1 files changed, 295 insertions, 112 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index a7785df2c944..9a36ac1c1fa1 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -26,6 +26,7 @@
 #include <linux/delay.h>
 #include <linux/crash_dump.h>
 #include <linux/prefetch.h>
+#include <linux/blk-crypto.h>
 
 #include <trace/events/block.h>
 
@@ -270,14 +271,14 @@ static inline bool blk_mq_need_time_stamp(struct request *rq)
 }
 
 static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
-		unsigned int tag, unsigned int op, u64 alloc_time_ns)
+		unsigned int tag, u64 alloc_time_ns)
 {
 	struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
 	struct request *rq = tags->static_rqs[tag];
 	req_flags_t rq_flags = 0;
 
 	if (data->flags & BLK_MQ_REQ_INTERNAL) {
-		rq->tag = -1;
+		rq->tag = BLK_MQ_NO_TAG;
 		rq->internal_tag = tag;
 	} else {
 		if (data->hctx->flags & BLK_MQ_F_TAG_SHARED) {
@@ -285,7 +286,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 			atomic_inc(&data->hctx->nr_active);
 		}
 		rq->tag = tag;
-		rq->internal_tag = -1;
+		rq->internal_tag = BLK_MQ_NO_TAG;
 		data->hctx->tags->rqs[rq->tag] = rq;
 	}
 
@@ -294,7 +295,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 	rq->mq_ctx = data->ctx;
 	rq->mq_hctx = data->hctx;
 	rq->rq_flags = rq_flags;
-	rq->cmd_flags = op;
+	rq->cmd_flags = data->cmd_flags;
 	if (data->flags & BLK_MQ_REQ_PREEMPT)
 		rq->rq_flags |= RQF_PREEMPT;
 	if (blk_queue_io_stat(data->q))
@@ -317,8 +318,8 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 	rq->nr_integrity_segments = 0;
 #endif
+	blk_crypto_rq_set_defaults(rq);
 	/* tag was already set */
-	rq->extra_len = 0;
 	WRITE_ONCE(rq->deadline, 0);
 
 	rq->timeout = 0;
@@ -326,35 +327,37 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 	rq->end_io = NULL;
 	rq->end_io_data = NULL;
 
-	data->ctx->rq_dispatched[op_is_sync(op)]++;
+	data->ctx->rq_dispatched[op_is_sync(data->cmd_flags)]++;
 	refcount_set(&rq->ref, 1);
+
+	if (!op_is_flush(data->cmd_flags)) {
+		struct elevator_queue *e = data->q->elevator;
+
+		rq->elv.icq = NULL;
+		if (e && e->type->ops.prepare_request) {
+			if (e->type->icq_cache)
+				blk_mq_sched_assign_ioc(rq);
+
+			e->type->ops.prepare_request(rq);
+			rq->rq_flags |= RQF_ELVPRIV;
+		}
+	}
+
+	data->hctx->queued++;
 	return rq;
 }
 
-static struct request *blk_mq_get_request(struct request_queue *q,
-					  struct bio *bio,
-					  struct blk_mq_alloc_data *data)
+static struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data)
 {
+	struct request_queue *q = data->q;
 	struct elevator_queue *e = q->elevator;
-	struct request *rq;
-	unsigned int tag;
-	bool clear_ctx_on_error = false;
 	u64 alloc_time_ns = 0;
-
-	blk_queue_enter_live(q);
+	unsigned int tag;
 
 	/* alloc_time includes depth and tag waits */
 	if (blk_queue_rq_alloc_time(q))
 		alloc_time_ns = ktime_get_ns();
 
-	data->q = q;
-	if (likely(!data->ctx)) {
-		data->ctx = blk_mq_get_ctx(q);
-		clear_ctx_on_error = true;
-	}
-	if (likely(!data->hctx))
-		data->hctx = blk_mq_map_queue(q, data->cmd_flags,
-						data->ctx);
 	if (data->cmd_flags & REQ_NOWAIT)
 		data->flags |= BLK_MQ_REQ_NOWAIT;
 
@@ -370,37 +373,43 @@ static struct request *blk_mq_get_request(struct request_queue *q,
 		    e->type->ops.limit_depth &&
 		    !(data->flags & BLK_MQ_REQ_RESERVED))
 			e->type->ops.limit_depth(data->cmd_flags, data);
-	} else {
-		blk_mq_tag_busy(data->hctx);
 	}
 
-	tag = blk_mq_get_tag(data);
-	if (tag == BLK_MQ_TAG_FAIL) {
-		if (clear_ctx_on_error)
-			data->ctx = NULL;
-		blk_queue_exit(q);
-		return NULL;
-	}
+retry:
+	data->ctx = blk_mq_get_ctx(q);
+	data->hctx = blk_mq_map_queue(q, data->cmd_flags, data->ctx);
+	if (!(data->flags & BLK_MQ_REQ_INTERNAL))
+		blk_mq_tag_busy(data->hctx);
 
-	rq = blk_mq_rq_ctx_init(data, tag, data->cmd_flags, alloc_time_ns);
-	if (!op_is_flush(data->cmd_flags)) {
-		rq->elv.icq = NULL;
-		if (e && e->type->ops.prepare_request) {
-			if (e->type->icq_cache)
-				blk_mq_sched_assign_ioc(rq);
+	/*
+	 * Waiting allocations only fail because of an inactive hctx.  In that
+	 * case just retry the hctx assignment and tag allocation as CPU hotplug
+	 * should have migrated us to an online CPU by now.
+	 */
+	tag = blk_mq_get_tag(data);
+	if (tag == BLK_MQ_NO_TAG) {
+		if (data->flags & BLK_MQ_REQ_NOWAIT)
+			return NULL;
 
-			e->type->ops.prepare_request(rq, bio);
-			rq->rq_flags |= RQF_ELVPRIV;
-		}
+		/*
+		 * Give up the CPU and sleep for a random short time to ensure
+		 * that thread using a realtime scheduling class are migrated
+		 * off the the CPU, and thus off the hctx that is going away.
+		 */
+		msleep(3);
+		goto retry;
 	}
-	data->hctx->queued++;
-	return rq;
+	return blk_mq_rq_ctx_init(data, tag, alloc_time_ns);
 }
 
 struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
 		blk_mq_req_flags_t flags)
 {
-	struct blk_mq_alloc_data alloc_data = { .flags = flags, .cmd_flags = op };
+	struct blk_mq_alloc_data data = {
+		.q		= q,
+		.flags		= flags,
+		.cmd_flags	= op,
+	};
 	struct request *rq;
 	int ret;
 
@@ -408,34 +417,43 @@ struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
 	if (ret)
 		return ERR_PTR(ret);
 
-	rq = blk_mq_get_request(q, NULL, &alloc_data);
-	blk_queue_exit(q);
-
+	rq = __blk_mq_alloc_request(&data);
 	if (!rq)
-		return ERR_PTR(-EWOULDBLOCK);
-
+		goto out_queue_exit;
 	rq->__data_len = 0;
 	rq->__sector = (sector_t) -1;
 	rq->bio = rq->biotail = NULL;
 	return rq;
+out_queue_exit:
+	blk_queue_exit(q);
+	return ERR_PTR(-EWOULDBLOCK);
 }
 EXPORT_SYMBOL(blk_mq_alloc_request);
 
 struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 	unsigned int op, blk_mq_req_flags_t flags, unsigned int hctx_idx)
 {
-	struct blk_mq_alloc_data alloc_data = { .flags = flags, .cmd_flags = op };
-	struct request *rq;
+	struct blk_mq_alloc_data data = {
+		.q		= q,
+		.flags		= flags,
+		.cmd_flags	= op,
+	};
+	u64 alloc_time_ns = 0;
 	unsigned int cpu;
+	unsigned int tag;
 	int ret;
 
+	/* alloc_time includes depth and tag waits */
+	if (blk_queue_rq_alloc_time(q))
+		alloc_time_ns = ktime_get_ns();
+
 	/*
 	 * If the tag allocator sleeps we could get an allocation for a
 	 * different hardware context.  No need to complicate the low level
 	 * allocator for this for the rare use case of a command tied to
 	 * a specific queue.
 	 */
-	if (WARN_ON_ONCE(!(flags & BLK_MQ_REQ_NOWAIT)))
+	if (WARN_ON_ONCE(!(flags & (BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_RESERVED))))
 		return ERR_PTR(-EINVAL);
 
 	if (hctx_idx >= q->nr_hw_queues)
@@ -449,21 +467,27 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 	 * Check if the hardware context is actually mapped to anything.
 	 * If not tell the caller that it should skip this queue.
 	 */
-	alloc_data.hctx = q->queue_hw_ctx[hctx_idx];
-	if (!blk_mq_hw_queue_mapped(alloc_data.hctx)) {
-		blk_queue_exit(q);
-		return ERR_PTR(-EXDEV);
-	}
-	cpu = cpumask_first_and(alloc_data.hctx->cpumask, cpu_online_mask);
-	alloc_data.ctx = __blk_mq_get_ctx(q, cpu);
-
-	rq = blk_mq_get_request(q, NULL, &alloc_data);
-	blk_queue_exit(q);
+	ret = -EXDEV;
+	data.hctx = q->queue_hw_ctx[hctx_idx];
+	if (!blk_mq_hw_queue_mapped(data.hctx))
+		goto out_queue_exit;
+	cpu = cpumask_first_and(data.hctx->cpumask, cpu_online_mask);
+	data.ctx = __blk_mq_get_ctx(q, cpu);
+
+	if (q->elevator)
+		data.flags |= BLK_MQ_REQ_INTERNAL;
+	else
+		blk_mq_tag_busy(data.hctx);
 
-	if (!rq)
-		return ERR_PTR(-EWOULDBLOCK);
+	ret = -EWOULDBLOCK;
+	tag = blk_mq_get_tag(&data);
+	if (tag == BLK_MQ_NO_TAG)
+		goto out_queue_exit;
+	return blk_mq_rq_ctx_init(&data, tag, alloc_time_ns);
 
-	return rq;
+out_queue_exit:
+	blk_queue_exit(q);
+	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx);
 
@@ -474,11 +498,12 @@ static void __blk_mq_free_request(struct request *rq)
 	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
 	const int sched_tag = rq->internal_tag;
 
+	blk_crypto_free_request(rq);
 	blk_pm_mark_last_busy(rq);
 	rq->mq_hctx = NULL;
-	if (rq->tag != -1)
+	if (rq->tag != BLK_MQ_NO_TAG)
 		blk_mq_put_tag(hctx->tags, ctx, rq->tag);
-	if (sched_tag != -1)
+	if (sched_tag != BLK_MQ_NO_TAG)
 		blk_mq_put_tag(hctx->sched_tags, ctx, sched_tag);
 	blk_mq_sched_restart(hctx);
 	blk_queue_exit(q);
@@ -527,7 +552,7 @@ inline void __blk_mq_end_request(struct request *rq, blk_status_t error)
 		blk_stat_add(rq, now);
 	}
 
-	if (rq->internal_tag != -1)
+	if (rq->internal_tag != BLK_MQ_NO_TAG)
 		blk_mq_sched_completed_request(rq, now);
 
 	blk_account_io_done(rq, now);
@@ -557,7 +582,17 @@ static void __blk_mq_complete_request_remote(void *data)
 	q->mq_ops->complete(rq);
 }
 
-static void __blk_mq_complete_request(struct request *rq)
+/**
+ * blk_mq_force_complete_rq() - Force complete the request, bypassing any error
+ * 				injection that could drop the completion.
+ * @rq: Request to be force completed
+ *
+ * Drivers should use blk_mq_complete_request() to complete requests in their
+ * normal IO path. For timeout error recovery, drivers may call this forced
+ * completion routine after they've reclaimed timed out requests to bypass
+ * potentially subsequent fake timeouts.
+ */
+void blk_mq_force_complete_rq(struct request *rq)
 {
 	struct blk_mq_ctx *ctx = rq->mq_ctx;
 	struct request_queue *q = rq->q;
@@ -603,6 +638,7 @@ static void __blk_mq_complete_request(struct request *rq)
 	}
 	put_cpu();
 }
+EXPORT_SYMBOL_GPL(blk_mq_force_complete_rq);
 
 static void hctx_unlock(struct blk_mq_hw_ctx *hctx, int srcu_idx)
 	__releases(hctx->srcu)
@@ -636,7 +672,7 @@ bool blk_mq_complete_request(struct request *rq)
 {
 	if (unlikely(blk_should_fake_timeout(rq->q)))
 		return false;
-	__blk_mq_complete_request(rq);
+	blk_mq_force_complete_rq(rq);
 	return true;
 }
 EXPORT_SYMBOL(blk_mq_complete_request);
@@ -667,15 +703,6 @@ void blk_mq_start_request(struct request *rq)
 	blk_add_timer(rq);
 	WRITE_ONCE(rq->state, MQ_RQ_IN_FLIGHT);
 
-	if (q->dma_drain_size && blk_rq_bytes(rq)) {
-		/*
-		 * Make sure space for the drain appears.  We know we can do
-		 * this because max_hw_segments has been adjusted to be one
-		 * fewer than the device can handle.
-		 */
-		rq->nr_phys_segments++;
-	}
-
 #ifdef CONFIG_BLK_DEV_INTEGRITY
 	if (blk_integrity_rq(rq) && req_op(rq) == REQ_OP_WRITE)
 		q->integrity.profile->prepare_fn(rq);
@@ -695,8 +722,6 @@ static void __blk_mq_requeue_request(struct request *rq)
 	if (blk_mq_request_started(rq)) {
 		WRITE_ONCE(rq->state, MQ_RQ_IDLE);
 		rq->rq_flags &= ~RQF_TIMED_OUT;
-		if (q->dma_drain_size && blk_rq_bytes(rq))
-			rq->nr_phys_segments--;
 	}
 }
 
@@ -1037,7 +1062,7 @@ bool blk_mq_get_driver_tag(struct request *rq)
 	};
 	bool shared;
 
-	if (rq->tag != -1)
+	if (rq->tag != BLK_MQ_NO_TAG)
 		return true;
 
 	if (blk_mq_tag_is_reserved(data.hctx->sched_tags, rq->internal_tag))
@@ -1053,7 +1078,7 @@ bool blk_mq_get_driver_tag(struct request *rq)
 		data.hctx->tags->rqs[rq->tag] = rq;
 	}
 
-	return rq->tag != -1;
+	return rq->tag != BLK_MQ_NO_TAG;
 }
 
 static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode,
@@ -1195,6 +1220,19 @@ static void blk_mq_handle_dev_resource(struct request *rq,
 	__blk_mq_requeue_request(rq);
 }
 
+static void blk_mq_handle_zone_resource(struct request *rq,
+					struct list_head *zone_list)
+{
+	/*
+	 * If we end up here it is because we cannot dispatch a request to a
+	 * specific zone due to LLD level zone-write locking or other zone
+	 * related resource not being available. In this case, set the request
+	 * aside in zone_list for retrying it later.
+	 */
+	list_add(&rq->queuelist, zone_list);
+	__blk_mq_requeue_request(rq);
+}
+
 /*
  * Returns true if we did some work AND can potentially do more.
  */
@@ -1206,6 +1244,8 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 	bool no_tag = false;
 	int errors, queued;
 	blk_status_t ret = BLK_STS_OK;
+	bool no_budget_avail = false;
+	LIST_HEAD(zone_list);
 
 	if (list_empty(list))
 		return false;
@@ -1224,6 +1264,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 		hctx = rq->mq_hctx;
 		if (!got_budget && !blk_mq_get_dispatch_budget(hctx)) {
 			blk_mq_put_driver_tag(rq);
+			no_budget_avail = true;
 			break;
 		}
 
@@ -1266,6 +1307,16 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 		if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) {
 			blk_mq_handle_dev_resource(rq, list);
 			break;
+		} else if (ret == BLK_STS_ZONE_RESOURCE) {
+			/*
+			 * Move the request to zone_list and keep going through
+			 * the dispatch list to find more requests the drive can
+			 * accept.
+			 */
+			blk_mq_handle_zone_resource(rq, &zone_list);
+			if (list_empty(list))
+				break;
+			continue;
 		}
 
 		if (unlikely(ret != BLK_STS_OK)) {
@@ -1277,6 +1328,9 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 		queued++;
 	} while (!list_empty(list));
 
+	if (!list_empty(&zone_list))
+		list_splice_tail_init(&zone_list, list);
+
 	hctx->dispatched[queued_to_index(queued)]++;
 
 	/*
@@ -1320,13 +1374,15 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 		 *
 		 * If driver returns BLK_STS_RESOURCE and SCHED_RESTART
 		 * bit is set, run queue after a delay to avoid IO stalls
-		 * that could otherwise occur if the queue is idle.
+		 * that could otherwise occur if the queue is idle.  We'll do
+		 * similar if we couldn't get budget and SCHED_RESTART is set.
 		 */
 		needs_restart = blk_mq_sched_needs_restart(hctx);
 		if (!needs_restart ||
 		    (no_tag && list_empty_careful(&hctx->dispatch_wait.entry)))
 			blk_mq_run_hw_queue(hctx, true);
-		else if (needs_restart && (ret == BLK_STS_RESOURCE))
+		else if (needs_restart && (ret == BLK_STS_RESOURCE ||
+					   no_budget_avail))
 			blk_mq_delay_run_hw_queue(hctx, BLK_MQ_RESOURCE_DELAY);
 
 		blk_mq_update_dispatch_busy(hctx, true);
@@ -1542,6 +1598,25 @@ void blk_mq_run_hw_queues(struct request_queue *q, bool async)
 EXPORT_SYMBOL(blk_mq_run_hw_queues);
 
 /**
+ * blk_mq_delay_run_hw_queues - Run all hardware queues asynchronously.
+ * @q: Pointer to the request queue to run.
+ * @msecs: Microseconds of delay to wait before running the queues.
+ */
+void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs)
+{
+	struct blk_mq_hw_ctx *hctx;
+	int i;
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		if (blk_mq_hctx_stopped(hctx))
+			continue;
+
+		blk_mq_delay_run_hw_queue(hctx, msecs);
+	}
+}
+EXPORT_SYMBOL(blk_mq_delay_run_hw_queues);
+
+/**
  * blk_mq_queue_stopped() - check whether one or more hctxs have been stopped
  * @q: request queue.
  *
@@ -1782,8 +1857,9 @@ static void blk_mq_bio_to_request(struct request *rq, struct bio *bio,
 	rq->__sector = bio->bi_iter.bi_sector;
 	rq->write_hint = bio->bi_write_hint;
 	blk_rq_bio_prep(rq, bio, nr_segs);
+	blk_crypto_rq_bio_prep(rq, bio, GFP_NOIO);
 
-	blk_account_io_start(rq, true);
+	blk_account_io_start(rq);
 }
 
 static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx,
@@ -1973,39 +2049,42 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq)
  *
  * Returns: Request queue cookie.
  */
-static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
+blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 {
 	const int is_sync = op_is_sync(bio->bi_opf);
 	const int is_flush_fua = op_is_flush(bio->bi_opf);
-	struct blk_mq_alloc_data data = { .flags = 0};
+	struct blk_mq_alloc_data data = {
+		.q		= q,
+	};
 	struct request *rq;
 	struct blk_plug *plug;
 	struct request *same_queue_rq = NULL;
 	unsigned int nr_segs;
 	blk_qc_t cookie;
+	blk_status_t ret;
 
 	blk_queue_bounce(q, &bio);
 	__blk_queue_split(q, &bio, &nr_segs);
 
 	if (!bio_integrity_prep(bio))
-		return BLK_QC_T_NONE;
+		goto queue_exit;
 
 	if (!is_flush_fua && !blk_queue_nomerges(q) &&
 	    blk_attempt_plug_merge(q, bio, nr_segs, &same_queue_rq))
-		return BLK_QC_T_NONE;
+		goto queue_exit;
 
 	if (blk_mq_sched_bio_merge(q, bio, nr_segs))
-		return BLK_QC_T_NONE;
+		goto queue_exit;
 
 	rq_qos_throttle(q, bio);
 
 	data.cmd_flags = bio->bi_opf;
-	rq = blk_mq_get_request(q, bio, &data);
+	rq = __blk_mq_alloc_request(&data);
 	if (unlikely(!rq)) {
 		rq_qos_cleanup(q, bio);
 		if (bio->bi_opf & REQ_NOWAIT)
 			bio_wouldblock_error(bio);
-		return BLK_QC_T_NONE;
+		goto queue_exit;
 	}
 
 	trace_block_getrq(q, bio, bio->bi_opf);
@@ -2016,6 +2095,14 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 
 	blk_mq_bio_to_request(rq, bio, nr_segs);
 
+	ret = blk_crypto_init_request(rq);
+	if (ret != BLK_STS_OK) {
+		bio->bi_status = ret;
+		bio_endio(bio);
+		blk_mq_free_request(rq);
+		return BLK_QC_T_NONE;
+	}
+
 	plug = blk_mq_plug(q, bio);
 	if (unlikely(is_flush_fua)) {
 		/* Bypass scheduler for flush requests */
@@ -2084,7 +2171,11 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	}
 
 	return cookie;
+queue_exit:
+	blk_queue_exit(q);
+	return BLK_QC_T_NONE;
 }
+EXPORT_SYMBOL_GPL(blk_mq_make_request); /* only for request based dm */
 
 void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
 		     unsigned int hctx_idx)
@@ -2260,6 +2351,86 @@ fail:
 	return -ENOMEM;
 }
 
+struct rq_iter_data {
+	struct blk_mq_hw_ctx *hctx;
+	bool has_rq;
+};
+
+static bool blk_mq_has_request(struct request *rq, void *data, bool reserved)
+{
+	struct rq_iter_data *iter_data = data;
+
+	if (rq->mq_hctx != iter_data->hctx)
+		return true;
+	iter_data->has_rq = true;
+	return false;
+}
+
+static bool blk_mq_hctx_has_requests(struct blk_mq_hw_ctx *hctx)
+{
+	struct blk_mq_tags *tags = hctx->sched_tags ?
+			hctx->sched_tags : hctx->tags;
+	struct rq_iter_data data = {
+		.hctx	= hctx,
+	};
+
+	blk_mq_all_tag_iter(tags, blk_mq_has_request, &data);
+	return data.has_rq;
+}
+
+static inline bool blk_mq_last_cpu_in_hctx(unsigned int cpu,
+		struct blk_mq_hw_ctx *hctx)
+{
+	if (cpumask_next_and(-1, hctx->cpumask, cpu_online_mask) != cpu)
+		return false;
+	if (cpumask_next_and(cpu, hctx->cpumask, cpu_online_mask) < nr_cpu_ids)
+		return false;
+	return true;
+}
+
+static int blk_mq_hctx_notify_offline(unsigned int cpu, struct hlist_node *node)
+{
+	struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node,
+			struct blk_mq_hw_ctx, cpuhp_online);
+
+	if (!cpumask_test_cpu(cpu, hctx->cpumask) ||
+	    !blk_mq_last_cpu_in_hctx(cpu, hctx))
+		return 0;
+
+	/*
+	 * Prevent new request from being allocated on the current hctx.
+	 *
+	 * The smp_mb__after_atomic() Pairs with the implied barrier in
+	 * test_and_set_bit_lock in sbitmap_get().  Ensures the inactive flag is
+	 * seen once we return from the tag allocator.
+	 */
+	set_bit(BLK_MQ_S_INACTIVE, &hctx->state);
+	smp_mb__after_atomic();
+
+	/*
+	 * Try to grab a reference to the queue and wait for any outstanding
+	 * requests.  If we could not grab a reference the queue has been
+	 * frozen and there are no requests.
+	 */
+	if (percpu_ref_tryget(&hctx->queue->q_usage_counter)) {
+		while (blk_mq_hctx_has_requests(hctx))
+			msleep(5);
+		percpu_ref_put(&hctx->queue->q_usage_counter);
+	}
+
+	return 0;
+}
+
+static int blk_mq_hctx_notify_online(unsigned int cpu, struct hlist_node *node)
+{
+	struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node,
+			struct blk_mq_hw_ctx, cpuhp_online);
+
+	if (cpumask_test_cpu(cpu, hctx->cpumask))
+		clear_bit(BLK_MQ_S_INACTIVE, &hctx->state);
+	return 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
@@ -2273,6 +2444,9 @@ static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node)
 	enum hctx_type type;
 
 	hctx = hlist_entry_safe(node, struct blk_mq_hw_ctx, cpuhp_dead);
+	if (!cpumask_test_cpu(cpu, hctx->cpumask))
+		return 0;
+
 	ctx = __blk_mq_get_ctx(hctx->queue, cpu);
 	type = hctx->type;
 
@@ -2296,6 +2470,9 @@ static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node)
 
 static void blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx)
 {
+	if (!(hctx->flags & BLK_MQ_F_STACKING))
+		cpuhp_state_remove_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE,
+						    &hctx->cpuhp_online);
 	cpuhp_state_remove_instance_nocalls(CPUHP_BLK_MQ_DEAD,
 					    &hctx->cpuhp_dead);
 }
@@ -2355,6 +2532,9 @@ static int blk_mq_init_hctx(struct request_queue *q,
 {
 	hctx->queue_num = hctx_idx;
 
+	if (!(hctx->flags & BLK_MQ_F_STACKING))
+		cpuhp_state_add_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE,
+				&hctx->cpuhp_online);
 	cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead);
 
 	hctx->tags = set->tags[hctx_idx];
@@ -2473,7 +2653,8 @@ static void blk_mq_init_cpu_queues(struct request_queue *q,
 	}
 }
 
-static bool __blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, int hctx_idx)
+static bool __blk_mq_alloc_map_and_request(struct blk_mq_tag_set *set,
+					int hctx_idx)
 {
 	int ret = 0;
 
@@ -2521,18 +2702,6 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 	 * If the cpu isn't present, the cpu is mapped to first hctx.
 	 */
 	for_each_possible_cpu(i) {
-		hctx_idx = set->map[HCTX_TYPE_DEFAULT].mq_map[i];
-		/* unmapped hw queue can be remapped after CPU topo changed */
-		if (!set->tags[hctx_idx] &&
-		    !__blk_mq_alloc_rq_map(set, hctx_idx)) {
-			/*
-			 * If tags initialization fail for some hctx,
-			 * that hctx won't be brought online.  In this
-			 * case, remap the current ctx to hctx[0] which
-			 * is guaranteed to always have tags allocated
-			 */
-			set->map[HCTX_TYPE_DEFAULT].mq_map[i] = 0;
-		}
 
 		ctx = per_cpu_ptr(q->queue_ctx, i);
 		for (j = 0; j < set->nr_maps; j++) {
@@ -2541,6 +2710,18 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 						HCTX_TYPE_DEFAULT, i);
 				continue;
 			}
+			hctx_idx = set->map[j].mq_map[i];
+			/* unmapped hw queue can be remapped after CPU topo changed */
+			if (!set->tags[hctx_idx] &&
+			    !__blk_mq_alloc_map_and_request(set, hctx_idx)) {
+				/*
+				 * If tags initialization fail for some hctx,
+				 * that hctx won't be brought online.  In this
+				 * case, remap the current ctx to hctx[0] which
+				 * is guaranteed to always have tags allocated
+				 */
+				set->map[j].mq_map[i] = 0;
+			}
 
 			hctx = blk_mq_map_queue_type(q, j, i);
 			ctx->hctxs[j] = hctx;
@@ -2944,7 +3125,6 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	INIT_LIST_HEAD(&q->requeue_list);
 	spin_lock_init(&q->requeue_lock);
 
-	q->make_request_fn = blk_mq_make_request;
 	q->nr_requests = set->queue_depth;
 
 	/*
@@ -2988,14 +3168,14 @@ static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
 	int i;
 
 	for (i = 0; i < set->nr_hw_queues; i++)
-		if (!__blk_mq_alloc_rq_map(set, i))
+		if (!__blk_mq_alloc_map_and_request(set, i))
 			goto out_unwind;
 
 	return 0;
 
 out_unwind:
 	while (--i >= 0)
-		blk_mq_free_rq_map(set->tags[i]);
+		blk_mq_free_map_and_requests(set, i);
 
 	return -ENOMEM;
 }
@@ -3005,7 +3185,7 @@ out_unwind:
  * may reduce the depth asked for, if memory is tight. set->queue_depth
  * will be updated to reflect the allocated depth.
  */
-static int blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
+static int blk_mq_alloc_map_and_requests(struct blk_mq_tag_set *set)
 {
 	unsigned int depth;
 	int err;
@@ -3165,7 +3345,7 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 	if (ret)
 		goto out_free_mq_map;
 
-	ret = blk_mq_alloc_rq_maps(set);
+	ret = blk_mq_alloc_map_and_requests(set);
 	if (ret)
 		goto out_free_mq_map;
 
@@ -3347,14 +3527,14 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 		blk_mq_sysfs_unregister(q);
 	}
 
+	prev_nr_hw_queues = set->nr_hw_queues;
 	if (blk_mq_realloc_tag_set_tags(set, set->nr_hw_queues, nr_hw_queues) <
 	    0)
 		goto reregister;
 
-	prev_nr_hw_queues = set->nr_hw_queues;
 	set->nr_hw_queues = nr_hw_queues;
-	blk_mq_update_queue_map(set);
 fallback:
+	blk_mq_update_queue_map(set);
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
 		blk_mq_realloc_hw_ctxs(set, q);
 		if (q->nr_hw_queues != set->nr_hw_queues) {
@@ -3609,6 +3789,9 @@ static int __init blk_mq_init(void)
 {
 	cpuhp_setup_state_multi(CPUHP_BLK_MQ_DEAD, "block/mq:dead", NULL,
 				blk_mq_hctx_notify_dead);
+	cpuhp_setup_state_multi(CPUHP_AP_BLK_MQ_ONLINE, "block/mq:online",
+				blk_mq_hctx_notify_online,
+				blk_mq_hctx_notify_offline);
 	return 0;
 }
 subsys_initcall(blk_mq_init);