From: Baokun Li <libaokun1@xxxxxxxxxx>
commit f87c7a4b084afc13190cbb263538e444cb2b392a upstream.
Hulk Robot reported a BUG_ON:
==================================================================
EXT4-fs error (device loop3): ext4_mb_generate_buddy:805: group 0,
block bitmap and bg descriptor inconsistent: 25 vs 31513 free clusters
kernel BUG at fs/ext4/ext4_jbd2.c:53!
invalid opcode: 0000 [#1] SMP KASAN PTI
CPU: 0 PID: 25371 Comm: syz-executor.3 Not tainted 5.10.0+ #1
RIP: 0010:ext4_put_nojournal fs/ext4/ext4_jbd2.c:53 [inline]
RIP: 0010:__ext4_journal_stop+0x10e/0x110 fs/ext4/ext4_jbd2.c:116
[...]
Call Trace:
ext4_write_inline_data_end+0x59a/0x730 fs/ext4/inline.c:795
generic_perform_write+0x279/0x3c0 mm/filemap.c:3344
ext4_buffered_write_iter+0x2e3/0x3d0 fs/ext4/file.c:270
ext4_file_write_iter+0x30a/0x11c0 fs/ext4/file.c:520
do_iter_readv_writev+0x339/0x3c0 fs/read_write.c:732
do_iter_write+0x107/0x430 fs/read_write.c:861
vfs_writev fs/read_write.c:934 [inline]
do_pwritev+0x1e5/0x380 fs/read_write.c:1031
[...]
==================================================================
Above issue may happen as follows:
cpu1 cpu2
__________________________|__________________________
do_pwritev
vfs_writev
do_iter_write
ext4_file_write_iter
ext4_buffered_write_iter
generic_perform_write
ext4_da_write_begin
vfs_fallocate
ext4_fallocate
ext4_convert_inline_data
ext4_convert_inline_data_nolock
ext4_destroy_inline_data_nolock
clear EXT4_STATE_MAY_INLINE_DATA
ext4_map_blocks
ext4_ext_map_blocks
ext4_mb_new_blocks
ext4_mb_regular_allocator
ext4_mb_good_group_nolock
ext4_mb_init_group
ext4_mb_init_cache
ext4_mb_generate_buddy --> error
ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)
ext4_restore_inline_data
set EXT4_STATE_MAY_INLINE_DATA
ext4_block_write_begin
ext4_da_write_end
ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)
ext4_write_inline_data_end
handle=NULL
ext4_journal_stop(handle)
__ext4_journal_stop
ext4_put_nojournal(handle)
ref_cnt = (unsigned long)handle
BUG_ON(ref_cnt == 0) ---> BUG_ON
The lock held by ext4_convert_inline_data is xattr_sem, but the lock
held by generic_perform_write is i_rwsem. Therefore, the two locks can
be concurrent.
To solve above issue, we add inode_lock() for ext4_convert_inline_data().
At the same time, move ext4_convert_inline_data() in front of
ext4_punch_hole(), remove similar handling from ext4_punch_hole().
Fixes: 0c8d414f163f ("ext4: let fallocate handle inline data correctly")
Cc: stable@xxxxxxxxxxxxxxx
Reported-by: Hulk Robot <hulkci@xxxxxxxxxx>
Signed-off-by: Baokun Li <libaokun1@xxxxxxxxxx>
Reviewed-by: Jan Kara <jack@xxxxxxx>
Link: https://lore.kernel.org/r/20220428134031.4153381-1-libaokun1@xxxxxxxxxx
Signed-off-by: Theodore Ts'o <tytso@xxxxxxx>
Signed-off-by: Tadeusz Struk <tadeusz.struk@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
fs/ext4/extents.c | 9 +++++----
fs/ext4/inode.c | 9 ---------
2 files changed, 5 insertions(+), 13 deletions(-)
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4691,16 +4691,17 @@ long ext4_fallocate(struct file *file, i
return -EOPNOTSUPP;
ext4_fc_start_update(inode);
+ inode_lock(inode);
+ ret = ext4_convert_inline_data(inode);
+ inode_unlock(inode);
+ if (ret)
+ goto exit;
if (mode & FALLOC_FL_PUNCH_HOLE) {
ret = ext4_punch_hole(file, offset, len);
goto exit;
}
- ret = ext4_convert_inline_data(inode);
- if (ret)
- goto exit;
-
if (mode & FALLOC_FL_COLLAPSE_RANGE) {
ret = ext4_collapse_range(file, offset, len);
goto exit;
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4042,15 +4042,6 @@ int ext4_punch_hole(struct file *file, l
trace_ext4_punch_hole(inode, offset, length, 0);
- ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
- if (ext4_has_inline_data(inode)) {
- down_write(&EXT4_I(inode)->i_mmap_sem);
- ret = ext4_convert_inline_data(inode);
- up_write(&EXT4_I(inode)->i_mmap_sem);
- if (ret)
- return ret;
- }
-
/*
* Write out all dirty pages to avoid race conditions
* Then release them.
