@@ -72,6 +72,7 @@ struct btrfs_dio_data {
u64 reserve;
u64 unsubmitted_oe_range_start;
u64 unsubmitted_oe_range_end;
+ int overwrite;
};
static const struct inode_operations btrfs_dir_inode_operations;
@@ -7833,7 +7834,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
* 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))
+ if (!dio_data->overwrite && start + len > i_size_read(inode))
i_size_write(inode, start + len);
adjust_dio_outstanding_extents(inode, dio_data, len);
@@ -8715,6 +8716,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
* not unlock the i_mutex at this case.
*/
if (offset + count <= inode->i_size) {
+ dio_data.overwrite = 1;
inode_unlock(inode);
relock = true;
}
Dio writes can update i_size in btrfs_get_blocks_direct when it writes to offset beyond EOF so that endio can update disk_i_size correctly (because we don't udpate disk_i_size beyond i_size). However, when truncating down a file, we firstly update i_size and then wait for in-flight lockless dio reads/writes, according to the above, i_size may have been changed in dio writes, and file extents don't get truncated. For lockless dio writes are always overwrites, i_size is not supposed to be changed, so this adds a check to filter out this case. The race could be reproduced by fstests/generic/299 with patch "Btrfs: fix btrfs_ordered_update_i_size to update disk_i_size properly" applied. Signed-off-by: Liu Bo <bo.li.liu@oracle.com> --- fs/btrfs/inode.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)