diff options
author | Chao Yu <chao@kernel.org> | 2023-05-23 14:17:25 +0800 |
---|---|---|
committer | Jaegeuk Kim <jaegeuk@kernel.org> | 2023-06-12 13:04:08 -0700 |
commit | d8189834d4348ae608083e1f1f53792cfcc2a9bc (patch) | |
tree | bfcf66e45f641f971d00d18487b1d242fd3cc8f8 /fs | |
parent | bfd476623999118d9c509cb0fa9380f2912bc225 (diff) |
f2fs: fix to avoid NULL pointer dereference f2fs_write_end_io()
butt3rflyh4ck reports a bug as below:
When a thread always calls F2FS_IOC_RESIZE_FS to resize fs, if resize fs is
failed, f2fs kernel thread would invoke callback function to update f2fs io
info, it would call f2fs_write_end_io and may trigger null-ptr-deref in
NODE_MAPPING.
general protection fault, probably for non-canonical address
KASAN: null-ptr-deref in range [0x0000000000000030-0x0000000000000037]
RIP: 0010:NODE_MAPPING fs/f2fs/f2fs.h:1972 [inline]
RIP: 0010:f2fs_write_end_io+0x727/0x1050 fs/f2fs/data.c:370
<TASK>
bio_endio+0x5af/0x6c0 block/bio.c:1608
req_bio_endio block/blk-mq.c:761 [inline]
blk_update_request+0x5cc/0x1690 block/blk-mq.c:906
blk_mq_end_request+0x59/0x4c0 block/blk-mq.c:1023
lo_complete_rq+0x1c6/0x280 drivers/block/loop.c:370
blk_complete_reqs+0xad/0xe0 block/blk-mq.c:1101
__do_softirq+0x1d4/0x8ef kernel/softirq.c:571
run_ksoftirqd kernel/softirq.c:939 [inline]
run_ksoftirqd+0x31/0x60 kernel/softirq.c:931
smpboot_thread_fn+0x659/0x9e0 kernel/smpboot.c:164
kthread+0x33e/0x440 kernel/kthread.c:379
ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:308
The root cause is below race case can cause leaving dirty metadata
in f2fs after filesystem is remount as ro:
Thread A Thread B
- f2fs_ioc_resize_fs
- f2fs_readonly --- return false
- f2fs_resize_fs
- f2fs_remount
- write_checkpoint
- set f2fs as ro
- free_segment_range
- update meta_inode's data
Then, if f2fs_put_super() fails to write_checkpoint due to readonly
status, and meta_inode's dirty data will be writebacked after node_inode
is put, finally, f2fs_write_end_io will access NULL pointer on
sbi->node_inode.
Thread A IRQ context
- f2fs_put_super
- write_checkpoint fails
- iput(node_inode)
- node_inode = NULL
- iput(meta_inode)
- write_inode_now
- f2fs_write_meta_page
- f2fs_write_end_io
- NODE_MAPPING(sbi)
: access NULL pointer on node_inode
Fixes: b4b10061ef98 ("f2fs: refactor resize_fs to avoid meta updates in progress")
Reported-by: butt3rflyh4ck <butterflyhuangxx@gmail.com>
Closes: https://lore.kernel.org/r/1684480657-2375-1-git-send-email-yangtiezhu@loongson.cn
Tested-by: butt3rflyh4ck <butterflyhuangxx@gmail.com>
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Diffstat (limited to 'fs')
-rw-r--r-- | fs/f2fs/f2fs.h | 2 | ||||
-rw-r--r-- | fs/f2fs/file.c | 2 | ||||
-rw-r--r-- | fs/f2fs/gc.c | 21 |
3 files changed, 20 insertions, 5 deletions
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index faa27f41f39d..ae47f522d859 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -3834,7 +3834,7 @@ void f2fs_stop_gc_thread(struct f2fs_sb_info *sbi); block_t f2fs_start_bidx_of_node(unsigned int node_ofs, struct inode *inode); int f2fs_gc(struct f2fs_sb_info *sbi, struct f2fs_gc_control *gc_control); void f2fs_build_gc_manager(struct f2fs_sb_info *sbi); -int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count); +int f2fs_resize_fs(struct file *filp, __u64 block_count); int __init f2fs_create_garbage_collection_cache(void); void f2fs_destroy_garbage_collection_cache(void); /* victim selection function for cleaning and SSR */ diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 78aa8cff4b41..015ed274dc31 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -3279,7 +3279,7 @@ static int f2fs_ioc_resize_fs(struct file *filp, unsigned long arg) sizeof(block_count))) return -EFAULT; - return f2fs_resize_fs(sbi, block_count); + return f2fs_resize_fs(filp, block_count); } static int f2fs_ioc_enable_verity(struct file *filp, unsigned long arg) diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 51d7e8d29bf1..339c4ba67eb7 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -2105,8 +2105,9 @@ static void update_fs_metadata(struct f2fs_sb_info *sbi, int secs) } } -int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count) +int f2fs_resize_fs(struct file *filp, __u64 block_count) { + struct f2fs_sb_info *sbi = F2FS_I_SB(file_inode(filp)); __u64 old_block_count, shrunk_blocks; struct cp_control cpc = { CP_RESIZE, 0, 0, 0 }; unsigned int secs; @@ -2144,12 +2145,18 @@ int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count) return -EINVAL; } + err = mnt_want_write_file(filp); + if (err) + return err; + shrunk_blocks = old_block_count - block_count; secs = div_u64(shrunk_blocks, BLKS_PER_SEC(sbi)); /* stop other GC */ - if (!f2fs_down_write_trylock(&sbi->gc_lock)) - return -EAGAIN; + if (!f2fs_down_write_trylock(&sbi->gc_lock)) { + err = -EAGAIN; + goto out_drop_write; + } /* stop CP to protect MAIN_SEC in free_segment_range */ f2fs_lock_op(sbi); @@ -2169,10 +2176,18 @@ int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count) out_unlock: f2fs_unlock_op(sbi); f2fs_up_write(&sbi->gc_lock); +out_drop_write: + mnt_drop_write_file(filp); if (err) return err; freeze_super(sbi->sb); + + if (f2fs_readonly(sbi->sb)) { + thaw_super(sbi->sb); + return -EROFS; + } + f2fs_down_write(&sbi->gc_lock); f2fs_down_write(&sbi->cp_global_sem); |