Re: [PATCH v23 17/28] mm: Add guard pages around a shadow stack.

[Kirill A. Shutemov]

On Tue, Mar 16, 2021 at 08:10:43AM -0700, Yu-cheng Yu wrote:
> INCSSP(Q/D) increments shadow stack pointer and 'pops and discards' the
> first and the last elements in the range, effectively touches those memory
> areas.
> 
> The maximum moving distance by INCSSPQ is 255 * 8 = 2040 bytes and
> 255 * 4 = 1020 bytes by INCSSPD.  Both ranges are far from PAGE_SIZE.
> Thus, putting a gap page on both ends of a shadow stack prevents INCSSP,
> CALL, and RET from going beyond.
> 
> Signed-off-by: Yu-cheng Yu <yu-cheng.yu@xxxxxxxxx>
> Reviewed-by: Kees Cook <keescook@xxxxxxxxxxxx>
> ---
>  arch/x86/include/asm/page_64_types.h | 10 ++++++++++
>  include/linux/mm.h                   | 24 ++++++++++++++++++++----
>  2 files changed, 30 insertions(+), 4 deletions(-)
> 
> diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
> index 64297eabad63..23e3d880ce6c 100644
> --- a/arch/x86/include/asm/page_64_types.h
> +++ b/arch/x86/include/asm/page_64_types.h
> @@ -115,4 +115,14 @@
>  #define KERNEL_IMAGE_SIZE	(512 * 1024 * 1024)
>  #endif
>  
> +/*
> + * Shadow stack pointer is moved by CALL, RET, and INCSSP(Q/D).  INCSSPQ
> + * moves shadow stack pointer up to 255 * 8 = ~2 KB (~1KB for INCSSPD) and
> + * touches the first and the last element in the range, which triggers a
> + * page fault if the range is not in a shadow stack.  Because of this,
> + * creating 4-KB guard pages around a shadow stack prevents these
> + * instructions from going beyond.
> + */
> +#define ARCH_SHADOW_STACK_GUARD_GAP PAGE_SIZE
> +
>  #endif /* _ASM_X86_PAGE_64_DEFS_H */
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index af805ffde48e..9890e9f5a5e0 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -2619,6 +2619,10 @@ extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf);
>  int __must_check write_one_page(struct page *page);
>  void task_dirty_inc(struct task_struct *tsk);
>  
> +#ifndef ARCH_SHADOW_STACK_GUARD_GAP
> +#define ARCH_SHADOW_STACK_GUARD_GAP 0
> +#endif
> +
>  extern unsigned long stack_guard_gap;
>  /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */
>  extern int expand_stack(struct vm_area_struct *vma, unsigned long address);
> @@ -2651,9 +2655,15 @@ static inline struct vm_area_struct * find_vma_intersection(struct mm_struct * m
>  static inline unsigned long vm_start_gap(struct vm_area_struct *vma)
>  {
>  	unsigned long vm_start = vma->vm_start;
> +	unsigned long gap = 0;
>  
> -	if (vma->vm_flags & VM_GROWSDOWN) {
> -		vm_start -= stack_guard_gap;
> +	if (vma->vm_flags & VM_GROWSDOWN)
> +		gap = stack_guard_gap;
> +	else if (vma->vm_flags & VM_SHSTK)
> +		gap = ARCH_SHADOW_STACK_GUARD_GAP;

Looks too x86-centric for generic code.

Maybe we can have a helper that would return gap for the given VMA?
The generic version of the helper would only return stack_guard_gap for
VM_GROWSDOWN. Arch code would override it to handle VM_SHSTK case too.

Similar can be done in vm_end_gap().

> +
> +	if (gap != 0) {
> +		vm_start -= gap;
>  		if (vm_start > vma->vm_start)
>  			vm_start = 0;
>  	}
> @@ -2663,9 +2673,15 @@ static inline unsigned long vm_start_gap(struct vm_area_struct *vma)
>  static inline unsigned long vm_end_gap(struct vm_area_struct *vma)
>  {
>  	unsigned long vm_end = vma->vm_end;
> +	unsigned long gap = 0;
> +
> +	if (vma->vm_flags & VM_GROWSUP)
> +		gap = stack_guard_gap;
> +	else if (vma->vm_flags & VM_SHSTK)
> +		gap = ARCH_SHADOW_STACK_GUARD_GAP;
>  
> -	if (vma->vm_flags & VM_GROWSUP) {
> -		vm_end += stack_guard_gap;
> +	if (gap != 0) {
> +		vm_end += gap;
>  		if (vm_end < vma->vm_end)
>  			vm_end = -PAGE_SIZE;
>  	}
> -- 
> 2.21.0
> 

-- 
 Kirill A. Shutemov