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>

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 348a5ff4a0e25de532b721244f3de6e1bc7c52af..80f76f092079017e12ed9389020e55695c8fbd35 100644 (file)
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2858,6 +2858,9 @@ static inline int ext4_update_inode_size(struct inode *inode, loff_t newsize)
        return changed;
 }
 
+int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
+                                     loff_t len);
+
 struct ext4_group_info {
        unsigned long   bb_state;
        struct rb_root  bb_free_root;

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 4b105c96df082e916209417348ded03d3ac599b5..3578b25fccfd8eef98062e22ee037037a9c8ca38 100644 (file)
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4847,6 +4847,11 @@ static long ext4_zero_range(struct file *file, loff_t offset,
                 * released from page cache.
                 */
                down_write(&EXT4_I(inode)->i_mmap_sem);
+               ret = ext4_update_disksize_before_punch(inode, offset, len);
+               if (ret) {
+                       up_write(&EXT4_I(inode)->i_mmap_sem);
+                       goto out_dio;
+               }
                /* Now release the pages and zero block aligned part of pages */
                truncate_pagecache_range(inode, start, end - 1);
                inode->i_mtime = inode->i_ctime = ext4_current_time(inode);

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index d1207d03c9617ab1ecf840661b5cf11e2851090a..472e608da13d4d65f47d59090d34823e9895b59c 100644 (file)
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3558,6 +3558,35 @@ int ext4_can_truncate(struct inode *inode)
        return 0;
 }
 
+/*
+ * 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);