mm: softdirty: enable write notifications on VMAs after VM_SOFTDIRTY cleared

For VMAs that don't want write notifications, PTEs created for read faults
have their write bit set.  If the read fault happens after VM_SOFTDIRTY is
cleared, then the PTE's softdirty bit will remain clear after subsequent
writes.

Here's a simple code snippet to demonstrate the bug:

  char* m = mmap(NULL, getpagesize(), PROT_READ | PROT_WRITE,
                 MAP_ANONYMOUS | MAP_SHARED, -1, 0);
  system("echo 4 > /proc/$PPID/clear_refs"); /* clear VM_SOFTDIRTY */
  assert(*m == '\0');     /* new PTE allows write access */
  assert(!soft_dirty(x));
  *m = 'x';               /* should dirty the page */
  assert(soft_dirty(x));  /* fails */

With this patch, write notifications are enabled when VM_SOFTDIRTY is
cleared.  Furthermore, to avoid unnecessary faults, write notifications
are disabled when VM_SOFTDIRTY is set.

As a side effect of enabling and disabling write notifications with
care, this patch fixes a bug in mprotect where vm_page_prot bits set by
drivers were zapped on mprotect.  An analogous bug was fixed in mmap by
commit c9d0bf241451 ("mm: uncached vma support with writenotify").

Signed-off-by: Peter Feiner <pfeiner@google.com>
Reported-by: Peter Feiner <pfeiner@google.com>
Suggested-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Jamie Liu <jamieliu@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 19 insertions, 0 deletions

diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 081ff8826bf6..752e30d63904 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -253,6 +253,20 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
 #define pgprot_device pgprot_noncached
 #endif
 
+#ifndef pgprot_modify
+#define pgprot_modify pgprot_modify
+static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
+{
+        if (pgprot_val(oldprot) == pgprot_val(pgprot_noncached(oldprot)))
+                newprot = pgprot_noncached(newprot);
+        if (pgprot_val(oldprot) == pgprot_val(pgprot_writecombine(oldprot)))
+                newprot = pgprot_writecombine(newprot);
+        if (pgprot_val(oldprot) == pgprot_val(pgprot_device(oldprot)))
+                newprot = pgprot_device(newprot);
+        return newprot;
+}
+#endif
+
 /*
  * When walking page tables, get the address of the next boundary,
  * or the end address of the range if that comes earlier.  Although no
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 4cd45cb95e6d..02d11ee7f19d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1974,11 +1974,16 @@ static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm,
 
 #ifdef CONFIG_MMU
 pgprot_t vm_get_page_prot(unsigned long vm_flags);
+void vma_set_page_prot(struct vm_area_struct *vma);
 #else
 static inline pgprot_t vm_get_page_prot(unsigned long vm_flags)
 {
         return __pgprot(0);
 }
+static inline void vma_set_page_prot(struct vm_area_struct *vma)
+{
+        vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
+}
 #endif
 
 #ifdef CONFIG_NUMA_BALANCING