4 files changed, 62 insertions, 101 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index abcb8684ba67..806ce2442819 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2385,8 +2385,20 @@ blk_qc_t generic_make_request(struct bio *bio)
 	 * yet.
 	 */
 	struct bio_list bio_list_on_stack[2];
+	blk_mq_req_flags_t flags = 0;
+	struct request_queue *q = bio->bi_disk->queue;
 	blk_qc_t ret = BLK_QC_T_NONE;
 
+	if (bio->bi_opf & REQ_NOWAIT)
+		flags = BLK_MQ_REQ_NOWAIT;
+	if (blk_queue_enter(q, flags) < 0) {
+		if (!blk_queue_dying(q) && (bio->bi_opf & REQ_NOWAIT))
+			bio_wouldblock_error(bio);
+		else
+			bio_io_error(bio);
+		return ret;
+	}
+
 	if (!generic_make_request_checks(bio))
 		goto out;
 
@@ -2423,11 +2435,22 @@ blk_qc_t generic_make_request(struct bio *bio)
 	bio_list_init(&bio_list_on_stack[0]);
 	current->bio_list = bio_list_on_stack;
 	do {
-		struct request_queue *q = bio->bi_disk->queue;
-		blk_mq_req_flags_t flags = bio->bi_opf & REQ_NOWAIT ?
-			BLK_MQ_REQ_NOWAIT : 0;
+		bool enter_succeeded = true;
+
+		if (unlikely(q != bio->bi_disk->queue)) {
+			if (q)
+				blk_queue_exit(q);
+			q = bio->bi_disk->queue;
+			flags = 0;
+			if (bio->bi_opf & REQ_NOWAIT)
+				flags = BLK_MQ_REQ_NOWAIT;
+			if (blk_queue_enter(q, flags) < 0) {
+				enter_succeeded = false;
+				q = NULL;
+			}
+		}
 
-		if (likely(blk_queue_enter(q, flags) == 0)) {
+		if (enter_succeeded) {
 			struct bio_list lower, same;
 
 			/* Create a fresh bio_list for all subordinate requests */
@@ -2435,8 +2458,6 @@ blk_qc_t generic_make_request(struct bio *bio)
 			bio_list_init(&bio_list_on_stack[0]);
 			ret = q->make_request_fn(q, bio);
 
-			blk_queue_exit(q);
-
 			/* sort new bios into those for a lower level
 			 * and those for the same level
 			 */
@@ -2463,6 +2484,8 @@ blk_qc_t generic_make_request(struct bio *bio)
 	current->bio_list = NULL; /* deactivate */
 
 out:
+	if (q)
+		blk_queue_exit(q);
 	return ret;
 }
 EXPORT_SYMBOL(generic_make_request);
diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c
index 9f8cffc8a701..3eb169f15842 100644
--- a/block/blk-mq-cpumap.c
+++ b/block/blk-mq-cpumap.c
@@ -16,11 +16,6 @@
 
 static int cpu_to_queue_index(unsigned int nr_queues, const int cpu)
 {
-	/*
-	 * Non present CPU will be mapped to queue index 0.
-	 */
-	if (!cpu_present(cpu))
-		return 0;
 	return cpu % nr_queues;
 }
 
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 58b3b79cbe83..3080e18cb859 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -235,7 +235,6 @@ static const char *const hctx_state_name[] = {
 	HCTX_STATE_NAME(STOPPED),
 	HCTX_STATE_NAME(TAG_ACTIVE),
 	HCTX_STATE_NAME(SCHED_RESTART),
-	HCTX_STATE_NAME(START_ON_RUN),
 };
 #undef HCTX_STATE_NAME
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index f5c7dbcb954f..0dc9e341c2a7 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1180,7 +1180,12 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 		struct blk_mq_queue_data bd;
 
 		rq = list_first_entry(list, struct request, queuelist);
-		if (!blk_mq_get_driver_tag(rq, &hctx, false)) {
+
+		hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu);
+		if (!got_budget && !blk_mq_get_dispatch_budget(hctx))
+			break;
+
+		if (!blk_mq_get_driver_tag(rq, NULL, false)) {
 			/*
 			 * The initial allocation attempt failed, so we need to
 			 * rerun the hardware queue when a tag is freed. The
@@ -1189,8 +1194,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 			 * we'll re-run it below.
 			 */
 			if (!blk_mq_mark_tag_wait(&hctx, rq)) {
-				if (got_budget)
-					blk_mq_put_dispatch_budget(hctx);
+				blk_mq_put_dispatch_budget(hctx);
 				/*
 				 * For non-shared tags, the RESTART check
 				 * will suffice.
@@ -1201,11 +1205,6 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 			}
 		}
 
-		if (!got_budget && !blk_mq_get_dispatch_budget(hctx)) {
-			blk_mq_put_driver_tag(rq);
-			break;
-		}
-
 		list_del_init(&rq->queuelist);
 
 		bd.rq = rq;
@@ -1336,6 +1335,15 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 	hctx_unlock(hctx, srcu_idx);
 }
 
+static inline int blk_mq_first_mapped_cpu(struct blk_mq_hw_ctx *hctx)
+{
+	int cpu = cpumask_first_and(hctx->cpumask, cpu_online_mask);
+
+	if (cpu >= nr_cpu_ids)
+		cpu = cpumask_first(hctx->cpumask);
+	return cpu;
+}
+
 /*
  * It'd be great if the workqueue API had a way to pass
  * in a mask and had some smarts for more clever placement.
@@ -1345,26 +1353,17 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx)
 {
 	bool tried = false;
+	int next_cpu = hctx->next_cpu;
 
 	if (hctx->queue->nr_hw_queues == 1)
 		return WORK_CPU_UNBOUND;
 
 	if (--hctx->next_cpu_batch <= 0) {
-		int next_cpu;
 select_cpu:
-		next_cpu = cpumask_next_and(hctx->next_cpu, hctx->cpumask,
+		next_cpu = cpumask_next_and(next_cpu, hctx->cpumask,
 				cpu_online_mask);
 		if (next_cpu >= nr_cpu_ids)
-			next_cpu = cpumask_first_and(hctx->cpumask,cpu_online_mask);
-
-		/*
-		 * No online CPU is found, so have to make sure hctx->next_cpu
-		 * is set correctly for not breaking workqueue.
-		 */
-		if (next_cpu >= nr_cpu_ids)
-			hctx->next_cpu = cpumask_first(hctx->cpumask);
-		else
-			hctx->next_cpu = next_cpu;
+			next_cpu = blk_mq_first_mapped_cpu(hctx);
 		hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
 	}
 
@@ -1372,7 +1371,7 @@ select_cpu:
 	 * Do unbound schedule if we can't find a online CPU for this hctx,
 	 * and it should only happen in the path of handling CPU DEAD.
 	 */
-	if (!cpu_online(hctx->next_cpu)) {
+	if (!cpu_online(next_cpu)) {
 		if (!tried) {
 			tried = true;
 			goto select_cpu;
@@ -1382,18 +1381,18 @@ select_cpu:
 		 * Make sure to re-select CPU next time once after CPUs
 		 * in hctx->cpumask become online again.
 		 */
+		hctx->next_cpu = next_cpu;
 		hctx->next_cpu_batch = 1;
 		return WORK_CPU_UNBOUND;
 	}
-	return hctx->next_cpu;
+
+	hctx->next_cpu = next_cpu;
+	return next_cpu;
 }
 
 static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
 					unsigned long msecs)
 {
-	if (WARN_ON_ONCE(!blk_mq_hw_queue_mapped(hctx)))
-		return;
-
 	if (unlikely(blk_mq_hctx_stopped(hctx)))
 		return;
 
@@ -1560,40 +1559,14 @@ static void blk_mq_run_work_fn(struct work_struct *work)
 	hctx = container_of(work, struct blk_mq_hw_ctx, run_work.work);
 
 	/*
-	 * If we are stopped, don't run the queue. The exception is if
-	 * BLK_MQ_S_START_ON_RUN is set. For that case, we auto-clear
-	 * the STOPPED bit and run it.
+	 * If we are stopped, don't run the queue.
 	 */
-	if (test_bit(BLK_MQ_S_STOPPED, &hctx->state)) {
-		if (!test_bit(BLK_MQ_S_START_ON_RUN, &hctx->state))
-			return;
-
-		clear_bit(BLK_MQ_S_START_ON_RUN, &hctx->state);
+	if (test_bit(BLK_MQ_S_STOPPED, &hctx->state))
 		clear_bit(BLK_MQ_S_STOPPED, &hctx->state);
-	}
 
 	__blk_mq_run_hw_queue(hctx);
 }
 
-
-void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
-{
-	if (WARN_ON_ONCE(!blk_mq_hw_queue_mapped(hctx)))
-		return;
-
-	/*
-	 * Stop the hw queue, then modify currently delayed work.
-	 * This should prevent us from running the queue prematurely.
-	 * Mark the queue as auto-clearing STOPPED when it runs.
-	 */
-	blk_mq_stop_hw_queue(hctx);
-	set_bit(BLK_MQ_S_START_ON_RUN, &hctx->state);
-	kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx),
-					&hctx->run_work,
-					msecs_to_jiffies(msecs));
-}
-EXPORT_SYMBOL(blk_mq_delay_queue);
-
 static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx,
 					    struct request *rq,
 					    bool at_head)
@@ -1804,11 +1777,11 @@ static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 	if (q->elevator && !bypass_insert)
 		goto insert;
 
-	if (!blk_mq_get_driver_tag(rq, NULL, false))
+	if (!blk_mq_get_dispatch_budget(hctx))
 		goto insert;
 
-	if (!blk_mq_get_dispatch_budget(hctx)) {
-		blk_mq_put_driver_tag(rq);
+	if (!blk_mq_get_driver_tag(rq, NULL, false)) {
+		blk_mq_put_dispatch_budget(hctx);
 		goto insert;
 	}
 
@@ -2356,7 +2329,7 @@ static void blk_mq_free_map_and_requests(struct blk_mq_tag_set *set,
 
 static void blk_mq_map_swqueue(struct request_queue *q)
 {
-	unsigned int i, hctx_idx;
+	unsigned int i;
 	struct blk_mq_hw_ctx *hctx;
 	struct blk_mq_ctx *ctx;
 	struct blk_mq_tag_set *set = q->tag_set;
@@ -2373,23 +2346,8 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 
 	/*
 	 * Map software to hardware queues.
-	 *
-	 * If the cpu isn't present, the cpu is mapped to first hctx.
 	 */
 	for_each_possible_cpu(i) {
-		hctx_idx = q->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
-			 */
-			q->mq_map[i] = 0;
-		}
-
 		ctx = per_cpu_ptr(q->queue_ctx, i);
 		hctx = blk_mq_map_queue(q, i);
 
@@ -2401,21 +2359,8 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 	mutex_unlock(&q->sysfs_lock);
 
 	queue_for_each_hw_ctx(q, hctx, i) {
-		/*
-		 * If no software queues are mapped to this hardware queue,
-		 * disable it and free the request entries.
-		 */
-		if (!hctx->nr_ctx) {
-			/* Never unmap queue 0.  We need it as a
-			 * fallback in case of a new remap fails
-			 * allocation
-			 */
-			if (i && set->tags[i])
-				blk_mq_free_map_and_requests(set, i);
-
-			hctx->tags = NULL;
-			continue;
-		}
+		/* every hctx should get mapped by at least one CPU */
+		WARN_ON(!hctx->nr_ctx);
 
 		hctx->tags = set->tags[i];
 		WARN_ON(!hctx->tags);
@@ -2430,8 +2375,7 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 		/*
 		 * Initialize batch roundrobin counts
 		 */
-		hctx->next_cpu = cpumask_first_and(hctx->cpumask,
-				cpu_online_mask);
+		hctx->next_cpu = blk_mq_first_mapped_cpu(hctx);
 		hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
 	}
 }