mainline inclusion from mainline-v6.8-rc3 commit acf795dc161f3cf481db20f05db4250714e375e5 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9DN5Z CVE: NA
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
--------------------------------
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: Zhang Yi yi.zhang@huawei.com Suggested-by: Jan Kara jack@suse.cz Reviewed-by: Jan Kara jack@suse.cz Link: https://lore.kernel.org/r/20240127015825.1608160-3-yi.zhang@huaweicloud.com Signed-off-by: Theodore Ts'o tytso@mit.edu --- fs/ext4/inode.c | 25 +++++++++++-------------- 1 file changed, 11 insertions(+), 14 deletions(-)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 945983622408..db6dbbe5988e 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1705,10 +1705,8 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
/* Lookup extent status tree firstly */ if (ext4_es_lookup_extent(inode, iblock, NULL, &es)) { - if (ext4_es_is_hole(&es)) { - down_read(&EXT4_I(inode)->i_data_sem); + if (ext4_es_is_hole(&es)) goto add_delayed; - }
/* * Delayed extent could be allocated by fallocate. @@ -1750,8 +1748,10 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, retval = ext4_ext_map_blocks(NULL, inode, map, 0); else retval = ext4_ind_map_blocks(NULL, inode, map, 0); - if (retval < 0) - goto out_unlock; + if (retval < 0) { + up_read(&EXT4_I(inode)->i_data_sem); + return retval; + } if (retval > 0) { unsigned int status;
@@ -1767,24 +1767,21 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; ext4_es_insert_extent(inode, map->m_lblk, map->m_len, 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: - /* - * XXX: __block_prepare_write() unmaps passed block, - * is it OK? - */ + down_write(&EXT4_I(inode)->i_data_sem); retval = ext4_insert_delayed_block(inode, map->m_lblk); + up_write(&EXT4_I(inode)->i_data_sem); if (retval) - goto out_unlock; + return retval;
map_bh(bh, inode->i_sb, invalid_block); set_buffer_new(bh); set_buffer_delay(bh); - -out_unlock: - up_read((&EXT4_I(inode)->i_data_sem)); return retval; }