Merge tag 'for-4.20-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave...

[sfrench/cifs-2.6.git] / fs / btrfs / file.c

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index a3c22e16509b3067e65e86f1b98d2d9e9e84d99a..58e93bce30362dc0584c212ba18822ed13fde723 100644 (file)
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2088,6 +2088,30 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 
        atomic_inc(&root->log_batch);
 
+       /*
+        * Before we acquired the inode's lock, someone may have dirtied more
+        * pages in the target range. We need to make sure that writeback for
+        * any such pages does not start while we are logging the inode, because
+        * if it does, any of the following might happen when we are not doing a
+        * full inode sync:
+        *
+        * 1) We log an extent after its writeback finishes but before its
+        *    checksums are added to the csum tree, leading to -EIO errors
+        *    when attempting to read the extent after a log replay.
+        *
+        * 2) We can end up logging an extent before its writeback finishes.
+        *    Therefore after the log replay we will have a file extent item
+        *    pointing to an unwritten extent (and no data checksums as well).
+        *
+        * So trigger writeback for any eventual new dirty pages and then we
+        * wait for all ordered extents to complete below.
+        */
+       ret = start_ordered_ops(inode, start, end);
+       if (ret) {
+               inode_unlock(inode);
+               goto out;
+       }
+
        /*
         * We have to do this here to avoid the priority inversion of waiting on
         * IO of a lower priority task while holding a transaciton open.