1 files changed, 217 insertions, 98 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 4b2c8e940f59..270cfd9fc6b0 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -92,7 +92,7 @@ static bool blk_mq_check_inflight(struct request *rq, void *priv)
 {
 	struct mq_inflight *mi = priv;
 
-	if (rq->part && blk_do_io_stat(rq) &&
+	if (rq->rq_flags & RQF_IO_STAT &&
 	    (!bdev_is_partition(mi->part) || rq->part == mi->part) &&
 	    blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT)
 		mi->inflight[rq_data_dir(rq)]++;
@@ -120,9 +120,59 @@ void blk_mq_in_flight_rw(struct request_queue *q, struct block_device *part,
 	inflight[1] = mi.inflight[1];
 }
 
-void blk_freeze_queue_start(struct request_queue *q)
+#ifdef CONFIG_LOCKDEP
+static bool blk_freeze_set_owner(struct request_queue *q,
+				 struct task_struct *owner)
+{
+	if (!owner)
+		return false;
+
+	if (!q->mq_freeze_depth) {
+		q->mq_freeze_owner = owner;
+		q->mq_freeze_owner_depth = 1;
+		return true;
+	}
+
+	if (owner == q->mq_freeze_owner)
+		q->mq_freeze_owner_depth += 1;
+	return false;
+}
+
+/* verify the last unfreeze in owner context */
+static bool blk_unfreeze_check_owner(struct request_queue *q)
 {
+	if (!q->mq_freeze_owner)
+		return false;
+	if (q->mq_freeze_owner != current)
+		return false;
+	if (--q->mq_freeze_owner_depth == 0) {
+		q->mq_freeze_owner = NULL;
+		return true;
+	}
+	return false;
+}
+
+#else
+
+static bool blk_freeze_set_owner(struct request_queue *q,
+				 struct task_struct *owner)
+{
+	return false;
+}
+
+static bool blk_unfreeze_check_owner(struct request_queue *q)
+{
+	return false;
+}
+#endif
+
+bool __blk_freeze_queue_start(struct request_queue *q,
+			      struct task_struct *owner)
+{
+	bool freeze;
+
 	mutex_lock(&q->mq_freeze_lock);
+	freeze = blk_freeze_set_owner(q, owner);
 	if (++q->mq_freeze_depth == 1) {
 		percpu_ref_kill(&q->q_usage_counter);
 		mutex_unlock(&q->mq_freeze_lock);
@@ -131,6 +181,14 @@ void blk_freeze_queue_start(struct request_queue *q)
 	} else {
 		mutex_unlock(&q->mq_freeze_lock);
 	}
+
+	return freeze;
+}
+
+void blk_freeze_queue_start(struct request_queue *q)
+{
+	if (__blk_freeze_queue_start(q, current))
+		blk_freeze_acquire_lock(q, false, false);
 }
 EXPORT_SYMBOL_GPL(blk_freeze_queue_start);
 
@@ -149,35 +207,17 @@ int blk_mq_freeze_queue_wait_timeout(struct request_queue *q,
 }
 EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_wait_timeout);
 
-/*
- * Guarantee no request is in use, so we can change any data structure of
- * the queue afterward.
- */
-void blk_freeze_queue(struct request_queue *q)
+void blk_mq_freeze_queue(struct request_queue *q)
 {
-	/*
-	 * In the !blk_mq case we are only calling this to kill the
-	 * q_usage_counter, otherwise this increases the freeze depth
-	 * and waits for it to return to zero.  For this reason there is
-	 * no blk_unfreeze_queue(), and blk_freeze_queue() is not
-	 * exported to drivers as the only user for unfreeze is blk_mq.
-	 */
 	blk_freeze_queue_start(q);
 	blk_mq_freeze_queue_wait(q);
 }
-
-void blk_mq_freeze_queue(struct request_queue *q)
-{
-	/*
-	 * ...just an alias to keep freeze and unfreeze actions balanced
-	 * in the blk_mq_* namespace
-	 */
-	blk_freeze_queue(q);
-}
 EXPORT_SYMBOL_GPL(blk_mq_freeze_queue);
 
-void __blk_mq_unfreeze_queue(struct request_queue *q, bool force_atomic)
+bool __blk_mq_unfreeze_queue(struct request_queue *q, bool force_atomic)
 {
+	bool unfreeze;
+
 	mutex_lock(&q->mq_freeze_lock);
 	if (force_atomic)
 		q->q_usage_counter.data->force_atomic = true;
@@ -187,16 +227,40 @@ void __blk_mq_unfreeze_queue(struct request_queue *q, bool force_atomic)
 		percpu_ref_resurrect(&q->q_usage_counter);
 		wake_up_all(&q->mq_freeze_wq);
 	}
+	unfreeze = blk_unfreeze_check_owner(q);
 	mutex_unlock(&q->mq_freeze_lock);
+
+	return unfreeze;
 }
 
 void blk_mq_unfreeze_queue(struct request_queue *q)
 {
-	__blk_mq_unfreeze_queue(q, false);
+	if (__blk_mq_unfreeze_queue(q, false))
+		blk_unfreeze_release_lock(q, false, false);
 }
 EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue);
 
 /*
+ * non_owner variant of blk_freeze_queue_start
+ *
+ * Unlike blk_freeze_queue_start, the queue doesn't need to be unfrozen
+ * by the same task.  This is fragile and should not be used if at all
+ * possible.
+ */
+void blk_freeze_queue_start_non_owner(struct request_queue *q)
+{
+	__blk_freeze_queue_start(q, NULL);
+}
+EXPORT_SYMBOL_GPL(blk_freeze_queue_start_non_owner);
+
+/* non_owner variant of blk_mq_unfreeze_queue */
+void blk_mq_unfreeze_queue_non_owner(struct request_queue *q)
+{
+	__blk_mq_unfreeze_queue(q, false);
+}
+EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue_non_owner);
+
+/*
  * FIXME: replace the scsi_internal_device_*block_nowait() calls in the
  * mpt3sas driver such that this function can be removed.
  */
@@ -283,8 +347,9 @@ void blk_mq_quiesce_tagset(struct blk_mq_tag_set *set)
 		if (!blk_queue_skip_tagset_quiesce(q))
 			blk_mq_quiesce_queue_nowait(q);
 	}
-	blk_mq_wait_quiesce_done(set);
 	mutex_unlock(&set->tag_list_lock);
+
+	blk_mq_wait_quiesce_done(set);
 }
 EXPORT_SYMBOL_GPL(blk_mq_quiesce_tagset);
 
@@ -331,14 +396,9 @@ EXPORT_SYMBOL(blk_rq_init);
 /* Set start and alloc time when the allocated request is actually used */
 static inline void blk_mq_rq_time_init(struct request *rq, u64 alloc_time_ns)
 {
-	if (blk_mq_need_time_stamp(rq))
-		rq->start_time_ns = blk_time_get_ns();
-	else
-		rq->start_time_ns = 0;
-
 #ifdef CONFIG_BLK_RQ_ALLOC_TIME
 	if (blk_queue_rq_alloc_time(rq->q))
-		rq->alloc_time_ns = alloc_time_ns ?: rq->start_time_ns;
+		rq->alloc_time_ns = alloc_time_ns;
 	else
 		rq->alloc_time_ns = 0;
 #endif
@@ -359,8 +419,6 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 
 	if (data->flags & BLK_MQ_REQ_PM)
 		data->rq_flags |= RQF_PM;
-	if (blk_queue_io_stat(q))
-		data->rq_flags |= RQF_IO_STAT;
 	rq->rq_flags = data->rq_flags;
 
 	if (data->rq_flags & RQF_SCHED_TAGS) {
@@ -420,7 +478,7 @@ __blk_mq_alloc_requests_batch(struct blk_mq_alloc_data *data)
 		prefetch(tags->static_rqs[tag]);
 		tag_mask &= ~(1UL << i);
 		rq = blk_mq_rq_ctx_init(data, tags, tag);
-		rq_list_add(data->cached_rq, rq);
+		rq_list_add_head(data->cached_rqs, rq);
 		nr++;
 	}
 	if (!(data->rq_flags & RQF_SCHED_TAGS))
@@ -429,7 +487,7 @@ __blk_mq_alloc_requests_batch(struct blk_mq_alloc_data *data)
 	percpu_ref_get_many(&data->q->q_usage_counter, nr - 1);
 	data->nr_tags -= nr;
 
-	return rq_list_pop(data->cached_rq);
+	return rq_list_pop(data->cached_rqs);
 }
 
 static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data)
@@ -526,7 +584,7 @@ static struct request *blk_mq_rq_cache_fill(struct request_queue *q,
 		.flags		= flags,
 		.cmd_flags	= opf,
 		.nr_tags	= plug->nr_ios,
-		.cached_rq	= &plug->cached_rq,
+		.cached_rqs	= &plug->cached_rqs,
 	};
 	struct request *rq;
 
@@ -551,14 +609,14 @@ static struct request *blk_mq_alloc_cached_request(struct request_queue *q,
 	if (!plug)
 		return NULL;
 
-	if (rq_list_empty(plug->cached_rq)) {
+	if (rq_list_empty(&plug->cached_rqs)) {
 		if (plug->nr_ios == 1)
 			return NULL;
 		rq = blk_mq_rq_cache_fill(q, plug, opf, flags);
 		if (!rq)
 			return NULL;
 	} else {
-		rq = rq_list_peek(&plug->cached_rq);
+		rq = rq_list_peek(&plug->cached_rqs);
 		if (!rq || rq->q != q)
 			return NULL;
 
@@ -567,8 +625,8 @@ static struct request *blk_mq_alloc_cached_request(struct request_queue *q,
 		if (op_is_flush(rq->cmd_flags) != op_is_flush(opf))
 			return NULL;
 
-		plug->cached_rq = rq_list_next(rq);
-		blk_mq_rq_time_init(rq, 0);
+		rq_list_pop(&plug->cached_rqs);
+		blk_mq_rq_time_init(rq, blk_time_get_ns());
 	}
 
 	rq->cmd_flags = opf;
@@ -744,7 +802,7 @@ void blk_mq_free_plug_rqs(struct blk_plug *plug)
 {
 	struct request *rq;
 
-	while ((rq = rq_list_pop(&plug->cached_rq)) != NULL)
+	while ((rq = rq_list_pop(&plug->cached_rqs)) != NULL)
 		blk_mq_free_request(rq);
 }
 
@@ -764,7 +822,7 @@ EXPORT_SYMBOL(blk_dump_rq_flags);
 
 static void blk_account_io_completion(struct request *req, unsigned int bytes)
 {
-	if (req->part && blk_do_io_stat(req)) {
+	if (req->rq_flags & RQF_IO_STAT) {
 		const int sgrp = op_stat_group(req_op(req));
 
 		part_stat_lock();
@@ -784,7 +842,7 @@ static void blk_print_req_error(struct request *req, blk_status_t status)
 		blk_op_str(req_op(req)),
 		(__force u32)(req->cmd_flags & ~REQ_OP_MASK),
 		req->nr_phys_segments,
-		IOPRIO_PRIO_CLASS(req->ioprio));
+		IOPRIO_PRIO_CLASS(req_get_ioprio(req)));
 }
 
 /*
@@ -982,8 +1040,7 @@ static inline void blk_account_io_done(struct request *req, u64 now)
 	 * normal IO on queueing nor completion.  Accounting the
 	 * containing request is enough.
 	 */
-	if (blk_do_io_stat(req) && req->part &&
-	    !(req->rq_flags & RQF_FLUSH_SEQ)) {
+	if ((req->rq_flags & (RQF_IO_STAT|RQF_FLUSH_SEQ)) == RQF_IO_STAT) {
 		const int sgrp = op_stat_group(req_op(req));
 
 		part_stat_lock();
@@ -996,28 +1053,63 @@ static inline void blk_account_io_done(struct request *req, u64 now)
 	}
 }
 
+static inline bool blk_rq_passthrough_stats(struct request *req)
+{
+	struct bio *bio = req->bio;
+
+	if (!blk_queue_passthrough_stat(req->q))
+		return false;
+
+	/* Requests without a bio do not transfer data. */
+	if (!bio)
+		return false;
+
+	/*
+	 * Stats are accumulated in the bdev, so must have one attached to a
+	 * bio to track stats. Most drivers do not set the bdev for passthrough
+	 * requests, but nvme is one that will set it.
+	 */
+	if (!bio->bi_bdev)
+		return false;
+
+	/*
+	 * We don't know what a passthrough command does, but we know the
+	 * payload size and data direction. Ensuring the size is aligned to the
+	 * block size filters out most commands with payloads that don't
+	 * represent sector access.
+	 */
+	if (blk_rq_bytes(req) & (bdev_logical_block_size(bio->bi_bdev) - 1))
+		return false;
+	return true;
+}
+
 static inline void blk_account_io_start(struct request *req)
 {
 	trace_block_io_start(req);
 
-	if (blk_do_io_stat(req)) {
-		/*
-		 * All non-passthrough requests are created from a bio with one
-		 * exception: when a flush command that is part of a flush sequence
-		 * generated by the state machine in blk-flush.c is cloned onto the
-		 * lower device by dm-multipath we can get here without a bio.
-		 */
-		if (req->bio)
-			req->part = req->bio->bi_bdev;
-		else
-			req->part = req->q->disk->part0;
+	if (!blk_queue_io_stat(req->q))
+		return;
+	if (blk_rq_is_passthrough(req) && !blk_rq_passthrough_stats(req))
+		return;
 
-		part_stat_lock();
-		update_io_ticks(req->part, jiffies, false);
-		part_stat_local_inc(req->part,
-				    in_flight[op_is_write(req_op(req))]);
-		part_stat_unlock();
-	}
+	req->rq_flags |= RQF_IO_STAT;
+	req->start_time_ns = blk_time_get_ns();
+
+	/*
+	 * All non-passthrough requests are created from a bio with one
+	 * exception: when a flush command that is part of a flush sequence
+	 * generated by the state machine in blk-flush.c is cloned onto the
+	 * lower device by dm-multipath we can get here without a bio.
+	 */
+	if (req->bio)
+		req->part = req->bio->bi_bdev;
+	else
+		req->part = req->q->disk->part0;
+
+	part_stat_lock();
+	update_io_ticks(req->part, jiffies, false);
+	part_stat_local_inc(req->part, in_flight[op_is_write(req_op(req))]);
+	part_stat_unlock();
 }
 
 static inline void __blk_mq_end_request_acct(struct request *rq, u64 now)
@@ -1300,8 +1392,7 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq)
 	 */
 	if (!plug->has_elevator && (rq->rq_flags & RQF_SCHED_TAGS))
 		plug->has_elevator = true;
-	rq->rq_next = NULL;
-	rq_list_add(&plug->mq_list, rq);
+	rq_list_add_tail(&plug->mq_list, rq);
 	plug->rq_count++;
 }
 
@@ -1698,7 +1789,6 @@ void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 
 	sbitmap_for_each_set(&hctx->ctx_map, flush_busy_ctx, &data);
 }
-EXPORT_SYMBOL_GPL(blk_mq_flush_busy_ctxs);
 
 struct dispatch_rq_data {
 	struct blk_mq_hw_ctx *hctx;
@@ -2200,6 +2290,24 @@ void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
 }
 EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);
 
+static inline bool blk_mq_hw_queue_need_run(struct blk_mq_hw_ctx *hctx)
+{
+	bool need_run;
+
+	/*
+	 * When queue is quiesced, we may be switching io scheduler, or
+	 * updating nr_hw_queues, or other things, and we can't run queue
+	 * any more, even blk_mq_hctx_has_pending() can't be called safely.
+	 *
+	 * And queue will be rerun in blk_mq_unquiesce_queue() if it is
+	 * quiesced.
+	 */
+	__blk_mq_run_dispatch_ops(hctx->queue, false,
+		need_run = !blk_queue_quiesced(hctx->queue) &&
+		blk_mq_hctx_has_pending(hctx));
+	return need_run;
+}
+
 /**
  * blk_mq_run_hw_queue - Start to run a hardware queue.
  * @hctx: Pointer to the hardware queue to run.
@@ -2220,20 +2328,23 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 
 	might_sleep_if(!async && hctx->flags & BLK_MQ_F_BLOCKING);
 
-	/*
-	 * When queue is quiesced, we may be switching io scheduler, or
-	 * updating nr_hw_queues, or other things, and we can't run queue
-	 * any more, even __blk_mq_hctx_has_pending() can't be called safely.
-	 *
-	 * And queue will be rerun in blk_mq_unquiesce_queue() if it is
-	 * quiesced.
-	 */
-	__blk_mq_run_dispatch_ops(hctx->queue, false,
-		need_run = !blk_queue_quiesced(hctx->queue) &&
-		blk_mq_hctx_has_pending(hctx));
+	need_run = blk_mq_hw_queue_need_run(hctx);
+	if (!need_run) {
+		unsigned long flags;
 
-	if (!need_run)
-		return;
+		/*
+		 * Synchronize with blk_mq_unquiesce_queue(), because we check
+		 * if hw queue is quiesced locklessly above, we need the use
+		 * ->queue_lock to make sure we see the up-to-date status to
+		 * not miss rerunning the hw queue.
+		 */
+		spin_lock_irqsave(&hctx->queue->queue_lock, flags);
+		need_run = blk_mq_hw_queue_need_run(hctx);
+		spin_unlock_irqrestore(&hctx->queue->queue_lock, flags);
+
+		if (!need_run)
+			return;
+	}
 
 	if (async || !cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask)) {
 		blk_mq_delay_run_hw_queue(hctx, 0);
@@ -2390,6 +2501,12 @@ void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 		return;
 
 	clear_bit(BLK_MQ_S_STOPPED, &hctx->state);
+	/*
+	 * Pairs with the smp_mb() in blk_mq_hctx_stopped() to order the
+	 * clearing of BLK_MQ_S_STOPPED above and the checking of dispatch
+	 * list in the subsequent routine.
+	 */
+	smp_mb__after_atomic();
 	blk_mq_run_hw_queue(hctx, async);
 }
 EXPORT_SYMBOL_GPL(blk_mq_start_stopped_hw_queue);
@@ -2542,7 +2659,6 @@ static void blk_mq_bio_to_request(struct request *rq, struct bio *bio,
 		rq->cmd_flags |= REQ_FAILFAST_MASK;
 
 	rq->__sector = bio->bi_iter.bi_sector;
-	rq->write_hint = bio->bi_write_hint;
 	blk_rq_bio_prep(rq, bio, nr_segs);
 	if (bio_integrity(bio))
 		rq->nr_integrity_segments = blk_rq_count_integrity_sg(rq->q,
@@ -2620,6 +2736,7 @@ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 
 	if (blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(rq->q)) {
 		blk_mq_insert_request(rq, 0);
+		blk_mq_run_hw_queue(hctx, false);
 		return;
 	}
 
@@ -2650,6 +2767,7 @@ static blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last)
 
 	if (blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(rq->q)) {
 		blk_mq_insert_request(rq, 0);
+		blk_mq_run_hw_queue(hctx, false);
 		return BLK_STS_OK;
 	}
 
@@ -2666,7 +2784,7 @@ static void blk_mq_plug_issue_direct(struct blk_plug *plug)
 	blk_status_t ret = BLK_STS_OK;
 
 	while ((rq = rq_list_pop(&plug->mq_list))) {
-		bool last = rq_list_empty(plug->mq_list);
+		bool last = rq_list_empty(&plug->mq_list);
 
 		if (hctx != rq->mq_hctx) {
 			if (hctx) {
@@ -2709,8 +2827,7 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched)
 {
 	struct blk_mq_hw_ctx *this_hctx = NULL;
 	struct blk_mq_ctx *this_ctx = NULL;
-	struct request *requeue_list = NULL;
-	struct request **requeue_lastp = &requeue_list;
+	struct rq_list requeue_list = {};
 	unsigned int depth = 0;
 	bool is_passthrough = false;
 	LIST_HEAD(list);
@@ -2724,12 +2841,12 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched)
 			is_passthrough = blk_rq_is_passthrough(rq);
 		} else if (this_hctx != rq->mq_hctx || this_ctx != rq->mq_ctx ||
 			   is_passthrough != blk_rq_is_passthrough(rq)) {
-			rq_list_add_tail(&requeue_lastp, rq);
+			rq_list_add_tail(&requeue_list, rq);
 			continue;
 		}
-		list_add(&rq->queuelist, &list);
+		list_add_tail(&rq->queuelist, &list);
 		depth++;
-	} while (!rq_list_empty(plug->mq_list));
+	} while (!rq_list_empty(&plug->mq_list));
 
 	plug->mq_list = requeue_list;
 	trace_block_unplug(this_hctx->queue, depth, !from_sched);
@@ -2784,19 +2901,19 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 		if (q->mq_ops->queue_rqs) {
 			blk_mq_run_dispatch_ops(q,
 				__blk_mq_flush_plug_list(q, plug));
-			if (rq_list_empty(plug->mq_list))
+			if (rq_list_empty(&plug->mq_list))
 				return;
 		}
 
 		blk_mq_run_dispatch_ops(q,
 				blk_mq_plug_issue_direct(plug));
-		if (rq_list_empty(plug->mq_list))
+		if (rq_list_empty(&plug->mq_list))
 			return;
 	}
 
 	do {
 		blk_mq_dispatch_plug_list(plug, from_schedule);
-	} while (!rq_list_empty(plug->mq_list));
+	} while (!rq_list_empty(&plug->mq_list));
 }
 
 static void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
@@ -2861,7 +2978,7 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q,
 	if (plug) {
 		data.nr_tags = plug->nr_ios;
 		plug->nr_ios = 1;
-		data.cached_rq = &plug->cached_rq;
+		data.cached_rqs = &plug->cached_rqs;
 	}
 
 	rq = __blk_mq_alloc_requests(&data);
@@ -2884,7 +3001,7 @@ static struct request *blk_mq_peek_cached_request(struct blk_plug *plug,
 
 	if (!plug)
 		return NULL;
-	rq = rq_list_peek(&plug->cached_rq);
+	rq = rq_list_peek(&plug->cached_rqs);
 	if (!rq || rq->q != q)
 		return NULL;
 	if (type != rq->mq_hctx->type &&
@@ -2898,17 +3015,17 @@ static struct request *blk_mq_peek_cached_request(struct blk_plug *plug,
 static void blk_mq_use_cached_rq(struct request *rq, struct blk_plug *plug,
 		struct bio *bio)
 {
-	WARN_ON_ONCE(rq_list_peek(&plug->cached_rq) != rq);
+	if (rq_list_pop(&plug->cached_rqs) != rq)
+		WARN_ON_ONCE(1);
 
 	/*
 	 * If any qos ->throttle() end up blocking, we will have flushed the
 	 * plug and hence killed the cached_rq list as well. Pop this entry
 	 * before we throttle.
 	 */
-	plug->cached_rq = rq_list_next(rq);
 	rq_qos_throttle(rq->q, bio);
 
-	blk_mq_rq_time_init(rq, 0);
+	blk_mq_rq_time_init(rq, blk_time_get_ns());
 	rq->cmd_flags = bio->bi_opf;
 	INIT_LIST_HEAD(&rq->queuelist);
 }
@@ -3187,8 +3304,6 @@ int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
 		rq->special_vec = rq_src->special_vec;
 	}
 	rq->nr_phys_segments = rq_src->nr_phys_segments;
-	rq->ioprio = rq_src->ioprio;
-	rq->write_hint = rq_src->write_hint;
 
 	if (rq->bio && blk_crypto_rq_bio_prep(rq, rq->bio, gfp_mask) < 0)
 		goto free_and_out;
@@ -4310,6 +4425,12 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	/* mark the queue as mq asap */
 	q->mq_ops = set->ops;
 
+	/*
+	 * ->tag_set has to be setup before initialize hctx, which cpuphp
+	 * handler needs it for checking queue mapping
+	 */
+	q->tag_set = set;
+
 	if (blk_mq_alloc_ctxs(q))
 		goto err_exit;
 
@@ -4328,8 +4449,6 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	INIT_WORK(&q->timeout_work, blk_mq_timeout_work);
 	blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30 * HZ);
 
-	q->tag_set = set;
-
 	q->queue_flags |= QUEUE_FLAG_MQ_DEFAULT;
 
 	INIT_DELAYED_WORK(&q->requeue_work, blk_mq_requeue_work);