1 files changed, 23 insertions, 0 deletions

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index cfeff1b8dce0..818f7ec8bb0e 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -43,6 +43,8 @@
 #include "qgroup.h"
 #include "tree-log.h"
 #include "compression.h"
+#include "space-info.h"
+#include "delalloc-space.h"
 
 #ifdef CONFIG_64BIT
 /* If we have a 32-bit userspace and 64-bit kernel, then the UAPI
@@ -3993,6 +3995,27 @@ static int btrfs_remap_file_range_prep(struct file *file_in, loff_t pos_in,
         if (!same_inode)
                 inode_dio_wait(inode_out);
 
+        /*
+         * Workaround to make sure NOCOW buffered write reach disk as NOCOW.
+         *
+         * Btrfs' back references do not have a block level granularity, they
+         * work at the whole extent level.
+         * NOCOW buffered write without data space reserved may not be able
+         * to fall back to CoW due to lack of data space, thus could cause
+         * data loss.
+         *
+         * Here we take a shortcut by flushing the whole inode, so that all
+         * nocow write should reach disk as nocow before we increase the
+         * reference of the extent. We could do better by only flushing NOCOW
+         * data, but that needs extra accounting.
+         *
+         * Also we don't need to check ASYNC_EXTENT, as async extent will be
+         * CoWed anyway, not affecting nocow part.
+         */
+        ret = filemap_flush(inode_in->i_mapping);
+        if (ret < 0)
+                return ret;
+
         ret = btrfs_wait_ordered_range(inode_in, ALIGN_DOWN(pos_in, bs),
                                        wb_len);
         if (ret < 0)