Re: [PATCH] md/raid1: prevent a race between write and stop request

[Abd-Alrhman Masalkhi <abd.masalkhi@gmail.com>]

Hi Edward,

On Fri, Aug 28, 2026 at 18:39 +0800, Edward Adam Davis wrote:
> A race condition exists between write and stop requests, leading to a
> null-ptr-deref in [1].
>
> CPU0				CPU1
> ====				====
> md_submit_bio()
> md_handle_request()		do_md_stop()__md_stop()

do_md_stop() must never execute while the array device file is open.
take a look if this rule is not meet.

> raid1_make_request()		 __md_stop()
> raid1_write_request()		   mddev->private = NULL
> wait_barrier()
> conf->nr_pending //trigger [1]
>
> The intervention of a stop request causes inconsistencies in the state
> of mddev members (such as private and pers) while a write request is
> executing; the mddev lock is used to synchronize write and stop requests,
> thereby ensuring consistent mddev state throughout the execution of the
> write request.
>
> Additionally, when a write operation reaches the RAID1 layer, if a stop
> request acquires the mddev lock first and releases mddev->private, the
> bio is terminated and the write request exits.
> 	
> [1]
> KASAN: null-ptr-deref in range [0x0000000000000120-0x0000000000000127]
> RIP: 0010:_wait_barrier+0x8d/0x700 drivers/md/raid1.c:1066
> Call Trace:
>  wait_barrier drivers/md/raid1.c:1154 [inline]
>  raid1_write_request drivers/md/raid1.c:1506 [inline]
>  raid1_make_request+0x484/0x31a0 drivers/md/raid1.c:1696
>  md_handle_request+0x824/0x1230 drivers/md/md.c:417
>  md_submit_bio+0x1e9/0x350 drivers/md/md.c:458
>  __submit_bio block/blk-core.c:681 [inline]
>  __submit_bio+0x20e/0x3d0 block/blk-core.c:670
>  __submit_bio_noacct block/blk-core.c:724 [inline]
>  submit_bio_noacct_nocheck+0x736/0xc00 block/blk-core.c:792
>  submit_bio_noacct+0xc93/0x2130 block/blk-core.c:925
>  bio_await+0x1fa/0x240 block/bio.c:1580
>  submit_bio_wait+0x19/0x60 block/bio.c:1598
>  __blkdev_direct_IO_simple+0x4cb/0x8c0 block/fops.c:98
>  blkdev_direct_IO+0xbee/0x2030 block/fops.c:429
>  blkdev_direct_write block/fops.c:699 [inline]
>  blkdev_write_iter+0x703/0xd30 block/fops.c:767
>  new_sync_write fs/read_write.c:595 [inline]
>  vfs_write+0x6af/0x1050 fs/read_write.c:687
>
> Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
> Reported-by: syzbot+3fe892ea5fc292e1353f@syzkaller.appspotmail.com
> Closes: https://syzkaller.appspot.com/bug?extid=3fe892ea5fc292e1353f
> Tested-by: syzbot+3fe892ea5fc292e1353f@syzkaller.appspotmail.com
> Signed-off-by: Edward Adam Davis <eadavis@sina.com>
> ---
>  drivers/md/raid1.c | 28 +++++++++++++++++++++++++++-
>  1 file changed, 27 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
> index f0646fb24371..3b9f1fa65e65 100644
> --- a/drivers/md/raid1.c
> +++ b/drivers/md/raid1.c
> @@ -1674,6 +1674,7 @@ static bool raid1_write_request(struct mddev *mddev, struct bio *bio,
>  static bool raid1_make_request(struct mddev *mddev, struct bio *bio)
>  {
>  	sector_t sectors;
> +	blk_status_t status;
>  
>  	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
>  	    && md_flush_request(mddev, bio))
> @@ -1692,11 +1693,36 @@ static bool raid1_make_request(struct mddev *mddev, struct bio *bio)
>  	if (bio_data_dir(bio) == READ)
>  		raid1_read_request(mddev, bio, sectors, NULL);
>  	else {
> +		int err;
> +
>  		md_write_start(mddev, bio);
> -		if (!raid1_write_request(mddev, bio, sectors))
> +		err = mddev_lock(mddev);
> +
> +		if (err < 0) {
> +			md_write_end(mddev);
> +			status = BLK_STS_IOERR;
> +			goto done;
> +		}
> +
> +		if (!mddev->private) {
> +			mddev_unlock(mddev);
> +			md_write_end(mddev);
> +			status = BLK_STS_OFFLINE;
> +			goto done;
> +		}
> +
> +		err = raid1_write_request(mddev, bio, sectors);
> +		mddev_unlock(mddev);
> +
> +		if (!err)
>  			md_write_end(mddev);
>  	}
> +out:
>  	return true;
> +done:
> +	bio->bi_status = status;
> +	bio_endio(bio);
> +	goto out;
>  }
>  
>  static void raid1_status(struct seq_file *seq, struct mddev *mddev)
> -- 
> 2.43.0
>
>

-- 
Best Regards,
Abd-Alrhman