ext4: check and update i_disksize properly

After commit 3da40c7b0898 ("ext4: only call ext4_truncate when size <=
isize"), i_disksize could always be updated to i_size in ext4_setattr(),
and we could sure that i_disksize <= i_size since holding inode lock and
if i_disksize < i_size there are delalloc writes pending in the range
upto i_size. If the end of the current write is <= i_size, there's no
need to touch i_disksize since writeback will push i_disksize upto
i_size eventually. So we can switch to check i_size instead of
i_disksize in ext4_da_write_end() when write to the end of the file.
we also could remove ext4_mark_inode_dirty() together because we defer
inode dirtying to generic_write_end() or ext4_da_write_inline_data_end().

Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Link: https://lore.kernel.org/r/20210716122024.1105856-2-yi.zhang@huawei.com

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 2c33c79..76d9e25 100644 (file)
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3084,35 +3084,37 @@ static int ext4_da_write_end(struct file *file,
        end = start + copied - 1;
 
        /*
-        * generic_write_end() will run mark_inode_dirty() if i_size
-        * changes.  So let's piggyback the i_disksize mark_inode_dirty
-        * into that.
+        * Since we are holding inode lock, we are sure i_disksize <=
+        * i_size. We also know that if i_disksize < i_size, there are
+        * delalloc writes pending in the range upto i_size. If the end of
+        * the current write is <= i_size, there's no need to touch
+        * i_disksize since writeback will push i_disksize upto i_size
+        * eventually. If the end of the current write is > i_size and
+        * inside an allocated block (ext4_da_should_update_i_disksize()
+        * check), we need to update i_disksize here as neither
+        * ext4_writepage() nor certain ext4_writepages() paths not
+        * allocating blocks update i_disksize.
+        *
+        * Note that we defer inode dirtying to generic_write_end() /
+        * ext4_da_write_inline_data_end().
         */
        new_i_size = pos + copied;
-       if (copied && new_i_size > EXT4_I(inode)->i_disksize) {
+       if (copied && new_i_size > inode->i_size) {
                if (ext4_has_inline_data(inode) ||
-                   ext4_da_should_update_i_disksize(page, end)) {
+                   ext4_da_should_update_i_disksize(page, end))
                        ext4_update_i_disksize(inode, new_i_size);
-                       /* We need to mark inode dirty even if
-                        * new_i_size is less that inode->i_size
-                        * bu greater than i_disksize.(hint delalloc)
-                        */
-                       ret = ext4_mark_inode_dirty(handle, inode);
-               }
        }
 
        if (write_mode != CONVERT_INLINE_DATA &&
            ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA) &&
            ext4_has_inline_data(inode))
-               ret2 = ext4_da_write_inline_data_end(inode, pos, len, copied,
+               ret = ext4_da_write_inline_data_end(inode, pos, len, copied,
                                                     page);
        else
-               ret2 = generic_write_end(file, mapping, pos, len, copied,
+               ret = generic_write_end(file, mapping, pos, len, copied,
                                                        page, fsdata);
 
-       copied = ret2;
-       if (ret2 < 0)
-               ret = ret2;
+       copied = ret;
        ret2 = ext4_journal_stop(handle);
        if (unlikely(ret2 && !ret))
                ret = ret2;