Btrfs: fix dio write vs buffered read race

Miao pointed out there's a problem with mixing dio writes and buffered
reads.  If the read happens between us invalidating the page range and
actually locking the extent we can bring in pages into page cache.  Then
once the write finishes if somebody tries to read again it will just find
uptodate pages and we'll read stale data.  So we need to lock the extent and
check for uptodate bits in the range.  If there are uptodate bits we need to
unlock and invalidate again.  This will keep this race from happening since
we will hold the extent locked until we create the ordered extent, and then
teh read side always waits for ordered extents.  There was also a race in
how we updated i_size, previously we were relying on the generic DIO stuff
to adjust the i_size after the DIO had completed, but this happens outside
of the extent lock which means reads could come in and not see the updated
i_size.  So instead move this work into where we create the extents, and
then this way the update ordered i_size stuff works properly in the endio
handlers.  Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>

fs/btrfs/file.c

@@ -1334,7 +1334,6 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb,
 				    loff_t *ppos, size_t count, size_t ocount)
 {
 	struct file *file = iocb->ki_filp;
-	struct inode *inode = fdentry(file)->d_inode;
 	struct iov_iter i;
 	ssize_t written;
 	ssize_t written_buffered;
@@ -1344,18 +1343,6 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb,
 	written = generic_file_direct_write(iocb, iov, &nr_segs, pos, ppos,
 					    count, ocount);
 
-	/*
-	 * the generic O_DIRECT will update in-memory i_size after the
-	 * DIOs are done.  But our endio handlers that update the on
-	 * disk i_size never update past the in memory i_size.  So we
-	 * need one more update here to catch any additions to the
-	 * file
-	 */
-	if (inode->i_size != BTRFS_I(inode)->disk_i_size) {
-		btrfs_ordered_update_i_size(inode, inode->i_size, NULL);
-		mark_inode_dirty(inode);
-	}
-
 	if (written < 0 || written == count)
 		return written;
 

fs/btrfs/inode.c

@@ -5904,9 +5904,18 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 	bh_result->b_size = len;
 	bh_result->b_bdev = em->bdev;
 	set_buffer_mapped(bh_result);
-	if (create && !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
+	if (create) {
+		if (!test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
 			set_buffer_new(bh_result);
 
+		/*
+		 * Need to update the i_size under the extent lock so buffered
+		 * readers will get the updated i_size when we unlock.
+		 */
+		if (start + len > i_size_read(inode))
+			i_size_write(inode, start + len);
+	}
+
 	free_extent_map(em);
 
 	return 0;
@@ -6388,12 +6397,48 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
 		 */
 		ordered = btrfs_lookup_ordered_range(inode, lockstart,
 						     lockend - lockstart + 1);
-		if (!ordered)
+
+		/*
+		 * We need to make sure there are no buffered pages in this
+		 * range either, we could have raced between the invalidate in
+		 * generic_file_direct_write and locking the extent.  The
+		 * invalidate needs to happen so that reads after a write do not
+		 * get stale data.
+		 */
+		if (!ordered && (!writing ||
+		    !test_range_bit(&BTRFS_I(inode)->io_tree,
+				    lockstart, lockend, EXTENT_UPTODATE, 0,
+				    cached_state)))
 			break;
+
 		unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend,
 				     &cached_state, GFP_NOFS);
+
+		if (ordered) {
 			btrfs_start_ordered_extent(inode, ordered, 1);
 			btrfs_put_ordered_extent(ordered);
+		} else {
+			/* Screw you mmap */
+			ret = filemap_write_and_wait_range(file->f_mapping,
+							   lockstart,
+							   lockend);
+			if (ret)
+				goto out;
+
+			/*
+			 * If we found a page that couldn't be invalidated just
+			 * fall back to buffered.
+			 */
+			ret = invalidate_inode_pages2_range(file->f_mapping,
+					lockstart >> PAGE_CACHE_SHIFT,
+					lockend >> PAGE_CACHE_SHIFT);
+			if (ret) {
+				if (ret == -EBUSY)
+					ret = 0;
+				goto out;
+			}
+		}
+
 		cond_resched();
 	}