ext4: fix races of writeback with punch hole and zero range

When doing delayed allocation, update of on-disk inode size is postponed
until IO submission time. However hole punch or zero range fallocate
calls can end up discarding the tail page cache page and thus on-disk
inode size would never be properly updated.

Make sure the on-disk inode size is updated before truncating page
cache.

Signed-off-by: Jan Kara <jack@suse.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

1 files changed, 34 insertions, 1 deletions

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index d1207d03c961..472e608da13d 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3559,6 +3559,35 @@ int ext4_can_truncate(struct inode *inode)
 }
 
 /*
+ * We have to make sure i_disksize gets properly updated before we truncate
+ * page cache due to hole punching or zero range. Otherwise i_disksize update
+ * can get lost as it may have been postponed to submission of writeback but
+ * that will never happen after we truncate page cache.
+ */
+int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
+                                      loff_t len)
+{
+        handle_t *handle;
+        loff_t size = i_size_read(inode);
+
+        WARN_ON(!mutex_is_locked(&inode->i_mutex));
+        if (offset > size || offset + len < size)
+                return 0;
+
+        if (EXT4_I(inode)->i_disksize >= size)
+                return 0;
+
+        handle = ext4_journal_start(inode, EXT4_HT_MISC, 1);
+        if (IS_ERR(handle))
+                return PTR_ERR(handle);
+        ext4_update_i_disksize(inode, size);
+        ext4_mark_inode_dirty(handle, inode);
+        ext4_journal_stop(handle);
+
+        return 0;
+}
+
+/*
  * ext4_punch_hole: punches a hole in a file by releaseing the blocks
  * associated with the given offset and length
  *
@@ -3636,9 +3665,13 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
         last_block_offset = round_down((offset + length), sb->s_blocksize) - 1;
 
         /* Now release the pages and zero block aligned part of pages*/
-        if (last_block_offset > first_block_offset)
+        if (last_block_offset > first_block_offset) {
+                ret = ext4_update_disksize_before_punch(inode, offset, length);
+                if (ret)
+                        goto out_dio;
                 truncate_pagecache_range(inode, first_block_offset,
                                          last_block_offset);
+        }
 
         if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
                 credits = ext4_writepage_trans_blocks(inode);