blk-mq-sched: add framework for MQ capable IO schedulers

This adds a set of hooks that intercepts the blk-mq path of
allocating/inserting/issuing/completing requests, allowing
us to develop a scheduler within that framework.

We reuse the existing elevator scheduler API on the registration
side, but augment that with the scheduler flagging support for
the blk-mq interfce, and with a separate set of ops hooks for MQ
devices.

We split driver and scheduler tags, so we can run the scheduling
independently of device queue depth.
Signed-off-by: Jens Axboe <axboe@fb.com>
Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Omar Sandoval <osandov@fb.com>

block/Makefile

@@ -6,7 +6,7 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-tag.o blk-sysfs.o \
 			blk-flush.o blk-settings.o blk-ioc.o blk-map.o \
 			blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \
 			blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \
-			blk-mq-sysfs.o blk-mq-cpumap.o ioctl.o \
+			blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \
 			genhd.o scsi_ioctl.o partition-generic.o ioprio.o \
 			badblocks.o partitions/
 

block/blk-cgroup.c

@@ -1223,7 +1223,11 @@ int blkcg_activate_policy(struct request_queue *q,
 	if (blkcg_policy_enabled(q, pol))
 		return 0;
 
-	blk_queue_bypass_start(q);
+	if (q->mq_ops) {
+		blk_mq_freeze_queue(q);
+		blk_mq_quiesce_queue(q);
+	} else
+		blk_queue_bypass_start(q);
 pd_prealloc:
 	if (!pd_prealloc) {
 		pd_prealloc = pol->pd_alloc_fn(GFP_KERNEL, q->node);
@@ -1261,7 +1265,10 @@ int blkcg_activate_policy(struct request_queue *q,
 
 	spin_unlock_irq(q->queue_lock);
 out_bypass_end:
-	blk_queue_bypass_end(q);
+	if (q->mq_ops)
+		blk_mq_unfreeze_queue(q);
+	else
+		blk_queue_bypass_end(q);
 	if (pd_prealloc)
 		pol->pd_free_fn(pd_prealloc);
 	return ret;
@@ -1284,7 +1291,12 @@ void blkcg_deactivate_policy(struct request_queue *q,
 	if (!blkcg_policy_enabled(q, pol))
 		return;
 
-	blk_queue_bypass_start(q);
+	if (q->mq_ops) {
+		blk_mq_freeze_queue(q);
+		blk_mq_quiesce_queue(q);
+	} else
+		blk_queue_bypass_start(q);
+
 	spin_lock_irq(q->queue_lock);
 
 	__clear_bit(pol->plid, q->blkcg_pols);
@@ -1304,7 +1316,11 @@ void blkcg_deactivate_policy(struct request_queue *q,
 	}
 
 	spin_unlock_irq(q->queue_lock);
-	blk_queue_bypass_end(q);
+
+	if (q->mq_ops)
+		blk_mq_unfreeze_queue(q);
+	else
+		blk_queue_bypass_end(q);
 }
 EXPORT_SYMBOL_GPL(blkcg_deactivate_policy);
 

block/blk-core.c

@@ -39,6 +39,7 @@
 
 #include "blk.h"
 #include "blk-mq.h"
+#include "blk-mq-sched.h"
 #include "blk-wbt.h"
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);
@@ -134,6 +135,7 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 	rq->cmd = rq->__cmd;
 	rq->cmd_len = BLK_MAX_CDB;
 	rq->tag = -1;
+	rq->internal_tag = -1;
 	rq->start_time = jiffies;
 	set_start_time_ns(rq);
 	rq->part = NULL;
@@ -2127,7 +2129,7 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 	if (q->mq_ops) {
 		if (blk_queue_io_stat(q))
 			blk_account_io_start(rq, true);
-		blk_mq_insert_request(rq, false, true, false);
+		blk_mq_sched_insert_request(rq, false, true, false);
 		return 0;
 	}
 

block/blk-exec.c

@@ -9,6 +9,7 @@
 #include <linux/sched/sysctl.h>
 
 #include "blk.h"
+#include "blk-mq-sched.h"
 
 /*
  * for max sense size
@@ -65,7 +66,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 	 * be reused after dying flag is set
 	 */
 	if (q->mq_ops) {
-		blk_mq_insert_request(rq, at_head, true, false);
+		blk_mq_sched_insert_request(rq, at_head, true, false);
 		return;
 	}
 

block/blk-flush.c

@@ -74,6 +74,7 @@
 #include "blk.h"
 #include "blk-mq.h"
 #include "blk-mq-tag.h"
+#include "blk-mq-sched.h"
 
 /* FLUSH/FUA sequences */
 enum {
@@ -391,9 +392,10 @@ static void mq_flush_data_end_io(struct request *rq, int error)
 	 * the comment in flush_end_io().
 	 */
 	spin_lock_irqsave(&fq->mq_flush_lock, flags);
-	if (blk_flush_complete_seq(rq, fq, REQ_FSEQ_DATA, error))
-		blk_mq_run_hw_queue(hctx, true);
+	blk_flush_complete_seq(rq, fq, REQ_FSEQ_DATA, error);
 	spin_unlock_irqrestore(&fq->mq_flush_lock, flags);
+
+	blk_mq_run_hw_queue(hctx, true);
 }
 
 /**
@@ -453,9 +455,9 @@ void blk_insert_flush(struct request *rq)
 	 */
 	if ((policy & REQ_FSEQ_DATA) &&
 	    !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
-		if (q->mq_ops) {
-			blk_mq_insert_request(rq, false, true, false);
-		} else
+		if (q->mq_ops)
+			blk_mq_sched_insert_request(rq, false, true, false);
+		else
 			list_add_tail(&rq->queuelist, &q->queue_head);
 		return;
 	}

block/blk-ioc.c

@@ -43,7 +43,9 @@ static void ioc_exit_icq(struct io_cq *icq)
 	if (icq->flags & ICQ_EXITED)
 		return;
 
-	if (et->ops.sq.elevator_exit_icq_fn)
+	if (et->uses_mq && et->ops.mq.exit_icq)
+		et->ops.mq.exit_icq(icq);
+	else if (!et->uses_mq && et->ops.sq.elevator_exit_icq_fn)
 		et->ops.sq.elevator_exit_icq_fn(icq);
 
 	icq->flags |= ICQ_EXITED;
@@ -383,7 +385,9 @@ struct io_cq *ioc_create_icq(struct io_context *ioc, struct request_queue *q,
 	if (likely(!radix_tree_insert(&ioc->icq_tree, q->id, icq))) {
 		hlist_add_head(&icq->ioc_node, &ioc->icq_list);
 		list_add(&icq->q_node, &q->icq_list);
-		if (et->ops.sq.elevator_init_icq_fn)
+		if (et->uses_mq && et->ops.mq.init_icq)
+			et->ops.mq.init_icq(icq);
+		else if (!et->uses_mq && et->ops.sq.elevator_init_icq_fn)
 			et->ops.sq.elevator_init_icq_fn(icq);
 	} else {
 		kmem_cache_free(et->icq_cache, icq);

block/blk-merge.c

@@ -763,7 +763,7 @@ int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.sq.elevator_allow_rq_merge_fn)
+	if (!e->uses_mq && e->type->ops.sq.elevator_allow_rq_merge_fn)
 		if (!e->type->ops.sq.elevator_allow_rq_merge_fn(q, rq, next))
 			return 0;
 

block/blk-mq-sched.c

+/*
+ * blk-mq scheduling framework
+ *
+ * Copyright (C) 2016 Jens Axboe
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/blk-mq.h>
+
+#include <trace/events/block.h>
+
+#include "blk.h"
+#include "blk-mq.h"
+#include "blk-mq-sched.h"
+#include "blk-mq-tag.h"
+#include "blk-wbt.h"
+
+void blk_mq_sched_free_hctx_data(struct request_queue *q,
+				 void (*exit)(struct blk_mq_hw_ctx *))
+{
+	struct blk_mq_hw_ctx *hctx;
+	int i;
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		if (exit && hctx->sched_data)
+			exit(hctx);
+		kfree(hctx->sched_data);
+		hctx->sched_data = NULL;
+	}
+}
+EXPORT_SYMBOL_GPL(blk_mq_sched_free_hctx_data);
+
+int blk_mq_sched_init_hctx_data(struct request_queue *q, size_t size,
+				int (*init)(struct blk_mq_hw_ctx *),
+				void (*exit)(struct blk_mq_hw_ctx *))
+{
+	struct blk_mq_hw_ctx *hctx;
+	int ret;
+	int i;
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		hctx->sched_data = kmalloc_node(size, GFP_KERNEL, hctx->numa_node);
+		if (!hctx->sched_data) {
+			ret = -ENOMEM;
+			goto error;
+		}
+
+		if (init) {
+			ret = init(hctx);
+			if (ret) {
+				/*
+				 * We don't want to give exit() a partially
+				 * initialized sched_data. init() must clean up
+				 * if it fails.
+				 */
+				kfree(hctx->sched_data);
+				hctx->sched_data = NULL;
+				goto error;
+			}
+		}
+	}
+
+	return 0;
+error:
+	blk_mq_sched_free_hctx_data(q, exit);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(blk_mq_sched_init_hctx_data);
+
+static void __blk_mq_sched_assign_ioc(struct request_queue *q,
+				      struct request *rq, struct io_context *ioc)
+{
+	struct io_cq *icq;
+
+	spin_lock_irq(q->queue_lock);
+	icq = ioc_lookup_icq(ioc, q);
+	spin_unlock_irq(q->queue_lock);
+
+	if (!icq) {
+		icq = ioc_create_icq(ioc, q, GFP_ATOMIC);
+		if (!icq)
+			return;
+	}
+
+	rq->elv.icq = icq;
+	if (!blk_mq_sched_get_rq_priv(q, rq)) {
+		rq->rq_flags |= RQF_ELVPRIV;
+		get_io_context(icq->ioc);
+		return;
+	}
+
+	rq->elv.icq = NULL;
+}
+
+static void blk_mq_sched_assign_ioc(struct request_queue *q,
+				    struct request *rq, struct bio *bio)
+{
+	struct io_context *ioc;
+
+	ioc = rq_ioc(bio);
+	if (ioc)
+		__blk_mq_sched_assign_ioc(q, rq, ioc);
+}
+
+struct request *blk_mq_sched_get_request(struct request_queue *q,
+					 struct bio *bio,
+					 unsigned int op,
+					 struct blk_mq_alloc_data *data)
+{
+	struct elevator_queue *e = q->elevator;
+	struct blk_mq_hw_ctx *hctx;
+	struct blk_mq_ctx *ctx;
+	struct request *rq;
+	const bool is_flush = op & (REQ_PREFLUSH | REQ_FUA);
+
+	blk_queue_enter_live(q);
+	ctx = blk_mq_get_ctx(q);
+	hctx = blk_mq_map_queue(q, ctx->cpu);
+
+	blk_mq_set_alloc_data(data, q, 0, ctx, hctx);
+
+	if (e) {
+		data->flags |= BLK_MQ_REQ_INTERNAL;
+
+		/*
+		 * Flush requests are special and go directly to the
+		 * dispatch list.
+		 */
+		if (!is_flush && e->type->ops.mq.get_request) {
+			rq = e->type->ops.mq.get_request(q, op, data);
+			if (rq)
+				rq->rq_flags |= RQF_QUEUED;
+		} else
+			rq = __blk_mq_alloc_request(data, op);
+	} else {
+		rq = __blk_mq_alloc_request(data, op);
+		data->hctx->tags->rqs[rq->tag] = rq;
+	}
+
+	if (rq) {
+		if (!is_flush) {
+			rq->elv.icq = NULL;
+			if (e && e->type->icq_cache)
+				blk_mq_sched_assign_ioc(q, rq, bio);
+		}
+		data->hctx->queued++;
+		return rq;
+	}
+
+	blk_queue_exit(q);
+	return NULL;
+}
+
+void blk_mq_sched_put_request(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+	struct elevator_queue *e = q->elevator;
+
+	if (rq->rq_flags & RQF_ELVPRIV) {
+		blk_mq_sched_put_rq_priv(rq->q, rq);
+		if (rq->elv.icq) {
+			put_io_context(rq->elv.icq->ioc);
+			rq->elv.icq = NULL;
+		}
+	}
+
+	if ((rq->rq_flags & RQF_QUEUED) && e && e->type->ops.mq.put_request)
+		e->type->ops.mq.put_request(rq);
+	else
+		blk_mq_finish_request(rq);
+}
+
+void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
+{
+	struct elevator_queue *e = hctx->queue->elevator;
+	LIST_HEAD(rq_list);
+
+	if (unlikely(blk_mq_hctx_stopped(hctx)))
+		return;
+
+	hctx->run++;
+
+	/*
+	 * If we have previous entries on our dispatch list, grab them first for
+	 * more fair dispatch.
+	 */
+	if (!list_empty_careful(&hctx->dispatch)) {
+		spin_lock(&hctx->lock);
+		if (!list_empty(&hctx->dispatch))
+			list_splice_init(&hctx->dispatch, &rq_list);
+		spin_unlock(&hctx->lock);
+	}
+
+	/*
+	 * Only ask the scheduler for requests, if we didn't have residual
+	 * requests from the dispatch list. This is to avoid the case where
+	 * we only ever dispatch a fraction of the requests available because
+	 * of low device queue depth. Once we pull requests out of the IO
+	 * scheduler, we can no longer merge or sort them. So it's best to
+	 * leave them there for as long as we can. Mark the hw queue as
+	 * needing a restart in that case.
+	 */
+	if (list_empty(&rq_list)) {
+		if (e && e->type->ops.mq.dispatch_requests)
+			e->type->ops.mq.dispatch_requests(hctx, &rq_list);
+		else
+			blk_mq_flush_busy_ctxs(hctx, &rq_list);
+	} else
+		blk_mq_sched_mark_restart(hctx);
+
+	blk_mq_dispatch_rq_list(hctx, &rq_list);
+}
+
+void blk_mq_sched_move_to_dispatch(struct blk_mq_hw_ctx *hctx,
+				   struct list_head *rq_list,
+				   struct request *(*get_rq)(struct blk_mq_hw_ctx *))
+{
+	do {
+		struct request *rq;
+
+		rq = get_rq(hctx);
+		if (!rq)
+			break;
+
+		list_add_tail(&rq->queuelist, rq_list);
+	} while (1);
+}
+EXPORT_SYMBOL_GPL(blk_mq_sched_move_to_dispatch);
+
+bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio)
+{
+	struct request *rq;
+	int ret;
+
+	ret = elv_merge(q, &rq, bio);
+	if (ret == ELEVATOR_BACK_MERGE) {
+		if (!blk_mq_sched_allow_merge(q, rq, bio))
+			return false;
+		if (bio_attempt_back_merge(q, rq, bio)) {
+			if (!attempt_back_merge(q, rq))
+				elv_merged_request(q, rq, ret);
+			return true;
+		}
+	} else if (ret == ELEVATOR_FRONT_MERGE) {
+		if (!blk_mq_sched_allow_merge(q, rq, bio))
+			return false;
+		if (bio_attempt_front_merge(q, rq, bio)) {
+			if (!attempt_front_merge(q, rq))
+				elv_merged_request(q, rq, ret);
+			return true;
+		}
+	}
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(blk_mq_sched_try_merge);
+
+bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (e->type->ops.mq.bio_merge) {
+		struct blk_mq_ctx *ctx = blk_mq_get_ctx(q);
+		struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
+
+		blk_mq_put_ctx(ctx);
+		return e->type->ops.mq.bio_merge(hctx, bio);
+	}
+
+	return false;
+}
+
+bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq)
+{
+	return rq_mergeable(rq) && elv_attempt_insert_merge(q, rq);
+}
+EXPORT_SYMBOL_GPL(blk_mq_sched_try_insert_merge);
+
+void blk_mq_sched_request_inserted(struct request *rq)
+{
+	trace_block_rq_insert(rq->q, rq);
+}
+EXPORT_SYMBOL_GPL(blk_mq_sched_request_inserted);
+
+bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx, struct request *rq)
+{
+	if (rq->tag == -1) {
+		rq->rq_flags |= RQF_SORTED;
+		return false;
+	}
+
+	/*
+	 * If we already have a real request tag, send directly to
+	 * the dispatch list.
+	 */
+	spin_lock(&hctx->lock);
+	list_add(&rq->queuelist, &hctx->dispatch);
+	spin_unlock(&hctx->lock);
+	return true;
+}
+EXPORT_SYMBOL_GPL(blk_mq_sched_bypass_insert);
+
+static void blk_mq_sched_free_tags(struct blk_mq_tag_set *set,
+				   struct blk_mq_hw_ctx *hctx,
+				   unsigned int hctx_idx)
+{
+	if (hctx->sched_tags) {
+		blk_mq_free_rqs(set, hctx->sched_tags, hctx_idx);
+		blk_mq_free_rq_map(hctx->sched_tags);
+		hctx->sched_tags = NULL;
+	}
+}
+
+int blk_mq_sched_setup(struct request_queue *q)
+{
+	struct blk_mq_tag_set *set = q->tag_set;
+	struct blk_mq_hw_ctx *hctx;
+	int ret, i;
+
+	/*
+	 * Default to 256, since we don't split into sync/async like the
+	 * old code did. Additionally, this is a per-hw queue depth.
+	 */
+	q->nr_requests = 2 * BLKDEV_MAX_RQ;
+
+	/*
+	 * We're switching to using an IO scheduler, so setup the hctx
+	 * scheduler tags and switch the request map from the regular
+	 * tags to scheduler tags. First allocate what we need, so we
+	 * can safely fail and fallback, if needed.
+	 */
+	ret = 0;
+	queue_for_each_hw_ctx(q, hctx, i) {
+		hctx->sched_tags = blk_mq_alloc_rq_map(set, i, q->nr_requests, 0);
+		if (!hctx->sched_tags) {
+			ret = -ENOMEM;
+			break;
+		}
+		ret = blk_mq_alloc_rqs(set, hctx->sched_tags, i, q->nr_requests);
+		if (ret)
+			break;
+	}
+
+	/*
+	 * If we failed, free what we did allocate
+	 */
+	if (ret) {
+		queue_for_each_hw_ctx(q, hctx, i) {
+			if (!hctx->sched_tags)
+				continue;
+			blk_mq_sched_free_tags(set, hctx, i);
+		}
+
+		return ret;
+	}
+
+	return 0;
+}
+
+void blk_mq_sched_teardown(struct request_queue *q)
+{
+	struct blk_mq_tag_set *set = q->tag_set;
+	struct blk_mq_hw_ctx *hctx;
+	int i;
+
+	queue_for_each_hw_ctx(q, hctx, i)
+		blk_mq_sched_free_tags(set, hctx, i);
+}

block/blk-mq-sched.h

+#ifndef BLK_MQ_SCHED_H
+#define BLK_MQ_SCHED_H
+
+#include "blk-mq.h"
+#include "blk-mq-tag.h"
+
+int blk_mq_sched_init_hctx_data(struct request_queue *q, size_t size,
+				int (*init)(struct blk_mq_hw_ctx *),
+				void (*exit)(struct blk_mq_hw_ctx *));
+
+void blk_mq_sched_free_hctx_data(struct request_queue *q,
+				 void (*exit)(struct blk_mq_hw_ctx *));
+
+struct request *blk_mq_sched_get_request(struct request_queue *q, struct bio *bio, unsigned int op, struct blk_mq_alloc_data *data);
+void blk_mq_sched_put_request(struct request *rq);
+
+void blk_mq_sched_request_inserted(struct request *rq);
+bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx, struct request *rq);
+bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio);
+bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio);
+bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq);
+
+void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx);
+void blk_mq_sched_move_to_dispatch(struct blk_mq_hw_ctx *hctx,
+			struct list_head *rq_list,
+			struct request *(*get_rq)(struct blk_mq_hw_ctx *));
+
+int blk_mq_sched_setup(struct request_queue *q);
+void blk_mq_sched_teardown(struct request_queue *q);
+
+static inline bool
+blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (!e || blk_queue_nomerges(q) || !bio_mergeable(bio))
+		return false;
+
+	return __blk_mq_sched_bio_merge(q, bio);
+}
+
+static inline int blk_mq_sched_get_rq_priv(struct request_queue *q,
+					   struct request *rq)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (e && e->type->ops.mq.get_rq_priv)
+		return e->type->ops.mq.get_rq_priv(q, rq);
+
+	return 0;
+}
+
+static inline void blk_mq_sched_put_rq_priv(struct request_queue *q,
+					    struct request *rq)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (e && e->type->ops.mq.put_rq_priv)
+		e->type->ops.mq.put_rq_priv(q, rq);
+}
+
+static inline void
+blk_mq_sched_insert_request(struct request *rq, bool at_head, bool run_queue,
+			    bool async)
+{
+	struct request_queue *q = rq->q;
+	struct elevator_queue *e = q->elevator;
+	struct blk_mq_ctx *ctx = rq->mq_ctx;
+	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
+
+	if (e && e->type->ops.mq.insert_requests) {
+		LIST_HEAD(list);
+
+		list_add(&rq->queuelist, &list);
+		e->type->ops.mq.insert_requests(hctx, &list, at_head);
+	} else {
+		spin_lock(&ctx->lock);
+		__blk_mq_insert_request(hctx, rq, at_head);
+		spin_unlock(&ctx->lock);
+	}
+
+	if (run_queue)
+		blk_mq_run_hw_queue(hctx, async);
+}
+
+static inline void
+blk_mq_sched_insert_requests(struct request_queue *q, struct blk_mq_ctx *ctx,
+			     struct list_head *list, bool run_queue_async)
+{
+	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
+	struct elevator_queue *e = hctx->queue->elevator;
+
+	if (e && e->type->ops.mq.insert_requests)
+		e->type->ops.mq.insert_requests(hctx, list, false);
+	else
+		blk_mq_insert_requests(hctx, ctx, list);
+
+	blk_mq_run_hw_queue(hctx, run_queue_async);
+}
+
+static inline bool
+blk_mq_sched_allow_merge(struct request_queue *q, struct request *rq,
+			 struct bio *bio)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (e && e->type->ops.mq.allow_merge)
+		return e->type->ops.mq.allow_merge(q, rq, bio);
+
+	return true;
+}
+
+static inline void
+blk_mq_sched_completed_request(struct blk_mq_hw_ctx *hctx, struct request *rq)
+{
+	struct elevator_queue *e = hctx->queue->elevator;
+
+	if (e && e->type->ops.mq.completed_request)
+		e->type->ops.mq.completed_request(hctx, rq);
+
+	BUG_ON(rq->internal_tag == -1);
+
+	blk_mq_put_tag(hctx, hctx->sched_tags, rq->mq_ctx, rq->internal_tag);
+
+	if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) {
+		clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
+		blk_mq_run_hw_queue(hctx, true);
+	}
+}
+
+static inline void blk_mq_sched_started_request(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+	struct elevator_queue *e = q->elevator;
+
+	if (e && e->type->ops.mq.started_request)
+		e->type->ops.mq.started_request(rq);
+}
+
+static inline void blk_mq_sched_requeue_request(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+	struct elevator_queue *e = q->elevator;
+
+	if (e && e->type->ops.mq.requeue_request)
+		e->type->ops.mq.requeue_request(rq);
+}
+
+static inline bool blk_mq_sched_has_work(struct blk_mq_hw_ctx *hctx)
+{
+	struct elevator_queue *e = hctx->queue->elevator;
+
+	if (e && e->type->ops.mq.has_work)
+		return e->type->ops.mq.has_work(hctx);
+
+	return false;
+}
+
+static inline void blk_mq_sched_mark_restart(struct blk_mq_hw_ctx *hctx)
+{
+	if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
+		set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
+}
+
+static inline bool blk_mq_sched_needs_restart(struct blk_mq_hw_ctx *hctx)
+{
+	return test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
+}
+
+#endif

block/blk-mq-sysfs.c

@@ -231,6 +231,14 @@ static ssize_t blk_mq_hw_sysfs_rq_list_show(struct blk_mq_hw_ctx *hctx,
 	return ret;
 }
 
+static ssize_t blk_mq_hw_sysfs_sched_tags_show(struct blk_mq_hw_ctx *hctx, char *page)
+{
+	if (hctx->sched_tags)
+		return blk_mq_tag_sysfs_show(hctx->sched_tags, page);
+
+	return 0;
+}
+
 static ssize_t blk_mq_hw_sysfs_tags_show(struct blk_mq_hw_ctx *hctx, char *page)
 {
 	return blk_mq_tag_sysfs_show(hctx->tags, page);
@@ -345,6 +353,10 @@ static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_pending = {
 	.attr = {.name = "pending", .mode = S_IRUGO },
 	.show = blk_mq_hw_sysfs_rq_list_show,
 };
+static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_sched_tags = {
+	.attr = {.name = "sched_tags", .mode = S_IRUGO },
+	.show = blk_mq_hw_sysfs_sched_tags_show,
+};
 static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_tags = {
 	.attr = {.name = "tags", .mode = S_IRUGO },
 	.show = blk_mq_hw_sysfs_tags_show,
@@ -370,6 +382,7 @@ static struct attribute *default_hw_ctx_attrs[] = {
 	&blk_mq_hw_sysfs_dispatched.attr,
 	&blk_mq_hw_sysfs_pending.attr,
 	&blk_mq_hw_sysfs_tags.attr,
+	&blk_mq_hw_sysfs_sched_tags.attr,
 	&blk_mq_hw_sysfs_cpus.attr,
 	&blk_mq_hw_sysfs_active.attr,
 	&blk_mq_hw_sysfs_poll.attr,

block/blk-mq.h

@@ -52,6 +52,8 @@ int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
  */
 void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 				bool at_head);
+void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
+				struct list_head *list);
 /*
  * CPU hotplug helpers
  */
@@ -124,6 +126,9 @@ static inline void blk_mq_set_alloc_data(struct blk_mq_alloc_data *data,
 
 static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data *data)
 {
+	if (data->flags & BLK_MQ_REQ_INTERNAL)
+		return data->hctx->sched_tags;
+
 	return data->hctx->tags;
 }
 
@@ -132,8 +137,9 @@ static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data
  */
 void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
 			struct request *rq, unsigned int op);
-void __blk_mq_free_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
+void __blk_mq_finish_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 				struct request *rq);
+void blk_mq_finish_request(struct request *rq);
 struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data,
 					unsigned int op);
 

block/blk-tag.c

@@ -272,6 +272,7 @@ void blk_queue_end_tag(struct request_queue *q, struct request *rq)
 	list_del_init(&rq->queuelist);
 	rq->rq_flags &= ~RQF_QUEUED;
 	rq->tag = -1;
+	rq->internal_tag = -1;
 
 	if (unlikely(bqt->tag_index[tag] == NULL))
 		printk(KERN_ERR "%s: tag %d is missing\n",

include/linux/blk-mq.h

@@ -22,6 +22,7 @@ struct blk_mq_hw_ctx {
 
 	unsigned long		flags;		/* BLK_MQ_F_* flags */
 
+	void			*sched_data;
 	struct request_queue	*queue;
 	struct blk_flush_queue	*fq;
 
@@ -35,6 +36,7 @@ struct blk_mq_hw_ctx {
 	atomic_t		wait_index;
 
 	struct blk_mq_tags	*tags;
+	struct blk_mq_tags	*sched_tags;
 
 	struct srcu_struct	queue_rq_srcu;
 
@@ -156,6 +158,7 @@ enum {
 
 	BLK_MQ_S_STOPPED	= 0,
 	BLK_MQ_S_TAG_ACTIVE	= 1,
+	BLK_MQ_S_SCHED_RESTART	= 2,
 
 	BLK_MQ_MAX_DEPTH	= 10240,
 
@@ -179,13 +182,13 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set);
 
 void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);
 
-void blk_mq_insert_request(struct request *, bool, bool, bool);
 void blk_mq_free_request(struct request *rq);
 bool blk_mq_can_queue(struct blk_mq_hw_ctx *);
 
 enum {
 	BLK_MQ_REQ_NOWAIT	= (1 << 0), /* return when out of requests */
 	BLK_MQ_REQ_RESERVED	= (1 << 1), /* allocate from reserved pool */
+	BLK_MQ_REQ_INTERNAL	= (1 << 2), /* allocate internal/sched tag */
 };
 
 struct request *blk_mq_alloc_request(struct request_queue *q, int rw,

include/linux/blkdev.h

@@ -154,6 +154,7 @@ struct request {
 
 	/* the following two fields are internal, NEVER access directly */
 	unsigned int __data_len;	/* total data len */
+	int tag;
 	sector_t __sector;		/* sector cursor */
 
 	struct bio *bio;
@@ -220,9 +221,10 @@ struct request {
 
 	unsigned short ioprio;
 
+	int internal_tag;
+
 	void *special;		/* opaque pointer available for LLD use */
 
-	int tag;
 	int errors;
 
 	/*

include/linux/elevator.h

@@ -77,6 +77,34 @@ struct elevator_ops
 	elevator_registered_fn *elevator_registered_fn;
 };
 
+struct blk_mq_alloc_data;
+struct blk_mq_hw_ctx;
+
+struct elevator_mq_ops {
+	int (*init_sched)(struct request_queue *, struct elevator_type *);
+	void (*exit_sched)(struct elevator_queue *);
+
+	bool (*allow_merge)(struct request_queue *, struct request *, struct bio *);
+	bool (*bio_merge)(struct blk_mq_hw_ctx *, struct bio *);
+	int (*request_merge)(struct request_queue *q, struct request **, struct bio *);
+	void (*request_merged)(struct request_queue *, struct request *, int);
+	void (*requests_merged)(struct request_queue *, struct request *, struct request *);
+	struct request *(*get_request)(struct request_queue *, unsigned int, struct blk_mq_alloc_data *);
+	void (*put_request)(struct request *);
+	void (*insert_requests)(struct blk_mq_hw_ctx *, struct list_head *, bool);
+	void (*dispatch_requests)(struct blk_mq_hw_ctx *, struct list_head *);
+	bool (*has_work)(struct blk_mq_hw_ctx *);
+	void (*completed_request)(struct blk_mq_hw_ctx *, struct request *);
+	void (*started_request)(struct request *);
+	void (*requeue_request)(struct request *);
+	struct request *(*former_request)(struct request_queue *, struct request *);
+	struct request *(*next_request)(struct request_queue *, struct request *);
+	int (*get_rq_priv)(struct request_queue *, struct request *);
+	void (*put_rq_priv)(struct request_queue *, struct request *);
+	void (*init_icq)(struct io_cq *);
+	void (*exit_icq)(struct io_cq *);
+};
+
 #define ELV_NAME_MAX	(16)
 
 struct elv_fs_entry {
@@ -96,12 +124,14 @@ struct elevator_type
 	/* fields provided by elevator implementation */
 	union {
 		struct elevator_ops sq;
+		struct elevator_mq_ops mq;
 	} ops;
 	size_t icq_size;	/* see iocontext.h */
 	size_t icq_align;	/* ditto */
 	struct elv_fs_entry *elevator_attrs;
 	char elevator_name[ELV_NAME_MAX];
 	struct module *elevator_owner;
+	bool uses_mq;
 
 	/* managed by elevator core */
 	char icq_cache_name[ELV_NAME_MAX + 5];	/* elvname + "_io_cq" */
@@ -125,6 +155,7 @@ struct elevator_queue
 	struct kobject kobj;
 	struct mutex sysfs_lock;
 	unsigned int registered:1;
+	unsigned int uses_mq:1;
 	DECLARE_HASHTABLE(hash, ELV_HASH_BITS);
 };
 
@@ -141,6 +172,7 @@ extern void elv_merge_requests(struct request_queue *, struct request *,
 extern void elv_merged_request(struct request_queue *, struct request *, int);
 extern void elv_bio_merged(struct request_queue *q, struct request *,
 				struct bio *);
+extern bool elv_attempt_insert_merge(struct request_queue *, struct request *);
 extern void elv_requeue_request(struct request_queue *, struct request *);
 extern struct request *elv_former_request(struct request_queue *, struct request *);
 extern struct request *elv_latter_request(struct request_queue *, struct request *);