On 4/8/23 08:58, Bart Van Assche wrote:
> Let deadline_next_request() only consider the first zoned write per
> zone. This patch fixes a race condition between deadline_next_request()
> and completion of zoned writes.
>
> Cc: Damien Le Moal <damien.lemoal@xxxxxxxxxxxxxxxxxx>
> Cc: Christoph Hellwig <hch@xxxxxx>
> Cc: Ming Lei <ming.lei@xxxxxxxxxx>
> Cc: Mike Snitzer <snitzer@xxxxxxxxxx>
> Signed-off-by: Bart Van Assche <bvanassche@xxxxxxx>
> ---
> block/mq-deadline.c | 24 +++++++++++++++++++++---
> include/linux/blk-mq.h | 5 +++++
> 2 files changed, 26 insertions(+), 3 deletions(-)
>
> diff --git a/block/mq-deadline.c b/block/mq-deadline.c
> index 8c2bc9fdcf8c..d49e20d3011d 100644
> --- a/block/mq-deadline.c
> +++ b/block/mq-deadline.c
> @@ -389,12 +389,30 @@ deadline_next_request(struct deadline_data *dd, struct dd_per_prio *per_prio,
> */
> spin_lock_irqsave(&dd->zone_lock, flags);
> while (rq) {
> + unsigned int zno = blk_rq_zone_no(rq);
> +
> if (blk_req_can_dispatch_to_zone(rq))
> break;
> - if (blk_queue_nonrot(q))
> - rq = deadline_latter_request(rq);
> - else
> +
> + WARN_ON_ONCE(!blk_queue_is_zoned(q));
I do not think this WARN is useful as blk_req_can_dispatch_to_zone() will always
return true for regular block devices.
> +
> + if (!blk_queue_nonrot(q)) {
> rq = deadline_skip_seq_writes(dd, rq);
> + if (!rq)
> + break;
> + rq = deadline_earlier_request(rq);
> + if (WARN_ON_ONCE(!rq))
> + break;
I do not understand why this is needed.
> + }
> +
> + /*
> + * Skip all other write requests for the zone with zone number
> + * 'zno'. This prevents that this function selects a zoned write
> + * that is not the first write for a given zone.
> + */
> + while ((rq = deadline_latter_request(rq)) &&
> + blk_rq_zone_no(rq) == zno)
> + ;
> }
> spin_unlock_irqrestore(&dd->zone_lock, flags);
>
> diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
> index e62feb17af96..515dfd04d736 100644
> --- a/include/linux/blk-mq.h
> +++ b/include/linux/blk-mq.h
> @@ -1193,6 +1193,11 @@ static inline bool blk_req_can_dispatch_to_zone(struct request *rq)
> return !blk_req_zone_is_write_locked(rq);
> }
> #else /* CONFIG_BLK_DEV_ZONED */
> +static inline unsigned int blk_rq_zone_no(struct request *rq)
> +{
> + return 0;
> +}
> +
> static inline bool blk_req_needs_zone_write_lock(struct request *rq)
> {
> return false;
