From: Zhang Yi <yi.zhang@xxxxxxxxxx>
Online defrag doesn't support iomap path yet, so we have to fall back to
buffer_head path for inodes which have been useing iomap. Fall back
active inode is dangerous, we must writeback and drop all dirty pages
under inode lock and mapping->invalidate_lock, those can protect us from
adding new folios into mapping.
Signed-off-by: Zhang Yi <yi.zhang@xxxxxxxxxx>
---
fs/ext4/move_extent.c | 34 ++++++++++++++++++++++++++++++++++
1 file changed, 34 insertions(+)
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 3aa57376d9c2..7a9ca71d4cac 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -538,6 +538,34 @@ mext_check_arguments(struct inode *orig_inode,
return 0;
}
+/*
+ * Disable buffered iomap path for the inode that requiring move extents,
+ * fallback to buffer_head path.
+ */
+static int ext4_disable_buffered_iomap_aops(struct inode *inode)
+{
+ int err;
+
+ /*
+ * The buffered_head aops don't know how to handle folios
+ * dirtied by iomap, so before falling back, flush all dirty
+ * folios the inode has.
+ */
+ filemap_invalidate_lock(inode->i_mapping);
+ err = filemap_write_and_wait(inode->i_mapping);
+ if (err < 0) {
+ filemap_invalidate_unlock(inode->i_mapping);
+ return err;
+ }
+ truncate_inode_pages(inode->i_mapping, 0);
+
+ ext4_clear_inode_state(inode, EXT4_STATE_BUFFERED_IOMAP);
+ ext4_set_aops(inode);
+ filemap_invalidate_unlock(inode->i_mapping);
+
+ return 0;
+}
+
/**
* ext4_move_extents - Exchange the specified range of a file
*
@@ -609,6 +637,12 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk,
inode_dio_wait(orig_inode);
inode_dio_wait(donor_inode);
+ /* Fallback to buffer_head aops for inodes with buffered iomap aops */
+ if (ext4_test_inode_state(orig_inode, EXT4_STATE_BUFFERED_IOMAP))
+ ext4_disable_buffered_iomap_aops(orig_inode);
+ if (ext4_test_inode_state(donor_inode, EXT4_STATE_BUFFERED_IOMAP))
+ ext4_disable_buffered_iomap_aops(donor_inode);
+
/* Protect extent tree against block allocations via delalloc */
ext4_double_down_write_data_sem(orig_inode, donor_inode);
/* Check the filesystem environment whether move_extent can be done */
--
2.39.2
