ext4: fix bug on in ext4_es_cache_extent as ext4_split_extent_at failed

We got follow bug_on when run fsstress with injecting IO fault:
[130747.323114] kernel BUG at fs/ext4/extents_status.c:762!
[130747.323117] Internal error: Oops - BUG: 0 [#1] SMP
......
[130747.334329] Call trace:
[130747.334553]  ext4_es_cache_extent+0x150/0x168 [ext4]
[130747.334975]  ext4_cache_extents+0x64/0xe8 [ext4]
[130747.335368]  ext4_find_extent+0x300/0x330 [ext4]
[130747.335759]  ext4_ext_map_blocks+0x74/0x1178 [ext4]
[130747.336179]  ext4_map_blocks+0x2f4/0x5f0 [ext4]
[130747.336567]  ext4_mpage_readpages+0x4a8/0x7a8 [ext4]
[130747.336995]  ext4_readpage+0x54/0x100 [ext4]
[130747.337359]  generic_file_buffered_read+0x410/0xae8
[130747.337767]  generic_file_read_iter+0x114/0x190
[130747.338152]  ext4_file_read_iter+0x5c/0x140 [ext4]
[130747.338556]  __vfs_read+0x11c/0x188
[130747.338851]  vfs_read+0x94/0x150
[130747.339110]  ksys_read+0x74/0xf0

This patch's modification is according to Jan Kara's suggestion in:
https://patchwork.ozlabs.org/project/linux-ext4/patch/20210428085158.3728201-1-yebin10@huawei.com/
"I see. Now I understand your patch. Honestly, seeing how fragile is trying
to fix extent tree after split has failed in the middle, I would probably
go even further and make sure we fix the tree properly in case of ENOSPC
and EDQUOT (those are easily user triggerable).  Anything else indicates a
HW problem or fs corruption so I'd rather leave the extent tree as is and
don't try to fix it (which also means we will not create overlapping
extents)."

Cc: stable@kernel.org
Signed-off-by: Ye Bin <yebin10@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20210506141042.3298679-1-yebin10@huawei.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 77c84d6f1af6b2489aa196e845f3b0b1a6060e83..cbf37b2cf871e59f8bac4a372d55db7ed223b41a 100644 (file)
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -3206,7 +3206,10 @@ static int ext4_split_extent_at(handle_t *handle,
                ext4_ext_mark_unwritten(ex2);
 
        err = ext4_ext_insert_extent(handle, inode, ppath, &newex, flags);
-       if (err == -ENOSPC && (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
+       if (err != -ENOSPC && err != -EDQUOT)
+               goto out;
+
+       if (EXT4_EXT_MAY_ZEROOUT & split_flag) {
                if (split_flag & (EXT4_EXT_DATA_VALID1|EXT4_EXT_DATA_VALID2)) {
                        if (split_flag & EXT4_EXT_DATA_VALID1) {
                                err = ext4_ext_zeroout(inode, ex2);
@@ -3232,25 +3235,22 @@ static int ext4_split_extent_at(handle_t *handle,
                                              ext4_ext_pblock(&orig_ex));
                }
 
-               if (err)
-                       goto fix_extent_len;
-               /* update the extent length and mark as initialized */
-               ex->ee_len = cpu_to_le16(ee_len);
-               ext4_ext_try_to_merge(handle, inode, path, ex);
-               err = ext4_ext_dirty(handle, inode, path + path->p_depth);
-               if (err)
-                       goto fix_extent_len;
-
-               /* update extent status tree */
-               err = ext4_zeroout_es(inode, &zero_ex);
-
-               goto out;
-       } else if (err)
-               goto fix_extent_len;
-
-out:
-       ext4_ext_show_leaf(inode, path);
-       return err;
+               if (!err) {
+                       /* update the extent length and mark as initialized */
+                       ex->ee_len = cpu_to_le16(ee_len);
+                       ext4_ext_try_to_merge(handle, inode, path, ex);
+                       err = ext4_ext_dirty(handle, inode, path + path->p_depth);
+                       if (!err)
+                               /* update extent status tree */
+                               err = ext4_zeroout_es(inode, &zero_ex);
+                       /* If we failed at this point, we don't know in which
+                        * state the extent tree exactly is so don't try to fix
+                        * length of the original extent as it may do even more
+                        * damage.
+                        */
+                       goto out;
+               }
+       }
 
 fix_extent_len:
        ex->ee_len = orig_ex.ee_len;
@@ -3260,6 +3260,9 @@ fix_extent_len:
         */
        ext4_ext_dirty(handle, inode, path + path->p_depth);
        return err;
+out:
+       ext4_ext_show_leaf(inode, path);
+       return err;
 }
 
 /*