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;