Re: [PATCH v19 18/25] mm: Update can_follow_write_pte() for shadow stack

[Kees Cook <keescook@chromium.org>]

On Wed, Feb 03, 2021 at 02:55:40PM -0800, Yu-cheng Yu wrote:
> Can_follow_write_pte() ensures a read-only page is COWed by checking the
> FOLL_COW flag, and uses pte_dirty() to validate the flag is still valid.
> 
> Like a writable data page, a shadow stack page is writable, and becomes
> read-only during copy-on-write, but it is always dirty.  Thus, in the
> can_follow_write_pte() check, it belongs to the writable page case and
> should be excluded from the read-only page pte_dirty() check.  Apply
> the same changes to can_follow_write_pmd().

Does this need the vma passed down? Should it just pass vm_flags? I
suppose it doesn't really matter, though.

Reviewed-by: Kees Cook <keescook@chromium.org>

-Kees

> 
> Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
> ---
>  mm/gup.c         | 8 +++++---
>  mm/huge_memory.c | 8 +++++---
>  2 files changed, 10 insertions(+), 6 deletions(-)
> 
> diff --git a/mm/gup.c b/mm/gup.c
> index e4c224cd9661..66ab67626f57 100644
> --- a/mm/gup.c
> +++ b/mm/gup.c
> @@ -357,10 +357,12 @@ static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address,
>   * FOLL_FORCE can write to even unwritable pte's, but only
>   * after we've gone through a COW cycle and they are dirty.
>   */
> -static inline bool can_follow_write_pte(pte_t pte, unsigned int flags)
> +static inline bool can_follow_write_pte(pte_t pte, unsigned int flags,
> +					struct vm_area_struct *vma)
>  {
>  	return pte_write(pte) ||
> -		((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte));
> +		((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte) &&
> +				  !arch_shadow_stack_mapping(vma->vm_flags));
>  }
>  
>  static struct page *follow_page_pte(struct vm_area_struct *vma,
> @@ -403,7 +405,7 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
>  	}
>  	if ((flags & FOLL_NUMA) && pte_protnone(pte))
>  		goto no_page;
> -	if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, flags)) {
> +	if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, flags, vma)) {
>  		pte_unmap_unlock(ptep, ptl);
>  		return NULL;
>  	}
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index bfec65c9308b..eb64e2b56bc9 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -1337,10 +1337,12 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)
>   * FOLL_FORCE can write to even unwritable pmd's, but only
>   * after we've gone through a COW cycle and they are dirty.
>   */
> -static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags)
> +static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags,
> +					struct vm_area_struct *vma)
>  {
>  	return pmd_write(pmd) ||
> -	       ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd));
> +	       ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd) &&
> +				  !arch_shadow_stack_mapping(vma->vm_flags));
>  }
>  
>  struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
> @@ -1353,7 +1355,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
>  
>  	assert_spin_locked(pmd_lockptr(mm, pmd));
>  
> -	if (flags & FOLL_WRITE && !can_follow_write_pmd(*pmd, flags))
> +	if (flags & FOLL_WRITE && !can_follow_write_pmd(*pmd, flags, vma))
>  		goto out;
>  
>  	/* Avoid dumping huge zero page */
> -- 
> 2.21.0
> 
> 

-- 
Kees Cook