1 files changed, 53 insertions, 34 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index a12b1763508d..f6291ceedee4 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -477,9 +477,9 @@ static void __blk_mq_free_request(struct request *rq)
 	blk_pm_mark_last_busy(rq);
 	rq->mq_hctx = NULL;
 	if (rq->tag != -1)
-		blk_mq_put_tag(hctx, hctx->tags, ctx, rq->tag);
+		blk_mq_put_tag(hctx->tags, ctx, rq->tag);
 	if (sched_tag != -1)
-		blk_mq_put_tag(hctx, hctx->sched_tags, ctx, sched_tag);
+		blk_mq_put_tag(hctx->sched_tags, ctx, sched_tag);
 	blk_mq_sched_restart(hctx);
 	blk_queue_exit(q);
 }
@@ -735,7 +735,7 @@ static void blk_mq_requeue_work(struct work_struct *work)
 		 * merge.
 		 */
 		if (rq->rq_flags & RQF_DONTPREP)
-			blk_mq_request_bypass_insert(rq, false);
+			blk_mq_request_bypass_insert(rq, false, false);
 		else
 			blk_mq_sched_insert_request(rq, true, false, false);
 	}
@@ -1178,6 +1178,23 @@ static void blk_mq_update_dispatch_busy(struct blk_mq_hw_ctx *hctx, bool busy)
 
 #define BLK_MQ_RESOURCE_DELAY	3		/* ms units */
 
+static void blk_mq_handle_dev_resource(struct request *rq,
+				       struct list_head *list)
+{
+	struct request *next =
+		list_first_entry_or_null(list, struct request, queuelist);
+
+	/*
+	 * If an I/O scheduler has been configured and we got a driver tag for
+	 * the next request already, free it.
+	 */
+	if (next)
+		blk_mq_put_driver_tag(next);
+
+	list_add(&rq->queuelist, list);
+	__blk_mq_requeue_request(rq);
+}
+
 /*
  * Returns true if we did some work AND can potentially do more.
  */
@@ -1245,17 +1262,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 
 		ret = q->mq_ops->queue_rq(hctx, &bd);
 		if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) {
-			/*
-			 * If an I/O scheduler has been configured and we got a
-			 * driver tag for the next request already, free it
-			 * again.
-			 */
-			if (!list_empty(list)) {
-				nxt = list_first_entry(list, struct request, queuelist);
-				blk_mq_put_driver_tag(nxt);
-			}
-			list_add(&rq->queuelist, list);
-			__blk_mq_requeue_request(rq);
+			blk_mq_handle_dev_resource(rq, list);
 			break;
 		}
 
@@ -1286,7 +1293,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 			q->mq_ops->commit_rqs(hctx);
 
 		spin_lock(&hctx->lock);
-		list_splice_init(list, &hctx->dispatch);
+		list_splice_tail_init(list, &hctx->dispatch);
 		spin_unlock(&hctx->lock);
 
 		/*
@@ -1677,12 +1684,16 @@ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
  * Should only be used carefully, when the caller knows we want to
  * bypass a potential IO scheduler on the target device.
  */
-void blk_mq_request_bypass_insert(struct request *rq, bool run_queue)
+void blk_mq_request_bypass_insert(struct request *rq, bool at_head,
+				  bool run_queue)
 {
 	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
 
 	spin_lock(&hctx->lock);
-	list_add_tail(&rq->queuelist, &hctx->dispatch);
+	if (at_head)
+		list_add(&rq->queuelist, &hctx->dispatch);
+	else
+		list_add_tail(&rq->queuelist, &hctx->dispatch);
 	spin_unlock(&hctx->lock);
 
 	if (run_queue)
@@ -1849,7 +1860,7 @@ insert:
 	if (bypass_insert)
 		return BLK_STS_RESOURCE;
 
-	blk_mq_request_bypass_insert(rq, run_queue);
+	blk_mq_request_bypass_insert(rq, false, run_queue);
 	return BLK_STS_OK;
 }
 
@@ -1876,7 +1887,7 @@ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 
 	ret = __blk_mq_try_issue_directly(hctx, rq, cookie, false, true);
 	if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE)
-		blk_mq_request_bypass_insert(rq, true);
+		blk_mq_request_bypass_insert(rq, false, true);
 	else if (ret != BLK_STS_OK)
 		blk_mq_end_request(rq, ret);
 
@@ -1910,7 +1921,7 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 		if (ret != BLK_STS_OK) {
 			if (ret == BLK_STS_RESOURCE ||
 					ret == BLK_STS_DEV_RESOURCE) {
-				blk_mq_request_bypass_insert(rq,
+				blk_mq_request_bypass_insert(rq, false,
 							list_empty(list));
 				break;
 			}
@@ -2405,8 +2416,7 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set,
 	init_waitqueue_func_entry(&hctx->dispatch_wait, blk_mq_dispatch_wake);
 	INIT_LIST_HEAD(&hctx->dispatch_wait.entry);
 
-	hctx->fq = blk_alloc_flush_queue(q, hctx->numa_node, set->cmd_size,
-			gfp);
+	hctx->fq = blk_alloc_flush_queue(hctx->numa_node, set->cmd_size, gfp);
 	if (!hctx->fq)
 		goto free_bitmap;
 
@@ -2714,13 +2724,15 @@ void blk_mq_release(struct request_queue *q)
 	blk_mq_sysfs_deinit(q);
 }
 
-struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
+struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set,
+		void *queuedata)
 {
 	struct request_queue *uninit_q, *q;
 
-	uninit_q = blk_alloc_queue_node(GFP_KERNEL, set->numa_node);
+	uninit_q = __blk_alloc_queue(set->numa_node);
 	if (!uninit_q)
 		return ERR_PTR(-ENOMEM);
+	uninit_q->queuedata = queuedata;
 
 	/*
 	 * Initialize the queue without an elevator. device_add_disk() will do
@@ -2732,6 +2744,12 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
 
 	return q;
 }
+EXPORT_SYMBOL_GPL(blk_mq_init_queue_data);
+
+struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
+{
+	return blk_mq_init_queue_data(set, NULL);
+}
 EXPORT_SYMBOL(blk_mq_init_queue);
 
 /*
@@ -2820,7 +2838,6 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 			memcpy(new_hctxs, hctxs, q->nr_hw_queues *
 			       sizeof(*hctxs));
 		q->queue_hw_ctx = new_hctxs;
-		q->nr_hw_queues = set->nr_hw_queues;
 		kfree(hctxs);
 		hctxs = new_hctxs;
 	}
@@ -2922,11 +2939,7 @@ 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);
 
-	blk_queue_make_request(q, blk_mq_make_request);
-
-	/*
-	 * Do this after blk_queue_make_request() overrides it...
-	 */
+	q->make_request_fn = blk_mq_make_request;
 	q->nr_requests = set->queue_depth;
 
 	/*
@@ -3019,6 +3032,14 @@ static int blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
 
 static int blk_mq_update_queue_map(struct blk_mq_tag_set *set)
 {
+	/*
+	 * blk_mq_map_queues() and multiple .map_queues() implementations
+	 * expect that set->map[HCTX_TYPE_DEFAULT].nr_queues is set to the
+	 * number of hardware queues.
+	 */
+	if (set->nr_maps == 1)
+		set->map[HCTX_TYPE_DEFAULT].nr_queues = set->nr_hw_queues;
+
 	if (set->ops->map_queues && !is_kdump_kernel()) {
 		int i;
 
@@ -3398,7 +3419,6 @@ static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb)
 }
 
 static unsigned long blk_mq_poll_nsecs(struct request_queue *q,
-				       struct blk_mq_hw_ctx *hctx,
 				       struct request *rq)
 {
 	unsigned long ret = 0;
@@ -3431,7 +3451,6 @@ static unsigned long blk_mq_poll_nsecs(struct request_queue *q,
 }
 
 static bool blk_mq_poll_hybrid_sleep(struct request_queue *q,
-				     struct blk_mq_hw_ctx *hctx,
 				     struct request *rq)
 {
 	struct hrtimer_sleeper hs;
@@ -3451,7 +3470,7 @@ static bool blk_mq_poll_hybrid_sleep(struct request_queue *q,
 	if (q->poll_nsec > 0)
 		nsecs = q->poll_nsec;
 	else
-		nsecs = blk_mq_poll_nsecs(q, hctx, rq);
+		nsecs = blk_mq_poll_nsecs(q, rq);
 
 	if (!nsecs)
 		return false;
@@ -3506,7 +3525,7 @@ static bool blk_mq_poll_hybrid(struct request_queue *q,
 			return false;
 	}
 
-	return blk_mq_poll_hybrid_sleep(q, hctx, rq);
+	return blk_mq_poll_hybrid_sleep(q, rq);
 }
 
 /**