- Linux-kselftest-mirror - lists.linaro.org

[PATCH v23 8/8] selftests/clone3: Test shadow stack support

by Mark Brown

Add basic test coverage for specifying the shadow stack for a newly created thread via clone3(), including coverage of the newly extended argument structure. We check that a user specified shadow stack can be provided, and that invalid combinations of parameters are rejected. In order to facilitate testing on systems without userspace shadow stack support we manually enable shadow stacks on startup, this is architecture specific due to the use of an arch_prctl() on x86. Due to interactions with potential userspace locking of features we actually detect support for shadow stacks on the running system by attempting to allocate a shadow stack page during initialisation using map_shadow_stack(), warning if this succeeds when the enable failed. In order to allow testing of user configured shadow stacks on architectures with that feature we need to ensure that we do not return from the function where the clone3() syscall is called in the child process, doing so would trigger a shadow stack underflow. To do this we use inline assembly rather than the standard syscall wrapper to call clone3(). In order to avoid surprises we also use a syscall rather than the libc exit() function., this should be overly cautious. Acked-by: Shuah Khan <skhan(a)linuxfoundation.org> Tested-by: Rick Edgecombe <rick.p.edgecombe(a)intel.com> Signed-off-by: Mark Brown <broonie(a)kernel.org> --- tools/testing/selftests/clone3/clone3.c | 143 +++++++++++++++++++++- tools/testing/selftests/clone3/clone3_selftests.h | 63 ++++++++++ 2 files changed, 205 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/clone3/clone3.c b/tools/testing/selftests/clone3/clone3.c index 932cc64e9ae4..829f0d1268c8 100644 --- a/tools/testing/selftests/clone3/clone3.c +++ b/tools/testing/selftests/clone3/clone3.c @@ -3,6 +3,7 @@ /* Based on Christian Brauner's clone3() example */ #define _GNU_SOURCE +#include <asm/mman.h> #include <errno.h> #include <inttypes.h> #include <linux/types.h> @@ -11,6 +12,7 @@ #include <stdint.h> #include <stdio.h> #include <stdlib.h> +#include <sys/mman.h> #include <sys/syscall.h> #include <sys/types.h> #include <sys/un.h> @@ -19,8 +21,12 @@ #include <sched.h> #include "kselftest.h" +#include "ksft_shstk.h" #include "clone3_selftests.h" +static bool shadow_stack_supported; +static size_t max_supported_args_size; + enum test_mode { CLONE3_ARGS_NO_TEST, CLONE3_ARGS_ALL_0, @@ -28,6 +34,10 @@ enum test_mode { CLONE3_ARGS_INVAL_EXIT_SIGNAL_NEG, CLONE3_ARGS_INVAL_EXIT_SIGNAL_CSIG, CLONE3_ARGS_INVAL_EXIT_SIGNAL_NSIG, + CLONE3_ARGS_SHADOW_STACK, + CLONE3_ARGS_SHADOW_STACK_MISALIGNED, + CLONE3_ARGS_SHADOW_STACK_NO_TOKEN, + CLONE3_ARGS_SHADOW_STACK_NORMAL_MEMORY, }; typedef bool (*filter_function)(void); @@ -44,6 +54,44 @@ struct test { filter_function filter; }; + +/* + * We check for shadow stack support by attempting to use + * map_shadow_stack() since features may have been locked by the + * dynamic linker resulting in spurious errors when we attempt to + * enable on startup. We warn if the enable failed. + */ +static void test_shadow_stack_supported(void) +{ + long ret; + + ret = syscall(__NR_map_shadow_stack, 0, getpagesize(), 0); + if (ret == -1) { + ksft_print_msg("map_shadow_stack() not supported\n"); + } else if ((void *)ret == MAP_FAILED) { + ksft_print_msg("Failed to map shadow stack\n"); + } else { + ksft_print_msg("Shadow stack supportd\n"); + shadow_stack_supported = true; + + if (!shadow_stack_enabled) + ksft_print_msg("Mapped but did not enable shadow stack\n"); + } +} + +static void *get_shadow_stack_page(unsigned long flags) +{ + unsigned long long page; + + page = syscall(__NR_map_shadow_stack, 0, getpagesize(), flags); + if ((void *)page == MAP_FAILED) { + ksft_print_msg("map_shadow_stack() failed: %d\n", errno); + return 0; + } + + return (void *)page; +} + static int call_clone3(uint64_t flags, size_t size, enum test_mode test_mode) { struct __clone_args args = { @@ -57,6 +105,7 @@ static int call_clone3(uint64_t flags, size_t size, enum test_mode test_mode) } args_ext; pid_t pid = -1; + void *p; int status; memset(&args_ext, 0, sizeof(args_ext)); @@ -89,6 +138,26 @@ static int call_clone3(uint64_t flags, size_t size, enum test_mode test_mode) case CLONE3_ARGS_INVAL_EXIT_SIGNAL_NSIG: args.exit_signal = 0x00000000000000f0ULL; break; + case CLONE3_ARGS_SHADOW_STACK: + p = get_shadow_stack_page(SHADOW_STACK_SET_TOKEN); + p += getpagesize() - sizeof(void *); + args.shstk_token = (unsigned long long)p; + break; + case CLONE3_ARGS_SHADOW_STACK_MISALIGNED: + p = get_shadow_stack_page(SHADOW_STACK_SET_TOKEN); + p += getpagesize() - sizeof(void *) - 1; + args.shstk_token = (unsigned long long)p; + break; + case CLONE3_ARGS_SHADOW_STACK_NORMAL_MEMORY: + p = malloc(getpagesize()); + p += getpagesize() - sizeof(void *); + args.shstk_token = (unsigned long long)p; + break; + case CLONE3_ARGS_SHADOW_STACK_NO_TOKEN: + p = get_shadow_stack_page(0); + p += getpagesize() - sizeof(void *); + args.shstk_token = (unsigned long long)p; + break; } memcpy(&args_ext.args, &args, sizeof(struct __clone_args)); @@ -102,7 +171,12 @@ static int call_clone3(uint64_t flags, size_t size, enum test_mode test_mode) if (pid == 0) { ksft_print_msg("I am the child, my PID is %d\n", getpid()); - _exit(EXIT_SUCCESS); + /* + * Use a raw syscall to ensure we don't get issues + * with manually specified shadow stack and exit handlers. + */ + syscall(__NR_exit, EXIT_SUCCESS); + ksft_print_msg("CHILD FAILED TO EXIT PID is %d\n", getpid()); } ksft_print_msg("I am the parent (%d). My child's pid is %d\n", @@ -184,6 +258,26 @@ static bool no_timenamespace(void) return true; } +static bool have_shadow_stack(void) +{ + if (shadow_stack_supported) { + ksft_print_msg("Shadow stack supported\n"); + return true; + } + + return false; +} + +static bool no_shadow_stack(void) +{ + if (!shadow_stack_supported) { + ksft_print_msg("Shadow stack not supported\n"); + return true; + } + + return false; +} + static size_t page_size_plus_8(void) { return getpagesize() + 8; @@ -327,6 +421,50 @@ static const struct test tests[] = { .expected = -EINVAL, .test_mode = CLONE3_ARGS_NO_TEST, }, + { + .name = "Shadow stack on system with shadow stack", + .size = 0, + .expected = 0, + .e2big_valid = true, + .test_mode = CLONE3_ARGS_SHADOW_STACK, + .filter = no_shadow_stack, + }, + { + .name = "Shadow stack with misaligned address", + .flags = CLONE_VM, + .size = 0, + .expected = -EINVAL, + .e2big_valid = true, + .test_mode = CLONE3_ARGS_SHADOW_STACK_MISALIGNED, + .filter = no_shadow_stack, + }, + { + .name = "Shadow stack with normal memory", + .flags = CLONE_VM, + .size = 0, + .expected = -EFAULT, + .e2big_valid = true, + .test_mode = CLONE3_ARGS_SHADOW_STACK_NORMAL_MEMORY, + .filter = no_shadow_stack, + }, + { + .name = "Shadow stack with no token", + .flags = CLONE_VM, + .size = 0, + .expected = -EINVAL, + .e2big_valid = true, + .test_mode = CLONE3_ARGS_SHADOW_STACK_NO_TOKEN, + .filter = no_shadow_stack, + }, + { + .name = "Shadow stack on system without shadow stack", + .flags = CLONE_VM, + .size = 0, + .expected = -EFAULT, + .e2big_valid = true, + .test_mode = CLONE3_ARGS_SHADOW_STACK_NORMAL_MEMORY, + .filter = have_shadow_stack, + }, }; int main(int argc, char *argv[]) @@ -334,9 +472,12 @@ int main(int argc, char *argv[]) size_t size; int i; + enable_shadow_stack(); + ksft_print_header(); ksft_set_plan(ARRAY_SIZE(tests)); test_clone3_supported(); + test_shadow_stack_supported(); for (i = 0; i < ARRAY_SIZE(tests); i++) test_clone3(&tests[i]); diff --git a/tools/testing/selftests/clone3/clone3_selftests.h b/tools/testing/selftests/clone3/clone3_selftests.h index a7ab2f1cccda..97d98d07fb78 100644 --- a/tools/testing/selftests/clone3/clone3_selftests.h +++ b/tools/testing/selftests/clone3/clone3_selftests.h @@ -31,12 +31,75 @@ struct __clone_args { __aligned_u64 set_tid; __aligned_u64 set_tid_size; __aligned_u64 cgroup; +#ifndef CLONE_ARGS_SIZE_VER2 +#define CLONE_ARGS_SIZE_VER2 88 /* sizeof third published struct */ +#endif + __aligned_u64 shstk_token; +#ifndef CLONE_ARGS_SIZE_VER3 +#define CLONE_ARGS_SIZE_VER3 96 /* sizeof fourth published struct */ +#endif }; +/* + * For architectures with shadow stack support we need to be + * absolutely sure that the clone3() syscall will be inline and not a + * function call so we open code. + */ +#ifdef __x86_64__ +static __always_inline pid_t sys_clone3(struct __clone_args *args, size_t size) +{ + register long _num __asm__ ("rax") = __NR_clone3; + register long _args __asm__ ("rdi") = (long)(args); + register long _size __asm__ ("rsi") = (long)(size); + long ret; + + __asm__ volatile ( + "syscall\n" + : "=a"(ret) + : "r"(_args), "r"(_size), + "0"(_num) + : "rcx", "r11", "memory", "cc" + ); + + if (ret < 0) { + errno = -ret; + return -1; + } + + return ret; +} +#elif defined(__aarch64__) +static __always_inline pid_t sys_clone3(struct __clone_args *args, size_t size) +{ + register long _num __asm__ ("x8") = __NR_clone3; + register long _args __asm__ ("x0") = (long)(args); + register long _size __asm__ ("x1") = (long)(size); + register long arg2 __asm__ ("x2") = 0; + register long arg3 __asm__ ("x3") = 0; + register long arg4 __asm__ ("x4") = 0; + + __asm__ volatile ( + "svc #0\n" + : "=r"(_args) + : "r"(_args), "r"(_size), + "r"(_num), "r"(arg2), + "r"(arg3), "r"(arg4) + : "memory", "cc" + ); + + if ((int)_args < 0) { + errno = -((int)_args); + return -1; + } + + return _args; +} +#else static pid_t sys_clone3(struct __clone_args *args, size_t size) { return syscall(__NR_clone3, args, size); } +#endif static inline void test_clone3_supported(void) { -- 2.47.3

9 hours, 37 minutes

1
0
0 0

[PATCH v23 7/8] selftests/clone3: Allow tests to flag if -E2BIG is a valid error code

by Mark Brown

The clone_args structure is extensible, with the syscall passing in the length of the structure. Inside the kernel we use copy_struct_from_user() to read the struct but this has the unfortunate side effect of silently accepting some overrun in the structure size providing the extra data is all zeros. This means that we can't discover the clone3() features that the running kernel supports by simply probing with various struct sizes. We need to check this for the benefit of test systems which run newer kselftests on old kernels. Add a flag which can be set on a test to indicate that clone3() may return -E2BIG due to the use of newer struct versions. Currently no tests need this but it will become an issue for testing clone3() support for shadow stacks, the support for shadow stacks is already present on x86. Reviewed-by: Kees Cook <kees(a)kernel.org> Tested-by: Kees Cook <kees(a)kernel.org> Acked-by: Shuah Khan <skhan(a)linuxfoundation.org> Reviewed-by: Catalin Marinas <catalin.marinas(a)arm.com> Tested-by: Rick Edgecombe <rick.p.edgecombe(a)intel.com> Signed-off-by: Mark Brown <broonie(a)kernel.org> --- tools/testing/selftests/clone3/clone3.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/tools/testing/selftests/clone3/clone3.c b/tools/testing/selftests/clone3/clone3.c index 8c852d022c55..932cc64e9ae4 100644 --- a/tools/testing/selftests/clone3/clone3.c +++ b/tools/testing/selftests/clone3/clone3.c @@ -39,6 +39,7 @@ struct test { size_t size; size_function size_function; int expected; + bool e2big_valid; enum test_mode test_mode; filter_function filter; }; @@ -146,6 +147,11 @@ static void test_clone3(const struct test *test) ksft_print_msg("[%d] clone3() with flags says: %d expected %d\n", getpid(), ret, test->expected); if (ret != test->expected) { + if (test->e2big_valid && ret == -E2BIG) { + ksft_print_msg("Test reported -E2BIG\n"); + ksft_test_result_skip("%s\n", test->name); + return; + } ksft_print_msg( "[%d] Result (%d) is different than expected (%d)\n", getpid(), ret, test->expected); -- 2.47.3

9 hours, 37 minutes

1
0
0 0

[PATCH v23 6/8] selftests/clone3: Factor more of main loop into test_clone3()

by Mark Brown

In order to make it easier to add more configuration for the tests and more support for runtime detection of when tests can be run pass the structure describing the tests into test_clone3() rather than picking the arguments out of it and have that function do all the per-test work. No functional change. Reviewed-by: Kees Cook <kees(a)kernel.org> Tested-by: Kees Cook <kees(a)kernel.org> Acked-by: Shuah Khan <skhan(a)linuxfoundation.org> Reviewed-by: Catalin Marinas <catalin.marinas(a)arm.com> Tested-by: Rick Edgecombe <rick.p.edgecombe(a)intel.com> Signed-off-by: Mark Brown <broonie(a)kernel.org> --- tools/testing/selftests/clone3/clone3.c | 77 ++++++++++++++++----------------- 1 file changed, 37 insertions(+), 40 deletions(-) diff --git a/tools/testing/selftests/clone3/clone3.c b/tools/testing/selftests/clone3/clone3.c index 289e0c7c1f09..8c852d022c55 100644 --- a/tools/testing/selftests/clone3/clone3.c +++ b/tools/testing/selftests/clone3/clone3.c @@ -30,6 +30,19 @@ enum test_mode { CLONE3_ARGS_INVAL_EXIT_SIGNAL_NSIG, }; +typedef bool (*filter_function)(void); +typedef size_t (*size_function)(void); + +struct test { + const char *name; + uint64_t flags; + size_t size; + size_function size_function; + int expected; + enum test_mode test_mode; + filter_function filter; +}; + static int call_clone3(uint64_t flags, size_t size, enum test_mode test_mode) { struct __clone_args args = { @@ -109,30 +122,40 @@ static int call_clone3(uint64_t flags, size_t size, enum test_mode test_mode) return 0; } -static bool test_clone3(uint64_t flags, size_t size, int expected, - enum test_mode test_mode) +static void test_clone3(const struct test *test) { + size_t size; int ret; + if (test->filter && test->filter()) { + ksft_test_result_skip("%s\n", test->name); + return; + } + + if (test->size_function) + size = test->size_function(); + else + size = test->size; + + ksft_print_msg("Running test '%s'\n", test->name); + ksft_print_msg( "[%d] Trying clone3() with flags %#" PRIx64 " (size %zu)\n", - getpid(), flags, size); - ret = call_clone3(flags, size, test_mode); + getpid(), test->flags, size); + ret = call_clone3(test->flags, size, test->test_mode); ksft_print_msg("[%d] clone3() with flags says: %d expected %d\n", - getpid(), ret, expected); - if (ret != expected) { + getpid(), ret, test->expected); + if (ret != test->expected) { ksft_print_msg( "[%d] Result (%d) is different than expected (%d)\n", - getpid(), ret, expected); - return false; + getpid(), ret, test->expected); + ksft_test_result_fail("%s\n", test->name); + return; } - return true; + ksft_test_result_pass("%s\n", test->name); } -typedef bool (*filter_function)(void); -typedef size_t (*size_function)(void); - static bool not_root(void) { if (getuid() != 0) { @@ -160,16 +183,6 @@ static size_t page_size_plus_8(void) return getpagesize() + 8; } -struct test { - const char *name; - uint64_t flags; - size_t size; - size_function size_function; - int expected; - enum test_mode test_mode; - filter_function filter; -}; - static const struct test tests[] = { { .name = "simple clone3()", @@ -319,24 +332,8 @@ int main(int argc, char *argv[]) ksft_set_plan(ARRAY_SIZE(tests)); test_clone3_supported(); - for (i = 0; i < ARRAY_SIZE(tests); i++) { - if (tests[i].filter && tests[i].filter()) { - ksft_test_result_skip("%s\n", tests[i].name); - continue; - } - - if (tests[i].size_function) - size = tests[i].size_function(); - else - size = tests[i].size; - - ksft_print_msg("Running test '%s'\n", tests[i].name); - - ksft_test_result(test_clone3(tests[i].flags, size, - tests[i].expected, - tests[i].test_mode), - "%s\n", tests[i].name); - } + for (i = 0; i < ARRAY_SIZE(tests); i++) + test_clone3(&tests[i]); ksft_finished(); } -- 2.47.3

9 hours, 37 minutes

1
0
0 0

[PATCH v23 5/8] selftests/clone3: Remove redundant flushes of output streams

by Mark Brown

Since there were widespread issues with output not being flushed the kselftest framework was modified to explicitly set the output streams unbuffered in commit 58e2847ad2e6 ("selftests: line buffer test program's stdout") so there is no need to explicitly flush in the clone3 tests. Reviewed-by: Kees Cook <kees(a)kernel.org> Tested-by: Kees Cook <kees(a)kernel.org> Acked-by: Shuah Khan <skhan(a)linuxfoundation.org> Reviewed-by: Catalin Marinas <catalin.marinas(a)arm.com> Tested-by: Rick Edgecombe <rick.p.edgecombe(a)intel.com> Signed-off-by: Mark Brown <broonie(a)kernel.org> --- tools/testing/selftests/clone3/clone3_selftests.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/tools/testing/selftests/clone3/clone3_selftests.h b/tools/testing/selftests/clone3/clone3_selftests.h index a0593e8950f0..a7ab2f1cccda 100644 --- a/tools/testing/selftests/clone3/clone3_selftests.h +++ b/tools/testing/selftests/clone3/clone3_selftests.h @@ -35,8 +35,6 @@ struct __clone_args { static pid_t sys_clone3(struct __clone_args *args, size_t size) { - fflush(stdout); - fflush(stderr); return syscall(__NR_clone3, args, size); } -- 2.47.3

9 hours, 37 minutes

1
0
0 0

[PATCH v23 4/8] fork: Add shadow stack support to clone3()

by Mark Brown

Unlike with the normal stack there is no API for configuring the shadow stack for a new thread, instead the kernel will dynamically allocate a new shadow stack with the same size as the normal stack. This appears to be due to the shadow stack series having been in development since before the more extensible clone3() was added rather than anything more deliberate. Add a parameter to clone3() specifying a shadow stack pointer to use for the new thread, this is inconsistent with the way we specify the normal stack but during review concerns were expressed about having to identify where the shadow stack pointer should be placed especially in cases where the shadow stack has been previously active. If no shadow stack is specified then the existing implicit allocation behaviour is maintained. If a shadow stack pointer is specified then it is required to have an architecture defined token placed on the stack, this will be consumed by the new task, the shadow stack is specified by pointing to this token. If no valid token is present then this will be reported with -EINVAL. This token prevents new threads being created pointing at the shadow stack of an existing running thread. On architectures with support for userspace pivoting of shadow stacks it is expected that the same format and placement of tokens will be used, this is the case for arm64 and x86. If the architecture does not support shadow stacks the shadow stack pointer must be not be specified, architectures that do support the feature are expected to enforce the same requirement on individual systems that lack shadow stack support. Update the existing arm64 and x86 implementations to pay attention to the newly added arguments, in order to maintain compatibility we use the existing behaviour if no shadow stack is specified. Since we are now using more fields from the kernel_clone_args we pass that into the shadow stack code rather than individual fields. Portions of the x86 architecture code were written by Rick Edgecombe. Acked-by: Yury Khrustalev <yury.khrustalev(a)arm.com> Reviewed-by: Rick Edgecombe <rick.p.edgecombe(a)intel.com> Reviewed-by: Catalin Marinas <catalin.marinas(a)arm.com> Signed-off-by: Mark Brown <broonie(a)kernel.org> --- arch/arm64/mm/gcs.c | 47 +++++++++++++++++++- arch/x86/include/asm/shstk.h | 11 +++-- arch/x86/kernel/process.c | 2 +- arch/x86/kernel/shstk.c | 53 ++++++++++++++++++++--- include/asm-generic/cacheflush.h | 11 +++++ include/linux/sched/task.h | 17 ++++++++ include/uapi/linux/sched.h | 9 ++-- kernel/fork.c | 93 ++++++++++++++++++++++++++++++++++------ 8 files changed, 217 insertions(+), 26 deletions(-) diff --git a/arch/arm64/mm/gcs.c b/arch/arm64/mm/gcs.c index 3abcbf9adb5c..fd1d5a6655de 100644 --- a/arch/arm64/mm/gcs.c +++ b/arch/arm64/mm/gcs.c @@ -43,8 +43,23 @@ int gcs_alloc_thread_stack(struct task_struct *tsk, { unsigned long addr, size; - if (!system_supports_gcs()) + if (!system_supports_gcs()) { + if (args->shstk_token) + return -EINVAL; + return 0; + } + + /* + * If the user specified a GCS then use it, otherwise fall + * back to a default allocation strategy. Validation is done + * in arch_shstk_validate_clone(). + */ + if (args->shstk_token) { + tsk->thread.gcs_base = 0; + tsk->thread.gcs_size = 0; + return 0; + } if (!task_gcs_el0_enabled(tsk)) return 0; @@ -68,6 +83,36 @@ int gcs_alloc_thread_stack(struct task_struct *tsk, return 0; } +static bool gcs_consume_token(struct vm_area_struct *vma, struct page *page, + unsigned long user_addr) +{ + u64 expected = GCS_CAP(user_addr); + u64 *token = page_address(page) + offset_in_page(user_addr); + + if (!cmpxchg_to_user_page(vma, page, user_addr, token, expected, 0)) + return false; + set_page_dirty_lock(page); + + return true; +} + +int arch_shstk_validate_clone(struct task_struct *tsk, + struct vm_area_struct *vma, + struct page *page, + struct kernel_clone_args *args) +{ + unsigned long gcspr_el0; + int ret = 0; + + gcspr_el0 = args->shstk_token; + if (!gcs_consume_token(vma, page, gcspr_el0)) + return -EINVAL; + + tsk->thread.gcspr_el0 = gcspr_el0 + sizeof(u64); + + return ret; +} + SYSCALL_DEFINE3(map_shadow_stack, unsigned long, addr, unsigned long, size, unsigned int, flags) { unsigned long alloc_size; diff --git a/arch/x86/include/asm/shstk.h b/arch/x86/include/asm/shstk.h index fc7dcec58fd4..42a5f03a51e2 100644 --- a/arch/x86/include/asm/shstk.h +++ b/arch/x86/include/asm/shstk.h @@ -6,6 +6,7 @@ #include <linux/types.h> struct task_struct; +struct kernel_clone_args; struct ksignal; #ifdef CONFIG_X86_USER_SHADOW_STACK @@ -16,8 +17,8 @@ struct thread_shstk { long shstk_prctl(struct task_struct *task, int option, unsigned long arg2); void reset_thread_features(void); -unsigned long shstk_alloc_thread_stack(struct task_struct *p, u64 clone_flags, - unsigned long stack_size); +unsigned long shstk_alloc_thread_stack(struct task_struct *p, + const struct kernel_clone_args *args); void shstk_free(struct task_struct *p); int setup_signal_shadow_stack(struct ksignal *ksig); int restore_signal_shadow_stack(void); @@ -30,8 +31,10 @@ static inline long shstk_prctl(struct task_struct *task, int option, unsigned long arg2) { return -EINVAL; } static inline void reset_thread_features(void) {} static inline unsigned long shstk_alloc_thread_stack(struct task_struct *p, - u64 clone_flags, - unsigned long stack_size) { return 0; } + const struct kernel_clone_args *args) +{ + return 0; +} static inline void shstk_free(struct task_struct *p) {} static inline int setup_signal_shadow_stack(struct ksignal *ksig) { return 0; } static inline int restore_signal_shadow_stack(void) { return 0; } diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 4c718f8adc59..449da29a9f92 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -219,7 +219,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) * is disabled, new_ssp will remain 0, and fpu_clone() will know not to * update it. */ - new_ssp = shstk_alloc_thread_stack(p, clone_flags, args->stack_size); + new_ssp = shstk_alloc_thread_stack(p, args); if (IS_ERR_VALUE(new_ssp)) return PTR_ERR((void *)new_ssp); diff --git a/arch/x86/kernel/shstk.c b/arch/x86/kernel/shstk.c index 978232b6d48d..d66c866274d0 100644 --- a/arch/x86/kernel/shstk.c +++ b/arch/x86/kernel/shstk.c @@ -191,18 +191,61 @@ void reset_thread_features(void) current->thread.features_locked = 0; } -unsigned long shstk_alloc_thread_stack(struct task_struct *tsk, u64 clone_flags, - unsigned long stack_size) +int arch_shstk_validate_clone(struct task_struct *t, + struct vm_area_struct *vma, + struct page *page, + struct kernel_clone_args *args) +{ + void *maddr = page_address(page); + unsigned long token; + int offset; + u64 expected; + + /* + * kernel_clone_args() verification assures token address is 8 + * byte aligned. + */ + token = args->shstk_token; + expected = (token + SS_FRAME_SIZE) | BIT(0); + offset = offset_in_page(token); + + if (!cmpxchg_to_user_page(vma, page, token, (unsigned long *)(maddr + offset), + expected, 0)) + return -EINVAL; + set_page_dirty_lock(page); + + return 0; +} + +unsigned long shstk_alloc_thread_stack(struct task_struct *tsk, + const struct kernel_clone_args *args) { struct thread_shstk *shstk = &tsk->thread.shstk; + u64 clone_flags = args->flags; unsigned long addr, size; /* * If shadow stack is not enabled on the new thread, skip any - * switch to a new shadow stack. + * implicit switch to a new shadow stack and reject attempts to + * explicitly specify one. */ - if (!features_enabled(ARCH_SHSTK_SHSTK)) + if (!features_enabled(ARCH_SHSTK_SHSTK)) { + if (args->shstk_token) + return (unsigned long)ERR_PTR(-EINVAL); + return 0; + } + + /* + * If the user specified a shadow stack then use it, otherwise + * fall back to a default allocation strategy. Validation is + * done in arch_shstk_validate_clone(). + */ + if (args->shstk_token) { + shstk->base = 0; + shstk->size = 0; + return args->shstk_token + 8; + } /* * For CLONE_VFORK the child will share the parents shadow stack. @@ -222,7 +265,7 @@ unsigned long shstk_alloc_thread_stack(struct task_struct *tsk, u64 clone_flags, if (!(clone_flags & CLONE_VM)) return 0; - size = adjust_shstk_size(stack_size); + size = adjust_shstk_size(args->stack_size); addr = alloc_shstk(0, size, 0, false); if (IS_ERR_VALUE(addr)) return addr; diff --git a/include/asm-generic/cacheflush.h b/include/asm-generic/cacheflush.h index 7ee8a179d103..96cc0c7a5c90 100644 --- a/include/asm-generic/cacheflush.h +++ b/include/asm-generic/cacheflush.h @@ -124,4 +124,15 @@ static inline void flush_cache_vunmap(unsigned long start, unsigned long end) } while (0) #endif +#ifndef cmpxchg_to_user_page +#define cmpxchg_to_user_page(vma, page, vaddr, ptr, old, new) \ +({ \ + bool ret; \ + \ + ret = try_cmpxchg(ptr, &old, new); \ + flush_icache_user_page(vma, page, vaddr, sizeof(*ptr)); \ + ret; \ +}) +#endif + #endif /* _ASM_GENERIC_CACHEFLUSH_H */ diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 525aa2a632b2..7f860edc58da 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -16,6 +16,7 @@ struct task_struct; struct rusage; union thread_union; struct css_set; +struct vm_area_struct; /* All the bits taken by the old clone syscall. */ #define CLONE_LEGACY_FLAGS 0xffffffffULL @@ -44,6 +45,7 @@ struct kernel_clone_args { struct cgroup *cgrp; struct css_set *cset; unsigned int kill_seq; + unsigned long shstk_token; }; /* @@ -225,4 +227,19 @@ static inline void task_unlock(struct task_struct *p) DEFINE_GUARD(task_lock, struct task_struct *, task_lock(_T), task_unlock(_T)) +#ifdef CONFIG_ARCH_HAS_USER_SHADOW_STACK +int arch_shstk_validate_clone(struct task_struct *p, + struct vm_area_struct *vma, + struct page *page, + struct kernel_clone_args *args); +#else +static inline int arch_shstk_validate_clone(struct task_struct *p, + struct vm_area_struct *vma, + struct page *page, + struct kernel_clone_args *args) +{ + return 0; +} +#endif + #endif /* _LINUX_SCHED_TASK_H */ diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h index 359a14cc76a4..7e18e7b3df3a 100644 --- a/include/uapi/linux/sched.h +++ b/include/uapi/linux/sched.h @@ -84,6 +84,7 @@ * kernel's limit of nested PID namespaces. * @cgroup: If CLONE_INTO_CGROUP is specified set this to * a file descriptor for the cgroup. + * @shstk_token: Pointer to shadow stack token at top of stack. * * The structure is versioned by size and thus extensible. * New struct members must go at the end of the struct and @@ -101,12 +102,14 @@ struct clone_args { __aligned_u64 set_tid; __aligned_u64 set_tid_size; __aligned_u64 cgroup; + __aligned_u64 shstk_token; }; #endif -#define CLONE_ARGS_SIZE_VER0 64 /* sizeof first published struct */ -#define CLONE_ARGS_SIZE_VER1 80 /* sizeof second published struct */ -#define CLONE_ARGS_SIZE_VER2 88 /* sizeof third published struct */ +#define CLONE_ARGS_SIZE_VER0 64 /* sizeof first published struct */ +#define CLONE_ARGS_SIZE_VER1 80 /* sizeof second published struct */ +#define CLONE_ARGS_SIZE_VER2 88 /* sizeof third published struct */ +#define CLONE_ARGS_SIZE_VER3 96 /* sizeof fourth published struct */ /* * Scheduling policies diff --git a/kernel/fork.c b/kernel/fork.c index b1f3915d5f8e..0d171e9055d6 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1955,6 +1955,51 @@ static bool need_futex_hash_allocate_default(u64 clone_flags) return true; } +static int shstk_validate_clone(struct task_struct *p, + struct kernel_clone_args *args) +{ + struct mm_struct *mm; + struct vm_area_struct *vma; + struct page *page; + unsigned long addr; + int ret; + + if (!IS_ENABLED(CONFIG_ARCH_HAS_USER_SHADOW_STACK)) + return 0; + + if (!args->shstk_token) + return 0; + + mm = get_task_mm(p); + if (!mm) + return -EFAULT; + + mmap_read_lock(mm); + + addr = untagged_addr_remote(mm, args->shstk_token); + page = get_user_page_vma_remote(mm, addr, FOLL_FORCE | FOLL_WRITE, + &vma); + if (IS_ERR(page)) { + ret = -EFAULT; + goto out; + } + + if (!(vma->vm_flags & VM_SHADOW_STACK) || + !(vma->vm_flags & VM_WRITE)) { + ret = -EFAULT; + goto out_page; + } + + ret = arch_shstk_validate_clone(p, vma, page, args); + +out_page: + put_page(page); +out: + mmap_read_unlock(mm); + mmput(mm); + return ret; +} + /* * This creates a new process as a copy of the old one, * but does not actually start it yet. @@ -2228,6 +2273,9 @@ __latent_entropy struct task_struct *copy_process( if (retval) goto bad_fork_cleanup_namespaces; retval = copy_thread(p, args); + if (retval) + goto bad_fork_cleanup_io; + retval = shstk_validate_clone(p, args); if (retval) goto bad_fork_cleanup_io; @@ -2807,7 +2855,9 @@ static noinline int copy_clone_args_from_user(struct kernel_clone_args *kargs, CLONE_ARGS_SIZE_VER1); BUILD_BUG_ON(offsetofend(struct clone_args, cgroup) != CLONE_ARGS_SIZE_VER2); - BUILD_BUG_ON(sizeof(struct clone_args) != CLONE_ARGS_SIZE_VER2); + BUILD_BUG_ON(offsetofend(struct clone_args, shstk_token) != + CLONE_ARGS_SIZE_VER3); + BUILD_BUG_ON(sizeof(struct clone_args) != CLONE_ARGS_SIZE_VER3); if (unlikely(usize > PAGE_SIZE)) return -E2BIG; @@ -2840,16 +2890,17 @@ static noinline int copy_clone_args_from_user(struct kernel_clone_args *kargs, return -EINVAL; *kargs = (struct kernel_clone_args){ - .flags = args.flags, - .pidfd = u64_to_user_ptr(args.pidfd), - .child_tid = u64_to_user_ptr(args.child_tid), - .parent_tid = u64_to_user_ptr(args.parent_tid), - .exit_signal = args.exit_signal, - .stack = args.stack, - .stack_size = args.stack_size, - .tls = args.tls, - .set_tid_size = args.set_tid_size, - .cgroup = args.cgroup, + .flags = args.flags, + .pidfd = u64_to_user_ptr(args.pidfd), + .child_tid = u64_to_user_ptr(args.child_tid), + .parent_tid = u64_to_user_ptr(args.parent_tid), + .exit_signal = args.exit_signal, + .stack = args.stack, + .stack_size = args.stack_size, + .tls = args.tls, + .set_tid_size = args.set_tid_size, + .cgroup = args.cgroup, + .shstk_token = args.shstk_token, }; if (args.set_tid && @@ -2890,6 +2941,24 @@ static inline bool clone3_stack_valid(struct kernel_clone_args *kargs) return true; } +/** + * clone3_shadow_stack_valid - check and prepare shadow stack + * @kargs: kernel clone args + * + * Verify that shadow stacks are only enabled if supported. + */ +static inline bool clone3_shadow_stack_valid(struct kernel_clone_args *kargs) +{ + if (!kargs->shstk_token) + return true; + + if (!IS_ALIGNED(kargs->shstk_token, sizeof(void *))) + return false; + + /* Fail if the kernel wasn't built with shadow stacks */ + return IS_ENABLED(CONFIG_ARCH_HAS_USER_SHADOW_STACK); +} + static bool clone3_args_valid(struct kernel_clone_args *kargs) { /* Verify that no unknown flags are passed along. */ @@ -2912,7 +2981,7 @@ static bool clone3_args_valid(struct kernel_clone_args *kargs) kargs->exit_signal) return false; - if (!clone3_stack_valid(kargs)) + if (!clone3_stack_valid(kargs) || !clone3_shadow_stack_valid(kargs)) return false; return true; -- 2.47.3

9 hours, 37 minutes

1
0
0 0

[PATCH v23 3/8] selftests: Provide helper header for shadow stack testing

by Mark Brown

While almost all users of shadow stacks should be relying on the dynamic linker and libc to enable the feature there are several low level test programs where it is useful to enable without any libc support, allowing testing without full system enablement. This low level testing is helpful during bringup of the support itself, and also in enabling coverage by automated testing without needing all system components in the target root filesystems to have enablement. Provide a header with helpers for this purpose, intended for use only by test programs directly exercising shadow stack interfaces. Reviewed-by: Rick Edgecombe <rick.p.edgecombe(a)intel.com> Reviewed-by: Kees Cook <kees(a)kernel.org> Tested-by: Kees Cook <kees(a)kernel.org> Acked-by: Shuah Khan <skhan(a)linuxfoundation.org> Acked-by: Catalin Marinas <catalin.marinas(a)arm.com> Tested-by: Rick Edgecombe <rick.p.edgecombe(a)intel.com> Signed-off-by: Mark Brown <broonie(a)kernel.org> --- tools/testing/selftests/ksft_shstk.h | 98 ++++++++++++++++++++++++++++++++++++ 1 file changed, 98 insertions(+) diff --git a/tools/testing/selftests/ksft_shstk.h b/tools/testing/selftests/ksft_shstk.h new file mode 100644 index 000000000000..fecf91218ea5 --- /dev/null +++ b/tools/testing/selftests/ksft_shstk.h @@ -0,0 +1,98 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Helpers for shadow stack enablement, this is intended to only be + * used by low level test programs directly exercising interfaces for + * working with shadow stacks. + * + * Copyright (C) 2024 ARM Ltd. + */ + +#ifndef __KSFT_SHSTK_H +#define __KSFT_SHSTK_H + +#include <asm/mman.h> + +/* This is currently only defined for x86 */ +#ifndef SHADOW_STACK_SET_TOKEN +#define SHADOW_STACK_SET_TOKEN (1ULL << 0) +#endif + +static bool shadow_stack_enabled; + +#ifdef __x86_64__ +#define ARCH_SHSTK_ENABLE 0x5001 +#define ARCH_SHSTK_SHSTK (1ULL << 0) + +#define ARCH_PRCTL(arg1, arg2) \ +({ \ + long _ret; \ + register long _num asm("eax") = __NR_arch_prctl; \ + register long _arg1 asm("rdi") = (long)(arg1); \ + register long _arg2 asm("rsi") = (long)(arg2); \ + \ + asm volatile ( \ + "syscall\n" \ + : "=a"(_ret) \ + : "r"(_arg1), "r"(_arg2), \ + "0"(_num) \ + : "rcx", "r11", "memory", "cc" \ + ); \ + _ret; \ +}) + +#define ENABLE_SHADOW_STACK +static __always_inline void enable_shadow_stack(void) +{ + int ret = ARCH_PRCTL(ARCH_SHSTK_ENABLE, ARCH_SHSTK_SHSTK); + if (ret == 0) + shadow_stack_enabled = true; +} + +#endif + +#ifdef __aarch64__ +#define PR_SET_SHADOW_STACK_STATUS 75 +# define PR_SHADOW_STACK_ENABLE (1UL << 0) + +#define my_syscall2(num, arg1, arg2) \ +({ \ + register long _num __asm__ ("x8") = (num); \ + register long _arg1 __asm__ ("x0") = (long)(arg1); \ + register long _arg2 __asm__ ("x1") = (long)(arg2); \ + register long _arg3 __asm__ ("x2") = 0; \ + register long _arg4 __asm__ ("x3") = 0; \ + register long _arg5 __asm__ ("x4") = 0; \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_arg1), "r"(_arg2), \ + "r"(_arg3), "r"(_arg4), \ + "r"(_arg5), "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define ENABLE_SHADOW_STACK +static __always_inline void enable_shadow_stack(void) +{ + int ret; + + ret = my_syscall2(__NR_prctl, PR_SET_SHADOW_STACK_STATUS, + PR_SHADOW_STACK_ENABLE); + if (ret == 0) + shadow_stack_enabled = true; +} + +#endif + +#ifndef __NR_map_shadow_stack +#define __NR_map_shadow_stack 453 +#endif + +#ifndef ENABLE_SHADOW_STACK +static inline void enable_shadow_stack(void) { } +#endif + +#endif -- 2.47.3

9 hours, 37 minutes

1
0
0 0

[PATCH v23 0/8] fork: Support shadow stacks in clone3()

by Mark Brown

At this point I think everyone in the on the kernel side is happy with this but there were some questions from the glibc side about the value of controlling the shadow stack placement and size, especially with the current inability to reuse the shadow stack for an exited thread. With support for reuse it would be possible to have a cache of shadow stacks as is currently supported for the normal stack. Since the discussion petered out I'm resending this in order to give people something work with while prototyping. It should be possible to prototype any potential kernel features to help build out shadow stack support in userspace by enabling shadow stack writes, as suggested by Rick Edgecombe this may end up being required anyway for supporting more exotic scenarios. On all current architectures with the feature writes to shadow stack require specific instructions so there are still security benefits even with writes enabled. I did send a change implementing a feature writing a token on thread exit to allow reuse: https://lore.kernel.org/r/20250921-arm64-gcs-exit-token-v1-0-45cf64e648d5@k… but wasn't planning to refresh it without some indication from the userspace side that that'd be useful. Non-process cover letter: The kernel has added support for shadow stacks, currently x86 only using their CET feature but both arm64 and RISC-V have equivalent features (GCS and Zicfiss respectively), I am actively working on GCS[1]. With shadow stacks the hardware maintains an additional stack containing only the return addresses for branch instructions which is not generally writeable by userspace and ensures that any returns are to the recorded addresses. This provides some protection against ROP attacks and making it easier to collect call stacks. These shadow stacks are allocated in the address space of the userspace process. Our API for shadow stacks does not currently offer userspace any flexiblity for managing the allocation of shadow stacks for newly created threads, instead the kernel allocates a new shadow stack with the same size as the normal stack whenever a thread is created with the feature enabled. The stacks allocated in this way are freed by the kernel when the thread exits or shadow stacks are disabled for the thread. This lack of flexibility and control isn't ideal, in the vast majority of cases the shadow stack will be over allocated and the implicit allocation and deallocation is not consistent with other interfaces. As far as I can tell the interface is done in this manner mainly because the shadow stack patches were in development since before clone3() was implemented. Since clone3() is readily extensible let's add support for specifying a shadow stack when creating a new thread or process, keeping the current implicit allocation behaviour if one is not specified either with clone3() or through the use of clone(). The user must provide a shadow stack pointer, this must point to memory mapped for use as a shadow stackby map_shadow_stack() with an architecture specified shadow stack token at the top of the stack. Yuri Khrustalev has raised questions from the libc side regarding discoverability of extended clone3() structure sizes[2], this seems like a general issue with clone3(). There was a suggestion to add a hwcap on arm64 which isn't ideal but is doable there, though architecture specific mechanisms would also be needed for x86 (and RISC-V if it's support gets merged before this does). The idea has, however, had strong pushback from the architecture maintainers and it is possible to detect support for this in clone3() by attempting a call with a misaligned shadow stack pointer specified so no hwcap has been added. [1] https://lore.kernel.org/linux-arm-kernel/20241001-arm64-gcs-v13-0-222b78d87… [2] https://lore.kernel.org/r/aCs65ccRQtJBnZ_5@arm.com Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Changes in v23: - Rebase onto v6.19-rc1. - Link to v22: https://lore.kernel.org/r/20251015-clone3-shadow-stack-v22-0-a8c8da011427@k… Changes in v22: - Rebase onto v6.18-rc1. - Cover letter updates. - Link to v21: https://lore.kernel.org/r/20250916-clone3-shadow-stack-v21-0-910493527013@k… Changes in v21: - Rebase onto https://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs.git kernel-6.18.clone3 - Rename shadow_stack_token to shstk_token, since it's a simple rename I've kept the acks and reviews but I dropped the tested-bys just to be safe. - Link to v20: https://lore.kernel.org/r/20250902-clone3-shadow-stack-v20-0-4d9fff1c53e7@k… Changes in v20: - Comment fixes and clarifications in x86 arch_shstk_validate_clone() from Rick Edgecombe. - Spelling fix in documentation. - Link to v19: https://lore.kernel.org/r/20250819-clone3-shadow-stack-v19-0-bc957075479b@k… Changes in v19: - Rebase onto v6.17-rc1. - Link to v18: https://lore.kernel.org/r/20250702-clone3-shadow-stack-v18-0-7965d2b694db@k… Changes in v18: - Rebase onto v6.16-rc3. - Thanks to pointers from Yuri Khrustalev this version has been tested on x86 so I have removed the RFT tag. - Clarify clone3_shadow_stack_valid() comment about the Kconfig check. - Remove redundant GCSB DSYNCs in arm64 code. - Fix token validation on x86. - Link to v17: https://lore.kernel.org/r/20250609-clone3-shadow-stack-v17-0-8840ed97ff6f@k… Changes in v17: - Rebase onto v6.16-rc1. - Link to v16: https://lore.kernel.org/r/20250416-clone3-shadow-stack-v16-0-2ffc9ca3917b@k… Changes in v16: - Rebase onto v6.15-rc2. - Roll in fixes from x86 testing from Rick Edgecombe. - Rework so that the argument is shadow_stack_token. - Link to v15: https://lore.kernel.org/r/20250408-clone3-shadow-stack-v15-0-3fa245c6e3be@k… Changes in v15: - Rebase onto v6.15-rc1. - Link to v14: https://lore.kernel.org/r/20250206-clone3-shadow-stack-v14-0-805b53af73b9@k… Changes in v14: - Rebase onto v6.14-rc1. - Link to v13: https://lore.kernel.org/r/20241203-clone3-shadow-stack-v13-0-93b89a81a5ed@k… Changes in v13: - Rebase onto v6.13-rc1. - Link to v12: https://lore.kernel.org/r/20241031-clone3-shadow-stack-v12-0-7183eb8bee17@k… Changes in v12: - Add the regular prctl() to the userspace API document since arm64 support is queued in -next. - Link to v11: https://lore.kernel.org/r/20241005-clone3-shadow-stack-v11-0-2a6a2bd6d651@k… Changes in v11: - Rebase onto arm64 for-next/gcs, which is based on v6.12-rc1, and integrate arm64 support. - Rework the interface to specify a shadow stack pointer rather than a base and size like we do for the regular stack. - Link to v10: https://lore.kernel.org/r/20240821-clone3-shadow-stack-v10-0-06e8797b9445@k… Changes in v10: - Integrate fixes & improvements for the x86 implementation from Rick Edgecombe. - Require that the shadow stack be VM_WRITE. - Require that the shadow stack base and size be sizeof(void *) aligned. - Clean up trailing newline. - Link to v9: https://lore.kernel.org/r/20240819-clone3-shadow-stack-v9-0-962d74f99464@ke… Changes in v9: - Pull token validation earlier and report problems with an error return to parent rather than signal delivery to the child. - Verify that the top of the supplied shadow stack is VM_SHADOW_STACK. - Rework token validation to only do the page mapping once. - Drop no longer needed support for testing for signals in selftest. - Fix typo in comments. - Link to v8: https://lore.kernel.org/r/20240808-clone3-shadow-stack-v8-0-0acf37caf14c@ke… Changes in v8: - Fix token verification with user specified shadow stack. - Don't track user managed shadow stacks for child processes. - Link to v7: https://lore.kernel.org/r/20240731-clone3-shadow-stack-v7-0-a9532eebfb1d@ke… Changes in v7: - Rebase onto v6.11-rc1. - Typo fixes. - Link to v6: https://lore.kernel.org/r/20240623-clone3-shadow-stack-v6-0-9ee7783b1fb9@ke… Changes in v6: - Rebase onto v6.10-rc3. - Ensure we don't try to free the parent shadow stack in error paths of x86 arch code. - Spelling fixes in userspace API document. - Additional cleanups and improvements to the clone3() tests to support the shadow stack tests. - Link to v5: https://lore.kernel.org/r/20240203-clone3-shadow-stack-v5-0-322c69598e4b@ke… Changes in v5: - Rebase onto v6.8-rc2. - Rework ABI to have the user allocate the shadow stack memory with map_shadow_stack() and a token. - Force inlining of the x86 shadow stack enablement. - Move shadow stack enablement out into a shared header for reuse by other tests. - Link to v4: https://lore.kernel.org/r/20231128-clone3-shadow-stack-v4-0-8b28ffe4f676@ke… Changes in v4: - Formatting changes. - Use a define for minimum shadow stack size and move some basic validation to fork.c. - Link to v3: https://lore.kernel.org/r/20231120-clone3-shadow-stack-v3-0-a7b8ed3e2acc@ke… Changes in v3: - Rebase onto v6.7-rc2. - Remove stale shadow_stack in internal kargs. - If a shadow stack is specified unconditionally use it regardless of CLONE_ parameters. - Force enable shadow stacks in the selftest. - Update changelogs for RISC-V feature rename. - Link to v2: https://lore.kernel.org/r/20231114-clone3-shadow-stack-v2-0-b613f8681155@ke… Changes in v2: - Rebase onto v6.7-rc1. - Remove ability to provide preallocated shadow stack, just specify the desired size. - Link to v1: https://lore.kernel.org/r/20231023-clone3-shadow-stack-v1-0-d867d0b5d4d0@ke… --- Mark Brown (8): arm64/gcs: Return a success value from gcs_alloc_thread_stack() Documentation: userspace-api: Add shadow stack API documentation selftests: Provide helper header for shadow stack testing fork: Add shadow stack support to clone3() selftests/clone3: Remove redundant flushes of output streams selftests/clone3: Factor more of main loop into test_clone3() selftests/clone3: Allow tests to flag if -E2BIG is a valid error code selftests/clone3: Test shadow stack support Documentation/userspace-api/index.rst | 1 + Documentation/userspace-api/shadow_stack.rst | 44 +++++ arch/arm64/include/asm/gcs.h | 8 +- arch/arm64/kernel/process.c | 8 +- arch/arm64/mm/gcs.c | 55 +++++- arch/x86/include/asm/shstk.h | 11 +- arch/x86/kernel/process.c | 2 +- arch/x86/kernel/shstk.c | 53 ++++- include/asm-generic/cacheflush.h | 11 ++ include/linux/sched/task.h | 17 ++ include/uapi/linux/sched.h | 9 +- kernel/fork.c | 93 +++++++-- tools/testing/selftests/clone3/clone3.c | 226 ++++++++++++++++++---- tools/testing/selftests/clone3/clone3_selftests.h | 65 ++++++- tools/testing/selftests/ksft_shstk.h | 98 ++++++++++ 15 files changed, 620 insertions(+), 81 deletions(-) --- base-commit: 8f0b4cce4481fb22653697cced8d0d04027cb1e8 change-id: 20231019-clone3-shadow-stack-15d40d2bf536 Best regards, -- Mark Brown <broonie(a)kernel.org>

9 hours, 37 minutes

1
1
0 0

[PATCH v23 1/8] arm64/gcs: Return a success value from gcs_alloc_thread_stack()

by Mark Brown

Currently as a result of templating from x86 code gcs_alloc_thread_stack() returns a pointer as an unsigned int however on arm64 we don't actually use this pointer value as anything other than a pass/fail flag. Simplify the interface to just return an int with 0 on success and a negative error code on failure. Acked-by: Deepak Gupta <debug(a)rivosinc.com> Reviewed-by: Catalin Marinas <catalin.marinas(a)arm.com> Signed-off-by: Mark Brown <broonie(a)kernel.org> --- arch/arm64/include/asm/gcs.h | 8 ++++---- arch/arm64/kernel/process.c | 8 ++++---- arch/arm64/mm/gcs.c | 8 ++++---- 3 files changed, 12 insertions(+), 12 deletions(-) diff --git a/arch/arm64/include/asm/gcs.h b/arch/arm64/include/asm/gcs.h index 8fa0707069e8..534ea5ae9281 100644 --- a/arch/arm64/include/asm/gcs.h +++ b/arch/arm64/include/asm/gcs.h @@ -64,8 +64,8 @@ static inline bool task_gcs_el0_enabled(struct task_struct *task) void gcs_set_el0_mode(struct task_struct *task); void gcs_free(struct task_struct *task); void gcs_preserve_current_state(void); -unsigned long gcs_alloc_thread_stack(struct task_struct *tsk, - const struct kernel_clone_args *args); +int gcs_alloc_thread_stack(struct task_struct *tsk, + const struct kernel_clone_args *args); static inline int gcs_check_locked(struct task_struct *task, unsigned long new_val) @@ -171,8 +171,8 @@ static inline void put_user_gcs(unsigned long val, unsigned long __user *addr, int *err) { } static inline void push_user_gcs(unsigned long val, int *err) { } -static inline unsigned long gcs_alloc_thread_stack(struct task_struct *tsk, - const struct kernel_clone_args *args) +static inline int gcs_alloc_thread_stack(struct task_struct *tsk, + const struct kernel_clone_args *args) { return -ENOTSUPP; } diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index fba7ca102a8c..4dadc70df16b 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -299,7 +299,7 @@ static void flush_gcs(void) static int copy_thread_gcs(struct task_struct *p, const struct kernel_clone_args *args) { - unsigned long gcs; + int ret; if (!system_supports_gcs()) return 0; @@ -310,9 +310,9 @@ static int copy_thread_gcs(struct task_struct *p, p->thread.gcs_el0_mode = current->thread.gcs_el0_mode; p->thread.gcs_el0_locked = current->thread.gcs_el0_locked; - gcs = gcs_alloc_thread_stack(p, args); - if (IS_ERR_VALUE(gcs)) - return PTR_ERR((void *)gcs); + ret = gcs_alloc_thread_stack(p, args); + if (ret != 0) + return ret; return 0; } diff --git a/arch/arm64/mm/gcs.c b/arch/arm64/mm/gcs.c index 6e93f78de79b..3abcbf9adb5c 100644 --- a/arch/arm64/mm/gcs.c +++ b/arch/arm64/mm/gcs.c @@ -38,8 +38,8 @@ static unsigned long gcs_size(unsigned long size) return max(PAGE_SIZE, size); } -unsigned long gcs_alloc_thread_stack(struct task_struct *tsk, - const struct kernel_clone_args *args) +int gcs_alloc_thread_stack(struct task_struct *tsk, + const struct kernel_clone_args *args) { unsigned long addr, size; @@ -59,13 +59,13 @@ unsigned long gcs_alloc_thread_stack(struct task_struct *tsk, size = gcs_size(size); addr = alloc_gcs(0, size); if (IS_ERR_VALUE(addr)) - return addr; + return PTR_ERR((void *)addr); tsk->thread.gcs_base = addr; tsk->thread.gcs_size = size; tsk->thread.gcspr_el0 = addr + size - sizeof(u64); - return addr; + return 0; } SYSCALL_DEFINE3(map_shadow_stack, unsigned long, addr, unsigned long, size, unsigned int, flags) -- 2.47.3

9 hours, 37 minutes

1
0
0 0

[PATCH][v2] watchdog: softlockup: panic when lockup duration exceeds N thresholds

by lirongqing

From: Li RongQing <lirongqing(a)baidu.com> The softlockup_panic sysctl is currently a binary option: panic immediately or never panic on soft lockups. Panicking on any soft lockup, regardless of duration, can be overly aggressive for brief stalls that may be caused by legitimate operations. Conversely, never panicking may allow severe system hangs to persist undetected. Extend softlockup_panic to accept an integer threshold, allowing the kernel to panic only when the normalized lockup duration exceeds N watchdog threshold periods. This provides finer-grained control to distinguish between transient delays and persistent system failures. The accepted values are: - 0: Don't panic (unchanged) - 1: Panic when duration >= 1 * threshold (20s default, original behavior) - N > 1: Panic when duration >= N * threshold (e.g., 2 = 40s, 3 = 60s.) The original behavior is preserved for values 0 and 1, maintaining full backward compatibility while allowing systems to tolerate brief lockups while still catching severe, persistent hangs. Signed-off-by: Li RongQing <lirongqing(a)baidu.com> Cc: Eduard Zingerman <eddyz87(a)gmail.com> Cc: Hao Luo <haoluo(a)google.com> Cc: Jiri Olsa <jolsa(a)kernel.org> Cc: John Fastabend <john.fastabend(a)gmail.com> Cc: KP Singh <kpsingh(a)kernel.org> Cc: Lance Yang <lance.yang(a)linux.dev> Cc: Martin KaFai Lau <martin.lau(a)linux.dev> Cc: Nicholas Piggin <npiggin(a)gmail.com> Cc: Song Liu <song(a)kernel.org> Cc: Stanislav Fomichev <sdf(a)fomichev.me> Cc: Yonghong Song <yonghong.song(a)linux.dev> Cc: Andrew Morton <akpm(a)linux-foundation.org> --- Diff with v1: add a temp variable thresh_count chang config to 0 in kernel/configs/debug.config Documentation/admin-guide/kernel-parameters.txt | 10 +++++----- arch/arm/configs/aspeed_g5_defconfig | 2 +- arch/arm/configs/pxa3xx_defconfig | 2 +- arch/openrisc/configs/or1klitex_defconfig | 2 +- arch/powerpc/configs/skiroot_defconfig | 2 +- drivers/gpu/drm/ci/arm.config | 2 +- drivers/gpu/drm/ci/arm64.config | 2 +- drivers/gpu/drm/ci/x86_64.config | 2 +- kernel/configs/debug.config | 2 +- kernel/watchdog.c | 10 ++++++---- lib/Kconfig.debug | 13 +++++++------ tools/testing/selftests/bpf/config | 2 +- tools/testing/selftests/wireguard/qemu/kernel.config | 2 +- 13 files changed, 28 insertions(+), 25 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index a8d0afd..27c5f96 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -6934,12 +6934,12 @@ Kernel parameters softlockup_panic= [KNL] Should the soft-lockup detector generate panics. - Format: 0 | 1 + Format: <int> - A value of 1 instructs the soft-lockup detector - to panic the machine when a soft-lockup occurs. It is - also controlled by the kernel.softlockup_panic sysctl - and CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC, which is the + A value of non-zero instructs the soft-lockup detector + to panic the machine when a soft-lockup duration exceeds + N thresholds. It is also controlled by the kernel.softlockup_panic + sysctl and CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC, which is the respective build-time switch to that functionality. softlockup_all_cpu_backtrace= diff --git a/arch/arm/configs/aspeed_g5_defconfig b/arch/arm/configs/aspeed_g5_defconfig index 2e6ea13..ec558e5 100644 --- a/arch/arm/configs/aspeed_g5_defconfig +++ b/arch/arm/configs/aspeed_g5_defconfig @@ -306,7 +306,7 @@ CONFIG_SCHED_STACK_END_CHECK=y CONFIG_PANIC_ON_OOPS=y CONFIG_PANIC_TIMEOUT=-1 CONFIG_SOFTLOCKUP_DETECTOR=y -CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y +CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=1 CONFIG_BOOTPARAM_HUNG_TASK_PANIC=1 CONFIG_WQ_WATCHDOG=y # CONFIG_SCHED_DEBUG is not set diff --git a/arch/arm/configs/pxa3xx_defconfig b/arch/arm/configs/pxa3xx_defconfig index 07d422f..fb272e3 100644 --- a/arch/arm/configs/pxa3xx_defconfig +++ b/arch/arm/configs/pxa3xx_defconfig @@ -100,7 +100,7 @@ CONFIG_PRINTK_TIME=y CONFIG_DEBUG_KERNEL=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_SHIRQ=y -CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y +CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=1 # CONFIG_SCHED_DEBUG is not set CONFIG_DEBUG_SPINLOCK=y CONFIG_DEBUG_SPINLOCK_SLEEP=y diff --git a/arch/openrisc/configs/or1klitex_defconfig b/arch/openrisc/configs/or1klitex_defconfig index fb1eb9a..984b0e3 100644 --- a/arch/openrisc/configs/or1klitex_defconfig +++ b/arch/openrisc/configs/or1klitex_defconfig @@ -52,5 +52,5 @@ CONFIG_LSM="lockdown,yama,loadpin,safesetid,integrity,bpf" CONFIG_PRINTK_TIME=y CONFIG_PANIC_ON_OOPS=y CONFIG_SOFTLOCKUP_DETECTOR=y -CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y +CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=1 CONFIG_BUG_ON_DATA_CORRUPTION=y diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig index 2b71a6d..a4114fc 100644 --- a/arch/powerpc/configs/skiroot_defconfig +++ b/arch/powerpc/configs/skiroot_defconfig @@ -289,7 +289,7 @@ CONFIG_SCHED_STACK_END_CHECK=y CONFIG_DEBUG_STACKOVERFLOW=y CONFIG_PANIC_ON_OOPS=y CONFIG_SOFTLOCKUP_DETECTOR=y -CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y +CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=1 CONFIG_HARDLOCKUP_DETECTOR=y CONFIG_BOOTPARAM_HARDLOCKUP_PANIC=y CONFIG_WQ_WATCHDOG=y diff --git a/drivers/gpu/drm/ci/arm.config b/drivers/gpu/drm/ci/arm.config index 411e814..d7c5167 100644 --- a/drivers/gpu/drm/ci/arm.config +++ b/drivers/gpu/drm/ci/arm.config @@ -52,7 +52,7 @@ CONFIG_TMPFS=y CONFIG_PROVE_LOCKING=n CONFIG_DEBUG_LOCKDEP=n CONFIG_SOFTLOCKUP_DETECTOR=n -CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=n +CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=0 CONFIG_FW_LOADER_COMPRESS=y diff --git a/drivers/gpu/drm/ci/arm64.config b/drivers/gpu/drm/ci/arm64.config index fddfbd4..ea0e307 100644 --- a/drivers/gpu/drm/ci/arm64.config +++ b/drivers/gpu/drm/ci/arm64.config @@ -161,7 +161,7 @@ CONFIG_TMPFS=y CONFIG_PROVE_LOCKING=n CONFIG_DEBUG_LOCKDEP=n CONFIG_SOFTLOCKUP_DETECTOR=y -CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y +CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=1 CONFIG_DETECT_HUNG_TASK=y diff --git a/drivers/gpu/drm/ci/x86_64.config b/drivers/gpu/drm/ci/x86_64.config index 8eaba388..7ac98a7 100644 --- a/drivers/gpu/drm/ci/x86_64.config +++ b/drivers/gpu/drm/ci/x86_64.config @@ -47,7 +47,7 @@ CONFIG_TMPFS=y CONFIG_PROVE_LOCKING=n CONFIG_DEBUG_LOCKDEP=n CONFIG_SOFTLOCKUP_DETECTOR=y -CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y +CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=1 CONFIG_DETECT_HUNG_TASK=y diff --git a/kernel/configs/debug.config b/kernel/configs/debug.config index 9f6ab7d..774702591 100644 --- a/kernel/configs/debug.config +++ b/kernel/configs/debug.config @@ -84,7 +84,7 @@ CONFIG_SLUB_DEBUG_ON=y # Debug Oops, Lockups and Hangs # CONFIG_BOOTPARAM_HUNG_TASK_PANIC=0 -# CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC is not set +CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=0 CONFIG_DEBUG_ATOMIC_SLEEP=y CONFIG_DETECT_HUNG_TASK=y CONFIG_PANIC_ON_OOPS=y diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 0685e3a..8168e0d 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -363,7 +363,7 @@ static struct cpumask watchdog_allowed_mask __read_mostly; /* Global variables, exported for sysctl */ unsigned int __read_mostly softlockup_panic = - IS_ENABLED(CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC); + CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC; static bool softlockup_initialized __read_mostly; static u64 __read_mostly sample_period; @@ -774,8 +774,8 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) { unsigned long touch_ts, period_ts, now; struct pt_regs *regs = get_irq_regs(); - int duration; int softlockup_all_cpu_backtrace; + int duration, thresh_count; unsigned long flags; if (!watchdog_enabled) @@ -879,7 +879,9 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) add_taint(TAINT_SOFTLOCKUP, LOCKDEP_STILL_OK); sys_info(softlockup_si_mask & ~SYS_INFO_ALL_BT); - if (softlockup_panic) + thresh_count = duration / get_softlockup_thresh(); + + if (softlockup_panic && thresh_count >= softlockup_panic) panic("softlockup: hung tasks"); } @@ -1228,7 +1230,7 @@ static const struct ctl_table watchdog_sysctls[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, + .extra2 = SYSCTL_INT_MAX, }, { .procname = "softlockup_sys_info", diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index ba36939..17a7a77 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1110,13 +1110,14 @@ config SOFTLOCKUP_DETECTOR_INTR_STORM the CPU stats and the interrupt counts during the "soft lockups". config BOOTPARAM_SOFTLOCKUP_PANIC - bool "Panic (Reboot) On Soft Lockups" + int "Panic (Reboot) On Soft Lockups" depends on SOFTLOCKUP_DETECTOR + default 0 help - Say Y here to enable the kernel to panic on "soft lockups", - which are bugs that cause the kernel to loop in kernel - mode for more than 20 seconds (configurable using the watchdog_thresh - sysctl), without giving other tasks a chance to run. + Set to a non-zero value N to enable the kernel to panic on "soft + lockups", which are bugs that cause the kernel to loop in kernel + mode for more than (N * 20 seconds) (configurable using the + watchdog_thresh sysctl), without giving other tasks a chance to run. The panic can be used in combination with panic_timeout, to cause the system to reboot automatically after a @@ -1124,7 +1125,7 @@ config BOOTPARAM_SOFTLOCKUP_PANIC high-availability systems that have uptime guarantees and where a lockup must be resolved ASAP. - Say N if unsure. + Say 0 if unsure. config HAVE_HARDLOCKUP_DETECTOR_BUDDY bool diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index 558839e..2485538 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -1,6 +1,6 @@ CONFIG_BLK_DEV_LOOP=y CONFIG_BOOTPARAM_HARDLOCKUP_PANIC=y -CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y +CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=1 CONFIG_BPF=y CONFIG_BPF_EVENTS=y CONFIG_BPF_JIT=y diff --git a/tools/testing/selftests/wireguard/qemu/kernel.config b/tools/testing/selftests/wireguard/qemu/kernel.config index 0504c11..bb89d2d 100644 --- a/tools/testing/selftests/wireguard/qemu/kernel.config +++ b/tools/testing/selftests/wireguard/qemu/kernel.config @@ -80,7 +80,7 @@ CONFIG_HARDLOCKUP_DETECTOR=y CONFIG_WQ_WATCHDOG=y CONFIG_DETECT_HUNG_TASK=y CONFIG_BOOTPARAM_HARDLOCKUP_PANIC=y -CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y +CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=1 CONFIG_BOOTPARAM_HUNG_TASK_PANIC=1 CONFIG_PANIC_TIMEOUT=-1 CONFIG_STACKTRACE=y -- 2.9.4

10 hours, 4 minutes

1
0
0 0

[PATCHSET v11 sched_ext/for-6.20] Add a deadline server for sched_ext tasks

by Andrea Righi

sched_ext tasks can be starved by long-running RT tasks, especially since RT throttling was replaced by deadline servers to boost only SCHED_NORMAL tasks. Several users in the community have reported issues with RT stalling sched_ext tasks. This is fairly common on distributions or environments where applications like video compositors, audio services, etc. run as RT tasks by default. Example trace (showing a per-CPU kthread stalled due to the sway Wayland compositor running as an RT task): runnable task stall (kworker/0:0[106377] failed to run for 5.043s) ... CPU 0 : nr_run=3 flags=0xd cpu_rel=0 ops_qseq=20646200 pnt_seq=45388738 curr=sway[994] class=rt_sched_class R kworker/0:0[106377] -5043ms scx_state/flags=3/0x1 dsq_flags=0x0 ops_state/qseq=0/0 sticky/holding_cpu=-1/-1 dsq_id=0x8000000000000002 dsq_vtime=0 slice=20000000 cpus=01 This is often perceived as a bug in the BPF schedulers, but in reality they can't do much: RT tasks run outside their control and can potentially consume 100% of the CPU bandwidth. Fix this by adding a sched_ext deadline server, so that sched_ext tasks are also boosted and do not suffer starvation. Two kselftests are also provided to verify the starvation fixes and bandwidth allocation is correct. == Design == - The EXT server is initialized at boot time and remains configured throughout the system's lifetime - It starts automatically when the first sched_ext task is enqueued (rq->scx.nr_running == 1) - The server's pick function (ext_server_pick_task) always selects sched_ext tasks when active - Runtime accounting happens in update_curr_scx() during task execution and update_curr_idle() when idle - Bandwidth accounting includes both fair and ext servers in root domain calculations - A debugfs interface (/sys/kernel/debug/sched/ext_server/) allows runtime tuning of server parameters == Highlights in this version == As discussed at the sched_ext microconference at LPC Tokyo, the plan is to start with a simpler approach, avoiding automatically creating or tearing down the EXT server bandwidth reservation when a BPF scheduler is loaded or unloaded. Instead, the reservation is kept permanently active. This significantly simplifies the logic while still addressing the starvation issue. Any fine-tuning of the bandwidth reservation is delegated to the system administrator, who can adjust it via the debugfs interface. In the future, a more suitable interface can be introduced and automatic removal of the reservation when the BPF scheduler is unloaded can be revisited. This patchset is also available in the following git branch: git://git.kernel.org/pub/scm/linux/kernel/git/arighi/linux.git scx-dl-server Changes in v11: - do not create/remove the bandwidth reservation for the ext server when a BPF scheduler is loaded/unloaded, but keep the reservation bandwdith always active - change rt_stall kselftest to validate both FAIR and EXT DL servers - Link to v10: https://lore.kernel.org/all/20250903095008.162049-1-arighi@nvidia.com/ Changes in v10: - reordered patches to better isolate sched_ext changes vs sched/deadline changes (Andrea Righi) - define ext_server only with CONFIG_SCHED_CLASS_EXT=y (Andrea Righi) - add WARN_ON_ONCE(!cpus) check in dl_server_apply_params() (Andrea Righi) - wait for inactive_task_timer to fire before removing the bandwidth reservation (Juri Lelli) - remove explicit dl_server_stop() in dequeue_task_scx() to reduce timer reprogramming overhead (Juri Lelli) - do not restart pick_task() when invoked by the dl_server (Tejun Heo) - rename rq_dl_server to dl_server (Peter Zijlstra) - fixed a missing dl_server start in dl_server_on() (Christian Loehle) - add a comment to the rt_stall selftest to better explain the 4% threshold (Emil Tsalapatis) - Link to v9: https://lore.kernel.org/all/20251017093214.70029-1-arighi@nvidia.com/ Changes in v9: - Drop the ->balance() logic as its functionality is now integrated into ->pick_task(), allowing dl_server to call pick_task_scx() directly - Link to v8: https://lore.kernel.org/all/20250903095008.162049-1-arighi@nvidia.com/ Changes in v8: - Add tj's patch to de-couple balance and pick_task and avoid changing sched/core callbacks to propagate @rf - Simplify dl_se->dl_server check (suggested by PeterZ) - Small coding style fixes in the kselftests - Link to v7: https://lore.kernel.org/all/20250809184800.129831-1-joelagnelf@nvidia.com/ Changes in v7: - Rebased to Linus master - Link to v6: https://lore.kernel.org/all/20250702232944.3221001-1-joelagnelf@nvidia.com/ Changes in v6: - Added Acks to few patches - Fixes to few nits suggested by Tejun - Link to v5: https://lore.kernel.org/all/20250620203234.3349930-1-joelagnelf@nvidia.com/ Changes in v5: - Added a kselftest (total_bw) to sched_ext to verify bandwidth values from debugfs - Address comment from Andrea about redundant rq clock invalidation - Link to v4: https://lore.kernel.org/all/20250617200523.1261231-1-joelagnelf@nvidia.com/ Changes in v4: - Fixed issues with hotplugged CPUs having their DL server bandwidth altered due to loading SCX - Fixed other issues - Rebased on Linus master - All sched_ext kselftests reliably pass now, also verified that the total_bw in debugfs (CONFIG_SCHED_DEBUG) is conserved with these patches - Link to v3: https://lore.kernel.org/all/20250613051734.4023260-1-joelagnelf@nvidia.com/ Changes in v3: - Removed code duplication in debugfs. Made ext interface separate - Fixed issue where rq_lock_irqsave was not used in the relinquish patch - Fixed running bw accounting issue in dl_server_remove_params - Link to v2: https://lore.kernel.org/all/20250602180110.816225-1-joelagnelf@nvidia.com/ Changes in v2: - Fixed a hang related to using rq_lock instead of rq_lock_irqsave - Added support to remove BW of DL servers when they are switched to/from EXT - Link to v1: https://lore.kernel.org/all/20250315022158.2354454-1-joelagnelf@nvidia.com/ Andrea Righi (2): sched_ext: Add a DL server for sched_ext tasks selftests/sched_ext: Add test for sched_ext dl_server Joel Fernandes (5): sched/deadline: Clear the defer params sched/debug: Fix updating of ppos on server write ops sched/debug: Stop and start server based on if it was active sched/debug: Add support to change sched_ext server params selftests/sched_ext: Add test for DL server total_bw consistency kernel/sched/core.c | 6 + kernel/sched/deadline.c | 87 +++++-- kernel/sched/debug.c | 171 +++++++++++--- kernel/sched/ext.c | 42 ++++ kernel/sched/idle.c | 3 + kernel/sched/sched.h | 2 + kernel/sched/topology.c | 5 + tools/testing/selftests/sched_ext/Makefile | 2 + tools/testing/selftests/sched_ext/rt_stall.bpf.c | 23 ++ tools/testing/selftests/sched_ext/rt_stall.c | 240 +++++++++++++++++++ tools/testing/selftests/sched_ext/total_bw.c | 281 +++++++++++++++++++++++ 11 files changed, 811 insertions(+), 51 deletions(-) create mode 100644 tools/testing/selftests/sched_ext/rt_stall.bpf.c create mode 100644 tools/testing/selftests/sched_ext/rt_stall.c create mode 100644 tools/testing/selftests/sched_ext/total_bw.c

10 hours, 33 minutes

2
11
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror