + writer = csv.writer(f) + writer.writerow( + ["timestamp", "cgroup_id", "category", "metric_type", "value"] + ) + writer.writerows(data_list) + print(f"[+] Data exported successfully: {output_csv}") + + def bucket_key(self, bucket_str): + """ + Parsing logic for histogram bucket labels to enable correct numerical sorting. + Example input: "bucket_[67.10 ms, 134.21 ms)" + + Returns: + float: The value converted to nanoseconds (ns). + """ + try: + # Regex to capture the first number and its unit (ns|us|ms|s) + match = re.search(r"(\d+\.?\d*)\s*(ns|us|ms|s)", bucket_str) + if not match: + return 0 + + value = float(match.group(1)) + unit = match.group(2).lower() + + # Conversion factors to nanoseconds + factors = {"ns": 1, "us": 1000, "ms": 1000000, "s": 1000000000} + + return value * factors.get(unit, 1) + except Exception: + return 0 + + def report(self, base_csv, curr_csv, output_html): + """ + Loads two CSV files and generates an interactive HTML dashboard. + + Args: + base_csv (str): Path to baseline data. + curr_csv (str): Path to current data. + output_html (str): Path to generate the HTML report. + """ + + df_b = pd.read_csv(base_csv) + single_mode = curr_csv is None or base_csv == curr_csv + df_c = None if single_mode else pd.read_csv(curr_csv) + + # Get unique union of categories present in both datasets + all_dfs = [df_b] if single_mode else [df_b, df_c] + categories = sorted( + list(set().union(*(df.category.unique() for df in all_dfs))) + ) + + # Color mapping to ensure consistent colors for categories across plots + color_sequence = [ + "#636EFA", + "#EF553B", + "#00CC96", + "#AB63FA", + "#FFA15A", + "#19D3F3", + "#FF6692", + "#B6E880", + "#FF97FF", + "#FECB52", + ] + color_map = { + cat: color_sequence[i % len(color_sequence)] + for i, cat in enumerate(categories) + } + + # Build HTML content with CSS for layout + html_parts = [ + "<html><head><title>IFS Analysis Dashboard</title>", + f"<script type='text/javascript'>{get_plotlyjs()}</script>", + ] + col_width = "100%" if single_mode else "49.5%" + html_parts.append( + f"""<style> + body{{font-family:'Segoe UI',sans-serif; background:#f0f2f5; padding:20px; color:#333;}} + .card{{background:white; padding:15px; margin-bottom:20px; border-radius:10px; box-shadow:0 2px 5px rgba(0,0,0,0.05);}} + .row-container{{display:flex; gap:15px; justify-content:space-between;}} + .col-item{{width:{col_width}; min-width:0;}} + .stat-box{{display:flex; gap:10px; margin:5px 0; font-size:0.85em; color:#555;}} + .stat-item{{background:#f1f3f5; padding:4px 8px; border-radius:4px; border-left:3px solid #007bff;}} + .section-header{{margin:30px 0 15px 0; padding-bottom:10px; border-bottom:2px solid #ddd;}} + </style></head><body>""" + ) + + title = "Performance Analysis" if single_mode else "Performance Comparison" + html_parts.append(f"<h2>{title} (CONFIG_CGROUP_IFS)</h2>") + info = ( + f"File: {base_csv}" + if single_mode + else f"Baseline: {base_csv} | Current: {curr_csv}" + ) + html_parts.append(f"<p style='color:#666;'>{info}</p>") + + # --- Part 1: Total Time Trends (Line Charts) --- + html_parts.append("<div class='card'>") + html_parts.append("<h3 style='margin-top:0;'>Total Time Delta (ns) Trend</h3>") + + # Subplots ensure Y-axis can be matched for direct visual comparison + fig_line = make_subplots( + rows=1, + cols=1 if single_mode else 2, + horizontal_spacing=0.05, + subplot_titles=("Latency",) if single_mode else ("Baseline", "Current"), + ) + + plot_configs = ( + [("Data", df_b)] if single_mode else [("Baseline", df_b), ("Current", df_c)] + ) + for i, (name, df) in enumerate(plot_configs, 1): + for cat in categories: + sub = df[ + (df["category"] == cat) & (df["metric_type"] == "total_time_ns") + ].sort_values("timestamp") + if not sub.empty: + y_val = sub["value"].diff().fillna(0) + fig_line.add_trace( + go.Scatter( + x=sub["timestamp"], + y=y_val, + name=f"{cat} ({name})", + legendgroup=cat, + mode="lines+markers", + line=dict(color=color_map[cat], width=2), + marker=dict(color=color_map[cat], size=6), + ), + row=1, + col=i, + ) + + # Sync Y-axes scale for baseline and current plots + if not single_mode: + fig_line.update_yaxes(matches="y", row=1, col=2) + fig_line.update_layout( + height=500, template="plotly_white", margin=dict(t=50, b=20) + ) + html_parts.append(fig_line.to_html(full_html=False, include_plotlyjs=False)) + html_parts.append("</div>") + + html_parts.append( + "<h3 class='section-header'>Detailed Latency Distribution</h3>" + ) + + # --- Part 2: Distribution Heatmaps --- + for cat in categories: + + def get_m_and_stats(df): + """Processes raw metrics into a delta-count matrix for heatmap visualization.""" + sub = df[ + (df["category"] == cat) + & (df["metric_type"].str.startswith("bucket_")) + ] + if sub.empty: + return pd.DataFrame(), {} + + # Transform to matrix (Buckets vs Time) + p = sub.pivot( + index="metric_type", columns="timestamp", values="value" + ).sort_index(axis=1) + # Sort Y-axis buckets based on numerical time value + p = p.reindex(sorted(p.index, key=self.bucket_key)) + # Calculate incremental change (delta) + delta = p.diff(axis=1).fillna(0) + return delta, { + "Total": int(delta.values.sum()), + "Peak": int(delta.values.max()), + } + + m_b, stats_b = get_m_and_stats(df_b) + m_c, stats_c = (None, None) if single_mode else get_m_and_stats(df_c) + + # Determine global max for heatmap color scaling consistency + z_vals = [m_b.values.max() if not m_b.empty else 0] + if not single_mode: + z_vals.append(m_c.values.max() if not m_c.empty else 0) + global_max_z = max(z_vals + [1]) + + html_parts.append(f"<div class='card'><h4>Category: {cat.upper()}</h4>") + html_parts.append("<div class='row-container'>") + + configs = ( + [("Data", m_b, stats_b)] + if single_mode + else [("Baseline", m_b, stats_b), ("Current", m_c, stats_c)] + ) + for name, m, stats in configs: + html_parts.append("<div class='col-item'>") + if not m.empty: + # Display summary statistics + html_parts.append("<div class='stat-box'>") + for k, v in stats.items(): + html_parts.append( + f"<div class='stat-item'><b>{k}:</b> {v}</div>" + ) + html_parts.append("</div>") + + # Generate Heatmap + fig = go.Figure( + data=go.Heatmap( + z=m.values, + x=m.columns, + y=m.index, + colorscale="Viridis", + zmin=0, + zmax=global_max_z, + colorbar=dict(title="Count", thickness=10, len=0.7), + ) + ) + fig.update_layout( + height=400, + margin=dict(l=120, r=0, t=10, b=30), + template="plotly_white", + ) + html_parts.append( + fig.to_html(full_html=False, include_plotlyjs=False) + ) + else: + html_parts.append( + "<div style='height:100px; display:flex; align-items:center; justify-content:center; background:#fafafa; color:#ccc;'>No Data</div>" + ) + html_parts.append("</div>") + + html_parts.append("</div></div>") # end row-container & card + + # Save the final HTML report + with open(output_html, "w") as f: + f.writelines(html_parts + ["</body></html>"]) + print(f"[+] Comparison report generated: {output_html}") + + +if __name__ == "__main__": + parser = argparse.ArgumentParser() + sub = parser.add_subparsers(dest="mode") + + # Monitor Mode Arguments + p_mon = sub.add_parser("monitor") + p_mon.add_argument( + "-G", + "--cgroup", + required=True, + help="Cgroup name (e.g. 'docker/cid'). " + "Tip: Find this via 'cat /proc/<PID>/cgroup'", + ) + p_mon.add_argument( + "-i", "--interval", type=float, default=1.0, help="Sampling interval (sec)" + ) + p_mon.add_argument( + "-d", "--duration", type=int, default=30, help="Sampling duration (sec)" + ) + p_mon.add_argument("-o", "--output", default="capture.csv") + + # Report Mode Arguments + p_comp = sub.add_parser("report") + p_comp.add_argument("-b", "--base", required=True, help="Baseline CSV file") + p_comp.add_argument( + "-c", "--curr", default=None, help="Current CSV file (optional, for comparison)" + ) + p_comp.add_argument("-o", "--output", default="report.html") + + args = parser.parse_args() + tool = InterferenceTool() + + if args.mode == "monitor": + tool.monitor(args.cgroup, args.interval, args.duration, args.output) + elif args.mode == "report": + tool.report(args.base, args.curr, args.output) + else: + parser.print_help() diff --git a/tools/kspect/ifstool.1 b/tools/kspect/ifstool.1 new file mode 100644 index 000000000000..7ff9d297fc08 --- /dev/null +++ b/tools/kspect/ifstool.1 @@ -0,0 +1,87 @@ +.TH IFSTOOL 1 "March 2026" "Linux" "User Commands" +.SH NAME +ifstool \- Analyze kernel interference statistics (CONFIG_CGROUP_IFS) +.SH SYNOPSIS +.B ifstool monitor +[\fB\-G\fR|\fB\-\-cgroup\fR \fICGROUP_ID\fR] [\fB\-d\fR|\fB\-\-duration\fR \fISEC\fR] [\fB\-i\fR|\fB\-\-interval\fR \fISEC\fR] [\fB\-o\fR|\fB\-\-output\fR \fICSV\fR] +.br +.B ifstool report +[\fB\-b\fR|\fB\-\-base\fR \fICSV\fR] [\fB\-c\fR|\fB\-\-curr\fR \fICSV\fR] [\fB\-o\fR|\fB\-\-output\fR \fIHTML\fR] + +.SH DESCRIPTION +.B IFSTOOL +is a specialized userspace utility designed to facilitate the monitoring and analysis of Interference Statistics (\fBCONFIG_CGROUP_IFS\fR). + +The \fBIFS infrastructure\fR is a kernel-level framework providing critical observability into execution jitter (noise) that disrupts task determinism. It quantifies CPU time stolen by kernel activities such as interrupt handling, softirqs, and lock contention. This telemetry is exposed via the \fBinterference.stat\fR control file within the cgroup hierarchy. + +\fBIFSTOOL\fR interfaces with this file to export raw metrics into structured CSV data and interactive HTML-based distribution reports. + +.SH SETUP +The host environment must meet the following criteria: +.IP \[bu] 2 +\fBKernel:\fR Compiled with \fBCONFIG_CGROUP_IFS=y\fR. +.IP \[bu] 2 +\fBBoot Parameters:\fR \fBcgroup_ifs=1\fR added to the kernel command line (optional, not needed if \fBCONFIG_CGROUP_IFS_DEFAULT_ENABLED=y\fR). +.IP \[bu] 2 +\fBPython Runtime:\fR Python 3.x with \fBpandas\fR and \fBplotly\fR libraries. +.IP \[bu] 2 +\fBCgroup Hierarchy:\fR Either v2 unified or v1 (with the \fBcpu\fR subsystem mounted). + +.SH COMMANDS +.SS monitor +Capture raw interference data from a target cgroup. +.TP +\fB\-G, \-\-cgroup\fR \fICGROUP_ID\fR +Specify the cgroup identifier (e.g., \fIdocker/<cid>\fR). For example, /sys/kernel/cgroup/A/B/C, when you want to monitor level B, the cgroup_id is A/B. Tip: Find this via cat \fI/proc/PID/cgroup\fR. +.TP +\fB\-d, \-\-duration\fR \fISEC\fR +Total collection time in seconds (default: 30). +.TP +\fB\-i, \-\-interval\fR \fISEC\fR +Sampling interval in seconds; supports floating point (default: 1.0). +.TP +\fB\-o, \-\-output\fR \fICSV\fR +Path to the output CSV file where raw sampled data will be stored (default: \fBcapture.csv\fR). + +.SS report +Transform captured CSV data into an interactive HTML dashboard. +.TP +\fB\-b, \-\-base\fR \fICSV\fR +Primary capture file for analysis. +.TP +\fB\-c, \-\-curr\fR \fICSV\fR +Optional secondary file for differential (comparison) analysis. +.TP +\fB\-o, \-\-output\fR \fIHTML\fR +Path to the generated interactive HTML dashboard (default: \fBreport.html\fR). + +.SH HTML REPORT STRUCTURE +The generated HTML report provides a multi-dimensional view of kernel noise: +.IP "Total Time Delta Trend" 4 +A time-series line chart illustrating the incremental nanoseconds of interference per category (e.g., irq, spinlock). +.IP "Latency Heatmaps" 4 +A frequency-domain visualization of the kernel's internal histogram: +.RS 8 +.IP "X-axis:" 8 +Wall-clock time of the trace. +.IP "Y-axis:" 8 +Latency magnitude (logarithmic buckets from ns to s). +.IP "Color Intensity:" 8 +Represents the event count (density) of interference within that specific latency window. +.RE + +.SH EXAMPLES +Monitor a Docker container for 10 seconds: +.IP +.B $ ifstool monitor \-\-cgroup docker/<cid> \-\-duration 10 \-\-interval 1 +.PP +Generate a single-session deep dive: +.IP +.B $ ifstool report \-\-base capture.csv +.PP +Generate a differential report between two traces: +.IP +.B $ ifstool report \-\-base baseline.csv \-\-curr current.csv + +.SH AUTHOR +Tengda Wu <wutengda2(a)huawei.com> \ No newline at end of file diff --git a/tools/kspect/requirements.txt b/tools/kspect/requirements.txt new file mode 100644 index 000000000000..8e5e376a0e9a --- /dev/null +++ b/tools/kspect/requirements.txt @@ -0,0 +1,2 @@ +pandas==3.* +plotly==6.* -- 2.34.1

2 1

[PATCH OLK-5.10] gic: Add hip09 support for HISILICON_ERRATUM_165010801
by Zeng Heng 10 Mar '26

10 Mar '26

From: Yifan Wu <wuyifan50(a)huawei.com> driver inclusion category: bugfix bugzilla: https://atomgit.com/openeuler/kernel/issues/7023 ---------------------------------------------------------------------- Add hip09 support for HISILICON_ERRATUM_165010801 Fixes: f0f9be237c22 ("gic: increase the arch_timer priority to avoid hardlockup") Signed-off-by: Yifan Wu <wuyifan50(a)huawei.com> Signed-off-by: Zeng Heng <zengheng4(a)huawei.com> --- arch/arm64/Kconfig | 11 ++++++----- drivers/clocksource/arm_arch_timer.c | 5 +++++ 2 files changed, 11 insertions(+), 5 deletions(-) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 715c2810a43d..48fc9c71ed31 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -878,11 +878,12 @@ config HISILICON_ERRATUM_165010801 depends on ARCH_HISI default y help - On HIP12, when GIC receives multiple interrupts of the same priority and - different types, the interrupts are selected in the following sequence: - SPI > LPI > SGI > PPI. This scheduling rule may cause PPI starvation. - To prevent starvation from triggering system watchdog hardlockup, the - interrupt priority is explicitly increased in the arch_timer driver. + On HIP09/12 hardware, observations indicate that the GIC's handling of + equal-priority interrupts across different interrupt types may not always + provide balanced servicing. In some cases, this could result in prolonged + service delays for particular interrupt types, creating conditions where + system watchdog hardlockup detection might be triggered. The arch_timer + driver addresses this by proactively increasing affected interrupt priorities. config QCOM_FALKOR_ERRATUM_1003 bool "Falkor E1003: Incorrect translation due to ASID change" diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index 7f29ee39af3a..c6664d435921 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -340,6 +340,11 @@ static struct ate_acpi_oem_info hisi_161010101_oem_info[] = { #ifdef CONFIG_HISILICON_ERRATUM_165010801 static struct ate_acpi_oem_info hisi_165010801_oem_info[] = { + { + .oem_id = "HISI ", + .oem_table_id = "HIP09 ", + .oem_revision = 0, + }, { .oem_id = "HISI ", .oem_table_id = "HIP12 ", -- 2.25.1

2 1

[PATCH OLK-6.6] net: yt6801: add link info for yt6801
by Frank_Sae 10 Mar '26

10 Mar '26

yt6801 inclusion category: bugfix bugzilla: https://https://atomgit.com/openeuler/kernel/issues/7229 -------------------------------------------------------------------- add link info for yt6801 to fix that the link info is not update on os installation. Fixes: b9f5c0893d16 ("net: yt6801: add link info for yt6801") Signed-off-by: Frank_Sae <Frank.Sae(a)motor-comm.com> --- .../ethernet/motorcomm/yt6801/yt6801_main.c | 90 +++++++++++++++++++ 1 file changed, 90 insertions(+) diff --git a/drivers/net/ethernet/motorcomm/yt6801/yt6801_main.c b/drivers/net/ethernet/motorcomm/yt6801/yt6801_main.c index 01eed3ace..cb54329ef 100644 --- a/drivers/net/ethernet/motorcomm/yt6801/yt6801_main.c +++ b/drivers/net/ethernet/motorcomm/yt6801/yt6801_main.c @@ -27,6 +27,95 @@ const struct net_device_ops *fxgmac_get_netdev_ops(void); static void fxgmac_napi_enable(struct fxgmac_pdata *priv); +const struct ethtool_ops *fxgmac_get_ethtool_ops(void); + +#define MII_SPEC_STATUS 0x11 /* PHY specific status */ +#define FXGMAC_EPHY_LINK_STATUS BIT(10) +#define PHY_MII_SPEC_DUPLEX BIT(13) + +static int fxgmac_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) +{ + struct fxgmac_pdata *pdata = netdev_priv(netdev); + struct phy_device *phydev = netdev->phydev; + u32 duplex, regval, link_status; + u32 adv = 0xFFFFFFFF; + + ethtool_link_ksettings_zero_link_mode(cmd, supported); + ethtool_link_ksettings_zero_link_mode(cmd, advertising); + + /* set the supported link speeds */ + ethtool_link_ksettings_add_link_mode(cmd, supported, 1000baseT_Full); + ethtool_link_ksettings_add_link_mode(cmd, supported, 100baseT_Full); + ethtool_link_ksettings_add_link_mode(cmd, supported, 100baseT_Half); + ethtool_link_ksettings_add_link_mode(cmd, supported, 10baseT_Full); + ethtool_link_ksettings_add_link_mode(cmd, supported, 10baseT_Half); + + /* Indicate pause support */ + ethtool_link_ksettings_add_link_mode(cmd, supported, Pause); + ethtool_link_ksettings_add_link_mode(cmd, supported, Asym_Pause); + + regval = phy_read(phydev, MII_ADVERTISE); + + if (field_get(ADVERTISE_PAUSE_CAP, regval)) + ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause); + + if (field_get(ADVERTISE_PAUSE_ASYM, regval)) + ethtool_link_ksettings_add_link_mode(cmd, advertising, Asym_Pause); + + ethtool_link_ksettings_add_link_mode(cmd, supported, MII); + cmd->base.port = PORT_MII; + + ethtool_link_ksettings_add_link_mode(cmd, supported, Autoneg); + regval = phy_read(phydev, MII_BMCR); + + regval = field_get(BMCR_ANENABLE, regval); + if (regval) { + ethtool_link_ksettings_add_link_mode(cmd, advertising, Autoneg); + + regval = phy_read(phydev, MII_ADVERTISE); + + if (adv & ADVERTISE_10HALF) + ethtool_link_ksettings_add_link_mode(cmd, advertising, 10baseT_Half); + if (adv & ADVERTISE_10FULL) + ethtool_link_ksettings_add_link_mode(cmd, advertising, 10baseT_Full); + if (adv & ADVERTISE_100HALF) + ethtool_link_ksettings_add_link_mode(cmd, advertising, 100baseT_Half); + if (adv & ADVERTISE_100FULL) + ethtool_link_ksettings_add_link_mode(cmd, advertising, 100baseT_Full); + + adv = phy_read(phydev, MII_CTRL1000); + + if (adv & ADVERTISE_1000FULL) + ethtool_link_ksettings_add_link_mode(cmd, advertising, 1000baseT_Full); + } + + cmd->base.autoneg = 1; + + regval = phy_read(phydev, MII_SPEC_STATUS); + + link_status = field_get(FXGMAC_EPHY_LINK_STATUS, regval); + if (link_status) { + duplex = field_get(PHY_MII_SPEC_DUPLEX, regval); + cmd->base.duplex = duplex; + cmd->base.speed = pdata->mac_speed; + } else { + cmd->base.duplex = DUPLEX_UNKNOWN; + cmd->base.speed = SPEED_UNKNOWN; + } + + return 0; +} + +static const struct ethtool_ops fxgmac_ethtool_ops = { + .get_link = ethtool_op_get_link, + .get_link_ksettings = fxgmac_get_link_ksettings, +}; + +const struct ethtool_ops *fxgmac_get_ethtool_ops(void) +{ + return &fxgmac_ethtool_ops; +} #define PHY_WR_CONFIG(reg_offset) (0x8000205 + ((reg_offset) * 0x10000)) static int fxgmac_phy_write_reg(struct fxgmac_pdata *priv, u32 reg_id, u32 data) @@ -1899,6 +1988,7 @@ static int fxgmac_init(struct fxgmac_pdata *priv, bool save_private_reg) FXGMAC_JUMBO_PACKET_MTU + (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN); ndev->netdev_ops = fxgmac_get_netdev_ops();/* Set device operations */ + ndev->ethtool_ops = fxgmac_get_ethtool_ops();/* Set device operations */ /* Set device features */ if (priv->hw_feat.tso) { -- 2.34.1

2 1

[PATCH OLK-6.6 0/2] Fix TLBI broadcast optimization loss and incorrect dvmbm handling
by Tian Zheng 10 Mar '26

10 Mar '26

Fix 1 In the TLBI broadcast-optimization feature, the SYS_LSUDVM_CTRL_EL2 register controls whether the feature is enabled. When LPI low-power mode is enabled, this register is cleared as the pCPU powers down into LPI mode, causing the TLBI broadcast optimization to stop working. The fix saves and restores this control register in the callbacks for entering and exiting LPI mode. Fix 2 The current TLBI broadcast-optimization logic only supports normal VMs. If the feature is enabled globally, VMs that are not yet adapted for it, such as CCA will use an incorrect TLBI broadcast bitmap, which can cause a panic in CCA VMs. The fix moves the actual enable/disable of the dvmbm functionality into the vcpu load and vcpu put functions. Tian Zheng (2): KVM: arm64: Fix TLBI optimization broken in LPI mode KVM: arm64: Fix CCA guest panic when dvmbm is enabled arch/arm64/kvm/arm.c | 6 ++++++ arch/arm64/kvm/hisilicon/hisi_virt.c | 9 ++++----- arch/arm64/kvm/hisilicon/hisi_virt.h | 19 +++++++++++++++++++ 3 files changed, 29 insertions(+), 5 deletions(-) -- 2.33.0

1 2

[PATCH openEuler-1.0-LTS] [Huawei] PCI: Fix AB-BA deadlock between aer_isr() and device_shutdown()
by Hongtao Zhang 10 Mar '26

10 Mar '26

From: Ziming Du <duziming2(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13854 CVE: NA Reference: NA -------------------------------- During system shutdown, a deadlock may occur between AER recovery process and device shutdown as follows: The device_shutdown path holds the device_lock throughout the entire process and waits for the irq handlers to complete when release nodes: device_shutdown device_lock # A hold device_lock pci_device_shutdown pcie_port_device_remove remove_iter device_unregister device_del bus_remove_device device_release_driver devres_release_all release_nodes # B wait for irq handlers The aer_isr path will acquire device_lock in pci_bus_reset(): aer_isr # B execute irq process aer_isr_one_error aer_process_err_devices handle_error_source pcie_do_recovery aer_root_reset pci_bus_error_reset pci_bus_reset # A acquire device_lock The circular dependency causes system hang. Fix it by using pci_bus_trylock() instead of pci_bus_lock() in pci_bus_reset(). When the lock is unavailable, return -EAGAIN, as in similar cases. Fixes: c4eed62a2143 ("PCI/ERR: Use slot reset if available") Signed-off-by: Ziming Du <duziming2(a)huawei.com> Signed-off-by: Zhang Hongtao <zhanghongtao35(a)huawei.com> --- drivers/pci/pci.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index b93605616d4e4..d1a8531df0271 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -5309,15 +5309,21 @@ static int pci_bus_reset(struct pci_bus *bus, int probe) if (probe) return 0; - pci_bus_lock(bus); + /* + * Replace blocking lock with trylock to prevent deadlock during bus reset. + * Same as above except return -EAGAIN if the bus cannot be locked. + */ + if (pci_bus_trylock(bus)) { + might_sleep(); - might_sleep(); + ret = pci_bridge_secondary_bus_reset(bus->self); - ret = pci_bridge_secondary_bus_reset(bus->self); + pci_bus_unlock(bus); - pci_bus_unlock(bus); + return ret; + } - return ret; + return -EAGAIN; } /** -- 2.43.0

2 1

[PATCH openEuler-1.0-LTS] [Huawei] PCI: Fix AB-BA deadlock between aer_isr() and device_shutdown()
by Hongtao Zhang 10 Mar '26

10 Mar '26

From: Ziming Du <duziming2(a)huawei.com> Offering: HULK hulk inclusion category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13854 -------------------------------- During system shutdown, a deadlock may occur between AER recovery process and device shutdown as follows: The device_shutdown path holds the device_lock throughout the entire process and waits for the irq handlers to complete when release nodes: device_shutdown device_lock # A hold device_lock pci_device_shutdown pcie_port_device_remove remove_iter device_unregister device_del bus_remove_device device_release_driver devres_release_all release_nodes # B wait for irq handlers The aer_isr path will acquire device_lock in pci_bus_reset(): aer_isr # B execute irq process aer_isr_one_error aer_process_err_devices handle_error_source pcie_do_recovery aer_root_reset pci_bus_error_reset pci_bus_reset # A acquire device_lock The circular dependency causes system hang. Fix it by using pci_bus_trylock() instead of pci_bus_lock() in pci_bus_reset(). When the lock is unavailable, return -EAGAIN, as in similar cases. Fixes: c4eed62a2143 ("PCI/ERR: Use slot reset if available") Signed-off-by: Ziming Du <duziming2(a)huawei.com> Signed-off-by: Zhang Hongtao <zhanghongtao35(a)huawei.com> --- drivers/pci/pci.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index b93605616d4e4..d1a8531df0271 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -5309,15 +5309,21 @@ static int pci_bus_reset(struct pci_bus *bus, int probe) if (probe) return 0; - pci_bus_lock(bus); + /* + * Replace blocking lock with trylock to prevent deadlock during bus reset. + * Same as above except return -EAGAIN if the bus cannot be locked. + */ + if (pci_bus_trylock(bus)) { + might_sleep(); - might_sleep(); + ret = pci_bridge_secondary_bus_reset(bus->self); - ret = pci_bridge_secondary_bus_reset(bus->self); + pci_bus_unlock(bus); - pci_bus_unlock(bus); + return ret; + } - return ret; + return -EAGAIN; } /** -- 2.43.0

2 1

[PATCH OLK-6.6] sched: Add SOFT_DOMAIN feature interface for cgroup2
by Wang Tao 10 Mar '26

10 Mar '26

hulk inclusion category: other bugzilla: https://atomgit.com/openeuler/kernel/issues/8692 -------------------------------- Adapt interfaces 'soft_domain', 'soft_domain_nr_cpu', 'soft_domain_cpu_list' for the SOFT_DOMAIN feature to cgroup2. Signed-off-by: Wang Tao <wangtao554(a)huawei.com> --- kernel/sched/core.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index bf8022acd6ad..69d10fdb84d8 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -12292,6 +12292,25 @@ static struct cftype cpu_files[] = { .write = cpu_uclamp_max_write, }, #endif +#ifdef CONFIG_SCHED_SOFT_DOMAIN + { + .name = "soft_domain", + .flags = CFTYPE_NOT_ON_ROOT, + .read_s64 = cpu_soft_domain_read_s64, + .write_s64 = cpu_soft_domain_write_s64, + }, + { + .name = "soft_domain_nr_cpu", + .flags = CFTYPE_NOT_ON_ROOT, + .read_u64 = cpu_soft_domain_quota_read_u64, + .write_u64 = cpu_soft_domain_quota_write_u64, + }, + { + .name = "soft_domain_cpu_list", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = soft_domain_cpu_list_seq_show, + }, +#endif #ifdef CONFIG_SCHED_SOFT_QUOTA { .name = "soft_quota", -- 2.34.1

2 1

[PATCH OLK-6.6 0/8] fix CVE-2025-39981
by Jiacheng Yu 09 Mar '26

09 Mar '26

CVE-2025-39981 Gustavo A. R. Silva (1): overflow: Fix direct struct member initialization in _DEFINE_FLEX() Jianpeng Chang (1): Bluetooth: MGMT: Fix memory leak in set_ssp_complete Kees Cook (2): overflow: Change DEFINE_FLEX to take __counted_by member overflow: Introduce __DEFINE_FLEX for having no initializer Luiz Augusto von Dentz (1): Bluetooth: MGMT: Fix possible UAFs Pauli Virtanen (1): Bluetooth: MGMT: fix crash in set_mesh_sync and set_mesh_complete Przemek Kitszel (1): overflow: add DEFINE_FLEX() for on-stack allocs Roman Smirnov (1): Bluetooth: mgmt: remove NULL check in mgmt_set_connectable_complete() include/linux/compiler_types.h | 32 ++-- include/linux/fortify-string.h | 4 - include/linux/overflow.h | 65 ++++++++ include/net/bluetooth/mgmt.h | 2 +- lib/overflow_kunit.c | 19 +++ net/bluetooth/mgmt.c | 263 +++++++++++++++++++++++---------- net/bluetooth/mgmt_util.c | 46 ++++++ net/bluetooth/mgmt_util.h | 3 + 8 files changed, 342 insertions(+), 92 deletions(-) -- 2.43.0

2 9

[PATCH OLK-6.6 0/8] fix CVE-2025-39981
by Jiacheng Yu 09 Mar '26

09 Mar '26

CVE-2025-39981 Gustavo A. R. Silva (1): overflow: Fix direct struct member initialization in _DEFINE_FLEX() Jianpeng Chang (1): Bluetooth: MGMT: Fix memory leak in set_ssp_complete Kees Cook (2): overflow: Change DEFINE_FLEX to take __counted_by member overflow: Introduce __DEFINE_FLEX for having no initializer Luiz Augusto von Dentz (1): Bluetooth: MGMT: Fix possible UAFs Pauli Virtanen (1): Bluetooth: MGMT: fix crash in set_mesh_sync and set_mesh_complete Przemek Kitszel (1): overflow: add DEFINE_FLEX() for on-stack allocs Roman Smirnov (1): Bluetooth: mgmt: remove NULL check in mgmt_set_connectable_complete() include/linux/compiler_types.h | 36 +++-- include/linux/fortify-string.h | 4 - include/linux/overflow.h | 65 ++++++++ include/net/bluetooth/mgmt.h | 2 +- lib/overflow_kunit.c | 19 +++ net/bluetooth/mgmt.c | 263 +++++++++++++++++++++++---------- net/bluetooth/mgmt_util.c | 46 ++++++ net/bluetooth/mgmt_util.h | 3 + 8 files changed, 346 insertions(+), 92 deletions(-) -- 2.43.0

2 9

[PATCH OLK-6.6] tools/interference: add ifstool utility for kernel interference statistics
by Tengda Wu 09 Mar '26

09 Mar '26

hulk inclusion category: feature bugzilla: https://atomgit.com/openeuler/kernel/issues/7429 -------------------------------- As real-time and high-performance workloads become more sensitive to execution jitter, observability into kernel-induced "noise" is critical. The CONFIG_IFS infrastructure provides this telemetry, but raw data from cgroups is difficult to parse and visualize manually. Introduce ifstool, a userspace utility to monitor and analyze the interference.stat interface. Signed-off-by: Tengda Wu <wutengda2(a)huawei.com> --- tools/Makefile | 11 +- tools/kspect/Makefile | 28 +++ tools/kspect/README | 64 ++++++ tools/kspect/ifstool | 396 ++++++++++++++++++++++++++++++++++ tools/kspect/ifstool.1 | 81 +++++++ tools/kspect/requirements.txt | 2 + 6 files changed, 578 insertions(+), 4 deletions(-) create mode 100644 tools/kspect/Makefile create mode 100644 tools/kspect/README create mode 100644 tools/kspect/ifstool create mode 100644 tools/kspect/ifstool.1 create mode 100644 tools/kspect/requirements.txt diff --git a/tools/Makefile b/tools/Makefile index 37e9f6804832..153817f0cc17 100644 --- a/tools/Makefile +++ b/tools/Makefile @@ -22,6 +22,7 @@ help: @echo ' hv - tools used when in Hyper-V clients' @echo ' iio - IIO tools' @echo ' intel-speed-select - Intel Speed Select tool' + @echo ' kspect - KSPECT tools' @echo ' kvm_stat - top-like utility for displaying kvm statistics' @echo ' leds - LEDs tools' @echo ' nolibc - nolibc headers testing and installation' @@ -69,7 +70,7 @@ acpi: FORCE cpupower: FORCE $(call descend,power/$@) -cgroup counter firewire hv guest bootconfig spi usb virtio mm bpf iio gpio objtool leds wmi pci firmware debugging tracing: FORCE +cgroup counter firewire hv guest bootconfig spi usb virtio mm bpf iio gpio objtool leds wmi pci firmware debugging tracing kspect: FORCE $(call descend,$@) bpf/%: FORCE @@ -120,7 +121,8 @@ all: acpi cgroup counter cpupower gpio hv firewire \ perf selftests bootconfig spi turbostat usb \ virtio mm bpf x86_energy_perf_policy \ tmon freefall iio objtool kvm_stat wmi \ - pci debugging tracing thermal thermometer thermal-engine + pci debugging tracing thermal thermometer thermal-engine \ + kspect acpi_install: $(call descend,power/$(@:_install=),install) @@ -128,7 +130,7 @@ acpi_install: cpupower_install: $(call descend,power/$(@:_install=),install) -cgroup_install counter_install firewire_install gpio_install hv_install iio_install perf_install bootconfig_install spi_install usb_install virtio_install mm_install bpf_install objtool_install wmi_install pci_install debugging_install tracing_install: +cgroup_install counter_install firewire_install gpio_install hv_install iio_install perf_install bootconfig_install spi_install usb_install virtio_install mm_install bpf_install objtool_install wmi_install pci_install debugging_install tracing_install kspect_install: $(call descend,$(@:_install=),install) selftests_install: @@ -161,7 +163,8 @@ install: acpi_install cgroup_install counter_install cpupower_install gpio_insta virtio_install mm_install bpf_install x86_energy_perf_policy_install \ tmon_install freefall_install objtool_install kvm_stat_install \ wmi_install pci_install debugging_install intel-speed-select_install \ - tracing_install thermometer_install thermal-engine_install + tracing_install thermometer_install thermal-engine_install \ + kspect_install acpi_clean: $(call descend,power/acpi,clean) diff --git a/tools/kspect/Makefile b/tools/kspect/Makefile new file mode 100644 index 000000000000..ffb380ddc885 --- /dev/null +++ b/tools/kspect/Makefile @@ -0,0 +1,28 @@ +# SPDX-License-Identifier: GPL-2.0 + +PREFIX ?= /usr/local +BINDIR = $(PREFIX)/bin +MANDIR = $(PREFIX)/share/man/man1 + +MAN1 = ifstool.1 +TARGET = ifstool + +all: man + +man: $(MAN1) + +install-man: + install -d $(MANDIR) + install -m 0644 $(MAN1) $(MANDIR) + +install-tools: + install -d $(BINDIR) + install -m 0755 $(TARGET) $(BINDIR) + +install: install-tools install-man + +uninstall: + rm -f $(BINDIR)/$(TARGET) + rm -f $(MANDIR)/$(MAN1) + +.PHONY: all install-tools install-man install diff --git a/tools/kspect/README b/tools/kspect/README new file mode 100644 index 000000000000..afb92a7f98d0 --- /dev/null +++ b/tools/kspect/README @@ -0,0 +1,64 @@ +IFSTOOL - Interference Statistics Analytical Utility + +Overview +======== +IFSTOOL is a specialized userspace utility designed to facilitate the +monitoring and analysis of Interference Statistics (CONFIG_IFS). + +The IFS infrastructure is a kernel-level framework that provides critical +observability into execution jitter (noise) that disrupts task determinism. +It monitors and quantifies the CPU time stolen by kernel-level activities, +such as: interrupt handling, softirqs, and lock contention. The framework +exposes this telemetry via the interference.stat control file within the +cgroup hierarchy. + +IFSTOOL interfaces with the interference.stat file to export raw metrics +into structured CSV data and interactive HTML-based distribution reports. + +Setup +===== +The host environment must meet the following criteria: + +* Kernel: Compiled with `CONFIG_IFS=y`. +* Boot Parameters: `cgroup_ifs=1` added to the kernel command line. +* Python Runtime: Python 3.x with `pandas` and `plotly` libraries. +* Cgroup Hierarchy: Either v2 unified or v1 with the cpu subsystem mounted. + +Build +===== +IFSTOOL provides a Makefile to streamline the installation of the +executable and its documentation. + + $ make install + +Run +=== +IFSTOOL operates via two primary functional modes: monitor and report. + +1. **Monitor:** Capture raw interference data from a target cgroup. + + $ ifstool monitor --cgroup docker/<cid> --interval 1 --output capture.csv + +2. **Report:** Transform captured CSV data into an interactive HTML dashboard. + + - Provide only --base for a single-session deep dive: + + $ ifstool report --base capture.csv + + - Provide both --base and --curr to render a differential report, + ideal for validating optimizations: + + $ ifstool report --base baseline.csv --curr current.csv + +HTML Description +================ +The generated HTML report provides a multi-dimensional view of kernel noise: + +- Total Time Delta Trend: A time-series line chart illustrating the incremental + nanoseconds of interference per category (e.g., irq, spinlock). +- Latency Heatmaps: A frequency-domain visualization of the kernel's internal + histogram. + - X-axis: Wall-clock time of the trace. + - Y-axis: Latency magnitude (logarithmic buckets from ns to s). + - Color Intensity: Represents the density (event count) of interference + within that specific latency window. diff --git a/tools/kspect/ifstool b/tools/kspect/ifstool new file mode 100644 index 000000000000..dcaa8a84272d --- /dev/null +++ b/tools/kspect/ifstool @@ -0,0 +1,396 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0-only +# +# ifstool: A tool to monitor and report interference statistics (CONFIG_IFS). +# +# Copyright(c) 2026. Huawei Technologies Co., Ltd +# +# Authors: +# Tengda Wu <wutengda2(a)huawei.com> + +import os +import time +import re +import csv +import argparse +import pandas as pd +import plotly.graph_objects as go +from plotly.subplots import make_subplots + + +class InterferenceTool: + """ + A utility class to monitor Linux cgroup interference statistics (CONFIG_IFS) + and generate visual comparison reports between baseline and current data. + """ + + def __init__(self): + # Default path for cgroup v2 interference stats + self.base_path = "/sys/fs/cgroup" + + def parse_stat(self, content): + """ + Parses the raw content of the interference.stat file. + + Args: + content (str): Raw string content from the stat file. + Returns: + tuple: (total_times dict, distributions dict) + """ + + total_times, distributions = {}, {} + + # Split content into sections: Top-level totals and various distributions + # Uses positive lookahead to split before a word followed by ' distribution' + sections = re.split(r"\n(?=[a-z]+ distribution)", content) + + # Parse global total times (first section) + for line in sections[0].strip().split("\n"): + match = re.match(r"^([a-z]+)\s+(\d+)$", line.strip()) + if match: + total_times[match.group(1)] = int(match.group(2)) + + # Parse histogram distributions (subsequent sections) + for section in sections[1:]: + lines = section.strip().split("\n") + # Extract header name (e.g., 'spinlock distribution') + header = lines[0].replace(" distribution", "").strip() + # Parse bucket key-value pairs (e.g., '[64 ns, 128 ns) : 143791') + dist_data = { + l.split(":")[0].strip(): int(l.split(":")[1].strip()) + for l in lines[1:] + if ":" in l + } + distributions[header] = dist_data + + return total_times, distributions + + def monitor(self, cgroup_id, interval, duration, output_csv): + """ + Periodically samples interference stats and saves results to a CSV file. + + Args: + cgroup_id (str): The specific cgroup folder name. + interval (float): Seconds between samples. + duration (int): Total monitoring time in seconds. + output_csv (str): Filename to save sampled data. + """ + + candidates = [ + os.path.join(self.base_path, cgroup_id), + os.path.join(self.base_path, "cpu", cgroup_id), # cgroup v1 + ] + path = next((p for p in candidates if os.path.exists(p)), None) + + if not path: + print( + f"\n[!] No access to cgroup: {os.path.join(self.base_path, cgroup_id)}" + ) + print(" Hint: You can find the correct cid by executing:") + print(" cat /proc/<PID>/cgroup") + return + + path = os.path.join(path, "interference.stat") + if not os.path.exists(path): + print(f"\n[!] Interface file '{path}' not found.") + print(" This usually happens due to one of the following:") + print(" 1. Kernel is not compiled with CONFIG_IFS=y") + print(" 2. Kernel boot parameter 'cgroup_ifs=1' is missing") + print(" 3. The current cgroup is not managed by the IFS controller") + return + + print( + f"[*] Starting monitor: {cgroup_id}, interval: {interval}s, duration: {duration}s" + ) + + data_list = [] + start_time = time.time() + + try: + while (time.time() - start_time) < duration: + ts = time.strftime("%H:%M:%S") + # Using fractional seconds in timestamp for sub-second intervals + if interval < 1.0: + ts = time.strftime("%H:%M:%S") + f".{int((time.time()%1)*100):02d}" + + with open(path, "r") as f: + total_times, dists = self.parse_stat(f.read()) + + # Append total time metrics + for cat, val in total_times.items(): + data_list.append([ts, cgroup_id, cat, "total_time_ns", val]) + + # Append bucket distribution metrics + for cat, dist in dists.items(): + for b, c in dist.items(): + data_list.append([ts, cgroup_id, cat, f"bucket_{b}", c]) + + time.sleep(interval) + except KeyboardInterrupt: + print("\n[!] Monitoring interrupted by user.") + + # Write buffered data to CSV + with open(output_csv, "w", newline="") as f: + writer = csv.writer(f) + writer.writerow( + ["timestamp", "cgroup_id", "category", "metric_type", "value"] + ) + writer.writerows(data_list) + print(f"[+] Data exported successfully: {output_csv}") + + def bucket_key(self, bucket_str): + """ + Parsing logic for histogram bucket labels to enable correct numerical sorting. + Example input: "bucket_[67.10 ms, 134.21 ms)" + + Returns: + float: The value converted to nanoseconds (ns). + """ + try: + # Regex to capture the first number and its unit (ns|us|ms|s) + match = re.search(r"(\d+\.?\d*)\s*(ns|us|ms|s)", bucket_str) + if not match: + return 0 + + value = float(match.group(1)) + unit = match.group(2).lower() + + # Conversion factors to nanoseconds + factors = {"ns": 1, "us": 1000, "ms": 1000000, "s": 1000000000} + + return value * factors.get(unit, 1) + except Exception: + return 0 + + def report(self, base_csv, curr_csv, output_html): + """ + Loads two CSV files and generates an interactive HTML dashboard. + + Args: + base_csv (str): Path to baseline data. + curr_csv (str): Path to current data. + output_html (str): Path to generate the HTML report. + """ + + df_b = pd.read_csv(base_csv) + single_mode = curr_csv is None or base_csv == curr_csv + df_c = None if single_mode else pd.read_csv(curr_csv) + + # Get unique union of categories present in both datasets + all_dfs = [df_b] if single_mode else [df_b, df_c] + categories = sorted( + list(set().union(*(df.category.unique() for df in all_dfs))) + ) + + # Color mapping to ensure consistent colors for categories across plots + color_sequence = [ + "#636EFA", + "#EF553B", + "#00CC96", + "#AB63FA", + "#FFA15A", + "#19D3F3", + "#FF6692", + "#B6E880", + "#FF97FF", + "#FECB52", + ] + color_map = { + cat: color_sequence[i % len(color_sequence)] + for i, cat in enumerate(categories) + } + + # Build HTML content with CSS for layout + html_parts = ["<html><head><title>IFS Analysis Dashboard</title>"] + col_width = "100%" if single_mode else "49.5%" + html_parts.append( + f"""<style> + body{{font-family:'Segoe UI',sans-serif; background:#f0f2f5; padding:20px; color:#333;}} + .card{{background:white; padding:15px; margin-bottom:20px; border-radius:10px; box-shadow:0 2px 5px rgba(0,0,0,0.05);}} + .row-container{{display:flex; gap:15px; justify-content:space-between;}} + .col-item{{width:{col_width}; min-width:0;}} + .stat-box{{display:flex; gap:10px; margin:5px 0; font-size:0.85em; color:#555;}} + .stat-item{{background:#f1f3f5; padding:4px 8px; border-radius:4px; border-left:3px solid #007bff;}} + .section-header{{margin:30px 0 15px 0; padding-bottom:10px; border-bottom:2px solid #ddd;}} + </style></head><body>""" + ) + + title = "Performance Analysis" if single_mode else "Performance Comparison" + html_parts.append(f"<h2>{title} (CONFIG_IFS)</h2>") + info = ( + f"File: {base_csv}" + if single_mode + else f"Baseline: {base_csv} | Current: {curr_csv}" + ) + html_parts.append(f"<p style='color:#666;'>{info}</p>") + + # --- Part 1: Total Time Trends (Line Charts) --- + html_parts.append("<div class='card'>") + html_parts.append("<h3 style='margin-top:0;'>Total Time Delta (ns) Trend</h3>") + + # Subplots ensure Y-axis can be matched for direct visual comparison + fig_line = make_subplots( + rows=1, + cols=1 if single_mode else 2, + horizontal_spacing=0.05, + subplot_titles=("Latency",) if single_mode else ("Baseline", "Current"), + ) + + plot_configs = ( + [("Data", df_b)] if single_mode else [("Baseline", df_b), ("Current", df_c)] + ) + for i, (name, df) in enumerate(plot_configs, 1): + for cat in categories: + sub = df[ + (df["category"] == cat) & (df["metric_type"] == "total_time_ns") + ].sort_values("timestamp") + if not sub.empty: + y_val = sub["value"].diff().fillna(0) + fig_line.add_trace( + go.Scatter( + x=sub["timestamp"], + y=y_val, + name=f"{cat} ({name})", + legendgroup=cat, + mode="lines+markers", + line=dict(color=color_map[cat], width=2), + marker=dict(color=color_map[cat], size=6), + ), + row=1, + col=i, + ) + + # Sync Y-axes scale for baseline and current plots + if not single_mode: + fig_line.update_yaxes(matches="y", row=1, col=2) + fig_line.update_layout( + height=500, template="plotly_white", margin=dict(t=50, b=20) + ) + html_parts.append(fig_line.to_html(full_html=False, include_plotlyjs="cdn")) + html_parts.append("</div>") + + html_parts.append( + "<h3 class='section-header'>Detailed Latency Distribution</h3>" + ) + + # --- Part 2: Distribution Heatmaps --- + for cat in categories: + + def get_m_and_stats(df): + """Processes raw metrics into a delta-count matrix for heatmap visualization.""" + sub = df[ + (df["category"] == cat) + & (df["metric_type"].str.startswith("bucket_")) + ] + if sub.empty: + return pd.DataFrame(), {} + + # Transform to matrix (Buckets vs Time) + p = sub.pivot( + index="metric_type", columns="timestamp", values="value" + ).sort_index(axis=1) + # Sort Y-axis buckets based on numerical time value + p = p.reindex(sorted(p.index, key=self.bucket_key)) + # Calculate incremental change (delta) + delta = p.diff(axis=1).fillna(0) + return delta, { + "Total": int(delta.values.sum()), + "Peak": int(delta.values.max()), + } + + m_b, stats_b = get_m_and_stats(df_b) + m_c, stats_c = (None, None) if single_mode else get_m_and_stats(df_c) + + # Determine global max for heatmap color scaling consistency + z_vals = [m_b.values.max() if not m_b.empty else 0] + if not single_mode: + z_vals.append(m_c.values.max() if not m_c.empty else 0) + global_max_z = max(z_vals + [1]) + + html_parts.append(f"<div class='card'><h4>Category: {cat.upper()}</h4>") + html_parts.append("<div class='row-container'>") + + configs = ( + [("Data", m_b, stats_b)] + if single_mode + else [("Baseline", m_b, stats_b), ("Current", m_c, stats_c)] + ) + for name, m, stats in configs: + html_parts.append("<div class='col-item'>") + if not m.empty: + # Display summary statistics + html_parts.append("<div class='stat-box'>") + for k, v in stats.items(): + html_parts.append( + f"<div class='stat-item'><b>{k}:</b> {v}</div>" + ) + html_parts.append("</div>") + + # Generate Heatmap + fig = go.Figure( + data=go.Heatmap( + z=m.values, + x=m.columns, + y=m.index, + colorscale="Viridis", + zmin=0, + zmax=global_max_z, + colorbar=dict(title="Count", thickness=10, len=0.7), + ) + ) + fig.update_layout( + height=400, + margin=dict(l=120, r=0, t=10, b=30), + template="plotly_white", + ) + html_parts.append( + fig.to_html(full_html=False, include_plotlyjs="cdn") + ) + else: + html_parts.append( + "<div style='height:100px; display:flex; align-items:center; justify-content:center; background:#fafafa; color:#ccc;'>No Data</div>" + ) + html_parts.append("</div>") + + html_parts.append("</div></div>") # end row-container & card + + # Save the final HTML report + with open(output_html, "w") as f: + f.writelines(html_parts + ["</body></html>"]) + print(f"[+] Comparison report generated: {output_html}") + + +if __name__ == "__main__": + parser = argparse.ArgumentParser() + sub = parser.add_subparsers(dest="mode") + + # Monitor Mode Arguments + p_mon = sub.add_parser("monitor") + p_mon.add_argument( + "-G", "--cgroup", required=True, help="Cgroup name (e.g. 'docker/cid'" + ) + p_mon.add_argument( + "-i", "--interval", type=float, default=1.0, help="Sampling interval (sec)" + ) + p_mon.add_argument( + "-d", "--duration", type=int, default=30, help="Sampling duration (sec)" + ) + p_mon.add_argument("-o", "--output", default="capture.csv") + + # Report Mode Arguments + p_comp = sub.add_parser("report") + p_comp.add_argument("-b", "--base", required=True, help="Baseline CSV file") + p_comp.add_argument( + "-c", "--curr", default=None, help="Current CSV file (optional, for comparison)" + ) + p_comp.add_argument("-o", "--output", default="report.html") + + args = parser.parse_args() + tool = InterferenceTool() + + if args.mode == "monitor": + tool.monitor(args.cgroup, args.interval, args.duration, args.output) + elif args.mode == "report": + tool.report(args.base, args.curr, args.output) + else: + parser.print_help() diff --git a/tools/kspect/ifstool.1 b/tools/kspect/ifstool.1 new file mode 100644 index 000000000000..347d54f36bec --- /dev/null +++ b/tools/kspect/ifstool.1 @@ -0,0 +1,81 @@ +.TH IFSTOOL 1 "March 2026" "Linux" "User Commands" +.SH NAME +ifstool \- Analyze kernel interference statistics (CONFIG_IFS) +.SH SYNOPSIS +.B ifstool monitor +[\fB\-G\fR|\fB\-\-cgroup\fR \fICGROUP_ID\fR] [\fB\-d\fR|\fB\-\-duration\fR \fISEC\fR] [\fB\-i\fR|\fB\-\-interval\fR \fISEC\fR] [\fB\-o\fR|\fB\-\-output\fR \fICSV\fR] +.br +.B ifstool report +[\fB\-b\fR|\fB\-\-base\fR \fICSV\fR] [\fB\-c\fR|\fB\-\-curr\fR \fICSV\fR] [\fB\-o\fR|\fB\-\-output\fR \fIHTML\fR] + +.SH DESCRIPTION +.B IFSTOOL +is a specialized userspace utility designed to facilitate the monitoring and analysis of Interference Statistics (\fBCONFIG_IFS\fR). + +The \fBIFS infrastructure\fR is a kernel-level framework providing critical observability into execution jitter (noise) that disrupts task determinism. It quantifies CPU time stolen by kernel activities such as interrupt handling, softirqs, and lock contention. This telemetry is exposed via the \fBinterference.stat\fR control file within the cgroup hierarchy. + +\fBIFSTOOL\fR interfaces with this file to export raw metrics into structured CSV data and interactive HTML-based distribution reports. + +.SH SETUP +The host environment must meet the following criteria: +.IP \[bu] 2 +\fBKernel:\fR Compiled with \fBCONFIG_IFS=y\fR. +.IP \[bu] 2 +\fBBoot Parameters:\fR \fBcgroup_ifs=1\fR must be added to the kernel command line. +.IP \[bu] 2 +\fBPython Runtime:\fR Python 3.x with \fBpandas\fR and \fBplotly\fR libraries. +.IP \[bu] 2 +\fBCgroup Hierarchy:\fR Either v2 unified or v1 (with the \fBcpu\fR subsystem mounted). + +.SH COMMANDS +.SS monitor +Capture raw interference data from a target cgroup. +.TP +\fB\-G, \-\-cgroup\fR \fICGROUP_ID\fR +Specify the cgroup identifier (e.g., \fIdocker/<cid>\fR or \fIsystem.slice\fR). +.TP +\fB\-d, \-\-duration\fR \fISEC\fR +Total collection time in seconds (default: 30). +.TP +\fB\-i, \-\-interval\fR \fISEC\fR +Sampling interval in seconds; supports floating point (default: 1.0). + +.SS report +Transform captured CSV data into an interactive HTML dashboard. +.TP +\fB\-b, \-\-base\fR \fICSV\fR +Primary capture file for analysis. +.TP +\fB\-c, \-\-curr\fR \fICSV\fR +Optional secondary file for differential (comparison) analysis. + +.SH HTML REPORT STRUCTURE +The generated HTML report provides a multi-dimensional view of kernel noise: +.IP "Total Time Delta Trend" 4 +A time-series line chart illustrating the incremental nanoseconds of interference per category (e.g., irq, spinlock). +.IP "Latency Heatmaps" 4 +A frequency-domain visualization of the kernel's internal histogram: +.RS 8 +.IP "X-axis:" 8 +Wall-clock time of the trace. +.IP "Y-axis:" 8 +Latency magnitude (logarithmic buckets from ns to s). +.IP "Color Intensity:" 8 +Represents the event count (density) of interference within that specific latency window. +.RE + +.SH EXAMPLES +Monitor a Docker container for 10 seconds: +.IP +.B $ ifstool monitor \-\-cgroup docker/<cid> \-\-duration 10 \-\-interval 1 +.PP +Generate a single-session deep dive: +.IP +.B $ ifstool report \-\-base capture.csv +.PP +Generate a differential report between two traces: +.IP +.B $ ifstool report \-\-base baseline.csv \-\-curr current.csv + +.SH AUTHOR +Tengda Wu <wutengda2(a)huawei.com> \ No newline at end of file diff --git a/tools/kspect/requirements.txt b/tools/kspect/requirements.txt new file mode 100644 index 000000000000..8e5e376a0e9a --- /dev/null +++ b/tools/kspect/requirements.txt @@ -0,0 +1,2 @@ +pandas==3.* +plotly==6.* -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS] [Huawei] PCI: Fix AB-BA deadlock between aer_isr() and device_shutdown()
by Hongtao Zhang 09 Mar '26

09 Mar '26

From: Ziming Du <duziming2(a)huawei.com> Offering: HULK hulk inclusion category: bugfix bugzilla: 190803 -------------------------------- During system shutdown, a deadlock may occur between AER recovery process and device shutdown as follows: The device_shutdown path holds the device_lock throughout the entire process and waits for the irq handlers to complete when release nodes: device_shutdown device_lock # A hold device_lock pci_device_shutdown pcie_port_device_remove remove_iter device_unregister device_del bus_remove_device device_release_driver devres_release_all release_nodes # B wait for irq handlers The aer_isr path will acquire device_lock in pci_bus_reset(): aer_isr # B execute irq process aer_isr_one_error aer_process_err_devices handle_error_source pcie_do_recovery aer_root_reset pci_bus_error_reset pci_bus_reset # A acquire device_lock The circular dependency causes system hang. Fix it by using pci_bus_trylock() instead of pci_bus_lock() in pci_bus_reset(). When the lock is unavailable, return -EAGAIN, as in similar cases. Fixes: c4eed62a2143 ("PCI/ERR: Use slot reset if available") Signed-off-by: Ziming Du <duziming2(a)huawei.com> Signed-off-by: Zhang Hongtao <zhanghongtao35(a)huawei.com> --- drivers/pci/pci.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index b93605616d4e4..d1a8531df0271 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -5309,15 +5309,21 @@ static int pci_bus_reset(struct pci_bus *bus, int probe) if (probe) return 0; - pci_bus_lock(bus); + /* + * Replace blocking lock with trylock to prevent deadlock during bus reset. + * Same as above except return -EAGAIN if the bus cannot be locked. + */ + if (pci_bus_trylock(bus)) { + might_sleep(); - might_sleep(); + ret = pci_bridge_secondary_bus_reset(bus->self); - ret = pci_bridge_secondary_bus_reset(bus->self); + pci_bus_unlock(bus); - pci_bus_unlock(bus); + return ret; + } - return ret; + return -EAGAIN; } /** -- 2.43.0

2 1

[PATCH OLK-6.6 0/4] fixup CVE-2025-39981
by Jiacheng Yu 09 Mar '26

09 Mar '26

CVE-2025-39981 Jianpeng Chang (1): Bluetooth: MGMT: Fix memory leak in set_ssp_complete Luiz Augusto von Dentz (1): Bluetooth: MGMT: Fix possible UAFs Pauli Virtanen (1): Bluetooth: MGMT: fix crash in set_mesh_sync and set_mesh_complete Roman Smirnov (1): Bluetooth: mgmt: remove NULL check in mgmt_set_connectable_complete() include/net/bluetooth/mgmt.h | 2 +- net/bluetooth/mgmt.c | 263 +++++++++++++++++++++++++---------- net/bluetooth/mgmt_util.c | 46 ++++++ net/bluetooth/mgmt_util.h | 3 + 4 files changed, 237 insertions(+), 77 deletions(-) -- 2.43.0

2 5

[PATCH OLK-6.6] net: yt6801: add link info for yt6801
by Frank_Sae 09 Mar '26

09 Mar '26

yt6801 inclusion category: bugfix bugzilla: https://https://atomgit.com/openeuler/kernel/issues/7229 -------------------------------------------------------------------- add link info for yt6801 to fix that the link info is not update on os installation. Signed-off-by: Frank_Sae <Frank.Sae(a)motor-comm.com> --- .../ethernet/motorcomm/yt6801/yt6801_main.c | 90 +++++++++++++++++++ 1 file changed, 90 insertions(+) diff --git a/drivers/net/ethernet/motorcomm/yt6801/yt6801_main.c b/drivers/net/ethernet/motorcomm/yt6801/yt6801_main.c index 01eed3ace..cb54329ef 100644 --- a/drivers/net/ethernet/motorcomm/yt6801/yt6801_main.c +++ b/drivers/net/ethernet/motorcomm/yt6801/yt6801_main.c @@ -27,6 +27,95 @@ const struct net_device_ops *fxgmac_get_netdev_ops(void); static void fxgmac_napi_enable(struct fxgmac_pdata *priv); +const struct ethtool_ops *fxgmac_get_ethtool_ops(void); + +#define MII_SPEC_STATUS 0x11 /* PHY specific status */ +#define FXGMAC_EPHY_LINK_STATUS BIT(10) +#define PHY_MII_SPEC_DUPLEX BIT(13) + +static int fxgmac_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) +{ + struct fxgmac_pdata *pdata = netdev_priv(netdev); + struct phy_device *phydev = netdev->phydev; + u32 duplex, regval, link_status; + u32 adv = 0xFFFFFFFF; + + ethtool_link_ksettings_zero_link_mode(cmd, supported); + ethtool_link_ksettings_zero_link_mode(cmd, advertising); + + /* set the supported link speeds */ + ethtool_link_ksettings_add_link_mode(cmd, supported, 1000baseT_Full); + ethtool_link_ksettings_add_link_mode(cmd, supported, 100baseT_Full); + ethtool_link_ksettings_add_link_mode(cmd, supported, 100baseT_Half); + ethtool_link_ksettings_add_link_mode(cmd, supported, 10baseT_Full); + ethtool_link_ksettings_add_link_mode(cmd, supported, 10baseT_Half); + + /* Indicate pause support */ + ethtool_link_ksettings_add_link_mode(cmd, supported, Pause); + ethtool_link_ksettings_add_link_mode(cmd, supported, Asym_Pause); + + regval = phy_read(phydev, MII_ADVERTISE); + + if (field_get(ADVERTISE_PAUSE_CAP, regval)) + ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause); + + if (field_get(ADVERTISE_PAUSE_ASYM, regval)) + ethtool_link_ksettings_add_link_mode(cmd, advertising, Asym_Pause); + + ethtool_link_ksettings_add_link_mode(cmd, supported, MII); + cmd->base.port = PORT_MII; + + ethtool_link_ksettings_add_link_mode(cmd, supported, Autoneg); + regval = phy_read(phydev, MII_BMCR); + + regval = field_get(BMCR_ANENABLE, regval); + if (regval) { + ethtool_link_ksettings_add_link_mode(cmd, advertising, Autoneg); + + regval = phy_read(phydev, MII_ADVERTISE); + + if (adv & ADVERTISE_10HALF) + ethtool_link_ksettings_add_link_mode(cmd, advertising, 10baseT_Half); + if (adv & ADVERTISE_10FULL) + ethtool_link_ksettings_add_link_mode(cmd, advertising, 10baseT_Full); + if (adv & ADVERTISE_100HALF) + ethtool_link_ksettings_add_link_mode(cmd, advertising, 100baseT_Half); + if (adv & ADVERTISE_100FULL) + ethtool_link_ksettings_add_link_mode(cmd, advertising, 100baseT_Full); + + adv = phy_read(phydev, MII_CTRL1000); + + if (adv & ADVERTISE_1000FULL) + ethtool_link_ksettings_add_link_mode(cmd, advertising, 1000baseT_Full); + } + + cmd->base.autoneg = 1; + + regval = phy_read(phydev, MII_SPEC_STATUS); + + link_status = field_get(FXGMAC_EPHY_LINK_STATUS, regval); + if (link_status) { + duplex = field_get(PHY_MII_SPEC_DUPLEX, regval); + cmd->base.duplex = duplex; + cmd->base.speed = pdata->mac_speed; + } else { + cmd->base.duplex = DUPLEX_UNKNOWN; + cmd->base.speed = SPEED_UNKNOWN; + } + + return 0; +} + +static const struct ethtool_ops fxgmac_ethtool_ops = { + .get_link = ethtool_op_get_link, + .get_link_ksettings = fxgmac_get_link_ksettings, +}; + +const struct ethtool_ops *fxgmac_get_ethtool_ops(void) +{ + return &fxgmac_ethtool_ops; +} #define PHY_WR_CONFIG(reg_offset) (0x8000205 + ((reg_offset) * 0x10000)) static int fxgmac_phy_write_reg(struct fxgmac_pdata *priv, u32 reg_id, u32 data) @@ -1899,6 +1988,7 @@ static int fxgmac_init(struct fxgmac_pdata *priv, bool save_private_reg) FXGMAC_JUMBO_PACKET_MTU + (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN); ndev->netdev_ops = fxgmac_get_netdev_ops();/* Set device operations */ + ndev->ethtool_ops = fxgmac_get_ethtool_ops();/* Set device operations */ /* Set device features */ if (priv->hw_feat.tso) { -- 2.34.1

2 1

[PATCH OLK-5.10] ksmbd: fix use-after-free in kerberos authentication
by Yongjian Sun 09 Mar '26

09 Mar '26

From: Sean Heelan <seanheelan(a)gmail.com> mainline inclusion from mainline-v6.15-rc5 commit e86e9134e1d1c90a960dd57f59ce574d27b9a124 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/10609 CVE: CVE-2025-37778 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Setting sess->user = NULL was introduced to fix the dangling pointer created by ksmbd_free_user. However, it is possible another thread could be operating on the session and make use of sess->user after it has been passed to ksmbd_free_user but before sess->user is set to NULL. Cc: stable(a)vger.kernel.org Signed-off-by: Sean Heelan <seanheelan(a)gmail.com> Acked-by: Namjae Jeon <linkinjeon(a)kernel.org> Signed-off-by: Steve French <stfrench(a)microsoft.com> Conflicts: fs/smb/server/smb2pdu.c fs/ksmbd/smb2pdu.c fs/smb/server/auth.c fs/ksmbd/auth.c [mainline commit 38c8a9a52082 changed the file name] [mainline commit 1e440d5b25b7 still has issues] Signed-off-by: Yongjian Sun <sunyongjian1(a)huawei.com> --- fs/ksmbd/auth.c | 14 +++++++++++++- fs/ksmbd/smb2pdu.c | 3 --- 2 files changed, 13 insertions(+), 4 deletions(-) diff --git a/fs/ksmbd/auth.c b/fs/ksmbd/auth.c index d8dabd19823f..c5916064b85e 100644 --- a/fs/ksmbd/auth.c +++ b/fs/ksmbd/auth.c @@ -514,7 +514,19 @@ int ksmbd_krb5_authenticate(struct ksmbd_session *sess, char *in_blob, retval = -ENOMEM; goto out; } - sess->user = user; + + if (!sess->user) { + /* First successful authentication */ + sess->user = user; + } else { + if (!ksmbd_compare_user(sess->user, user)) { + ksmbd_debug(AUTH, "different user tried to reuse session\n"); + retval = -EPERM; + ksmbd_free_user(user); + goto out; + } + ksmbd_free_user(user); + } memcpy(sess->sess_key, resp->payload, resp->session_key_len); memcpy(out_blob, resp->payload + resp->session_key_len, diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 13f2a81d3621..1588867b4e71 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -1612,9 +1612,6 @@ static int krb5_authenticate(struct ksmbd_work *work, if (prev_sess_id && prev_sess_id != sess->id) destroy_previous_session(conn, sess->user, prev_sess_id); - if (sess->state == SMB2_SESSION_VALID) - ksmbd_free_user(sess->user); - retval = ksmbd_krb5_authenticate(sess, in_blob, in_len, out_blob, &out_len); if (retval) { -- 2.39.2

2 1

[PATCH openEuler-1.0-LTS] PCI: Fix pci_slot_trylock() error handling
by Ziming Du 09 Mar '26

09 Mar '26

From: Jinhui Guo <guojinhui.liam(a)bytedance.com> mainline inclusion from mainline-v7.0-rc1 commit 9368d1ee62829b08aa31836b3ca003803caf0b72 category: bugfix bugzilla: https://atomgit.com/openeuler/kernel/issues/8599 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Commit a4e772898f8b ("PCI: Add missing bridge lock to pci_bus_lock()") delegates the bridge device's pci_dev_trylock() to pci_bus_trylock() in pci_slot_trylock(), but it forgets to remove the corresponding pci_dev_unlock() when pci_bus_trylock() fails. Before a4e772898f8b, the code did: if (!pci_dev_trylock(dev)) /* <- lock bridge device */ goto unlock; if (dev->subordinate) { if (!pci_bus_trylock(dev->subordinate)) { pci_dev_unlock(dev); /* <- unlock bridge device */ goto unlock; } } After a4e772898f8b the bridge-device lock is no longer taken, but the pci_dev_unlock(dev) on the failure path was left in place, leading to the bug. This yields one of two errors: 1. A warning that the lock is being unlocked when no one holds it. 2. An incorrect unlock of a lock that belongs to another thread. Fix it by removing the now-redundant pci_dev_unlock(dev) on the failure path. [Same patch later posted by Keith at https://patch.msgid.link/20260116184150.3013258-1-kbusch@meta.com] Fixes: a4e772898f8b ("PCI: Add missing bridge lock to pci_bus_lock()") Signed-off-by: Jinhui Guo <guojinhui.liam(a)bytedance.com> Signed-off-by: Bjorn Helgaas <bhelgaas(a)google.com> Reviewed-by: Dan Williams <dan.j.williams(a)intel.com> Cc: stable(a)vger.kernel.org Link: https://patch.msgid.link/20251212145528.2555-1-guojinhui.liam@bytedance.com Signed-off-by: Ziming Du <duziming2(a)huawei.com> --- drivers/pci/pci.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index b93605616d4e4..fbef3c37f37fa 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -5144,10 +5144,8 @@ static int pci_slot_trylock(struct pci_slot *slot) if (!dev->slot || dev->slot != slot) continue; if (dev->subordinate) { - if (!pci_bus_trylock(dev->subordinate)) { - pci_dev_unlock(dev); + if (!pci_bus_trylock(dev->subordinate)) goto unlock; - } } else if (!pci_dev_trylock(dev)) goto unlock; } -- 2.43.0

2 1

[PATCH OLK-5.10] [Backport] sched/rt: Skip currently executing CPU in rto_next_cpu()
by Chen Jinghuang 09 Mar '26

09 Mar '26

mainline inclusion from mainline-v7.0-rc1 commit 94894c9c477e53bcea052e075c53f89df3d2a33e category: bugfix bugzilla: https://atomgit.com/openeuler/kernel/issues/8689 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- CPU0 becomes overloaded when hosting a CPU-bound RT task, a non-CPU-bound RT task, and a CFS task stuck in kernel space. When other CPUs switch from RT to non-RT tasks, RT load balancing (LB) is triggered; with HAVE_RT_PUSH_IPI enabled, they send IPIs to CPU0 to drive the execution of rto_push_irq_work_func. During push_rt_task on CPU0, if next_task->prio < rq->donor->prio, resched_curr() sets NEED_RESCHED and after the push operation completes, CPU0 calls rto_next_cpu(). Since only CPU0 is overloaded in this scenario, rto_next_cpu() should ideally return -1 (no further IPI needed). However, multiple CPUs invoking tell_cpu_to_push() during LB increments rd->rto_loop_next. Even when rd->rto_cpu is set to -1, the mismatch between rd->rto_loop and rd->rto_loop_next forces rto_next_cpu() to restart its search from -1. With CPU0 remaining overloaded (satisfying rt_nr_migratory && rt_nr_total > 1), it gets reselected, causing CPU0 to queue irq_work to itself and send self-IPIs repeatedly. As long as CPU0 stays overloaded and other CPUs run pull_rt_tasks(), it falls into an infinite self-IPI loop, which triggers a CPU hardlockup due to continuous self-interrupts. The trigging scenario is as follows: cpu0 cpu1 cpu2 pull_rt_task tell_cpu_to_push <------------irq_work_queue_on rto_push_irq_work_func push_rt_task resched_curr(rq) pull_rt_task rto_next_cpu tell_cpu_to_push <-------------------------- atomic_inc(rto_loop_next) rd->rto_loop != next rto_next_cpu irq_work_queue_on rto_push_irq_work_func Fix redundant self-IPI by filtering the initiating CPU in rto_next_cpu(). This solution has been verified to effectively eliminate spurious self-IPIs and prevent CPU hardlockup scenarios. Fixes: 4bdced5c9a29 ("sched/rt: Simplify the IPI based RT balancing logic") Suggested-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> Suggested-by: K Prateek Nayak <kprateek.nayak(a)amd.com> Signed-off-by: Chen Jinghuang <chenjinghuang2(a)huawei.com> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Reviewed-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> Reviewed-by: Valentin Schneider <vschneid(a)redhat.com> Link: https://patch.msgid.link/20260122012533.673768-1-chenjinghuang2@huawei.com Signed-off-by: Chen Jinghuang <chenjinghuang2(a)huawei.com> --- kernel/sched/rt.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index ddbc857a28b8..dbc3a40a68fa 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -2013,6 +2013,7 @@ static void push_rt_tasks(struct rq *rq) */ static int rto_next_cpu(struct root_domain *rd) { + int this_cpu = smp_processor_id(); int next; int cpu; @@ -2036,6 +2037,10 @@ static int rto_next_cpu(struct root_domain *rd) rd->rto_cpu = cpu; + /* Do not send IPI to self */ + if (cpu == this_cpu) + continue; + if (cpu < nr_cpu_ids) return cpu; -- 2.34.1

2 1

[PATCH OLK-6.6] arm64/mpam: Fix warning of schedule state in resctrl_arch_mon_ctx_alloc()
by Zeng Heng 09 Mar '26

09 Mar '26

hulk inclusion category: bugfix bugzilla: https://atomgit.com/openeuler/kernel/issues/8686 ------------------ resctrl_arch_mon_ctx_alloc() triggers a scheduling state warning when calling kmalloc() while the task is in a non-running state: do not call blocking ops when !TASK_RUNNING; state=1 set at prepare_to_wait WARNING: CPU: 78 PID: 12592 at kernel/sched/core.c:10584 _might_sleep Call trace: _might_sleep+0x1cc/0xf8 _kmalloc_cache_alloc_node+0x3a0/0x4e0 kmalloc_trace+0x44/0x120 resctrl_arch_mon_ctx_alloc+0xf0/0x178 mon_event_read+0xa0/0x308 mkdir_mondata_subdir+0x24c/0x330 mkdir_mondata_all+0x17c/0x248 rdt_get_tree+0x2e8/0x680 vfs_get_tree+0x5c/0x190 do_new_mount+0x27c/0x408 path_mount+0x2ac/0x448 arm64_sys_mount+0x1d4/0x228 Refactor the call sequence in resctrl_arch_mon_ctx_alloc() and ensure the allocation is performed in TASK_RUNNING state to avoid schedule state corrupted. Fixes: 9119da143939 ("arm_mpam: resctrl: Allow resctrl to allocate monitors") Signed-off-by: Zeng Heng <zengheng4(a)huawei.com> --- drivers/platform/mpam/mpam_resctrl.c | 24 +++++++++++------------- 1 file changed, 11 insertions(+), 13 deletions(-) diff --git a/drivers/platform/mpam/mpam_resctrl.c b/drivers/platform/mpam/mpam_resctrl.c index 9950cc4eebf4..a33957651732 100644 --- a/drivers/platform/mpam/mpam_resctrl.c +++ b/drivers/platform/mpam/mpam_resctrl.c @@ -388,32 +388,30 @@ struct rdt_resource *resctrl_arch_get_resource(enum resctrl_res_level l) return &mpam_resctrl_exports[l].resctrl_res; } -static void *resctrl_arch_mon_ctx_alloc_no_wait(struct rdt_resource *r, - int evtid) +static u32 resctrl_arch_mon_ctx_alloc_no_wait(struct rdt_resource *r, + int evtid) { - u32 *ret = kmalloc(sizeof(*ret), GFP_KERNEL); - - if (!ret) - return ERR_PTR(-ENOMEM); - - *ret = __mon_is_rmid_idx; - return ret; + return __mon_is_rmid_idx; } void *resctrl_arch_mon_ctx_alloc(struct rdt_resource *r, int evtid) { DEFINE_WAIT(wait); - void *ret; + u32 *ret; + + ret = kmalloc(sizeof(*ret), GFP_KERNEL); + if (!ret) + return ERR_PTR(-ENOMEM); might_sleep(); do { prepare_to_wait(&resctrl_mon_ctx_waiters, &wait, TASK_INTERRUPTIBLE); - ret = resctrl_arch_mon_ctx_alloc_no_wait(r, evtid); - if (PTR_ERR(ret) == -ENOSPC) + *ret = resctrl_arch_mon_ctx_alloc_no_wait(r, evtid); + if (*ret == -ENOSPC) schedule(); - } while (PTR_ERR(ret) == -ENOSPC && !signal_pending(current)); + } while (*ret == -ENOSPC && !signal_pending(current)); finish_wait(&resctrl_mon_ctx_waiters, &wait); return ret; -- 2.25.1

2 1

[PATCH OLK-6.6 0/2] Fix TLBI broadcast optimization loss and incorrect dvmbm handling
by Tian Zheng 09 Mar '26

09 Mar '26

Fix 1 In the TLBI broadcast-optimization feature, the SYS_LSUDVM_CTRL_EL2 register controls whether the feature is enabled. When LPI low-power mode is enabled, this register is cleared as the pCPU powers down into LPI mode, causing the TLBI broadcast optimization to stop working. The fix saves and restores this control register in the callbacks for entering and exiting LPI mode. Fix 2 The current TLBI broadcast-optimization logic only supports normal VMs. If the feature is enabled globally, VMs that are not yet adapted for it, such as CCA will use an incorrect TLBI broadcast bitmap, which can cause a panic in CCA VMs. The fix moves the actual enable/disable of the dvmbm functionality into the vcpu load and vcpu put functions. Tian Zheng (2): KVM: arm64: Fix TLBI optimization broken in LPI mode KVM: arm64: Fix CCA guest panic when dvmbm is enabled arch/arm64/kvm/arm.c | 6 ++++++ arch/arm64/kvm/hisilicon/hisi_virt.c | 8 +++----- arch/arm64/kvm/hisilicon/hisi_virt.h | 19 +++++++++++++++++++ 3 files changed, 28 insertions(+), 5 deletions(-) -- 2.33.0

1 2