Merge v7.1.4linux-rolling-stable

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 56 insertions, 4 deletions

diff --git a/fs/btrfs/direct-io.c b/fs/btrfs/direct-io.c
index 57167d56dc72..412309825d6f 100644
--- a/fs/btrfs/direct-io.c
+++ b/fs/btrfs/direct-io.c
@@ -15,10 +15,12 @@
 
 struct btrfs_dio_data {
 	ssize_t submitted;
+	loff_t old_isize;
 	struct extent_changeset *data_reserved;
 	struct btrfs_ordered_extent *ordered;
 	bool data_space_reserved;
 	bool nocow_done;
+	bool updated_isize;
 };
 
 struct btrfs_dio_private {
@@ -228,6 +230,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map,
 	bool space_reserved = false;
 	u64 len = *lenp;
 	u64 prev_len;
+	loff_t old_isize;
 	int ret = 0;
 
 	/*
@@ -341,8 +344,14 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map,
 	 * 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))
+	old_isize = i_size_read(inode);
+	if (start + len > old_isize) {
+		if (!dio_data->updated_isize) {
+			dio_data->old_isize = old_isize;
+			dio_data->updated_isize = true;
+		}
 		i_size_write(inode, start + len);
+	}
 out:
 	if (ret && space_reserved) {
 		btrfs_delalloc_release_extents(BTRFS_I(inode), len);
@@ -624,12 +633,55 @@ static int btrfs_dio_iomap_end(struct inode *inode, loff_t pos, loff_t length,
 	if (submitted < length) {
 		pos += submitted;
 		length -= submitted;
-		if (write)
+		if (write) {
+			/*
+			 * Got a short write and have updated the isize, need to
+			 * revert the isize change.
+			 *
+			 * Normally we need to update isize with extent lock hold,
+			 * but we're safe due to the following factors:
+			 *
+			 * - Only a single writer can be enlarging isize
+			 *   Enlarging isize will take the exclusive inode lock.
+			 *
+			 * - Buffered readers need to wait for the OE we're holding
+			 *   Buffered readers will lock extent and wait for OE
+			 *   of the folio range, and since page cache is invalidated
+			 *   the OE wait can not be skipped.
+			 *
+			 * So here we are safe to revert the isize before
+			 * finishing the OE, and no reader of the remaining range
+			 * can see the enlarged size.
+			 *
+			 * TODO: Extend the DIO_LOCKED lifespan for direct writes,
+			 * and only enlarge isize after a successful write.
+			 */
+			if (dio_data->updated_isize) {
+				u64 new_isize;
+
+				if (submitted == 0)
+					new_isize = dio_data->old_isize;
+				else
+					new_isize = max(dio_data->old_isize, pos);
+				i_size_write(inode, new_isize);
+				dio_data->updated_isize = false;
+			}
+			/*
+			 * We have a short write, if there is any range
+			 * that is submitted properly, that part will have
+			 * its own OE split from the original one.
+			 *
+			 * So for the OE at dio_data->ordered, it's the part
+			 * that is not submitted, and should be marked
+			 * as fully truncated.
+			 */
+			btrfs_mark_ordered_extent_truncated(dio_data->ordered, 0);
 			btrfs_finish_ordered_extent(dio_data->ordered,
-						    pos, length, false);
-		else
+						    pos, length, true);
+		} else {
 			btrfs_unlock_dio_extent(&BTRFS_I(inode)->io_tree, pos,
 						pos + length - 1, NULL);
+		}
 		ret = -ENOTBLK;
 	}
 	if (write) {