diff options
| -rw-r--r-- | arch/x86/include/asm/fpu/sched.h | 3 | ||||
| -rw-r--r-- | arch/x86/include/asm/mmu_context.h | 2 | ||||
| -rw-r--r-- | arch/x86/include/asm/shstk.h | 5 | ||||
| -rw-r--r-- | arch/x86/kernel/fpu/core.c | 36 | ||||
| -rw-r--r-- | arch/x86/kernel/process.c | 21 | ||||
| -rw-r--r-- | arch/x86/kernel/shstk.c | 41 |
6 files changed, 103 insertions, 5 deletions
diff --git a/arch/x86/include/asm/fpu/sched.h b/arch/x86/include/asm/fpu/sched.h index 78fcde7b1f07..ca6e5e5f16b2 100644 --- a/arch/x86/include/asm/fpu/sched.h +++ b/arch/x86/include/asm/fpu/sched.h @@ -11,7 +11,8 @@ extern void save_fpregs_to_fpstate(struct fpu *fpu); extern void fpu__drop(struct fpu *fpu); -extern int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal); +extern int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal, + unsigned long shstk_addr); extern void fpu_flush_thread(void); /* diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 1d29dc791f5a..416901d406f8 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -186,6 +186,8 @@ do { \ #else #define deactivate_mm(tsk, mm) \ do { \ + if (!tsk->vfork_done) \ + shstk_free(tsk); \ load_gs_index(0); \ loadsegment(fs, 0); \ } while (0) diff --git a/arch/x86/include/asm/shstk.h b/arch/x86/include/asm/shstk.h index 2b1f7c9b9995..d4a5c7b10cb5 100644 --- a/arch/x86/include/asm/shstk.h +++ b/arch/x86/include/asm/shstk.h @@ -15,11 +15,16 @@ struct thread_shstk { long shstk_prctl(struct task_struct *task, int option, unsigned long features); void reset_thread_features(void); +unsigned long shstk_alloc_thread_stack(struct task_struct *p, unsigned long clone_flags, + unsigned long stack_size); void shstk_free(struct task_struct *p); #else 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; } static inline void shstk_free(struct task_struct *p) {} #endif /* CONFIG_X86_USER_SHADOW_STACK */ diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 375852cf8fac..e03b6b107b20 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -552,8 +552,36 @@ static inline void fpu_inherit_perms(struct fpu *dst_fpu) } } +/* A passed ssp of zero will not cause any update */ +static int update_fpu_shstk(struct task_struct *dst, unsigned long ssp) +{ +#ifdef CONFIG_X86_USER_SHADOW_STACK + struct cet_user_state *xstate; + + /* If ssp update is not needed. */ + if (!ssp) + return 0; + + xstate = get_xsave_addr(&dst->thread.fpu.fpstate->regs.xsave, + XFEATURE_CET_USER); + + /* + * If there is a non-zero ssp, then 'dst' must be configured with a shadow + * stack and the fpu state should be up to date since it was just copied + * from the parent in fpu_clone(). So there must be a valid non-init CET + * state location in the buffer. + */ + if (WARN_ON_ONCE(!xstate)) + return 1; + + xstate->user_ssp = (u64)ssp; +#endif + return 0; +} + /* Clone current's FPU state on fork */ -int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal) +int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal, + unsigned long ssp) { struct fpu *src_fpu = ¤t->thread.fpu; struct fpu *dst_fpu = &dst->thread.fpu; @@ -613,6 +641,12 @@ int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal) if (use_xsave()) dst_fpu->fpstate->regs.xsave.header.xfeatures &= ~XFEATURE_MASK_PASID; + /* + * Update shadow stack pointer, in case it changed during clone. + */ + if (update_fpu_shstk(dst, ssp)) + return 1; + trace_x86_fpu_copy_src(src_fpu); trace_x86_fpu_copy_dst(dst_fpu); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index ff9b80a0e3e3..cc7a642f8c9d 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -50,6 +50,7 @@ #include <asm/unwind.h> #include <asm/tdx.h> #include <asm/mmu_context.h> +#include <asm/shstk.h> #include "process.h" @@ -121,6 +122,7 @@ void exit_thread(struct task_struct *tsk) free_vm86(t); + shstk_free(tsk); fpu__drop(fpu); } @@ -142,6 +144,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) struct inactive_task_frame *frame; struct fork_frame *fork_frame; struct pt_regs *childregs; + unsigned long new_ssp; int ret = 0; childregs = task_pt_regs(p); @@ -179,7 +182,16 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) frame->flags = X86_EFLAGS_FIXED; #endif - fpu_clone(p, clone_flags, args->fn); + /* + * Allocate a new shadow stack for thread if needed. If shadow stack, + * 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); + if (IS_ERR_VALUE(new_ssp)) + return PTR_ERR((void *)new_ssp); + + fpu_clone(p, clone_flags, args->fn, new_ssp); /* Kernel thread ? */ if (unlikely(p->flags & PF_KTHREAD)) { @@ -225,6 +237,13 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) if (!ret && unlikely(test_tsk_thread_flag(current, TIF_IO_BITMAP))) io_bitmap_share(p); + /* + * If copy_thread() if failing, don't leak the shadow stack possibly + * allocated in shstk_alloc_thread_stack() above. + */ + if (ret) + shstk_free(p); + return ret; } diff --git a/arch/x86/kernel/shstk.c b/arch/x86/kernel/shstk.c index 3cb85224d856..bd9cdc3a7338 100644 --- a/arch/x86/kernel/shstk.c +++ b/arch/x86/kernel/shstk.c @@ -47,7 +47,7 @@ static unsigned long alloc_shstk(unsigned long size) unsigned long addr, unused; mmap_write_lock(mm); - addr = do_mmap(NULL, addr, size, PROT_READ, flags, + addr = do_mmap(NULL, 0, size, PROT_READ, flags, VM_SHADOW_STACK | VM_WRITE, 0, &unused, NULL); mmap_write_unlock(mm); @@ -126,6 +126,37 @@ 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) +{ + struct thread_shstk *shstk = &tsk->thread.shstk; + unsigned long addr, size; + + /* + * If shadow stack is not enabled on the new thread, skip any + * switch to a new shadow stack. + */ + if (!features_enabled(ARCH_SHSTK_SHSTK)) + return 0; + + /* + * For CLONE_VM, except vfork, the child needs a separate shadow + * stack. + */ + if ((clone_flags & (CLONE_VFORK | CLONE_VM)) != CLONE_VM) + return 0; + + size = adjust_shstk_size(stack_size); + addr = alloc_shstk(size); + if (IS_ERR_VALUE(addr)) + return addr; + + shstk->base = addr; + shstk->size = size; + + return addr + size; +} + void shstk_free(struct task_struct *tsk) { struct thread_shstk *shstk = &tsk->thread.shstk; @@ -134,7 +165,13 @@ void shstk_free(struct task_struct *tsk) !features_enabled(ARCH_SHSTK_SHSTK)) return; - if (!tsk->mm) + /* + * When fork() with CLONE_VM fails, the child (tsk) already has a + * shadow stack allocated, and exit_thread() calls this function to + * free it. In this case the parent (current) and the child share + * the same mm struct. + */ + if (!tsk->mm || tsk->mm != current->mm) return; unmap_shadow_stack(shstk->base, shstk->size); |