On Tue, 2018-07-17 at 16:15 -0700, Dave Hansen wrote:

On 07/17/2018 04:03 PM, Yu-cheng Yu wrote:

quoted

We need to find a way to differentiate "someone can write to this PTE"
from "the write bit is set in this PTE".

Please think about this:

	Should pte_write() tell us whether PTE.W=1, or should it tell us
	that *something* can write to the PTE, which would include
	PTE.W=0/D=1?

Is it better now?


Subject: [PATCH] mm: Modify can_follow_write_pte/pmd for shadow stack

can_follow_write_pte/pmd look for the (RO & DIRTY) PTE/PMD to
verify a non-sharing RO page still exists after a broken COW.

However, a shadow stack PTE is always RO & DIRTY; it can be:

  RO & DIRTY_HW - is_shstk_pte(pte) is true; or
  RO & DIRTY_SW - the page is being shared.

Update these functions to check a non-sharing shadow stack page
still exists after the COW.

Also rename can_follow_write_pte/pmd() to can_follow_write() to
make their meaning clear; i.e. "Can we write to the page?", not
"Is the PTE writable?"

Signed-off-by: Yu-cheng Yu <redacted>
---
 mm/gup.c         | 38 ++++++++++++++++++++++++++++++++++----
 mm/huge_memory.c | 19 ++++++++++++++-----
 2 files changed, 48 insertions(+), 9 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c
index fc5f98069f4e..316967996232 100644
--- a/mm/gup.c
+++ b/mm/gup.c

@@ -63,11 +63,41 @@ 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.
+ *
+ * Background:
+ *
+ * When we force-write to a read-only page, the page fault
+ * handler copies the page and sets the new page's PTE to
+ * RO & DIRTY.  This routine tells
+ *
+ *     "Can we write to the page?"
+ *
+ * by checking:
+ *
+ *     (1) The page has been copied, i.e. FOLL_COW is set;
+ *     (2) The copy still exists and its PTE is RO & DIRTY.
+ *
+ * However, a shadow stack PTE is always RO & DIRTY; it can
+ * be:
+ *
+ *     RO & DIRTY_HW: when is_shstk_pte(pte) is true; or
+ *     RO & DIRTY_SW: when the page is being shared.
+ *
+ * To test a shadow stack's non-sharing page still exists,
+ * we verify that the new page's PTE is_shstk_pte(pte).
  */
-static inline bool can_follow_write_pte(pte_t pte, unsigned int flags)
+static inline bool can_follow_write(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 (!is_shstk_mapping(vma->vm_flags)) {
+		if (pte_write(pte))
+			return true;
+		return ((flags & FOLL_FORCE) && (flags & FOLL_COW) &&
+			pte_dirty(pte));
+	} else {
+		return ((flags & FOLL_FORCE) && (flags & FOLL_COW) &&
+			is_shstk_pte(pte));
+	}
 }
 
 static struct page *follow_page_pte(struct vm_area_struct *vma,

@@ -105,7 +135,7 @@ 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, flags, vma)) {
 		pte_unmap_unlock(ptep, ptl);
 		return NULL;
 	}

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 7f3e11d3b64a..822a563678b5 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c

@@ -1388,11 +1388,20 @@ int 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.
+ * See comments in mm/gup.c, can_follow_write().
  */
-static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags)
-{
-	return pmd_write(pmd) ||
-	       ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd));
+static inline bool can_follow_write(pmd_t pmd, unsigned int flags,
+				    struct vm_area_struct *vma)
+{
+	if (!is_shstk_mapping(vma->vm_flags)) {
+		if (pmd_write(pmd))
+			return true;
+		return ((flags & FOLL_FORCE) && (flags & FOLL_COW) &&
+			pmd_dirty(pmd));
+	} else {
+		return ((flags & FOLL_FORCE) && (flags & FOLL_COW) &&
+			is_shstk_pmd(pmd));
+	}
 }
 
 struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,

@@ -1405,7 +1414,7 @@ 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, flags, vma))
 		goto out;
 
 	/* Avoid dumping huge zero page */
--