[PATCH v3 03/10] ext4: don't write back data before punch hole in nojournal mode

[Zhang Yi]

There is no need to write back all data before punching a hole in
data=ordered|writeback mode since it will be dropped soon after removing
space, so just remove the filemap_write_and_wait_range() in these modes.
However, in data=journal mode, we need to write dirty pages out before
discarding page cache in case of crash before committing the freeing
data transaction, which could expose old, stale data.

Signed-off-by: Zhang Yi <yi.zhang@xxxxxxxxxx>
---
 fs/ext4/inode.c | 26 +++++++++++++++-----------
 1 file changed, 15 insertions(+), 11 deletions(-)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index f8796f7b0f94..94b923afcd9c 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3965,17 +3965,6 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
 
 	trace_ext4_punch_hole(inode, offset, length, 0);
 
-	/*
-	 * Write out all dirty pages to avoid race conditions
-	 * Then release them.
-	 */
-	if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
-		ret = filemap_write_and_wait_range(mapping, offset,
-						   offset + length - 1);
-		if (ret)
-			return ret;
-	}
-
 	inode_lock(inode);
 
 	/* No need to punch hole beyond i_size */
@@ -4037,6 +4026,21 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
 		ret = ext4_update_disksize_before_punch(inode, offset, length);
 		if (ret)
 			goto out_dio;
+
+		/*
+		 * For journalled data we need to write (and checkpoint) pages
+		 * before discarding page cache to avoid inconsitent data on
+		 * disk in case of crash before punching trans is committed.
+		 */
+		if (ext4_should_journal_data(inode)) {
+			ret = filemap_write_and_wait_range(mapping,
+					first_block_offset, last_block_offset);
+			if (ret)
+				goto out_dio;
+		}
+
+		ext4_truncate_folios_range(inode, first_block_offset,
+					   last_block_offset + 1);
 		truncate_pagecache_range(inode, first_block_offset,
 					 last_block_offset);
 	}
-- 
2.39.2