Re: [PATCH v8] block: cancel all throttled bios in del_gendisk()

[Ming Lei]

On Tue, Feb 08, 2022 at 07:38:08PM +0800, Yu Kuai wrote:
> Throttled bios can't be issued after del_gendisk() is done, thus
> it's better to cancel them immediately rather than waiting for
> throttle is done.
> 
> For example, if user thread is throttled with low bps while it's
> issuing large io, and the device is deleted. The user thread will
> wait for a long time for io to return.
> 
> Signed-off-by: Yu Kuai <yukuai3@xxxxxxxxxx>
> ---
> Changes in v8:
>  - fold two patches into one
> Changes in v7:
>  - use the new solution as suggested by Ming.
> 
>  block/blk-throttle.c | 49 ++++++++++++++++++++++++++++++++++++++++----
>  block/blk-throttle.h |  2 ++
>  block/genhd.c        |  2 ++
>  3 files changed, 49 insertions(+), 4 deletions(-)
> 
> diff --git a/block/blk-throttle.c b/block/blk-throttle.c
> index 7c462c006b26..557d20796157 100644
> --- a/block/blk-throttle.c
> +++ b/block/blk-throttle.c
> @@ -43,8 +43,12 @@
>  static struct workqueue_struct *kthrotld_workqueue;
>  
>  enum tg_state_flags {
> -	THROTL_TG_PENDING	= 1 << 0,	/* on parent's pending tree */
> -	THROTL_TG_WAS_EMPTY	= 1 << 1,	/* bio_lists[] became non-empty */
> +	/* on parent's pending tree */
> +	THROTL_TG_PENDING	= 1 << 0,
> +	/* bio_lists[] became non-empty */
> +	THROTL_TG_WAS_EMPTY	= 1 << 1,
> +	/* starts to cancel all bios, will be set if the disk is deleted */
> +	THROTL_TG_CANCELING	= 1 << 2,
>  };
>  
>  #define rb_entry_tg(node)	rb_entry((node), struct throtl_grp, rb_node)
> @@ -871,7 +875,8 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio,
>  	       bio != throtl_peek_queued(&tg->service_queue.queued[rw]));
>  
>  	/* If tg->bps = -1, then BW is unlimited */
> -	if (bps_limit == U64_MAX && iops_limit == UINT_MAX) {
> +	if ((bps_limit == U64_MAX && iops_limit == UINT_MAX) ||
> +	    tg->flags & THROTL_TG_CANCELING) {
>  		if (wait)
>  			*wait = 0;
>  		return true;
> @@ -974,6 +979,9 @@ static void tg_update_disptime(struct throtl_grp *tg)
>  	unsigned long read_wait = -1, write_wait = -1, min_wait = -1, disptime;
>  	struct bio *bio;
>  
> +	if (tg->flags & THROTL_TG_CANCELING)
> +		goto update;
> +
>  	bio = throtl_peek_queued(&sq->queued[READ]);
>  	if (bio)
>  		tg_may_dispatch(tg, bio, &read_wait);
> @@ -983,9 +991,10 @@ static void tg_update_disptime(struct throtl_grp *tg)
>  		tg_may_dispatch(tg, bio, &write_wait);
>  
>  	min_wait = min(read_wait, write_wait);
> -	disptime = jiffies + min_wait;
>  
> +update:
>  	/* Update dispatch time */
> +	disptime = jiffies + min_wait;

As I mentioned on V7, the change in tg_update_disptime() isn't needed, please
drop it.

>  	throtl_dequeue_tg(tg);
>  	tg->disptime = disptime;
>  	throtl_enqueue_tg(tg);
> @@ -1763,6 +1772,38 @@ static bool throtl_hierarchy_can_upgrade(struct throtl_grp *tg)
>  	return false;
>  }
>  
> +void blk_throtl_cancel_bios(struct request_queue *q)
> +{
> +	struct cgroup_subsys_state *pos_css;
> +	struct blkcg_gq *blkg;
> +
> +	spin_lock_irq(&q->queue_lock);
> +	/*
> +	 * queue_lock is held, rcu lock is not needed here technically.
> +	 * However, rcu lock is still held to emphasize that following
> +	 * path need RCU protection and to prevent warning from lockdep.
> +	 */
> +	rcu_read_lock();
> +	blkg_for_each_descendant_post(blkg, pos_css, q->root_blkg) {
> +		struct throtl_grp *tg = blkg_to_tg(blkg);
> +		struct throtl_service_queue *sq = &tg->service_queue;
> +
> +		/*
> +		 * Set disptime in the past to make sure
> +		 * throtl_select_dispatch() won't exit without dispatching.
> +		 */
> +		tg->disptime = jiffies - 1;

It might be better to replace the above line with tg_update_disptime().

Otherwise, the patch looks good.

Thanks,
Ming