When all CPUs in one hctx are offline, we shouldn't run this hw queue
for completing request any more.

So steal bios from the request, and resubmit them, and finally free
the request in blk_mq_hctx_notify_dead().

Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Thomas Gleixner <redacted>
Cc: Keith Busch <redacted>
Signed-off-by: Ming Lei <redacted>
---
 block/blk-mq.c | 48 +++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 41 insertions(+), 7 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 6931b2ba2776..ed334fd867c4 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c

@@ -2261,10 +2261,30 @@ static int blk_mq_hctx_notify_online(unsigned int cpu, struct hlist_node *node)
 	return 0;
 }
 
+static void blk_mq_resubmit_io(struct request *rq)
+{
+	struct bio_list list;
+	struct bio *bio;
+
+	bio_list_init(&list);
+	blk_steal_bios(&list, rq);
+
+	while (true) {
+		bio = bio_list_pop(&list);
+		if (!bio)
+			break;
+
+		generic_make_request(bio);
+	}
+
+	blk_mq_cleanup_rq(rq);
+	blk_mq_end_request(rq, 0);
+}
+
 /*
- * 'cpu' is going away. splice any existing rq_list entries from this
- * software queue to the hw queue dispatch list, and ensure that it
- * gets run.
+ * 'cpu' has gone away. If this hctx is dead, we can't dispatch request
+ * to the hctx any more, so steal bios from requests of this hctx, and
+ * re-submit them to the request queue, and free these requests finally.
  */
 static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node)
 {

@@ -2272,6 +2292,8 @@ static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node)
 	struct blk_mq_ctx *ctx;
 	LIST_HEAD(tmp);
 	enum hctx_type type;
+	bool hctx_dead;
+	struct request *rq;
 
 	hctx = hlist_entry_safe(node, struct blk_mq_hw_ctx, cpuhp_dead);
 	ctx = __blk_mq_get_ctx(hctx->queue, cpu);

@@ -2279,6 +2301,9 @@ static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node)
 
 	clear_bit(BLK_MQ_S_INTERNAL_STOPPED, &hctx->state);
 
+	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);

@@ -2289,11 +2314,20 @@ static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node)
 	if (list_empty(&tmp))
 		return 0;
 
-	spin_lock(&hctx->lock);
-	list_splice_tail_init(&tmp, &hctx->dispatch);
-	spin_unlock(&hctx->lock);
+	if (!hctx_dead) {
+		spin_lock(&hctx->lock);
+		list_splice_tail_init(&tmp, &hctx->dispatch);
+		spin_unlock(&hctx->lock);
+		blk_mq_run_hw_queue(hctx, true);
+		return 0;
+	}
+
+	while (!list_empty(&tmp)) {
+		rq = list_entry(tmp.next, struct request, queuelist);
+		list_del_init(&rq->queuelist);
+		blk_mq_resubmit_io(rq);
+	}
 
-	blk_mq_run_hw_queue(hctx, true);
 	return 0;
 }