dm: move request-based code out to dm-rq.[hc]

Add some seperation between bio-based and request-based DM core code.

'struct mapped_device' and other DM core only structures and functions
have been moved to dm-core.h and all relevant DM core .c files have been
updated to include dm-core.h rather than dm.h

DM targets should _never_ include dm-core.h!

[block core merge conflict resolution from Stephen Rothwell]
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>

15 files changed, 1200 insertions, 1131 deletions

diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index 52ba8dd82821..3cbda1af87a0 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -3,7 +3,8 @@
 #
 
 dm-mod-y	+= dm.o dm-table.o dm-target.o dm-linear.o dm-stripe.o \
-		   dm-ioctl.o dm-io.o dm-kcopyd.o dm-sysfs.o dm-stats.o
+		   dm-ioctl.o dm-io.o dm-kcopyd.o dm-sysfs.o dm-stats.o \
+		   dm-rq.o
 dm-multipath-y	+= dm-path-selector.o dm-mpath.o
 dm-snapshot-y	+= dm-snap.o dm-exception-store.o dm-snap-transient.o \
 		    dm-snap-persistent.o
diff --git a/drivers/md/dm-builtin.c b/drivers/md/dm-builtin.c
index 6c9049c51b2b..f092771878c2 100644
--- a/drivers/md/dm-builtin.c
+++ b/drivers/md/dm-builtin.c
@@ -1,4 +1,4 @@
-#include "dm.h"
+#include "dm-core.h"
 
 /*
  * The kobject release method must not be placed in the module itself,
diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h
new file mode 100644
index 000000000000..40ceba1fe8be
--- /dev/null
+++ b/drivers/md/dm-core.h
@@ -0,0 +1,149 @@
+/*
+ * Internal header file _only_ for device mapper core
+ *
+ * Copyright (C) 2016 Red Hat, Inc. All rights reserved.
+ *
+ * This file is released under the LGPL.
+ */
+
+#ifndef DM_CORE_INTERNAL_H
+#define DM_CORE_INTERNAL_H
+
+#include <linux/kthread.h>
+#include <linux/ktime.h>
+#include <linux/blk-mq.h>
+
+#include <trace/events/block.h>
+
+#include "dm.h"
+
+#define DM_RESERVED_MAX_IOS		1024
+
+struct dm_kobject_holder {
+	struct kobject kobj;
+	struct completion completion;
+};
+
+/*
+ * DM core internal structure that used directly by dm.c and dm-rq.c
+ * DM targets must _not_ deference a mapped_device to directly access its members!
+ */
+struct mapped_device {
+	struct srcu_struct io_barrier;
+	struct mutex suspend_lock;
+
+	/*
+	 * The current mapping (struct dm_table *).
+	 * Use dm_get_live_table{_fast} or take suspend_lock for
+	 * dereference.
+	 */
+	void __rcu *map;
+
+	struct list_head table_devices;
+	struct mutex table_devices_lock;
+
+	unsigned long flags;
+
+	struct request_queue *queue;
+	int numa_node_id;
+
+	unsigned type;
+	/* Protect queue and type against concurrent access. */
+	struct mutex type_lock;
+
+	atomic_t holders;
+	atomic_t open_count;
+
+	struct dm_target *immutable_target;
+	struct target_type *immutable_target_type;
+
+	struct gendisk *disk;
+	char name[16];
+
+	void *interface_ptr;
+
+	/*
+	 * A list of ios that arrived while we were suspended.
+	 */
+	atomic_t pending[2];
+	wait_queue_head_t wait;
+	struct work_struct work;
+	spinlock_t deferred_lock;
+	struct bio_list deferred;
+
+	/*
+	 * Event handling.
+	 */
+	wait_queue_head_t eventq;
+	atomic_t event_nr;
+	atomic_t uevent_seq;
+	struct list_head uevent_list;
+	spinlock_t uevent_lock; /* Protect access to uevent_list */
+
+	/* the number of internal suspends */
+	unsigned internal_suspend_count;
+
+	/*
+	 * Processing queue (flush)
+	 */
+	struct workqueue_struct *wq;
+
+	/*
+	 * io objects are allocated from here.
+	 */
+	mempool_t *io_pool;
+	mempool_t *rq_pool;
+
+	struct bio_set *bs;
+
+	/*
+	 * freeze/thaw support require holding onto a super block
+	 */
+	struct super_block *frozen_sb;
+
+	/* forced geometry settings */
+	struct hd_geometry geometry;
+
+	struct block_device *bdev;
+
+	/* kobject and completion */
+	struct dm_kobject_holder kobj_holder;
+
+	/* zero-length flush that will be cloned and submitted to targets */
+	struct bio flush_bio;
+
+	struct dm_stats stats;
+
+	struct kthread_worker kworker;
+	struct task_struct *kworker_task;
+
+	/* for request-based merge heuristic in dm_request_fn() */
+	unsigned seq_rq_merge_deadline_usecs;
+	int last_rq_rw;
+	sector_t last_rq_pos;
+	ktime_t last_rq_start_time;
+
+	/* for blk-mq request-based DM support */
+	struct blk_mq_tag_set *tag_set;
+	bool use_blk_mq:1;
+	bool init_tio_pdu:1;
+};
+
+void dm_init_md_queue(struct mapped_device *md);
+void dm_init_normal_md_queue(struct mapped_device *md);
+int md_in_flight(struct mapped_device *md);
+void disable_write_same(struct mapped_device *md);
+
+static inline struct completion *dm_get_completion_from_kobject(struct kobject *kobj)
+{
+	return &container_of(kobj, struct dm_kobject_holder, kobj)->completion;
+}
+
+unsigned __dm_get_module_param(unsigned *module_param, unsigned def, unsigned max);
+
+static inline bool dm_message_test_buffer_overflow(char *result, unsigned maxlen)
+{
+	return !maxlen || strlen(result) + 1 >= maxlen;
+}
+
+#endif
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index 0e225fd4a8d1..daa03e41654a 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -5,7 +5,7 @@
  * This file is released under the GPL.
  */
 
-#include "dm.h"
+#include "dm-core.h"
 
 #include <linux/device-mapper.h>
 
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 2c7ca258c4e4..b59e34595ad8 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -5,7 +5,7 @@
  * This file is released under the GPL.
  */
 
-#include "dm.h"
+#include "dm-core.h"
 
 #include <linux/module.h>
 #include <linux/vmalloc.h>
diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c
index 9da1d54ac6cb..9e9d04cb7d51 100644
--- a/drivers/md/dm-kcopyd.c
+++ b/drivers/md/dm-kcopyd.c
@@ -26,7 +26,7 @@
 #include <linux/device-mapper.h>
 #include <linux/dm-kcopyd.h>
 
-#include "dm.h"
+#include "dm-core.h"
 
 #define SUB_JOB_SIZE	128
 #define SPLIT_COUNT	8
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 52baf8a5b0f4..e1c07d1ec80b 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -7,7 +7,7 @@
 
 #include <linux/device-mapper.h>
 
-#include "dm.h"
+#include "dm-rq.h"
 #include "dm-path-selector.h"
 #include "dm-uevent.h"
 
@@ -1328,7 +1328,7 @@ static int do_end_io(struct multipath *m, struct request *clone,
 	 * during end I/O handling, since those clone requests don't have
 	 * bio clones.  If we queue them inside the multipath target,
 	 * we need to make bio clones, that requires memory allocation.
-	 * (See drivers/md/dm.c:end_clone_bio() about why the clone requests
+	 * (See drivers/md/dm-rq.c:end_clone_bio() about why the clone requests
 	 *  don't have bio clones.)
 	 * Instead of queueing the clone request here, we queue the original
 	 * request into dm core, which will remake a clone request and
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
new file mode 100644
index 000000000000..787c81b16a26
--- /dev/null
+++ b/drivers/md/dm-rq.c
@@ -0,0 +1,959 @@
+/*
+ * Copyright (C) 2016 Red Hat, Inc. All rights reserved.
+ *
+ * This file is released under the GPL.
+ */
+
+#include "dm-core.h"
+#include "dm-rq.h"
+
+#include <linux/elevator.h> /* for rq_end_sector() */
+#include <linux/blk-mq.h>
+
+#define DM_MSG_PREFIX "core-rq"
+
+#define DM_MQ_NR_HW_QUEUES 1
+#define DM_MQ_QUEUE_DEPTH 2048
+static unsigned dm_mq_nr_hw_queues = DM_MQ_NR_HW_QUEUES;
+static unsigned dm_mq_queue_depth = DM_MQ_QUEUE_DEPTH;
+
+/*
+ * Request-based DM's mempools' reserved IOs set by the user.
+ */
+#define RESERVED_REQUEST_BASED_IOS	256
+static unsigned reserved_rq_based_ios = RESERVED_REQUEST_BASED_IOS;
+
+#ifdef CONFIG_DM_MQ_DEFAULT
+static bool use_blk_mq = true;
+#else
+static bool use_blk_mq = false;
+#endif
+
+bool dm_use_blk_mq_default(void)
+{
+	return use_blk_mq;
+}
+
+bool dm_use_blk_mq(struct mapped_device *md)
+{
+	return md->use_blk_mq;
+}
+EXPORT_SYMBOL_GPL(dm_use_blk_mq);
+
+unsigned dm_get_reserved_rq_based_ios(void)
+{
+	return __dm_get_module_param(&reserved_rq_based_ios,
+				     RESERVED_REQUEST_BASED_IOS, DM_RESERVED_MAX_IOS);
+}
+EXPORT_SYMBOL_GPL(dm_get_reserved_rq_based_ios);
+
+static unsigned dm_get_blk_mq_nr_hw_queues(void)
+{
+	return __dm_get_module_param(&dm_mq_nr_hw_queues, 1, 32);
+}
+
+static unsigned dm_get_blk_mq_queue_depth(void)
+{
+	return __dm_get_module_param(&dm_mq_queue_depth,
+				     DM_MQ_QUEUE_DEPTH, BLK_MQ_MAX_DEPTH);
+}
+
+int dm_request_based(struct mapped_device *md)
+{
+	return blk_queue_stackable(md->queue);
+}
+
+static void dm_old_start_queue(struct request_queue *q)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+	if (blk_queue_stopped(q))
+		blk_start_queue(q);
+	spin_unlock_irqrestore(q->queue_lock, flags);
+}
+
+void dm_start_queue(struct request_queue *q)
+{
+	if (!q->mq_ops)
+		dm_old_start_queue(q);
+	else {
+		blk_mq_start_stopped_hw_queues(q, true);
+		blk_mq_kick_requeue_list(q);
+	}
+}
+
+static void dm_old_stop_queue(struct request_queue *q)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+	if (blk_queue_stopped(q)) {
+		spin_unlock_irqrestore(q->queue_lock, flags);
+		return;
+	}
+
+	blk_stop_queue(q);
+	spin_unlock_irqrestore(q->queue_lock, flags);
+}
+
+void dm_stop_queue(struct request_queue *q)
+{
+	if (!q->mq_ops)
+		dm_old_stop_queue(q);
+	else
+		blk_mq_stop_hw_queues(q);
+}
+
+static struct dm_rq_target_io *alloc_old_rq_tio(struct mapped_device *md,
+						gfp_t gfp_mask)
+{
+	return mempool_alloc(md->io_pool, gfp_mask);
+}
+
+static void free_old_rq_tio(struct dm_rq_target_io *tio)
+{
+	mempool_free(tio, tio->md->io_pool);
+}
+
+static struct request *alloc_old_clone_request(struct mapped_device *md,
+					       gfp_t gfp_mask)
+{
+	return mempool_alloc(md->rq_pool, gfp_mask);
+}
+
+static void free_old_clone_request(struct mapped_device *md, struct request *rq)
+{
+	mempool_free(rq, md->rq_pool);
+}
+
+/*
+ * Partial completion handling for request-based dm
+ */
+static void end_clone_bio(struct bio *clone)
+{
+	struct dm_rq_clone_bio_info *info =
+		container_of(clone, struct dm_rq_clone_bio_info, clone);
+	struct dm_rq_target_io *tio = info->tio;
+	struct bio *bio = info->orig;
+	unsigned int nr_bytes = info->orig->bi_iter.bi_size;
+	int error = clone->bi_error;
+
+	bio_put(clone);
+
+	if (tio->error)
+		/*
+		 * An error has already been detected on the request.
+		 * Once error occurred, just let clone->end_io() handle
+		 * the remainder.
+		 */
+		return;
+	else if (error) {
+		/*
+		 * Don't notice the error to the upper layer yet.
+		 * The error handling decision is made by the target driver,
+		 * when the request is completed.
+		 */
+		tio->error = error;
+		return;
+	}
+
+	/*
+	 * I/O for the bio successfully completed.
+	 * Notice the data completion to the upper layer.
+	 */
+
+	/*
+	 * bios are processed from the head of the list.
+	 * So the completing bio should always be rq->bio.
+	 * If it's not, something wrong is happening.
+	 */
+	if (tio->orig->bio != bio)
+		DMERR("bio completion is going in the middle of the request");
+
+	/*
+	 * Update the original request.
+	 * Do not use blk_end_request() here, because it may complete
+	 * the original request before the clone, and break the ordering.
+	 */
+	blk_update_request(tio->orig, 0, nr_bytes);
+}
+
+static struct dm_rq_target_io *tio_from_request(struct request *rq)
+{
+	return (rq->q->mq_ops ? blk_mq_rq_to_pdu(rq) : rq->special);
+}
+
+static void rq_end_stats(struct mapped_device *md, struct request *orig)
+{
+	if (unlikely(dm_stats_used(&md->stats))) {
+		struct dm_rq_target_io *tio = tio_from_request(orig);
+		tio->duration_jiffies = jiffies - tio->duration_jiffies;
+		dm_stats_account_io(&md->stats, rq_data_dir(orig),
+				    blk_rq_pos(orig), tio->n_sectors, true,
+				    tio->duration_jiffies, &tio->stats_aux);
+	}
+}
+
+/*
+ * Don't touch any member of the md after calling this function because
+ * the md may be freed in dm_put() at the end of this function.
+ * Or do dm_get() before calling this function and dm_put() later.
+ */
+static void rq_completed(struct mapped_device *md, int rw, bool run_queue)
+{
+	atomic_dec(&md->pending[rw]);
+
+	/* nudge anyone waiting on suspend queue */
+	if (!md_in_flight(md))
+		wake_up(&md->wait);
+
+	/*
+	 * Run this off this callpath, as drivers could invoke end_io while
+	 * inside their request_fn (and holding the queue lock). Calling
+	 * back into ->request_fn() could deadlock attempting to grab the
+	 * queue lock again.
+	 */
+	if (!md->queue->mq_ops && run_queue)
+		blk_run_queue_async(md->queue);
+
+	/*
+	 * dm_put() must be at the end of this function. See the comment above
+	 */
+	dm_put(md);
+}
+
+static void free_rq_clone(struct request *clone)
+{
+	struct dm_rq_target_io *tio = clone->end_io_data;
+	struct mapped_device *md = tio->md;
+
+	blk_rq_unprep_clone(clone);
+
+	if (md->type == DM_TYPE_MQ_REQUEST_BASED)
+		/* stacked on blk-mq queue(s) */
+		tio->ti->type->release_clone_rq(clone);
+	else if (!md->queue->mq_ops)
+		/* request_fn queue stacked on request_fn queue(s) */
+		free_old_clone_request(md, clone);
+
+	if (!md->queue->mq_ops)
+		free_old_rq_tio(tio);
+}
+
+/*
+ * Complete the clone and the original request.
+ * Must be called without clone's queue lock held,
+ * see end_clone_request() for more details.
+ */
+static void dm_end_request(struct request *clone, int error)
+{
+	int rw = rq_data_dir(clone);
+	struct dm_rq_target_io *tio = clone->end_io_data;
+	struct mapped_device *md = tio->md;
+	struct request *rq = tio->orig;
+
+	if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
+		rq->errors = clone->errors;
+		rq->resid_len = clone->resid_len;
+
+		if (rq->sense)
+			/*
+			 * We are using the sense buffer of the original
+			 * request.
+			 * So setting the length of the sense data is enough.
+			 */
+			rq->sense_len = clone->sense_len;
+	}
+
+	free_rq_clone(clone);
+	rq_end_stats(md, rq);
+	if (!rq->q->mq_ops)
+		blk_end_request_all(rq, error);
+	else
+		blk_mq_end_request(rq, error);
+	rq_completed(md, rw, true);
+}
+
+static void dm_unprep_request(struct request *rq)
+{
+	struct dm_rq_target_io *tio = tio_from_request(rq);
+	struct request *clone = tio->clone;
+
+	if (!rq->q->mq_ops) {
+		rq->special = NULL;
+		rq->cmd_flags &= ~REQ_DONTPREP;
+	}
+
+	if (clone)
+		free_rq_clone(clone);
+	else if (!tio->md->queue->mq_ops)
+		free_old_rq_tio(tio);
+}
+
+/*
+ * Requeue the original request of a clone.
+ */
+static void dm_old_requeue_request(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+	unsigned long flags;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+	blk_requeue_request(q, rq);
+	blk_run_queue_async(q);
+	spin_unlock_irqrestore(q->queue_lock, flags);
+}
+
+static void dm_mq_requeue_request(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+	unsigned long flags;
+
+	blk_mq_requeue_request(rq);
+	spin_lock_irqsave(q->queue_lock, flags);
+	if (!blk_queue_stopped(q))
+		blk_mq_kick_requeue_list(q);
+	spin_unlock_irqrestore(q->queue_lock, flags);
+}
+
+static void dm_requeue_original_request(struct mapped_device *md,
+					struct request *rq)
+{
+	int rw = rq_data_dir(rq);
+
+	rq_end_stats(md, rq);
+	dm_unprep_request(rq);
+
+	if (!rq->q->mq_ops)
+		dm_old_requeue_request(rq);
+	else
+		dm_mq_requeue_request(rq);
+
+	rq_completed(md, rw, false);
+}
+
+static void dm_done(struct request *clone, int error, bool mapped)
+{
+	int r = error;
+	struct dm_rq_target_io *tio = clone->end_io_data;
+	dm_request_endio_fn rq_end_io = NULL;
+
+	if (tio->ti) {
+		rq_end_io = tio->ti->type->rq_end_io;
+
+		if (mapped && rq_end_io)
+			r = rq_end_io(tio->ti, clone, error, &tio->info);
+	}
+
+	if (unlikely(r == -EREMOTEIO && (req_op(clone) == REQ_OP_WRITE_SAME) &&
+		     !clone->q->limits.max_write_same_sectors))
+		disable_write_same(tio->md);
+
+	if (r <= 0)
+		/* The target wants to complete the I/O */
+		dm_end_request(clone, r);
+	else if (r == DM_ENDIO_INCOMPLETE)
+		/* The target will handle the I/O */
+		return;
+	else if (r == DM_ENDIO_REQUEUE)
+		/* The target wants to requeue the I/O */
+		dm_requeue_original_request(tio->md, tio->orig);
+	else {
+		DMWARN("unimplemented target endio return value: %d", r);
+		BUG();
+	}
+}
+
+/*
+ * Request completion handler for request-based dm
+ */
+static void dm_softirq_done(struct request *rq)
+{
+	bool mapped = true;
+	struct dm_rq_target_io *tio = tio_from_request(rq);
+	struct request *clone = tio->clone;
+	int rw;
+
+	if (!clone) {
+		rq_end_stats(tio->md, rq);
+		rw = rq_data_dir(rq);
+		if (!rq->q->mq_ops) {
+			blk_end_request_all(rq, tio->error);
+			rq_completed(tio->md, rw, false);
+			free_old_rq_tio(tio);
+		} else {
+			blk_mq_end_request(rq, tio->error);
+			rq_completed(tio->md, rw, false);
+		}
+		return;
+	}
+
+	if (rq->cmd_flags & REQ_FAILED)
+		mapped = false;
+
+	dm_done(clone, tio->error, mapped);
+}
+
+/*
+ * Complete the clone and the original request with the error status
+ * through softirq context.
+ */
+static void dm_complete_request(struct request *rq, int error)
+{
+	struct dm_rq_target_io *tio = tio_from_request(rq);
+
+	tio->error = error;
+	if (!rq->q->mq_ops)
+		blk_complete_request(rq);
+	else
+		blk_mq_complete_request(rq, error);
+}
+
+/*
+ * Complete the not-mapped clone and the original request with the error status
+ * through softirq context.
+ * Target's rq_end_io() function isn't called.
+ * This may be used when the target's map_rq() or clone_and_map_rq() functions fail.
+ */
+static void dm_kill_unmapped_request(struct request *rq, int error)
+{
+	rq->cmd_flags |= REQ_FAILED;
+	dm_complete_request(rq, error);
+}
+
+/*
+ * Called with the clone's queue lock held (in the case of .request_fn)
+ */
+static void end_clone_request(struct request *clone, int error)
+{
+	struct dm_rq_target_io *tio = clone->end_io_data;
+
+	if (!clone->q->mq_ops) {
+		/*
+		 * For just cleaning up the information of the queue in which
+		 * the clone was dispatched.
+		 * The clone is *NOT* freed actually here because it is alloced
+		 * from dm own mempool (REQ_ALLOCED isn't set).
+		 */
+		__blk_put_request(clone->q, clone);
+	}
+
+	/*
+	 * Actual request completion is done in a softirq context which doesn't
+	 * hold the clone's queue lock.  Otherwise, deadlock could occur because:
+	 *     - another request may be submitted by the upper level driver
+	 *       of the stacking during the completion
+	 *     - the submission which requires queue lock may be done
+	 *       against this clone's queue
+	 */
+	dm_complete_request(tio->orig, error);
+}
+
+static void dm_dispatch_clone_request(struct request *clone, struct request *rq)
+{
+	int r;
+
+	if (blk_queue_io_stat(clone->q))
+		clone->cmd_flags |= REQ_IO_STAT;
+
+	clone->start_time = jiffies;
+	r = blk_insert_cloned_request(clone->q, clone);
+	if (r)
+		/* must complete clone in terms of original request */
+		dm_complete_request(rq, r);
+}
+
+static int dm_rq_bio_constructor(struct bio *bio, struct bio *bio_orig,
+				 void *data)
+{
+	struct dm_rq_target_io *tio = data;
+	struct dm_rq_clone_bio_info *info =
+		container_of(bio, struct dm_rq_clone_bio_info, clone);
+
+	info->orig = bio_orig;
+	info->tio = tio;
+	bio->bi_end_io = end_clone_bio;
+
+	return 0;
+}
+
+static int setup_clone(struct request *clone, struct request *rq,
+		       struct dm_rq_target_io *tio, gfp_t gfp_mask)
+{
+	int r;
+
+	r = blk_rq_prep_clone(clone, rq, tio->md->bs, gfp_mask,
+			      dm_rq_bio_constructor, tio);
+	if (r)
+		return r;
+
+	clone->cmd = rq->cmd;
+	clone->cmd_len = rq->cmd_len;
+	clone->sense = rq->sense;
+	clone->end_io = end_clone_request;
+	clone->end_io_data = tio;
+
+	tio->clone = clone;
+
+	return 0;
+}
+
+static struct request *clone_old_rq(struct request *rq, struct mapped_device *md,
+				    struct dm_rq_target_io *tio, gfp_t gfp_mask)
+{
+	/*
+	 * Create clone for use with .request_fn request_queue
+	 */
+	struct request *clone;
+
+	clone = alloc_old_clone_request(md, gfp_mask);
+	if (!clone)
+		return NULL;
+
+	blk_rq_init(NULL, clone);
+	if (setup_clone(clone, rq, tio, gfp_mask)) {
+		/* -ENOMEM */
+		free_old_clone_request(md, clone);
+		return NULL;
+	}
+
+	return clone;
+}
+
+static void map_tio_request(struct kthread_work *work);
+
+static void init_tio(struct dm_rq_target_io *tio, struct request *rq,
+		     struct mapped_device *md)
+{
+	tio->md = md;
+	tio->ti = NULL;
+	tio->clone = NULL;
+	tio->orig = rq;
+	tio->error = 0;
+	/*
+	 * Avoid initializing info for blk-mq; it passes
+	 * target-specific data through info.ptr
+	 * (see: dm_mq_init_request)
+	 */
+	if (!md->init_tio_pdu)
+		memset(&tio->info, 0, sizeof(tio->info));
+	if (md->kworker_task)
+		init_kthread_work(&tio->work, map_tio_request);
+}
+
+static struct dm_rq_target_io *dm_old_prep_tio(struct request *rq,
+					       struct mapped_device *md,
+					       gfp_t gfp_mask)
+{
+	struct dm_rq_target_io *tio;
+	int srcu_idx;
+	struct dm_table *table;
+
+	tio = alloc_old_rq_tio(md, gfp_mask);
+	if (!tio)
+		return NULL;
+
+	init_tio(tio, rq, md);
+
+	table = dm_get_live_table(md, &srcu_idx);
+	/*
+	 * Must clone a request if this .request_fn DM device
+	 * is stacked on .request_fn device(s).
+	 */
+	if (!dm_table_mq_request_based(table)) {
+		if (!clone_old_rq(rq, md, tio, gfp_mask)) {
+			dm_put_live_table(md, srcu_idx);
+			free_old_rq_tio(tio);
+			return NULL;
+		}
+	}
+	dm_put_live_table(md, srcu_idx);
+
+	return tio;
+}
+
+/*
+ * Called with the queue lock held.
+ */
+static int dm_old_prep_fn(struct request_queue *q, struct request *rq)
+{
+	struct mapped_device *md = q->queuedata;
+	struct dm_rq_target_io *tio;
+
+	if (unlikely(rq->special)) {
+		DMWARN("Already has something in rq->special.");
+		return BLKPREP_KILL;
+	}
+
+	tio = dm_old_prep_tio(rq, md, GFP_ATOMIC);
+	if (!tio)
+		return BLKPREP_DEFER;
+
+	rq->special = tio;
+	rq->cmd_flags |= REQ_DONTPREP;
+
+	return BLKPREP_OK;
+}
+
+/*
+ * Returns:
+ * 0                : the request has been processed
+ * DM_MAPIO_REQUEUE : the original request needs to be requeued
+ * < 0              : the request was completed due to failure
+ */
+static int map_request(struct dm_rq_target_io *tio, struct request *rq,
+		       struct mapped_device *md)
+{
+	int r;
+	struct dm_target *ti = tio->ti;
+	struct request *clone = NULL;
+
+	if (tio->clone) {
+		clone = tio->clone;
+		r = ti->type->map_rq(ti, clone, &tio->info);
+	} else {
+		r = ti->type->clone_and_map_rq(ti, rq, &tio->info, &clone);
+		if (r < 0) {
+			/* The target wants to complete the I/O */
+			dm_kill_unmapped_request(rq, r);
+			return r;
+		}
+		if (r != DM_MAPIO_REMAPPED)
+			return r;
+		if (setup_clone(clone, rq, tio, GFP_ATOMIC)) {
+			/* -ENOMEM */
+			ti->type->release_clone_rq(clone);
+			return DM_MAPIO_REQUEUE;
+		}
+	}
+
+	switch (r) {
+	case DM_MAPIO_SUBMITTED:
+		/* The target has taken the I/O to submit by itself later */
+		break;
+	case DM_MAPIO_REMAPPED:
+		/* The target has remapped the I/O so dispatch it */
+		trace_block_rq_remap(clone->q, clone, disk_devt(dm_disk(md)),
+				     blk_rq_pos(rq));
+		dm_dispatch_clone_request(clone, rq);
+		break;
+	case DM_MAPIO_REQUEUE:
+		/* The target wants to requeue the I/O */
+		dm_requeue_original_request(md, tio->orig);
+		break;
+	default:
+		if (r > 0) {
+			DMWARN("unimplemented target map return value: %d", r);
+			BUG();
+		}
+
+		/* The target wants to complete the I/O */
+		dm_kill_unmapped_request(rq, r);
+		return r;
+	}
+
+	return 0;
+}
+
+static void dm_start_request(struct mapped_device *md, struct request *orig)
+{
+	if (!orig->q->mq_ops)
+		blk_start_request(orig);
+	else
+		blk_mq_start_request(orig);
+	atomic_inc(&md->pending[rq_data_dir(orig)]);
+
+	if (md->seq_rq_merge_deadline_usecs) {
+		md->last_rq_pos = rq_end_sector(orig);
+		md->last_rq_rw = rq_data_dir(orig);
+		md->last_rq_start_time = ktime_get();
+	}
+
+	if (unlikely(dm_stats_used(&md->stats))) {
+		struct dm_rq_target_io *tio = tio_from_request(orig);
+		tio->duration_jiffies = jiffies;
+		tio->n_sectors = blk_rq_sectors(orig);
+		dm_stats_account_io(&md->stats, rq_data_dir(orig),
+				    blk_rq_pos(orig), tio->n_sectors, false, 0,
+				    &tio->stats_aux);
+	}
+
+	/*
+	 * Hold the md reference here for the in-flight I/O.
+	 * We can't rely on the reference count by device opener,
+	 * because the device may be closed during the request completion
+	 * when all bios are completed.
+	 * See the comment in rq_completed() too.
+	 */
+	dm_get(md);
+}
+
+static void map_tio_request(struct kthread_work *work)
+{
+	struct dm_rq_target_io *tio = container_of(work, struct dm_rq_target_io, work);
+	struct request *rq = tio->orig;
+	struct mapped_device *md = tio->md;
+
+	if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE)
+		dm_requeue_original_request(md, rq);
+}
+
+ssize_t dm_attr_rq_based_seq_io_merge_deadline_show(struct mapped_device *md, char *buf)
+{
+	return sprintf(buf, "%u\n", md->seq_rq_merge_deadline_usecs);
+}
+
+#define MAX_SEQ_RQ_MERGE_DEADLINE_USECS 100000
+
+ssize_t dm_attr_rq_based_seq_io_merge_deadline_store(struct mapped_device *md,
+						     const char *buf, size_t count)
+{
+	unsigned deadline;
+
+	if (!dm_request_based(md) || md->use_blk_mq)
+		return count;
+
+	if (kstrtouint(buf, 10, &deadline))
+		return -EINVAL;
+
+	if (deadline > MAX_SEQ_RQ_MERGE_DEADLINE_USECS)
+		deadline = MAX_SEQ_RQ_MERGE_DEADLINE_USECS;
+
+	md->seq_rq_merge_deadline_usecs = deadline;
+
+	return count;
+}
+
+static bool dm_old_request_peeked_before_merge_deadline(struct mapped_device *md)
+{
+	ktime_t kt_deadline;
+
+	if (!md->seq_rq_merge_deadline_usecs)
+		return false;
+
+	kt_deadline = ns_to_ktime((u64)md->seq_rq_merge_deadline_usecs * NSEC_PER_USEC);
+	kt_deadline = ktime_add_safe(md->last_rq_start_time, kt_deadline);
+
+	return !ktime_after(ktime_get(), kt_deadline);
+}
+
+/*
+ * q->request_fn for old request-based dm.
+ * Called with the queue lock held.
+ */
+static void dm_old_request_fn(struct request_queue *q)
+{
+	struct mapped_device *md = q->queuedata;
+	struct dm_target *ti = md->immutable_target;
+	struct request *rq;
+	struct dm_rq_target_io *tio;
+	sector_t pos = 0;
+
+	if (unlikely(!ti)) {
+		int srcu_idx;
+		struct dm_table *map = dm_get_live_table(md, &srcu_idx);
+
+		ti = dm_table_find_target(map, pos);
+		dm_put_live_table(md, srcu_idx);
+	}
+
+	/*
+	 * For suspend, check blk_queue_stopped() and increment
+	 * ->pending within a single queue_lock not to increment the
+	 * number of in-flight I/Os after the queue is stopped in
+	 * dm_suspend().
+	 */
+	while (!blk_queue_stopped(q)) {
+		rq = blk_peek_request(q);
+		if (!rq)
+			return;
+
+		/* always use block 0 to find the target for flushes for now */
+		pos = 0;
+		if (req_op(rq) != REQ_OP_FLUSH)
+			pos = blk_rq_pos(rq);
+
+		if ((dm_old_request_peeked_before_merge_deadline(md) &&
+		     md_in_flight(md) && rq->bio && rq->bio->bi_vcnt == 1 &&
+		     md->last_rq_pos == pos && md->last_rq_rw == rq_data_dir(rq)) ||
+		    (ti->type->busy && ti->type->busy(ti))) {
+			blk_delay_queue(q, HZ / 100);
+			return;
+		}
+
+		dm_start_request(md, rq);
+
+		tio = tio_from_request(rq);
+		/* Establish tio->ti before queuing work (map_tio_request) */
+		tio->ti = ti;
+		queue_kthread_work(&md->kworker, &tio->work);
+		BUG_ON(!irqs_disabled());
+	}
+}
+
+/*
+ * Fully initialize a .request_fn request-based queue.
+ */
+int dm_old_init_request_queue(struct mapped_device *md)
+{
+	/* Fully initialize the queue */
+	if (!blk_init_allocated_queue(md->queue, dm_old_request_fn, NULL))
+		return -EINVAL;
+
+	/* disable dm_old_request_fn's merge heuristic by default */
+	md->seq_rq_merge_deadline_usecs = 0;
+
+	dm_init_normal_md_queue(md);
+	blk_queue_softirq_done(md->queue, dm_softirq_done);
+	blk_queue_prep_rq(md->queue, dm_old_prep_fn);
+
+	/* Initialize the request-based DM worker thread */
+	init_kthread_worker(&md->kworker);
+	md->kworker_task = kthread_run(kthread_worker_fn, &md->kworker,
+				       "kdmwork-%s", dm_device_name(md));
+
+	elv_register_queue(md->queue);
+
+	return 0;
+}
+
+static int dm_mq_init_request(void *data, struct request *rq,
+		       unsigned int hctx_idx, unsigned int request_idx,
+		       unsigned int numa_node)
+{
+	struct mapped_device *md = data;
+	struct dm_rq_target_io *tio = blk_mq_rq_to_pdu(rq);
+
+	/*
+	 * Must initialize md member of tio, otherwise it won't
+	 * be available in dm_mq_queue_rq.
+	 */
+	tio->md = md;
+
+	if (md->init_tio_pdu) {
+		/* target-specific per-io data is immediately after the tio */
+		tio->info.ptr = tio + 1;
+	}
+
+	return 0;
+}
+
+static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
+			  const struct blk_mq_queue_data *bd)
+{
+	struct request *rq = bd->rq;
+	struct dm_rq_target_io *tio = blk_mq_rq_to_pdu(rq);
+	struct mapped_device *md = tio->md;
+	struct dm_target *ti = md->immutable_target;
+
+	if (unlikely(!ti)) {
+		int srcu_idx;
+		struct dm_table *map = dm_get_live_table(md, &srcu_idx);
+
+		ti = dm_table_find_target(map, 0);
+		dm_put_live_table(md, srcu_idx);
+	}
+
+	if (ti->type->busy && ti->type->busy(ti))
+		return BLK_MQ_RQ_QUEUE_BUSY;
+
+	dm_start_request(md, rq);
+
+	/* Init tio using md established in .init_request */
+	init_tio(tio, rq, md);
+
+	/*
+	 * Establish tio->ti before calling map_request().
+	 */
+	tio->ti = ti;
+
+	/* Direct call is fine since .queue_rq allows allocations */
+	if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE) {
+		/* Undo dm_start_request() before requeuing */
+		rq_end_stats(md, rq);
+		rq_completed(md, rq_data_dir(rq), false);
+		return BLK_MQ_RQ_QUEUE_BUSY;
+	}
+
+	return BLK_MQ_RQ_QUEUE_OK;
+}
+
+static struct blk_mq_ops dm_mq_ops = {
+	.queue_rq = dm_mq_queue_rq,
+	.map_queue = blk_mq_map_queue,
+	.complete = dm_softirq_done,
+	.init_request = dm_mq_init_request,
+};
+
+int dm_mq_init_request_queue(struct mapped_device *md, struct dm_target *immutable_tgt)
+{
+	struct request_queue *q;
+	int err;
+
+	if (dm_get_md_type(md) == DM_TYPE_REQUEST_BASED) {
+		DMERR("request-based dm-mq may only be stacked on blk-mq device(s)");
+		return -EINVAL;
+	}
+
+	md->tag_set = kzalloc_node(sizeof(struct blk_mq_tag_set), GFP_KERNEL, md->numa_node_id);
+	if (!md->tag_set)
+		return -ENOMEM;
+
+	md->tag_set->ops = &dm_mq_ops;
+	md->tag_set->queue_depth = dm_get_blk_mq_queue_depth();
+	md->tag_set->numa_node = md->numa_node_id;
+	md->tag_set->flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
+	md->tag_set->nr_hw_queues = dm_get_blk_mq_nr_hw_queues();
+	md->tag_set->driver_data = md;
+
+	md->tag_set->cmd_size = sizeof(struct dm_rq_target_io);
+	if (immutable_tgt && immutable_tgt->per_io_data_size) {
+		/* any target-specific per-io data is immediately after the tio */
+		md->tag_set->cmd_size += immutable_tgt->per_io_data_size;
+		md->init_tio_pdu = true;
+	}
+
+	err = blk_mq_alloc_tag_set(md->tag_set);
+	if (err)
+		goto out_kfree_tag_set;
+
+	q = blk_mq_init_allocated_queue(md->tag_set, md->queue);
+	if (IS_ERR(q)) {
+		err = PTR_ERR(q);
+		goto out_tag_set;
+	}
+	dm_init_md_queue(md);
+
+	/* backfill 'mq' sysfs registration normally done in blk_register_queue */
+	blk_mq_register_disk(md->disk);
+
+	return 0;
+
+out_tag_set:
+	blk_mq_free_tag_set(md->tag_set);
+out_kfree_tag_set:
+	kfree(md->tag_set);
+
+	return err;
+}
+
+void dm_mq_cleanup_mapped_device(struct mapped_device *md)
+{
+	if (md->tag_set) {
+		blk_mq_free_tag_set(md->tag_set);
+		kfree(md->tag_set);
+	}
+}
+
+module_param(reserved_rq_based_ios, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(reserved_rq_based_ios, "Reserved IOs in request-based mempools");
+
+module_param(use_blk_mq, bool, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(use_blk_mq, "Use block multiqueue for request-based DM devices");
+
+module_param(dm_mq_nr_hw_queues, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(dm_mq_nr_hw_queues, "Number of hardware queues for request-based dm-mq devices");
+
+module_param(dm_mq_queue_depth, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(dm_mq_queue_depth, "Queue depth for request-based dm-mq devices");
diff --git a/drivers/md/dm-rq.h b/drivers/md/dm-rq.h
new file mode 100644
index 000000000000..1559f6486024
--- /dev/null
+++ b/drivers/md/dm-rq.h
@@ -0,0 +1,64 @@
+/*
+ * Internal header file for device mapper
+ *
+ * Copyright (C) 2016 Red Hat, Inc. All rights reserved.
+ *
+ * This file is released under the LGPL.
+ */
+
+#ifndef DM_RQ_INTERNAL_H
+#define DM_RQ_INTERNAL_H
+
+#include <linux/bio.h>
+#include <linux/kthread.h>
+
+#include "dm-stats.h"
+
+struct mapped_device;
+
+/*
+ * One of these is allocated per request.
+ */
+struct dm_rq_target_io {
+	struct mapped_device *md;
+	struct dm_target *ti;
+	struct request *orig, *clone;
+	struct kthread_work work;
+	int error;
+	union map_info info;
+	struct dm_stats_aux stats_aux;
+	unsigned long duration_jiffies;
+	unsigned n_sectors;
+};
+
+/*
+ * For request-based dm - the bio clones we allocate are embedded in these
+ * structs.
+ *
+ * We allocate these with bio_alloc_bioset, using the front_pad parameter when
+ * the bioset is created - this means the bio has to come at the end of the
+ * struct.
+ */
+struct dm_rq_clone_bio_info {
+	struct bio *orig;
+	struct dm_rq_target_io *tio;
+	struct bio clone;
+};
+
+bool dm_use_blk_mq_default(void);
+bool dm_use_blk_mq(struct mapped_device *md);
+
+int dm_old_init_request_queue(struct mapped_device *md);
+int dm_mq_init_request_queue(struct mapped_device *md, struct dm_target *immutable_tgt);
+void dm_mq_cleanup_mapped_device(struct mapped_device *md);
+
+void dm_start_queue(struct request_queue *q);
+void dm_stop_queue(struct request_queue *q);
+
+unsigned dm_get_reserved_rq_based_ios(void);
+
+ssize_t dm_attr_rq_based_seq_io_merge_deadline_show(struct mapped_device *md, char *buf);
+ssize_t dm_attr_rq_based_seq_io_merge_deadline_store(struct mapped_device *md,
+						     const char *buf, size_t count);
+
+#endif
diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c
index 4fba26cd6bdb..38b05f23b96c 100644
--- a/drivers/md/dm-stats.c
+++ b/drivers/md/dm-stats.c
@@ -10,7 +10,7 @@
 #include <linux/module.h>
 #include <linux/device-mapper.h>
 
-#include "dm.h"
+#include "dm-core.h"
 #include "dm-stats.h"
 
 #define DM_MSG_PREFIX "stats"
diff --git a/drivers/md/dm-sysfs.c b/drivers/md/dm-sysfs.c
index 7e818f5f1dc4..c209b8a19b84 100644
--- a/drivers/md/dm-sysfs.c
+++ b/drivers/md/dm-sysfs.c
@@ -6,7 +6,8 @@
 
 #include <linux/sysfs.h>
 #include <linux/dm-ioctl.h>
-#include "dm.h"
+#include "dm-core.h"
+#include "dm-rq.h"
 
 struct dm_sysfs_attr {
 	struct attribute attr;
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 626a5ec04466..a682d51111dd 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -5,7 +5,7 @@
  * This file is released under the GPL.
  */
 
-#include "dm.h"
+#include "dm-core.h"
 
 #include <linux/module.h>
 #include <linux/vmalloc.h>
diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c
index a317dd884ba6..5c826b450aad 100644
--- a/drivers/md/dm-target.c
+++ b/drivers/md/dm-target.c
@@ -4,7 +4,7 @@
  * This file is released under the GPL.
  */
 
-#include "dm.h"
+#include "dm-core.h"
 
 #include <linux/module.h>
 #include <linux/init.h>
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index aba7ed9abb3a..8f22527134e9 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -5,13 +5,13 @@
  * This file is released under the GPL.
  */
 
-#include "dm.h"
+#include "dm-core.h"
+#include "dm-rq.h"
 #include "dm-uevent.h"
 
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
-#include <linux/moduleparam.h>
 #include <linux/blkpg.h>
 #include <linux/bio.h>
 #include <linux/mempool.h>
@@ -20,14 +20,8 @@
 #include <linux/hdreg.h>
 #include <linux/delay.h>
 #include <linux/wait.h>
-#include <linux/kthread.h>
-#include <linux/ktime.h>
-#include <linux/elevator.h> /* for rq_end_sector() */
-#include <linux/blk-mq.h>
 #include <linux/pr.h>
 
-#include <trace/events/block.h>
-
 #define DM_MSG_PREFIX "core"
 
 #ifdef CONFIG_PRINTK
@@ -63,7 +57,6 @@ static DECLARE_WORK(deferred_remove_work, do_deferred_remove);
 static struct workqueue_struct *deferred_remove_workqueue;
 
 /*
- * For bio-based dm.
  * One of these is allocated per bio.
  */
 struct dm_io {
@@ -76,36 +69,6 @@ struct dm_io {
 	struct dm_stats_aux stats_aux;
 };
 
-/*
- * For request-based dm.
- * One of these is allocated per request.
- */
-struct dm_rq_target_io {
-	struct mapped_device *md;
-	struct dm_target *ti;
-	struct request *orig, *clone;
-	struct kthread_work work;
-	int error;
-	union map_info info;
-	struct dm_stats_aux stats_aux;
-	unsigned long duration_jiffies;
-	unsigned n_sectors;
-};
-
-/*
- * For request-based dm - the bio clones we allocate are embedded in these
- * structs.
- *
- * We allocate these with bio_alloc_bioset, using the front_pad parameter when
- * the bioset is created - this means the bio has to come at the end of the
- * struct.
- */
-struct dm_rq_clone_bio_info {
-	struct bio *orig;
-	struct dm_rq_target_io *tio;
-	struct bio clone;
-};
-
 #define MINOR_ALLOCED ((void *)-1)
 
 /*
@@ -120,130 +83,9 @@ struct dm_rq_clone_bio_info {
 #define DMF_DEFERRED_REMOVE 6
 #define DMF_SUSPENDED_INTERNALLY 7
 
-/*
- * Work processed by per-device workqueue.
- */
-struct mapped_device {
-	struct srcu_struct io_barrier;
-	struct mutex suspend_lock;
-
-	/*
-	 * The current mapping (struct dm_table *).
-	 * Use dm_get_live_table{_fast} or take suspend_lock for
-	 * dereference.
-	 */
-	void __rcu *map;
-
-	struct list_head table_devices;
-	struct mutex table_devices_lock;
-
-	unsigned long flags;
-
-	struct request_queue *queue;
-	int numa_node_id;
-
-	unsigned type;
-	/* Protect queue and type against concurrent access. */
-	struct mutex type_lock;
-
-	atomic_t holders;
-	atomic_t open_count;
-
-	struct dm_target *immutable_target;
-	struct target_type *immutable_target_type;
-
-	struct gendisk *disk;
-	char name[16];
-
-	void *interface_ptr;
-
-	/*
-	 * A list of ios that arrived while we were suspended.
-	 */
-	atomic_t pending[2];
-	wait_queue_head_t wait;
-	struct work_struct work;
-	spinlock_t deferred_lock;
-	struct bio_list deferred;
-
-	/*
-	 * Event handling.
-	 */
-	wait_queue_head_t eventq;
-	atomic_t event_nr;
-	atomic_t uevent_seq;
-	struct list_head uevent_list;
-	spinlock_t uevent_lock; /* Protect access to uevent_list */
-
-	/* the number of internal suspends */
-	unsigned internal_suspend_count;
-
-	/*
-	 * Processing queue (flush)
-	 */
-	struct workqueue_struct *wq;
-
-	/*
-	 * io objects are allocated from here.
-	 */
-	mempool_t *io_pool;
-	mempool_t *rq_pool;
-
-	struct bio_set *bs;
-
-	/*
-	 * freeze/thaw support require holding onto a super block
-	 */
-	struct super_block *frozen_sb;
-
-	/* forced geometry settings */
-	struct hd_geometry geometry;
-
-	struct block_device *bdev;
-
-	/* kobject and completion */
-	struct dm_kobject_holder kobj_holder;
-
-	/* zero-length flush that will be cloned and submitted to targets */
-	struct bio flush_bio;
-
-	struct dm_stats stats;
-
-	struct kthread_worker kworker;
-	struct task_struct *kworker_task;
-
-	/* for request-based merge heuristic in dm_request_fn() */
-	unsigned seq_rq_merge_deadline_usecs;
-	int last_rq_rw;
-	sector_t last_rq_pos;
-	ktime_t last_rq_start_time;
-
-	/* for blk-mq request-based DM support */
-	struct blk_mq_tag_set *tag_set;
-	bool use_blk_mq:1;
-	bool init_tio_pdu:1;
-};
-
-#ifdef CONFIG_DM_MQ_DEFAULT
-static bool use_blk_mq = true;
-#else
-static bool use_blk_mq = false;
-#endif
-
-#define DM_MQ_NR_HW_QUEUES 1
-#define DM_MQ_QUEUE_DEPTH 2048
 #define DM_NUMA_NODE NUMA_NO_NODE
-
-static unsigned dm_mq_nr_hw_queues = DM_MQ_NR_HW_QUEUES;
-static unsigned dm_mq_queue_depth = DM_MQ_QUEUE_DEPTH;
 static int dm_numa_node = DM_NUMA_NODE;
 
-bool dm_use_blk_mq(struct mapped_device *md)
-{
-	return md->use_blk_mq;
-}
-EXPORT_SYMBOL_GPL(dm_use_blk_mq);
-
 /*
  * For mempools pre-allocation at the table loading time.
  */
@@ -259,9 +101,6 @@ struct table_device {
 	struct dm_dev dm_dev;
 };
 
-#define RESERVED_BIO_BASED_IOS		16
-#define RESERVED_REQUEST_BASED_IOS	256
-#define RESERVED_MAX_IOS		1024
 static struct kmem_cache *_io_cache;
 static struct kmem_cache *_rq_tio_cache;
 static struct kmem_cache *_rq_cache;
@@ -269,13 +108,9 @@ static struct kmem_cache *_rq_cache;
 /*
  * Bio-based DM's mempools' reserved IOs set by the user.
  */
+#define RESERVED_BIO_BASED_IOS		16
 static unsigned reserved_bio_based_ios = RESERVED_BIO_BASED_IOS;
 
-/*
- * Request-based DM's mempools' reserved IOs set by the user.
- */
-static unsigned reserved_rq_based_ios = RESERVED_REQUEST_BASED_IOS;
-
 static int __dm_get_module_param_int(int *module_param, int min, int max)
 {
 	int param = ACCESS_ONCE(*module_param);
@@ -297,8 +132,8 @@ static int __dm_get_module_param_int(int *module_param, int min, int max)
 	return param;
 }
 
-static unsigned __dm_get_module_param(unsigned *module_param,
-				      unsigned def, unsigned max)
+unsigned __dm_get_module_param(unsigned *module_param,
+			       unsigned def, unsigned max)
 {
 	unsigned param = ACCESS_ONCE(*module_param);
 	unsigned modified_param = 0;
@@ -319,28 +154,10 @@ static unsigned __dm_get_module_param(unsigned *module_param,
 unsigned dm_get_reserved_bio_based_ios(void)
 {
 	return __dm_get_module_param(&reserved_bio_based_ios,
-				     RESERVED_BIO_BASED_IOS, RESERVED_MAX_IOS);
+				     RESERVED_BIO_BASED_IOS, DM_RESERVED_MAX_IOS);
 }
 EXPORT_SYMBOL_GPL(dm_get_reserved_bio_based_ios);
 
-unsigned dm_get_reserved_rq_based_ios(void)
-{
-	return __dm_get_module_param(&reserved_rq_based_ios,
-				     RESERVED_REQUEST_BASED_IOS, RESERVED_MAX_IOS);
-}
-EXPORT_SYMBOL_GPL(dm_get_reserved_rq_based_ios);
-
-static unsigned dm_get_blk_mq_nr_hw_queues(void)
-{
-	return __dm_get_module_param(&dm_mq_nr_hw_queues, 1, 32);
-}
-
-static unsigned dm_get_blk_mq_queue_depth(void)
-{
-	return __dm_get_module_param(&dm_mq_queue_depth,
-				     DM_MQ_QUEUE_DEPTH, BLK_MQ_MAX_DEPTH);
-}
-
 static unsigned dm_get_numa_node(void)
 {
 	return __dm_get_module_param_int(&dm_numa_node,
@@ -679,29 +496,7 @@ static void free_tio(struct dm_target_io *tio)
 	bio_put(&tio->clone);
 }
 
-static struct dm_rq_target_io *alloc_old_rq_tio(struct mapped_device *md,
-						gfp_t gfp_mask)
-{
-	return mempool_alloc(md->io_pool, gfp_mask);
-}
-
-static void free_old_rq_tio(struct dm_rq_target_io *tio)
-{
-	mempool_free(tio, tio->md->io_pool);
-}
-
-static struct request *alloc_old_clone_request(struct mapped_device *md,
-					       gfp_t gfp_mask)
-{
-	return mempool_alloc(md->rq_pool, gfp_mask);
-}
-
-static void free_old_clone_request(struct mapped_device *md, struct request *rq)
-{
-	mempool_free(rq, md->rq_pool);
-}
-
-static int md_in_flight(struct mapped_device *md)
+int md_in_flight(struct mapped_device *md)
 {
 	return atomic_read(&md->pending[READ]) +
 	       atomic_read(&md->pending[WRITE]);
@@ -1019,7 +814,7 @@ static void dec_pending(struct dm_io *io, int error)
 	}
 }
 
-static void disable_write_same(struct mapped_device *md)
+void disable_write_same(struct mapped_device *md)
 {
 	struct queue_limits *limits = dm_get_queue_limits(md);
 
@@ -1062,371 +857,6 @@ static void clone_endio(struct bio *bio)
 }
 
 /*
- * Partial completion handling for request-based dm
- */
-static void end_clone_bio(struct bio *clone)
-{
-	struct dm_rq_clone_bio_info *info =
-		container_of(clone, struct dm_rq_clone_bio_info, clone);
-	struct dm_rq_target_io *tio = info->tio;
-	struct bio *bio = info->orig;
-	unsigned int nr_bytes = info->orig->bi_iter.bi_size;
-	int error = clone->bi_error;
-
-	bio_put(clone);
-
-	if (tio->error)
-		/*
-		 * An error has already been detected on the request.
-		 * Once error occurred, just let clone->end_io() handle
-		 * the remainder.
-		 */
-		return;
-	else if (error) {
-		/*
-		 * Don't notice the error to the upper layer yet.
-		 * The error handling decision is made by the target driver,
-		 * when the request is completed.
-		 */
-		tio->error = error;
-		return;
-	}
-
-	/*
-	 * I/O for the bio successfully completed.
-	 * Notice the data completion to the upper layer.
-	 */
-
-	/*
-	 * bios are processed from the head of the list.
-	 * So the completing bio should always be rq->bio.
-	 * If it's not, something wrong is happening.
-	 */
-	if (tio->orig->bio != bio)
-		DMERR("bio completion is going in the middle of the request");
-
-	/*
-	 * Update the original request.
-	 * Do not use blk_end_request() here, because it may complete
-	 * the original request before the clone, and break the ordering.
-	 */
-	blk_update_request(tio->orig, 0, nr_bytes);
-}
-
-static struct dm_rq_target_io *tio_from_request(struct request *rq)
-{
-	return (rq->q->mq_ops ? blk_mq_rq_to_pdu(rq) : rq->special);
-}
-
-static void rq_end_stats(struct mapped_device *md, struct request *orig)
-{
-	if (unlikely(dm_stats_used(&md->stats))) {
-		struct dm_rq_target_io *tio = tio_from_request(orig);
-		tio->duration_jiffies = jiffies - tio->duration_jiffies;
-		dm_stats_account_io(&md->stats, rq_data_dir(orig),
-				    blk_rq_pos(orig), tio->n_sectors, true,
-				    tio->duration_jiffies, &tio->stats_aux);
-	}
-}
-
-/*
- * Don't touch any member of the md after calling this function because
- * the md may be freed in dm_put() at the end of this function.
- * Or do dm_get() before calling this function and dm_put() later.
- */
-static void rq_completed(struct mapped_device *md, int rw, bool run_queue)
-{
-	atomic_dec(&md->pending[rw]);
-
-	/* nudge anyone waiting on suspend queue */
-	if (!md_in_flight(md))
-		wake_up(&md->wait);
-
-	/*
-	 * Run this off this callpath, as drivers could invoke end_io while
-	 * inside their request_fn (and holding the queue lock). Calling
-	 * back into ->request_fn() could deadlock attempting to grab the
-	 * queue lock again.
-	 */
-	if (!md->queue->mq_ops && run_queue)
-		blk_run_queue_async(md->queue);
-
-	/*
-	 * dm_put() must be at the end of this function. See the comment above
-	 */
-	dm_put(md);
-}
-
-static void free_rq_clone(struct request *clone)
-{
-	struct dm_rq_target_io *tio = clone->end_io_data;
-	struct mapped_device *md = tio->md;
-
-	blk_rq_unprep_clone(clone);
-
-	if (md->type == DM_TYPE_MQ_REQUEST_BASED)
-		/* stacked on blk-mq queue(s) */
-		tio->ti->type->release_clone_rq(clone);
-	else if (!md->queue->mq_ops)
-		/* request_fn queue stacked on request_fn queue(s) */
-		free_old_clone_request(md, clone);
-
-	if (!md->queue->mq_ops)
-		free_old_rq_tio(tio);
-}
-
-/*
- * Complete the clone and the original request.
- * Must be called without clone's queue lock held,
- * see end_clone_request() for more details.
- */
-static void dm_end_request(struct request *clone, int error)
-{
-	int rw = rq_data_dir(clone);
-	struct dm_rq_target_io *tio = clone->end_io_data;
-	struct mapped_device *md = tio->md;
-	struct request *rq = tio->orig;
-
-	if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
-		rq->errors = clone->errors;
-		rq->resid_len = clone->resid_len;
-
-		if (rq->sense)
-			/*
-			 * We are using the sense buffer of the original
-			 * request.
-			 * So setting the length of the sense data is enough.
-			 */
-			rq->sense_len = clone->sense_len;
-	}
-
-	free_rq_clone(clone);
-	rq_end_stats(md, rq);
-	if (!rq->q->mq_ops)
-		blk_end_request_all(rq, error);
-	else
-		blk_mq_end_request(rq, error);
-	rq_completed(md, rw, true);
-}
-
-static void dm_unprep_request(struct request *rq)
-{
-	struct dm_rq_target_io *tio = tio_from_request(rq);
-	struct request *clone = tio->clone;
-
-	if (!rq->q->mq_ops) {
-		rq->special = NULL;
-		rq->cmd_flags &= ~REQ_DONTPREP;
-	}
-
-	if (clone)
-		free_rq_clone(clone);
-	else if (!tio->md->queue->mq_ops)
-		free_old_rq_tio(tio);
-}
-
-/*
- * Requeue the original request of a clone.
- */
-static void dm_old_requeue_request(struct request *rq)
-{
-	struct request_queue *q = rq->q;
-	unsigned long flags;
-
-	spin_lock_irqsave(q->queue_lock, flags);
-	blk_requeue_request(q, rq);
-	blk_run_queue_async(q);
-	spin_unlock_irqrestore(q->queue_lock, flags);
-}
-
-static void dm_mq_requeue_request(struct request *rq)
-{
-	struct request_queue *q = rq->q;
-	unsigned long flags;
-
-	blk_mq_requeue_request(rq);
-	spin_lock_irqsave(q->queue_lock, flags);
-	if (!blk_queue_stopped(q))
-		blk_mq_kick_requeue_list(q);
-	spin_unlock_irqrestore(q->queue_lock, flags);
-}
-
-static void dm_requeue_original_request(struct mapped_device *md,
-					struct request *rq)
-{
-	int rw = rq_data_dir(rq);
-
-	rq_end_stats(md, rq);
-	dm_unprep_request(rq);
-
-	if (!rq->q->mq_ops)
-		dm_old_requeue_request(rq);
-	else
-		dm_mq_requeue_request(rq);
-
-	rq_completed(md, rw, false);
-}
-
-static void dm_old_stop_queue(struct request_queue *q)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(q->queue_lock, flags);
-	if (blk_queue_stopped(q)) {
-		spin_unlock_irqrestore(q->queue_lock, flags);
-		return;
-	}
-
-	blk_stop_queue(q);
-	spin_unlock_irqrestore(q->queue_lock, flags);
-}
-
-static void dm_stop_queue(struct request_queue *q)
-{
-	if (!q->mq_ops)
-		dm_old_stop_queue(q);
-	else
-		blk_mq_stop_hw_queues(q);
-}
-
-static void dm_old_start_queue(struct request_queue *q)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(q->queue_lock, flags);
-	if (blk_queue_stopped(q))
-		blk_start_queue(q);
-	spin_unlock_irqrestore(q->queue_lock, flags);
-}
-
-static void dm_start_queue(struct request_queue *q)
-{
-	if (!q->mq_ops)
-		dm_old_start_queue(q);
-	else {
-		blk_mq_start_stopped_hw_queues(q, true);
-		blk_mq_kick_requeue_list(q);
-	}
-}
-
-static void dm_done(struct request *clone, int error, bool mapped)
-{
-	int r = error;
-	struct dm_rq_target_io *tio = clone->end_io_data;
-	dm_request_endio_fn rq_end_io = NULL;
-
-	if (tio->ti) {
-		rq_end_io = tio->ti->type->rq_end_io;
-
-		if (mapped && rq_end_io)
-			r = rq_end_io(tio->ti, clone, error, &tio->info);
-	}
-
-	if (unlikely(r == -EREMOTEIO && (req_op(clone) == REQ_OP_WRITE_SAME) &&
-		     !clone->q->limits.max_write_same_sectors))
-		disable_write_same(tio->md);
-
-	if (r <= 0)
-		/* The target wants to complete the I/O */
-		dm_end_request(clone, r);
-	else if (r == DM_ENDIO_INCOMPLETE)
-		/* The target will handle the I/O */
-		return;
-	else if (r == DM_ENDIO_REQUEUE)
-		/* The target wants to requeue the I/O */
-		dm_requeue_original_request(tio->md, tio->orig);
-	else {
-		DMWARN("unimplemented target endio return value: %d", r);
-		BUG();
-	}
-}
-
-/*
- * Request completion handler for request-based dm
- */
-static void dm_softirq_done(struct request *rq)
-{
-	bool mapped = true;
-	struct dm_rq_target_io *tio = tio_from_request(rq);
-	struct request *clone = tio->clone;
-	int rw;
-
-	if (!clone) {
-		rq_end_stats(tio->md, rq);
-		rw = rq_data_dir(rq);
-		if (!rq->q->mq_ops) {
-			blk_end_request_all(rq, tio->error);
-			rq_completed(tio->md, rw, false);
-			free_old_rq_tio(tio);
-		} else {
-			blk_mq_end_request(rq, tio->error);
-			rq_completed(tio->md, rw, false);
-		}
-		return;
-	}
-
-	if (rq->cmd_flags & REQ_FAILED)
-		mapped = false;
-
-	dm_done(clone, tio->error, mapped);
-}
-
-/*
- * Complete the clone and the original request with the error status
- * through softirq context.
- */
-static void dm_complete_request(struct request *rq, int error)
-{
-	struct dm_rq_target_io *tio = tio_from_request(rq);
-
-	tio->error = error;
-	if (!rq->q->mq_ops)
-		blk_complete_request(rq);
-	else
-		blk_mq_complete_request(rq, error);
-}
-
-/*
- * Complete the not-mapped clone and the original request with the error status
- * through softirq context.
- * Target's rq_end_io() function isn't called.
- * This may be used when the target's map_rq() or clone_and_map_rq() functions fail.
- */
-static void dm_kill_unmapped_request(struct request *rq, int error)
-{
-	rq->cmd_flags |= REQ_FAILED;
-	dm_complete_request(rq, error);
-}
-
-/*
- * Called with the clone's queue lock held (in the case of .request_fn)
- */
-static void end_clone_request(struct request *clone, int error)
-{
-	struct dm_rq_target_io *tio = clone->end_io_data;
-
-	if (!clone->q->mq_ops) {
-		/*
-		 * For just cleaning up the information of the queue in which
-		 * the clone was dispatched.
-		 * The clone is *NOT* freed actually here because it is alloced
-		 * from dm own mempool (REQ_ALLOCED isn't set).
-		 */
-		__blk_put_request(clone->q, clone);
-	}
-
-	/*
-	 * Actual request completion is done in a softirq context which doesn't
-	 * hold the clone's queue lock.  Otherwise, deadlock could occur because:
-	 *     - another request may be submitted by the upper level driver
-	 *       of the stacking during the completion
-	 *     - the submission which requires queue lock may be done
-	 *       against this clone's queue
-	 */
-	dm_complete_request(tio->orig, error);
-}
-
-/*
  * Return maximum size of I/O possible at the supplied sector up to the current
  * target boundary.
  */
@@ -1845,353 +1275,6 @@ static blk_qc_t dm_make_request(struct request_queue *q, struct bio *bio)
 	return BLK_QC_T_NONE;
 }
 
-int dm_request_based(struct mapped_device *md)
-{
-	return blk_queue_stackable(md->queue);
-}
-
-static void dm_dispatch_clone_request(struct request *clone, struct request *rq)
-{
-	int r;
-
-	if (blk_queue_io_stat(clone->q))
-		clone->cmd_flags |= REQ_IO_STAT;
-
-	clone->start_time = jiffies;
-	r = blk_insert_cloned_request(clone->q, clone);
-	if (r)
-		/* must complete clone in terms of original request */
-		dm_complete_request(rq, r);
-}
-
-static int dm_rq_bio_constructor(struct bio *bio, struct bio *bio_orig,
-				 void *data)
-{
-	struct dm_rq_target_io *tio = data;
-	struct dm_rq_clone_bio_info *info =
-		container_of(bio, struct dm_rq_clone_bio_info, clone);
-
-	info->orig = bio_orig;
-	info->tio = tio;
-	bio->bi_end_io = end_clone_bio;
-
-	return 0;
-}
-
-static int setup_clone(struct request *clone, struct request *rq,
-		       struct dm_rq_target_io *tio, gfp_t gfp_mask)
-{
-	int r;
-
-	r = blk_rq_prep_clone(clone, rq, tio->md->bs, gfp_mask,
-			      dm_rq_bio_constructor, tio);
-	if (r)
-		return r;
-
-	clone->cmd = rq->cmd;
-	clone->cmd_len = rq->cmd_len;
-	clone->sense = rq->sense;
-	clone->end_io = end_clone_request;
-	clone->end_io_data = tio;
-
-	tio->clone = clone;
-
-	return 0;
-}
-
-static struct request *clone_old_rq(struct request *rq, struct mapped_device *md,
-				    struct dm_rq_target_io *tio, gfp_t gfp_mask)
-{
-	/*
-	 * Create clone for use with .request_fn request_queue
-	 */
-	struct request *clone;
-
-	clone = alloc_old_clone_request(md, gfp_mask);
-	if (!clone)
-		return NULL;
-
-	blk_rq_init(NULL, clone);
-	if (setup_clone(clone, rq, tio, gfp_mask)) {
-		/* -ENOMEM */
-		free_old_clone_request(md, clone);
-		return NULL;
-	}
-
-	return clone;
-}
-
-static void map_tio_request(struct kthread_work *work);
-
-static void init_tio(struct dm_rq_target_io *tio, struct request *rq,
-		     struct mapped_device *md)
-{
-	tio->md = md;
-	tio->ti = NULL;
-	tio->clone = NULL;
-	tio->orig = rq;
-	tio->error = 0;
-	/*
-	 * Avoid initializing info for blk-mq; it passes
-	 * target-specific data through info.ptr
-	 * (see: dm_mq_init_request)
-	 */
-	if (!md->init_tio_pdu)
-		memset(&tio->info, 0, sizeof(tio->info));
-	if (md->kworker_task)
-		init_kthread_work(&tio->work, map_tio_request);
-}
-
-static struct dm_rq_target_io *dm_old_prep_tio(struct request *rq,
-					       struct mapped_device *md,
-					       gfp_t gfp_mask)
-{
-	struct dm_rq_target_io *tio;
-	int srcu_idx;
-	struct dm_table *table;
-
-	tio = alloc_old_rq_tio(md, gfp_mask);
-	if (!tio)
-		return NULL;
-
-	init_tio(tio, rq, md);
-
-	table = dm_get_live_table(md, &srcu_idx);
-	/*
-	 * Must clone a request if this .request_fn DM device
-	 * is stacked on .request_fn device(s).
-	 */
-	if (!dm_table_mq_request_based(table)) {
-		if (!clone_old_rq(rq, md, tio, gfp_mask)) {
-			dm_put_live_table(md, srcu_idx);
-			free_old_rq_tio(tio);
-			return NULL;
-		}
-	}
-	dm_put_live_table(md, srcu_idx);
-
-	return tio;
-}
-
-/*
- * Called with the queue lock held.
- */
-static int dm_old_prep_fn(struct request_queue *q, struct request *rq)
-{
-	struct mapped_device *md = q->queuedata;
-	struct dm_rq_target_io *tio;
-
-	if (unlikely(rq->special)) {
-		DMWARN("Already has something in rq->special.");
-		return BLKPREP_KILL;
-	}
-
-	tio = dm_old_prep_tio(rq, md, GFP_ATOMIC);
-	if (!tio)
-		return BLKPREP_DEFER;
-
-	rq->special = tio;
-	rq->cmd_flags |= REQ_DONTPREP;
-
-	return BLKPREP_OK;
-}
-
-/*
- * Returns:
- * 0                : the request has been processed
- * DM_MAPIO_REQUEUE : the original request needs to be requeued
- * < 0              : the request was completed due to failure
- */
-static int map_request(struct dm_rq_target_io *tio, struct request *rq,
-		       struct mapped_device *md)
-{
-	int r;
-	struct dm_target *ti = tio->ti;
-	struct request *clone = NULL;
-
-	if (tio->clone) {
-		clone = tio->clone;
-		r = ti->type->map_rq(ti, clone, &tio->info);
-	} else {
-		r = ti->type->clone_and_map_rq(ti, rq, &tio->info, &clone);
-		if (r < 0) {
-			/* The target wants to complete the I/O */
-			dm_kill_unmapped_request(rq, r);
-			return r;
-		}
-		if (r != DM_MAPIO_REMAPPED)
-			return r;
-		if (setup_clone(clone, rq, tio, GFP_ATOMIC)) {
-			/* -ENOMEM */
-			ti->type->release_clone_rq(clone);
-			return DM_MAPIO_REQUEUE;
-		}
-	}
-
-	switch (r) {
-	case DM_MAPIO_SUBMITTED:
-		/* The target has taken the I/O to submit by itself later */
-		break;
-	case DM_MAPIO_REMAPPED:
-		/* The target has remapped the I/O so dispatch it */
-		trace_block_rq_remap(clone->q, clone, disk_devt(dm_disk(md)),
-				     blk_rq_pos(rq));
-		dm_dispatch_clone_request(clone, rq);
-		break;
-	case DM_MAPIO_REQUEUE:
-		/* The target wants to requeue the I/O */
-		dm_requeue_original_request(md, tio->orig);
-		break;
-	default:
-		if (r > 0) {
-			DMWARN("unimplemented target map return value: %d", r);
-			BUG();
-		}
-
-		/* The target wants to complete the I/O */
-		dm_kill_unmapped_request(rq, r);
-		return r;
-	}
-
-	return 0;
-}
-
-static void map_tio_request(struct kthread_work *work)
-{
-	struct dm_rq_target_io *tio = container_of(work, struct dm_rq_target_io, work);
-	struct request *rq = tio->orig;
-	struct mapped_device *md = tio->md;
-
-	if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE)
-		dm_requeue_original_request(md, rq);
-}
-
-static void dm_start_request(struct mapped_device *md, struct request *orig)
-{
-	if (!orig->q->mq_ops)
-		blk_start_request(orig);
-	else
-		blk_mq_start_request(orig);
-	atomic_inc(&md->pending[rq_data_dir(orig)]);
-
-	if (md->seq_rq_merge_deadline_usecs) {
-		md->last_rq_pos = rq_end_sector(orig);
-		md->last_rq_rw = rq_data_dir(orig);
-		md->last_rq_start_time = ktime_get();
-	}
-
-	if (unlikely(dm_stats_used(&md->stats))) {
-		struct dm_rq_target_io *tio = tio_from_request(orig);
-		tio->duration_jiffies = jiffies;
-		tio->n_sectors = blk_rq_sectors(orig);
-		dm_stats_account_io(&md->stats, rq_data_dir(orig),
-				    blk_rq_pos(orig), tio->n_sectors, false, 0,
-				    &tio->stats_aux);
-	}
-
-	/*
-	 * Hold the md reference here for the in-flight I/O.
-	 * We can't rely on the reference count by device opener,
-	 * because the device may be closed during the request completion
-	 * when all bios are completed.
-	 * See the comment in rq_completed() too.
-	 */
-	dm_get(md);
-}
-
-#define MAX_SEQ_RQ_MERGE_DEADLINE_USECS 100000
-
-ssize_t dm_attr_rq_based_seq_io_merge_deadline_show(struct mapped_device *md, char *buf)
-{
-	return sprintf(buf, "%u\n", md->seq_rq_merge_deadline_usecs);
-}
-
-ssize_t dm_attr_rq_based_seq_io_merge_deadline_store(struct mapped_device *md,
-						     const char *buf, size_t count)
-{
-	unsigned deadline;
-
-	if (!dm_request_based(md) || md->use_blk_mq)
-		return count;
-
-	if (kstrtouint(buf, 10, &deadline))
-		return -EINVAL;
-
-	if (deadline > MAX_SEQ_RQ_MERGE_DEADLINE_USECS)
-		deadline = MAX_SEQ_RQ_MERGE_DEADLINE_USECS;
-
-	md->seq_rq_merge_deadline_usecs = deadline;
-
-	return count;
-}
-
-static bool dm_request_peeked_before_merge_deadline(struct mapped_device *md)
-{
-	ktime_t kt_deadline;
-
-	if (!md->seq_rq_merge_deadline_usecs)
-		return false;
-
-	kt_deadline = ns_to_ktime((u64)md->seq_rq_merge_deadline_usecs * NSEC_PER_USEC);
-	kt_deadline = ktime_add_safe(md->last_rq_start_time, kt_deadline);
-
-	return !ktime_after(ktime_get(), kt_deadline);
-}
-
-/*
- * q->request_fn for request-based dm.
- * Called with the queue lock held.
- */
-static void dm_request_fn(struct request_queue *q)
-{
-	struct mapped_device *md = q->queuedata;
-	struct dm_target *ti = md->immutable_target;
-	struct request *rq;
-	struct dm_rq_target_io *tio;
-	sector_t pos = 0;
-
-	if (unlikely(!ti)) {
-		int srcu_idx;
-		struct dm_table *map = dm_get_live_table(md, &srcu_idx);
-
-		ti = dm_table_find_target(map, pos);
-		dm_put_live_table(md, srcu_idx);
-	}
-
-	/*
-	 * For suspend, check blk_queue_stopped() and increment
-	 * ->pending within a single queue_lock not to increment the
-	 * number of in-flight I/Os after the queue is stopped in
-	 * dm_suspend().
-	 */
-	while (!blk_queue_stopped(q)) {
-		rq = blk_peek_request(q);
-		if (!rq)
-			return;
-
-		/* always use block 0 to find the target for flushes for now */
-		pos = 0;
-		if (req_op(rq) != REQ_OP_FLUSH)
-			pos = blk_rq_pos(rq);
-
-		if ((dm_request_peeked_before_merge_deadline(md) &&
-		     md_in_flight(md) && rq->bio && rq->bio->bi_vcnt == 1 &&
-		     md->last_rq_pos == pos && md->last_rq_rw == rq_data_dir(rq)) ||
-		    (ti->type->busy && ti->type->busy(ti))) {
-			blk_delay_queue(q, HZ / 100);
-			return;
-		}
-
-		dm_start_request(md, rq);
-
-		tio = tio_from_request(rq);
-		/* Establish tio->ti before queuing work (map_tio_request) */
-		tio->ti = ti;
-		queue_kthread_work(&md->kworker, &tio->work);
-		BUG_ON(!irqs_disabled());
-	}
-}
-
 static int dm_any_congested(void *congested_data, int bdi_bits)
 {
 	int r = bdi_bits;
@@ -2269,7 +1352,7 @@ static const struct block_device_operations dm_blk_dops;
 
 static void dm_wq_work(struct work_struct *work);
 
-static void dm_init_md_queue(struct mapped_device *md)
+void dm_init_md_queue(struct mapped_device *md)
 {
 	/*
 	 * Request-based dm devices cannot be stacked on top of bio-based dm
@@ -2290,7 +1373,7 @@ static void dm_init_md_queue(struct mapped_device *md)
 	md->queue->backing_dev_info.congested_data = md;
 }
 
-static void dm_init_normal_md_queue(struct mapped_device *md)
+void dm_init_normal_md_queue(struct mapped_device *md)
 {
 	md->use_blk_mq = false;
 	dm_init_md_queue(md);
@@ -2330,6 +1413,8 @@ static void cleanup_mapped_device(struct mapped_device *md)
 		bdput(md->bdev);
 		md->bdev = NULL;
 	}
+
+	dm_mq_cleanup_mapped_device(md);
 }
 
 /*
@@ -2363,7 +1448,7 @@ static struct mapped_device *alloc_dev(int minor)
 		goto bad_io_barrier;
 
 	md->numa_node_id = numa_node_id;
-	md->use_blk_mq = use_blk_mq;
+	md->use_blk_mq = dm_use_blk_mq_default();
 	md->init_tio_pdu = false;
 	md->type = DM_TYPE_NONE;
 	mutex_init(&md->suspend_lock);
@@ -2448,10 +1533,6 @@ static void free_dev(struct mapped_device *md)
 	unlock_fs(md);
 
 	cleanup_mapped_device(md);
-	if (md->tag_set) {
-		blk_mq_free_tag_set(md->tag_set);
-		kfree(md->tag_set);
-	}
 
 	free_table_devices(&md->table_devices);
 	dm_stats_cleanup(&md->stats);
@@ -2657,159 +1738,6 @@ struct queue_limits *dm_get_queue_limits(struct mapped_device *md)
 }
 EXPORT_SYMBOL_GPL(dm_get_queue_limits);
 
-static void dm_old_init_rq_based_worker_thread(struct mapped_device *md)
-{
-	/* Initialize the request-based DM worker thread */
-	init_kthread_worker(&md->kworker);
-	md->kworker_task = kthread_run(kthread_worker_fn, &md->kworker,
-				       "kdmwork-%s", dm_device_name(md));
-}
-
-/*
- * Fully initialize a .request_fn request-based queue.
- */
-static int dm_old_init_request_queue(struct mapped_device *md)
-{
-	/* Fully initialize the queue */
-	if (!blk_init_allocated_queue(md->queue, dm_request_fn, NULL))
-		return -EINVAL;
-
-	/* disable dm_request_fn's merge heuristic by default */
-	md->seq_rq_merge_deadline_usecs = 0;
-
-	dm_init_normal_md_queue(md);
-	blk_queue_softirq_done(md->queue, dm_softirq_done);
-	blk_queue_prep_rq(md->queue, dm_old_prep_fn);
-
-	dm_old_init_rq_based_worker_thread(md);
-
-	elv_register_queue(md->queue);
-
-	return 0;
-}
-
-static int dm_mq_init_request(void *data, struct request *rq,
-			      unsigned int hctx_idx, unsigned int request_idx,
-			      unsigned int numa_node)
-{
-	struct mapped_device *md = data;
-	struct dm_rq_target_io *tio = blk_mq_rq_to_pdu(rq);
-
-	/*
-	 * Must initialize md member of tio, otherwise it won't
-	 * be available in dm_mq_queue_rq.
-	 */
-	tio->md = md;
-
-	if (md->init_tio_pdu) {
-		/* target-specific per-io data is immediately after the tio */
-		tio->info.ptr = tio + 1;
-	}
-
-	return 0;
-}
-
-static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
-			  const struct blk_mq_queue_data *bd)
-{
-	struct request *rq = bd->rq;
-	struct dm_rq_target_io *tio = blk_mq_rq_to_pdu(rq);
-	struct mapped_device *md = tio->md;
-	struct dm_target *ti = md->immutable_target;
-
-	if (unlikely(!ti)) {
-		int srcu_idx;
-		struct dm_table *map = dm_get_live_table(md, &srcu_idx);
-
-		ti = dm_table_find_target(map, 0);
-		dm_put_live_table(md, srcu_idx);
-	}
-
-	if (ti->type->busy && ti->type->busy(ti))
-		return BLK_MQ_RQ_QUEUE_BUSY;
-
-	dm_start_request(md, rq);
-
-	/* Init tio using md established in .init_request */
-	init_tio(tio, rq, md);
-
-	/*
-	 * Establish tio->ti before queuing work (map_tio_request)
-	 * or making direct call to map_request().
-	 */
-	tio->ti = ti;
-
-	/* Direct call is fine since .queue_rq allows allocations */
-	if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE) {
-		/* Undo dm_start_request() before requeuing */
-		rq_end_stats(md, rq);
-		rq_completed(md, rq_data_dir(rq), false);
-		return BLK_MQ_RQ_QUEUE_BUSY;
-	}
-
-	return BLK_MQ_RQ_QUEUE_OK;
-}
-
-static struct blk_mq_ops dm_mq_ops = {
-	.queue_rq = dm_mq_queue_rq,
-	.map_queue = blk_mq_map_queue,
-	.complete = dm_softirq_done,
-	.init_request = dm_mq_init_request,
-};
-
-static int dm_mq_init_request_queue(struct mapped_device *md,
-				    struct dm_target *immutable_tgt)
-{
-	struct request_queue *q;
-	int err;
-
-	if (dm_get_md_type(md) == DM_TYPE_REQUEST_BASED) {
-		DMERR("request-based dm-mq may only be stacked on blk-mq device(s)");
-		return -EINVAL;
-	}
-
-	md->tag_set = kzalloc_node(sizeof(struct blk_mq_tag_set), GFP_KERNEL, md->numa_node_id);
-	if (!md->tag_set)
-		return -ENOMEM;
-
-	md->tag_set->ops = &dm_mq_ops;
-	md->tag_set->queue_depth = dm_get_blk_mq_queue_depth();
-	md->tag_set->numa_node = md->numa_node_id;
-	md->tag_set->flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
-	md->tag_set->nr_hw_queues = dm_get_blk_mq_nr_hw_queues();
-	md->tag_set->driver_data = md;
-
-	md->tag_set->cmd_size = sizeof(struct dm_rq_target_io);
-	if (immutable_tgt && immutable_tgt->per_io_data_size) {
-		/* any target-specific per-io data is immediately after the tio */
-		md->tag_set->cmd_size += immutable_tgt->per_io_data_size;
-		md->init_tio_pdu = true;
-	}
-
-	err = blk_mq_alloc_tag_set(md->tag_set);
-	if (err)
-		goto out_kfree_tag_set;
-
-	q = blk_mq_init_allocated_queue(md->tag_set, md->queue);
-	if (IS_ERR(q)) {
-		err = PTR_ERR(q);
-		goto out_tag_set;
-	}
-	dm_init_md_queue(md);
-
-	/* backfill 'mq' sysfs registration normally done in blk_register_queue */
-	blk_mq_register_disk(md->disk);
-
-	return 0;
-
-out_tag_set:
-	blk_mq_free_tag_set(md->tag_set);
-out_kfree_tag_set:
-	kfree(md->tag_set);
-
-	return err;
-}
-
 static unsigned filter_md_type(unsigned type, struct mapped_device *md)
 {
 	if (type == DM_TYPE_BIO_BASED)
@@ -3741,18 +2669,6 @@ MODULE_PARM_DESC(major, "The major number of the device mapper");
 module_param(reserved_bio_based_ios, uint, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(reserved_bio_based_ios, "Reserved IOs in bio-based mempools");
 
-module_param(reserved_rq_based_ios, uint, S_IRUGO | S_IWUSR);
-MODULE_PARM_DESC(reserved_rq_based_ios, "Reserved IOs in request-based mempools");
-
-module_param(use_blk_mq, bool, S_IRUGO | S_IWUSR);
-MODULE_PARM_DESC(use_blk_mq, "Use block multiqueue for request-based DM devices");
-
-module_param(dm_mq_nr_hw_queues, uint, S_IRUGO | S_IWUSR);
-MODULE_PARM_DESC(dm_mq_nr_hw_queues, "Number of hardware queues for request-based dm-mq devices");
-
-module_param(dm_mq_queue_depth, uint, S_IRUGO | S_IWUSR);
-MODULE_PARM_DESC(dm_mq_queue_depth, "Queue depth for request-based dm-mq devices");
-
 module_param(dm_numa_node, int, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(dm_numa_node, "NUMA node for DM device memory allocations");
 
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 13a758ec0f88..b611b3064a7c 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -13,6 +13,7 @@
 #include <linux/fs.h>
 #include <linux/device-mapper.h>
 #include <linux/list.h>
+#include <linux/moduleparam.h>
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
 #include <linux/hdreg.h>
@@ -161,16 +162,6 @@ void dm_interface_exit(void);
 /*
  * sysfs interface
  */
-struct dm_kobject_holder {
-	struct kobject kobj;
-	struct completion completion;
-};
-
-static inline struct completion *dm_get_completion_from_kobject(struct kobject *kobj)
-{
-	return &container_of(kobj, struct dm_kobject_holder, kobj)->completion;
-}
-
 int dm_sysfs_init(struct mapped_device *md);
 void dm_sysfs_exit(struct mapped_device *md);
 struct kobject *dm_kobject(struct mapped_device *md);
@@ -212,8 +203,6 @@ int dm_kobject_uevent(struct mapped_device *md, enum kobject_action action,
 void dm_internal_suspend(struct mapped_device *md);
 void dm_internal_resume(struct mapped_device *md);
 
-bool dm_use_blk_mq(struct mapped_device *md);
-
 int dm_io_init(void);
 void dm_io_exit(void);
 
@@ -228,18 +217,8 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, unsigned t
 void dm_free_md_mempools(struct dm_md_mempools *pools);
 
 /*
- * Helpers that are used by DM core
+ * Various helpers
  */
 unsigned dm_get_reserved_bio_based_ios(void);
-unsigned dm_get_reserved_rq_based_ios(void);
-
-static inline bool dm_message_test_buffer_overflow(char *result, unsigned maxlen)
-{
-	return !maxlen || strlen(result) + 1 >= maxlen;
-}
-
-ssize_t dm_attr_rq_based_seq_io_merge_deadline_show(struct mapped_device *md, char *buf);
-ssize_t dm_attr_rq_based_seq_io_merge_deadline_store(struct mapped_device *md,
-						     const char *buf, size_t count);
 
 #endif