On Fri, Sep 27, 2019 at 04:19:55PM +0800, Yufen Yu wrote:
> We got a null pointer deference BUG_ON in blk_mq_rq_timed_out()
> as following:
>
> [ 108.825472] BUG: kernel NULL pointer dereference, address: 0000000000000040
> [ 108.827059] PGD 0 P4D 0
> [ 108.827313] Oops: 0000 [#1] SMP PTI
> [ 108.827657] CPU: 6 PID: 198 Comm: kworker/6:1H Not tainted 5.3.0-rc8+ #431
> [ 108.829503] Workqueue: kblockd blk_mq_timeout_work
> [ 108.829913] RIP: 0010:blk_mq_check_expired+0x258/0x330
> [ 108.838191] Call Trace:
> [ 108.838406] bt_iter+0x74/0x80
> [ 108.838665] blk_mq_queue_tag_busy_iter+0x204/0x450
> [ 108.839074] ? __switch_to_asm+0x34/0x70
> [ 108.839405] ? blk_mq_stop_hw_queue+0x40/0x40
> [ 108.839823] ? blk_mq_stop_hw_queue+0x40/0x40
> [ 108.840273] ? syscall_return_via_sysret+0xf/0x7f
> [ 108.840732] blk_mq_timeout_work+0x74/0x200
> [ 108.841151] process_one_work+0x297/0x680
> [ 108.841550] worker_thread+0x29c/0x6f0
> [ 108.841926] ? rescuer_thread+0x580/0x580
> [ 108.842344] kthread+0x16a/0x1a0
> [ 108.842666] ? kthread_flush_work+0x170/0x170
> [ 108.843100] ret_from_fork+0x35/0x40
>
> The bug is caused by the race between timeout handle and completion for
> flush request.
>
> When timeout handle function blk_mq_rq_timed_out() try to read
> 'req->q->mq_ops', the 'req' have completed and reinitiated by next
> flush request, which would call blk_rq_init() to clear 'req' as 0.
>
> After commit 12f5b93145 ("blk-mq: Remove generation seqeunce"),
> normal requests lifetime are protected by refcount. Until 'rq->ref'
> drop to zero, the request can really be free. Thus, these requests
> cannot been reused before timeout handle finish.
>
> However, flush request has defined .end_io and rq->end_io() is still
> called even if 'rq->ref' doesn't drop to zero. After that, the 'flush_rq'
> can be reused by the next flush request handle, resulting in null
> pointer deference BUG ON.
>
> We fix this problem by covering flush request with 'rq->ref'.
> If the refcount is not zero, flush_end_io() return and wait the
> last holder recall it. To record the request status, we add a new
> entry 'rq_status', which will be used in flush_end_io().
>
> Cc: Ming Lei <[email protected]>
> Cc: Christoph Hellwig <[email protected]>
> Cc: Keith Busch <[email protected]>
> Cc: Bart Van Assche <[email protected]>
> Cc: [email protected] # v4.18+
> Signed-off-by: Yufen Yu <[email protected]>
>
> -------
> v2:
> - move rq_status from struct request to struct blk_flush_queue
> v3:
> - remove unnecessary '{}' pair.
> v4:
> - let spinlock to protect 'fq->rq_status'
> v5:
> - move rq_status after flush_running_idx member of struct blk_flush_queue
> ---
> block/blk-flush.c | 10 ++++++++++
> block/blk-mq.c | 5 ++++-
> block/blk.h | 7 +++++++
> 3 files changed, 21 insertions(+), 1 deletion(-)
>
> diff --git a/block/blk-flush.c b/block/blk-flush.c
> index aedd9320e605..1eec9cbe5a0a 100644
> --- a/block/blk-flush.c
> +++ b/block/blk-flush.c
> @@ -214,6 +214,16 @@ static void flush_end_io(struct request *flush_rq,
> blk_status_t error)
>
> /* release the tag's ownership to the req cloned from */
> spin_lock_irqsave(&fq->mq_flush_lock, flags);
> +
> + if (!refcount_dec_and_test(&flush_rq->ref)) {
> + fq->rq_status = error;
> + spin_unlock_irqrestore(&fq->mq_flush_lock, flags);
> + return;
> + }
> +
> + if (fq->rq_status != BLK_STS_OK)
> + error = fq->rq_status;
> +
> hctx = flush_rq->mq_hctx;
> if (!q->elevator) {
> blk_mq_tag_set_rq(hctx, flush_rq->tag, fq->orig_rq);
> diff --git a/block/blk-mq.c b/block/blk-mq.c
> index 20a49be536b5..e04fa9ab5574 100644
> --- a/block/blk-mq.c
> +++ b/block/blk-mq.c
> @@ -912,7 +912,10 @@ static bool blk_mq_check_expired(struct blk_mq_hw_ctx
> *hctx,
> */
> if (blk_mq_req_expired(rq, next))
> blk_mq_rq_timed_out(rq, reserved);
> - if (refcount_dec_and_test(&rq->ref))
> +
> + if (is_flush_rq(rq, hctx))
> + rq->end_io(rq, 0);
> + else if (refcount_dec_and_test(&rq->ref))
> __blk_mq_free_request(rq);
>
> return true;
> diff --git a/block/blk.h b/block/blk.h
> index ed347f7a97b1..2d8cdafee799 100644
> --- a/block/blk.h
> +++ b/block/blk.h
> @@ -19,6 +19,7 @@ struct blk_flush_queue {
> unsigned int flush_queue_delayed:1;
> unsigned int flush_pending_idx:1;
> unsigned int flush_running_idx:1;
> + blk_status_t rq_status;
> unsigned long flush_pending_since;
> struct list_head flush_queue[2];
> struct list_head flush_data_in_flight;
> @@ -47,6 +48,12 @@ static inline void __blk_get_queue(struct request_queue *q)
> kobject_get(&q->kobj);
> }
>
> +static inline bool
> +is_flush_rq(struct request *req, struct blk_mq_hw_ctx *hctx)
> +{
> + return hctx->fq->flush_rq == req;
> +}
> +
> struct blk_flush_queue *blk_alloc_flush_queue(struct request_queue *q,
> int node, int cmd_size, gfp_t flags);
> void blk_free_flush_queue(struct blk_flush_queue *q);
> --
> 2.17.2
>
Reviewed-by: Ming Lei <[email protected]>
thanks,
Ming
