There are a number of architectures with shadow stack features which we are presenting to userspace with as consistent an API as we can (though there are some architecture specifics). Especially given that there are some important considerations for userspace code interacting directly with the feature let's provide some documentation covering the common aspects.

Reviewed-by: Catalin Marinas catalin.marinas@arm.com Reviewed-by: Kees Cook kees@kernel.org Tested-by: Kees Cook kees@kernel.org Acked-by: Shuah Khan skhan@linuxfoundation.org Signed-off-by: Mark Brown broonie@kernel.org --- Documentation/userspace-api/index.rst | 1 + Documentation/userspace-api/shadow_stack.rst | 41 ++++++++++++++++++++++++++++ 2 files changed, 42 insertions(+)

diff --git a/Documentation/userspace-api/index.rst b/Documentation/userspace-api/index.rst index 274cc7546efc..c39709bfba2c 100644 --- a/Documentation/userspace-api/index.rst +++ b/Documentation/userspace-api/index.rst @@ -59,6 +59,7 @@ Everything else

ELF netlink/index + shadow_stack sysfs-platform_profile vduse futex2 diff --git a/Documentation/userspace-api/shadow_stack.rst b/Documentation/userspace-api/shadow_stack.rst new file mode 100644 index 000000000000..c576ad3d7ec1 --- /dev/null +++ b/Documentation/userspace-api/shadow_stack.rst @@ -0,0 +1,41 @@ +============= +Shadow Stacks +============= + +Introduction +============ + +Several architectures have features which provide backward edge +control flow protection through a hardware maintained stack, only +writeable by userspace through very limited operations. This feature +is referred to as shadow stacks on Linux, on x86 it is part of Intel +Control Enforcement Technology (CET), on arm64 it is Guarded Control +Stacks feature (FEAT_GCS) and for RISC-V it is the Zicfiss extension. +It is expected that this feature will normally be managed by the +system dynamic linker and libc in ways broadly transparent to +application code, this document covers interfaces and considerations. + + +Enabling +======== + +Shadow stacks default to disabled when a userspace process is +executed, they can be enabled for the current thread with a syscall: + + - For x86 the ARCH_SHSTK_ENABLE arch_prctl() + +It is expected that this will normally be done by the dynamic linker. +Any new threads created by a thread with shadow stacks enabled will +themselves have shadow stacks enabled. + + +Enablement considerations +========================= + +- Returning from the function that enables shadow stacks without first + disabling them will cause a shadow stack exception. This includes + any syscall wrapper or other library functions, the syscall will need + to be inlined. +- A lock feature allows userspace to prevent disabling of shadow stacks. +- Those that change the stack context like longjmp() or use of ucontext + changes on signal return will need support from libc.

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 | 103 +++++++++++++++++++++++++++++--------- include/linux/sched/task.h | 18 +++++++ include/uapi/linux/sched.h | 13 +++-- kernel/fork.c | 114 ++++++++++++++++++++++++++++++++++++++----- 6 files changed, 219 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..42b2b18de20d 100644 --- a/arch/x86/kernel/shstk.c +++ b/arch/x86/kernel/shstk.c @@ -191,44 +191,103 @@ 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_validate_clone(struct task_struct *t, + struct vm_area_struct *vma, + struct page *page, + struct kernel_clone_args *args) +{ + /* + * SSP is aligned, so reserved bits and mode bit are a zero, just mark + * the token 64-bit. + */ + void *maddr = kmap_local_page(page); + int offset; + unsigned long addr, ssp; + u64 expected; + u64 val; + + if (!features_enabled(ARCH_SHSTK_SHSTK)) + return 0; + + ssp = args->shadow_stack + args->shadow_stack_size; + addr = ssp - SS_FRAME_SIZE; + expected = ssp | BIT(0); + offset = offset_in_page(ssp); + + /* This should really be an atomic cmpxchg. It is not. */ + copy_from_user_page(vma, page, addr, &val, maddr + offset, + sizeof(val)); + + if (val != expected) + return false; + val = 0; + + copy_to_user_page(vma, page, addr, maddr + offset, &val, sizeof(val)); + 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; + 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 + * explicitly 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..c818efdd57af 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 @@ -43,6 +44,8 @@ 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 +233,19 @@ 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 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..275d8cf3f66b 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) */ @@ -2107,6 +2112,56 @@ static void rv_task_fork(struct task_struct *p) #define rv_task_fork(p) do {} while (0) #endif

+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->shadow_stack) + return 0; + + mm = get_task_mm(p); + if (!mm) + return -EFAULT; + + mmap_read_lock(mm); + + /* + * All current shadow stack architectures have tokens at the + * top of a downward growing shadow stack. + */ + addr = args->shadow_stack + args->shadow_stack_size - 1; + addr = untagged_addr_remote(mm, addr); + + 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)) { + 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. @@ -2381,6 +2436,9 @@ __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;

@@ -2939,7 +2997,9 @@ 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 +3032,18 @@ 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 +3084,34 @@ 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 +3134,7 @@ 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.

Reviewed-by: Kees Cook kees@kernel.org Tested-by: Kees Cook kees@kernel.org Acked-by: Shuah Khan skhan@linuxfoundation.org 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(); }

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@linuxfoundation.org Signed-off-by: Mark Brown broonie@kernel.org --- tools/testing/selftests/clone3/clone3.c | 147 +++++++++++++++++++++- tools/testing/selftests/clone3/clone3_selftests.h | 38 ++++++ 2 files changed, 184 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/clone3/clone3.c b/tools/testing/selftests/clone3/clone3.c index 5b8b7d640e70..f64fe5cd701d 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 +34,11 @@ 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_NO_SIZE, + CLONE3_ARGS_SHADOW_STACK_NO_POINTER, + CLONE3_ARGS_SHADOW_STACK_NO_TOKEN, + CLONE3_ARGS_SHADOW_STACK_NORMAL_MEMORY, };

typedef bool (*filter_function)(void); @@ -44,6 +55,44 @@ 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 unsigned long long 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 page; +} + static int call_clone3(uint64_t flags, size_t size, enum test_mode test_mode) { struct __clone_args args = { @@ -89,6 +138,24 @@ 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: + args.shadow_stack = get_shadow_stack_page(SHADOW_STACK_SET_TOKEN); + args.shadow_stack_size = getpagesize(); + break; + case CLONE3_ARGS_SHADOW_STACK_NO_POINTER: + args.shadow_stack_size = getpagesize(); + break; + case CLONE3_ARGS_SHADOW_STACK_NO_SIZE: + args.shadow_stack = get_shadow_stack_page(SHADOW_STACK_SET_TOKEN); + break; + case CLONE3_ARGS_SHADOW_STACK_NORMAL_MEMORY: + args.shadow_stack = (unsigned long long)malloc(getpagesize()); + args.shadow_stack_size = getpagesize(); + break; + case CLONE3_ARGS_SHADOW_STACK_NO_TOKEN: + args.shadow_stack = get_shadow_stack_page(0); + args.shadow_stack_size = getpagesize(); + break; }

memcpy(&args_ext.args, &args, sizeof(struct __clone_args)); @@ -102,7 +169,12 @@ 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 +256,26 @@ 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 +419,56 @@ 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 no pointer", + .size = 0, + .expected = -EINVAL, + .e2big_valid = true, + .test_mode = CLONE3_ARGS_SHADOW_STACK_NO_POINTER, + }, + { + .name = "Shadow stack with no size", + .size = 0, + .expected = -EINVAL, + .e2big_valid = true, + .test_mode = CLONE3_ARGS_SHADOW_STACK_NO_SIZE, + .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 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 on system without shadow stack", + .flags = CLONE_VM, + .size = 0, + .expected = -EINVAL, + .e2big_valid = true, + .test_mode = CLONE3_ARGS_SHADOW_STACK, + .filter = have_shadow_stack, + }, };

int main(int argc, char *argv[]) @@ -334,9 +476,12 @@ 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 39b5dcba663c..38d82934668a 100644 --- a/tools/testing/selftests/clone3/clone3_selftests.h +++ b/tools/testing/selftests/clone3/clone3_selftests.h @@ -31,12 +31,50 @@ 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 shadow_stack; + __aligned_u64 shadow_stack_size; +#ifndef CLONE_ARGS_SIZE_VER3 +#define CLONE_ARGS_SIZE_VER3 104 /* 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 pid_t __always_inline sys_clone3(struct __clone_args *args, size_t size) +{ + long ret; + register long _num __asm__ ("rax") = __NR_clone3; + register long _args __asm__ ("rdi") = (long)(args); + register long _size __asm__ ("rsi") = (long)(size); + + __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; +} +#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) {