mm: close page_mkwrite races

commit b827e496c893de0c0f142abfaeb8730a2fd6b37f upstream

mm: close page_mkwrite races

Change page_mkwrite to allow implementations to return with the page
locked, and also change it's callers (in page fault paths) to hold the
lock until the page is marked dirty.  This allows the filesystem to have
full control of page dirtying events coming from the VM.

Rather than simply hold the page locked over the page_mkwrite call, we
call page_mkwrite with the page unlocked and allow callers to return with
it locked, so filesystems can avoid LOR conditions with page lock.

The problem with the current scheme is this: a filesystem that wants to
associate some metadata with a page as long as the page is dirty, will
perform this manipulation in its ->page_mkwrite.  It currently then must
return with the page unlocked and may not hold any other locks (according
to existing page_mkwrite convention).

In this window, the VM could write out the page, clearing page-dirty.  The
filesystem has no good way to detect that a dirty pte is about to be
attached, so it will happily write out the page, at which point, the
filesystem may manipulate the metadata to reflect that the page is no
longer dirty.

It is not always possible to perform the required metadata manipulation in
->set_page_dirty, because that function cannot block or fail.  The
filesystem may need to allocate some data structure, for example.

And the VM cannot mark the pte dirty before page_mkwrite, because
page_mkwrite is allowed to fail, so we must not allow any window where the
page could be written to if page_mkwrite does fail.

This solution of holding the page locked over the 3 critical operations
(page_mkwrite, setting the pte dirty, and finally setting the page dirty)
closes out races nicely, preventing page cleaning for writeout being
initiated in that window.  This provides the filesystem with a strong
synchronisation against the VM here.

- Sage needs this race closed for ceph filesystem.
- Trond for NFS (http://bugzilla.kernel.org/show_bug.cgi?id=12913).
- I need it for fsblock.
- I suspect other filesystems may need it too (eg. btrfs).
- I have converted buffer.c to the new locking. Even simple block allocation
  under dirty pages might be susceptible to i_size changing under partial page
  at the end of file (we also have a buffer.c-side problem here, but it cannot
  be fixed properly without this patch).
- Other filesystems (eg. NFS, maybe btrfs) will need to change their
  page_mkwrite functions themselves.

[ This also moves page_mkwrite another step closer to fault, which should
  eventually allow page_mkwrite to be moved into ->fault, and thus avoiding a
  filesystem calldown and page lock/unlock cycle in __do_fault. ]

[akpm@linux-foundation.org: fix derefs of NULL ->mapping]
Cc: Sage Weil <sage@newdream.net>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Signed-off-by: Nick Piggin <npiggin@suse.de>
Cc: Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

1 files changed, 76 insertions, 32 deletions

diff --git a/mm/memory.c b/mm/memory.c
index f34850e3e2c4..3856c3681fcf 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1827,6 +1827,15 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 				ret = tmp;
 				goto unwritable_page;
 			}
+			if (unlikely(!(tmp & VM_FAULT_LOCKED))) {
+				lock_page(old_page);
+				if (!old_page->mapping) {
+					ret = 0; /* retry the fault */
+					unlock_page(old_page);
+					goto unwritable_page;
+				}
+			} else
+				VM_BUG_ON(!PageLocked(old_page));
 
 			/*
 			 * Since we dropped the lock we need to revalidate
@@ -1836,9 +1845,11 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			 */
 			page_table = pte_offset_map_lock(mm, pmd, address,
 							 &ptl);
-			page_cache_release(old_page);
-			if (!pte_same(*page_table, orig_pte))
+			if (!pte_same(*page_table, orig_pte)) {
+				unlock_page(old_page);
+				page_cache_release(old_page);
 				goto unlock;
+			}
 
 			page_mkwrite = 1;
 		}
@@ -1943,9 +1954,6 @@ gotten:
 unlock:
 	pte_unmap_unlock(page_table, ptl);
 	if (dirty_page) {
-		if (vma->vm_file)
-			file_update_time(vma->vm_file);
-
 		/*
 		 * Yes, Virginia, this is actually required to prevent a race
 		 * with clear_page_dirty_for_io() from clearing the page dirty
@@ -1954,16 +1962,41 @@ unlock:
 		 *
 		 * do_no_page is protected similarly.
 		 */
-		wait_on_page_locked(dirty_page);
-		set_page_dirty_balance(dirty_page, page_mkwrite);
+		if (!page_mkwrite) {
+			wait_on_page_locked(dirty_page);
+			set_page_dirty_balance(dirty_page, page_mkwrite);
+		}
 		put_page(dirty_page);
+		if (page_mkwrite) {
+			struct address_space *mapping = dirty_page->mapping;
+
+			set_page_dirty(dirty_page);
+			unlock_page(dirty_page);
+			page_cache_release(dirty_page);
+			if (mapping)	{
+				/*
+				 * Some device drivers do not set page.mapping
+				 * but still dirty their pages
+				 */
+				balance_dirty_pages_ratelimited(mapping);
+			}
+		}
+
+		/* file_update_time outside page_lock */
+		if (vma->vm_file)
+			file_update_time(vma->vm_file);
 	}
 	return ret;
 oom_free_new:
 	page_cache_release(new_page);
 oom:
-	if (old_page)
+	if (old_page) {
+		if (page_mkwrite) {
+			unlock_page(old_page);
+			page_cache_release(old_page);
+		}
 		page_cache_release(old_page);
+	}
 	return VM_FAULT_OOM;
 
 unwritable_page:
@@ -2488,27 +2521,22 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 				int tmp;
 
 				unlock_page(page);
-				vmf.flags |= FAULT_FLAG_MKWRITE;
+				vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE;
 				tmp = vma->vm_ops->page_mkwrite(vma, &vmf);
 				if (unlikely(tmp &
 					  (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) {
 					ret = tmp;
-					anon = 1; /* no anon but release vmf.page */
-					goto out_unlocked;
-				}
-				lock_page(page);
-				/*
-				 * XXX: this is not quite right (racy vs
-				 * invalidate) to unlock and relock the page
-				 * like this, however a better fix requires
-				 * reworking page_mkwrite locking API, which
-				 * is better done later.
-				 */
-				if (!page->mapping) {
-					ret = 0;
-					anon = 1; /* no anon but release vmf.page */
-					goto out;
+					goto unwritable_page;
 				}
+				if (unlikely(!(tmp & VM_FAULT_LOCKED))) {
+					lock_page(page);
+					if (!page->mapping) {
+						ret = 0; /* retry the fault */
+						unlock_page(page);
+						goto unwritable_page;
+					}
+				} else
+					VM_BUG_ON(!PageLocked(page));
 				page_mkwrite = 1;
 			}
 		}
@@ -2565,19 +2593,35 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	pte_unmap_unlock(page_table, ptl);
 
 out:
-	unlock_page(vmf.page);
-out_unlocked:
-	if (anon)
-		page_cache_release(vmf.page);
-	else if (dirty_page) {
-		if (vma->vm_file)
-			file_update_time(vma->vm_file);
+	if (dirty_page) {
+		struct address_space *mapping = page->mapping;
 
-		set_page_dirty_balance(dirty_page, page_mkwrite);
+		if (set_page_dirty(dirty_page))
+			page_mkwrite = 1;
+		unlock_page(dirty_page);
 		put_page(dirty_page);
+		if (page_mkwrite && mapping) {
+			/*
+			 * Some device drivers do not set page.mapping but still
+			 * dirty their pages
+			 */
+			balance_dirty_pages_ratelimited(mapping);
+		}
+
+		/* file_update_time outside page_lock */
+		if (vma->vm_file)
+			file_update_time(vma->vm_file);
+	} else {
+		unlock_page(vmf.page);
+		if (anon)
+			page_cache_release(vmf.page);
 	}
 
 	return ret;
+
+unwritable_page:
+	page_cache_release(page);
+	return ret;
 }
 
 static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma,