[PATCH v27 20/31] mm: Update can_follow_write_pte() for shadow stack

From: Yu-cheng Yu
Date: Fri May 21 2021 - 18:14:10 EST


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().

While at it, also split the long line into smaller ones.

Signed-off-by: Yu-cheng Yu <yu-cheng.yu@xxxxxxxxx>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Kees Cook <keescook@xxxxxxxxxxxx>
---
v26:
- Instead of passing vm_flags, pass down vma pointer to can_follow_write_*().

v25:
- Split long line into smaller ones.

v24:
- Change arch_shadow_stack_mapping() to is_shadow_stack_mapping().

mm/gup.c | 16 ++++++++++++----
mm/huge_memory.c | 16 ++++++++++++----
2 files changed, 24 insertions(+), 8 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c
index 0697134b6a12..432ba7ccf8ae 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -438,10 +438,18 @@ 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));
+ if (pte_write(pte))
+ return true;
+ if ((flags & (FOLL_FORCE | FOLL_COW)) != (FOLL_FORCE | FOLL_COW))
+ return false;
+ if (!pte_dirty(pte))
+ return false;
+ if (is_shadow_stack_mapping(vma->vm_flags))
+ return false;
+ return true;
}

static struct page *follow_page_pte(struct vm_area_struct *vma,
@@ -484,7 +492,7 @@ 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 819f6c32eb5b..99352caf7188 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1337,10 +1337,18 @@ 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));
+ if (pmd_write(pmd))
+ return true;
+ if ((flags & (FOLL_FORCE | FOLL_COW)) != (FOLL_FORCE | FOLL_COW))
+ return false;
+ if (!pmd_dirty(pmd))
+ return false;
+ if (is_shadow_stack_mapping(vma->vm_flags))
+ return false;
+ return true;
}

struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
@@ -1353,7 +1361,7 @@ 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