Re: [PATCH v2] blk-mq: Fix stall due to recursive flush plug

[Bart Van Assche <bvanassche@acm.org>]

On 7/14/23 03:11, Ross Lagerwall wrote:
> diff --git a/block/blk-core.c b/block/blk-core.c
> index 99d8b9812b18..90de50082146 100644
> --- a/block/blk-core.c
> +++ b/block/blk-core.c
> @@ -1144,8 +1144,7 @@ void __blk_flush_plug(struct blk_plug *plug, bool from_schedule)
>   {
>   	if (!list_empty(&plug->cb_list))
>   		flush_plug_callbacks(plug, from_schedule);
> -	if (!rq_list_empty(plug->mq_list))
> -		blk_mq_flush_plug_list(plug, from_schedule);
> +	blk_mq_flush_plug_list(plug, from_schedule);
>   	/*
>   	 * Unconditionally flush out cached requests, even if the unplug
>   	 * event came from schedule. Since we know hold references to the
> diff --git a/block/blk-mq.c b/block/blk-mq.c
> index 5504719b970d..e6bd9c5f42bb 100644
> --- a/block/blk-mq.c
> +++ b/block/blk-mq.c
> @@ -2742,7 +2742,14 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
>   {
>   	struct request *rq;
>   
> -	if (rq_list_empty(plug->mq_list))
> +	/*
> +	 * We may have been called recursively midway through handling
> +	 * plug->mq_list via a schedule() in the driver's queue_rq() callback.
> +	 * To avoid mq_list changing under our feet, clear rq_count early and
> +	 * bail out specifically if rq_count is 0 rather than checking
> +	 * whether the mq_list is empty.
> +	 */
> +	if (plug->rq_count == 0)
>   		return;
>   	plug->rq_count = 0;

Reviewed-by: Bart Van Assche <bvanassche@acm.org>