[RFC PATCH 7/7] blk-mq: handle requests dispatched from IO scheduler in case that hctx is dead

From: Ming Lei <ming.lei@redhat.com>
To: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org,
	"James E . J . Bottomley" <jejb@linux.ibm.com>,
	"Martin K . Petersen" <martin.petersen@oracle.com>,
	linux-scsi@vger.kernel.org, Ming Lei <ming.lei@redhat.com>,
	Bart Van Assche <bvanassche@acm.org>,
	Hannes Reinecke <hare@suse.com>, Christoph Hellwig <hch@lst.de>,
	Thomas Gleixner <tglx@linutronix.de>,
	Keith Busch <keith.busch@intel.com>
Subject: [RFC PATCH 7/7] blk-mq: handle requests dispatched from IO scheduler in case that hctx is dead
Date: Fri, 12 Jul 2019 10:47:26 +0800	[thread overview]
Message-ID: <20190712024726.1227-8-ming.lei@redhat.com> (raw)
In-Reply-To: <20190712024726.1227-1-ming.lei@redhat.com>

If hctx becomes dead, all in-queue IO requests aimed at this hctx have to
be re-submitted, so cover requests queued in scheduler queue.

Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Keith Busch <keith.busch@intel.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
---
 block/blk-mq.c | 30 +++++++++++++++++++++++++-----
 1 file changed, 25 insertions(+), 5 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index e4588d30840c..3ad1944a8e70 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2298,6 +2298,7 @@ static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node)
 	enum hctx_type type;
 	bool hctx_dead;
 	struct request *rq;
+	struct elevator_queue *e;
 
 	hctx = hlist_entry_safe(node, struct blk_mq_hw_ctx, cpuhp_dead);
 	ctx = __blk_mq_get_ctx(hctx->queue, cpu);
@@ -2309,12 +2310,31 @@ static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node)
 	hctx_dead = cpumask_first_and(hctx->cpumask, cpu_online_mask) >=
 		nr_cpu_ids;
 
-	spin_lock(&ctx->lock);
-	if (!list_empty(&ctx->rq_lists[type])) {
-		list_splice_init(&ctx->rq_lists[type], &tmp);
-		blk_mq_hctx_clear_pending(hctx, ctx);
+	e = hctx->queue->elevator;
+	if (!e) {
+		spin_lock(&ctx->lock);
+		if (!list_empty(&ctx->rq_lists[type])) {
+			list_splice_init(&ctx->rq_lists[type], &tmp);
+			blk_mq_hctx_clear_pending(hctx, ctx);
+		}
+		spin_unlock(&ctx->lock);
+	} else if (hctx_dead) {
+		LIST_HEAD(sched_tmp);
+
+		while ((rq = e->type->ops.dispatch_request(hctx))) {
+			if (rq->mq_hctx != hctx)
+				list_add(&rq->queuelist, &sched_tmp);
+			else
+				list_add(&rq->queuelist, &tmp);
+		}
+
+		while (!list_empty(&sched_tmp)) {
+			rq = list_entry(sched_tmp.next, struct request,
+					queuelist);
+			list_del_init(&rq->queuelist);
+			blk_mq_sched_insert_request(rq, true, true, true);
+		}
 	}
-	spin_unlock(&ctx->lock);
 
 	if (list_empty(&tmp))
 		return 0;
-- 
2.20.1

