ext4: remove writable userspace mappings before truncating page cache

When zeroing a range of folios on the filesystem which block size is
less than the page size, the file's mapped blocks within one page will
be marked as unwritten, we should remove writable userspace mappings to
ensure that ext4_page_mkwrite() can be called during subsequent write
access to these partial folios. Otherwise, data written by subsequent
mmap writes may not be saved to disk.

 $mkfs.ext4 -b 1024 /dev/vdb
 $mount /dev/vdb /mnt
 $xfs_io -t -f -c "pwrite -S 0x58 0 4096" -c "mmap -rw 0 4096" \
               -c "mwrite -S 0x5a 2048 2048" -c "fzero 2048 2048" \
               -c "mwrite -S 0x59 2048 2048" -c "close" /mnt/foo

 $od -Ax -t x1z /mnt/foo
 000000 58 58 58 58 58 58 58 58 58 58 58 58 58 58 58 58
 *
 000800 59 59 59 59 59 59 59 59 59 59 59 59 59 59 59 59
 *
 001000

 $umount /mnt && mount /dev/vdb /mnt
 $od -Ax -t x1z /mnt/foo
 000000 58 58 58 58 58 58 58 58 58 58 58 58 58 58 58 58
 *
 000800 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
 *
 001000

Fix this by introducing ext4_truncate_page_cache_block_range() to remove
writable userspace mappings when truncating a partial folio range.
Additionally, move the journal data mode-specific handlers and
truncate_pagecache_range() into this function, allowing it to serve as a
common helper that correctly manages the page cache in preparation for
block range manipulations.

Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Ojaswin Mujoo <ojaswin@linux.ibm.com>
Link: https://patch.msgid.link/20241220011637.1157197-2-yi.zhang@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

1 files changed, 5 insertions, 14 deletions

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index a07a98a4b97a..8dc6b4271b15 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4667,22 +4667,13 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 			goto out_mutex;
 		}
 
-		/*
-		 * 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 zeroing trans is committed.
-		 */
-		if (ext4_should_journal_data(inode)) {
-			ret = filemap_write_and_wait_range(mapping, start,
-							   end - 1);
-			if (ret) {
-				filemap_invalidate_unlock(mapping);
-				goto out_mutex;
-			}
+		/* Now release the pages and zero block aligned part of pages */
+		ret = ext4_truncate_page_cache_block_range(inode, start, end);
+		if (ret) {
+			filemap_invalidate_unlock(mapping);
+			goto out_mutex;
 		}
 
-		/* Now release the pages and zero block aligned part of pages */
-		truncate_pagecache_range(inode, start, end - 1);
 		inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
 
 		ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,