Commit acf795dc authored by Zhang Yi's avatar Zhang Yi Committed by Theodore Ts'o

ext4: convert to exclusive lock while inserting delalloc extents

ext4_da_map_blocks() only hold i_data_sem in shared mode and i_rwsem
when inserting delalloc extents, it could be raced by another querying
path of ext4_map_blocks() without i_rwsem, .e.g buffered read path.
Suppose we buffered read a file containing just a hole, and without any
cached extents tree, then it is raced by another delayed buffered write
to the same area or the near area belongs to the same hole, and the new
delalloc extent could be overwritten to a hole extent.

 pread()                           pwrite()
  filemap_read_folio()
   ext4_mpage_readpages()
    ext4_map_blocks()
     down_read(i_data_sem)
     ext4_ext_determine_hole()
     //find hole
     ext4_ext_put_gap_in_cache()
      ext4_es_find_extent_range()
      //no delalloc extent
                                    ext4_da_map_blocks()
                                     down_read(i_data_sem)
                                     ext4_insert_delayed_block()
                                     //insert delalloc extent
      ext4_es_insert_extent()
      //overwrite delalloc extent to hole

This race could lead to inconsistent delalloc extents tree and
incorrect reserved space counter. Fix this by converting to hold
i_data_sem in exclusive mode when adding a new delalloc extent in
ext4_da_map_blocks().

Cc: stable@vger.kernel.org
Signed-off-by: default avatarZhang Yi <yi.zhang@huawei.com>
Suggested-by: default avatarJan Kara <jack@suse.cz>
Reviewed-by: default avatarJan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20240127015825.1608160-3-yi.zhang@huaweicloud.comSigned-off-by: default avatarTheodore Ts'o <tytso@mit.edu>
parent 3fcc2b88
...@@ -1703,10 +1703,8 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, ...@@ -1703,10 +1703,8 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
/* Lookup extent status tree firstly */ /* Lookup extent status tree firstly */
if (ext4_es_lookup_extent(inode, iblock, NULL, &es)) { if (ext4_es_lookup_extent(inode, iblock, NULL, &es)) {
if (ext4_es_is_hole(&es)) { if (ext4_es_is_hole(&es))
down_read(&EXT4_I(inode)->i_data_sem);
goto add_delayed; goto add_delayed;
}
/* /*
* Delayed extent could be allocated by fallocate. * Delayed extent could be allocated by fallocate.
...@@ -1748,8 +1746,10 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, ...@@ -1748,8 +1746,10 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
retval = ext4_ext_map_blocks(NULL, inode, map, 0); retval = ext4_ext_map_blocks(NULL, inode, map, 0);
else else
retval = ext4_ind_map_blocks(NULL, inode, map, 0); retval = ext4_ind_map_blocks(NULL, inode, map, 0);
if (retval < 0) if (retval < 0) {
goto out_unlock; up_read(&EXT4_I(inode)->i_data_sem);
return retval;
}
if (retval > 0) { if (retval > 0) {
unsigned int status; unsigned int status;
...@@ -1765,24 +1765,21 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, ...@@ -1765,24 +1765,21 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
ext4_es_insert_extent(inode, map->m_lblk, map->m_len, ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
map->m_pblk, status); map->m_pblk, status);
goto out_unlock; up_read(&EXT4_I(inode)->i_data_sem);
return retval;
} }
up_read(&EXT4_I(inode)->i_data_sem);
add_delayed: add_delayed:
/* down_write(&EXT4_I(inode)->i_data_sem);
* XXX: __block_prepare_write() unmaps passed block,
* is it OK?
*/
retval = ext4_insert_delayed_block(inode, map->m_lblk); retval = ext4_insert_delayed_block(inode, map->m_lblk);
up_write(&EXT4_I(inode)->i_data_sem);
if (retval) if (retval)
goto out_unlock; return retval;
map_bh(bh, inode->i_sb, invalid_block); map_bh(bh, inode->i_sb, invalid_block);
set_buffer_new(bh); set_buffer_new(bh);
set_buffer_delay(bh); set_buffer_delay(bh);
out_unlock:
up_read((&EXT4_I(inode)->i_data_sem));
return retval; return retval;
} }
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment