1 files changed, 253 insertions, 137 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 4e0d173beaa3..667155f752f7 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -41,6 +41,8 @@
 #include "blk-mq-sched.h"
 #include "blk-rq-qos.h"
 
+static DEFINE_PER_CPU(struct list_head, blk_cpu_done);
+
 static void blk_mq_poll_stats_start(struct request_queue *q);
 static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb);
 
@@ -275,26 +277,20 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 {
 	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) {
+	if (data->q->elevator) {
 		rq->tag = BLK_MQ_NO_TAG;
 		rq->internal_tag = tag;
 	} else {
-		if (data->hctx->flags & BLK_MQ_F_TAG_SHARED) {
-			rq_flags = RQF_MQ_INFLIGHT;
-			atomic_inc(&data->hctx->nr_active);
-		}
 		rq->tag = tag;
 		rq->internal_tag = BLK_MQ_NO_TAG;
-		data->hctx->tags->rqs[rq->tag] = rq;
 	}
 
 	/* csd/requeue_work/fifo_time is initialized before use */
 	rq->q = data->q;
 	rq->mq_ctx = data->ctx;
 	rq->mq_hctx = data->hctx;
-	rq->rq_flags = rq_flags;
+	rq->rq_flags = 0;
 	rq->cmd_flags = data->cmd_flags;
 	if (data->flags & BLK_MQ_REQ_PREEMPT)
 		rq->rq_flags |= RQF_PREEMPT;
@@ -362,8 +358,6 @@ static struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data)
 		data->flags |= BLK_MQ_REQ_NOWAIT;
 
 	if (e) {
-		data->flags |= BLK_MQ_REQ_INTERNAL;
-
 		/*
 		 * Flush requests are special and go directly to the
 		 * dispatch list. Don't include reserved tags in the
@@ -378,7 +372,7 @@ static struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data)
 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))
+	if (!e)
 		blk_mq_tag_busy(data->hctx);
 
 	/*
@@ -474,9 +468,7 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 	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
+	if (!q->elevator)
 		blk_mq_tag_busy(data.hctx);
 
 	ret = -EWOULDBLOCK;
@@ -552,8 +544,7 @@ inline void __blk_mq_end_request(struct request *rq, blk_status_t error)
 		blk_stat_add(rq, now);
 	}
 
-	if (rq->internal_tag != BLK_MQ_NO_TAG)
-		blk_mq_sched_completed_request(rq, now);
+	blk_mq_sched_completed_request(rq, now);
 
 	blk_account_io_done(rq, now);
 
@@ -574,71 +565,139 @@ void blk_mq_end_request(struct request *rq, blk_status_t error)
 }
 EXPORT_SYMBOL(blk_mq_end_request);
 
-static void __blk_mq_complete_request_remote(void *data)
+/*
+ * Softirq action handler - move entries to local list and loop over them
+ * while passing them to the queue registered handler.
+ */
+static __latent_entropy void blk_done_softirq(struct softirq_action *h)
 {
-	struct request *rq = data;
-	struct request_queue *q = rq->q;
+	struct list_head *cpu_list, local_list;
 
-	q->mq_ops->complete(rq);
+	local_irq_disable();
+	cpu_list = this_cpu_ptr(&blk_cpu_done);
+	list_replace_init(cpu_list, &local_list);
+	local_irq_enable();
+
+	while (!list_empty(&local_list)) {
+		struct request *rq;
+
+		rq = list_entry(local_list.next, struct request, ipi_list);
+		list_del_init(&rq->ipi_list);
+		rq->q->mq_ops->complete(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)
+static void blk_mq_trigger_softirq(struct request *rq)
 {
-	struct blk_mq_ctx *ctx = rq->mq_ctx;
-	struct request_queue *q = rq->q;
-	bool shared = false;
-	int cpu;
+	struct list_head *list;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	list = this_cpu_ptr(&blk_cpu_done);
+	list_add_tail(&rq->ipi_list, list);
+
+	/*
+	 * If the list only contains our just added request, signal a raise of
+	 * the softirq.  If there are already entries there, someone already
+	 * raised the irq but it hasn't run yet.
+	 */
+	if (list->next == &rq->ipi_list)
+		raise_softirq_irqoff(BLOCK_SOFTIRQ);
+	local_irq_restore(flags);
+}
+
+static int blk_softirq_cpu_dead(unsigned int cpu)
+{
+	/*
+	 * If a CPU goes away, splice its entries to the current CPU
+	 * and trigger a run of the softirq
+	 */
+	local_irq_disable();
+	list_splice_init(&per_cpu(blk_cpu_done, cpu),
+			 this_cpu_ptr(&blk_cpu_done));
+	raise_softirq_irqoff(BLOCK_SOFTIRQ);
+	local_irq_enable();
+
+	return 0;
+}
+
+
+static void __blk_mq_complete_request_remote(void *data)
+{
+	struct request *rq = data;
 
-	WRITE_ONCE(rq->state, MQ_RQ_COMPLETE);
 	/*
-	 * Most of single queue controllers, there is only one irq vector
-	 * for handling IO completion, and the only irq's affinity is set
-	 * as all possible CPUs. On most of ARCHs, this affinity means the
-	 * irq is handled on one specific CPU.
+	 * For most of single queue controllers, there is only one irq vector
+	 * for handling I/O completion, and the only irq's affinity is set
+	 * to all possible CPUs.  On most of ARCHs, this affinity means the irq
+	 * is handled on one specific CPU.
 	 *
-	 * So complete IO reqeust in softirq context in case of single queue
-	 * for not degrading IO performance by irqsoff latency.
+	 * So complete I/O requests in softirq context in case of single queue
+	 * devices to avoid degrading I/O performance due to irqsoff latency.
 	 */
-	if (q->nr_hw_queues == 1) {
-		__blk_complete_request(rq);
-		return;
-	}
+	if (rq->q->nr_hw_queues == 1)
+		blk_mq_trigger_softirq(rq);
+	else
+		rq->q->mq_ops->complete(rq);
+}
+
+static inline bool blk_mq_complete_need_ipi(struct request *rq)
+{
+	int cpu = raw_smp_processor_id();
+
+	if (!IS_ENABLED(CONFIG_SMP) ||
+	    !test_bit(QUEUE_FLAG_SAME_COMP, &rq->q->queue_flags))
+		return false;
+
+	/* same CPU or cache domain?  Complete locally */
+	if (cpu == rq->mq_ctx->cpu ||
+	    (!test_bit(QUEUE_FLAG_SAME_FORCE, &rq->q->queue_flags) &&
+	     cpus_share_cache(cpu, rq->mq_ctx->cpu)))
+		return false;
+
+	/* don't try to IPI to an offline CPU */
+	return cpu_online(rq->mq_ctx->cpu);
+}
+
+bool blk_mq_complete_request_remote(struct request *rq)
+{
+	WRITE_ONCE(rq->state, MQ_RQ_COMPLETE);
 
 	/*
 	 * For a polled request, always complete locallly, it's pointless
 	 * to redirect the completion.
 	 */
-	if ((rq->cmd_flags & REQ_HIPRI) ||
-	    !test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags)) {
-		q->mq_ops->complete(rq);
-		return;
-	}
-
-	cpu = get_cpu();
-	if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags))
-		shared = cpus_share_cache(cpu, ctx->cpu);
+	if (rq->cmd_flags & REQ_HIPRI)
+		return false;
 
-	if (cpu != ctx->cpu && !shared && cpu_online(ctx->cpu)) {
+	if (blk_mq_complete_need_ipi(rq)) {
 		rq->csd.func = __blk_mq_complete_request_remote;
 		rq->csd.info = rq;
 		rq->csd.flags = 0;
-		smp_call_function_single_async(ctx->cpu, &rq->csd);
+		smp_call_function_single_async(rq->mq_ctx->cpu, &rq->csd);
 	} else {
-		q->mq_ops->complete(rq);
+		if (rq->q->nr_hw_queues > 1)
+			return false;
+		blk_mq_trigger_softirq(rq);
 	}
-	put_cpu();
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(blk_mq_complete_request_remote);
+
+/**
+ * blk_mq_complete_request - end I/O on a request
+ * @rq:		the request being processed
+ *
+ * Description:
+ *	Complete a request by scheduling the ->complete_rq operation.
+ **/
+void blk_mq_complete_request(struct request *rq)
+{
+	if (!blk_mq_complete_request_remote(rq))
+		rq->q->mq_ops->complete(rq);
 }
-EXPORT_SYMBOL_GPL(blk_mq_force_complete_rq);
+EXPORT_SYMBOL(blk_mq_complete_request);
 
 static void hctx_unlock(struct blk_mq_hw_ctx *hctx, int srcu_idx)
 	__releases(hctx->srcu)
@@ -661,23 +720,6 @@ static void hctx_lock(struct blk_mq_hw_ctx *hctx, int *srcu_idx)
 }
 
 /**
- * blk_mq_complete_request - end I/O on a request
- * @rq:		the request being processed
- *
- * Description:
- *	Ends all I/O on a request. It does not handle partial completions.
- *	The actual completion happens out-of-order, through a IPI handler.
- **/
-bool blk_mq_complete_request(struct request *rq)
-{
-	if (unlikely(blk_should_fake_timeout(rq->q)))
-		return false;
-	blk_mq_force_complete_rq(rq);
-	return true;
-}
-EXPORT_SYMBOL(blk_mq_complete_request);
-
-/**
  * blk_mq_start_request - Start processing a request
  * @rq: Pointer to request to be started
  *
@@ -1052,6 +1094,45 @@ static inline unsigned int queued_to_index(unsigned int queued)
 	return min(BLK_MQ_MAX_DISPATCH_ORDER - 1, ilog2(queued) + 1);
 }
 
+static bool __blk_mq_get_driver_tag(struct request *rq)
+{
+	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;
+		tag_offset = 0;
+	}
+
+	if (!hctx_may_queue(rq->mq_hctx, bt))
+		return false;
+	tag = __sbitmap_queue_get(bt);
+	if (tag == BLK_MQ_NO_TAG)
+		return false;
+
+	rq->tag = tag + tag_offset;
+	return true;
+}
+
+static bool blk_mq_get_driver_tag(struct request *rq)
+{
+	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
+
+	if (rq->tag == BLK_MQ_NO_TAG && !__blk_mq_get_driver_tag(rq))
+		return false;
+
+	if ((hctx->flags & BLK_MQ_F_TAG_SHARED) &&
+			!(rq->rq_flags & RQF_MQ_INFLIGHT)) {
+		rq->rq_flags |= RQF_MQ_INFLIGHT;
+		atomic_inc(&hctx->nr_active);
+	}
+	hctx->tags->rqs[rq->tag] = rq;
+	return true;
+}
+
 static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode,
 				int flags, void *key)
 {
@@ -1204,25 +1285,70 @@ static void blk_mq_handle_zone_resource(struct request *rq,
 	__blk_mq_requeue_request(rq);
 }
 
+enum prep_dispatch {
+	PREP_DISPATCH_OK,
+	PREP_DISPATCH_NO_TAG,
+	PREP_DISPATCH_NO_BUDGET,
+};
+
+static enum prep_dispatch blk_mq_prep_dispatch_rq(struct request *rq,
+						  bool need_budget)
+{
+	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
+
+	if (need_budget && !blk_mq_get_dispatch_budget(rq->q)) {
+		blk_mq_put_driver_tag(rq);
+		return PREP_DISPATCH_NO_BUDGET;
+	}
+
+	if (!blk_mq_get_driver_tag(rq)) {
+		/*
+		 * The initial allocation attempt failed, so we need to
+		 * rerun the hardware queue when a tag is freed. The
+		 * waitqueue takes care of that. If the queue is run
+		 * before we add this entry back on the dispatch list,
+		 * we'll re-run it below.
+		 */
+		if (!blk_mq_mark_tag_wait(hctx, rq)) {
+			/*
+			 * All budgets not got from this function will be put
+			 * together during handling partial dispatch
+			 */
+			if (need_budget)
+				blk_mq_put_dispatch_budget(rq->q);
+			return PREP_DISPATCH_NO_TAG;
+		}
+	}
+
+	return PREP_DISPATCH_OK;
+}
+
+/* release all allocated budgets before calling to blk_mq_dispatch_rq_list */
+static void blk_mq_release_budgets(struct request_queue *q,
+		unsigned int nr_budgets)
+{
+	int i;
+
+	for (i = 0; i < nr_budgets; i++)
+		blk_mq_put_dispatch_budget(q);
+}
+
 /*
  * Returns true if we did some work AND can potentially do more.
  */
-bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
-			     bool got_budget)
+bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
+			     unsigned int nr_budgets)
 {
-	struct blk_mq_hw_ctx *hctx;
+	enum prep_dispatch prep;
+	struct request_queue *q = hctx->queue;
 	struct request *rq, *nxt;
-	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;
 
-	WARN_ON(!list_is_singular(list) && got_budget);
-
 	/*
 	 * Now process all the entries, sending them to the driver.
 	 */
@@ -1232,32 +1358,10 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 
 		rq = list_first_entry(list, struct request, queuelist);
 
-		hctx = rq->mq_hctx;
-		if (!got_budget && !blk_mq_get_dispatch_budget(hctx)) {
-			blk_mq_put_driver_tag(rq);
-			no_budget_avail = true;
+		WARN_ON_ONCE(hctx != rq->mq_hctx);
+		prep = blk_mq_prep_dispatch_rq(rq, !nr_budgets);
+		if (prep != PREP_DISPATCH_OK)
 			break;
-		}
-
-		if (!blk_mq_get_driver_tag(rq)) {
-			/*
-			 * The initial allocation attempt failed, so we need to
-			 * rerun the hardware queue when a tag is freed. The
-			 * waitqueue takes care of that. If the queue is run
-			 * before we add this entry back on the dispatch list,
-			 * we'll re-run it below.
-			 */
-			if (!blk_mq_mark_tag_wait(hctx, rq)) {
-				blk_mq_put_dispatch_budget(hctx);
-				/*
-				 * For non-shared tags, the RESTART check
-				 * will suffice.
-				 */
-				if (hctx->flags & BLK_MQ_F_TAG_SHARED)
-					no_tag = true;
-				break;
-			}
-		}
 
 		list_del_init(&rq->queuelist);
 
@@ -1274,31 +1378,35 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 			bd.last = !blk_mq_get_driver_tag(nxt);
 		}
 
+		/*
+		 * once the request is queued to lld, no need to cover the
+		 * budget any more
+		 */
+		if (nr_budgets)
+			nr_budgets--;
 		ret = q->mq_ops->queue_rq(hctx, &bd);
-		if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) {
-			blk_mq_handle_dev_resource(rq, list);
+		switch (ret) {
+		case BLK_STS_OK:
+			queued++;
 			break;
-		} else if (ret == BLK_STS_ZONE_RESOURCE) {
+		case BLK_STS_RESOURCE:
+		case BLK_STS_DEV_RESOURCE:
+			blk_mq_handle_dev_resource(rq, list);
+			goto out;
+		case 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)) {
+			break;
+		default:
 			errors++;
 			blk_mq_end_request(rq, BLK_STS_IOERR);
-			continue;
 		}
-
-		queued++;
 	} while (!list_empty(list));
-
+out:
 	if (!list_empty(&zone_list))
 		list_splice_tail_init(&zone_list, list);
 
@@ -1310,6 +1418,12 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 	 */
 	if (!list_empty(list)) {
 		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);
+		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
@@ -1361,13 +1475,6 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 	} else
 		blk_mq_update_dispatch_busy(hctx, false);
 
-	/*
-	 * If the host/device is unable to accept more work, inform the
-	 * caller of that.
-	 */
-	if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE)
-		return false;
-
 	return (queued + errors) != 0;
 }
 
@@ -1896,11 +2003,11 @@ 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_dispatch_budget(hctx))
+	if (!blk_mq_get_dispatch_budget(q))
 		goto insert;
 
 	if (!blk_mq_get_driver_tag(rq)) {
-		blk_mq_put_dispatch_budget(hctx);
+		blk_mq_put_dispatch_budget(q);
 		goto insert;
 	}
 
@@ -2005,8 +2112,7 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq)
 }
 
 /**
- * blk_mq_make_request - Create and send a request to block device.
- * @q: Request queue pointer.
+ * blk_mq_submit_bio - Create and send a request to block device.
  * @bio: Bio pointer.
  *
  * Builds up a request structure from @q and @bio and send to the device. The
@@ -2020,8 +2126,9 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq)
  *
  * Returns: Request queue cookie.
  */
-blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
+blk_qc_t blk_mq_submit_bio(struct bio *bio)
 {
+	struct request_queue *q = bio->bi_disk->queue;
 	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 = {
@@ -2035,7 +2142,7 @@ blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	blk_status_t ret;
 
 	blk_queue_bounce(q, &bio);
-	__blk_queue_split(q, &bio, &nr_segs);
+	__blk_queue_split(&bio, &nr_segs);
 
 	if (!bio_integrity_prep(bio))
 		goto queue_exit;
@@ -2146,7 +2253,7 @@ queue_exit:
 	blk_queue_exit(q);
 	return BLK_QC_T_NONE;
 }
-EXPORT_SYMBOL_GPL(blk_mq_make_request); /* only for request based dm */
+EXPORT_SYMBOL_GPL(blk_mq_submit_bio); /* 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)
@@ -2886,7 +2993,7 @@ struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set,
 {
 	struct request_queue *uninit_q, *q;
 
-	uninit_q = __blk_alloc_queue(set->numa_node);
+	uninit_q = blk_alloc_queue(set->numa_node);
 	if (!uninit_q)
 		return ERR_PTR(-ENOMEM);
 	uninit_q->queuedata = queuedata;
@@ -3760,6 +3867,15 @@ EXPORT_SYMBOL(blk_mq_rq_cpu);
 
 static int __init blk_mq_init(void)
 {
+	int i;
+
+	for_each_possible_cpu(i)
+		INIT_LIST_HEAD(&per_cpu(blk_cpu_done, i));
+	open_softirq(BLOCK_SOFTIRQ, blk_done_softirq);
+
+	cpuhp_setup_state_nocalls(CPUHP_BLOCK_SOFTIRQ_DEAD,
+				  "block/softirq:dead", NULL,
+				  blk_softirq_cpu_dead);
 	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",