Merge branch 'for-4.11/block' into for-4.11/rq-refactor

Signed-off-by: Jens Axboe <axboe@fb.com>

MAINTAINERS

@@ -8604,10 +8604,10 @@ S:	Maintained
 F:	drivers/net/ethernet/netronome/
 
 NETWORK BLOCK DEVICE (NBD)
-M:	Markus Pargmann <mpa@pengutronix.de>
+M:	Josef Bacik <jbacik@fb.com>
 S:	Maintained
+L:	linux-block@vger.kernel.org
 L:	nbd-general@lists.sourceforge.net
-T:	git git://git.pengutronix.de/git/mpa/linux-nbd.git
 F:	Documentation/blockdev/nbd.txt
 F:	drivers/block/nbd.c
 F:	include/uapi/linux/nbd.h

block/Kconfig

@@ -147,6 +147,18 @@ config BLK_WBT_MQ
 	Multiqueue currently doesn't have support for IO scheduling,
 	enabling this option is recommended.
 
+config BLK_DEBUG_FS
+	bool "Block layer debugging information in debugfs"
+	default y
+	depends on DEBUG_FS
+	---help---
+	Include block layer debugging information in debugfs. This information
+	is mostly useful for kernel developers, but it doesn't incur any cost
+	at runtime.
+
+	Unless you are building a kernel for a tiny system, you should
+	say Y here.
+
 menu "Partition Types"
 
 source "block/partitions/Kconfig"

block/Kconfig.iosched

@@ -63,6 +63,56 @@ config DEFAULT_IOSCHED
 	default "cfq" if DEFAULT_CFQ
 	default "noop" if DEFAULT_NOOP
 
+config MQ_IOSCHED_DEADLINE
+	tristate "MQ deadline I/O scheduler"
+	default y
+	---help---
+	  MQ version of the deadline IO scheduler.
+
+config MQ_IOSCHED_NONE
+	bool
+	default y
+
+choice
+	prompt "Default single-queue blk-mq I/O scheduler"
+	default DEFAULT_SQ_NONE
+	help
+	  Select the I/O scheduler which will be used by default for blk-mq
+	  managed block devices with a single queue.
+
+	config DEFAULT_SQ_DEADLINE
+		bool "MQ Deadline" if MQ_IOSCHED_DEADLINE=y
+
+	config DEFAULT_SQ_NONE
+		bool "None"
+
+endchoice
+
+config DEFAULT_SQ_IOSCHED
+	string
+	default "mq-deadline" if DEFAULT_SQ_DEADLINE
+	default "none" if DEFAULT_SQ_NONE
+
+choice
+	prompt "Default multi-queue blk-mq I/O scheduler"
+	default DEFAULT_MQ_NONE
+	help
+	  Select the I/O scheduler which will be used by default for blk-mq
+	  managed block devices with multiple queues.
+
+	config DEFAULT_MQ_DEADLINE
+		bool "MQ Deadline" if MQ_IOSCHED_DEADLINE=y
+
+	config DEFAULT_MQ_NONE
+		bool "None"
+
+endchoice
+
+config DEFAULT_MQ_IOSCHED
+	string
+	default "mq-deadline" if DEFAULT_MQ_DEADLINE
+	default "none" if DEFAULT_MQ_NONE
+
 endmenu
 
 endif

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/
 
@@ -18,6 +18,7 @@ obj-$(CONFIG_BLK_DEV_THROTTLING)	+= blk-throttle.o
 obj-$(CONFIG_IOSCHED_NOOP)	+= noop-iosched.o
 obj-$(CONFIG_IOSCHED_DEADLINE)	+= deadline-iosched.o
 obj-$(CONFIG_IOSCHED_CFQ)	+= cfq-iosched.o
+obj-$(CONFIG_MQ_IOSCHED_DEADLINE)	+= mq-deadline.o
 
 obj-$(CONFIG_BLOCK_COMPAT)	+= compat_ioctl.o
 obj-$(CONFIG_BLK_CMDLINE_PARSER)	+= cmdline-parser.o
@@ -25,3 +26,4 @@ obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o t10-pi.o
 obj-$(CONFIG_BLK_MQ_PCI)	+= blk-mq-pci.o
 obj-$(CONFIG_BLK_DEV_ZONED)	+= blk-zoned.o
 obj-$(CONFIG_BLK_WBT)		+= blk-wbt.o
+obj-$(CONFIG_BLK_DEBUG_FS)	+= blk-mq-debugfs.o

block/blk-cgroup.c

@@ -1223,7 +1223,10 @@ 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);
+	else
+		blk_queue_bypass_start(q);
 pd_prealloc:
 	if (!pd_prealloc) {
 		pd_prealloc = pol->pd_alloc_fn(GFP_KERNEL, q->node);
@@ -1261,7 +1264,10 @@ pd_prealloc:
 
 	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 +1290,11 @@ 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);
+	else
+		blk_queue_bypass_start(q);
+
 	spin_lock_irq(q->queue_lock);
 
 	__clear_bit(pol->plid, q->blkcg_pols);
@@ -1304,7 +1314,11 @@ 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;
@@ -1033,28 +1035,12 @@ static bool blk_rq_should_init_elevator(struct bio *bio)
 	 * Flush requests do not use the elevator so skip initialization.
 	 * This allows a request to share the flush and elevator data.
 	 */
-	if (bio->bi_opf & (REQ_PREFLUSH | REQ_FUA))
+	if (op_is_flush(bio->bi_opf))
 		return false;
 
 	return true;
 }
 
-/**
- * rq_ioc - determine io_context for request allocation
- * @bio: request being allocated is for this bio (can be %NULL)
- *
- * Determine io_context to use for request allocation for @bio.  May return
- * %NULL if %current->io_context doesn't exist.
- */
-static struct io_context *rq_ioc(struct bio *bio)
-{
-#ifdef CONFIG_BLK_CGROUP
-	if (bio && bio->bi_ioc)
-		return bio->bi_ioc;
-#endif
-	return current->io_context;
-}
-
 /**
  * __get_request - get a free request
  * @rl: request list to allocate from
@@ -1655,7 +1641,7 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 		return BLK_QC_T_NONE;
 	}
 
-	if (bio->bi_opf & (REQ_PREFLUSH | REQ_FUA)) {
+	if (op_is_flush(bio->bi_opf)) {
 		spin_lock_irq(q->queue_lock);
 		where = ELEVATOR_INSERT_FLUSH;
 		goto get_rq;
@@ -1894,7 +1880,7 @@ generic_make_request_checks(struct bio *bio)
 	 * drivers without flush support don't have to worry
 	 * about them.
 	 */
-	if ((bio->bi_opf & (REQ_PREFLUSH | REQ_FUA)) &&
+	if (op_is_flush(bio->bi_opf) &&
 	    !test_bit(QUEUE_FLAG_WC, &q->queue_flags)) {
 		bio->bi_opf &= ~(REQ_PREFLUSH | REQ_FUA);
 		if (!nr_sectors) {
@@ -2143,7 +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, false);
 		return 0;
 	}
 
@@ -2159,7 +2145,7 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 	 */
 	BUG_ON(blk_queued_rq(rq));
 
-	if (rq->cmd_flags & (REQ_PREFLUSH | REQ_FUA))
+	if (op_is_flush(rq->cmd_flags))
 		where = ELEVATOR_INSERT_FLUSH;
 
 	add_acct_request(q, rq, where);
@@ -3270,7 +3256,7 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 		/*
 		 * rq is already accounted, so use raw insert
 		 */
-		if (rq->cmd_flags & (REQ_PREFLUSH | REQ_FUA))
+		if (op_is_flush(rq->cmd_flags))
 			__elv_add_request(q, rq, ELEVATOR_INSERT_FLUSH);
 		else
 			__elv_add_request(q, rq, ELEVATOR_INSERT_SORT_MERGE);

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, 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, false);
+		else
 			list_add_tail(&rq->queuelist, &q->queue_head);
 		return;
 	}

block/blk-ioc.c

@@ -43,8 +43,10 @@ static void ioc_exit_icq(struct io_cq *icq)
 	if (icq->flags & ICQ_EXITED)
 		return;
 
-	if (et->ops.elevator_exit_icq_fn)
-		et->ops.elevator_exit_icq_fn(icq);
+	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;
 }
@@ -383,8 +385,10 @@ 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.elevator_init_icq_fn)
-			et->ops.elevator_init_icq_fn(icq);
+		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);
 		icq = ioc_lookup_icq(ioc, q);

block/blk-merge.c

@@ -763,8 +763,8 @@ int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_allow_rq_merge_fn)
-		if (!e->type->ops.elevator_allow_rq_merge_fn(q, rq, next))
+	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;
 
 	return attempt_merge(q, rq, next);

block/blk-mq-debugfs.c

@@ -0,0 +1,756 @@
+/*
+ * Copyright (C) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <https://www.gnu.org/licenses/>.
+ */
+
+#include <linux/kernel.h>
+#include <linux/blkdev.h>
+#include <linux/debugfs.h>
+
+#include <linux/blk-mq.h>
+#include "blk-mq.h"
+#include "blk-mq-tag.h"
+
+struct blk_mq_debugfs_attr {
+	const char *name;
+	umode_t mode;
+	const struct file_operations *fops;
+};
+
+static struct dentry *block_debugfs_root;
+
+static int blk_mq_debugfs_seq_open(struct inode *inode, struct file *file,
+				   const struct seq_operations *ops)
+{
+	struct seq_file *m;
+	int ret;
+
+	ret = seq_open(file, ops);
+	if (!ret) {
+		m = file->private_data;
+		m->private = inode->i_private;
+	}
+	return ret;
+}
+
+static int hctx_state_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+
+	seq_printf(m, "0x%lx\n", hctx->state);
+	return 0;
+}
+
+static int hctx_state_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hctx_state_show, inode->i_private);
+}
+
+static const struct file_operations hctx_state_fops = {
+	.open		= hctx_state_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int hctx_flags_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+
+	seq_printf(m, "0x%lx\n", hctx->flags);
+	return 0;
+}
+
+static int hctx_flags_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hctx_flags_show, inode->i_private);
+}
+
+static const struct file_operations hctx_flags_fops = {
+	.open		= hctx_flags_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int blk_mq_debugfs_rq_show(struct seq_file *m, void *v)
+{
+	struct request *rq = list_entry_rq(v);
+
+	seq_printf(m, "%p {.cmd_type=%u, .cmd_flags=0x%x, .rq_flags=0x%x, .tag=%d, .internal_tag=%d}\n",
+		   rq, rq->cmd_type, rq->cmd_flags, (unsigned int)rq->rq_flags,
+		   rq->tag, rq->internal_tag);
+	return 0;
+}
+
+static void *hctx_dispatch_start(struct seq_file *m, loff_t *pos)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+
+	spin_lock(&hctx->lock);
+	return seq_list_start(&hctx->dispatch, *pos);
+}
+
+static void *hctx_dispatch_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+
+	return seq_list_next(v, &hctx->dispatch, pos);
+}
+
+static void hctx_dispatch_stop(struct seq_file *m, void *v)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+
+	spin_unlock(&hctx->lock);
+}
+
+static const struct seq_operations hctx_dispatch_seq_ops = {
+	.start	= hctx_dispatch_start,
+	.next	= hctx_dispatch_next,
+	.stop	= hctx_dispatch_stop,
+	.show	= blk_mq_debugfs_rq_show,
+};
+
+static int hctx_dispatch_open(struct inode *inode, struct file *file)
+{
+	return blk_mq_debugfs_seq_open(inode, file, &hctx_dispatch_seq_ops);
+}
+
+static const struct file_operations hctx_dispatch_fops = {
+	.open		= hctx_dispatch_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+static int hctx_ctx_map_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+
+	sbitmap_bitmap_show(&hctx->ctx_map, m);
+	return 0;
+}
+
+static int hctx_ctx_map_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hctx_ctx_map_show, inode->i_private);
+}
+
+static const struct file_operations hctx_ctx_map_fops = {
+	.open		= hctx_ctx_map_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static void blk_mq_debugfs_tags_show(struct seq_file *m,
+				     struct blk_mq_tags *tags)
+{
+	seq_printf(m, "nr_tags=%u\n", tags->nr_tags);
+	seq_printf(m, "nr_reserved_tags=%u\n", tags->nr_reserved_tags);
+	seq_printf(m, "active_queues=%d\n",
+		   atomic_read(&tags->active_queues));
+
+	seq_puts(m, "\nbitmap_tags:\n");
+	sbitmap_queue_show(&tags->bitmap_tags, m);
+
+	if (tags->nr_reserved_tags) {
+		seq_puts(m, "\nbreserved_tags:\n");
+		sbitmap_queue_show(&tags->breserved_tags, m);
+	}
+}
+
+static int hctx_tags_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+	struct request_queue *q = hctx->queue;
+
+	mutex_lock(&q->sysfs_lock);
+	if (hctx->tags)
+		blk_mq_debugfs_tags_show(m, hctx->tags);
+	mutex_unlock(&q->sysfs_lock);
+
+	return 0;
+}
+
+static int hctx_tags_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hctx_tags_show, inode->i_private);
+}
+
+static const struct file_operations hctx_tags_fops = {
+	.open		= hctx_tags_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int hctx_tags_bitmap_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+	struct request_queue *q = hctx->queue;
+
+	mutex_lock(&q->sysfs_lock);
+	if (hctx->tags)
+		sbitmap_bitmap_show(&hctx->tags->bitmap_tags.sb, m);
+	mutex_unlock(&q->sysfs_lock);
+	return 0;
+}
+
+static int hctx_tags_bitmap_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hctx_tags_bitmap_show, inode->i_private);
+}
+
+static const struct file_operations hctx_tags_bitmap_fops = {
+	.open		= hctx_tags_bitmap_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int hctx_sched_tags_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+	struct request_queue *q = hctx->queue;
+
+	mutex_lock(&q->sysfs_lock);
+	if (hctx->sched_tags)
+		blk_mq_debugfs_tags_show(m, hctx->sched_tags);
+	mutex_unlock(&q->sysfs_lock);
+
+	return 0;
+}
+
+static int hctx_sched_tags_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hctx_sched_tags_show, inode->i_private);
+}
+
+static const struct file_operations hctx_sched_tags_fops = {
+	.open		= hctx_sched_tags_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int hctx_sched_tags_bitmap_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+	struct request_queue *q = hctx->queue;
+
+	mutex_lock(&q->sysfs_lock);
+	if (hctx->sched_tags)
+		sbitmap_bitmap_show(&hctx->sched_tags->bitmap_tags.sb, m);
+	mutex_unlock(&q->sysfs_lock);
+	return 0;
+}
+
+static int hctx_sched_tags_bitmap_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hctx_sched_tags_bitmap_show, inode->i_private);
+}
+
+static const struct file_operations hctx_sched_tags_bitmap_fops = {
+	.open		= hctx_sched_tags_bitmap_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int hctx_io_poll_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+
+	seq_printf(m, "considered=%lu\n", hctx->poll_considered);
+	seq_printf(m, "invoked=%lu\n", hctx->poll_invoked);
+	seq_printf(m, "success=%lu\n", hctx->poll_success);
+	return 0;
+}
+
+static int hctx_io_poll_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hctx_io_poll_show, inode->i_private);
+}
+
+static ssize_t hctx_io_poll_write(struct file *file, const char __user *buf,
+				  size_t count, loff_t *ppos)
+{
+	struct seq_file *m = file->private_data;
+	struct blk_mq_hw_ctx *hctx = m->private;
+
+	hctx->poll_considered = hctx->poll_invoked = hctx->poll_success = 0;
+	return count;
+}
+
+static const struct file_operations hctx_io_poll_fops = {
+	.open		= hctx_io_poll_open,
+	.read		= seq_read,
+	.write		= hctx_io_poll_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static void print_stat(struct seq_file *m, struct blk_rq_stat *stat)
+{
+	seq_printf(m, "samples=%d, mean=%lld, min=%llu, max=%llu",
+		   stat->nr_samples, stat->mean, stat->min, stat->max);
+}
+
+static int hctx_stats_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+	struct blk_rq_stat stat[2];
+
+	blk_stat_init(&stat[BLK_STAT_READ]);
+	blk_stat_init(&stat[BLK_STAT_WRITE]);
+
+	blk_hctx_stat_get(hctx, stat);
+
+	seq_puts(m, "read: ");
+	print_stat(m, &stat[BLK_STAT_READ]);
+	seq_puts(m, "\n");
+
+	seq_puts(m, "write: ");
+	print_stat(m, &stat[BLK_STAT_WRITE]);
+	seq_puts(m, "\n");
+	return 0;
+}
+
+static int hctx_stats_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hctx_stats_show, inode->i_private);
+}
+
+static ssize_t hctx_stats_write(struct file *file, const char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	struct seq_file *m = file->private_data;
+	struct blk_mq_hw_ctx *hctx = m->private;
+	struct blk_mq_ctx *ctx;
+	int i;
+
+	hctx_for_each_ctx(hctx, ctx, i) {
+		blk_stat_init(&ctx->stat[BLK_STAT_READ]);
+		blk_stat_init(&ctx->stat[BLK_STAT_WRITE]);
+	}
+	return count;
+}
+
+static const struct file_operations hctx_stats_fops = {
+	.open		= hctx_stats_open,
+	.read		= seq_read,
+	.write		= hctx_stats_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int hctx_dispatched_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+	int i;
+
+	seq_printf(m, "%8u\t%lu\n", 0U, hctx->dispatched[0]);
+
+	for (i = 1; i < BLK_MQ_MAX_DISPATCH_ORDER - 1; i++) {
+		unsigned int d = 1U << (i - 1);
+
+		seq_printf(m, "%8u\t%lu\n", d, hctx->dispatched[i]);
+	}
+
+	seq_printf(m, "%8u+\t%lu\n", 1U << (i - 1), hctx->dispatched[i]);
+	return 0;
+}
+
+static int hctx_dispatched_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hctx_dispatched_show, inode->i_private);
+}
+
+static ssize_t hctx_dispatched_write(struct file *file, const char __user *buf,
+				     size_t count, loff_t *ppos)
+{
+	struct seq_file *m = file->private_data;
+	struct blk_mq_hw_ctx *hctx = m->private;
+	int i;
+
+	for (i = 0; i < BLK_MQ_MAX_DISPATCH_ORDER; i++)
+		hctx->dispatched[i] = 0;
+	return count;
+}
+
+static const struct file_operations hctx_dispatched_fops = {
+	.open		= hctx_dispatched_open,
+	.read		= seq_read,
+	.write		= hctx_dispatched_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int hctx_queued_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+
+	seq_printf(m, "%lu\n", hctx->queued);
+	return 0;
+}
+
+static int hctx_queued_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hctx_queued_show, inode->i_private);
+}
+
+static ssize_t hctx_queued_write(struct file *file, const char __user *buf,
+				 size_t count, loff_t *ppos)
+{
+	struct seq_file *m = file->private_data;
+	struct blk_mq_hw_ctx *hctx = m->private;
+
+	hctx->queued = 0;
+	return count;
+}
+
+static const struct file_operations hctx_queued_fops = {
+	.open		= hctx_queued_open,
+	.read		= seq_read,
+	.write		= hctx_queued_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int hctx_run_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+
+	seq_printf(m, "%lu\n", hctx->run);
+	return 0;
+}
+
+static int hctx_run_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hctx_run_show, inode->i_private);
+}
+
+static ssize_t hctx_run_write(struct file *file, const char __user *buf,
+				 size_t count, loff_t *ppos)
+{
+	struct seq_file *m = file->private_data;
+	struct blk_mq_hw_ctx *hctx = m->private;
+
+	hctx->run = 0;
+	return count;
+}
+
+static const struct file_operations hctx_run_fops = {
+	.open		= hctx_run_open,
+	.read		= seq_read,
+	.write		= hctx_run_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int hctx_active_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+
+	seq_printf(m, "%d\n", atomic_read(&hctx->nr_active));
+	return 0;
+}
+
+static int hctx_active_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hctx_active_show, inode->i_private);
+}
+
+static const struct file_operations hctx_active_fops = {
+	.open		= hctx_active_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static void *ctx_rq_list_start(struct seq_file *m, loff_t *pos)
+{
+	struct blk_mq_ctx *ctx = m->private;
+
+	spin_lock(&ctx->lock);
+	return seq_list_start(&ctx->rq_list, *pos);
+}
+
+static void *ctx_rq_list_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	struct blk_mq_ctx *ctx = m->private;
+
+	return seq_list_next(v, &ctx->rq_list, pos);
+}
+
+static void ctx_rq_list_stop(struct seq_file *m, void *v)
+{
+	struct blk_mq_ctx *ctx = m->private;
+
+	spin_unlock(&ctx->lock);
+}
+
+static const struct seq_operations ctx_rq_list_seq_ops = {
+	.start	= ctx_rq_list_start,
+	.next	= ctx_rq_list_next,
+	.stop	= ctx_rq_list_stop,
+	.show	= blk_mq_debugfs_rq_show,
+};
+
+static int ctx_rq_list_open(struct inode *inode, struct file *file)
+{
+	return blk_mq_debugfs_seq_open(inode, file, &ctx_rq_list_seq_ops);
+}
+
+static const struct file_operations ctx_rq_list_fops = {
+	.open		= ctx_rq_list_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+static int ctx_dispatched_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_ctx *ctx = m->private;
+
+	seq_printf(m, "%lu %lu\n", ctx->rq_dispatched[1], ctx->rq_dispatched[0]);
+	return 0;
+}
+
+static int ctx_dispatched_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, ctx_dispatched_show, inode->i_private);
+}
+
+static ssize_t ctx_dispatched_write(struct file *file, const char __user *buf,
+				    size_t count, loff_t *ppos)
+{
+	struct seq_file *m = file->private_data;
+	struct blk_mq_ctx *ctx = m->private;
+
+	ctx->rq_dispatched[0] = ctx->rq_dispatched[1] = 0;
+	return count;
+}
+
+static const struct file_operations ctx_dispatched_fops = {
+	.open		= ctx_dispatched_open,
+	.read		= seq_read,
+	.write		= ctx_dispatched_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int ctx_merged_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_ctx *ctx = m->private;
+
+	seq_printf(m, "%lu\n", ctx->rq_merged);
+	return 0;
+}
+
+static int ctx_merged_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, ctx_merged_show, inode->i_private);
+}
+
+static ssize_t ctx_merged_write(struct file *file, const char __user *buf,
+				    size_t count, loff_t *ppos)
+{
+	struct seq_file *m = file->private_data;
+	struct blk_mq_ctx *ctx = m->private;
+
+	ctx->rq_merged = 0;
+	return count;
+}
+
+static const struct file_operations ctx_merged_fops = {
+	.open		= ctx_merged_open,
+	.read		= seq_read,
+	.write		= ctx_merged_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int ctx_completed_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_ctx *ctx = m->private;
+
+	seq_printf(m, "%lu %lu\n", ctx->rq_completed[1], ctx->rq_completed[0]);
+	return 0;
+}
+
+static int ctx_completed_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, ctx_completed_show, inode->i_private);
+}
+
+static ssize_t ctx_completed_write(struct file *file, const char __user *buf,
+				   size_t count, loff_t *ppos)
+{
+	struct seq_file *m = file->private_data;
+	struct blk_mq_ctx *ctx = m->private;
+
+	ctx->rq_completed[0] = ctx->rq_completed[1] = 0;
+	return count;
+}
+
+static const struct file_operations ctx_completed_fops = {
+	.open		= ctx_completed_open,
+	.read		= seq_read,
+	.write		= ctx_completed_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = {
+	{"state", 0400, &hctx_state_fops},
+	{"flags", 0400, &hctx_flags_fops},
+	{"dispatch", 0400, &hctx_dispatch_fops},
+	{"ctx_map", 0400, &hctx_ctx_map_fops},
+	{"tags", 0400, &hctx_tags_fops},
+	{"tags_bitmap", 0400, &hctx_tags_bitmap_fops},
+	{"sched_tags", 0400, &hctx_sched_tags_fops},
+	{"sched_tags_bitmap", 0400, &hctx_sched_tags_bitmap_fops},
+	{"io_poll", 0600, &hctx_io_poll_fops},
+	{"stats", 0600, &hctx_stats_fops},
+	{"dispatched", 0600, &hctx_dispatched_fops},
+	{"queued", 0600, &hctx_queued_fops},
+	{"run", 0600, &hctx_run_fops},
+	{"active", 0400, &hctx_active_fops},
+};
+
+static const struct blk_mq_debugfs_attr blk_mq_debugfs_ctx_attrs[] = {
+	{"rq_list", 0400, &ctx_rq_list_fops},
+	{"dispatched", 0600, &ctx_dispatched_fops},
+	{"merged", 0600, &ctx_merged_fops},
+	{"completed", 0600, &ctx_completed_fops},
+};
+
+int blk_mq_debugfs_register(struct request_queue *q, const char *name)
+{
+	if (!block_debugfs_root)
+		return -ENOENT;
+
+	q->debugfs_dir = debugfs_create_dir(name, block_debugfs_root);
+	if (!q->debugfs_dir)
+		goto err;
+
+	if (blk_mq_debugfs_register_hctxs(q))
+		goto err;
+
+	return 0;
+
+err:
+	blk_mq_debugfs_unregister(q);
+	return -ENOMEM;
+}
+
+void blk_mq_debugfs_unregister(struct request_queue *q)
+{
+	debugfs_remove_recursive(q->debugfs_dir);
+	q->mq_debugfs_dir = NULL;
+	q->debugfs_dir = NULL;
+}
+
+static int blk_mq_debugfs_register_ctx(struct request_queue *q,
+				       struct blk_mq_ctx *ctx,
+				       struct dentry *hctx_dir)
+{
+	struct dentry *ctx_dir;
+	char name[20];
+	int i;
+
+	snprintf(name, sizeof(name), "cpu%u", ctx->cpu);
+	ctx_dir = debugfs_create_dir(name, hctx_dir);
+	if (!ctx_dir)
+		return -ENOMEM;
+
+	for (i = 0; i < ARRAY_SIZE(blk_mq_debugfs_ctx_attrs); i++) {
+		const struct blk_mq_debugfs_attr *attr;
+
+		attr = &blk_mq_debugfs_ctx_attrs[i];
+		if (!debugfs_create_file(attr->name, attr->mode, ctx_dir, ctx,
+					 attr->fops))
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static int blk_mq_debugfs_register_hctx(struct request_queue *q,
+					struct blk_mq_hw_ctx *hctx)
+{
+	struct blk_mq_ctx *ctx;
+	struct dentry *hctx_dir;
+	char name[20];
+	int i;
+
+	snprintf(name, sizeof(name), "%u", hctx->queue_num);
+	hctx_dir = debugfs_create_dir(name, q->mq_debugfs_dir);
+	if (!hctx_dir)
+		return -ENOMEM;
+
+	for (i = 0; i < ARRAY_SIZE(blk_mq_debugfs_hctx_attrs); i++) {
+		const struct blk_mq_debugfs_attr *attr;
+
+		attr = &blk_mq_debugfs_hctx_attrs[i];
+		if (!debugfs_create_file(attr->name, attr->mode, hctx_dir, hctx,
+					 attr->fops))
+			return -ENOMEM;
+	}
+
+	hctx_for_each_ctx(hctx, ctx, i) {
+		if (blk_mq_debugfs_register_ctx(q, ctx, hctx_dir))
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+int blk_mq_debugfs_register_hctxs(struct request_queue *q)
+{
+	struct blk_mq_hw_ctx *hctx;
+	int i;
+
+	if (!q->debugfs_dir)
+		return -ENOENT;
+
+	q->mq_debugfs_dir = debugfs_create_dir("mq", q->debugfs_dir);
+	if (!q->mq_debugfs_dir)
+		goto err;
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		if (blk_mq_debugfs_register_hctx(q, hctx))
+			goto err;
+	}
+
+	return 0;
+
+err:
+	blk_mq_debugfs_unregister_hctxs(q);
+	return -ENOMEM;
+}
+
+void blk_mq_debugfs_unregister_hctxs(struct request_queue *q)
+{
+	debugfs_remove_recursive(q->mq_debugfs_dir);
+	q->mq_debugfs_dir = NULL;
+}
+
+void blk_mq_debugfs_init(void)
+{
+	block_debugfs_root = debugfs_create_dir("block", NULL);
+}

block/blk-mq-sched.c

@@ -0,0 +1,481 @@
+/*
+ * 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;
+
+	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, data->flags, ctx, hctx);
+
+	if (e) {
+		data->flags |= BLK_MQ_REQ_INTERNAL;
+
+		/*
+		 * Flush requests are special and go directly to the
+		 * dispatch list.
+		 */
+		if (!op_is_flush(op) && 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);
+		if (rq)
+			data->hctx->tags->rqs[rq->tag] = rq;
+	}
+
+	if (rq) {
+		if (!op_is_flush(op)) {
+			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)) {
+		blk_mq_sched_mark_restart(hctx);
+		blk_mq_dispatch_rq_list(hctx, &rq_list);
+	} else if (!e || !e->type->ops.mq.dispatch_request) {
+		blk_mq_flush_busy_ctxs(hctx, &rq_list);
+		blk_mq_dispatch_rq_list(hctx, &rq_list);
+	} else {
+		do {
+			struct request *rq;
+
+			rq = e->type->ops.mq.dispatch_request(hctx);
+			if (!rq)
+				break;
+			list_add(&rq->queuelist, &rq_list);
+		} while (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_restart_hctx(struct blk_mq_hw_ctx *hctx)
+{
+	if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) {
+		clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
+		if (blk_mq_hctx_has_pending(hctx))
+			blk_mq_run_hw_queue(hctx, true);
+	}
+}
+
+void blk_mq_sched_restart_queues(struct blk_mq_hw_ctx *hctx)
+{
+	unsigned int i;
+
+	if (!(hctx->flags & BLK_MQ_F_TAG_SHARED))
+		blk_mq_sched_restart_hctx(hctx);
+	else {
+		struct request_queue *q = hctx->queue;
+
+		if (!test_bit(QUEUE_FLAG_RESTART, &q->queue_flags))
+			return;
+
+		clear_bit(QUEUE_FLAG_RESTART, &q->queue_flags);
+
+		queue_for_each_hw_ctx(q, hctx, i)
+			blk_mq_sched_restart_hctx(hctx);
+	}
+}
+
+/*
+ * Add flush/fua to the queue. If we fail getting a driver tag, then
+ * punt to the requeue list. Requeue will re-invoke us from a context
+ * that's safe to block from.
+ */
+static void blk_mq_sched_insert_flush(struct blk_mq_hw_ctx *hctx,
+				      struct request *rq, bool can_block)
+{
+	if (blk_mq_get_driver_tag(rq, &hctx, can_block)) {
+		blk_insert_flush(rq);
+		blk_mq_run_hw_queue(hctx, true);
+	} else
+		blk_mq_add_to_requeue_list(rq, true, true);
+}
+
+void blk_mq_sched_insert_request(struct request *rq, bool at_head,
+				 bool run_queue, bool async, bool can_block)
+{
+	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 (rq->tag == -1 && op_is_flush(rq->cmd_flags)) {
+		blk_mq_sched_insert_flush(hctx, rq, can_block);
+		return;
+	}
+
+	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);
+}
+
+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 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);
+}
+
+int blk_mq_sched_init(struct request_queue *q)
+{
+	int ret;
+
+#if defined(CONFIG_DEFAULT_SQ_NONE)
+	if (q->nr_hw_queues == 1)
+		return 0;
+#endif
+#if defined(CONFIG_DEFAULT_MQ_NONE)
+	if (q->nr_hw_queues > 1)
+		return 0;
+#endif
+
+	mutex_lock(&q->sysfs_lock);
+	ret = elevator_init(q, NULL);
+	mutex_unlock(&q->sysfs_lock);
+
+	return ret;
+}

block/blk-mq-sched.h

@@ -0,0 +1,142 @@
+#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_restart_queues(struct blk_mq_hw_ctx *hctx);
+
+void blk_mq_sched_insert_request(struct request *rq, bool at_head,
+				 bool run_queue, bool async, bool can_block);
+void blk_mq_sched_insert_requests(struct request_queue *q,
+				  struct blk_mq_ctx *ctx,
+				  struct list_head *list, bool run_queue_async);
+
+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);
+
+int blk_mq_sched_init(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 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);
+}
+
+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);
+		if (hctx->flags & BLK_MQ_F_TAG_SHARED) {
+			struct request_queue *q = hctx->queue;
+
+			if (!test_bit(QUEUE_FLAG_RESTART, &q->queue_flags))
+				set_bit(QUEUE_FLAG_RESTART, &q->queue_flags);
+		}
+	}
+}
+
+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

@@ -122,123 +122,16 @@ static ssize_t blk_mq_hw_sysfs_store(struct kobject *kobj,
 	return res;
 }
 
-static ssize_t blk_mq_sysfs_dispatched_show(struct blk_mq_ctx *ctx, char *page)
-{
-	return sprintf(page, "%lu %lu\n", ctx->rq_dispatched[1],
-				ctx->rq_dispatched[0]);
-}
-
-static ssize_t blk_mq_sysfs_merged_show(struct blk_mq_ctx *ctx, char *page)
-{
-	return sprintf(page, "%lu\n", ctx->rq_merged);
-}
-
-static ssize_t blk_mq_sysfs_completed_show(struct blk_mq_ctx *ctx, char *page)
-{
-	return sprintf(page, "%lu %lu\n", ctx->rq_completed[1],
-				ctx->rq_completed[0]);
-}
-
-static ssize_t sysfs_list_show(char *page, struct list_head *list, char *msg)
-{
-	struct request *rq;
-	int len = snprintf(page, PAGE_SIZE - 1, "%s:\n", msg);
-
-	list_for_each_entry(rq, list, queuelist) {
-		const int rq_len = 2 * sizeof(rq) + 2;
-
-		/* if the output will be truncated */
-		if (PAGE_SIZE - 1 < len + rq_len) {
-			/* backspacing if it can't hold '\t...\n' */
-			if (PAGE_SIZE - 1 < len + 5)
-				len -= rq_len;
-			len += snprintf(page + len, PAGE_SIZE - 1 - len,
-					"\t...\n");
-			break;
-		}
-		len += snprintf(page + len, PAGE_SIZE - 1 - len,
-				"\t%p\n", rq);
-	}
-
-	return len;
-}
-
-static ssize_t blk_mq_sysfs_rq_list_show(struct blk_mq_ctx *ctx, char *page)
-{
-	ssize_t ret;
-
-	spin_lock(&ctx->lock);
-	ret = sysfs_list_show(page, &ctx->rq_list, "CTX pending");
-	spin_unlock(&ctx->lock);
-
-	return ret;
-}
-
-static ssize_t blk_mq_hw_sysfs_poll_show(struct blk_mq_hw_ctx *hctx, char *page)
-{
-	return sprintf(page, "considered=%lu, invoked=%lu, success=%lu\n",
-		       hctx->poll_considered, hctx->poll_invoked,
-		       hctx->poll_success);
-}
-
-static ssize_t blk_mq_hw_sysfs_poll_store(struct blk_mq_hw_ctx *hctx,
-					  const char *page, size_t size)
-{
-	hctx->poll_considered = hctx->poll_invoked = hctx->poll_success = 0;
-
-	return size;
-}
-
-static ssize_t blk_mq_hw_sysfs_queued_show(struct blk_mq_hw_ctx *hctx,
-					   char *page)
-{
-	return sprintf(page, "%lu\n", hctx->queued);
-}
-
-static ssize_t blk_mq_hw_sysfs_run_show(struct blk_mq_hw_ctx *hctx, char *page)
-{
-	return sprintf(page, "%lu\n", hctx->run);
-}
-
-static ssize_t blk_mq_hw_sysfs_dispatched_show(struct blk_mq_hw_ctx *hctx,
-					       char *page)
-{
-	char *start_page = page;
-	int i;
-
-	page += sprintf(page, "%8u\t%lu\n", 0U, hctx->dispatched[0]);
-
-	for (i = 1; i < BLK_MQ_MAX_DISPATCH_ORDER - 1; i++) {
-		unsigned int d = 1U << (i - 1);
-
-		page += sprintf(page, "%8u\t%lu\n", d, hctx->dispatched[i]);
-	}
-
-	page += sprintf(page, "%8u+\t%lu\n", 1U << (i - 1),
-						hctx->dispatched[i]);
-	return page - start_page;
-}
-
-static ssize_t blk_mq_hw_sysfs_rq_list_show(struct blk_mq_hw_ctx *hctx,
+static ssize_t blk_mq_hw_sysfs_nr_tags_show(struct blk_mq_hw_ctx *hctx,
 					    char *page)
 {
-	ssize_t ret;
-
-	spin_lock(&hctx->lock);
-	ret = sysfs_list_show(page, &hctx->dispatch, "HCTX pending");
-	spin_unlock(&hctx->lock);
-
-	return ret;
+	return sprintf(page, "%u\n", hctx->tags->nr_tags);
 }
 
-static ssize_t blk_mq_hw_sysfs_tags_show(struct blk_mq_hw_ctx *hctx, char *page)
+static ssize_t blk_mq_hw_sysfs_nr_reserved_tags_show(struct blk_mq_hw_ctx *hctx,
+						     char *page)
 {
-	return blk_mq_tag_sysfs_show(hctx->tags, page);
-}
-
-static ssize_t blk_mq_hw_sysfs_active_show(struct blk_mq_hw_ctx *hctx, char *page)
-{
-	return sprintf(page, "%u\n", atomic_read(&hctx->nr_active));
+	return sprintf(page, "%u\n", hctx->tags->nr_reserved_tags);
 }
 
 static ssize_t blk_mq_hw_sysfs_cpus_show(struct blk_mq_hw_ctx *hctx, char *page)
@@ -259,121 +152,27 @@ static ssize_t blk_mq_hw_sysfs_cpus_show(struct blk_mq_hw_ctx *hctx, char *page)
 	return ret;
 }
 
-static void blk_mq_stat_clear(struct blk_mq_hw_ctx *hctx)
-{
-	struct blk_mq_ctx *ctx;
-	unsigned int i;
-
-	hctx_for_each_ctx(hctx, ctx, i) {
-		blk_stat_init(&ctx->stat[BLK_STAT_READ]);
-		blk_stat_init(&ctx->stat[BLK_STAT_WRITE]);
-	}
-}
-
-static ssize_t blk_mq_hw_sysfs_stat_store(struct blk_mq_hw_ctx *hctx,
-					  const char *page, size_t count)
-{
-	blk_mq_stat_clear(hctx);
-	return count;
-}
-
-static ssize_t print_stat(char *page, struct blk_rq_stat *stat, const char *pre)
-{
-	return sprintf(page, "%s samples=%llu, mean=%lld, min=%lld, max=%lld\n",
-			pre, (long long) stat->nr_samples,
-			(long long) stat->mean, (long long) stat->min,
-			(long long) stat->max);
-}
-
-static ssize_t blk_mq_hw_sysfs_stat_show(struct blk_mq_hw_ctx *hctx, char *page)
-{
-	struct blk_rq_stat stat[2];
-	ssize_t ret;
-
-	blk_stat_init(&stat[BLK_STAT_READ]);
-	blk_stat_init(&stat[BLK_STAT_WRITE]);
-
-	blk_hctx_stat_get(hctx, stat);
-
-	ret = print_stat(page, &stat[BLK_STAT_READ], "read :");
-	ret += print_stat(page + ret, &stat[BLK_STAT_WRITE], "write:");
-	return ret;
-}
-
-static struct blk_mq_ctx_sysfs_entry blk_mq_sysfs_dispatched = {
-	.attr = {.name = "dispatched", .mode = S_IRUGO },
-	.show = blk_mq_sysfs_dispatched_show,
-};
-static struct blk_mq_ctx_sysfs_entry blk_mq_sysfs_merged = {
-	.attr = {.name = "merged", .mode = S_IRUGO },
-	.show = blk_mq_sysfs_merged_show,
-};
-static struct blk_mq_ctx_sysfs_entry blk_mq_sysfs_completed = {
-	.attr = {.name = "completed", .mode = S_IRUGO },
-	.show = blk_mq_sysfs_completed_show,
-};
-static struct blk_mq_ctx_sysfs_entry blk_mq_sysfs_rq_list = {
-	.attr = {.name = "rq_list", .mode = S_IRUGO },
-	.show = blk_mq_sysfs_rq_list_show,
-};
-
 static struct attribute *default_ctx_attrs[] = {
-	&blk_mq_sysfs_dispatched.attr,
-	&blk_mq_sysfs_merged.attr,
-	&blk_mq_sysfs_completed.attr,
-	&blk_mq_sysfs_rq_list.attr,
 	NULL,
 };
 
-static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_queued = {
-	.attr = {.name = "queued", .mode = S_IRUGO },
-	.show = blk_mq_hw_sysfs_queued_show,
+static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_nr_tags = {
+	.attr = {.name = "nr_tags", .mode = S_IRUGO },
+	.show = blk_mq_hw_sysfs_nr_tags_show,
 };
-static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_run = {
-	.attr = {.name = "run", .mode = S_IRUGO },
-	.show = blk_mq_hw_sysfs_run_show,
-};
-static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_dispatched = {
-	.attr = {.name = "dispatched", .mode = S_IRUGO },
-	.show = blk_mq_hw_sysfs_dispatched_show,
-};
-static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_active = {
-	.attr = {.name = "active", .mode = S_IRUGO },
-	.show = blk_mq_hw_sysfs_active_show,
-};
-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_tags = {
-	.attr = {.name = "tags", .mode = S_IRUGO },
-	.show = blk_mq_hw_sysfs_tags_show,
+static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_nr_reserved_tags = {
+	.attr = {.name = "nr_reserved_tags", .mode = S_IRUGO },
+	.show = blk_mq_hw_sysfs_nr_reserved_tags_show,
 };
 static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_cpus = {
 	.attr = {.name = "cpu_list", .mode = S_IRUGO },
 	.show = blk_mq_hw_sysfs_cpus_show,
 };
-static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_poll = {
-	.attr = {.name = "io_poll", .mode = S_IWUSR | S_IRUGO },
-	.show = blk_mq_hw_sysfs_poll_show,
-	.store = blk_mq_hw_sysfs_poll_store,
-};
-static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_stat = {
-	.attr = {.name = "stats", .mode = S_IRUGO | S_IWUSR },
-	.show = blk_mq_hw_sysfs_stat_show,
-	.store = blk_mq_hw_sysfs_stat_store,
-};
 
 static struct attribute *default_hw_ctx_attrs[] = {
-	&blk_mq_hw_sysfs_queued.attr,
-	&blk_mq_hw_sysfs_run.attr,
-	&blk_mq_hw_sysfs_dispatched.attr,
-	&blk_mq_hw_sysfs_pending.attr,
-	&blk_mq_hw_sysfs_tags.attr,
+	&blk_mq_hw_sysfs_nr_tags.attr,
+	&blk_mq_hw_sysfs_nr_reserved_tags.attr,
 	&blk_mq_hw_sysfs_cpus.attr,
-	&blk_mq_hw_sysfs_active.attr,
-	&blk_mq_hw_sysfs_poll.attr,
-	&blk_mq_hw_sysfs_stat.attr,
 	NULL,
 };
 
@@ -455,6 +254,8 @@ static void __blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
 		kobject_put(&hctx->kobj);
 	}
 
+	blk_mq_debugfs_unregister(q);
+
 	kobject_uevent(&q->mq_kobj, KOBJ_REMOVE);
 	kobject_del(&q->mq_kobj);
 	kobject_put(&q->mq_kobj);
@@ -504,6 +305,8 @@ int blk_mq_register_dev(struct device *dev, struct request_queue *q)
 
 	kobject_uevent(&q->mq_kobj, KOBJ_ADD);
 
+	blk_mq_debugfs_register(q, kobject_name(&dev->kobj));
+
 	queue_for_each_hw_ctx(q, hctx, i) {
 		ret = blk_mq_register_hctx(hctx);
 		if (ret)
@@ -529,6 +332,8 @@ void blk_mq_sysfs_unregister(struct request_queue *q)
 	if (!q->mq_sysfs_init_done)
 		return;
 
+	blk_mq_debugfs_unregister_hctxs(q);
+
 	queue_for_each_hw_ctx(q, hctx, i)
 		blk_mq_unregister_hctx(hctx);
 }
@@ -541,6 +346,8 @@ int blk_mq_sysfs_register(struct request_queue *q)
 	if (!q->mq_sysfs_init_done)
 		return ret;
 
+	blk_mq_debugfs_register_hctxs(q);
+
 	queue_for_each_hw_ctx(q, hctx, i) {
 		ret = blk_mq_register_hctx(hctx);
 		if (ret)

block/blk-mq-tag.c

@@ -90,113 +90,97 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
 	return atomic_read(&hctx->nr_active) < depth;
 }
 
-static int __bt_get(struct blk_mq_hw_ctx *hctx, struct sbitmap_queue *bt)
+static int __blk_mq_get_tag(struct blk_mq_alloc_data *data,
+			    struct sbitmap_queue *bt)
 {
-	if (!hctx_may_queue(hctx, bt))
+	if (!(data->flags & BLK_MQ_REQ_INTERNAL) &&
+	    !hctx_may_queue(data->hctx, bt))
 		return -1;
 	return __sbitmap_queue_get(bt);
 }
 
-static int bt_get(struct blk_mq_alloc_data *data, struct sbitmap_queue *bt,
-		  struct blk_mq_hw_ctx *hctx, struct blk_mq_tags *tags)
+unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
 {
+	struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
+	struct sbitmap_queue *bt;
 	struct sbq_wait_state *ws;
 	DEFINE_WAIT(wait);
+	unsigned int tag_offset;
+	bool drop_ctx;
 	int tag;
 
-	tag = __bt_get(hctx, bt);
+	if (data->flags & BLK_MQ_REQ_RESERVED) {
+		if (unlikely(!tags->nr_reserved_tags)) {
+			WARN_ON_ONCE(1);
+			return BLK_MQ_TAG_FAIL;
+		}
+		bt = &tags->breserved_tags;
+		tag_offset = 0;
+	} else {
+		bt = &tags->bitmap_tags;
+		tag_offset = tags->nr_reserved_tags;
+	}
+
+	tag = __blk_mq_get_tag(data, bt);
 	if (tag != -1)
-		return tag;
+		goto found_tag;
 
 	if (data->flags & BLK_MQ_REQ_NOWAIT)
-		return -1;
+		return BLK_MQ_TAG_FAIL;
 
-	ws = bt_wait_ptr(bt, hctx);
+	ws = bt_wait_ptr(bt, data->hctx);
+	drop_ctx = data->ctx == NULL;
 	do {
 		prepare_to_wait(&ws->wait, &wait, TASK_UNINTERRUPTIBLE);
 
-		tag = __bt_get(hctx, bt);
+		tag = __blk_mq_get_tag(data, bt);
 		if (tag != -1)
 			break;
 
 		/*
 		 * We're out of tags on this hardware queue, kick any
 		 * pending IO submits before going to sleep waiting for
-		 * some to complete. Note that hctx can be NULL here for
-		 * reserved tag allocation.
+		 * some to complete.
 		 */
-		if (hctx)
-			blk_mq_run_hw_queue(hctx, false);
+		blk_mq_run_hw_queue(data->hctx, false);
 
 		/*
 		 * Retry tag allocation after running the hardware queue,
 		 * as running the queue may also have found completions.
 		 */
-		tag = __bt_get(hctx, bt);
+		tag = __blk_mq_get_tag(data, bt);
 		if (tag != -1)
 			break;
 
-		blk_mq_put_ctx(data->ctx);
+		if (data->ctx)
+			blk_mq_put_ctx(data->ctx);
 
 		io_schedule();
 
 		data->ctx = blk_mq_get_ctx(data->q);
 		data->hctx = blk_mq_map_queue(data->q, data->ctx->cpu);
-		if (data->flags & BLK_MQ_REQ_RESERVED) {
-			bt = &data->hctx->tags->breserved_tags;
-		} else {
-			hctx = data->hctx;
-			bt = &hctx->tags->bitmap_tags;
-		}
+		tags = blk_mq_tags_from_data(data);
+		if (data->flags & BLK_MQ_REQ_RESERVED)
+			bt = &tags->breserved_tags;
+		else
+			bt = &tags->bitmap_tags;
+
 		finish_wait(&ws->wait, &wait);
-		ws = bt_wait_ptr(bt, hctx);
+		ws = bt_wait_ptr(bt, data->hctx);
 	} while (1);
 
-	finish_wait(&ws->wait, &wait);
-	return tag;
-}
-
-static unsigned int __blk_mq_get_tag(struct blk_mq_alloc_data *data)
-{
-	int tag;
-
-	tag = bt_get(data, &data->hctx->tags->bitmap_tags, data->hctx,
-		     data->hctx->tags);
-	if (tag >= 0)
-		return tag + data->hctx->tags->nr_reserved_tags;
-
-	return BLK_MQ_TAG_FAIL;
-}
-
-static unsigned int __blk_mq_get_reserved_tag(struct blk_mq_alloc_data *data)
-{
-	int tag;
-
-	if (unlikely(!data->hctx->tags->nr_reserved_tags)) {
-		WARN_ON_ONCE(1);
-		return BLK_MQ_TAG_FAIL;
-	}
-
-	tag = bt_get(data, &data->hctx->tags->breserved_tags, NULL,
-		     data->hctx->tags);
-	if (tag < 0)
-		return BLK_MQ_TAG_FAIL;
+	if (drop_ctx && data->ctx)
+		blk_mq_put_ctx(data->ctx);
 
-	return tag;
-}
+	finish_wait(&ws->wait, &wait);
 
-unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
-{
-	if (data->flags & BLK_MQ_REQ_RESERVED)
-		return __blk_mq_get_reserved_tag(data);
-	return __blk_mq_get_tag(data);
+found_tag:
+	return tag + tag_offset;
 }
 
-void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
-		    unsigned int tag)
+void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags *tags,
+		    struct blk_mq_ctx *ctx, unsigned int tag)
 {
-	struct blk_mq_tags *tags = hctx->tags;
-
 	if (tag >= tags->nr_reserved_tags) {
 		const int real_tag = tag - tags->nr_reserved_tags;
 
@@ -312,11 +296,11 @@ int blk_mq_reinit_tagset(struct blk_mq_tag_set *set)
 		struct blk_mq_tags *tags = set->tags[i];
 
 		for (j = 0; j < tags->nr_tags; j++) {
-			if (!tags->rqs[j])
+			if (!tags->static_rqs[j])
 				continue;
 
 			ret = set->ops->reinit_request(set->driver_data,
-						tags->rqs[j]);
+						tags->static_rqs[j]);
 			if (ret)
 				goto out;
 		}
@@ -351,11 +335,6 @@ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
 
 }
 
-static unsigned int bt_unused_tags(const struct sbitmap_queue *bt)
-{
-	return bt->sb.depth - sbitmap_weight(&bt->sb);
-}
-
 static int bt_alloc(struct sbitmap_queue *bt, unsigned int depth,
 		    bool round_robin, int node)
 {
@@ -411,19 +390,56 @@ void blk_mq_free_tags(struct blk_mq_tags *tags)
 	kfree(tags);
 }
 
-int blk_mq_tag_update_depth(struct blk_mq_tags *tags, unsigned int tdepth)
+int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
+			    struct blk_mq_tags **tagsptr, unsigned int tdepth,
+			    bool can_grow)
 {
-	tdepth -= tags->nr_reserved_tags;
-	if (tdepth > tags->nr_tags)
+	struct blk_mq_tags *tags = *tagsptr;
+
+	if (tdepth <= tags->nr_reserved_tags)
 		return -EINVAL;
 
+	tdepth -= tags->nr_reserved_tags;
+
 	/*
-	 * Don't need (or can't) update reserved tags here, they remain
-	 * static and should never need resizing.
+	 * If we are allowed to grow beyond the original size, allocate
+	 * a new set of tags before freeing the old one.
 	 */
-	sbitmap_queue_resize(&tags->bitmap_tags, tdepth);
+	if (tdepth > tags->nr_tags) {
+		struct blk_mq_tag_set *set = hctx->queue->tag_set;
+		struct blk_mq_tags *new;
+		bool ret;
+
+		if (!can_grow)
+			return -EINVAL;
+
+		/*
+		 * We need some sort of upper limit, set it high enough that
+		 * no valid use cases should require more.
+		 */
+		if (tdepth > 16 * BLKDEV_MAX_RQ)
+			return -EINVAL;
+
+		new = blk_mq_alloc_rq_map(set, hctx->queue_num, tdepth, 0);
+		if (!new)
+			return -ENOMEM;
+		ret = blk_mq_alloc_rqs(set, new, hctx->queue_num, tdepth);
+		if (ret) {
+			blk_mq_free_rq_map(new);
+			return -ENOMEM;
+		}
+
+		blk_mq_free_rqs(set, *tagsptr, hctx->queue_num);
+		blk_mq_free_rq_map(*tagsptr);
+		*tagsptr = new;
+	} else {
+		/*
+		 * Don't need (or can't) update reserved tags here, they
+		 * remain static and should never need resizing.
+		 */
+		sbitmap_queue_resize(&tags->bitmap_tags, tdepth);
+	}
 
-	blk_mq_tag_wakeup_all(tags, false);
 	return 0;
 }
 
@@ -454,25 +470,3 @@ u32 blk_mq_unique_tag(struct request *rq)
 		(rq->tag & BLK_MQ_UNIQUE_TAG_MASK);
 }
 EXPORT_SYMBOL(blk_mq_unique_tag);
-
-ssize_t blk_mq_tag_sysfs_show(struct blk_mq_tags *tags, char *page)
-{
-	char *orig_page = page;
-	unsigned int free, res;
-
-	if (!tags)
-		return 0;
-
-	page += sprintf(page, "nr_tags=%u, reserved_tags=%u, "
-			"bits_per_word=%u\n",
-			tags->nr_tags, tags->nr_reserved_tags,
-			1U << tags->bitmap_tags.sb.shift);
-
-	free = bt_unused_tags(&tags->bitmap_tags);
-	res = bt_unused_tags(&tags->breserved_tags);
-
-	page += sprintf(page, "nr_free=%u, nr_reserved=%u\n", free, res);
-	page += sprintf(page, "active_queues=%u\n", atomic_read(&tags->active_queues));
-
-	return page - orig_page;
-}

block/blk-mq-tag.h

@@ -16,6 +16,7 @@ struct blk_mq_tags {
 	struct sbitmap_queue breserved_tags;
 
 	struct request **rqs;
+	struct request **static_rqs;
 	struct list_head page_list;
 };
 
@@ -24,11 +25,12 @@ extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, unsigned int r
 extern void blk_mq_free_tags(struct blk_mq_tags *tags);
 
 extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data);
-extern void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
-			   unsigned int tag);
+extern void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags *tags,
+			   struct blk_mq_ctx *ctx, unsigned int tag);
 extern bool blk_mq_has_free_tags(struct blk_mq_tags *tags);
-extern ssize_t blk_mq_tag_sysfs_show(struct blk_mq_tags *tags, char *page);
-extern int blk_mq_tag_update_depth(struct blk_mq_tags *tags, unsigned int depth);
+extern int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
+					struct blk_mq_tags **tags,
+					unsigned int depth, bool can_grow);
 extern void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool);
 void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
 		void *priv);

block/blk-mq.c

@@ -32,6 +32,7 @@
 #include "blk-mq-tag.h"
 #include "blk-stat.h"
 #include "blk-wbt.h"
+#include "blk-mq-sched.h"
 
 static DEFINE_MUTEX(all_q_mutex);
 static LIST_HEAD(all_q_list);
@@ -39,9 +40,11 @@ static LIST_HEAD(all_q_list);
 /*
  * Check if any of the ctx's have pending work in this hardware queue
  */
-static bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx)
+bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx)
 {
-	return sbitmap_any_bit_set(&hctx->ctx_map);
+	return sbitmap_any_bit_set(&hctx->ctx_map) ||
+			!list_empty_careful(&hctx->dispatch) ||
+			blk_mq_sched_has_work(hctx);
 }
 
 /*
@@ -167,8 +170,8 @@ bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx)
 }
 EXPORT_SYMBOL(blk_mq_can_queue);
 
-static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
-			       struct request *rq, unsigned int op)
+void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
+			struct request *rq, unsigned int op)
 {
 	INIT_LIST_HEAD(&rq->queuelist);
 	/* csd/requeue_work/fifo_time is initialized before use */
@@ -213,53 +216,58 @@ static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
 
 	ctx->rq_dispatched[op_is_sync(op)]++;
 }
+EXPORT_SYMBOL_GPL(blk_mq_rq_ctx_init);
 
-static struct request *
-__blk_mq_alloc_request(struct blk_mq_alloc_data *data, unsigned int op)
+struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data,
+				       unsigned int op)
 {
 	struct request *rq;
 	unsigned int tag;
 
 	tag = blk_mq_get_tag(data);
 	if (tag != BLK_MQ_TAG_FAIL) {
-		rq = data->hctx->tags->rqs[tag];
+		struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
 
-		if (blk_mq_tag_busy(data->hctx)) {
-			rq->rq_flags = RQF_MQ_INFLIGHT;
-			atomic_inc(&data->hctx->nr_active);
+		rq = tags->static_rqs[tag];
+
+		if (data->flags & BLK_MQ_REQ_INTERNAL) {
+			rq->tag = -1;
+			rq->internal_tag = tag;
+		} else {
+			if (blk_mq_tag_busy(data->hctx)) {
+				rq->rq_flags = RQF_MQ_INFLIGHT;
+				atomic_inc(&data->hctx->nr_active);
+			}
+			rq->tag = tag;
+			rq->internal_tag = -1;
 		}
 
-		rq->tag = tag;
 		blk_mq_rq_ctx_init(data->q, data->ctx, rq, op);
 		return rq;
 	}
 
 	return NULL;
 }
+EXPORT_SYMBOL_GPL(__blk_mq_alloc_request);
 
 struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
 		unsigned int flags)
 {
-	struct blk_mq_ctx *ctx;
-	struct blk_mq_hw_ctx *hctx;
+	struct blk_mq_alloc_data alloc_data = { .flags = flags };
 	struct request *rq;
-	struct blk_mq_alloc_data alloc_data;
 	int ret;
 
 	ret = blk_queue_enter(q, flags & BLK_MQ_REQ_NOWAIT);
 	if (ret)
 		return ERR_PTR(ret);
 
-	ctx = blk_mq_get_ctx(q);
-	hctx = blk_mq_map_queue(q, ctx->cpu);
-	blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx);
-	rq = __blk_mq_alloc_request(&alloc_data, rw);
-	blk_mq_put_ctx(ctx);
+	rq = blk_mq_sched_get_request(q, NULL, rw, &alloc_data);
 
-	if (!rq) {
-		blk_queue_exit(q);
+	blk_mq_put_ctx(alloc_data.ctx);
+	blk_queue_exit(q);
+
+	if (!rq)
 		return ERR_PTR(-EWOULDBLOCK);
-	}
 
 	rq->__data_len = 0;
 	rq->__sector = (sector_t) -1;
@@ -319,10 +327,10 @@ out_queue_exit:
 }
 EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx);
 
-static void __blk_mq_free_request(struct blk_mq_hw_ctx *hctx,
-				  struct blk_mq_ctx *ctx, struct request *rq)
+void __blk_mq_finish_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
+			     struct request *rq)
 {
-	const int tag = rq->tag;
+	const int sched_tag = rq->internal_tag;
 	struct request_queue *q = rq->q;
 
 	if (rq->rq_flags & RQF_MQ_INFLIGHT)
@@ -333,23 +341,31 @@ static void __blk_mq_free_request(struct blk_mq_hw_ctx *hctx,
 
 	clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
 	clear_bit(REQ_ATOM_POLL_SLEPT, &rq->atomic_flags);
-	blk_mq_put_tag(hctx, ctx, tag);
+	if (rq->tag != -1)
+		blk_mq_put_tag(hctx, hctx->tags, ctx, rq->tag);
+	if (sched_tag != -1)
+		blk_mq_sched_completed_request(hctx, rq);
+	blk_mq_sched_restart_queues(hctx);
 	blk_queue_exit(q);
 }
 
-void blk_mq_free_hctx_request(struct blk_mq_hw_ctx *hctx, struct request *rq)
+static void blk_mq_finish_hctx_request(struct blk_mq_hw_ctx *hctx,
+				     struct request *rq)
 {
 	struct blk_mq_ctx *ctx = rq->mq_ctx;
 
 	ctx->rq_completed[rq_is_sync(rq)]++;
-	__blk_mq_free_request(hctx, ctx, rq);
+	__blk_mq_finish_request(hctx, ctx, rq);
+}
 
+void blk_mq_finish_request(struct request *rq)
+{
+	blk_mq_finish_hctx_request(blk_mq_map_queue(rq->q, rq->mq_ctx->cpu), rq);
 }
-EXPORT_SYMBOL_GPL(blk_mq_free_hctx_request);
 
 void blk_mq_free_request(struct request *rq)
 {
-	blk_mq_free_hctx_request(blk_mq_map_queue(rq->q, rq->mq_ctx->cpu), rq);
+	blk_mq_sched_put_request(rq);
 }
 EXPORT_SYMBOL_GPL(blk_mq_free_request);
 
@@ -467,6 +483,8 @@ void blk_mq_start_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 
+	blk_mq_sched_started_request(rq);
+
 	trace_block_rq_issue(q, rq);
 
 	rq->resid_len = blk_rq_bytes(rq);
@@ -515,6 +533,7 @@ static void __blk_mq_requeue_request(struct request *rq)
 
 	trace_block_rq_requeue(q, rq);
 	wbt_requeue(q->rq_wb, &rq->issue_stat);
+	blk_mq_sched_requeue_request(rq);
 
 	if (test_and_clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags)) {
 		if (q->dma_drain_size && blk_rq_bytes(rq))
@@ -549,13 +568,13 @@ static void blk_mq_requeue_work(struct work_struct *work)
 
 		rq->rq_flags &= ~RQF_SOFTBARRIER;
 		list_del_init(&rq->queuelist);
-		blk_mq_insert_request(rq, true, false, false);
+		blk_mq_sched_insert_request(rq, true, false, false, true);
 	}
 
 	while (!list_empty(&rq_list)) {
 		rq = list_entry(rq_list.next, struct request, queuelist);
 		list_del_init(&rq->queuelist);
-		blk_mq_insert_request(rq, false, false, false);
+		blk_mq_sched_insert_request(rq, false, false, false, true);
 	}
 
 	blk_mq_run_hw_queues(q, false);
@@ -639,7 +658,7 @@ struct blk_mq_timeout_data {
 
 void blk_mq_rq_timed_out(struct request *req, bool reserved)
 {
-	struct blk_mq_ops *ops = req->q->mq_ops;
+	const struct blk_mq_ops *ops = req->q->mq_ops;
 	enum blk_eh_timer_return ret = BLK_EH_RESET_TIMER;
 
 	/*
@@ -763,6 +782,12 @@ static bool blk_mq_attempt_merge(struct request_queue *q,
 			continue;
 
 		el_ret = blk_try_merge(rq, bio);
+		if (el_ret == ELEVATOR_NO_MERGE)
+			continue;
+
+		if (!blk_mq_sched_allow_merge(q, rq, bio))
+			break;
+
 		if (el_ret == ELEVATOR_BACK_MERGE) {
 			if (bio_attempt_back_merge(q, rq, bio)) {
 				ctx->rq_merged++;
@@ -803,7 +828,7 @@ static bool flush_busy_ctx(struct sbitmap *sb, unsigned int bitnr, void *data)
  * Process software queues that have been marked busy, splicing them
  * to the for-dispatch
  */
-static void flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list)
+void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 {
 	struct flush_busy_ctx_data data = {
 		.hctx = hctx,
@@ -812,6 +837,7 @@ static void flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 
 	sbitmap_for_each_set(&hctx->ctx_map, flush_busy_ctx, &data);
 }
+EXPORT_SYMBOL_GPL(blk_mq_flush_busy_ctxs);
 
 static inline unsigned int queued_to_index(unsigned int queued)
 {
@@ -821,6 +847,77 @@ static inline unsigned int queued_to_index(unsigned int queued)
 	return min(BLK_MQ_MAX_DISPATCH_ORDER - 1, ilog2(queued) + 1);
 }
 
+bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
+			   bool wait)
+{
+	struct blk_mq_alloc_data data = {
+		.q = rq->q,
+		.hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu),
+		.flags = wait ? 0 : BLK_MQ_REQ_NOWAIT,
+	};
+
+	if (blk_mq_hctx_stopped(data.hctx))
+		return false;
+
+	if (rq->tag != -1) {
+done:
+		if (hctx)
+			*hctx = data.hctx;
+		return true;
+	}
+
+	rq->tag = blk_mq_get_tag(&data);
+	if (rq->tag >= 0) {
+		if (blk_mq_tag_busy(data.hctx)) {
+			rq->rq_flags |= RQF_MQ_INFLIGHT;
+			atomic_inc(&data.hctx->nr_active);
+		}
+		data.hctx->tags->rqs[rq->tag] = rq;
+		goto done;
+	}
+
+	return false;
+}
+
+static void blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
+				  struct request *rq)
+{
+	if (rq->tag == -1 || rq->internal_tag == -1)
+		return;
+
+	blk_mq_put_tag(hctx, hctx->tags, rq->mq_ctx, rq->tag);
+	rq->tag = -1;
+
+	if (rq->rq_flags & RQF_MQ_INFLIGHT) {
+		rq->rq_flags &= ~RQF_MQ_INFLIGHT;
+		atomic_dec(&hctx->nr_active);
+	}
+}
+
+/*
+ * If we fail getting a driver tag because all the driver tags are already
+ * assigned and on the dispatch list, BUT the first entry does not have a
+ * tag, then we could deadlock. For that case, move entries with assigned
+ * driver tags to the front, leaving the set of tagged requests in the
+ * same order, and the untagged set in the same order.
+ */
+static bool reorder_tags_to_front(struct list_head *list)
+{
+	struct request *rq, *tmp, *first = NULL;
+
+	list_for_each_entry_safe_reverse(rq, tmp, list, queuelist) {
+		if (rq == first)
+			break;
+		if (rq->tag != -1) {
+			list_move(&rq->queuelist, list);
+			if (!first)
+				first = rq;
+		}
+	}
+
+	return first != NULL;
+}
+
 bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 {
 	struct request_queue *q = hctx->queue;
@@ -843,6 +940,20 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, 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)) {
+			if (!queued && reorder_tags_to_front(list))
+				continue;
+
+			/*
+			 * We failed getting a driver tag. Mark the queue(s)
+			 * as needing a restart. Retry getting a tag again,
+			 * in case the needed IO completed right before we
+			 * marked the queue as needing a restart.
+			 */
+			blk_mq_sched_mark_restart(hctx);
+			if (!blk_mq_get_driver_tag(rq, &hctx, false))
+				break;
+		}
 		list_del_init(&rq->queuelist);
 
 		bd.rq = rq;
@@ -855,6 +966,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 			queued++;
 			break;
 		case BLK_MQ_RQ_QUEUE_BUSY:
+			blk_mq_put_driver_tag(hctx, rq);
 			list_add(&rq->queuelist, list);
 			__blk_mq_requeue_request(rq);
 			break;
@@ -885,7 +997,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 	 */
 	if (!list_empty(list)) {
 		spin_lock(&hctx->lock);
-		list_splice(list, &hctx->dispatch);
+		list_splice_init(list, &hctx->dispatch);
 		spin_unlock(&hctx->lock);
 
 		/*
@@ -896,47 +1008,17 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 		 * the requests in rq_list might get lost.
 		 *
 		 * blk_mq_run_hw_queue() already checks the STOPPED bit
-		 **/
-		blk_mq_run_hw_queue(hctx, true);
+		 *
+		 * If RESTART is set, then let completion restart the queue
+		 * instead of potentially looping here.
+		 */
+		if (!blk_mq_sched_needs_restart(hctx))
+			blk_mq_run_hw_queue(hctx, true);
 	}
 
 	return ret != BLK_MQ_RQ_QUEUE_BUSY;
 }
 
-/*
- * Run this hardware queue, pulling any software queues mapped to it in.
- * Note that this function currently has various problems around ordering
- * of IO. In particular, we'd like FIFO behaviour on handling existing
- * items on the hctx->dispatch list. Ignore that for now.
- */
-static void blk_mq_process_rq_list(struct blk_mq_hw_ctx *hctx)
-{
-	LIST_HEAD(rq_list);
-
-	if (unlikely(blk_mq_hctx_stopped(hctx)))
-		return;
-
-	hctx->run++;
-
-	/*
-	 * Touch any software queue that has pending entries.
-	 */
-	flush_busy_ctxs(hctx, &rq_list);
-
-	/*
-	 * If we have previous entries on our dispatch list, grab them
-	 * and stuff them at the front 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);
-	}
-
-	blk_mq_dispatch_rq_list(hctx, &rq_list);
-}
-
 static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 {
 	int srcu_idx;
@@ -946,11 +1028,11 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 
 	if (!(hctx->flags & BLK_MQ_F_BLOCKING)) {
 		rcu_read_lock();
-		blk_mq_process_rq_list(hctx);
+		blk_mq_sched_dispatch_requests(hctx);
 		rcu_read_unlock();
 	} else {
 		srcu_idx = srcu_read_lock(&hctx->queue_rq_srcu);
-		blk_mq_process_rq_list(hctx);
+		blk_mq_sched_dispatch_requests(hctx);
 		srcu_read_unlock(&hctx->queue_rq_srcu, srcu_idx);
 	}
 }
@@ -1006,8 +1088,7 @@ void blk_mq_run_hw_queues(struct request_queue *q, bool async)
 	int i;
 
 	queue_for_each_hw_ctx(q, hctx, i) {
-		if ((!blk_mq_hctx_has_pending(hctx) &&
-		    list_empty_careful(&hctx->dispatch)) ||
+		if (!blk_mq_hctx_has_pending(hctx) ||
 		    blk_mq_hctx_stopped(hctx))
 			continue;
 
@@ -1116,6 +1197,7 @@ void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
 	if (unlikely(!blk_mq_hw_queue_mapped(hctx)))
 		return;
 
+	blk_mq_stop_hw_queue(hctx);
 	kblockd_schedule_delayed_work_on(blk_mq_hctx_next_cpu(hctx),
 			&hctx->delay_work, msecs_to_jiffies(msecs));
 }
@@ -1135,8 +1217,8 @@ static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx,
 		list_add_tail(&rq->queuelist, &ctx->rq_list);
 }
 
-static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx,
-				    struct request *rq, bool at_head)
+void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
+			     bool at_head)
 {
 	struct blk_mq_ctx *ctx = rq->mq_ctx;
 
@@ -1144,32 +1226,10 @@ static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx,
 	blk_mq_hctx_mark_pending(hctx, ctx);
 }
 
-void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue,
-			   bool async)
-{
-	struct blk_mq_ctx *ctx = rq->mq_ctx;
-	struct request_queue *q = rq->q;
-	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
-
-	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 void blk_mq_insert_requests(struct request_queue *q,
-				     struct blk_mq_ctx *ctx,
-				     struct list_head *list,
-				     int depth,
-				     bool from_schedule)
+void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
+			    struct list_head *list)
 
 {
-	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
-
-	trace_block_unplug(q, depth, !from_schedule);
-
 	/*
 	 * preemption doesn't flush plug list, so it's possible ctx->cpu is
 	 * offline now
@@ -1185,8 +1245,6 @@ static void blk_mq_insert_requests(struct request_queue *q,
 	}
 	blk_mq_hctx_mark_pending(hctx, ctx);
 	spin_unlock(&ctx->lock);
-
-	blk_mq_run_hw_queue(hctx, from_schedule);
 }
 
 static int plug_ctx_cmp(void *priv, struct list_head *a, struct list_head *b)
@@ -1222,9 +1280,10 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 		BUG_ON(!rq->q);
 		if (rq->mq_ctx != this_ctx) {
 			if (this_ctx) {
-				blk_mq_insert_requests(this_q, this_ctx,
-							&ctx_list, depth,
-							from_schedule);
+				trace_block_unplug(this_q, depth, from_schedule);
+				blk_mq_sched_insert_requests(this_q, this_ctx,
+								&ctx_list,
+								from_schedule);
 			}
 
 			this_ctx = rq->mq_ctx;
@@ -1241,8 +1300,9 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 	 * on 'ctx_list'. Do those.
 	 */
 	if (this_ctx) {
-		blk_mq_insert_requests(this_q, this_ctx, &ctx_list, depth,
-				       from_schedule);
+		trace_block_unplug(this_q, depth, from_schedule);
+		blk_mq_sched_insert_requests(this_q, this_ctx, &ctx_list,
+						from_schedule);
 	}
 }
 
@@ -1280,46 +1340,39 @@ insert_rq:
 		}
 
 		spin_unlock(&ctx->lock);
-		__blk_mq_free_request(hctx, ctx, rq);
+		__blk_mq_finish_request(hctx, ctx, rq);
 		return true;
 	}
 }
 
-static struct request *blk_mq_map_request(struct request_queue *q,
-					  struct bio *bio,
-					  struct blk_mq_alloc_data *data)
+static blk_qc_t request_to_qc_t(struct blk_mq_hw_ctx *hctx, struct request *rq)
 {
-	struct blk_mq_hw_ctx *hctx;
-	struct blk_mq_ctx *ctx;
-	struct request *rq;
-
-	blk_queue_enter_live(q);
-	ctx = blk_mq_get_ctx(q);
-	hctx = blk_mq_map_queue(q, ctx->cpu);
-
-	trace_block_getrq(q, bio, bio->bi_opf);
-	blk_mq_set_alloc_data(data, q, 0, ctx, hctx);
-	rq = __blk_mq_alloc_request(data, bio->bi_opf);
+	if (rq->tag != -1)
+		return blk_tag_to_qc_t(rq->tag, hctx->queue_num, false);
 
-	data->hctx->queued++;
-	return rq;
+	return blk_tag_to_qc_t(rq->internal_tag, hctx->queue_num, true);
 }
 
 static void blk_mq_try_issue_directly(struct request *rq, blk_qc_t *cookie)
 {
-	int ret;
 	struct request_queue *q = rq->q;
-	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, rq->mq_ctx->cpu);
 	struct blk_mq_queue_data bd = {
 		.rq = rq,
 		.list = NULL,
 		.last = 1
 	};
-	blk_qc_t new_cookie = blk_tag_to_qc_t(rq->tag, hctx->queue_num);
+	struct blk_mq_hw_ctx *hctx;
+	blk_qc_t new_cookie;
+	int ret;
 
-	if (blk_mq_hctx_stopped(hctx))
+	if (q->elevator)
 		goto insert;
 
+	if (!blk_mq_get_driver_tag(rq, &hctx, false))
+		goto insert;
+
+	new_cookie = request_to_qc_t(hctx, rq);
+
 	/*
 	 * For OK queue, we are done. For error, kill it. Any other
 	 * error (busy), just add it to our list as we previously
@@ -1341,7 +1394,7 @@ static void blk_mq_try_issue_directly(struct request *rq, blk_qc_t *cookie)
 	}
 
 insert:
-	blk_mq_insert_request(rq, false, true, true);
+	blk_mq_sched_insert_request(rq, false, true, true, false);
 }
 
 /*
@@ -1352,8 +1405,8 @@ insert:
 static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 {
 	const int is_sync = op_is_sync(bio->bi_opf);
-	const int is_flush_fua = bio->bi_opf & (REQ_PREFLUSH | REQ_FUA);
-	struct blk_mq_alloc_data data;
+	const int is_flush_fua = op_is_flush(bio->bi_opf);
+	struct blk_mq_alloc_data data = { .flags = 0 };
 	struct request *rq;
 	unsigned int request_count = 0, srcu_idx;
 	struct blk_plug *plug;
@@ -1374,9 +1427,14 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	    blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq))
 		return BLK_QC_T_NONE;
 
+	if (blk_mq_sched_bio_merge(q, bio))
+		return BLK_QC_T_NONE;
+
 	wb_acct = wbt_wait(q->rq_wb, bio, NULL);
 
-	rq = blk_mq_map_request(q, bio, &data);
+	trace_block_getrq(q, bio, bio->bi_opf);
+
+	rq = blk_mq_sched_get_request(q, bio, bio->bi_opf, &data);
 	if (unlikely(!rq)) {
 		__wbt_done(q->rq_wb, wb_acct);
 		return BLK_QC_T_NONE;
@@ -1384,12 +1442,15 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 
 	wbt_track(&rq->issue_stat, wb_acct);
 
-	cookie = blk_tag_to_qc_t(rq->tag, data.hctx->queue_num);
+	cookie = request_to_qc_t(data.hctx, rq);
 
 	if (unlikely(is_flush_fua)) {
+		blk_mq_put_ctx(data.ctx);
 		blk_mq_bio_to_request(rq, bio);
+		blk_mq_get_driver_tag(rq, NULL, true);
 		blk_insert_flush(rq);
-		goto run_queue;
+		blk_mq_run_hw_queue(data.hctx, true);
+		goto done;
 	}
 
 	plug = current->plug;
@@ -1438,6 +1499,13 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		goto done;
 	}
 
+	if (q->elevator) {
+		blk_mq_put_ctx(data.ctx);
+		blk_mq_bio_to_request(rq, bio);
+		blk_mq_sched_insert_request(rq, false, true,
+						!is_sync || is_flush_fua, true);
+		goto done;
+	}
 	if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
 		/*
 		 * For a SYNC request, send it to the hardware immediately. For
@@ -1445,7 +1513,6 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		 * latter allows for merging opportunities and more efficient
 		 * dispatching.
 		 */
-run_queue:
 		blk_mq_run_hw_queue(data.hctx, !is_sync || is_flush_fua);
 	}
 	blk_mq_put_ctx(data.ctx);
@@ -1460,10 +1527,10 @@ done:
 static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 {
 	const int is_sync = op_is_sync(bio->bi_opf);
-	const int is_flush_fua = bio->bi_opf & (REQ_PREFLUSH | REQ_FUA);
+	const int is_flush_fua = op_is_flush(bio->bi_opf);
 	struct blk_plug *plug;
 	unsigned int request_count = 0;
-	struct blk_mq_alloc_data data;
+	struct blk_mq_alloc_data data = { .flags = 0 };
 	struct request *rq;
 	blk_qc_t cookie;
 	unsigned int wb_acct;
@@ -1483,9 +1550,14 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 	} else
 		request_count = blk_plug_queued_count(q);
 
+	if (blk_mq_sched_bio_merge(q, bio))
+		return BLK_QC_T_NONE;
+
 	wb_acct = wbt_wait(q->rq_wb, bio, NULL);
 
-	rq = blk_mq_map_request(q, bio, &data);
+	trace_block_getrq(q, bio, bio->bi_opf);
+
+	rq = blk_mq_sched_get_request(q, bio, bio->bi_opf, &data);
 	if (unlikely(!rq)) {
 		__wbt_done(q->rq_wb, wb_acct);
 		return BLK_QC_T_NONE;
@@ -1493,12 +1565,15 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 
 	wbt_track(&rq->issue_stat, wb_acct);
 
-	cookie = blk_tag_to_qc_t(rq->tag, data.hctx->queue_num);
+	cookie = request_to_qc_t(data.hctx, rq);
 
 	if (unlikely(is_flush_fua)) {
+		blk_mq_put_ctx(data.ctx);
 		blk_mq_bio_to_request(rq, bio);
+		blk_mq_get_driver_tag(rq, NULL, true);
 		blk_insert_flush(rq);
-		goto run_queue;
+		blk_mq_run_hw_queue(data.hctx, true);
+		goto done;
 	}
 
 	/*
@@ -1535,6 +1610,13 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 		return cookie;
 	}
 
+	if (q->elevator) {
+		blk_mq_put_ctx(data.ctx);
+		blk_mq_bio_to_request(rq, bio);
+		blk_mq_sched_insert_request(rq, false, true,
+						!is_sync || is_flush_fua, true);
+		goto done;
+	}
 	if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
 		/*
 		 * For a SYNC request, send it to the hardware immediately. For
@@ -1542,16 +1624,16 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 		 * latter allows for merging opportunities and more efficient
 		 * dispatching.
 		 */
-run_queue:
 		blk_mq_run_hw_queue(data.hctx, !is_sync || is_flush_fua);
 	}
 
 	blk_mq_put_ctx(data.ctx);
+done:
 	return cookie;
 }
 
-static void blk_mq_free_rq_map(struct blk_mq_tag_set *set,
-		struct blk_mq_tags *tags, unsigned int hctx_idx)
+void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
+		     unsigned int hctx_idx)
 {
 	struct page *page;
 
@@ -1559,11 +1641,13 @@ static void blk_mq_free_rq_map(struct blk_mq_tag_set *set,
 		int i;
 
 		for (i = 0; i < tags->nr_tags; i++) {
-			if (!tags->rqs[i])
+			struct request *rq = tags->static_rqs[i];
+
+			if (!rq)
 				continue;
-			set->ops->exit_request(set->driver_data, tags->rqs[i],
+			set->ops->exit_request(set->driver_data, rq,
 						hctx_idx, i);
-			tags->rqs[i] = NULL;
+			tags->static_rqs[i] = NULL;
 		}
 	}
 
@@ -1577,33 +1661,32 @@ static void blk_mq_free_rq_map(struct blk_mq_tag_set *set,
 		kmemleak_free(page_address(page));
 		__free_pages(page, page->private);
 	}
+}
 
+void blk_mq_free_rq_map(struct blk_mq_tags *tags)
+{
 	kfree(tags->rqs);
+	tags->rqs = NULL;
+	kfree(tags->static_rqs);
+	tags->static_rqs = NULL;
 
 	blk_mq_free_tags(tags);
 }
 
-static size_t order_to_size(unsigned int order)
-{
-	return (size_t)PAGE_SIZE << order;
-}
-
-static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
-		unsigned int hctx_idx)
+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)
 {
 	struct blk_mq_tags *tags;
-	unsigned int i, j, entries_per_page, max_order = 4;
-	size_t rq_size, left;
 
-	tags = blk_mq_init_tags(set->queue_depth, set->reserved_tags,
+	tags = blk_mq_init_tags(nr_tags, reserved_tags,
 				set->numa_node,
 				BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags));
 	if (!tags)
 		return NULL;
 
-	INIT_LIST_HEAD(&tags->page_list);
-
-	tags->rqs = kzalloc_node(set->queue_depth * sizeof(struct request *),
+	tags->rqs = kzalloc_node(nr_tags * sizeof(struct request *),
 				 GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
 				 set->numa_node);
 	if (!tags->rqs) {
@@ -1611,15 +1694,40 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
 		return NULL;
 	}
 
+	tags->static_rqs = kzalloc_node(nr_tags * sizeof(struct request *),
+				 GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
+				 set->numa_node);
+	if (!tags->static_rqs) {
+		kfree(tags->rqs);
+		blk_mq_free_tags(tags);
+		return NULL;
+	}
+
+	return tags;
+}
+
+static size_t order_to_size(unsigned int order)
+{
+	return (size_t)PAGE_SIZE << order;
+}
+
+int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
+		     unsigned int hctx_idx, unsigned int depth)
+{
+	unsigned int i, j, entries_per_page, max_order = 4;
+	size_t rq_size, left;
+
+	INIT_LIST_HEAD(&tags->page_list);
+
 	/*
 	 * rq_size is the size of the request plus driver payload, rounded
 	 * to the cacheline size
 	 */
 	rq_size = round_up(sizeof(struct request) + set->cmd_size,
 				cache_line_size());
-	left = rq_size * set->queue_depth;
+	left = rq_size * depth;
 
-	for (i = 0; i < set->queue_depth; ) {
+	for (i = 0; i < depth; ) {
 		int this_order = max_order;
 		struct page *page;
 		int to_do;
@@ -1653,15 +1761,17 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
 		 */
 		kmemleak_alloc(p, order_to_size(this_order), 1, GFP_NOIO);
 		entries_per_page = order_to_size(this_order) / rq_size;
-		to_do = min(entries_per_page, set->queue_depth - i);
+		to_do = min(entries_per_page, depth - i);
 		left -= to_do * rq_size;
 		for (j = 0; j < to_do; j++) {
-			tags->rqs[i] = p;
+			struct request *rq = p;
+
+			tags->static_rqs[i] = rq;
 			if (set->ops->init_request) {
 				if (set->ops->init_request(set->driver_data,
-						tags->rqs[i], hctx_idx, i,
+						rq, hctx_idx, i,
 						set->numa_node)) {
-					tags->rqs[i] = NULL;
+					tags->static_rqs[i] = NULL;
 					goto fail;
 				}
 			}
@@ -1670,11 +1780,11 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
 			i++;
 		}
 	}
-	return tags;
+	return 0;
 
 fail:
-	blk_mq_free_rq_map(set, tags, hctx_idx);
-	return NULL;
+	blk_mq_free_rqs(set, tags, hctx_idx);
+	return -ENOMEM;
 }
 
 /*
@@ -1866,6 +1976,35 @@ static void blk_mq_init_cpu_queues(struct request_queue *q,
 	}
 }
 
+static bool __blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, int hctx_idx)
+{
+	int ret = 0;
+
+	set->tags[hctx_idx] = blk_mq_alloc_rq_map(set, hctx_idx,
+					set->queue_depth, set->reserved_tags);
+	if (!set->tags[hctx_idx])
+		return false;
+
+	ret = blk_mq_alloc_rqs(set, set->tags[hctx_idx], hctx_idx,
+				set->queue_depth);
+	if (!ret)
+		return true;
+
+	blk_mq_free_rq_map(set->tags[hctx_idx]);
+	set->tags[hctx_idx] = NULL;
+	return false;
+}
+
+static void blk_mq_free_map_and_requests(struct blk_mq_tag_set *set,
+					 unsigned int hctx_idx)
+{
+	if (set->tags[hctx_idx]) {
+		blk_mq_free_rqs(set, set->tags[hctx_idx], hctx_idx);
+		blk_mq_free_rq_map(set->tags[hctx_idx]);
+		set->tags[hctx_idx] = NULL;
+	}
+}
+
 static void blk_mq_map_swqueue(struct request_queue *q,
 			       const struct cpumask *online_mask)
 {
@@ -1894,17 +2033,15 @@ static void blk_mq_map_swqueue(struct request_queue *q,
 
 		hctx_idx = q->mq_map[i];
 		/* unmapped hw queue can be remapped after CPU topo changed */
-		if (!set->tags[hctx_idx]) {
-			set->tags[hctx_idx] = blk_mq_init_rq_map(set, hctx_idx);
-
+		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
 			 */
-			if (!set->tags[hctx_idx])
-				q->mq_map[i] = 0;
+			q->mq_map[i] = 0;
 		}
 
 		ctx = per_cpu_ptr(q->queue_ctx, i);
@@ -1927,10 +2064,9 @@ static void blk_mq_map_swqueue(struct request_queue *q,
 			 * fallback in case of a new remap fails
 			 * allocation
 			 */
-			if (i && set->tags[i]) {
-				blk_mq_free_rq_map(set, set->tags[i], i);
-				set->tags[i] = NULL;
-			}
+			if (i && set->tags[i])
+				blk_mq_free_map_and_requests(set, i);
+
 			hctx->tags = NULL;
 			continue;
 		}
@@ -2023,6 +2159,8 @@ void blk_mq_release(struct request_queue *q)
 	struct blk_mq_hw_ctx *hctx;
 	unsigned int i;
 
+	blk_mq_sched_teardown(q);
+
 	/* hctx kobj stays in hctx */
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (!hctx)
@@ -2097,10 +2235,8 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 		struct blk_mq_hw_ctx *hctx = hctxs[j];
 
 		if (hctx) {
-			if (hctx->tags) {
-				blk_mq_free_rq_map(set, hctx->tags, j);
-				set->tags[j] = NULL;
-			}
+			if (hctx->tags)
+				blk_mq_free_map_and_requests(set, j);
 			blk_mq_exit_hctx(q, set, hctx, j);
 			free_cpumask_var(hctx->cpumask);
 			kobject_put(&hctx->kobj);
@@ -2181,6 +2317,14 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	mutex_unlock(&all_q_mutex);
 	put_online_cpus();
 
+	if (!(set->flags & BLK_MQ_F_NO_SCHED)) {
+		int ret;
+
+		ret = blk_mq_sched_init(q);
+		if (ret)
+			return ERR_PTR(ret);
+	}
+
 	return q;
 
 err_hctxs:
@@ -2279,10 +2423,10 @@ static int blk_mq_queue_reinit_dead(unsigned int cpu)
  * Now CPU1 is just onlined and a request is inserted into ctx1->rq_list
  * and set bit0 in pending bitmap as ctx1->index_hw is still zero.
  *
- * And then while running hw queue, flush_busy_ctxs() finds bit0 is set in
- * pending bitmap and tries to retrieve requests in hctx->ctxs[0]->rq_list.
- * But htx->ctxs[0] is a pointer to ctx0, so the request in ctx1->rq_list
- * is ignored.
+ * And then while running hw queue, blk_mq_flush_busy_ctxs() finds bit0 is set
+ * in pending bitmap and tries to retrieve requests in hctx->ctxs[0]->rq_list.
+ * But htx->ctxs[0] is a pointer to ctx0, so the request in ctx1->rq_list is
+ * ignored.
  */
 static int blk_mq_queue_reinit_prepare(unsigned int cpu)
 {
@@ -2296,17 +2440,15 @@ static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
 {
 	int i;
 
-	for (i = 0; i < set->nr_hw_queues; i++) {
-		set->tags[i] = blk_mq_init_rq_map(set, i);
-		if (!set->tags[i])
+	for (i = 0; i < set->nr_hw_queues; i++)
+		if (!__blk_mq_alloc_rq_map(set, i))
 			goto out_unwind;
-	}
 
 	return 0;
 
 out_unwind:
 	while (--i >= 0)
-		blk_mq_free_rq_map(set, set->tags[i], i);
+		blk_mq_free_rq_map(set->tags[i]);
 
 	return -ENOMEM;
 }
@@ -2430,10 +2572,8 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set)
 {
 	int i;
 
-	for (i = 0; i < nr_cpu_ids; i++) {
-		if (set->tags[i])
-			blk_mq_free_rq_map(set, set->tags[i], i);
-	}
+	for (i = 0; i < nr_cpu_ids; i++)
+		blk_mq_free_map_and_requests(set, i);
 
 	kfree(set->mq_map);
 	set->mq_map = NULL;
@@ -2449,14 +2589,28 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
 	struct blk_mq_hw_ctx *hctx;
 	int i, ret;
 
-	if (!set || nr > set->queue_depth)
+	if (!set)
 		return -EINVAL;
 
+	blk_mq_freeze_queue(q);
+	blk_mq_quiesce_queue(q);
+
 	ret = 0;
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (!hctx->tags)
 			continue;
-		ret = blk_mq_tag_update_depth(hctx->tags, nr);
+		/*
+		 * If we're using an MQ scheduler, just update the scheduler
+		 * queue depth. This is similar to what the old code would do.
+		 */
+		if (!hctx->sched_tags) {
+			ret = blk_mq_tag_update_depth(hctx, &hctx->tags,
+							min(nr, set->queue_depth),
+							false);
+		} else {
+			ret = blk_mq_tag_update_depth(hctx, &hctx->sched_tags,
+							nr, true);
+		}
 		if (ret)
 			break;
 	}
@@ -2464,6 +2618,9 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
 	if (!ret)
 		q->nr_requests = nr;
 
+	blk_mq_unfreeze_queue(q);
+	blk_mq_start_stopped_hw_queues(q, true);
+
 	return ret;
 }
 
@@ -2649,7 +2806,10 @@ bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie)
 		blk_flush_plug_list(plug, false);
 
 	hctx = q->queue_hw_ctx[blk_qc_t_to_queue_num(cookie)];
-	rq = blk_mq_tag_to_rq(hctx->tags, blk_qc_t_to_tag(cookie));
+	if (!blk_qc_t_is_internal(cookie))
+		rq = blk_mq_tag_to_rq(hctx->tags, blk_qc_t_to_tag(cookie));
+	else
+		rq = blk_mq_tag_to_rq(hctx->sched_tags, blk_qc_t_to_tag(cookie));
 
 	return __blk_mq_poll(hctx, rq);
 }
@@ -2667,6 +2827,8 @@ void blk_mq_enable_hotplug(void)
 
 static int __init blk_mq_init(void)
 {
+	blk_mq_debugfs_init();
+
 	cpuhp_setup_state_multi(CPUHP_BLK_MQ_DEAD, "block/mq:dead", NULL,
 				blk_mq_hctx_notify_dead);
 

block/blk-mq.h

@@ -32,7 +32,31 @@ void blk_mq_free_queue(struct request_queue *q);
 int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
 void blk_mq_wake_waiters(struct request_queue *q);
 bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *, struct list_head *);
+void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list);
+bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx);
+bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
+				bool wait);
 
+/*
+ * Internal helpers for allocating/freeing the request map
+ */
+void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
+		     unsigned int hctx_idx);
+void blk_mq_free_rq_map(struct blk_mq_tags *tags);
+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);
+int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
+		     unsigned int hctx_idx, unsigned int depth);
+
+/*
+ * Internal helpers for request insertion into sw queues
+ */
+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
  */
@@ -57,6 +81,40 @@ extern int blk_mq_sysfs_register(struct request_queue *q);
 extern void blk_mq_sysfs_unregister(struct request_queue *q);
 extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
 
+/*
+ * debugfs helpers
+ */
+#ifdef CONFIG_BLK_DEBUG_FS
+void blk_mq_debugfs_init(void);
+int blk_mq_debugfs_register(struct request_queue *q, const char *name);
+void blk_mq_debugfs_unregister(struct request_queue *q);
+int blk_mq_debugfs_register_hctxs(struct request_queue *q);
+void blk_mq_debugfs_unregister_hctxs(struct request_queue *q);
+#else
+static inline void blk_mq_debugfs_init(void)
+{
+}
+
+static inline int blk_mq_debugfs_register(struct request_queue *q,
+					  const char *name)
+{
+	return 0;
+}
+
+static inline void blk_mq_debugfs_unregister(struct request_queue *q)
+{
+}
+
+static inline int blk_mq_debugfs_register_hctxs(struct request_queue *q)
+{
+	return 0;
+}
+
+static inline void blk_mq_debugfs_unregister_hctxs(struct request_queue *q)
+{
+}
+#endif
+
 extern void blk_mq_rq_timed_out(struct request *req, bool reserved);
 
 void blk_mq_release(struct request_queue *q);
@@ -103,6 +161,25 @@ static inline void blk_mq_set_alloc_data(struct blk_mq_alloc_data *data,
 	data->hctx = hctx;
 }
 
+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;
+}
+
+/*
+ * Internal helpers for request allocation/init/free
+ */
+void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
+			struct request *rq, unsigned int op);
+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);
+
 static inline bool blk_mq_hctx_stopped(struct blk_mq_hw_ctx *hctx)
 {
 	return test_bit(BLK_MQ_S_STOPPED, &hctx->state);

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",

block/blk-throttle.c

@@ -866,10 +866,12 @@ static void tg_update_disptime(struct throtl_grp *tg)
 	unsigned long read_wait = -1, write_wait = -1, min_wait = -1, disptime;
 	struct bio *bio;
 
-	if ((bio = throtl_peek_queued(&sq->queued[READ])))
+	bio = throtl_peek_queued(&sq->queued[READ]);
+	if (bio)
 		tg_may_dispatch(tg, bio, &read_wait);
 
-	if ((bio = throtl_peek_queued(&sq->queued[WRITE])))
+	bio = throtl_peek_queued(&sq->queued[WRITE]);
+	if (bio)
 		tg_may_dispatch(tg, bio, &write_wait);
 
 	min_wait = min(read_wait, write_wait);

block/blk.h

@@ -167,7 +167,7 @@ static inline struct request *__elv_next_request(struct request_queue *q)
 			return NULL;
 		}
 		if (unlikely(blk_queue_bypass(q)) ||
-		    !q->elevator->type->ops.elevator_dispatch_fn(q, 0))
+		    !q->elevator->type->ops.sq.elevator_dispatch_fn(q, 0))
 			return NULL;
 	}
 }
@@ -176,16 +176,16 @@ static inline void elv_activate_rq(struct request_queue *q, struct request *rq)
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_activate_req_fn)
-		e->type->ops.elevator_activate_req_fn(q, rq);
+	if (e->type->ops.sq.elevator_activate_req_fn)
+		e->type->ops.sq.elevator_activate_req_fn(q, rq);
 }
 
 static inline void elv_deactivate_rq(struct request_queue *q, struct request *rq)
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_deactivate_req_fn)
-		e->type->ops.elevator_deactivate_req_fn(q, rq);
+	if (e->type->ops.sq.elevator_deactivate_req_fn)
+		e->type->ops.sq.elevator_deactivate_req_fn(q, rq);
 }
 
 #ifdef CONFIG_FAIL_IO_TIMEOUT
@@ -263,6 +263,22 @@ void ioc_clear_queue(struct request_queue *q);
 
 int create_task_io_context(struct task_struct *task, gfp_t gfp_mask, int node);
 
+/**
+ * rq_ioc - determine io_context for request allocation
+ * @bio: request being allocated is for this bio (can be %NULL)
+ *
+ * Determine io_context to use for request allocation for @bio.  May return
+ * %NULL if %current->io_context doesn't exist.
+ */
+static inline struct io_context *rq_ioc(struct bio *bio)
+{
+#ifdef CONFIG_BLK_CGROUP
+	if (bio && bio->bi_ioc)
+		return bio->bi_ioc;
+#endif
+	return current->io_context;
+}
+
 /**
  * create_io_context - try to create task->io_context
  * @gfp_mask: allocation mask

block/cfq-iosched.c

@@ -2749,9 +2749,11 @@ static struct cfq_queue *cfq_get_next_queue_forced(struct cfq_data *cfqd)
 	if (!cfqg)
 		return NULL;
 
-	for_each_cfqg_st(cfqg, i, j, st)
-		if ((cfqq = cfq_rb_first(st)) != NULL)
+	for_each_cfqg_st(cfqg, i, j, st) {
+		cfqq = cfq_rb_first(st);
+		if (cfqq)
 			return cfqq;
+	}
 	return NULL;
 }
 
@@ -3864,6 +3866,8 @@ cfq_get_queue(struct cfq_data *cfqd, bool is_sync, struct cfq_io_cq *cic,
 		goto out;
 	}
 
+	/* cfq_init_cfqq() assumes cfqq->ioprio_class is initialized. */
+	cfqq->ioprio_class = IOPRIO_CLASS_NONE;
 	cfq_init_cfqq(cfqd, cfqq, current->pid, is_sync);
 	cfq_init_prio_data(cfqq, cic);
 	cfq_link_cfqq_cfqg(cfqq, cfqg);
@@ -4837,7 +4841,7 @@ static struct elv_fs_entry cfq_attrs[] = {
 };
 
 static struct elevator_type iosched_cfq = {
-	.ops = {
+	.ops.sq = {
 		.elevator_merge_fn = 		cfq_merge,
 		.elevator_merged_fn =		cfq_merged_request,
 		.elevator_merge_req_fn =	cfq_merged_requests,

block/deadline-iosched.c

@@ -439,7 +439,7 @@ static struct elv_fs_entry deadline_attrs[] = {
 };
 
 static struct elevator_type iosched_deadline = {
-	.ops = {
+	.ops.sq = {
 		.elevator_merge_fn = 		deadline_merge,
 		.elevator_merged_fn =		deadline_merged_request,
 		.elevator_merge_req_fn =	deadline_merged_requests,

block/elevator.c

@@ -40,6 +40,7 @@
 #include <trace/events/block.h>
 
 #include "blk.h"
+#include "blk-mq-sched.h"
 
 static DEFINE_SPINLOCK(elv_list_lock);
 static LIST_HEAD(elv_list);
@@ -58,8 +59,10 @@ static int elv_iosched_allow_bio_merge(struct request *rq, struct bio *bio)
 	struct request_queue *q = rq->q;
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_allow_bio_merge_fn)
-		return e->type->ops.elevator_allow_bio_merge_fn(q, rq, bio);
+	if (e->uses_mq && e->type->ops.mq.allow_merge)
+		return e->type->ops.mq.allow_merge(q, rq, bio);
+	else if (!e->uses_mq && e->type->ops.sq.elevator_allow_bio_merge_fn)
+		return e->type->ops.sq.elevator_allow_bio_merge_fn(q, rq, bio);
 
 	return 1;
 }
@@ -163,6 +166,7 @@ struct elevator_queue *elevator_alloc(struct request_queue *q,
 	kobject_init(&eq->kobj, &elv_ktype);
 	mutex_init(&eq->sysfs_lock);
 	hash_init(eq->hash);
+	eq->uses_mq = e->uses_mq;
 
 	return eq;
 }
@@ -215,18 +219,32 @@ int elevator_init(struct request_queue *q, char *name)
 	}
 
 	if (!e) {
-		e = elevator_get(CONFIG_DEFAULT_IOSCHED, false);
+		if (q->mq_ops && q->nr_hw_queues == 1)
+			e = elevator_get(CONFIG_DEFAULT_SQ_IOSCHED, false);
+		else if (q->mq_ops)
+			e = elevator_get(CONFIG_DEFAULT_MQ_IOSCHED, false);
+		else
+			e = elevator_get(CONFIG_DEFAULT_IOSCHED, false);
+
 		if (!e) {
 			printk(KERN_ERR
 				"Default I/O scheduler not found. " \
-				"Using noop.\n");
+				"Using noop/none.\n");
 			e = elevator_get("noop", false);
 		}
 	}
 
-	err = e->ops.elevator_init_fn(q, e);
-	if (err)
+	if (e->uses_mq) {
+		err = blk_mq_sched_setup(q);
+		if (!err)
+			err = e->ops.mq.init_sched(q, e);
+	} else
+		err = e->ops.sq.elevator_init_fn(q, e);
+	if (err) {
+		if (e->uses_mq)
+			blk_mq_sched_teardown(q);
 		elevator_put(e);
+	}
 	return err;
 }
 EXPORT_SYMBOL(elevator_init);
@@ -234,8 +252,10 @@ EXPORT_SYMBOL(elevator_init);
 void elevator_exit(struct elevator_queue *e)
 {
 	mutex_lock(&e->sysfs_lock);
-	if (e->type->ops.elevator_exit_fn)
-		e->type->ops.elevator_exit_fn(e);
+	if (e->uses_mq && e->type->ops.mq.exit_sched)
+		e->type->ops.mq.exit_sched(e);
+	else if (!e->uses_mq && e->type->ops.sq.elevator_exit_fn)
+		e->type->ops.sq.elevator_exit_fn(e);
 	mutex_unlock(&e->sysfs_lock);
 
 	kobject_put(&e->kobj);
@@ -253,6 +273,7 @@ void elv_rqhash_del(struct request_queue *q, struct request *rq)
 	if (ELV_ON_HASH(rq))
 		__elv_rqhash_del(rq);
 }
+EXPORT_SYMBOL_GPL(elv_rqhash_del);
 
 void elv_rqhash_add(struct request_queue *q, struct request *rq)
 {
@@ -262,6 +283,7 @@ void elv_rqhash_add(struct request_queue *q, struct request *rq)
 	hash_add(e->hash, &rq->hash, rq_hash_key(rq));
 	rq->rq_flags |= RQF_HASHED;
 }
+EXPORT_SYMBOL_GPL(elv_rqhash_add);
 
 void elv_rqhash_reposition(struct request_queue *q, struct request *rq)
 {
@@ -443,8 +465,10 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
 		return ELEVATOR_BACK_MERGE;
 	}
 
-	if (e->type->ops.elevator_merge_fn)
-		return e->type->ops.elevator_merge_fn(q, req, bio);
+	if (e->uses_mq && e->type->ops.mq.request_merge)
+		return e->type->ops.mq.request_merge(q, req, bio);
+	else if (!e->uses_mq && e->type->ops.sq.elevator_merge_fn)
+		return e->type->ops.sq.elevator_merge_fn(q, req, bio);
 
 	return ELEVATOR_NO_MERGE;
 }
@@ -456,8 +480,7 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
  *
  * Returns true if we merged, false otherwise
  */
-static bool elv_attempt_insert_merge(struct request_queue *q,
-				     struct request *rq)
+bool elv_attempt_insert_merge(struct request_queue *q, struct request *rq)
 {
 	struct request *__rq;
 	bool ret;
@@ -495,8 +518,10 @@ void elv_merged_request(struct request_queue *q, struct request *rq, int type)
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_merged_fn)
-		e->type->ops.elevator_merged_fn(q, rq, type);
+	if (e->uses_mq && e->type->ops.mq.request_merged)
+		e->type->ops.mq.request_merged(q, rq, type);
+	else if (!e->uses_mq && e->type->ops.sq.elevator_merged_fn)
+		e->type->ops.sq.elevator_merged_fn(q, rq, type);
 
 	if (type == ELEVATOR_BACK_MERGE)
 		elv_rqhash_reposition(q, rq);
@@ -508,10 +533,15 @@ void elv_merge_requests(struct request_queue *q, struct request *rq,
 			     struct request *next)
 {
 	struct elevator_queue *e = q->elevator;
-	const int next_sorted = next->rq_flags & RQF_SORTED;
-
-	if (next_sorted && e->type->ops.elevator_merge_req_fn)
-		e->type->ops.elevator_merge_req_fn(q, rq, next);
+	bool next_sorted = false;
+
+	if (e->uses_mq && e->type->ops.mq.requests_merged)
+		e->type->ops.mq.requests_merged(q, rq, next);
+	else if (e->type->ops.sq.elevator_merge_req_fn) {
+		next_sorted = next->rq_flags & RQF_SORTED;
+		if (next_sorted)
+			e->type->ops.sq.elevator_merge_req_fn(q, rq, next);
+	}
 
 	elv_rqhash_reposition(q, rq);
 
@@ -528,8 +558,11 @@ void elv_bio_merged(struct request_queue *q, struct request *rq,
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_bio_merged_fn)
-		e->type->ops.elevator_bio_merged_fn(q, rq, bio);
+	if (WARN_ON_ONCE(e->uses_mq))
+		return;
+
+	if (e->type->ops.sq.elevator_bio_merged_fn)
+		e->type->ops.sq.elevator_bio_merged_fn(q, rq, bio);
 }
 
 #ifdef CONFIG_PM
@@ -574,11 +607,15 @@ void elv_requeue_request(struct request_queue *q, struct request *rq)
 
 void elv_drain_elevator(struct request_queue *q)
 {
+	struct elevator_queue *e = q->elevator;
 	static int printed;
 
+	if (WARN_ON_ONCE(e->uses_mq))
+		return;
+
 	lockdep_assert_held(q->queue_lock);
 
-	while (q->elevator->type->ops.elevator_dispatch_fn(q, 1))
+	while (e->type->ops.sq.elevator_dispatch_fn(q, 1))
 		;
 	if (q->nr_sorted && printed++ < 10) {
 		printk(KERN_ERR "%s: forced dispatching is broken "
@@ -653,7 +690,7 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where)
 		 * rq cannot be accessed after calling
 		 * elevator_add_req_fn.
 		 */
-		q->elevator->type->ops.elevator_add_req_fn(q, rq);
+		q->elevator->type->ops.sq.elevator_add_req_fn(q, rq);
 		break;
 
 	case ELEVATOR_INSERT_FLUSH:
@@ -682,8 +719,11 @@ struct request *elv_latter_request(struct request_queue *q, struct request *rq)
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_latter_req_fn)
-		return e->type->ops.elevator_latter_req_fn(q, rq);
+	if (e->uses_mq && e->type->ops.mq.next_request)
+		return e->type->ops.mq.next_request(q, rq);
+	else if (!e->uses_mq && e->type->ops.sq.elevator_latter_req_fn)
+		return e->type->ops.sq.elevator_latter_req_fn(q, rq);
+
 	return NULL;
 }
 
@@ -691,8 +731,10 @@ struct request *elv_former_request(struct request_queue *q, struct request *rq)
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_former_req_fn)
-		return e->type->ops.elevator_former_req_fn(q, rq);
+	if (e->uses_mq && e->type->ops.mq.former_request)
+		return e->type->ops.mq.former_request(q, rq);
+	if (!e->uses_mq && e->type->ops.sq.elevator_former_req_fn)
+		return e->type->ops.sq.elevator_former_req_fn(q, rq);
 	return NULL;
 }
 
@@ -701,8 +743,11 @@ int elv_set_request(struct request_queue *q, struct request *rq,
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_set_req_fn)
-		return e->type->ops.elevator_set_req_fn(q, rq, bio, gfp_mask);
+	if (WARN_ON_ONCE(e->uses_mq))
+		return 0;
+
+	if (e->type->ops.sq.elevator_set_req_fn)
+		return e->type->ops.sq.elevator_set_req_fn(q, rq, bio, gfp_mask);
 	return 0;
 }
 
@@ -710,16 +755,22 @@ void elv_put_request(struct request_queue *q, struct request *rq)
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_put_req_fn)
-		e->type->ops.elevator_put_req_fn(rq);
+	if (WARN_ON_ONCE(e->uses_mq))
+		return;
+
+	if (e->type->ops.sq.elevator_put_req_fn)
+		e->type->ops.sq.elevator_put_req_fn(rq);
 }
 
 int elv_may_queue(struct request_queue *q, unsigned int op)
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_may_queue_fn)
-		return e->type->ops.elevator_may_queue_fn(q, op);
+	if (WARN_ON_ONCE(e->uses_mq))
+		return 0;
+
+	if (e->type->ops.sq.elevator_may_queue_fn)
+		return e->type->ops.sq.elevator_may_queue_fn(q, op);
 
 	return ELV_MQUEUE_MAY;
 }
@@ -728,14 +779,17 @@ void elv_completed_request(struct request_queue *q, struct request *rq)
 {
 	struct elevator_queue *e = q->elevator;
 
+	if (WARN_ON_ONCE(e->uses_mq))
+		return;
+
 	/*
 	 * request is released from the driver, io must be done
 	 */
 	if (blk_account_rq(rq)) {
 		q->in_flight[rq_is_sync(rq)]--;
 		if ((rq->rq_flags & RQF_SORTED) &&
-		    e->type->ops.elevator_completed_req_fn)
-			e->type->ops.elevator_completed_req_fn(q, rq);
+		    e->type->ops.sq.elevator_completed_req_fn)
+			e->type->ops.sq.elevator_completed_req_fn(q, rq);
 	}
 }
 
@@ -803,8 +857,8 @@ int elv_register_queue(struct request_queue *q)
 		}
 		kobject_uevent(&e->kobj, KOBJ_ADD);
 		e->registered = 1;
-		if (e->type->ops.elevator_registered_fn)
-			e->type->ops.elevator_registered_fn(q);
+		if (!e->uses_mq && e->type->ops.sq.elevator_registered_fn)
+			e->type->ops.sq.elevator_registered_fn(q);
 	}
 	return error;
 }
@@ -891,9 +945,14 @@ EXPORT_SYMBOL_GPL(elv_unregister);
 static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 {
 	struct elevator_queue *old = q->elevator;
-	bool registered = old->registered;
+	bool old_registered = false;
 	int err;
 
+	if (q->mq_ops) {
+		blk_mq_freeze_queue(q);
+		blk_mq_quiesce_queue(q);
+	}
+
 	/*
 	 * Turn on BYPASS and drain all requests w/ elevator private data.
 	 * Block layer doesn't call into a quiesced elevator - all requests
@@ -901,42 +960,76 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 	 * using INSERT_BACK.  All requests have SOFTBARRIER set and no
 	 * merge happens either.
 	 */
-	blk_queue_bypass_start(q);
+	if (old) {
+		old_registered = old->registered;
 
-	/* unregister and clear all auxiliary data of the old elevator */
-	if (registered)
-		elv_unregister_queue(q);
+		if (old->uses_mq)
+			blk_mq_sched_teardown(q);
 
-	spin_lock_irq(q->queue_lock);
-	ioc_clear_queue(q);
-	spin_unlock_irq(q->queue_lock);
+		if (!q->mq_ops)
+			blk_queue_bypass_start(q);
+
+		/* unregister and clear all auxiliary data of the old elevator */
+		if (old_registered)
+			elv_unregister_queue(q);
+
+		spin_lock_irq(q->queue_lock);
+		ioc_clear_queue(q);
+		spin_unlock_irq(q->queue_lock);
+	}
 
 	/* allocate, init and register new elevator */
-	err = new_e->ops.elevator_init_fn(q, new_e);
-	if (err)
-		goto fail_init;
+	if (new_e) {
+		if (new_e->uses_mq) {
+			err = blk_mq_sched_setup(q);
+			if (!err)
+				err = new_e->ops.mq.init_sched(q, new_e);
+		} else
+			err = new_e->ops.sq.elevator_init_fn(q, new_e);
+		if (err)
+			goto fail_init;
 
-	if (registered) {
 		err = elv_register_queue(q);
 		if (err)
 			goto fail_register;
-	}
+	} else
+		q->elevator = NULL;
 
 	/* done, kill the old one and finish */
-	elevator_exit(old);
-	blk_queue_bypass_end(q);
+	if (old) {
+		elevator_exit(old);
+		if (!q->mq_ops)
+			blk_queue_bypass_end(q);
+	}
 
-	blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name);
+	if (q->mq_ops) {
+		blk_mq_unfreeze_queue(q);
+		blk_mq_start_stopped_hw_queues(q, true);
+	}
+
+	if (new_e)
+		blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name);
+	else
+		blk_add_trace_msg(q, "elv switch: none");
 
 	return 0;
 
 fail_register:
+	if (q->mq_ops)
+		blk_mq_sched_teardown(q);
 	elevator_exit(q->elevator);
 fail_init:
 	/* switch failed, restore and re-register old elevator */
-	q->elevator = old;
-	elv_register_queue(q);
-	blk_queue_bypass_end(q);
+	if (old) {
+		q->elevator = old;
+		elv_register_queue(q);
+		if (!q->mq_ops)
+			blk_queue_bypass_end(q);
+	}
+	if (q->mq_ops) {
+		blk_mq_unfreeze_queue(q);
+		blk_mq_start_stopped_hw_queues(q, true);
+	}
 
 	return err;
 }
@@ -949,8 +1042,11 @@ static int __elevator_change(struct request_queue *q, const char *name)
 	char elevator_name[ELV_NAME_MAX];
 	struct elevator_type *e;
 
-	if (!q->elevator)
-		return -ENXIO;
+	/*
+	 * Special case for mq, turn off scheduling
+	 */
+	if (q->mq_ops && !strncmp(name, "none", 4))
+		return elevator_switch(q, NULL);
 
 	strlcpy(elevator_name, name, sizeof(elevator_name));
 	e = elevator_get(strstrip(elevator_name), true);
@@ -959,11 +1055,21 @@ static int __elevator_change(struct request_queue *q, const char *name)
 		return -EINVAL;
 	}
 
-	if (!strcmp(elevator_name, q->elevator->type->elevator_name)) {
+	if (q->elevator &&
+	    !strcmp(elevator_name, q->elevator->type->elevator_name)) {
 		elevator_put(e);
 		return 0;
 	}
 
+	if (!e->uses_mq && q->mq_ops) {
+		elevator_put(e);
+		return -EINVAL;
+	}
+	if (e->uses_mq && !q->mq_ops) {
+		elevator_put(e);
+		return -EINVAL;
+	}
+
 	return elevator_switch(q, e);
 }
 
@@ -985,7 +1091,7 @@ ssize_t elv_iosched_store(struct request_queue *q, const char *name,
 {
 	int ret;
 
-	if (!q->elevator)
+	if (!(q->mq_ops || q->request_fn))
 		return count;
 
 	ret = __elevator_change(q, name);
@@ -999,24 +1105,34 @@ ssize_t elv_iosched_store(struct request_queue *q, const char *name,
 ssize_t elv_iosched_show(struct request_queue *q, char *name)
 {
 	struct elevator_queue *e = q->elevator;
-	struct elevator_type *elv;
+	struct elevator_type *elv = NULL;
 	struct elevator_type *__e;
 	int len = 0;
 
-	if (!q->elevator || !blk_queue_stackable(q))
+	if (!blk_queue_stackable(q))
 		return sprintf(name, "none\n");
 
-	elv = e->type;
+	if (!q->elevator)
+		len += sprintf(name+len, "[none] ");
+	else
+		elv = e->type;
 
 	spin_lock(&elv_list_lock);
 	list_for_each_entry(__e, &elv_list, list) {
-		if (!strcmp(elv->elevator_name, __e->elevator_name))
+		if (elv && !strcmp(elv->elevator_name, __e->elevator_name)) {
 			len += sprintf(name+len, "[%s] ", elv->elevator_name);
-		else
+			continue;
+		}
+		if (__e->uses_mq && q->mq_ops)
+			len += sprintf(name+len, "%s ", __e->elevator_name);
+		else if (!__e->uses_mq && !q->mq_ops)
 			len += sprintf(name+len, "%s ", __e->elevator_name);
 	}
 	spin_unlock(&elv_list_lock);
 
+	if (q->mq_ops && q->elevator)
+		len += sprintf(name+len, "none");
+
 	len += sprintf(len+name, "\n");
 	return len;
 }

block/mq-deadline.c

@@ -0,0 +1,555 @@
+/*
+ *  MQ Deadline i/o scheduler - adaptation of the legacy deadline scheduler,
+ *  for the blk-mq scheduling framework
+ *
+ *  Copyright (C) 2016 Jens Axboe <axboe@kernel.dk>
+ */
+#include <linux/kernel.h>
+#include <linux/fs.h>
+#include <linux/blkdev.h>
+#include <linux/blk-mq.h>
+#include <linux/elevator.h>
+#include <linux/bio.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/compiler.h>
+#include <linux/rbtree.h>
+#include <linux/sbitmap.h>
+
+#include "blk.h"
+#include "blk-mq.h"
+#include "blk-mq-tag.h"
+#include "blk-mq-sched.h"
+
+/*
+ * See Documentation/block/deadline-iosched.txt
+ */
+static const int read_expire = HZ / 2;  /* max time before a read is submitted. */
+static const int write_expire = 5 * HZ; /* ditto for writes, these limits are SOFT! */
+static const int writes_starved = 2;    /* max times reads can starve a write */
+static const int fifo_batch = 16;       /* # of sequential requests treated as one
+				     by the above parameters. For throughput. */
+
+struct deadline_data {
+	/*
+	 * run time data
+	 */
+
+	/*
+	 * requests (deadline_rq s) are present on both sort_list and fifo_list
+	 */
+	struct rb_root sort_list[2];
+	struct list_head fifo_list[2];
+
+	/*
+	 * next in sort order. read, write or both are NULL
+	 */
+	struct request *next_rq[2];
+	unsigned int batching;		/* number of sequential requests made */
+	unsigned int starved;		/* times reads have starved writes */
+
+	/*
+	 * settings that change how the i/o scheduler behaves
+	 */
+	int fifo_expire[2];
+	int fifo_batch;
+	int writes_starved;
+	int front_merges;
+
+	spinlock_t lock;
+	struct list_head dispatch;
+};
+
+static inline struct rb_root *
+deadline_rb_root(struct deadline_data *dd, struct request *rq)
+{
+	return &dd->sort_list[rq_data_dir(rq)];
+}
+
+/*
+ * get the request after `rq' in sector-sorted order
+ */
+static inline struct request *
+deadline_latter_request(struct request *rq)
+{
+	struct rb_node *node = rb_next(&rq->rb_node);
+
+	if (node)
+		return rb_entry_rq(node);
+
+	return NULL;
+}
+
+static void
+deadline_add_rq_rb(struct deadline_data *dd, struct request *rq)
+{
+	struct rb_root *root = deadline_rb_root(dd, rq);
+
+	elv_rb_add(root, rq);
+}
+
+static inline void
+deadline_del_rq_rb(struct deadline_data *dd, struct request *rq)
+{
+	const int data_dir = rq_data_dir(rq);
+
+	if (dd->next_rq[data_dir] == rq)
+		dd->next_rq[data_dir] = deadline_latter_request(rq);
+
+	elv_rb_del(deadline_rb_root(dd, rq), rq);
+}
+
+/*
+ * remove rq from rbtree and fifo.
+ */
+static void deadline_remove_request(struct request_queue *q, struct request *rq)
+{
+	struct deadline_data *dd = q->elevator->elevator_data;
+
+	list_del_init(&rq->queuelist);
+
+	/*
+	 * We might not be on the rbtree, if we are doing an insert merge
+	 */
+	if (!RB_EMPTY_NODE(&rq->rb_node))
+		deadline_del_rq_rb(dd, rq);
+
+	elv_rqhash_del(q, rq);
+	if (q->last_merge == rq)
+		q->last_merge = NULL;
+}
+
+static void dd_request_merged(struct request_queue *q, struct request *req,
+			      int type)
+{
+	struct deadline_data *dd = q->elevator->elevator_data;
+
+	/*
+	 * if the merge was a front merge, we need to reposition request
+	 */
+	if (type == ELEVATOR_FRONT_MERGE) {
+		elv_rb_del(deadline_rb_root(dd, req), req);
+		deadline_add_rq_rb(dd, req);
+	}
+}
+
+static void dd_merged_requests(struct request_queue *q, struct request *req,
+			       struct request *next)
+{
+	/*
+	 * if next expires before rq, assign its expire time to rq
+	 * and move into next position (next will be deleted) in fifo
+	 */
+	if (!list_empty(&req->queuelist) && !list_empty(&next->queuelist)) {
+		if (time_before((unsigned long)next->fifo_time,
+				(unsigned long)req->fifo_time)) {
+			list_move(&req->queuelist, &next->queuelist);
+			req->fifo_time = next->fifo_time;
+		}
+	}
+
+	/*
+	 * kill knowledge of next, this one is a goner
+	 */
+	deadline_remove_request(q, next);
+}
+
+/*
+ * move an entry to dispatch queue
+ */
+static void
+deadline_move_request(struct deadline_data *dd, struct request *rq)
+{
+	const int data_dir = rq_data_dir(rq);
+
+	dd->next_rq[READ] = NULL;
+	dd->next_rq[WRITE] = NULL;
+	dd->next_rq[data_dir] = deadline_latter_request(rq);
+
+	/*
+	 * take it off the sort and fifo list
+	 */
+	deadline_remove_request(rq->q, rq);
+}
+
+/*
+ * deadline_check_fifo returns 0 if there are no expired requests on the fifo,
+ * 1 otherwise. Requires !list_empty(&dd->fifo_list[data_dir])
+ */
+static inline int deadline_check_fifo(struct deadline_data *dd, int ddir)
+{
+	struct request *rq = rq_entry_fifo(dd->fifo_list[ddir].next);
+
+	/*
+	 * rq is expired!
+	 */
+	if (time_after_eq(jiffies, (unsigned long)rq->fifo_time))
+		return 1;
+
+	return 0;
+}
+
+/*
+ * deadline_dispatch_requests selects the best request according to
+ * read/write expire, fifo_batch, etc
+ */
+static struct request *__dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
+{
+	struct deadline_data *dd = hctx->queue->elevator->elevator_data;
+	struct request *rq;
+	bool reads, writes;
+	int data_dir;
+
+	if (!list_empty(&dd->dispatch)) {
+		rq = list_first_entry(&dd->dispatch, struct request, queuelist);
+		list_del_init(&rq->queuelist);
+		goto done;
+	}
+
+	reads = !list_empty(&dd->fifo_list[READ]);
+	writes = !list_empty(&dd->fifo_list[WRITE]);
+
+	/*
+	 * batches are currently reads XOR writes
+	 */
+	if (dd->next_rq[WRITE])
+		rq = dd->next_rq[WRITE];
+	else
+		rq = dd->next_rq[READ];
+
+	if (rq && dd->batching < dd->fifo_batch)
+		/* we have a next request are still entitled to batch */
+		goto dispatch_request;
+
+	/*
+	 * at this point we are not running a batch. select the appropriate
+	 * data direction (read / write)
+	 */
+
+	if (reads) {
+		BUG_ON(RB_EMPTY_ROOT(&dd->sort_list[READ]));
+
+		if (writes && (dd->starved++ >= dd->writes_starved))
+			goto dispatch_writes;
+
+		data_dir = READ;
+
+		goto dispatch_find_request;
+	}
+
+	/*
+	 * there are either no reads or writes have been starved
+	 */
+
+	if (writes) {
+dispatch_writes:
+		BUG_ON(RB_EMPTY_ROOT(&dd->sort_list[WRITE]));
+
+		dd->starved = 0;
+
+		data_dir = WRITE;
+
+		goto dispatch_find_request;
+	}
+
+	return NULL;
+
+dispatch_find_request:
+	/*
+	 * we are not running a batch, find best request for selected data_dir
+	 */
+	if (deadline_check_fifo(dd, data_dir) || !dd->next_rq[data_dir]) {
+		/*
+		 * A deadline has expired, the last request was in the other
+		 * direction, or we have run out of higher-sectored requests.
+		 * Start again from the request with the earliest expiry time.
+		 */
+		rq = rq_entry_fifo(dd->fifo_list[data_dir].next);
+	} else {
+		/*
+		 * The last req was the same dir and we have a next request in
+		 * sort order. No expired requests so continue on from here.
+		 */
+		rq = dd->next_rq[data_dir];
+	}
+
+	dd->batching = 0;
+
+dispatch_request:
+	/*
+	 * rq is the selected appropriate request.
+	 */
+	dd->batching++;
+	deadline_move_request(dd, rq);
+done:
+	rq->rq_flags |= RQF_STARTED;
+	return rq;
+}
+
+static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
+{
+	struct deadline_data *dd = hctx->queue->elevator->elevator_data;
+	struct request *rq;
+
+	spin_lock(&dd->lock);
+	rq = __dd_dispatch_request(hctx);
+	spin_unlock(&dd->lock);
+
+	return rq;
+}
+
+static void dd_exit_queue(struct elevator_queue *e)
+{
+	struct deadline_data *dd = e->elevator_data;
+
+	BUG_ON(!list_empty(&dd->fifo_list[READ]));
+	BUG_ON(!list_empty(&dd->fifo_list[WRITE]));
+
+	kfree(dd);
+}
+
+/*
+ * initialize elevator private data (deadline_data).
+ */
+static int dd_init_queue(struct request_queue *q, struct elevator_type *e)
+{
+	struct deadline_data *dd;
+	struct elevator_queue *eq;
+
+	eq = elevator_alloc(q, e);
+	if (!eq)
+		return -ENOMEM;
+
+	dd = kzalloc_node(sizeof(*dd), GFP_KERNEL, q->node);
+	if (!dd) {
+		kobject_put(&eq->kobj);
+		return -ENOMEM;
+	}
+	eq->elevator_data = dd;
+
+	INIT_LIST_HEAD(&dd->fifo_list[READ]);
+	INIT_LIST_HEAD(&dd->fifo_list[WRITE]);
+	dd->sort_list[READ] = RB_ROOT;
+	dd->sort_list[WRITE] = RB_ROOT;
+	dd->fifo_expire[READ] = read_expire;
+	dd->fifo_expire[WRITE] = write_expire;
+	dd->writes_starved = writes_starved;
+	dd->front_merges = 1;
+	dd->fifo_batch = fifo_batch;
+	spin_lock_init(&dd->lock);
+	INIT_LIST_HEAD(&dd->dispatch);
+
+	q->elevator = eq;
+	return 0;
+}
+
+static int dd_request_merge(struct request_queue *q, struct request **rq,
+			    struct bio *bio)
+{
+	struct deadline_data *dd = q->elevator->elevator_data;
+	sector_t sector = bio_end_sector(bio);
+	struct request *__rq;
+
+	if (!dd->front_merges)
+		return ELEVATOR_NO_MERGE;
+
+	__rq = elv_rb_find(&dd->sort_list[bio_data_dir(bio)], sector);
+	if (__rq) {
+		BUG_ON(sector != blk_rq_pos(__rq));
+
+		if (elv_bio_merge_ok(__rq, bio)) {
+			*rq = __rq;
+			return ELEVATOR_FRONT_MERGE;
+		}
+	}
+
+	return ELEVATOR_NO_MERGE;
+}
+
+static bool dd_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio)
+{
+	struct request_queue *q = hctx->queue;
+	struct deadline_data *dd = q->elevator->elevator_data;
+	int ret;
+
+	spin_lock(&dd->lock);
+	ret = blk_mq_sched_try_merge(q, bio);
+	spin_unlock(&dd->lock);
+
+	return ret;
+}
+
+/*
+ * add rq to rbtree and fifo
+ */
+static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
+			      bool at_head)
+{
+	struct request_queue *q = hctx->queue;
+	struct deadline_data *dd = q->elevator->elevator_data;
+	const int data_dir = rq_data_dir(rq);
+
+	if (blk_mq_sched_try_insert_merge(q, rq))
+		return;
+
+	blk_mq_sched_request_inserted(rq);
+
+	if (blk_mq_sched_bypass_insert(hctx, rq))
+		return;
+
+	if (at_head || rq->cmd_type != REQ_TYPE_FS) {
+		if (at_head)
+			list_add(&rq->queuelist, &dd->dispatch);
+		else
+			list_add_tail(&rq->queuelist, &dd->dispatch);
+	} else {
+		deadline_add_rq_rb(dd, rq);
+
+		if (rq_mergeable(rq)) {
+			elv_rqhash_add(q, rq);
+			if (!q->last_merge)
+				q->last_merge = rq;
+		}
+
+		/*
+		 * set expire time and add to fifo list
+		 */
+		rq->fifo_time = jiffies + dd->fifo_expire[data_dir];
+		list_add_tail(&rq->queuelist, &dd->fifo_list[data_dir]);
+	}
+}
+
+static void dd_insert_requests(struct blk_mq_hw_ctx *hctx,
+			       struct list_head *list, bool at_head)
+{
+	struct request_queue *q = hctx->queue;
+	struct deadline_data *dd = q->elevator->elevator_data;
+
+	spin_lock(&dd->lock);
+	while (!list_empty(list)) {
+		struct request *rq;
+
+		rq = list_first_entry(list, struct request, queuelist);
+		list_del_init(&rq->queuelist);
+		dd_insert_request(hctx, rq, at_head);
+	}
+	spin_unlock(&dd->lock);
+}
+
+static bool dd_has_work(struct blk_mq_hw_ctx *hctx)
+{
+	struct deadline_data *dd = hctx->queue->elevator->elevator_data;
+
+	return !list_empty_careful(&dd->dispatch) ||
+		!list_empty_careful(&dd->fifo_list[0]) ||
+		!list_empty_careful(&dd->fifo_list[1]);
+}
+
+/*
+ * sysfs parts below
+ */
+static ssize_t
+deadline_var_show(int var, char *page)
+{
+	return sprintf(page, "%d\n", var);
+}
+
+static ssize_t
+deadline_var_store(int *var, const char *page, size_t count)
+{
+	char *p = (char *) page;
+
+	*var = simple_strtol(p, &p, 10);
+	return count;
+}
+
+#define SHOW_FUNCTION(__FUNC, __VAR, __CONV)				\
+static ssize_t __FUNC(struct elevator_queue *e, char *page)		\
+{									\
+	struct deadline_data *dd = e->elevator_data;			\
+	int __data = __VAR;						\
+	if (__CONV)							\
+		__data = jiffies_to_msecs(__data);			\
+	return deadline_var_show(__data, (page));			\
+}
+SHOW_FUNCTION(deadline_read_expire_show, dd->fifo_expire[READ], 1);
+SHOW_FUNCTION(deadline_write_expire_show, dd->fifo_expire[WRITE], 1);
+SHOW_FUNCTION(deadline_writes_starved_show, dd->writes_starved, 0);
+SHOW_FUNCTION(deadline_front_merges_show, dd->front_merges, 0);
+SHOW_FUNCTION(deadline_fifo_batch_show, dd->fifo_batch, 0);
+#undef SHOW_FUNCTION
+
+#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV)			\
+static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)	\
+{									\
+	struct deadline_data *dd = e->elevator_data;			\
+	int __data;							\
+	int ret = deadline_var_store(&__data, (page), count);		\
+	if (__data < (MIN))						\
+		__data = (MIN);						\
+	else if (__data > (MAX))					\
+		__data = (MAX);						\
+	if (__CONV)							\
+		*(__PTR) = msecs_to_jiffies(__data);			\
+	else								\
+		*(__PTR) = __data;					\
+	return ret;							\
+}
+STORE_FUNCTION(deadline_read_expire_store, &dd->fifo_expire[READ], 0, INT_MAX, 1);
+STORE_FUNCTION(deadline_write_expire_store, &dd->fifo_expire[WRITE], 0, INT_MAX, 1);
+STORE_FUNCTION(deadline_writes_starved_store, &dd->writes_starved, INT_MIN, INT_MAX, 0);
+STORE_FUNCTION(deadline_front_merges_store, &dd->front_merges, 0, 1, 0);
+STORE_FUNCTION(deadline_fifo_batch_store, &dd->fifo_batch, 0, INT_MAX, 0);
+#undef STORE_FUNCTION
+
+#define DD_ATTR(name) \
+	__ATTR(name, S_IRUGO|S_IWUSR, deadline_##name##_show, \
+				      deadline_##name##_store)
+
+static struct elv_fs_entry deadline_attrs[] = {
+	DD_ATTR(read_expire),
+	DD_ATTR(write_expire),
+	DD_ATTR(writes_starved),
+	DD_ATTR(front_merges),
+	DD_ATTR(fifo_batch),
+	__ATTR_NULL
+};
+
+static struct elevator_type mq_deadline = {
+	.ops.mq = {
+		.insert_requests	= dd_insert_requests,
+		.dispatch_request	= dd_dispatch_request,
+		.next_request		= elv_rb_latter_request,
+		.former_request		= elv_rb_former_request,
+		.bio_merge		= dd_bio_merge,
+		.request_merge		= dd_request_merge,
+		.requests_merged	= dd_merged_requests,
+		.request_merged		= dd_request_merged,
+		.has_work		= dd_has_work,
+		.init_sched		= dd_init_queue,
+		.exit_sched		= dd_exit_queue,
+	},
+
+	.uses_mq	= true,
+	.elevator_attrs = deadline_attrs,
+	.elevator_name = "mq-deadline",
+	.elevator_owner = THIS_MODULE,
+};
+
+static int __init deadline_init(void)
+{
+	return elv_register(&mq_deadline);
+}
+
+static void __exit deadline_exit(void)
+{
+	elv_unregister(&mq_deadline);
+}
+
+module_init(deadline_init);
+module_exit(deadline_exit);
+
+MODULE_AUTHOR("Jens Axboe");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("MQ deadline IO scheduler");

block/noop-iosched.c

@@ -92,7 +92,7 @@ static void noop_exit_queue(struct elevator_queue *e)
 }
 
 static struct elevator_type elevator_noop = {
-	.ops = {
+	.ops.sq = {
 		.elevator_merge_req_fn		= noop_merged_requests,
 		.elevator_dispatch_fn		= noop_dispatch,
 		.elevator_add_req_fn		= noop_add_request,

block/partitions/efi.c

@@ -293,7 +293,7 @@ static gpt_entry *alloc_read_gpt_entries(struct parsed_partitions *state,
 	if (!gpt)
 		return NULL;
 
-	count = le32_to_cpu(gpt->num_partition_entries) *
+	count = (size_t)le32_to_cpu(gpt->num_partition_entries) *
                 le32_to_cpu(gpt->sizeof_partition_entry);
 	if (!count)
 		return NULL;
@@ -352,7 +352,7 @@ static int is_gpt_valid(struct parsed_partitions *state, u64 lba,
 			gpt_header **gpt, gpt_entry **ptes)
 {
 	u32 crc, origcrc;
-	u64 lastlba;
+	u64 lastlba, pt_size;
 
 	if (!ptes)
 		return 0;
@@ -434,13 +434,20 @@ static int is_gpt_valid(struct parsed_partitions *state, u64 lba,
 		goto fail;
 	}
 
+	/* Sanity check partition table size */
+	pt_size = (u64)le32_to_cpu((*gpt)->num_partition_entries) *
+		le32_to_cpu((*gpt)->sizeof_partition_entry);
+	if (pt_size > KMALLOC_MAX_SIZE) {
+		pr_debug("GUID Partition Table is too large: %llu > %lu bytes\n",
+			 (unsigned long long)pt_size, KMALLOC_MAX_SIZE);
+		goto fail;
+	}
+
 	if (!(*ptes = alloc_read_gpt_entries(state, *gpt)))
 		goto fail;
 
 	/* Check the GUID Partition Entry Array CRC */
-	crc = efi_crc32((const unsigned char *) (*ptes),
-			le32_to_cpu((*gpt)->num_partition_entries) *
-			le32_to_cpu((*gpt)->sizeof_partition_entry));
+	crc = efi_crc32((const unsigned char *) (*ptes), pt_size);
 
 	if (crc != le32_to_cpu((*gpt)->partition_entry_array_crc32)) {
 		pr_debug("GUID Partition Entry Array CRC check failed.\n");

drivers/block/floppy.c

@@ -3119,7 +3119,7 @@ static int raw_cmd_copyin(int cmd, void __user *param,
 	*rcmd = NULL;
 
 loop:
-	ptr = kmalloc(sizeof(struct floppy_raw_cmd), GFP_USER);
+	ptr = kmalloc(sizeof(struct floppy_raw_cmd), GFP_KERNEL);
 	if (!ptr)
 		return -ENOMEM;
 	*rcmd = ptr;

drivers/md/bcache/request.c

@@ -666,7 +666,7 @@ static inline struct search *search_alloc(struct bio *bio,
 	s->iop.write_prio	= 0;
 	s->iop.error		= 0;
 	s->iop.flags		= 0;
-	s->iop.flush_journal	= (bio->bi_opf & (REQ_PREFLUSH|REQ_FUA)) != 0;
+	s->iop.flush_journal	= op_is_flush(bio->bi_opf);
 	s->iop.wq		= bcache_wq;
 
 	return s;

drivers/md/dm-cache-target.c

@@ -787,8 +787,7 @@ static void check_if_tick_bio_needed(struct cache *cache, struct bio *bio)
 	struct per_bio_data *pb = get_per_bio_data(bio, pb_data_size);
 
 	spin_lock_irqsave(&cache->lock, flags);
-	if (cache->need_tick_bio &&
-	    !(bio->bi_opf & (REQ_FUA | REQ_PREFLUSH)) &&
+	if (cache->need_tick_bio && !op_is_flush(bio->bi_opf) &&
 	    bio_op(bio) != REQ_OP_DISCARD) {
 		pb->tick = true;
 		cache->need_tick_bio = false;
@@ -828,11 +827,6 @@ static dm_oblock_t get_bio_block(struct cache *cache, struct bio *bio)
 	return to_oblock(block_nr);
 }
 
-static int bio_triggers_commit(struct cache *cache, struct bio *bio)
-{
-	return bio->bi_opf & (REQ_PREFLUSH | REQ_FUA);
-}
-
 /*
  * You must increment the deferred set whilst the prison cell is held.  To
  * encourage this, we ask for 'cell' to be passed in.
@@ -884,7 +878,7 @@ static void issue(struct cache *cache, struct bio *bio)
 {
 	unsigned long flags;
 
-	if (!bio_triggers_commit(cache, bio)) {
+	if (!op_is_flush(bio->bi_opf)) {
 		accounted_request(cache, bio);
 		return;
 	}
@@ -1069,8 +1063,7 @@ static void dec_io_migrations(struct cache *cache)
 
 static bool discard_or_flush(struct bio *bio)
 {
-	return bio_op(bio) == REQ_OP_DISCARD ||
-	       bio->bi_opf & (REQ_PREFLUSH | REQ_FUA);
+	return bio_op(bio) == REQ_OP_DISCARD || op_is_flush(bio->bi_opf);
 }
 
 static void __cell_defer(struct cache *cache, struct dm_bio_prison_cell *cell)

drivers/md/dm-thin.c

@@ -699,7 +699,7 @@ static void remap_to_origin(struct thin_c *tc, struct bio *bio)
 
 static int bio_triggers_commit(struct thin_c *tc, struct bio *bio)
 {
-	return (bio->bi_opf & (REQ_PREFLUSH | REQ_FUA)) &&
+	return op_is_flush(bio->bi_opf) &&
 		dm_thin_changed_this_transaction(tc->td);
 }
 
@@ -870,8 +870,7 @@ static void __inc_remap_and_issue_cell(void *context,
 	struct bio *bio;
 
 	while ((bio = bio_list_pop(&cell->bios))) {
-		if (bio->bi_opf & (REQ_PREFLUSH | REQ_FUA) ||
-		    bio_op(bio) == REQ_OP_DISCARD)
+		if (op_is_flush(bio->bi_opf) || bio_op(bio) == REQ_OP_DISCARD)
 			bio_list_add(&info->defer_bios, bio);
 		else {
 			inc_all_io_entry(info->tc->pool, bio);
@@ -1716,9 +1715,8 @@ static void __remap_and_issue_shared_cell(void *context,
 	struct bio *bio;
 
 	while ((bio = bio_list_pop(&cell->bios))) {
-		if ((bio_data_dir(bio) == WRITE) ||
-		    (bio->bi_opf & (REQ_PREFLUSH | REQ_FUA) ||
-		     bio_op(bio) == REQ_OP_DISCARD))
+		if (bio_data_dir(bio) == WRITE || op_is_flush(bio->bi_opf) ||
+		    bio_op(bio) == REQ_OP_DISCARD)
 			bio_list_add(&info->defer_bios, bio);
 		else {
 			struct dm_thin_endio_hook *h = dm_per_bio_data(bio, sizeof(struct dm_thin_endio_hook));;
@@ -2635,8 +2633,7 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio)
 		return DM_MAPIO_SUBMITTED;
 	}
 
-	if (bio->bi_opf & (REQ_PREFLUSH | REQ_FUA) ||
-	    bio_op(bio) == REQ_OP_DISCARD) {
+	if (op_is_flush(bio->bi_opf) || bio_op(bio) == REQ_OP_DISCARD) {
 		thin_defer_bio_with_throttle(tc, bio);
 		return DM_MAPIO_SUBMITTED;
 	}

drivers/nvme/host/pci.c

@@ -1178,6 +1178,7 @@ static int nvme_alloc_admin_tags(struct nvme_dev *dev)
 		dev->admin_tagset.timeout = ADMIN_TIMEOUT;
 		dev->admin_tagset.numa_node = dev_to_node(dev->dev);
 		dev->admin_tagset.cmd_size = nvme_cmd_size(dev);
+		dev->admin_tagset.flags = BLK_MQ_F_NO_SCHED;
 		dev->admin_tagset.driver_data = dev;
 
 		if (blk_mq_alloc_tag_set(&dev->admin_tagset))

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;
 
@@ -60,7 +62,7 @@ struct blk_mq_hw_ctx {
 
 struct blk_mq_tag_set {
 	unsigned int		*mq_map;
-	struct blk_mq_ops	*ops;
+	const struct blk_mq_ops	*ops;
 	unsigned int		nr_hw_queues;
 	unsigned int		queue_depth;	/* max hw supported */
 	unsigned int		reserved_tags;
@@ -151,11 +153,13 @@ enum {
 	BLK_MQ_F_SG_MERGE	= 1 << 2,
 	BLK_MQ_F_DEFER_ISSUE	= 1 << 4,
 	BLK_MQ_F_BLOCKING	= 1 << 5,
+	BLK_MQ_F_NO_SCHED	= 1 << 6,
 	BLK_MQ_F_ALLOC_POLICY_START_BIT = 8,
 	BLK_MQ_F_ALLOC_POLICY_BITS = 1,
 
 	BLK_MQ_S_STOPPED	= 0,
 	BLK_MQ_S_TAG_ACTIVE	= 1,
+	BLK_MQ_S_SCHED_RESTART	= 2,
 
 	BLK_MQ_MAX_DEPTH	= 10240,
 
@@ -179,14 +183,13 @@ 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);
-void blk_mq_free_hctx_request(struct blk_mq_hw_ctx *, 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/blk_types.h

@@ -220,6 +220,15 @@ static inline bool op_is_write(unsigned int op)
 	return (op & 1);
 }
 
+/*
+ * Check if the bio or request is one that needs special treatment in the
+ * flush state machine.
+ */
+static inline bool op_is_flush(unsigned int op)
+{
+	return op & (REQ_FUA | REQ_PREFLUSH);
+}
+
 /*
  * Reads are always treated as synchronous, as are requests with the FUA or
  * PREFLUSH flag.  Other operations may be marked as synchronous using the
@@ -232,22 +241,29 @@ static inline bool op_is_sync(unsigned int op)
 }
 
 typedef unsigned int blk_qc_t;
-#define BLK_QC_T_NONE	-1U
-#define BLK_QC_T_SHIFT	16
+#define BLK_QC_T_NONE		-1U
+#define BLK_QC_T_SHIFT		16
+#define BLK_QC_T_INTERNAL	(1U << 31)
 
 static inline bool blk_qc_t_valid(blk_qc_t cookie)
 {
 	return cookie != BLK_QC_T_NONE;
 }
 
-static inline blk_qc_t blk_tag_to_qc_t(unsigned int tag, unsigned int queue_num)
+static inline blk_qc_t blk_tag_to_qc_t(unsigned int tag, unsigned int queue_num,
+				       bool internal)
 {
-	return tag | (queue_num << BLK_QC_T_SHIFT);
+	blk_qc_t ret = tag | (queue_num << BLK_QC_T_SHIFT);
+
+	if (internal)
+		ret |= BLK_QC_T_INTERNAL;
+
+	return ret;
 }
 
 static inline unsigned int blk_qc_t_to_queue_num(blk_qc_t cookie)
 {
-	return cookie >> BLK_QC_T_SHIFT;
+	return (cookie & ~BLK_QC_T_INTERNAL) >> BLK_QC_T_SHIFT;
 }
 
 static inline unsigned int blk_qc_t_to_tag(blk_qc_t cookie)
@@ -255,6 +271,11 @@ static inline unsigned int blk_qc_t_to_tag(blk_qc_t cookie)
 	return cookie & ((1u << BLK_QC_T_SHIFT) - 1);
 }
 
+static inline bool blk_qc_t_is_internal(blk_qc_t cookie)
+{
+	return (cookie & BLK_QC_T_INTERNAL) != 0;
+}
+
 struct blk_issue_stat {
 	u64 time;
 };

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;
 
 	/*
@@ -407,7 +409,7 @@ struct request_queue {
 	dma_drain_needed_fn	*dma_drain_needed;
 	lld_busy_fn		*lld_busy_fn;
 
-	struct blk_mq_ops	*mq_ops;
+	const struct blk_mq_ops	*mq_ops;
 
 	unsigned int		*mq_map;
 
@@ -569,6 +571,11 @@ struct request_queue {
 	struct list_head	tag_set_list;
 	struct bio_set		*bio_split;
 
+#ifdef CONFIG_DEBUG_FS
+	struct dentry		*debugfs_dir;
+	struct dentry		*mq_debugfs_dir;
+#endif
+
 	bool			mq_sysfs_init_done;
 };
 
@@ -600,6 +607,7 @@ struct request_queue {
 #define QUEUE_FLAG_FLUSH_NQ    25	/* flush not queueuable */
 #define QUEUE_FLAG_DAX         26	/* device supports DAX */
 #define QUEUE_FLAG_STATS       27	/* track rq completion times */
+#define QUEUE_FLAG_RESTART     28	/* queue needs restart at completion */
 
 #define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_STACKABLE)	|	\
@@ -1620,6 +1628,25 @@ static inline bool bvec_gap_to_prev(struct request_queue *q,
 	return __bvec_gap_to_prev(q, bprv, offset);
 }
 
+/*
+ * Check if the two bvecs from two bios can be merged to one segment.
+ * If yes, no need to check gap between the two bios since the 1st bio
+ * and the 1st bvec in the 2nd bio can be handled in one segment.
+ */
+static inline bool bios_segs_mergeable(struct request_queue *q,
+		struct bio *prev, struct bio_vec *prev_last_bv,
+		struct bio_vec *next_first_bv)
+{
+	if (!BIOVEC_PHYS_MERGEABLE(prev_last_bv, next_first_bv))
+		return false;
+	if (!BIOVEC_SEG_BOUNDARY(q, prev_last_bv, next_first_bv))
+		return false;
+	if (prev->bi_seg_back_size + next_first_bv->bv_len >
+			queue_max_segment_size(q))
+		return false;
+	return true;
+}
+
 static inline bool bio_will_gap(struct request_queue *q, struct bio *prev,
 			 struct bio *next)
 {
@@ -1629,7 +1656,8 @@ static inline bool bio_will_gap(struct request_queue *q, struct bio *prev,
 		bio_get_last_bvec(prev, &pb);
 		bio_get_first_bvec(next, &nb);
 
-		return __bvec_gap_to_prev(q, &pb, nb.bv_offset);
+		if (!bios_segs_mergeable(q, prev, &pb, &nb))
+			return __bvec_gap_to_prev(q, &pb, nb.bv_offset);
 	}
 
 	return false;

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);
+	struct request *(*dispatch_request)(struct blk_mq_hw_ctx *);
+	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 {
@@ -94,12 +122,16 @@ struct elevator_type
 	struct kmem_cache *icq_cache;
 
 	/* fields provided by elevator implementation */
-	struct elevator_ops ops;
+	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" */
@@ -123,6 +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);
 };
 
@@ -139,6 +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 *);

include/linux/sbitmap.h

@@ -258,6 +258,26 @@ static inline int sbitmap_test_bit(struct sbitmap *sb, unsigned int bitnr)
 
 unsigned int sbitmap_weight(const struct sbitmap *sb);
 
+/**
+ * sbitmap_show() - Dump &struct sbitmap information to a &struct seq_file.
+ * @sb: Bitmap to show.
+ * @m: struct seq_file to write to.
+ *
+ * This is intended for debugging. The format may change at any time.
+ */
+void sbitmap_show(struct sbitmap *sb, struct seq_file *m);
+
+/**
+ * sbitmap_bitmap_show() - Write a hex dump of a &struct sbitmap to a &struct
+ * seq_file.
+ * @sb: Bitmap to show.
+ * @m: struct seq_file to write to.
+ *
+ * This is intended for debugging. The output isn't guaranteed to be internally
+ * consistent.
+ */
+void sbitmap_bitmap_show(struct sbitmap *sb, struct seq_file *m);
+
 /**
  * sbitmap_queue_init_node() - Initialize a &struct sbitmap_queue on a specific
  * memory node.
@@ -370,4 +390,14 @@ static inline struct sbq_wait_state *sbq_wait_ptr(struct sbitmap_queue *sbq,
  */
 void sbitmap_queue_wake_all(struct sbitmap_queue *sbq);
 
+/**
+ * sbitmap_queue_show() - Dump &struct sbitmap_queue information to a &struct
+ * seq_file.
+ * @sbq: Bitmap queue to show.
+ * @m: struct seq_file to write to.
+ *
+ * This is intended for debugging. The format may change at any time.
+ */
+void sbitmap_queue_show(struct sbitmap_queue *sbq, struct seq_file *m);
+
 #endif /* __LINUX_SCALE_BITMAP_H */

lib/sbitmap.c

@@ -17,6 +17,7 @@
 
 #include <linux/random.h>
 #include <linux/sbitmap.h>
+#include <linux/seq_file.h>
 
 int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift,
 		      gfp_t flags, int node)
@@ -180,6 +181,62 @@ unsigned int sbitmap_weight(const struct sbitmap *sb)
 }
 EXPORT_SYMBOL_GPL(sbitmap_weight);
 
+void sbitmap_show(struct sbitmap *sb, struct seq_file *m)
+{
+	seq_printf(m, "depth=%u\n", sb->depth);
+	seq_printf(m, "busy=%u\n", sbitmap_weight(sb));
+	seq_printf(m, "bits_per_word=%u\n", 1U << sb->shift);
+	seq_printf(m, "map_nr=%u\n", sb->map_nr);
+}
+EXPORT_SYMBOL_GPL(sbitmap_show);
+
+static inline void emit_byte(struct seq_file *m, unsigned int offset, u8 byte)
+{
+	if ((offset & 0xf) == 0) {
+		if (offset != 0)
+			seq_putc(m, '\n');
+		seq_printf(m, "%08x:", offset);
+	}
+	if ((offset & 0x1) == 0)
+		seq_putc(m, ' ');
+	seq_printf(m, "%02x", byte);
+}
+
+void sbitmap_bitmap_show(struct sbitmap *sb, struct seq_file *m)
+{
+	u8 byte = 0;
+	unsigned int byte_bits = 0;
+	unsigned int offset = 0;
+	int i;
+
+	for (i = 0; i < sb->map_nr; i++) {
+		unsigned long word = READ_ONCE(sb->map[i].word);
+		unsigned int word_bits = READ_ONCE(sb->map[i].depth);
+
+		while (word_bits > 0) {
+			unsigned int bits = min(8 - byte_bits, word_bits);
+
+			byte |= (word & (BIT(bits) - 1)) << byte_bits;
+			byte_bits += bits;
+			if (byte_bits == 8) {
+				emit_byte(m, offset, byte);
+				byte = 0;
+				byte_bits = 0;
+				offset++;
+			}
+			word >>= bits;
+			word_bits -= bits;
+		}
+	}
+	if (byte_bits) {
+		emit_byte(m, offset, byte);
+		offset++;
+	}
+	if (offset)
+		seq_putc(m, '\n');
+}
+EXPORT_SYMBOL_GPL(sbitmap_bitmap_show);
+
 static unsigned int sbq_calc_wake_batch(unsigned int depth)
 {
 	unsigned int wake_batch;
@@ -239,7 +296,19 @@ EXPORT_SYMBOL_GPL(sbitmap_queue_init_node);
 
 void sbitmap_queue_resize(struct sbitmap_queue *sbq, unsigned int depth)
 {
-	sbq->wake_batch = sbq_calc_wake_batch(depth);
+	unsigned int wake_batch = sbq_calc_wake_batch(depth);
+	int i;
+
+	if (sbq->wake_batch != wake_batch) {
+		WRITE_ONCE(sbq->wake_batch, wake_batch);
+		/*
+		 * Pairs with the memory barrier in sbq_wake_up() to ensure that
+		 * the batch size is updated before the wait counts.
+		 */
+		smp_mb__before_atomic();
+		for (i = 0; i < SBQ_WAIT_QUEUES; i++)
+			atomic_set(&sbq->ws[i].wait_cnt, 1);
+	}
 	sbitmap_resize(&sbq->sb, depth);
 }
 EXPORT_SYMBOL_GPL(sbitmap_queue_resize);
@@ -297,20 +366,39 @@ static struct sbq_wait_state *sbq_wake_ptr(struct sbitmap_queue *sbq)
 static void sbq_wake_up(struct sbitmap_queue *sbq)
 {
 	struct sbq_wait_state *ws;
+	unsigned int wake_batch;
 	int wait_cnt;
 
-	/* Ensure that the wait list checks occur after clear_bit(). */
-	smp_mb();
+	/*
+	 * Pairs with the memory barrier in set_current_state() to ensure the
+	 * proper ordering of clear_bit()/waitqueue_active() in the waker and
+	 * test_and_set_bit()/prepare_to_wait()/finish_wait() in the waiter. See
+	 * the comment on waitqueue_active(). This is __after_atomic because we
+	 * just did clear_bit() in the caller.
+	 */
+	smp_mb__after_atomic();
 
 	ws = sbq_wake_ptr(sbq);
 	if (!ws)
 		return;
 
 	wait_cnt = atomic_dec_return(&ws->wait_cnt);
-	if (unlikely(wait_cnt < 0))
-		wait_cnt = atomic_inc_return(&ws->wait_cnt);
-	if (wait_cnt == 0) {
-		atomic_add(sbq->wake_batch, &ws->wait_cnt);
+	if (wait_cnt <= 0) {
+		wake_batch = READ_ONCE(sbq->wake_batch);
+		/*
+		 * Pairs with the memory barrier in sbitmap_queue_resize() to
+		 * ensure that we see the batch size update before the wait
+		 * count is reset.
+		 */
+		smp_mb__before_atomic();
+		/*
+		 * If there are concurrent callers to sbq_wake_up(), the last
+		 * one to decrement the wait count below zero will bump it back
+		 * up. If there is a concurrent resize, the count reset will
+		 * either cause the cmpxchg to fail or overwrite after the
+		 * cmpxchg.
+		 */
+		atomic_cmpxchg(&ws->wait_cnt, wait_cnt, wait_cnt + wake_batch);
 		sbq_index_atomic_inc(&sbq->wake_index);
 		wake_up(&ws->wait);
 	}
@@ -331,7 +419,8 @@ void sbitmap_queue_wake_all(struct sbitmap_queue *sbq)
 	int i, wake_index;
 
 	/*
-	 * Make sure all changes prior to this are visible from other CPUs.
+	 * Pairs with the memory barrier in set_current_state() like in
+	 * sbq_wake_up().
 	 */
 	smp_mb();
 	wake_index = atomic_read(&sbq->wake_index);
@@ -345,3 +434,37 @@ void sbitmap_queue_wake_all(struct sbitmap_queue *sbq)
 	}
 }
 EXPORT_SYMBOL_GPL(sbitmap_queue_wake_all);
+
+void sbitmap_queue_show(struct sbitmap_queue *sbq, struct seq_file *m)
+{
+	bool first;
+	int i;
+
+	sbitmap_show(&sbq->sb, m);
+
+	seq_puts(m, "alloc_hint={");
+	first = true;
+	for_each_possible_cpu(i) {
+		if (!first)
+			seq_puts(m, ", ");
+		first = false;
+		seq_printf(m, "%u", *per_cpu_ptr(sbq->alloc_hint, i));
+	}
+	seq_puts(m, "}\n");
+
+	seq_printf(m, "wake_batch=%u\n", sbq->wake_batch);
+	seq_printf(m, "wake_index=%d\n", atomic_read(&sbq->wake_index));
+
+	seq_puts(m, "ws={\n");
+	for (i = 0; i < SBQ_WAIT_QUEUES; i++) {
+		struct sbq_wait_state *ws = &sbq->ws[i];
+
+		seq_printf(m, "\t{.wait_cnt=%d, .wait=%s},\n",
+			   atomic_read(&ws->wait_cnt),
+			   waitqueue_active(&ws->wait) ? "active" : "inactive");
+	}
+	seq_puts(m, "}\n");
+
+	seq_printf(m, "round_robin=%d\n", sbq->round_robin);
+}
+EXPORT_SYMBOL_GPL(sbitmap_queue_show);