1 files changed, 86 insertions, 46 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 0015a1892153..deca157032c2 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -105,7 +105,7 @@ static bool blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx,
 {
 	struct mq_inflight *mi = priv;
 
-	if (rq->part == mi->part)
+	if (rq->part == mi->part && blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT)
 		mi->inflight[rq_data_dir(rq)]++;
 
 	return true;
@@ -519,7 +519,7 @@ void blk_mq_free_request(struct request *rq)
 
 	ctx->rq_completed[rq_is_sync(rq)]++;
 	if (rq->rq_flags & RQF_MQ_INFLIGHT)
-		atomic_dec(&hctx->nr_active);
+		__blk_mq_dec_active_requests(hctx);
 
 	if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq)))
 		laptop_io_completion(q->backing_dev_info);
@@ -1096,19 +1096,20 @@ static inline unsigned int queued_to_index(unsigned int queued)
 
 static bool __blk_mq_get_driver_tag(struct request *rq)
 {
-	struct sbitmap_queue *bt = &rq->mq_hctx->tags->bitmap_tags;
+	struct sbitmap_queue *bt = rq->mq_hctx->tags->bitmap_tags;
 	unsigned int tag_offset = rq->mq_hctx->tags->nr_reserved_tags;
 	int tag;
 
 	blk_mq_tag_busy(rq->mq_hctx);
 
 	if (blk_mq_tag_is_reserved(rq->mq_hctx->sched_tags, rq->internal_tag)) {
-		bt = &rq->mq_hctx->tags->breserved_tags;
+		bt = rq->mq_hctx->tags->breserved_tags;
 		tag_offset = 0;
+	} else {
+		if (!hctx_may_queue(rq->mq_hctx, bt))
+			return false;
 	}
 
-	if (!hctx_may_queue(rq->mq_hctx, bt))
-		return false;
 	tag = __sbitmap_queue_get(bt);
 	if (tag == BLK_MQ_NO_TAG)
 		return false;
@@ -1124,10 +1125,10 @@ static bool blk_mq_get_driver_tag(struct request *rq)
 	if (rq->tag == BLK_MQ_NO_TAG && !__blk_mq_get_driver_tag(rq))
 		return false;
 
-	if ((hctx->flags & BLK_MQ_F_TAG_SHARED) &&
+	if ((hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) &&
 			!(rq->rq_flags & RQF_MQ_INFLIGHT)) {
 		rq->rq_flags |= RQF_MQ_INFLIGHT;
-		atomic_inc(&hctx->nr_active);
+		__blk_mq_inc_active_requests(hctx);
 	}
 	hctx->tags->rqs[rq->tag] = rq;
 	return true;
@@ -1145,7 +1146,7 @@ static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode,
 		struct sbitmap_queue *sbq;
 
 		list_del_init(&wait->entry);
-		sbq = &hctx->tags->bitmap_tags;
+		sbq = hctx->tags->bitmap_tags;
 		atomic_dec(&sbq->ws_active);
 	}
 	spin_unlock(&hctx->dispatch_wait_lock);
@@ -1163,12 +1164,12 @@ static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode,
 static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
 				 struct request *rq)
 {
-	struct sbitmap_queue *sbq = &hctx->tags->bitmap_tags;
+	struct sbitmap_queue *sbq = hctx->tags->bitmap_tags;
 	struct wait_queue_head *wq;
 	wait_queue_entry_t *wait;
 	bool ret;
 
-	if (!(hctx->flags & BLK_MQ_F_TAG_SHARED)) {
+	if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) {
 		blk_mq_sched_mark_restart_hctx(hctx);
 
 		/*
@@ -1412,6 +1413,11 @@ out:
 
 	hctx->dispatched[queued_to_index(queued)]++;
 
+	/* If we didn't flush the entire list, we could have told the driver
+	 * there was more coming, but that turned out to be a lie.
+	 */
+	if ((!list_empty(list) || errors) && q->mq_ops->commit_rqs && queued)
+		q->mq_ops->commit_rqs(hctx);
 	/*
 	 * Any items that need requeuing? Stuff them into hctx->dispatch,
 	 * that is where we will continue on next queue run.
@@ -1420,24 +1426,25 @@ out:
 		bool needs_restart;
 		/* For non-shared tags, the RESTART check will suffice */
 		bool no_tag = prep == PREP_DISPATCH_NO_TAG &&
-                        (hctx->flags & BLK_MQ_F_TAG_SHARED);
+			(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED);
 		bool no_budget_avail = prep == PREP_DISPATCH_NO_BUDGET;
 
 		blk_mq_release_budgets(q, nr_budgets);
 
-		/*
-		 * If we didn't flush the entire list, we could have told
-		 * the driver there was more coming, but that turned out to
-		 * be a lie.
-		 */
-		if (q->mq_ops->commit_rqs && queued)
-			q->mq_ops->commit_rqs(hctx);
-
 		spin_lock(&hctx->lock);
 		list_splice_tail_init(list, &hctx->dispatch);
 		spin_unlock(&hctx->lock);
 
 		/*
+		 * Order adding requests to hctx->dispatch and checking
+		 * SCHED_RESTART flag. The pair of this smp_mb() is the one
+		 * in blk_mq_sched_restart(). Avoid restart code path to
+		 * miss the new added requests to hctx->dispatch, meantime
+		 * SCHED_RESTART is observed here.
+		 */
+		smp_mb();
+
+		/*
 		 * If SCHED_RESTART was set by the caller of this function and
 		 * it is no longer set that means that it was cleared by another
 		 * thread and hence that a queue rerun is needed.
@@ -1797,7 +1804,7 @@ static void blk_mq_run_work_fn(struct work_struct *work)
 	/*
 	 * If we are stopped, don't run the queue.
 	 */
-	if (test_bit(BLK_MQ_S_STOPPED, &hctx->state))
+	if (blk_mq_hctx_stopped(hctx))
 		return;
 
 	__blk_mq_run_hw_queue(hctx);
@@ -1834,6 +1841,7 @@ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 /**
  * blk_mq_request_bypass_insert - Insert a request at dispatch list.
  * @rq: Pointer to request to be inserted.
+ * @at_head: true if the request should be inserted at the head of the list.
  * @run_queue: If we should run the hardware queue after inserting the request.
  *
  * Should only be used carefully, when the caller knows we want to
@@ -1929,13 +1937,18 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 static void blk_mq_bio_to_request(struct request *rq, struct bio *bio,
 		unsigned int nr_segs)
 {
+	int err;
+
 	if (bio->bi_opf & REQ_RAHEAD)
 		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);
-	blk_crypto_rq_bio_prep(rq, bio, GFP_NOIO);
+
+	/* This can't fail, since GFP_NOIO includes __GFP_DIRECT_RECLAIM. */
+	err = blk_crypto_rq_bio_prep(rq, bio, GFP_NOIO);
+	WARN_ON_ONCE(err);
 
 	blk_account_io_start(rq);
 }
@@ -2016,7 +2029,8 @@ insert:
 	if (bypass_insert)
 		return BLK_STS_RESOURCE;
 
-	blk_mq_request_bypass_insert(rq, false, run_queue);
+	blk_mq_sched_insert_request(rq, false, run_queue, false);
+
 	return BLK_STS_OK;
 }
 
@@ -2068,6 +2082,7 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 		struct list_head *list)
 {
 	int queued = 0;
+	int errors = 0;
 
 	while (!list_empty(list)) {
 		blk_status_t ret;
@@ -2084,6 +2099,7 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 				break;
 			}
 			blk_mq_end_request(rq, ret);
+			errors++;
 		} else
 			queued++;
 	}
@@ -2093,7 +2109,8 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 	 * the driver there was more coming, but that turned out to
 	 * be a lie.
 	 */
-	if (!list_empty(list) && hctx->queue->mq_ops->commit_rqs && queued)
+	if ((!list_empty(list) || errors) &&
+	     hctx->queue->mq_ops->commit_rqs && queued)
 		hctx->queue->mq_ops->commit_rqs(hctx);
 }
 
@@ -2285,20 +2302,21 @@ void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
 	}
 }
 
-void blk_mq_free_rq_map(struct blk_mq_tags *tags)
+void blk_mq_free_rq_map(struct blk_mq_tags *tags, unsigned int flags)
 {
 	kfree(tags->rqs);
 	tags->rqs = NULL;
 	kfree(tags->static_rqs);
 	tags->static_rqs = NULL;
 
-	blk_mq_free_tags(tags);
+	blk_mq_free_tags(tags, flags);
 }
 
 struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
 					unsigned int hctx_idx,
 					unsigned int nr_tags,
-					unsigned int reserved_tags)
+					unsigned int reserved_tags,
+					unsigned int flags)
 {
 	struct blk_mq_tags *tags;
 	int node;
@@ -2307,8 +2325,7 @@ struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
 	if (node == NUMA_NO_NODE)
 		node = set->numa_node;
 
-	tags = blk_mq_init_tags(nr_tags, reserved_tags, node,
-				BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags));
+	tags = blk_mq_init_tags(nr_tags, reserved_tags, node, flags);
 	if (!tags)
 		return NULL;
 
@@ -2316,7 +2333,7 @@ struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
 				 GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
 				 node);
 	if (!tags->rqs) {
-		blk_mq_free_tags(tags);
+		blk_mq_free_tags(tags, flags);
 		return NULL;
 	}
 
@@ -2325,7 +2342,7 @@ struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
 					node);
 	if (!tags->static_rqs) {
 		kfree(tags->rqs);
-		blk_mq_free_tags(tags);
+		blk_mq_free_tags(tags, flags);
 		return NULL;
 	}
 
@@ -2649,6 +2666,7 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set,
 		goto free_hctx;
 
 	atomic_set(&hctx->nr_active, 0);
+	atomic_set(&hctx->elevator_queued, 0);
 	if (node == NUMA_NO_NODE)
 		node = set->numa_node;
 	hctx->numa_node = node;
@@ -2657,7 +2675,7 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set,
 	spin_lock_init(&hctx->lock);
 	INIT_LIST_HEAD(&hctx->dispatch);
 	hctx->queue = q;
-	hctx->flags = set->flags & ~BLK_MQ_F_TAG_SHARED;
+	hctx->flags = set->flags & ~BLK_MQ_F_TAG_QUEUE_SHARED;
 
 	INIT_LIST_HEAD(&hctx->hctx_list);
 
@@ -2734,10 +2752,11 @@ static void blk_mq_init_cpu_queues(struct request_queue *q,
 static bool __blk_mq_alloc_map_and_request(struct blk_mq_tag_set *set,
 					int hctx_idx)
 {
+	unsigned int flags = set->flags;
 	int ret = 0;
 
 	set->tags[hctx_idx] = blk_mq_alloc_rq_map(set, hctx_idx,
-					set->queue_depth, set->reserved_tags);
+					set->queue_depth, set->reserved_tags, flags);
 	if (!set->tags[hctx_idx])
 		return false;
 
@@ -2746,7 +2765,7 @@ static bool __blk_mq_alloc_map_and_request(struct blk_mq_tag_set *set,
 	if (!ret)
 		return true;
 
-	blk_mq_free_rq_map(set->tags[hctx_idx]);
+	blk_mq_free_rq_map(set->tags[hctx_idx], flags);
 	set->tags[hctx_idx] = NULL;
 	return false;
 }
@@ -2754,9 +2773,11 @@ static bool __blk_mq_alloc_map_and_request(struct blk_mq_tag_set *set,
 static void blk_mq_free_map_and_requests(struct blk_mq_tag_set *set,
 					 unsigned int hctx_idx)
 {
+	unsigned int flags = set->flags;
+
 	if (set->tags && set->tags[hctx_idx]) {
 		blk_mq_free_rqs(set, set->tags[hctx_idx], hctx_idx);
-		blk_mq_free_rq_map(set->tags[hctx_idx]);
+		blk_mq_free_rq_map(set->tags[hctx_idx], flags);
 		set->tags[hctx_idx] = NULL;
 	}
 }
@@ -2874,14 +2895,14 @@ static void queue_set_hctx_shared(struct request_queue *q, bool shared)
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (shared)
-			hctx->flags |= BLK_MQ_F_TAG_SHARED;
+			hctx->flags |= BLK_MQ_F_TAG_QUEUE_SHARED;
 		else
-			hctx->flags &= ~BLK_MQ_F_TAG_SHARED;
+			hctx->flags &= ~BLK_MQ_F_TAG_QUEUE_SHARED;
 	}
 }
 
-static void blk_mq_update_tag_set_depth(struct blk_mq_tag_set *set,
-					bool shared)
+static void blk_mq_update_tag_set_shared(struct blk_mq_tag_set *set,
+					 bool shared)
 {
 	struct request_queue *q;
 
@@ -2902,9 +2923,9 @@ static void blk_mq_del_queue_tag_set(struct request_queue *q)
 	list_del(&q->tag_set_list);
 	if (list_is_singular(&set->tag_list)) {
 		/* just transitioned to unshared */
-		set->flags &= ~BLK_MQ_F_TAG_SHARED;
+		set->flags &= ~BLK_MQ_F_TAG_QUEUE_SHARED;
 		/* update existing queue */
-		blk_mq_update_tag_set_depth(set, false);
+		blk_mq_update_tag_set_shared(set, false);
 	}
 	mutex_unlock(&set->tag_list_lock);
 	INIT_LIST_HEAD(&q->tag_set_list);
@@ -2919,12 +2940,12 @@ static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set,
 	 * Check to see if we're transitioning to shared (from 1 to 2 queues).
 	 */
 	if (!list_empty(&set->tag_list) &&
-	    !(set->flags & BLK_MQ_F_TAG_SHARED)) {
-		set->flags |= BLK_MQ_F_TAG_SHARED;
+	    !(set->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) {
+		set->flags |= BLK_MQ_F_TAG_QUEUE_SHARED;
 		/* update existing queue */
-		blk_mq_update_tag_set_depth(set, true);
+		blk_mq_update_tag_set_shared(set, true);
 	}
-	if (set->flags & BLK_MQ_F_TAG_SHARED)
+	if (set->flags & BLK_MQ_F_TAG_QUEUE_SHARED)
 		queue_set_hctx_shared(q, true);
 	list_add_tail(&q->tag_set_list, &set->tag_list);
 
@@ -3245,9 +3266,11 @@ static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
 {
 	int i;
 
-	for (i = 0; i < set->nr_hw_queues; i++)
+	for (i = 0; i < set->nr_hw_queues; i++) {
 		if (!__blk_mq_alloc_map_and_request(set, i))
 			goto out_unwind;
+		cond_resched();
+	}
 
 	return 0;
 
@@ -3427,11 +3450,23 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 	if (ret)
 		goto out_free_mq_map;
 
+	if (blk_mq_is_sbitmap_shared(set->flags)) {
+		atomic_set(&set->active_queues_shared_sbitmap, 0);
+
+		if (blk_mq_init_shared_sbitmap(set, set->flags)) {
+			ret = -ENOMEM;
+			goto out_free_mq_rq_maps;
+		}
+	}
+
 	mutex_init(&set->tag_list_lock);
 	INIT_LIST_HEAD(&set->tag_list);
 
 	return 0;
 
+out_free_mq_rq_maps:
+	for (i = 0; i < set->nr_hw_queues; i++)
+		blk_mq_free_map_and_requests(set, i);
 out_free_mq_map:
 	for (i = 0; i < set->nr_maps; i++) {
 		kfree(set->map[i].mq_map);
@@ -3450,6 +3485,9 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set)
 	for (i = 0; i < set->nr_hw_queues; i++)
 		blk_mq_free_map_and_requests(set, i);
 
+	if (blk_mq_is_sbitmap_shared(set->flags))
+		blk_mq_exit_shared_sbitmap(set);
+
 	for (j = 0; j < set->nr_maps; j++) {
 		kfree(set->map[j].mq_map);
 		set->map[j].mq_map = NULL;
@@ -3486,6 +3524,8 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
 		if (!hctx->sched_tags) {
 			ret = blk_mq_tag_update_depth(hctx, &hctx->tags, nr,
 							false);
+			if (!ret && blk_mq_is_sbitmap_shared(set->flags))
+				blk_mq_tag_resize_shared_sbitmap(set, nr);
 		} else {
 			ret = blk_mq_tag_update_depth(hctx, &hctx->sched_tags,
 							nr, true);