Since multiple architectures have support for shadow stacks and we need to select support for this feature in several places in the generic code provide a generic config option that the architectures can select.

Suggested-by: David Hildenbrand david@redhat.com Acked-by: David Hildenbrand david@redhat.com Reviewed-by: Deepak Gupta debug@rivosinc.com Reviewed-by: Rick Edgecombe rick.p.edgecombe@intel.com Signed-off-by: Mark Brown broonie@kernel.org --- arch/x86/Kconfig | 1 + fs/proc/task_mmu.c | 2 +- include/linux/mm.h | 2 +- mm/Kconfig | 6 ++++++ 4 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 007bab9f2a0e..320e1f411163 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1957,6 +1957,7 @@ config X86_USER_SHADOW_STACK depends on AS_WRUSS depends on X86_64 select ARCH_USES_HIGH_VMA_FLAGS + select ARCH_HAS_USER_SHADOW_STACK select X86_CET help Shadow stack protection is a hardware feature that detects function diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 5f171ad7b436..0ea49725f524 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -984,7 +984,7 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR [ilog2(VM_UFFD_MINOR)] = "ui", #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ -#ifdef CONFIG_X86_USER_SHADOW_STACK +#ifdef CONFIG_ARCH_HAS_USER_SHADOW_STACK [ilog2(VM_SHADOW_STACK)] = "ss", #endif #ifdef CONFIG_64BIT diff --git a/include/linux/mm.h b/include/linux/mm.h index c4b238a20b76..3357625c1db3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -342,7 +342,7 @@ extern unsigned int kobjsize(const void *objp); #endif #endif /* CONFIG_ARCH_HAS_PKEYS */

-#ifdef CONFIG_X86_USER_SHADOW_STACK +#ifdef CONFIG_ARCH_HAS_USER_SHADOW_STACK /* * VM_SHADOW_STACK should not be set with VM_SHARED because of lack of * support core mm. diff --git a/mm/Kconfig b/mm/Kconfig index b72e7d040f78..3167be663bca 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -1263,6 +1263,12 @@ config IOMMU_MM_DATA config EXECMEM bool

+config ARCH_HAS_USER_SHADOW_STACK + bool + help + The architecture has hardware support for userspace shadow call + stacks (eg, x86 CET, arm64 GCS or RISC-V Zicfiss). + source "mm/damon/Kconfig"

endmenu

Unlike with the normal stack there is no API for configuring the 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 parameters to clone3() specifying the location and size of a shadow stack for the newly created process. If no shadow stack is specified then the existing implicit allocation behaviour is maintained.

If a stack is specified then it is required to have an architecture defined token placed on the stack, this will be consumed by the new task. If the token is not provided then this will be reported as a segmentation fault with si_code SEGV_CPERR, as a runtime shadow stack protection error would be. This allows architectures to implement the validation of the token in the child process context.

If the architecture does not support shadow stacks the shadow stack parameters must be zero, architectures that do support the feature are expected to enforce the same requirement on individual systems that lack shadow stack support.

Update the existing x86 implementation to pay attention to the newly added arguments, in order to maintain compatibility we use the existing behaviour if no shadow stack is specified. Minimal validation is done of the supplied parameters, detailed enforcement is left to when the thread is executed. Since we are now using more fields from the kernel_clone_args we pass that into the shadow stack code rather than individual fields.

At present this implementation does not consume the shadow stack token atomically as would be desirable, it uses a separate read and write.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/x86/include/asm/shstk.h | 11 +++-- arch/x86/kernel/process.c | 2 +- arch/x86/kernel/shstk.c | 105 ++++++++++++++++++++++++++++++++++--------- include/linux/sched/task.h | 13 ++++++ include/uapi/linux/sched.h | 13 ++++-- kernel/fork.c | 76 ++++++++++++++++++++++++++----- 6 files changed, 178 insertions(+), 42 deletions(-)

diff --git a/arch/x86/include/asm/shstk.h b/arch/x86/include/asm/shstk.h index 4cb77e004615..252feeda6999 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, unsigned long 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); @@ -28,8 +29,10 @@ 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, - unsigned long 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 f63f8fd00a91..59456ab8d93f 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -207,7 +207,7 @@ 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 059685612362..d7005974aff5 100644 --- a/arch/x86/kernel/shstk.c +++ b/arch/x86/kernel/shstk.c @@ -191,44 +191,105 @@ void reset_thread_features(void) current->thread.features_locked = 0; }

-unsigned long shstk_alloc_thread_stack(struct task_struct *tsk, unsigned long clone_flags, - unsigned long stack_size) +int arch_shstk_post_fork(struct task_struct *t, struct kernel_clone_args *args) +{ + /* + * SSP is aligned, so reserved bits and mode bit are a zero, just mark + * the token 64-bit. + */ + struct mm_struct *mm; + unsigned long addr, ssp; + u64 expected; + u64 val; + int ret = -EINVAL; + + ssp = args->shadow_stack + args->shadow_stack_size; + addr = ssp - SS_FRAME_SIZE; + expected = ssp | BIT(0); + + mm = get_task_mm(t); + if (!mm) + return -EFAULT; + + /* This should really be an atomic cmpxchg. It is not. */ + if (access_remote_vm(mm, addr, &val, sizeof(val), + FOLL_FORCE) != sizeof(val)) + goto out; + + if (val != expected) + goto out; + val = 0; + if (access_remote_vm(mm, addr, &val, sizeof(val), + FOLL_FORCE | FOLL_WRITE) != sizeof(val)) + goto out; + + ret = 0; + +out: + mmput(mm); + return ret; +} + +unsigned long shstk_alloc_thread_stack(struct task_struct *tsk, + const struct kernel_clone_args *args) { struct thread_shstk *shstk = &tsk->thread.shstk; + unsigned long 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 + * explciitly specify one. */ - if (!features_enabled(ARCH_SHSTK_SHSTK)) + if (!features_enabled(ARCH_SHSTK_SHSTK)) { + if (args->shadow_stack || args->shadow_stack_size) + return (unsigned long)ERR_PTR(-EINVAL); + return 0; + }

/* - * For CLONE_VFORK the child will share the parents shadow stack. - * Make sure to clear the internal tracking of the thread shadow - * stack so the freeing logic run for child knows to leave it alone. + * If the user specified a shadow stack then do some basic + * validation and use it, otherwise fall back to a default + * shadow stack size if the clone_flags don't indicate an + * allocation is unneeded. */ - if (clone_flags & CLONE_VFORK) { + if (args->shadow_stack) { + addr = args->shadow_stack; + size = args->shadow_stack_size; shstk->base = 0; shstk->size = 0; - return 0; - } + } else { + /* + * For CLONE_VFORK the child will share the parents + * shadow stack. Make sure to clear the internal + * tracking of the thread shadow stack so the freeing + * logic run for child knows to leave it alone. + */ + if (clone_flags & CLONE_VFORK) { + shstk->base = 0; + shstk->size = 0; + return 0; + }

- /* - * For !CLONE_VM the child will use a copy of the parents shadow - * stack. - */ - if (!(clone_flags & CLONE_VM)) - return 0; + /* + * For !CLONE_VM the child will use a copy of the + * parents shadow stack. + */ + if (!(clone_flags & CLONE_VM)) + return 0;

- size = adjust_shstk_size(stack_size); - addr = alloc_shstk(0, size, 0, false); - if (IS_ERR_VALUE(addr)) - return addr; + size = args->stack_size; + size = adjust_shstk_size(size); + addr = alloc_shstk(0, size, 0, false); + if (IS_ERR_VALUE(addr)) + return addr;

- shstk->base = addr; - shstk->size = size; + /* We allocated the shadow stack, we should deallocate it. */ + shstk->base = addr; + shstk->size = size; + }

return addr + size; } diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index d362aacf9f89..56b2013d7fe5 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -43,6 +43,8 @@ struct kernel_clone_args { void *fn_arg; struct cgroup *cgrp; struct css_set *cset; + unsigned long shadow_stack; + unsigned long shadow_stack_size; };

/* @@ -230,4 +232,15 @@ 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_post_fork(struct task_struct *p, + struct kernel_clone_args *args); +#else +static inline int arch_shstk_post_fork(struct task_struct *p, + 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 3bac0a8ceab2..8b7af52548fd 100644 --- a/include/uapi/linux/sched.h +++ b/include/uapi/linux/sched.h @@ -84,6 +84,10 @@ * kernel's limit of nested PID namespaces. * @cgroup: If CLONE_INTO_CGROUP is specified set this to * a file descriptor for the cgroup. + * @shadow_stack: Pointer to the memory allocated for the child + * shadow stack. + * @shadow_stack_size: Specify the size of the shadow stack for + * the child process. * * The structure is versioned by size and thus extensible. * New struct members must go at the end of the struct and @@ -101,12 +105,15 @@ struct clone_args { __aligned_u64 set_tid; __aligned_u64 set_tid_size; __aligned_u64 cgroup; + __aligned_u64 shadow_stack; + __aligned_u64 shadow_stack_size; }; #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 104 /* sizeof fourth published struct */

/* * Scheduling policies diff --git a/kernel/fork.c b/kernel/fork.c index cc760491f201..18278c72681c 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -128,6 +128,11 @@ */ #define MAX_THREADS FUTEX_TID_MASK

+/* + * Require that shadow stacks can store at least one element + */ +#define SHADOW_STACK_SIZE_MIN sizeof(void *) + /* * Protected counters by write_lock_irq(&tasklist_lock) */ @@ -2729,6 +2734,19 @@ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node) return copy_process(NULL, 0, node, &args); }

+static void shstk_post_fork(struct task_struct *p, + struct kernel_clone_args *args) +{ + if (!IS_ENABLED(CONFIG_ARCH_HAS_USER_SHADOW_STACK)) + return; + + if (!args->shadow_stack) + return; + + if (arch_shstk_post_fork(p, args) != 0) + force_sig_fault_to_task(SIGSEGV, SEGV_CPERR, NULL, p); +} + /* * Ok, this is the main fork-routine. * @@ -2790,6 +2808,8 @@ pid_t kernel_clone(struct kernel_clone_args *args) */ trace_sched_process_fork(current, p);

+ shstk_post_fork(p, args); + pid = get_task_pid(p, PIDTYPE_PID); nr = pid_vnr(pid);

@@ -2939,7 +2959,9 @@ noinline static 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, shadow_stack_size) != + CLONE_ARGS_SIZE_VER3); + BUILD_BUG_ON(sizeof(struct clone_args) != CLONE_ARGS_SIZE_VER3);

if (unlikely(usize > PAGE_SIZE)) return -E2BIG; @@ -2972,16 +2994,18 @@ noinline static 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, + .shadow_stack = args.shadow_stack, + .shadow_stack_size = args.shadow_stack_size, };

if (args.set_tid && @@ -3022,6 +3046,34 @@ 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->shadow_stack) { + if (!kargs->shadow_stack_size) + return false; + + if (kargs->shadow_stack_size < SHADOW_STACK_SIZE_MIN) + return false; + + if (kargs->shadow_stack_size > rlimit(RLIMIT_STACK)) + return false; + + /* + * The architecture must check support on the specific + * machine. + */ + return IS_ENABLED(CONFIG_ARCH_HAS_USER_SHADOW_STACK); + } else { + return !kargs->shadow_stack_size; + } +} + static bool clone3_args_valid(struct kernel_clone_args *kargs) { /* Verify that no unknown flags are passed along. */ @@ -3044,7 +3096,7 @@ 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;

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.

Signed-off-by: Mark Brown broonie@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 e61f07973ce5..e066b201fa64 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(); }

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.

Signed-off-by: Mark Brown broonie@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 3b3a08e6a34d..26221661e9ae 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; }; @@ -153,6 +154,11 @@ 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);