Merge branch 'linus' into WIP.x86/boot, to fix up conflicts and to pick up updates

 Conflicts:
	arch/x86/xen/setup.c

Signed-off-by: Ingo Molnar <mingo@kernel.org>

42 files changed, 6337 insertions, 1087 deletions

diff --git a/block/Kconfig b/block/Kconfig
index 8bf114a3858a..a2a92e57a87d 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -49,9 +49,13 @@ config LBDAF
 
 	  If unsure, say Y.
 
+config BLK_SCSI_REQUEST
+	bool
+
 config BLK_DEV_BSG
 	bool "Block layer SG support v4"
 	default y
+	select BLK_SCSI_REQUEST
 	help
 	  Saying Y here will enable generic SG (SCSI generic) v4 support
 	  for any block device.
@@ -71,6 +75,7 @@ config BLK_DEV_BSGLIB
 	bool "Block layer SG support v4 helper lib"
 	default n
 	select BLK_DEV_BSG
+	select BLK_SCSI_REQUEST
 	help
 	  Subsystems will normally enable this if needed. Users will not
 	  normally need to manually enable this.
@@ -147,6 +152,25 @@ 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.
+
+config BLK_SED_OPAL
+	bool "Logic for interfacing with Opal enabled SEDs"
+	---help---
+	Builds Logic for interfacing with Opal enabled controllers.
+	Enabling this option enables users to setup/unlock/lock
+	Locking ranges for SED devices using the Opal protocol.
+
 menu "Partition Types"
 
 source "block/partitions/Kconfig"
diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched
index 421bef9c4c48..58fc8684788d 100644
--- a/block/Kconfig.iosched
+++ b/block/Kconfig.iosched
@@ -63,6 +63,12 @@ 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.
+
 endmenu
 
 endif
diff --git a/block/Makefile b/block/Makefile
index a827f988c4e6..2ad7c304e3f5 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -6,11 +6,12 @@ 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 \
-			genhd.o scsi_ioctl.o partition-generic.o ioprio.o \
+			blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \
+			genhd.o partition-generic.o ioprio.o \
 			badblocks.o partitions/
 
-obj-$(CONFIG_BOUNCE)	+= bounce.o
+obj-$(CONFIG_BOUNCE)		+= bounce.o
+obj-$(CONFIG_BLK_SCSI_REQUEST)	+= scsi_ioctl.o
 obj-$(CONFIG_BLK_DEV_BSG)	+= bsg.o
 obj-$(CONFIG_BLK_DEV_BSGLIB)	+= bsg-lib.o
 obj-$(CONFIG_BLK_CGROUP)	+= blk-cgroup.o
@@ -18,6 +19,7 @@ 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 +27,5 @@ 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-$(CONFIG_BLK_DEBUG_FS)	+= blk-mq-debugfs.o
+obj-$(CONFIG_BLK_SED_OPAL)	+= sed-opal.o
diff --git a/block/bio.c b/block/bio.c
index 2b375020fc49..5eec5e08417f 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -625,21 +625,20 @@ struct bio *bio_clone_fast(struct bio *bio, gfp_t gfp_mask, struct bio_set *bs)
 }
 EXPORT_SYMBOL(bio_clone_fast);
 
-/**
- * 	bio_clone_bioset - clone a bio
- * 	@bio_src: bio to clone
- *	@gfp_mask: allocation priority
- *	@bs: bio_set to allocate from
- *
- *	Clone bio. Caller will own the returned bio, but not the actual data it
- *	points to. Reference count of returned bio will be one.
- */
-struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask,
-			     struct bio_set *bs)
+static struct bio *__bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask,
+				      struct bio_set *bs, int offset,
+				      int size)
 {
 	struct bvec_iter iter;
 	struct bio_vec bv;
 	struct bio *bio;
+	struct bvec_iter iter_src = bio_src->bi_iter;
+
+	/* for supporting partial clone */
+	if (offset || size != bio_src->bi_iter.bi_size) {
+		bio_advance_iter(bio_src, &iter_src, offset);
+		iter_src.bi_size = size;
+	}
 
 	/*
 	 * Pre immutable biovecs, __bio_clone() used to just do a memcpy from
@@ -663,7 +662,8 @@ struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask,
 	 *    __bio_clone_fast() anyways.
 	 */
 
-	bio = bio_alloc_bioset(gfp_mask, bio_segments(bio_src), bs);
+	bio = bio_alloc_bioset(gfp_mask, __bio_segments(bio_src,
+			       &iter_src), bs);
 	if (!bio)
 		return NULL;
 	bio->bi_bdev		= bio_src->bi_bdev;
@@ -680,7 +680,7 @@ struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask,
 		bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0];
 		break;
 	default:
-		bio_for_each_segment(bv, bio_src, iter)
+		__bio_for_each_segment(bv, bio_src, iter, iter_src)
 			bio->bi_io_vec[bio->bi_vcnt++] = bv;
 		break;
 	}
@@ -699,9 +699,44 @@ struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask,
 
 	return bio;
 }
+
+/**
+ * 	bio_clone_bioset - clone a bio
+ * 	@bio_src: bio to clone
+ *	@gfp_mask: allocation priority
+ *	@bs: bio_set to allocate from
+ *
+ *	Clone bio. Caller will own the returned bio, but not the actual data it
+ *	points to. Reference count of returned bio will be one.
+ */
+struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask,
+			     struct bio_set *bs)
+{
+	return __bio_clone_bioset(bio_src, gfp_mask, bs, 0,
+				  bio_src->bi_iter.bi_size);
+}
 EXPORT_SYMBOL(bio_clone_bioset);
 
 /**
+ * 	bio_clone_bioset_partial - clone a partial bio
+ * 	@bio_src: bio to clone
+ *	@gfp_mask: allocation priority
+ *	@bs: bio_set to allocate from
+ *	@offset: cloned starting from the offset
+ *	@size: size for the cloned bio
+ *
+ *	Clone bio. Caller will own the returned bio, but not the actual data it
+ *	points to. Reference count of returned bio will be one.
+ */
+struct bio *bio_clone_bioset_partial(struct bio *bio_src, gfp_t gfp_mask,
+				     struct bio_set *bs, int offset,
+				     int size)
+{
+	return __bio_clone_bioset(bio_src, gfp_mask, bs, offset, size);
+}
+EXPORT_SYMBOL(bio_clone_bioset_partial);
+
+/**
  *	bio_add_pc_page	-	attempt to add page to bio
  *	@q: the target queue
  *	@bio: destination bio
@@ -1227,9 +1262,6 @@ struct bio *bio_copy_user_iov(struct request_queue *q,
 	if (!bio)
 		goto out_bmd;
 
-	if (iter->type & WRITE)
-		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
-
 	ret = 0;
 
 	if (map_data) {
@@ -1394,16 +1426,10 @@ struct bio *bio_map_user_iov(struct request_queue *q,
 
 	kfree(pages);
 
-	/*
-	 * set data direction, and check if mapped pages need bouncing
-	 */
-	if (iter->type & WRITE)
-		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
-
 	bio_set_flag(bio, BIO_USER_MAPPED);
 
 	/*
-	 * subtle -- if __bio_map_user() ended up bouncing a bio,
+	 * subtle -- if bio_map_user_iov() ended up bouncing a bio,
 	 * it would normally disappear when its bi_end_io is run.
 	 * however, we need it for the unmap, so grab an extra
 	 * reference to it
@@ -1445,8 +1471,8 @@ static void __bio_unmap_user(struct bio *bio)
  *	bio_unmap_user	-	unmap a bio
  *	@bio:		the bio being unmapped
  *
- *	Unmap a bio previously mapped by bio_map_user(). Must be called with
- *	a process context.
+ *	Unmap a bio previously mapped by bio_map_user_iov(). Must be called from
+ *	process context.
  *
  *	bio_unmap_user() may sleep.
  */
@@ -1590,7 +1616,6 @@ struct bio *bio_copy_kern(struct request_queue *q, void *data, unsigned int len,
 		bio->bi_private = data;
 	} else {
 		bio->bi_end_io = bio_copy_kern_endio;
-		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 	}
 
 	return bio;
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 8ba0af780e88..295e98c2c8cc 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -184,7 +184,7 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
 		goto err_free_blkg;
 	}
 
-	wb_congested = wb_congested_get_create(&q->backing_dev_info,
+	wb_congested = wb_congested_get_create(q->backing_dev_info,
 					       blkcg->css.id,
 					       GFP_NOWAIT | __GFP_NOWARN);
 	if (!wb_congested) {
@@ -469,8 +469,8 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css,
 const char *blkg_dev_name(struct blkcg_gq *blkg)
 {
 	/* some drivers (floppy) instantiate a queue w/o disk registered */
-	if (blkg->q->backing_dev_info.dev)
-		return dev_name(blkg->q->backing_dev_info.dev);
+	if (blkg->q->backing_dev_info->dev)
+		return dev_name(blkg->q->backing_dev_info->dev);
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(blkg_dev_name);
@@ -1079,10 +1079,8 @@ int blkcg_init_queue(struct request_queue *q)
 	if (preloaded)
 		radix_tree_preload_end();
 
-	if (IS_ERR(blkg)) {
-		blkg_free(new_blkg);
+	if (IS_ERR(blkg))
 		return PTR_ERR(blkg);
-	}
 
 	q->root_blkg = blkg;
 	q->root_rl.blkg = blkg;
@@ -1223,7 +1221,10 @@ 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 +1262,10 @@ 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 +1288,11 @@ 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 +1312,11 @@ 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);
 
diff --git a/block/blk-core.c b/block/blk-core.c
index 61ba08c58b64..b9e857f4afe8 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -33,14 +33,20 @@
 #include <linux/ratelimit.h>
 #include <linux/pm_runtime.h>
 #include <linux/blk-cgroup.h>
+#include <linux/debugfs.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/block.h>
 
 #include "blk.h"
 #include "blk-mq.h"
+#include "blk-mq-sched.h"
 #include "blk-wbt.h"
 
+#ifdef CONFIG_DEBUG_FS
+struct dentry *blk_debugfs_root;
+#endif
+
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete);
@@ -74,7 +80,7 @@ static void blk_clear_congested(struct request_list *rl, int sync)
 	 * flip its congestion state for events on other blkcgs.
 	 */
 	if (rl == &rl->q->root_rl)
-		clear_wb_congested(rl->q->backing_dev_info.wb.congested, sync);
+		clear_wb_congested(rl->q->backing_dev_info->wb.congested, sync);
 #endif
 }
 
@@ -85,7 +91,7 @@ static void blk_set_congested(struct request_list *rl, int sync)
 #else
 	/* see blk_clear_congested() */
 	if (rl == &rl->q->root_rl)
-		set_wb_congested(rl->q->backing_dev_info.wb.congested, sync);
+		set_wb_congested(rl->q->backing_dev_info->wb.congested, sync);
 #endif
 }
 
@@ -104,22 +110,6 @@ void blk_queue_congestion_threshold(struct request_queue *q)
 	q->nr_congestion_off = nr;
 }
 
-/**
- * blk_get_backing_dev_info - get the address of a queue's backing_dev_info
- * @bdev:	device
- *
- * Locates the passed device's request queue and returns the address of its
- * backing_dev_info.  This function can only be called if @bdev is opened
- * and the return value is never NULL.
- */
-struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev)
-{
-	struct request_queue *q = bdev_get_queue(bdev);
-
-	return &q->backing_dev_info;
-}
-EXPORT_SYMBOL(blk_get_backing_dev_info);
-
 void blk_rq_init(struct request_queue *q, struct request *rq)
 {
 	memset(rq, 0, sizeof(*rq));
@@ -131,9 +121,8 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 	rq->__sector = (sector_t) -1;
 	INIT_HLIST_NODE(&rq->hash);
 	RB_CLEAR_NODE(&rq->rb_node);
-	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;
@@ -158,10 +147,8 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 
 void blk_dump_rq_flags(struct request *rq, char *msg)
 {
-	int bit;
-
-	printk(KERN_INFO "%s: dev %s: type=%x, flags=%llx\n", msg,
-		rq->rq_disk ? rq->rq_disk->disk_name : "?", rq->cmd_type,
+	printk(KERN_INFO "%s: dev %s: flags=%llx\n", msg,
+		rq->rq_disk ? rq->rq_disk->disk_name : "?",
 		(unsigned long long) rq->cmd_flags);
 
 	printk(KERN_INFO "  sector %llu, nr/cnr %u/%u\n",
@@ -169,13 +156,6 @@ void blk_dump_rq_flags(struct request *rq, char *msg)
 	       blk_rq_sectors(rq), blk_rq_cur_sectors(rq));
 	printk(KERN_INFO "  bio %p, biotail %p, len %u\n",
 	       rq->bio, rq->biotail, blk_rq_bytes(rq));
-
-	if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
-		printk(KERN_INFO "  cdb: ");
-		for (bit = 0; bit < BLK_MAX_CDB; bit++)
-			printk("%02x ", rq->cmd[bit]);
-		printk("\n");
-	}
 }
 EXPORT_SYMBOL(blk_dump_rq_flags);
 
@@ -525,12 +505,14 @@ void blk_set_queue_dying(struct request_queue *q)
 	else {
 		struct request_list *rl;
 
+		spin_lock_irq(q->queue_lock);
 		blk_queue_for_each_rl(rl, q) {
 			if (rl->rq_pool) {
 				wake_up(&rl->wait[BLK_RW_SYNC]);
 				wake_up(&rl->wait[BLK_RW_ASYNC]);
 			}
 		}
+		spin_unlock_irq(q->queue_lock);
 	}
 }
 EXPORT_SYMBOL_GPL(blk_set_queue_dying);
@@ -584,7 +566,7 @@ void blk_cleanup_queue(struct request_queue *q)
 	blk_flush_integrity();
 
 	/* @q won't process any more request, flush async actions */
-	del_timer_sync(&q->backing_dev_info.laptop_mode_wb_timer);
+	del_timer_sync(&q->backing_dev_info->laptop_mode_wb_timer);
 	blk_sync_queue(q);
 
 	if (q->mq_ops)
@@ -596,7 +578,8 @@ void blk_cleanup_queue(struct request_queue *q)
 		q->queue_lock = &q->__queue_lock;
 	spin_unlock_irq(lock);
 
-	bdi_unregister(&q->backing_dev_info);
+	bdi_unregister(q->backing_dev_info);
+	put_disk_devt(q->disk_devt);
 
 	/* @q is and will stay empty, shutdown and put */
 	blk_put_queue(q);
@@ -604,17 +587,41 @@ void blk_cleanup_queue(struct request_queue *q)
 EXPORT_SYMBOL(blk_cleanup_queue);
 
 /* Allocate memory local to the request queue */
-static void *alloc_request_struct(gfp_t gfp_mask, void *data)
+static void *alloc_request_simple(gfp_t gfp_mask, void *data)
 {
-	int nid = (int)(long)data;
-	return kmem_cache_alloc_node(request_cachep, gfp_mask, nid);
+	struct request_queue *q = data;
+
+	return kmem_cache_alloc_node(request_cachep, gfp_mask, q->node);
 }
 
-static void free_request_struct(void *element, void *unused)
+static void free_request_simple(void *element, void *data)
 {
 	kmem_cache_free(request_cachep, element);
 }
 
+static void *alloc_request_size(gfp_t gfp_mask, void *data)
+{
+	struct request_queue *q = data;
+	struct request *rq;
+
+	rq = kmalloc_node(sizeof(struct request) + q->cmd_size, gfp_mask,
+			q->node);
+	if (rq && q->init_rq_fn && q->init_rq_fn(q, rq, gfp_mask) < 0) {
+		kfree(rq);
+		rq = NULL;
+	}
+	return rq;
+}
+
+static void free_request_size(void *element, void *data)
+{
+	struct request_queue *q = data;
+
+	if (q->exit_rq_fn)
+		q->exit_rq_fn(q, element);
+	kfree(element);
+}
+
 int blk_init_rl(struct request_list *rl, struct request_queue *q,
 		gfp_t gfp_mask)
 {
@@ -627,10 +634,15 @@ int blk_init_rl(struct request_list *rl, struct request_queue *q,
 	init_waitqueue_head(&rl->wait[BLK_RW_SYNC]);
 	init_waitqueue_head(&rl->wait[BLK_RW_ASYNC]);
 
-	rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ, alloc_request_struct,
-					  free_request_struct,
-					  (void *)(long)q->node, gfp_mask,
-					  q->node);
+	if (q->cmd_size) {
+		rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ,
+				alloc_request_size, free_request_size,
+				q, gfp_mask, q->node);
+	} else {
+		rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ,
+				alloc_request_simple, free_request_simple,
+				q, gfp_mask, q->node);
+	}
 	if (!rl->rq_pool)
 		return -ENOMEM;
 
@@ -693,7 +705,6 @@ static void blk_rq_timed_out_timer(unsigned long data)
 struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 {
 	struct request_queue *q;
-	int err;
 
 	q = kmem_cache_alloc_node(blk_requestq_cachep,
 				gfp_mask | __GFP_ZERO, node_id);
@@ -708,17 +719,17 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	if (!q->bio_split)
 		goto fail_id;
 
-	q->backing_dev_info.ra_pages =
+	q->backing_dev_info = bdi_alloc_node(gfp_mask, node_id);
+	if (!q->backing_dev_info)
+		goto fail_split;
+
+	q->backing_dev_info->ra_pages =
 			(VM_MAX_READAHEAD * 1024) / PAGE_SIZE;
-	q->backing_dev_info.capabilities = BDI_CAP_CGROUP_WRITEBACK;
-	q->backing_dev_info.name = "block";
+	q->backing_dev_info->capabilities = BDI_CAP_CGROUP_WRITEBACK;
+	q->backing_dev_info->name = "block";
 	q->node = node_id;
 
-	err = bdi_init(&q->backing_dev_info);
-	if (err)
-		goto fail_split;
-
-	setup_timer(&q->backing_dev_info.laptop_mode_wb_timer,
+	setup_timer(&q->backing_dev_info->laptop_mode_wb_timer,
 		    laptop_mode_timer_fn, (unsigned long) q);
 	setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q);
 	INIT_LIST_HEAD(&q->queue_head);
@@ -768,7 +779,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 fail_ref:
 	percpu_ref_exit(&q->q_usage_counter);
 fail_bdi:
-	bdi_destroy(&q->backing_dev_info);
+	bdi_put(q->backing_dev_info);
 fail_split:
 	bioset_free(q->bio_split);
 fail_id:
@@ -821,15 +832,19 @@ EXPORT_SYMBOL(blk_init_queue);
 struct request_queue *
 blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
 {
-	struct request_queue *uninit_q, *q;
+	struct request_queue *q;
 
-	uninit_q = blk_alloc_queue_node(GFP_KERNEL, node_id);
-	if (!uninit_q)
+	q = blk_alloc_queue_node(GFP_KERNEL, node_id);
+	if (!q)
 		return NULL;
 
-	q = blk_init_allocated_queue(uninit_q, rfn, lock);
-	if (!q)
-		blk_cleanup_queue(uninit_q);
+	q->request_fn = rfn;
+	if (lock)
+		q->queue_lock = lock;
+	if (blk_init_allocated_queue(q) < 0) {
+		blk_cleanup_queue(q);
+		return NULL;
+	}
 
 	return q;
 }
@@ -837,30 +852,22 @@ EXPORT_SYMBOL(blk_init_queue_node);
 
 static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio);
 
-struct request_queue *
-blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
-			 spinlock_t *lock)
-{
-	if (!q)
-		return NULL;
 
-	q->fq = blk_alloc_flush_queue(q, NUMA_NO_NODE, 0);
+int blk_init_allocated_queue(struct request_queue *q)
+{
+	q->fq = blk_alloc_flush_queue(q, NUMA_NO_NODE, q->cmd_size);
 	if (!q->fq)
-		return NULL;
+		return -ENOMEM;
+
+	if (q->init_rq_fn && q->init_rq_fn(q, q->fq->flush_rq, GFP_KERNEL))
+		goto out_free_flush_queue;
 
 	if (blk_init_rl(&q->root_rl, q, GFP_KERNEL))
-		goto fail;
+		goto out_exit_flush_rq;
 
 	INIT_WORK(&q->timeout_work, blk_timeout_work);
-	q->request_fn		= rfn;
-	q->prep_rq_fn		= NULL;
-	q->unprep_rq_fn		= NULL;
 	q->queue_flags		|= QUEUE_FLAG_DEFAULT;
 
-	/* Override internal queue lock with supplied lock pointer */
-	if (lock)
-		q->queue_lock		= lock;
-
 	/*
 	 * This also sets hw/phys segments, boundary and size
 	 */
@@ -874,17 +881,19 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
 	/* init elevator */
 	if (elevator_init(q, NULL)) {
 		mutex_unlock(&q->sysfs_lock);
-		goto fail;
+		goto out_exit_flush_rq;
 	}
 
 	mutex_unlock(&q->sysfs_lock);
+	return 0;
 
-	return q;
-
-fail:
+out_exit_flush_rq:
+	if (q->exit_rq_fn)
+		q->exit_rq_fn(q, q->fq->flush_rq);
+out_free_flush_queue:
 	blk_free_flush_queue(q->fq);
 	wbt_exit(q);
-	return NULL;
+	return -ENOMEM;
 }
 EXPORT_SYMBOL(blk_init_allocated_queue);
 
@@ -1020,41 +1029,6 @@ int blk_update_nr_requests(struct request_queue *q, unsigned int nr)
 	return 0;
 }
 
-/*
- * Determine if elevator data should be initialized when allocating the
- * request associated with @bio.
- */
-static bool blk_rq_should_init_elevator(struct bio *bio)
-{
-	if (!bio)
-		return true;
-
-	/*
-	 * 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))
-		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
@@ -1133,10 +1107,13 @@ static struct request *__get_request(struct request_list *rl, unsigned int op,
 	 * request is freed.  This guarantees icq's won't be destroyed and
 	 * makes creating new ones safe.
 	 *
+	 * Flush requests do not use the elevator so skip initialization.
+	 * This allows a request to share the flush and elevator data.
+	 *
 	 * Also, lookup icq while holding queue_lock.  If it doesn't exist,
 	 * it will be created after releasing queue_lock.
 	 */
-	if (blk_rq_should_init_elevator(bio) && !blk_queue_bypass(q)) {
+	if (!op_is_flush(op) && !blk_queue_bypass(q)) {
 		rq_flags |= RQF_ELVPRIV;
 		q->nr_rqs_elvpriv++;
 		if (et->icq_cache && ioc)
@@ -1196,7 +1173,7 @@ fail_elvpriv:
 	 * disturb iosched and blkcg but weird is bettern than dead.
 	 */
 	printk_ratelimited(KERN_WARNING "%s: dev %s: request aux data allocation failed, iosched may be disturbed\n",
-			   __func__, dev_name(q->backing_dev_info.dev));
+			   __func__, dev_name(q->backing_dev_info->dev));
 
 	rq->rq_flags &= ~RQF_ELVPRIV;
 	rq->elv.icq = NULL;
@@ -1290,8 +1267,6 @@ static struct request *blk_old_get_request(struct request_queue *q, int rw,
 {
 	struct request *rq;
 
-	BUG_ON(rw != READ && rw != WRITE);
-
 	/* create ioc upfront */
 	create_io_context(gfp_mask, q->node);
 
@@ -1321,18 +1296,6 @@ struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
 EXPORT_SYMBOL(blk_get_request);
 
 /**
- * blk_rq_set_block_pc - initialize a request to type BLOCK_PC
- * @rq:		request to be initialized
- *
- */
-void blk_rq_set_block_pc(struct request *rq)
-{
-	rq->cmd_type = REQ_TYPE_BLOCK_PC;
-	memset(rq->__cmd, 0, sizeof(rq->__cmd));
-}
-EXPORT_SYMBOL(blk_rq_set_block_pc);
-
-/**
  * blk_requeue_request - put a request back on queue
  * @q:		request queue where request should be inserted
  * @rq:		request to be inserted
@@ -1522,6 +1485,30 @@ bool bio_attempt_front_merge(struct request_queue *q, struct request *req,
 	return true;
 }
 
+bool bio_attempt_discard_merge(struct request_queue *q, struct request *req,
+		struct bio *bio)
+{
+	unsigned short segments = blk_rq_nr_discard_segments(req);
+
+	if (segments >= queue_max_discard_segments(q))
+		goto no_merge;
+	if (blk_rq_sectors(req) + bio_sectors(bio) >
+	    blk_rq_get_max_sectors(req, blk_rq_pos(req)))
+		goto no_merge;
+
+	req->biotail->bi_next = bio;
+	req->biotail = bio;
+	req->__data_len += bio->bi_iter.bi_size;
+	req->ioprio = ioprio_best(req->ioprio, bio_prio(bio));
+	req->nr_phys_segments = segments + 1;
+
+	blk_account_io_start(req, false);
+	return true;
+no_merge:
+	req_set_nomerge(q, req);
+	return false;
+}
+
 /**
  * blk_attempt_plug_merge - try to merge with %current's plugged list
  * @q: request_queue new bio is being queued at
@@ -1550,12 +1537,11 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 {
 	struct blk_plug *plug;
 	struct request *rq;
-	bool ret = false;
 	struct list_head *plug_list;
 
 	plug = current->plug;
 	if (!plug)
-		goto out;
+		return false;
 	*request_count = 0;
 
 	if (q->mq_ops)
@@ -1564,7 +1550,7 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 		plug_list = &plug->list;
 
 	list_for_each_entry_reverse(rq, plug_list, queuelist) {
-		int el_ret;
+		bool merged = false;
 
 		if (rq->q == q) {
 			(*request_count)++;
@@ -1580,19 +1566,25 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 		if (rq->q != q || !blk_rq_merge_ok(rq, bio))
 			continue;
 
-		el_ret = blk_try_merge(rq, bio);
-		if (el_ret == ELEVATOR_BACK_MERGE) {
-			ret = bio_attempt_back_merge(q, rq, bio);
-			if (ret)
-				break;
-		} else if (el_ret == ELEVATOR_FRONT_MERGE) {
-			ret = bio_attempt_front_merge(q, rq, bio);
-			if (ret)
-				break;
+		switch (blk_try_merge(rq, bio)) {
+		case ELEVATOR_BACK_MERGE:
+			merged = bio_attempt_back_merge(q, rq, bio);
+			break;
+		case ELEVATOR_FRONT_MERGE:
+			merged = bio_attempt_front_merge(q, rq, bio);
+			break;
+		case ELEVATOR_DISCARD_MERGE:
+			merged = bio_attempt_discard_merge(q, rq, bio);
+			break;
+		default:
+			break;
 		}
+
+		if (merged)
+			return true;
 	}
-out:
-	return ret;
+
+	return false;
 }
 
 unsigned int blk_plug_queued_count(struct request_queue *q)
@@ -1621,7 +1613,6 @@ out:
 
 void init_request_from_bio(struct request *req, struct bio *bio)
 {
-	req->cmd_type = REQ_TYPE_FS;
 	if (bio->bi_opf & REQ_RAHEAD)
 		req->cmd_flags |= REQ_FAILFAST_MASK;
 
@@ -1635,8 +1626,8 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 {
 	struct blk_plug *plug;
-	int el_ret, where = ELEVATOR_INSERT_SORT;
-	struct request *req;
+	int where = ELEVATOR_INSERT_SORT;
+	struct request *req, *free;
 	unsigned int request_count = 0;
 	unsigned int wb_acct;
 
@@ -1655,7 +1646,7 @@ 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;
@@ -1673,21 +1664,29 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 
 	spin_lock_irq(q->queue_lock);
 
-	el_ret = elv_merge(q, &req, bio);
-	if (el_ret == ELEVATOR_BACK_MERGE) {
-		if (bio_attempt_back_merge(q, req, bio)) {
-			elv_bio_merged(q, req, bio);
-			if (!attempt_back_merge(q, req))
-				elv_merged_request(q, req, el_ret);
-			goto out_unlock;
-		}
-	} else if (el_ret == ELEVATOR_FRONT_MERGE) {
-		if (bio_attempt_front_merge(q, req, bio)) {
-			elv_bio_merged(q, req, bio);
-			if (!attempt_front_merge(q, req))
-				elv_merged_request(q, req, el_ret);
-			goto out_unlock;
-		}
+	switch (elv_merge(q, &req, bio)) {
+	case ELEVATOR_BACK_MERGE:
+		if (!bio_attempt_back_merge(q, req, bio))
+			break;
+		elv_bio_merged(q, req, bio);
+		free = attempt_back_merge(q, req);
+		if (free)
+			__blk_put_request(q, free);
+		else
+			elv_merged_request(q, req, ELEVATOR_BACK_MERGE);
+		goto out_unlock;
+	case ELEVATOR_FRONT_MERGE:
+		if (!bio_attempt_front_merge(q, req, bio))
+			break;
+		elv_bio_merged(q, req, bio);
+		free = attempt_front_merge(q, req);
+		if (free)
+			__blk_put_request(q, free);
+		else
+			elv_merged_request(q, req, ELEVATOR_FRONT_MERGE);
+		goto out_unlock;
+	default:
+		break;
 	}
 
 get_rq:
@@ -1894,7 +1893,7 @@ 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 +2142,7 @@ 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 +2158,7 @@ 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);
@@ -2464,14 +2463,6 @@ void blk_start_request(struct request *req)
 		wbt_issue(req->q->rq_wb, &req->issue_stat);
 	}
 
-	/*
-	 * We are now handing the request to the hardware, initialize
-	 * resid_len to full count and add the timeout handler.
-	 */
-	req->resid_len = blk_rq_bytes(req);
-	if (unlikely(blk_bidi_rq(req)))
-		req->next_rq->resid_len = blk_rq_bytes(req->next_rq);
-
 	BUG_ON(test_bit(REQ_ATOM_COMPLETE, &req->atomic_flags));
 	blk_add_timer(req);
 }
@@ -2542,10 +2533,10 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 	 * TODO: tj: This is too subtle.  It would be better to let
 	 * low level drivers do what they see fit.
 	 */
-	if (req->cmd_type == REQ_TYPE_FS)
+	if (!blk_rq_is_passthrough(req))
 		req->errors = 0;
 
-	if (error && req->cmd_type == REQ_TYPE_FS &&
+	if (error && !blk_rq_is_passthrough(req) &&
 	    !(req->rq_flags & RQF_QUIET)) {
 		char *error_type;
 
@@ -2617,7 +2608,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 	req->__data_len -= total_bytes;
 
 	/* update sector only for requests with clear definition of sector */
-	if (req->cmd_type == REQ_TYPE_FS)
+	if (!blk_rq_is_passthrough(req))
 		req->__sector += total_bytes >> 9;
 
 	/* mixed attributes always follow the first bio */
@@ -2695,8 +2686,8 @@ void blk_finish_request(struct request *req, int error)
 
 	BUG_ON(blk_queued_rq(req));
 
-	if (unlikely(laptop_mode) && req->cmd_type == REQ_TYPE_FS)
-		laptop_io_completion(&req->q->backing_dev_info);
+	if (unlikely(laptop_mode) && !blk_rq_is_passthrough(req))
+		laptop_io_completion(req->q->backing_dev_info);
 
 	blk_delete_timer(req);
 
@@ -3019,8 +3010,6 @@ EXPORT_SYMBOL_GPL(blk_rq_unprep_clone);
 static void __blk_rq_prep_clone(struct request *dst, struct request *src)
 {
 	dst->cpu = src->cpu;
-	dst->cmd_flags = src->cmd_flags | REQ_NOMERGE;
-	dst->cmd_type = src->cmd_type;
 	dst->__sector = blk_rq_pos(src);
 	dst->__data_len = blk_rq_bytes(src);
 	dst->nr_phys_segments = src->nr_phys_segments;
@@ -3270,7 +3259,7 @@ 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);
@@ -3496,5 +3485,9 @@ int __init blk_dev_init(void)
 	blk_requestq_cachep = kmem_cache_create("request_queue",
 			sizeof(struct request_queue), 0, SLAB_PANIC, NULL);
 
+#ifdef CONFIG_DEBUG_FS
+	blk_debugfs_root = debugfs_create_dir("block", NULL);
+#endif
+
 	return 0;
 }
diff --git a/block/blk-exec.c b/block/blk-exec.c
index 3ecb00a6cf45..8cd0e9bc8dc8 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -9,11 +9,7 @@
 #include <linux/sched/sysctl.h>
 
 #include "blk.h"
-
-/*
- * for max sense size
- */
-#include <scsi/scsi_cmnd.h>
+#include "blk-mq-sched.h"
 
 /**
  * blk_end_sync_rq - executes a completion event on a request
@@ -55,7 +51,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 	int where = at_head ? ELEVATOR_INSERT_FRONT : ELEVATOR_INSERT_BACK;
 
 	WARN_ON(irqs_disabled());
-	WARN_ON(rq->cmd_type == REQ_TYPE_FS);
+	WARN_ON(!blk_rq_is_passthrough(rq));
 
 	rq->rq_disk = bd_disk;
 	rq->end_io = done;
@@ -65,7 +61,7 @@ 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;
 	}
 
@@ -100,16 +96,9 @@ int blk_execute_rq(struct request_queue *q, struct gendisk *bd_disk,
 		   struct request *rq, int at_head)
 {
 	DECLARE_COMPLETION_ONSTACK(wait);
-	char sense[SCSI_SENSE_BUFFERSIZE];
 	int err = 0;
 	unsigned long hang_check;
 
-	if (!rq->sense) {
-		memset(sense, 0, sizeof(sense));
-		rq->sense = sense;
-		rq->sense_len = 0;
-	}
-
 	rq->end_io_data = &wait;
 	blk_execute_rq_nowait(q, bd_disk, rq, at_head, blk_end_sync_rq);
 
@@ -123,11 +112,6 @@ int blk_execute_rq(struct request_queue *q, struct gendisk *bd_disk,
 	if (rq->errors)
 		err = -EIO;
 
-	if (rq->sense == sense)	{
-		rq->sense = NULL;
-		rq->sense_len = 0;
-	}
-
 	return err;
 }
 EXPORT_SYMBOL(blk_execute_rq);
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 20b7c7a02f1c..0d5a9c1da1fc 100644
--- a/block/blk-flush.c
+++ b/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 {
@@ -296,8 +297,14 @@ static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq)
 	if (fq->flush_pending_idx != fq->flush_running_idx || list_empty(pending))
 		return false;
 
-	/* C2 and C3 */
+	/* C2 and C3
+	 *
+	 * For blk-mq + scheduling, we can risk having all driver tags
+	 * assigned to empty flushes, and we deadlock if we are expecting
+	 * other requests to make progress. Don't defer for that case.
+	 */
 	if (!list_empty(&fq->flush_data_in_flight) &&
+	    !(q->mq_ops && q->elevator) &&
 	    time_before(jiffies,
 			fq->flush_pending_since + FLUSH_PENDING_TIMEOUT))
 		return false;
@@ -326,7 +333,6 @@ static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq)
 		blk_mq_tag_set_rq(hctx, first_rq->tag, flush_rq);
 	}
 
-	flush_rq->cmd_type = REQ_TYPE_FS;
 	flush_rq->cmd_flags = REQ_OP_FLUSH | REQ_PREFLUSH;
 	flush_rq->rq_flags |= RQF_FLUSH_SEQ;
 	flush_rq->rq_disk = first_rq->rq_disk;
@@ -391,9 +397,10 @@ 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 +460,9 @@ 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;
 	}
@@ -545,11 +552,10 @@ struct blk_flush_queue *blk_alloc_flush_queue(struct request_queue *q,
 	if (!fq)
 		goto fail;
 
-	if (q->mq_ops) {
+	if (q->mq_ops)
 		spin_lock_init(&fq->mq_flush_lock);
-		rq_sz = round_up(rq_sz + cmd_size, cache_line_size());
-	}
 
+	rq_sz = round_up(rq_sz + cmd_size, cache_line_size());
 	fq->flush_rq = kzalloc_node(rq_sz, GFP_KERNEL, node);
 	if (!fq->flush_rq)
 		goto fail_rq;
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index d69c5c79f98e..9f0ff5ba4f84 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -443,10 +443,10 @@ void blk_integrity_revalidate(struct gendisk *disk)
 		return;
 
 	if (bi->profile)
-		disk->queue->backing_dev_info.capabilities |=
+		disk->queue->backing_dev_info->capabilities |=
 			BDI_CAP_STABLE_WRITES;
 	else
-		disk->queue->backing_dev_info.capabilities &=
+		disk->queue->backing_dev_info->capabilities &=
 			~BDI_CAP_STABLE_WRITES;
 }
 
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 381cb50a673c..b12f9c87b4c3 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -35,7 +35,10 @@ static void icq_free_icq_rcu(struct rcu_head *head)
 	kmem_cache_free(icq->__rcu_icq_cache, icq);
 }
 
-/* Exit an icq. Called with both ioc and q locked. */
+/*
+ * Exit an icq. Called with both ioc and q locked for sq, only ioc locked for
+ * mq.
+ */
 static void ioc_exit_icq(struct io_cq *icq)
 {
 	struct elevator_type *et = icq->q->elevator->type;
@@ -43,8 +46,10 @@ 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;
 }
@@ -164,6 +169,7 @@ EXPORT_SYMBOL(put_io_context);
  */
 void put_io_context_active(struct io_context *ioc)
 {
+	struct elevator_type *et;
 	unsigned long flags;
 	struct io_cq *icq;
 
@@ -182,13 +188,19 @@ retry:
 	hlist_for_each_entry(icq, &ioc->icq_list, ioc_node) {
 		if (icq->flags & ICQ_EXITED)
 			continue;
-		if (spin_trylock(icq->q->queue_lock)) {
+
+		et = icq->q->elevator->type;
+		if (et->uses_mq) {
 			ioc_exit_icq(icq);
-			spin_unlock(icq->q->queue_lock);
 		} else {
-			spin_unlock_irqrestore(&ioc->lock, flags);
-			cpu_relax();
-			goto retry;
+			if (spin_trylock(icq->q->queue_lock)) {
+				ioc_exit_icq(icq);
+				spin_unlock(icq->q->queue_lock);
+			} else {
+				spin_unlock_irqrestore(&ioc->lock, flags);
+				cpu_relax();
+				goto retry;
+			}
 		}
 	}
 	spin_unlock_irqrestore(&ioc->lock, flags);
@@ -383,8 +395,10 @@ 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);
diff --git a/block/blk-lib.c b/block/blk-lib.c
index f8c82a9b4012..ed1e78e24db0 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -306,11 +306,6 @@ int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 	if (ret == 0 || (ret && ret != -EOPNOTSUPP))
 		goto out;
 
-	ret = __blkdev_issue_write_same(bdev, sector, nr_sects, gfp_mask,
-			ZERO_PAGE(0), biop);
-	if (ret == 0 || (ret && ret != -EOPNOTSUPP))
-		goto out;
-
 	ret = 0;
 	while (nr_sects != 0) {
 		bio = next_bio(bio, min(nr_sects, (sector_t)BIO_MAX_PAGES),
@@ -369,6 +364,10 @@ int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 			return 0;
 	}
 
+	if (!blkdev_issue_write_same(bdev, sector, nr_sects, gfp_mask,
+			ZERO_PAGE(0)))
+		return 0;
+
 	blk_start_plug(&plug);
 	ret = __blkdev_issue_zeroout(bdev, sector, nr_sects, gfp_mask,
 			&bio, discard);
diff --git a/block/blk-map.c b/block/blk-map.c
index 0acb6640ead7..2f18c2a0be1b 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -16,8 +16,6 @@
 int blk_rq_append_bio(struct request *rq, struct bio *bio)
 {
 	if (!rq->bio) {
-		rq->cmd_flags &= REQ_OP_MASK;
-		rq->cmd_flags |= (bio->bi_opf & REQ_OP_MASK);
 		blk_rq_bio_prep(rq->q, rq, bio);
 	} else {
 		if (!ll_back_merge_fn(rq->q, rq, bio))
@@ -62,6 +60,9 @@ static int __blk_rq_map_user_iov(struct request *rq,
 	if (IS_ERR(bio))
 		return PTR_ERR(bio);
 
+	bio->bi_opf &= ~REQ_OP_MASK;
+	bio->bi_opf |= req_op(rq);
+
 	if (map_data && map_data->null_mapped)
 		bio_set_flag(bio, BIO_NULL_MAPPED);
 
@@ -90,7 +91,7 @@ static int __blk_rq_map_user_iov(struct request *rq,
 }
 
 /**
- * blk_rq_map_user_iov - map user data to a request, for REQ_TYPE_BLOCK_PC usage
+ * blk_rq_map_user_iov - map user data to a request, for passthrough requests
  * @q:		request queue where request should be inserted
  * @rq:		request to map data to
  * @map_data:   pointer to the rq_map_data holding pages (if necessary)
@@ -199,7 +200,7 @@ int blk_rq_unmap_user(struct bio *bio)
 EXPORT_SYMBOL(blk_rq_unmap_user);
 
 /**
- * blk_rq_map_kern - map kernel data to a request, for REQ_TYPE_BLOCK_PC usage
+ * blk_rq_map_kern - map kernel data to a request, for passthrough requests
  * @q:		request queue where request should be inserted
  * @rq:		request to fill
  * @kbuf:	the kernel buffer
@@ -234,8 +235,8 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 	if (IS_ERR(bio))
 		return PTR_ERR(bio);
 
-	if (!reading)
-		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+	bio->bi_opf &= ~REQ_OP_MASK;
+	bio->bi_opf |= req_op(rq);
 
 	if (do_copy)
 		rq->rq_flags |= RQF_COPY_USER;
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 182398cb1524..2afa262425d1 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -482,13 +482,6 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq,
 }
 EXPORT_SYMBOL(blk_rq_map_sg);
 
-static void req_set_nomerge(struct request_queue *q, struct request *req)
-{
-	req->cmd_flags |= REQ_NOMERGE;
-	if (req == q->last_merge)
-		q->last_merge = NULL;
-}
-
 static inline int ll_new_hw_segment(struct request_queue *q,
 				    struct request *req,
 				    struct bio *bio)
@@ -659,31 +652,32 @@ static void blk_account_io_merge(struct request *req)
 }
 
 /*
- * Has to be called with the request spinlock acquired
+ * For non-mq, this has to be called with the request spinlock acquired.
+ * For mq with scheduling, the appropriate queue wide lock should be held.
  */
-static int attempt_merge(struct request_queue *q, struct request *req,
-			  struct request *next)
+static struct request *attempt_merge(struct request_queue *q,
+				     struct request *req, struct request *next)
 {
 	if (!rq_mergeable(req) || !rq_mergeable(next))
-		return 0;
+		return NULL;
 
 	if (req_op(req) != req_op(next))
-		return 0;
+		return NULL;
 
 	/*
 	 * not contiguous
 	 */
 	if (blk_rq_pos(req) + blk_rq_sectors(req) != blk_rq_pos(next))
-		return 0;
+		return NULL;
 
 	if (rq_data_dir(req) != rq_data_dir(next)
 	    || req->rq_disk != next->rq_disk
 	    || req_no_special_merge(next))
-		return 0;
+		return NULL;
 
 	if (req_op(req) == REQ_OP_WRITE_SAME &&
 	    !blk_write_same_mergeable(req->bio, next->bio))
-		return 0;
+		return NULL;
 
 	/*
 	 * If we are allowed to merge, then append bio list
@@ -692,7 +686,7 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 	 * counts here.
 	 */
 	if (!ll_merge_requests_fn(q, req, next))
-		return 0;
+		return NULL;
 
 	/*
 	 * If failfast settings disagree or any of the two is already
@@ -732,42 +726,51 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 	if (blk_rq_cpu_valid(next))
 		req->cpu = next->cpu;
 
-	/* owner-ship of bio passed from next to req */
+	/*
+	 * ownership of bio passed from next to req, return 'next' for
+	 * the caller to free
+	 */
 	next->bio = NULL;
-	__blk_put_request(q, next);
-	return 1;
+	return next;
 }
 
-int attempt_back_merge(struct request_queue *q, struct request *rq)
+struct request *attempt_back_merge(struct request_queue *q, struct request *rq)
 {
 	struct request *next = elv_latter_request(q, rq);
 
 	if (next)
 		return attempt_merge(q, rq, next);
 
-	return 0;
+	return NULL;
 }
 
-int attempt_front_merge(struct request_queue *q, struct request *rq)
+struct request *attempt_front_merge(struct request_queue *q, struct request *rq)
 {
 	struct request *prev = elv_former_request(q, rq);
 
 	if (prev)
 		return attempt_merge(q, prev, rq);
 
-	return 0;
+	return NULL;
 }
 
 int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
 			  struct request *next)
 {
 	struct elevator_queue *e = q->elevator;
+	struct request *free;
 
-	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);
+	free = attempt_merge(q, rq, next);
+	if (free) {
+		__blk_put_request(q, free);
+		return 1;
+	}
+
+	return 0;
 }
 
 bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
@@ -798,9 +801,12 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 	return true;
 }
 
-int blk_try_merge(struct request *rq, struct bio *bio)
+enum elv_merge blk_try_merge(struct request *rq, struct bio *bio)
 {
-	if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_iter.bi_sector)
+	if (req_op(rq) == REQ_OP_DISCARD &&
+	    queue_max_discard_segments(rq->q) > 1)
+		return ELEVATOR_DISCARD_MERGE;
+	else if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_iter.bi_sector)
 		return ELEVATOR_BACK_MERGE;
 	else if (blk_rq_pos(rq) - bio_sectors(bio) == bio->bi_iter.bi_sector)
 		return ELEVATOR_FRONT_MERGE;
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
new file mode 100644
index 000000000000..f6d917977b33
--- /dev/null
+++ b/block/blk-mq-debugfs.c
@@ -0,0 +1,772 @@
+/*
+ * 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.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 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_flags=0x%x, .rq_flags=0x%x, .tag=%d, .internal_tag=%d}\n",
+		   rq, rq->cmd_flags, (__force unsigned int)rq->rq_flags,
+		   rq->tag, rq->internal_tag);
+	return 0;
+}
+
+static void *hctx_dispatch_start(struct seq_file *m, loff_t *pos)
+	__acquires(&hctx->lock)
+{
+	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)
+	__releases(&hctx->lock)
+{
+	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;
+	int res;
+
+	res = mutex_lock_interruptible(&q->sysfs_lock);
+	if (res)
+		goto out;
+	if (hctx->tags)
+		blk_mq_debugfs_tags_show(m, hctx->tags);
+	mutex_unlock(&q->sysfs_lock);
+
+out:
+	return res;
+}
+
+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;
+	int res;
+
+	res = mutex_lock_interruptible(&q->sysfs_lock);
+	if (res)
+		goto out;
+	if (hctx->tags)
+		sbitmap_bitmap_show(&hctx->tags->bitmap_tags.sb, m);
+	mutex_unlock(&q->sysfs_lock);
+
+out:
+	return res;
+}
+
+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;
+	int res;
+
+	res = mutex_lock_interruptible(&q->sysfs_lock);
+	if (res)
+		goto out;
+	if (hctx->sched_tags)
+		blk_mq_debugfs_tags_show(m, hctx->sched_tags);
+	mutex_unlock(&q->sysfs_lock);
+
+out:
+	return res;
+}
+
+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;
+	int res;
+
+	res = mutex_lock_interruptible(&q->sysfs_lock);
+	if (res)
+		goto out;
+	if (hctx->sched_tags)
+		sbitmap_bitmap_show(&hctx->sched_tags->bitmap_tags.sb, m);
+	mutex_unlock(&q->sysfs_lock);
+
+out:
+	return res;
+}
+
+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)
+	__acquires(&ctx->lock)
+{
+	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)
+	__releases(&ctx->lock)
+{
+	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 (!blk_debugfs_root)
+		return -ENOENT;
+
+	q->debugfs_dir = debugfs_create_dir(name, blk_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 bool debugfs_create_files(struct dentry *parent, void *data,
+				const struct blk_mq_debugfs_attr *attr)
+{
+	for (; attr->name; attr++) {
+		if (!debugfs_create_file(attr->name, attr->mode, parent,
+					 data, attr->fops))
+			return false;
+	}
+	return true;
+}
+
+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];
+
+	snprintf(name, sizeof(name), "cpu%u", ctx->cpu);
+	ctx_dir = debugfs_create_dir(name, hctx_dir);
+	if (!ctx_dir)
+		return -ENOMEM;
+
+	if (!debugfs_create_files(ctx_dir, ctx, blk_mq_debugfs_ctx_attrs))
+		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;
+
+	if (!debugfs_create_files(hctx_dir, hctx, blk_mq_debugfs_hctx_attrs))
+		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;
+}
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
new file mode 100644
index 000000000000..98c7b061781e
--- /dev/null
+++ b/block/blk-mq-sched.c
@@ -0,0 +1,502 @@
+/*
+ * 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 bio *bio,
+				      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, bio)) {
+		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, bio, 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;
+	const bool has_sched_dispatch = e && e->type->ops.mq.dispatch_request;
+	bool did_work = false;
+	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(hctx);
+		did_work = blk_mq_dispatch_rq_list(hctx, &rq_list);
+	} else if (!has_sched_dispatch) {
+		blk_mq_flush_busy_ctxs(hctx, &rq_list);
+		blk_mq_dispatch_rq_list(hctx, &rq_list);
+	}
+
+	/*
+	 * We want to dispatch from the scheduler if we had no work left
+	 * on the dispatch list, OR if we did have work but weren't able
+	 * to make progress.
+	 */
+	if (!did_work && has_sched_dispatch) {
+		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 **merged_request)
+{
+	struct request *rq;
+
+	switch (elv_merge(q, &rq, bio)) {
+	case ELEVATOR_BACK_MERGE:
+		if (!blk_mq_sched_allow_merge(q, rq, bio))
+			return false;
+		if (!bio_attempt_back_merge(q, rq, bio))
+			return false;
+		*merged_request = attempt_back_merge(q, rq);
+		if (!*merged_request)
+			elv_merged_request(q, rq, ELEVATOR_BACK_MERGE);
+		return true;
+	case ELEVATOR_FRONT_MERGE:
+		if (!blk_mq_sched_allow_merge(q, rq, bio))
+			return false;
+		if (!bio_attempt_front_merge(q, rq, bio))
+			return false;
+		*merged_request = attempt_front_merge(q, rq);
+		if (!*merged_request)
+			elv_merged_request(q, rq, ELEVATOR_FRONT_MERGE);
+		return true;
+	default:
+		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);
+
+static 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;
+}
+
+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)
+{
+	struct request_queue *q = hctx->queue;
+	unsigned int i;
+
+	if (test_bit(QUEUE_FLAG_RESTART, &q->queue_flags)) {
+		if (test_and_clear_bit(QUEUE_FLAG_RESTART, &q->queue_flags)) {
+			queue_for_each_hw_ctx(q, hctx, i)
+				blk_mq_sched_restart_hctx(hctx);
+		}
+	} else {
+		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, false, 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 && blk_mq_sched_bypass_insert(hctx, rq))
+		goto run;
+
+	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);
+	}
+
+run:
+	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) {
+		struct request *rq, *next;
+
+		/*
+		 * We bypass requests that already have a driver tag assigned,
+		 * which should only be flushes. Flushes are only ever inserted
+		 * as single requests, so we shouldn't ever hit the
+		 * WARN_ON_ONCE() below (but let's handle it just in case).
+		 */
+		list_for_each_entry_safe(rq, next, list, queuelist) {
+			if (WARN_ON_ONCE(rq->tag != -1)) {
+				list_del_init(&rq->queuelist);
+				blk_mq_sched_bypass_insert(hctx, rq);
+			}
+		}
+	}
+
+	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;
+
+	mutex_lock(&q->sysfs_lock);
+	ret = elevator_init(q, NULL);
+	mutex_unlock(&q->sysfs_lock);
+
+	return ret;
+}
diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h
new file mode 100644
index 000000000000..a75b16b123f7
--- /dev/null
+++ b/block/blk-mq-sched.h
@@ -0,0 +1,153 @@
+#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_try_merge(struct request_queue *q, struct bio *bio,
+				struct request **merged_request);
+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 bio *bio)
+{
+	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, bio);
+
+	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;
+}
+
+/*
+ * Mark a hardware queue as needing a restart.
+ */
+static inline void blk_mq_sched_mark_restart_hctx(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);
+}
+
+/*
+ * Mark a hardware queue and the request queue it belongs to as needing a
+ * restart.
+ */
+static inline void blk_mq_sched_mark_restart_queue(struct blk_mq_hw_ctx *hctx)
+{
+	struct request_queue *q = hctx->queue;
+
+	if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
+		set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
+	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
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index eacd3af72099..295e69670c39 100644
--- a/block/blk-mq-sysfs.c
+++ b/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_hctxs(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)
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index dcf5ce3ba4bf..54c84363c1b2 100644
--- a/block/blk-mq-tag.c
+++ b/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;
-}
diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h
index d1662734dc53..63497423c5cd 100644
--- a/block/blk-mq-tag.h
+++ b/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);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index c3400b5444a7..9e6b064e5339 100644
--- a/block/blk-mq.c
+++ b/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 */
@@ -196,13 +199,7 @@ static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
 	rq->special = NULL;
 	/* tag was already set */
 	rq->errors = 0;
-
-	rq->cmd = rq->__cmd;
-
 	rq->extra_len = 0;
-	rq->sense_len = 0;
-	rq->resid_len = 0;
-	rq->sense = NULL;
 
 	INIT_LIST_HEAD(&rq->timeout_list);
 	rq->timeout = 0;
@@ -213,53 +210,58 @@ 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 +321,10 @@ 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 +335,31 @@ 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);
 
@@ -467,11 +477,9 @@ void blk_mq_start_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 
-	trace_block_rq_issue(q, rq);
+	blk_mq_sched_started_request(rq);
 
-	rq->resid_len = blk_rq_bytes(rq);
-	if (unlikely(blk_bidi_rq(rq)))
-		rq->next_rq->resid_len = blk_rq_bytes(rq->next_rq);
+	trace_block_rq_issue(q, rq);
 
 	if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
 		blk_stat_set_issue_time(&rq->issue_stat);
@@ -515,6 +523,7 @@ 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 +558,13 @@ 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 +648,7 @@ 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;
 
 	/*
@@ -754,7 +763,7 @@ static bool blk_mq_attempt_merge(struct request_queue *q,
 	int checked = 8;
 
 	list_for_each_entry_reverse(rq, &ctx->rq_list, queuelist) {
-		int el_ret;
+		bool merged = false;
 
 		if (!checked--)
 			break;
@@ -762,20 +771,25 @@ static bool blk_mq_attempt_merge(struct request_queue *q,
 		if (!blk_rq_merge_ok(rq, bio))
 			continue;
 
-		el_ret = blk_try_merge(rq, bio);
-		if (el_ret == ELEVATOR_BACK_MERGE) {
-			if (bio_attempt_back_merge(q, rq, bio)) {
-				ctx->rq_merged++;
-				return true;
-			}
+		switch (blk_try_merge(rq, bio)) {
+		case ELEVATOR_BACK_MERGE:
+			if (blk_mq_sched_allow_merge(q, rq, bio))
+				merged = bio_attempt_back_merge(q, rq, bio);
 			break;
-		} else if (el_ret == ELEVATOR_FRONT_MERGE) {
-			if (bio_attempt_front_merge(q, rq, bio)) {
-				ctx->rq_merged++;
-				return true;
-			}
+		case ELEVATOR_FRONT_MERGE:
+			if (blk_mq_sched_allow_merge(q, rq, bio))
+				merged = bio_attempt_front_merge(q, rq, bio);
 			break;
+		case ELEVATOR_DISCARD_MERGE:
+			merged = bio_attempt_discard_merge(q, rq, bio);
+			break;
+		default:
+			continue;
 		}
+
+		if (merged)
+			ctx->rq_merged++;
+		return merged;
 	}
 
 	return false;
@@ -803,7 +817,7 @@ 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 +826,7 @@ 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 +836,112 @@ 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 (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;
+}
+
+static int blk_mq_dispatch_wake(wait_queue_t *wait, unsigned mode, int flags,
+				void *key)
+{
+	struct blk_mq_hw_ctx *hctx;
+
+	hctx = container_of(wait, struct blk_mq_hw_ctx, dispatch_wait);
+
+	list_del(&wait->task_list);
+	clear_bit_unlock(BLK_MQ_S_TAG_WAITING, &hctx->state);
+	blk_mq_run_hw_queue(hctx, true);
+	return 1;
+}
+
+static bool blk_mq_dispatch_wait_add(struct blk_mq_hw_ctx *hctx)
+{
+	struct sbq_wait_state *ws;
+
+	/*
+	 * The TAG_WAITING bit serves as a lock protecting hctx->dispatch_wait.
+	 * The thread which wins the race to grab this bit adds the hardware
+	 * queue to the wait queue.
+	 */
+	if (test_bit(BLK_MQ_S_TAG_WAITING, &hctx->state) ||
+	    test_and_set_bit_lock(BLK_MQ_S_TAG_WAITING, &hctx->state))
+		return false;
+
+	init_waitqueue_func_entry(&hctx->dispatch_wait, blk_mq_dispatch_wake);
+	ws = bt_wait_ptr(&hctx->tags->bitmap_tags, hctx);
+
+	/*
+	 * As soon as this returns, it's no longer safe to fiddle with
+	 * hctx->dispatch_wait, since a completion can wake up the wait queue
+	 * and unlock the bit.
+	 */
+	add_wait_queue(&ws->wait, &hctx->dispatch_wait);
+	return true;
+}
+
 bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 {
 	struct request_queue *q = hctx->queue;
@@ -843,6 +964,27 @@ 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;
+
+			/*
+			 * The initial allocation attempt failed, so we need to
+			 * rerun the hardware queue when a tag is freed.
+			 */
+			if (blk_mq_dispatch_wait_add(hctx)) {
+				/*
+				 * It's possible that a tag was freed in the
+				 * window between the allocation failure and
+				 * adding the hardware queue to the wait queue.
+				 */
+				if (!blk_mq_get_driver_tag(rq, &hctx, false))
+					break;
+			} else {
+				break;
+			}
+		}
+
 		list_del_init(&rq->queuelist);
 
 		bd.rq = rq;
@@ -855,6 +997,7 @@ 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 +1028,7 @@ 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);
 
 		/*
@@ -896,45 +1039,16 @@ 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);
-	}
-
-	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);
+		 *
+		 * If RESTART or TAG_WAITING is set, then let completion restart
+		 * the queue instead of potentially looping here.
+		 */
+		if (!blk_mq_sched_needs_restart(hctx) &&
+		    !test_bit(BLK_MQ_S_TAG_WAITING, &hctx->state))
+			blk_mq_run_hw_queue(hctx, true);
 	}
 
-	blk_mq_dispatch_rq_list(hctx, &rq_list);
+	return queued != 0;
 }
 
 static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
@@ -946,11 +1060,11 @@ 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 +1120,7 @@ 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 +1229,7 @@ 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 +1249,8 @@ 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 +1258,10 @@ 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 +1277,6 @@ 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 +1312,10 @@ 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 +1332,9 @@ 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 +1372,39 @@ 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);
+	if (rq->tag != -1)
+		return blk_tag_to_qc_t(rq->tag, hctx->queue_num, false);
 
-	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);
-
-	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 +1426,7 @@ 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 +1437,8 @@ 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 +1459,14 @@ 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;
@@ -1384,9 +1474,11 @@ 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)) {
+		if (q->elevator)
+			goto elv_insert;
 		blk_mq_bio_to_request(rq, bio);
 		blk_insert_flush(rq);
 		goto run_queue;
@@ -1438,6 +1530,14 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		goto done;
 	}
 
+	if (q->elevator) {
+elv_insert:
+		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
@@ -1460,10 +1560,10 @@ 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 +1583,14 @@ 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;
@@ -1493,9 +1598,11 @@ 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)) {
+		if (q->elevator)
+			goto elv_insert;
 		blk_mq_bio_to_request(rq, bio);
 		blk_insert_flush(rq);
 		goto run_queue;
@@ -1535,6 +1642,14 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 		return cookie;
 	}
 
+	if (q->elevator) {
+elv_insert:
+		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
@@ -1547,11 +1662,12 @@ run_queue:
 	}
 
 	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 +1675,13 @@ 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 +1695,32 @@ 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 +1728,40 @@ 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 +1795,17 @@ 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 +1814,11 @@ 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 +2010,35 @@ 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 +2067,15 @@ 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 +2098,9 @@ 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 +2193,8 @@ 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 +2269,8 @@ 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 +2351,14 @@ 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 +2457,10 @@ 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 +2474,15 @@ 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 +2606,8 @@ 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 +2623,28 @@ 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 +2652,9 @@ 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;
 }
 
@@ -2483,10 +2674,14 @@ void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
 		blk_mq_realloc_hw_ctxs(set, q);
 
+		/*
+		 * Manually set the make_request_fn as blk_queue_make_request
+		 * resets a lot of the queue settings.
+		 */
 		if (q->nr_hw_queues > 1)
-			blk_queue_make_request(q, blk_mq_make_request);
+			q->make_request_fn = blk_mq_make_request;
 		else
-			blk_queue_make_request(q, blk_sq_make_request);
+			q->make_request_fn = blk_sq_make_request;
 
 		blk_mq_queue_reinit(q, cpu_online_mask);
 	}
@@ -2649,7 +2844,10 @@ 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);
 }
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 63e9116cddbd..24b2256186f3 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -32,8 +32,32 @@ 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
  */
 void blk_mq_enable_hotplug(void);
@@ -57,6 +81,35 @@ 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
+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 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 +156,25 @@ 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);
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 529e55f52a03..1e7174ffc9d4 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -88,6 +88,7 @@ EXPORT_SYMBOL_GPL(blk_queue_lld_busy);
 void blk_set_default_limits(struct queue_limits *lim)
 {
 	lim->max_segments = BLK_MAX_SEGMENTS;
+	lim->max_discard_segments = 1;
 	lim->max_integrity_segments = 0;
 	lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
 	lim->virt_boundary_mask = 0;
@@ -128,6 +129,7 @@ void blk_set_stacking_limits(struct queue_limits *lim)
 	/* Inherit limits from component devices */
 	lim->discard_zeroes_data = 1;
 	lim->max_segments = USHRT_MAX;
+	lim->max_discard_segments = 1;
 	lim->max_hw_sectors = UINT_MAX;
 	lim->max_segment_size = UINT_MAX;
 	lim->max_sectors = UINT_MAX;
@@ -253,7 +255,7 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_secto
 	max_sectors = min_not_zero(max_hw_sectors, limits->max_dev_sectors);
 	max_sectors = min_t(unsigned int, max_sectors, BLK_DEF_MAX_SECTORS);
 	limits->max_sectors = max_sectors;
-	q->backing_dev_info.io_pages = max_sectors >> (PAGE_SHIFT - 9);
+	q->backing_dev_info->io_pages = max_sectors >> (PAGE_SHIFT - 9);
 }
 EXPORT_SYMBOL(blk_queue_max_hw_sectors);
 
@@ -337,6 +339,22 @@ void blk_queue_max_segments(struct request_queue *q, unsigned short max_segments
 EXPORT_SYMBOL(blk_queue_max_segments);
 
 /**
+ * blk_queue_max_discard_segments - set max segments for discard requests
+ * @q:  the request queue for the device
+ * @max_segments:  max number of segments
+ *
+ * Description:
+ *    Enables a low level driver to set an upper limit on the number of
+ *    segments in a discard request.
+ **/
+void blk_queue_max_discard_segments(struct request_queue *q,
+		unsigned short max_segments)
+{
+	q->limits.max_discard_segments = max_segments;
+}
+EXPORT_SYMBOL_GPL(blk_queue_max_discard_segments);
+
+/**
  * blk_queue_max_segment_size - set max segment size for blk_rq_map_sg
  * @q:  the request queue for the device
  * @max_size:  max size of segment in bytes
@@ -553,6 +571,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 					    b->virt_boundary_mask);
 
 	t->max_segments = min_not_zero(t->max_segments, b->max_segments);
+	t->max_discard_segments = min_not_zero(t->max_discard_segments,
+					       b->max_discard_segments);
 	t->max_integrity_segments = min_not_zero(t->max_integrity_segments,
 						 b->max_integrity_segments);
 
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 1dbce057592d..002af836aa87 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -89,7 +89,7 @@ queue_requests_store(struct request_queue *q, const char *page, size_t count)
 
 static ssize_t queue_ra_show(struct request_queue *q, char *page)
 {
-	unsigned long ra_kb = q->backing_dev_info.ra_pages <<
+	unsigned long ra_kb = q->backing_dev_info->ra_pages <<
 					(PAGE_SHIFT - 10);
 
 	return queue_var_show(ra_kb, (page));
@@ -104,7 +104,7 @@ queue_ra_store(struct request_queue *q, const char *page, size_t count)
 	if (ret < 0)
 		return ret;
 
-	q->backing_dev_info.ra_pages = ra_kb >> (PAGE_SHIFT - 10);
+	q->backing_dev_info->ra_pages = ra_kb >> (PAGE_SHIFT - 10);
 
 	return ret;
 }
@@ -121,6 +121,12 @@ static ssize_t queue_max_segments_show(struct request_queue *q, char *page)
 	return queue_var_show(queue_max_segments(q), (page));
 }
 
+static ssize_t queue_max_discard_segments_show(struct request_queue *q,
+		char *page)
+{
+	return queue_var_show(queue_max_discard_segments(q), (page));
+}
+
 static ssize_t queue_max_integrity_segments_show(struct request_queue *q, char *page)
 {
 	return queue_var_show(q->limits.max_integrity_segments, (page));
@@ -236,7 +242,7 @@ queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
 
 	spin_lock_irq(q->queue_lock);
 	q->limits.max_sectors = max_sectors_kb << 1;
-	q->backing_dev_info.io_pages = max_sectors_kb >> (PAGE_SHIFT - 10);
+	q->backing_dev_info->io_pages = max_sectors_kb >> (PAGE_SHIFT - 10);
 	spin_unlock_irq(q->queue_lock);
 
 	return ret;
@@ -545,6 +551,11 @@ static struct queue_sysfs_entry queue_max_segments_entry = {
 	.show = queue_max_segments_show,
 };
 
+static struct queue_sysfs_entry queue_max_discard_segments_entry = {
+	.attr = {.name = "max_discard_segments", .mode = S_IRUGO },
+	.show = queue_max_discard_segments_show,
+};
+
 static struct queue_sysfs_entry queue_max_integrity_segments_entry = {
 	.attr = {.name = "max_integrity_segments", .mode = S_IRUGO },
 	.show = queue_max_integrity_segments_show,
@@ -697,6 +708,7 @@ static struct attribute *default_attrs[] = {
 	&queue_max_hw_sectors_entry.attr,
 	&queue_max_sectors_entry.attr,
 	&queue_max_segments_entry.attr,
+	&queue_max_discard_segments_entry.attr,
 	&queue_max_integrity_segments_entry.attr,
 	&queue_max_segment_size_entry.attr,
 	&queue_iosched_entry.attr,
@@ -799,7 +811,7 @@ static void blk_release_queue(struct kobject *kobj)
 		container_of(kobj, struct request_queue, kobj);
 
 	wbt_exit(q);
-	bdi_exit(&q->backing_dev_info);
+	bdi_put(q->backing_dev_info);
 	blkcg_exit_queue(q);
 
 	if (q->elevator) {
@@ -814,13 +826,19 @@ static void blk_release_queue(struct kobject *kobj)
 	if (q->queue_tags)
 		__blk_queue_free_tags(q);
 
-	if (!q->mq_ops)
+	if (!q->mq_ops) {
+		if (q->exit_rq_fn)
+			q->exit_rq_fn(q, q->fq->flush_rq);
 		blk_free_flush_queue(q->fq);
-	else
+	} else {
 		blk_mq_release(q);
+	}
 
 	blk_trace_shutdown(q);
 
+	if (q->mq_ops)
+		blk_mq_debugfs_unregister(q);
+
 	if (q->bio_split)
 		bioset_free(q->bio_split);
 
@@ -884,32 +902,36 @@ int blk_register_queue(struct gendisk *disk)
 	if (ret)
 		return ret;
 
+	if (q->mq_ops)
+		blk_mq_register_dev(dev, q);
+
+	/* Prevent changes through sysfs until registration is completed. */
+	mutex_lock(&q->sysfs_lock);
+
 	ret = kobject_add(&q->kobj, kobject_get(&dev->kobj), "%s", "queue");
 	if (ret < 0) {
 		blk_trace_remove_sysfs(dev);
-		return ret;
+		goto unlock;
 	}
 
 	kobject_uevent(&q->kobj, KOBJ_ADD);
 
-	if (q->mq_ops)
-		blk_mq_register_dev(dev, q);
-
 	blk_wb_init(q);
 
-	if (!q->request_fn)
-		return 0;
-
-	ret = elv_register_queue(q);
-	if (ret) {
-		kobject_uevent(&q->kobj, KOBJ_REMOVE);
-		kobject_del(&q->kobj);
-		blk_trace_remove_sysfs(dev);
-		kobject_put(&dev->kobj);
-		return ret;
+	if (q->request_fn || (q->mq_ops && q->elevator)) {
+		ret = elv_register_queue(q);
+		if (ret) {
+			kobject_uevent(&q->kobj, KOBJ_REMOVE);
+			kobject_del(&q->kobj);
+			blk_trace_remove_sysfs(dev);
+			kobject_put(&dev->kobj);
+			goto unlock;
+		}
 	}
-
-	return 0;
+	ret = 0;
+unlock:
+	mutex_unlock(&q->sysfs_lock);
+	return ret;
 }
 
 void blk_unregister_queue(struct gendisk *disk)
@@ -922,7 +944,7 @@ void blk_unregister_queue(struct gendisk *disk)
 	if (q->mq_ops)
 		blk_mq_unregister_dev(disk_to_dev(disk), q);
 
-	if (q->request_fn)
+	if (q->request_fn || (q->mq_ops && q->elevator))
 		elv_unregister_queue(q);
 
 	kobject_uevent(&q->kobj, KOBJ_REMOVE);
diff --git a/block/blk-tag.c b/block/blk-tag.c
index bae1decb6ec3..07cc329fa4b0 100644
--- a/block/blk-tag.c
+++ b/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",
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index a6bb4fe326c3..8fab716e4059 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -185,7 +185,7 @@ static struct throtl_grp *sq_to_tg(struct throtl_service_queue *sq)
  * sq_to_td - return throtl_data the specified service queue belongs to
  * @sq: the throtl_service_queue of interest
  *
- * A service_queue can be embeded in either a throtl_grp or throtl_data.
+ * A service_queue can be embedded in either a throtl_grp or throtl_data.
  * Determine the associated throtl_data accordingly and return it.
  */
 static struct throtl_data *sq_to_td(struct throtl_service_queue *sq)
@@ -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);
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index f0a9c07b4c7a..1aedb1f7ee0c 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -96,7 +96,7 @@ static void wb_timestamp(struct rq_wb *rwb, unsigned long *var)
  */
 static bool wb_recent_wait(struct rq_wb *rwb)
 {
-	struct bdi_writeback *wb = &rwb->queue->backing_dev_info.wb;
+	struct bdi_writeback *wb = &rwb->queue->backing_dev_info->wb;
 
 	return time_before(jiffies, wb->dirty_sleep + HZ);
 }
@@ -279,7 +279,7 @@ enum {
 
 static int __latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat)
 {
-	struct backing_dev_info *bdi = &rwb->queue->backing_dev_info;
+	struct backing_dev_info *bdi = rwb->queue->backing_dev_info;
 	u64 thislat;
 
 	/*
@@ -339,7 +339,7 @@ static int latency_exceeded(struct rq_wb *rwb)
 
 static void rwb_trace_step(struct rq_wb *rwb, const char *msg)
 {
-	struct backing_dev_info *bdi = &rwb->queue->backing_dev_info;
+	struct backing_dev_info *bdi = rwb->queue->backing_dev_info;
 
 	trace_wbt_step(bdi, msg, rwb->scale_step, rwb->cur_win_nsec,
 			rwb->wb_background, rwb->wb_normal, rwb->wb_max);
@@ -423,7 +423,7 @@ static void wb_timer_fn(unsigned long data)
 
 	status = latency_exceeded(rwb);
 
-	trace_wbt_timer(&rwb->queue->backing_dev_info, status, rwb->scale_step,
+	trace_wbt_timer(rwb->queue->backing_dev_info, status, rwb->scale_step,
 			inflight);
 
 	/*
diff --git a/block/blk.h b/block/blk.h
index 041185e5f129..d1ea4bd9b9a3 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -14,6 +14,10 @@
 /* Max future timer expiry for timeouts */
 #define BLK_MAX_TIMEOUT		(5 * HZ)
 
+#ifdef CONFIG_DEBUG_FS
+extern struct dentry *blk_debugfs_root;
+#endif
+
 struct blk_flush_queue {
 	unsigned int		flush_queue_delayed:1;
 	unsigned int		flush_pending_idx:1;
@@ -96,6 +100,8 @@ bool bio_attempt_front_merge(struct request_queue *q, struct request *req,
 			     struct bio *bio);
 bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
 			    struct bio *bio);
+bool bio_attempt_discard_merge(struct request_queue *q, struct request *req,
+		struct bio *bio);
 bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 			    unsigned int *request_count,
 			    struct request **same_queue_rq);
@@ -167,7 +173,7 @@ 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 +182,16 @@ 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
@@ -204,14 +210,14 @@ int ll_back_merge_fn(struct request_queue *q, struct request *req,
 		     struct bio *bio);
 int ll_front_merge_fn(struct request_queue *q, struct request *req, 
 		      struct bio *bio);
-int attempt_back_merge(struct request_queue *q, struct request *rq);
-int attempt_front_merge(struct request_queue *q, struct request *rq);
+struct request *attempt_back_merge(struct request_queue *q, struct request *rq);
+struct request *attempt_front_merge(struct request_queue *q, struct request *rq);
 int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
 				struct request *next);
 void blk_recalc_rq_segments(struct request *rq);
 void blk_rq_set_mixed_merge(struct request *rq);
 bool blk_rq_merge_ok(struct request *rq, struct bio *bio);
-int blk_try_merge(struct request *rq, struct bio *bio);
+enum elv_merge blk_try_merge(struct request *rq, struct bio *bio);
 
 void blk_queue_congestion_threshold(struct request_queue *q);
 
@@ -249,7 +255,14 @@ static inline int blk_do_io_stat(struct request *rq)
 {
 	return rq->rq_disk &&
 	       (rq->rq_flags & RQF_IO_STAT) &&
-		(rq->cmd_type == REQ_TYPE_FS);
+		!blk_rq_is_passthrough(rq);
+}
+
+static inline void req_set_nomerge(struct request_queue *q, struct request *req)
+{
+	req->cmd_flags |= REQ_NOMERGE;
+	if (req == q->last_merge)
+		q->last_merge = NULL;
 }
 
 /*
@@ -264,6 +277,22 @@ 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
  * @node: allocation node
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index 9d652a992316..cd15f9dbb147 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -71,22 +71,24 @@ void bsg_job_done(struct bsg_job *job, int result,
 {
 	struct request *req = job->req;
 	struct request *rsp = req->next_rq;
+	struct scsi_request *rq = scsi_req(req);
 	int err;
 
 	err = job->req->errors = result;
 	if (err < 0)
 		/* we're only returning the result field in the reply */
-		job->req->sense_len = sizeof(u32);
+		rq->sense_len = sizeof(u32);
 	else
-		job->req->sense_len = job->reply_len;
+		rq->sense_len = job->reply_len;
 	/* we assume all request payload was transferred, residual == 0 */
-	req->resid_len = 0;
+	rq->resid_len = 0;
 
 	if (rsp) {
-		WARN_ON(reply_payload_rcv_len > rsp->resid_len);
+		WARN_ON(reply_payload_rcv_len > scsi_req(rsp)->resid_len);
 
 		/* set reply (bidi) residual */
-		rsp->resid_len -= min(reply_payload_rcv_len, rsp->resid_len);
+		scsi_req(rsp)->resid_len -=
+			min(reply_payload_rcv_len, scsi_req(rsp)->resid_len);
 	}
 	blk_complete_request(req);
 }
@@ -113,6 +115,7 @@ static int bsg_map_buffer(struct bsg_buffer *buf, struct request *req)
 	if (!buf->sg_list)
 		return -ENOMEM;
 	sg_init_table(buf->sg_list, req->nr_phys_segments);
+	scsi_req(req)->resid_len = blk_rq_bytes(req);
 	buf->sg_cnt = blk_rq_map_sg(req->q, req, buf->sg_list);
 	buf->payload_len = blk_rq_bytes(req);
 	return 0;
@@ -127,6 +130,7 @@ static int bsg_create_job(struct device *dev, struct request *req)
 {
 	struct request *rsp = req->next_rq;
 	struct request_queue *q = req->q;
+	struct scsi_request *rq = scsi_req(req);
 	struct bsg_job *job;
 	int ret;
 
@@ -140,9 +144,9 @@ static int bsg_create_job(struct device *dev, struct request *req)
 	job->req = req;
 	if (q->bsg_job_size)
 		job->dd_data = (void *)&job[1];
-	job->request = req->cmd;
-	job->request_len = req->cmd_len;
-	job->reply = req->sense;
+	job->request = rq->cmd;
+	job->request_len = rq->cmd_len;
+	job->reply = rq->sense;
 	job->reply_len = SCSI_SENSE_BUFFERSIZE;	/* Size of sense buffer
 						 * allocated */
 	if (req->bio) {
@@ -177,7 +181,7 @@ failjob_rls_job:
  *
  * Drivers/subsys should pass this to the queue init function.
  */
-void bsg_request_fn(struct request_queue *q)
+static void bsg_request_fn(struct request_queue *q)
 	__releases(q->queue_lock)
 	__acquires(q->queue_lock)
 {
@@ -214,24 +218,30 @@ void bsg_request_fn(struct request_queue *q)
 	put_device(dev);
 	spin_lock_irq(q->queue_lock);
 }
-EXPORT_SYMBOL_GPL(bsg_request_fn);
 
 /**
  * bsg_setup_queue - Create and add the bsg hooks so we can receive requests
  * @dev: device to attach bsg device to
- * @q: request queue setup by caller
  * @name: device to give bsg device
  * @job_fn: bsg job handler
  * @dd_job_size: size of LLD data needed for each job
- *
- * The caller should have setup the reuqest queue with bsg_request_fn
- * as the request_fn.
  */
-int bsg_setup_queue(struct device *dev, struct request_queue *q,
-		    char *name, bsg_job_fn *job_fn, int dd_job_size)
+struct request_queue *bsg_setup_queue(struct device *dev, char *name,
+		bsg_job_fn *job_fn, int dd_job_size)
 {
+	struct request_queue *q;
 	int ret;
 
+	q = blk_alloc_queue(GFP_KERNEL);
+	if (!q)
+		return ERR_PTR(-ENOMEM);
+	q->cmd_size = sizeof(struct scsi_request);
+	q->request_fn = bsg_request_fn;
+
+	ret = blk_init_allocated_queue(q);
+	if (ret)
+		goto out_cleanup_queue;
+
 	q->queuedata = dev;
 	q->bsg_job_size = dd_job_size;
 	q->bsg_job_fn = job_fn;
@@ -243,9 +253,12 @@ int bsg_setup_queue(struct device *dev, struct request_queue *q,
 	if (ret) {
 		printk(KERN_ERR "%s: bsg interface failed to "
 		       "initialize - register queue\n", dev->kobj.name);
-		return ret;
+		goto out_cleanup_queue;
 	}
 
-	return 0;
+	return q;
+out_cleanup_queue:
+	blk_cleanup_queue(q);
+	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(bsg_setup_queue);
diff --git a/block/bsg.c b/block/bsg.c
index a57046de2f07..74835dbf0c47 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -85,7 +85,6 @@ struct bsg_command {
 	struct bio *bidi_bio;
 	int err;
 	struct sg_io_v4 hdr;
-	char sense[SCSI_SENSE_BUFFERSIZE];
 };
 
 static void bsg_free_command(struct bsg_command *bc)
@@ -140,18 +139,20 @@ static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq,
 				struct sg_io_v4 *hdr, struct bsg_device *bd,
 				fmode_t has_write_perm)
 {
+	struct scsi_request *req = scsi_req(rq);
+
 	if (hdr->request_len > BLK_MAX_CDB) {
-		rq->cmd = kzalloc(hdr->request_len, GFP_KERNEL);
-		if (!rq->cmd)
+		req->cmd = kzalloc(hdr->request_len, GFP_KERNEL);
+		if (!req->cmd)
 			return -ENOMEM;
 	}
 
-	if (copy_from_user(rq->cmd, (void __user *)(unsigned long)hdr->request,
+	if (copy_from_user(req->cmd, (void __user *)(unsigned long)hdr->request,
 			   hdr->request_len))
 		return -EFAULT;
 
 	if (hdr->subprotocol == BSG_SUB_PROTOCOL_SCSI_CMD) {
-		if (blk_verify_command(rq->cmd, has_write_perm))
+		if (blk_verify_command(req->cmd, has_write_perm))
 			return -EPERM;
 	} else if (!capable(CAP_SYS_RAWIO))
 		return -EPERM;
@@ -159,7 +160,7 @@ static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq,
 	/*
 	 * fill in request structure
 	 */
-	rq->cmd_len = hdr->request_len;
+	req->cmd_len = hdr->request_len;
 
 	rq->timeout = msecs_to_jiffies(hdr->timeout);
 	if (!rq->timeout)
@@ -176,7 +177,7 @@ static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq,
  * Check if sg_io_v4 from user is allowed and valid
  */
 static int
-bsg_validate_sgv4_hdr(struct sg_io_v4 *hdr, int *rw)
+bsg_validate_sgv4_hdr(struct sg_io_v4 *hdr, int *op)
 {
 	int ret = 0;
 
@@ -197,7 +198,7 @@ bsg_validate_sgv4_hdr(struct sg_io_v4 *hdr, int *rw)
 		ret = -EINVAL;
 	}
 
-	*rw = hdr->dout_xfer_len ? WRITE : READ;
+	*op = hdr->dout_xfer_len ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN;
 	return ret;
 }
 
@@ -205,13 +206,12 @@ bsg_validate_sgv4_hdr(struct sg_io_v4 *hdr, int *rw)
  * map sg_io_v4 to a request.
  */
 static struct request *
-bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm,
-	    u8 *sense)
+bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm)
 {
 	struct request_queue *q = bd->queue;
 	struct request *rq, *next_rq = NULL;
-	int ret, rw;
-	unsigned int dxfer_len;
+	int ret;
+	unsigned int op, dxfer_len;
 	void __user *dxferp = NULL;
 	struct bsg_class_device *bcd = &q->bsg_dev;
 
@@ -226,36 +226,35 @@ bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm,
 		hdr->dout_xfer_len, (unsigned long long) hdr->din_xferp,
 		hdr->din_xfer_len);
 
-	ret = bsg_validate_sgv4_hdr(hdr, &rw);
+	ret = bsg_validate_sgv4_hdr(hdr, &op);
 	if (ret)
 		return ERR_PTR(ret);
 
 	/*
 	 * map scatter-gather elements separately and string them to request
 	 */
-	rq = blk_get_request(q, rw, GFP_KERNEL);
+	rq = blk_get_request(q, op, GFP_KERNEL);
 	if (IS_ERR(rq))
 		return rq;
-	blk_rq_set_block_pc(rq);
+	scsi_req_init(rq);
 
 	ret = blk_fill_sgv4_hdr_rq(q, rq, hdr, bd, has_write_perm);
 	if (ret)
 		goto out;
 
-	if (rw == WRITE && hdr->din_xfer_len) {
+	if (op == REQ_OP_SCSI_OUT && hdr->din_xfer_len) {
 		if (!test_bit(QUEUE_FLAG_BIDI, &q->queue_flags)) {
 			ret = -EOPNOTSUPP;
 			goto out;
 		}
 
-		next_rq = blk_get_request(q, READ, GFP_KERNEL);
+		next_rq = blk_get_request(q, REQ_OP_SCSI_IN, GFP_KERNEL);
 		if (IS_ERR(next_rq)) {
 			ret = PTR_ERR(next_rq);
 			next_rq = NULL;
 			goto out;
 		}
 		rq->next_rq = next_rq;
-		next_rq->cmd_type = rq->cmd_type;
 
 		dxferp = (void __user *)(unsigned long)hdr->din_xferp;
 		ret =  blk_rq_map_user(q, next_rq, NULL, dxferp,
@@ -280,13 +279,9 @@ bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm,
 			goto out;
 	}
 
-	rq->sense = sense;
-	rq->sense_len = 0;
-
 	return rq;
 out:
-	if (rq->cmd != rq->__cmd)
-		kfree(rq->cmd);
+	scsi_req_free_cmd(scsi_req(rq));
 	blk_put_request(rq);
 	if (next_rq) {
 		blk_rq_unmap_user(next_rq->bio);
@@ -393,6 +388,7 @@ static struct bsg_command *bsg_get_done_cmd(struct bsg_device *bd)
 static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 				    struct bio *bio, struct bio *bidi_bio)
 {
+	struct scsi_request *req = scsi_req(rq);
 	int ret = 0;
 
 	dprintk("rq %p bio %p 0x%x\n", rq, bio, rq->errors);
@@ -407,12 +403,12 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 		hdr->info |= SG_INFO_CHECK;
 	hdr->response_len = 0;
 
-	if (rq->sense_len && hdr->response) {
+	if (req->sense_len && hdr->response) {
 		int len = min_t(unsigned int, hdr->max_response_len,
-					rq->sense_len);
+					req->sense_len);
 
 		ret = copy_to_user((void __user *)(unsigned long)hdr->response,
-				   rq->sense, len);
+				   req->sense, len);
 		if (!ret)
 			hdr->response_len = len;
 		else
@@ -420,14 +416,14 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 	}
 
 	if (rq->next_rq) {
-		hdr->dout_resid = rq->resid_len;
-		hdr->din_resid = rq->next_rq->resid_len;
+		hdr->dout_resid = req->resid_len;
+		hdr->din_resid = scsi_req(rq->next_rq)->resid_len;
 		blk_rq_unmap_user(bidi_bio);
 		blk_put_request(rq->next_rq);
 	} else if (rq_data_dir(rq) == READ)
-		hdr->din_resid = rq->resid_len;
+		hdr->din_resid = req->resid_len;
 	else
-		hdr->dout_resid = rq->resid_len;
+		hdr->dout_resid = req->resid_len;
 
 	/*
 	 * If the request generated a negative error number, return it
@@ -439,8 +435,7 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 		ret = rq->errors;
 
 	blk_rq_unmap_user(bio);
-	if (rq->cmd != rq->__cmd)
-		kfree(rq->cmd);
+	scsi_req_free_cmd(req);
 	blk_put_request(rq);
 
 	return ret;
@@ -578,7 +573,7 @@ bsg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 	int ret;
 	ssize_t bytes_read;
 
-	dprintk("%s: read %Zd bytes\n", bd->name, count);
+	dprintk("%s: read %zd bytes\n", bd->name, count);
 
 	bsg_set_block(bd, file);
 
@@ -625,7 +620,7 @@ static int __bsg_write(struct bsg_device *bd, const char __user *buf,
 		/*
 		 * get a request, fill in the blanks, and add to request queue
 		 */
-		rq = bsg_map_hdr(bd, &bc->hdr, has_write_perm, bc->sense);
+		rq = bsg_map_hdr(bd, &bc->hdr, has_write_perm);
 		if (IS_ERR(rq)) {
 			ret = PTR_ERR(rq);
 			rq = NULL;
@@ -653,7 +648,7 @@ bsg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
 	ssize_t bytes_written;
 	int ret;
 
-	dprintk("%s: write %Zd bytes\n", bd->name, count);
+	dprintk("%s: write %zd bytes\n", bd->name, count);
 
 	if (unlikely(segment_eq(get_fs(), KERNEL_DS)))
 		return -EINVAL;
@@ -672,7 +667,7 @@ bsg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
 	if (!bytes_written || err_block_err(ret))
 		bytes_written = ret;
 
-	dprintk("%s: returning %Zd\n", bd->name, bytes_written);
+	dprintk("%s: returning %zd\n", bd->name, bytes_written);
 	return bytes_written;
 }
 
@@ -911,12 +906,11 @@ static long bsg_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		struct bio *bio, *bidi_bio = NULL;
 		struct sg_io_v4 hdr;
 		int at_head;
-		u8 sense[SCSI_SENSE_BUFFERSIZE];
 
 		if (copy_from_user(&hdr, uarg, sizeof(hdr)))
 			return -EFAULT;
 
-		rq = bsg_map_hdr(bd, &hdr, file->f_mode & FMODE_WRITE, sense);
+		rq = bsg_map_hdr(bd, &hdr, file->f_mode & FMODE_WRITE);
 		if (IS_ERR(rq))
 			return PTR_ERR(rq);
 
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index c73a6fcaeb9d..137944777859 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -2528,7 +2528,7 @@ static void cfq_remove_request(struct request *rq)
 	}
 }
 
-static int cfq_merge(struct request_queue *q, struct request **req,
+static enum elv_merge cfq_merge(struct request_queue *q, struct request **req,
 		     struct bio *bio)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
@@ -2544,7 +2544,7 @@ static int cfq_merge(struct request_queue *q, struct request **req,
 }
 
 static void cfq_merged_request(struct request_queue *q, struct request *req,
-			       int type)
+			       enum elv_merge type)
 {
 	if (type == ELEVATOR_FRONT_MERGE) {
 		struct cfq_queue *cfqq = RQ_CFQQ(req);
@@ -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;
 }
 
@@ -3758,7 +3760,7 @@ static void cfq_init_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 }
 
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
-static void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
+static bool check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
 {
 	struct cfq_data *cfqd = cic_to_cfqd(cic);
 	struct cfq_queue *cfqq;
@@ -3775,15 +3777,7 @@ static void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
 	 * spuriously on a newly created cic but there's no harm.
 	 */
 	if (unlikely(!cfqd) || likely(cic->blkcg_serial_nr == serial_nr))
-		return;
-
-	/*
-	 * If we have a non-root cgroup, we can depend on that to
-	 * do proper throttling of writes. Turn off wbt for that
-	 * case, if it was enabled by default.
-	 */
-	if (nonroot_cg)
-		wbt_disable_default(cfqd->queue);
+		return nonroot_cg;
 
 	/*
 	 * Drop reference to queues.  New queues will be assigned in new
@@ -3804,9 +3798,13 @@ static void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
 	}
 
 	cic->blkcg_serial_nr = serial_nr;
+	return nonroot_cg;
 }
 #else
-static inline void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio) { }
+static inline bool check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
+{
+	return false;
+}
 #endif  /* CONFIG_CFQ_GROUP_IOSCHED */
 
 static struct cfq_queue **
@@ -3864,6 +3862,8 @@ 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);
@@ -4448,11 +4448,12 @@ cfq_set_request(struct request_queue *q, struct request *rq, struct bio *bio,
 	const int rw = rq_data_dir(rq);
 	const bool is_sync = rq_is_sync(rq);
 	struct cfq_queue *cfqq;
+	bool disable_wbt;
 
 	spin_lock_irq(q->queue_lock);
 
 	check_ioprio_changed(cic, bio);
-	check_blkcg_changed(cic, bio);
+	disable_wbt = check_blkcg_changed(cic, bio);
 new_queue:
 	cfqq = cic_to_cfqq(cic, is_sync);
 	if (!cfqq || cfqq == &cfqd->oom_cfqq) {
@@ -4488,6 +4489,10 @@ new_queue:
 	rq->elv.priv[0] = cfqq;
 	rq->elv.priv[1] = cfqq->cfqg;
 	spin_unlock_irq(q->queue_lock);
+
+	if (disable_wbt)
+		wbt_disable_default(q);
+
 	return 0;
 }
 
@@ -4837,7 +4842,7 @@ 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,
diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c
index 556826ac7cb4..570021a0dc1c 100644
--- a/block/compat_ioctl.c
+++ b/block/compat_ioctl.c
@@ -661,7 +661,6 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	struct block_device *bdev = inode->i_bdev;
 	struct gendisk *disk = bdev->bd_disk;
 	fmode_t mode = file->f_mode;
-	struct backing_dev_info *bdi;
 	loff_t size;
 	unsigned int max_sectors;
 
@@ -708,9 +707,8 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	case BLKFRAGET:
 		if (!arg)
 			return -EINVAL;
-		bdi = blk_get_backing_dev_info(bdev);
 		return compat_put_long(arg,
-				       (bdi->ra_pages * PAGE_SIZE) / 512);
+			       (bdev->bd_bdi->ra_pages * PAGE_SIZE) / 512);
 	case BLKROGET: /* compatible */
 		return compat_put_int(arg, bdev_read_only(bdev) != 0);
 	case BLKBSZGET_32: /* get the logical block size (cf. BLKSSZGET) */
@@ -728,8 +726,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	case BLKFRASET:
 		if (!capable(CAP_SYS_ADMIN))
 			return -EACCES;
-		bdi = blk_get_backing_dev_info(bdev);
-		bdi->ra_pages = (arg * 512) / PAGE_SIZE;
+		bdev->bd_bdi->ra_pages = (arg * 512) / PAGE_SIZE;
 		return 0;
 	case BLKGETSIZE:
 		size = i_size_read(bdev->bd_inode);
diff --git a/block/deadline-iosched.c b/block/deadline-iosched.c
index 55e0bb6d7da7..c68f6bbc0dcd 100644
--- a/block/deadline-iosched.c
+++ b/block/deadline-iosched.c
@@ -120,12 +120,11 @@ static void deadline_remove_request(struct request_queue *q, struct request *rq)
 	deadline_del_rq_rb(dd, rq);
 }
 
-static int
+static enum elv_merge
 deadline_merge(struct request_queue *q, struct request **req, struct bio *bio)
 {
 	struct deadline_data *dd = q->elevator->elevator_data;
 	struct request *__rq;
-	int ret;
 
 	/*
 	 * check for front merge
@@ -138,20 +137,17 @@ deadline_merge(struct request_queue *q, struct request **req, struct bio *bio)
 			BUG_ON(sector != blk_rq_pos(__rq));
 
 			if (elv_bio_merge_ok(__rq, bio)) {
-				ret = ELEVATOR_FRONT_MERGE;
-				goto out;
+				*req = __rq;
+				return ELEVATOR_FRONT_MERGE;
 			}
 		}
 	}
 
 	return ELEVATOR_NO_MERGE;
-out:
-	*req = __rq;
-	return ret;
 }
 
 static void deadline_merged_request(struct request_queue *q,
-				    struct request *req, int type)
+				    struct request *req, enum elv_merge type)
 {
 	struct deadline_data *dd = q->elevator->elevator_data;
 
@@ -439,7 +435,7 @@ 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,
diff --git a/block/elevator.c b/block/elevator.c
index 40f0c04e5ad3..ac1c9f481a98 100644
--- a/block/elevator.c
+++ b/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;
 }
@@ -203,11 +207,12 @@ int elevator_init(struct request_queue *q, char *name)
 	}
 
 	/*
-	 * Use the default elevator specified by config boot param or
-	 * config option.  Don't try to load modules as we could be running
-	 * off async and request_module() isn't allowed from async.
+	 * Use the default elevator specified by config boot param for
+	 * non-mq devices, or by config option. Don't try to load modules
+	 * as we could be running off async and request_module() isn't
+	 * allowed from async.
 	 */
-	if (!e && *chosen_elevator) {
+	if (!e && !q->mq_ops && *chosen_elevator) {
 		e = elevator_get(chosen_elevator, false);
 		if (!e)
 			printk(KERN_ERR "I/O scheduler %s not found\n",
@@ -215,7 +220,20 @@ int elevator_init(struct request_queue *q, char *name)
 	}
 
 	if (!e) {
-		e = elevator_get(CONFIG_DEFAULT_IOSCHED, false);
+		/*
+		 * For blk-mq devices, we default to using mq-deadline,
+		 * if available, for single queue devices. If deadline
+		 * isn't available OR we have multiple queues, default
+		 * to "none".
+		 */
+		if (q->mq_ops) {
+			if (q->nr_hw_queues == 1)
+				e = elevator_get("mq-deadline", false);
+			if (!e)
+				return 0;
+		} else
+			e = elevator_get(CONFIG_DEFAULT_IOSCHED, false);
+
 		if (!e) {
 			printk(KERN_ERR
 				"Default I/O scheduler not found. " \
@@ -224,9 +242,17 @@ int elevator_init(struct request_queue *q, char *name)
 		}
 	}
 
-	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 +260,10 @@ 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 +281,7 @@ 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 +291,7 @@ 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)
 {
@@ -405,11 +435,11 @@ void elv_dispatch_add_tail(struct request_queue *q, struct request *rq)
 }
 EXPORT_SYMBOL(elv_dispatch_add_tail);
 
-int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
+enum elv_merge elv_merge(struct request_queue *q, struct request **req,
+		struct bio *bio)
 {
 	struct elevator_queue *e = q->elevator;
 	struct request *__rq;
-	int ret;
 
 	/*
 	 * Levels of merges:
@@ -424,7 +454,8 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
 	 * First try one-hit cache.
 	 */
 	if (q->last_merge && elv_bio_merge_ok(q->last_merge, bio)) {
-		ret = blk_try_merge(q->last_merge, bio);
+		enum elv_merge ret = blk_try_merge(q->last_merge, bio);
+
 		if (ret != ELEVATOR_NO_MERGE) {
 			*req = q->last_merge;
 			return ret;
@@ -443,8 +474,10 @@ 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 +489,7 @@ 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;
@@ -491,12 +523,15 @@ static bool elv_attempt_insert_merge(struct request_queue *q,
 	return ret;
 }
 
-void elv_merged_request(struct request_queue *q, struct request *rq, int type)
+void elv_merged_request(struct request_queue *q, struct request *rq,
+		enum elv_merge 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 +543,15 @@ 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 = (__force bool)(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 +568,11 @@ 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 +617,15 @@ 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 "
@@ -597,7 +644,7 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where)
 
 	if (rq->rq_flags & RQF_SOFTBARRIER) {
 		/* barriers are scheduling boundary, update end_sector */
-		if (rq->cmd_type == REQ_TYPE_FS) {
+		if (!blk_rq_is_passthrough(rq)) {
 			q->end_sector = rq_end_sector(rq);
 			q->boundary_rq = rq;
 		}
@@ -639,7 +686,7 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where)
 		if (elv_attempt_insert_merge(q, rq))
 			break;
 	case ELEVATOR_INSERT_SORT:
-		BUG_ON(rq->cmd_type != REQ_TYPE_FS);
+		BUG_ON(blk_rq_is_passthrough(rq));
 		rq->rq_flags |= RQF_SORTED;
 		q->nr_sorted++;
 		if (rq_mergeable(rq)) {
@@ -653,7 +700,7 @@ 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 +729,11 @@ 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 +741,10 @@ 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 +753,11 @@ 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 +765,22 @@ 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 +789,17 @@ 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 +867,8 @@ 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 +955,14 @@ 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 +970,76 @@ 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;
+
+		if (old->uses_mq)
+			blk_mq_sched_teardown(q);
 
-	/* unregister and clear all auxiliary data of the old elevator */
-	if (registered)
-		elv_unregister_queue(q);
+		if (!q->mq_ops)
+			blk_queue_bypass_start(q);
 
-	spin_lock_irq(q->queue_lock);
-	ioc_clear_queue(q);
-	spin_unlock_irq(q->queue_lock);
+		/* 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 +1052,11 @@ 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 +1065,21 @@ 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 +1101,7 @@ 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 +1115,34 @@ 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;
 }
diff --git a/block/genhd.c b/block/genhd.c
index fcd6d4fae657..2f444b87a5f2 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -572,6 +572,20 @@ exit:
 	disk_part_iter_exit(&piter);
 }
 
+void put_disk_devt(struct disk_devt *disk_devt)
+{
+	if (disk_devt && atomic_dec_and_test(&disk_devt->count))
+		disk_devt->release(disk_devt);
+}
+EXPORT_SYMBOL(put_disk_devt);
+
+void get_disk_devt(struct disk_devt *disk_devt)
+{
+	if (disk_devt)
+		atomic_inc(&disk_devt->count);
+}
+EXPORT_SYMBOL(get_disk_devt);
+
 /**
  * device_add_disk - add partitioning information to kernel list
  * @parent: parent device for the disk
@@ -612,8 +626,15 @@ void device_add_disk(struct device *parent, struct gendisk *disk)
 
 	disk_alloc_events(disk);
 
+	/*
+	 * Take a reference on the devt and assign it to queue since it
+	 * must not be reallocated while the bdi is registered
+	 */
+	disk->queue->disk_devt = disk->disk_devt;
+	get_disk_devt(disk->disk_devt);
+
 	/* Register BDI before referencing it from bdev */
-	bdi = &disk->queue->backing_dev_info;
+	bdi = disk->queue->backing_dev_info;
 	bdi_register_owner(bdi, disk_to_dev(disk));
 
 	blk_register_region(disk_devt(disk), disk->minors, NULL,
@@ -649,11 +670,13 @@ void del_gendisk(struct gendisk *disk)
 			     DISK_PITER_INCL_EMPTY | DISK_PITER_REVERSE);
 	while ((part = disk_part_iter_next(&piter))) {
 		invalidate_partition(disk, part->partno);
+		bdev_unhash_inode(part_devt(part));
 		delete_partition(disk, part->partno);
 	}
 	disk_part_iter_exit(&piter);
 
 	invalidate_partition(disk, 0);
+	bdev_unhash_inode(disk_devt(disk));
 	set_capacity(disk, 0);
 	disk->flags &= ~GENHD_FL_UP;
 
diff --git a/block/ioctl.c b/block/ioctl.c
index be7f4de3eb3c..7b88820b93d9 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -505,7 +505,6 @@ static int blkdev_bszset(struct block_device *bdev, fmode_t mode,
 int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 			unsigned long arg)
 {
-	struct backing_dev_info *bdi;
 	void __user *argp = (void __user *)arg;
 	loff_t size;
 	unsigned int max_sectors;
@@ -532,8 +531,7 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 	case BLKFRAGET:
 		if (!arg)
 			return -EINVAL;
-		bdi = blk_get_backing_dev_info(bdev);
-		return put_long(arg, (bdi->ra_pages * PAGE_SIZE) / 512);
+		return put_long(arg, (bdev->bd_bdi->ra_pages*PAGE_SIZE) / 512);
 	case BLKROGET:
 		return put_int(arg, bdev_read_only(bdev) != 0);
 	case BLKBSZGET: /* get block device soft block size (cf. BLKSSZGET) */
@@ -560,8 +558,7 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 	case BLKFRASET:
 		if(!capable(CAP_SYS_ADMIN))
 			return -EACCES;
-		bdi = blk_get_backing_dev_info(bdev);
-		bdi->ra_pages = (arg * 512) / PAGE_SIZE;
+		bdev->bd_bdi->ra_pages = (arg * 512) / PAGE_SIZE;
 		return 0;
 	case BLKBSZSET:
 		return blkdev_bszset(bdev, mode, argp);
diff --git a/block/ioprio.c b/block/ioprio.c
index 01b8116298a1..3790669232ff 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -122,14 +122,14 @@ SYSCALL_DEFINE3(ioprio_set, int, which, int, who, int, ioprio)
 			if (!user)
 				break;
 
-			do_each_thread(g, p) {
+			for_each_process_thread(g, p) {
 				if (!uid_eq(task_uid(p), uid) ||
 				    !task_pid_vnr(p))
 					continue;
 				ret = set_task_ioprio(p, ioprio);
 				if (ret)
 					goto free_uid;
-			} while_each_thread(g, p);
+			}
 free_uid:
 			if (who)
 				free_uid(user);
@@ -222,7 +222,7 @@ SYSCALL_DEFINE2(ioprio_get, int, which, int, who)
 			if (!user)
 				break;
 
-			do_each_thread(g, p) {
+			for_each_process_thread(g, p) {
 				if (!uid_eq(task_uid(p), user->uid) ||
 				    !task_pid_vnr(p))
 					continue;
@@ -233,7 +233,7 @@ SYSCALL_DEFINE2(ioprio_get, int, which, int, who)
 					ret = tmpio;
 				else
 					ret = ioprio_best(ret, tmpio);
-			} while_each_thread(g, p);
+			}
 
 			if (who)
 				free_uid(user);
diff --git a/block/mq-deadline.c b/block/mq-deadline.c
new file mode 100644
index 000000000000..236121633ca0
--- /dev/null
+++ b/block/mq-deadline.c
@@ -0,0 +1,556 @@
+/*
+ *  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,
+			      enum elv_merge 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;
+	struct request *free = NULL;
+	bool ret;
+
+	spin_lock(&dd->lock);
+	ret = blk_mq_sched_try_merge(q, bio, &free);
+	spin_unlock(&dd->lock);
+
+	if (free)
+		blk_mq_free_request(free);
+
+	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 (at_head || blk_rq_is_passthrough(rq)) {
+		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");
diff --git a/block/noop-iosched.c b/block/noop-iosched.c
index a163c487cf38..2d1b15d89b45 100644
--- a/block/noop-iosched.c
+++ b/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,
diff --git a/block/opal_proto.h b/block/opal_proto.h
new file mode 100644
index 000000000000..f40c9acf8895
--- /dev/null
+++ b/block/opal_proto.h
@@ -0,0 +1,452 @@
+/*
+ * Copyright © 2016 Intel Corporation
+ *
+ * Authors:
+ *    Rafael Antognolli <rafael.antognolli@intel.com>
+ *    Scott  Bauer      <scott.bauer@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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.
+ */
+#include <linux/types.h>
+
+#ifndef _OPAL_PROTO_H
+#define _OPAL_PROTO_H
+
+/*
+ * These constant values come from:
+ * SPC-4 section
+ * 6.30 SECURITY PROTOCOL IN command / table 265.
+ */
+enum {
+	TCG_SECP_00 = 0,
+	TCG_SECP_01,
+};
+
+/*
+ * Token defs derived from:
+ * TCG_Storage_Architecture_Core_Spec_v2.01_r1.00
+ * 3.2.2 Data Stream Encoding
+ */
+enum opal_response_token {
+	OPAL_DTA_TOKENID_BYTESTRING = 0xe0,
+	OPAL_DTA_TOKENID_SINT = 0xe1,
+	OPAL_DTA_TOKENID_UINT = 0xe2,
+	OPAL_DTA_TOKENID_TOKEN = 0xe3, /* actual token is returned */
+	OPAL_DTA_TOKENID_INVALID = 0X0
+};
+
+#define DTAERROR_NO_METHOD_STATUS 0x89
+#define GENERIC_HOST_SESSION_NUM 0x41
+
+#define TPER_SYNC_SUPPORTED 0x01
+
+#define TINY_ATOM_DATA_MASK 0x3F
+#define TINY_ATOM_SIGNED 0x40
+
+#define SHORT_ATOM_ID 0x80
+#define SHORT_ATOM_BYTESTRING 0x20
+#define SHORT_ATOM_SIGNED 0x10
+#define SHORT_ATOM_LEN_MASK 0xF
+
+#define MEDIUM_ATOM_ID 0xC0
+#define MEDIUM_ATOM_BYTESTRING 0x10
+#define MEDIUM_ATOM_SIGNED 0x8
+#define MEDIUM_ATOM_LEN_MASK 0x7
+
+#define LONG_ATOM_ID 0xe0
+#define LONG_ATOM_BYTESTRING 0x2
+#define LONG_ATOM_SIGNED 0x1
+
+/* Derived from TCG Core spec 2.01 Section:
+ * 3.2.2.1
+ * Data Type
+ */
+#define TINY_ATOM_BYTE   0x7F
+#define SHORT_ATOM_BYTE  0xBF
+#define MEDIUM_ATOM_BYTE 0xDF
+#define LONG_ATOM_BYTE   0xE3
+
+#define OPAL_INVAL_PARAM 12
+#define OPAL_MANUFACTURED_INACTIVE 0x08
+#define OPAL_DISCOVERY_COMID 0x0001
+
+#define LOCKING_RANGE_NON_GLOBAL 0x03
+/*
+ * User IDs used in the TCG storage SSCs
+ * Derived from: TCG_Storage_Architecture_Core_Spec_v2.01_r1.00
+ * Section: 6.3 Assigned UIDs
+ */
+#define OPAL_UID_LENGTH 8
+#define OPAL_METHOD_LENGTH 8
+#define OPAL_MSID_KEYLEN 15
+#define OPAL_UID_LENGTH_HALF 4
+
+/* Enum to index OPALUID array */
+enum opal_uid {
+	/* users */
+	OPAL_SMUID_UID,
+	OPAL_THISSP_UID,
+	OPAL_ADMINSP_UID,
+	OPAL_LOCKINGSP_UID,
+	OPAL_ENTERPRISE_LOCKINGSP_UID,
+	OPAL_ANYBODY_UID,
+	OPAL_SID_UID,
+	OPAL_ADMIN1_UID,
+	OPAL_USER1_UID,
+	OPAL_USER2_UID,
+	OPAL_PSID_UID,
+	OPAL_ENTERPRISE_BANDMASTER0_UID,
+	OPAL_ENTERPRISE_ERASEMASTER_UID,
+	/* tables */
+	OPAL_LOCKINGRANGE_GLOBAL,
+	OPAL_LOCKINGRANGE_ACE_RDLOCKED,
+	OPAL_LOCKINGRANGE_ACE_WRLOCKED,
+	OPAL_MBRCONTROL,
+	OPAL_MBR,
+	OPAL_AUTHORITY_TABLE,
+	OPAL_C_PIN_TABLE,
+	OPAL_LOCKING_INFO_TABLE,
+	OPAL_ENTERPRISE_LOCKING_INFO_TABLE,
+	/* C_PIN_TABLE object ID's */
+	OPAL_C_PIN_MSID,
+	OPAL_C_PIN_SID,
+	OPAL_C_PIN_ADMIN1,
+	/* half UID's (only first 4 bytes used) */
+	OPAL_HALF_UID_AUTHORITY_OBJ_REF,
+	OPAL_HALF_UID_BOOLEAN_ACE,
+	/* omitted optional parameter */
+	OPAL_UID_HEXFF,
+};
+
+#define OPAL_METHOD_LENGTH 8
+
+/* Enum for indexing the OPALMETHOD array */
+enum opal_method {
+	OPAL_PROPERTIES,
+	OPAL_STARTSESSION,
+	OPAL_REVERT,
+	OPAL_ACTIVATE,
+	OPAL_EGET,
+	OPAL_ESET,
+	OPAL_NEXT,
+	OPAL_EAUTHENTICATE,
+	OPAL_GETACL,
+	OPAL_GENKEY,
+	OPAL_REVERTSP,
+	OPAL_GET,
+	OPAL_SET,
+	OPAL_AUTHENTICATE,
+	OPAL_RANDOM,
+	OPAL_ERASE,
+};
+
+enum opal_token {
+	/* Boolean */
+	OPAL_TRUE = 0x01,
+	OPAL_FALSE = 0x00,
+	OPAL_BOOLEAN_EXPR = 0x03,
+	/* cellblocks */
+	OPAL_TABLE = 0x00,
+	OPAL_STARTROW = 0x01,
+	OPAL_ENDROW = 0x02,
+	OPAL_STARTCOLUMN = 0x03,
+	OPAL_ENDCOLUMN = 0x04,
+	OPAL_VALUES = 0x01,
+	/* authority table */
+	OPAL_PIN = 0x03,
+	/* locking tokens */
+	OPAL_RANGESTART = 0x03,
+	OPAL_RANGELENGTH = 0x04,
+	OPAL_READLOCKENABLED = 0x05,
+	OPAL_WRITELOCKENABLED = 0x06,
+	OPAL_READLOCKED = 0x07,
+	OPAL_WRITELOCKED = 0x08,
+	OPAL_ACTIVEKEY = 0x0A,
+	/* locking info table */
+	OPAL_MAXRANGES = 0x04,
+	 /* mbr control */
+	OPAL_MBRENABLE = 0x01,
+	OPAL_MBRDONE = 0x02,
+	/* properties */
+	OPAL_HOSTPROPERTIES = 0x00,
+	/* atoms */
+	OPAL_STARTLIST = 0xf0,
+	OPAL_ENDLIST = 0xf1,
+	OPAL_STARTNAME = 0xf2,
+	OPAL_ENDNAME = 0xf3,
+	OPAL_CALL = 0xf8,
+	OPAL_ENDOFDATA = 0xf9,
+	OPAL_ENDOFSESSION = 0xfa,
+	OPAL_STARTTRANSACTON = 0xfb,
+	OPAL_ENDTRANSACTON = 0xfC,
+	OPAL_EMPTYATOM = 0xff,
+	OPAL_WHERE = 0x00,
+};
+
+/* Locking state for a locking range */
+enum opal_lockingstate {
+	OPAL_LOCKING_READWRITE = 0x01,
+	OPAL_LOCKING_READONLY = 0x02,
+	OPAL_LOCKING_LOCKED = 0x03,
+};
+
+/* Packets derived from:
+ * TCG_Storage_Architecture_Core_Spec_v2.01_r1.00
+ * Secion: 3.2.3 ComPackets, Packets & Subpackets
+ */
+
+/* Comm Packet (header) for transmissions. */
+struct opal_compacket {
+	__be32 reserved0;
+	u8 extendedComID[4];
+	__be32 outstandingData;
+	__be32 minTransfer;
+	__be32 length;
+};
+
+/* Packet structure. */
+struct opal_packet {
+	__be32 tsn;
+	__be32 hsn;
+	__be32 seq_number;
+	__be16 reserved0;
+	__be16 ack_type;
+	__be32 acknowledgment;
+	__be32 length;
+};
+
+/* Data sub packet header */
+struct opal_data_subpacket {
+	u8 reserved0[6];
+	__be16 kind;
+	__be32 length;
+};
+
+/* header of a response */
+struct opal_header {
+	struct opal_compacket cp;
+	struct opal_packet pkt;
+	struct opal_data_subpacket subpkt;
+};
+
+#define FC_TPER       0x0001
+#define FC_LOCKING    0x0002
+#define FC_GEOMETRY   0x0003
+#define FC_ENTERPRISE 0x0100
+#define FC_DATASTORE  0x0202
+#define FC_SINGLEUSER 0x0201
+#define FC_OPALV100   0x0200
+#define FC_OPALV200   0x0203
+
+/*
+ * The Discovery 0 Header. As defined in
+ * Opal SSC Documentation
+ * Section: 3.3.5 Capability Discovery
+ */
+struct d0_header {
+	__be32 length; /* the length of the header 48 in 2.00.100 */
+	__be32 revision; /**< revision of the header 1 in 2.00.100 */
+	__be32 reserved01;
+	__be32 reserved02;
+	/*
+	 * the remainder of the structure is vendor specific and will not be
+	 * addressed now
+	 */
+	u8 ignored[32];
+};
+
+/*
+ * TPer Feature Descriptor. Contains flags indicating support for the
+ * TPer features described in the OPAL specification. The names match the
+ * OPAL terminology
+ *
+ * code == 0x001 in 2.00.100
+ */
+struct d0_tper_features {
+	/*
+	 * supported_features bits:
+	 * bit 7: reserved
+	 * bit 6: com ID management
+	 * bit 5: reserved
+	 * bit 4: streaming support
+	 * bit 3: buffer management
+	 * bit 2: ACK/NACK
+	 * bit 1: async
+	 * bit 0: sync
+	 */
+	u8 supported_features;
+	/*
+	 * bytes 5 through 15 are reserved, but we represent the first 3 as
+	 * u8 to keep the other two 32bits integers aligned.
+	 */
+	u8 reserved01[3];
+	__be32 reserved02;
+	__be32 reserved03;
+};
+
+/*
+ * Locking Feature Descriptor. Contains flags indicating support for the
+ * locking features described in the OPAL specification. The names match the
+ * OPAL terminology
+ *
+ * code == 0x0002 in 2.00.100
+ */
+struct d0_locking_features {
+	/*
+	 * supported_features bits:
+	 * bits 6-7: reserved
+	 * bit 5: MBR done
+	 * bit 4: MBR enabled
+	 * bit 3: media encryption
+	 * bit 2: locked
+	 * bit 1: locking enabled
+	 * bit 0: locking supported
+	 */
+	u8 supported_features;
+	/*
+	 * bytes 5 through 15 are reserved, but we represent the first 3 as
+	 * u8 to keep the other two 32bits integers aligned.
+	 */
+	u8 reserved01[3];
+	__be32 reserved02;
+	__be32 reserved03;
+};
+
+/*
+ * Geometry Feature Descriptor. Contains flags indicating support for the
+ * geometry features described in the OPAL specification. The names match the
+ * OPAL terminology
+ *
+ * code == 0x0003 in 2.00.100
+ */
+struct d0_geometry_features {
+	/*
+	 * skip 32 bits from header, needed to align the struct to 64 bits.
+	 */
+	u8 header[4];
+	/*
+	 * reserved01:
+	 * bits 1-6: reserved
+	 * bit 0: align
+	 */
+	u8 reserved01;
+	u8 reserved02[7];
+	__be32 logical_block_size;
+	__be64 alignment_granularity;
+	__be64 lowest_aligned_lba;
+};
+
+/*
+ * Enterprise SSC Feature
+ *
+ * code == 0x0100
+ */
+struct d0_enterprise_ssc {
+	__be16 baseComID;
+	__be16 numComIDs;
+	/* range_crossing:
+	 * bits 1-6: reserved
+	 * bit 0: range crossing
+	 */
+	u8 range_crossing;
+	u8 reserved01;
+	__be16 reserved02;
+	__be32 reserved03;
+	__be32 reserved04;
+};
+
+/*
+ * Opal V1 feature
+ *
+ * code == 0x0200
+ */
+struct d0_opal_v100 {
+	__be16 baseComID;
+	__be16 numComIDs;
+};
+
+/*
+ * Single User Mode feature
+ *
+ * code == 0x0201
+ */
+struct d0_single_user_mode {
+	__be32 num_locking_objects;
+	/* reserved01:
+	 * bit 0: any
+	 * bit 1: all
+	 * bit 2: policy
+	 * bits 3-7: reserved
+	 */
+	u8 reserved01;
+	u8 reserved02;
+	__be16 reserved03;
+	__be32 reserved04;
+};
+
+/*
+ * Additonal Datastores feature
+ *
+ * code == 0x0202
+ */
+struct d0_datastore_table {
+	__be16 reserved01;
+	__be16 max_tables;
+	__be32 max_size_tables;
+	__be32 table_size_alignment;
+};
+
+/*
+ * OPAL 2.0 feature
+ *
+ * code == 0x0203
+ */
+struct d0_opal_v200 {
+	__be16 baseComID;
+	__be16 numComIDs;
+	/* range_crossing:
+	 * bits 1-6: reserved
+	 * bit 0: range crossing
+	 */
+	u8 range_crossing;
+	/* num_locking_admin_auth:
+	 * not aligned to 16 bits, so use two u8.
+	 * stored in big endian:
+	 * 0: MSB
+	 * 1: LSB
+	 */
+	u8 num_locking_admin_auth[2];
+	/* num_locking_user_auth:
+	 * not aligned to 16 bits, so use two u8.
+	 * stored in big endian:
+	 * 0: MSB
+	 * 1: LSB
+	 */
+	u8 num_locking_user_auth[2];
+	u8 initialPIN;
+	u8 revertedPIN;
+	u8 reserved01;
+	__be32 reserved02;
+};
+
+/* Union of features used to parse the discovery 0 response */
+struct d0_features {
+	__be16 code;
+	/*
+	 * r_version bits:
+	 * bits 4-7: version
+	 * bits 0-3: reserved
+	 */
+	u8 r_version;
+	u8 length;
+	u8 features[];
+};
+
+#endif /* _OPAL_PROTO_H */
diff --git a/block/partitions/efi.c b/block/partitions/efi.c
index bcd86e5cd546..39f70d968754 100644
--- a/block/partitions/efi.c
+++ b/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");
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index c2b64923ab66..2a2fc768b27a 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -230,15 +230,17 @@ EXPORT_SYMBOL(blk_verify_command);
 static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq,
 			     struct sg_io_hdr *hdr, fmode_t mode)
 {
-	if (copy_from_user(rq->cmd, hdr->cmdp, hdr->cmd_len))
+	struct scsi_request *req = scsi_req(rq);
+
+	if (copy_from_user(req->cmd, hdr->cmdp, hdr->cmd_len))
 		return -EFAULT;
-	if (blk_verify_command(rq->cmd, mode & FMODE_WRITE))
+	if (blk_verify_command(req->cmd, mode & FMODE_WRITE))
 		return -EPERM;
 
 	/*
 	 * fill in request structure
 	 */
-	rq->cmd_len = hdr->cmd_len;
+	req->cmd_len = hdr->cmd_len;
 
 	rq->timeout = msecs_to_jiffies(hdr->timeout);
 	if (!rq->timeout)
@@ -254,6 +256,7 @@ static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq,
 static int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr,
 				 struct bio *bio)
 {
+	struct scsi_request *req = scsi_req(rq);
 	int r, ret = 0;
 
 	/*
@@ -267,13 +270,13 @@ static int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr,
 	hdr->info = 0;
 	if (hdr->masked_status || hdr->host_status || hdr->driver_status)
 		hdr->info |= SG_INFO_CHECK;
-	hdr->resid = rq->resid_len;
+	hdr->resid = req->resid_len;
 	hdr->sb_len_wr = 0;
 
-	if (rq->sense_len && hdr->sbp) {
-		int len = min((unsigned int) hdr->mx_sb_len, rq->sense_len);
+	if (req->sense_len && hdr->sbp) {
+		int len = min((unsigned int) hdr->mx_sb_len, req->sense_len);
 
-		if (!copy_to_user(hdr->sbp, rq->sense, len))
+		if (!copy_to_user(hdr->sbp, req->sense, len))
 			hdr->sb_len_wr = len;
 		else
 			ret = -EFAULT;
@@ -294,7 +297,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 	int writing = 0;
 	int at_head = 0;
 	struct request *rq;
-	char sense[SCSI_SENSE_BUFFERSIZE];
+	struct scsi_request *req;
 	struct bio *bio;
 
 	if (hdr->interface_id != 'S')
@@ -318,14 +321,16 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 		at_head = 1;
 
 	ret = -ENOMEM;
-	rq = blk_get_request(q, writing ? WRITE : READ, GFP_KERNEL);
+	rq = blk_get_request(q, writing ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN,
+			GFP_KERNEL);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
-	blk_rq_set_block_pc(rq);
+	req = scsi_req(rq);
+	scsi_req_init(rq);
 
 	if (hdr->cmd_len > BLK_MAX_CDB) {
-		rq->cmd = kzalloc(hdr->cmd_len, GFP_KERNEL);
-		if (!rq->cmd)
+		req->cmd = kzalloc(hdr->cmd_len, GFP_KERNEL);
+		if (!req->cmd)
 			goto out_put_request;
 	}
 
@@ -357,9 +362,6 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 		goto out_free_cdb;
 
 	bio = rq->bio;
-	memset(sense, 0, sizeof(sense));
-	rq->sense = sense;
-	rq->sense_len = 0;
 	rq->retries = 0;
 
 	start_time = jiffies;
@@ -375,8 +377,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 	ret = blk_complete_sghdr_rq(rq, hdr, bio);
 
 out_free_cdb:
-	if (rq->cmd != rq->__cmd)
-		kfree(rq->cmd);
+	scsi_req_free_cmd(req);
 out_put_request:
 	blk_put_request(rq);
 	return ret;
@@ -420,9 +421,10 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 		struct scsi_ioctl_command __user *sic)
 {
 	struct request *rq;
+	struct scsi_request *req;
 	int err;
 	unsigned int in_len, out_len, bytes, opcode, cmdlen;
-	char *buffer = NULL, sense[SCSI_SENSE_BUFFERSIZE];
+	char *buffer = NULL;
 
 	if (!sic)
 		return -EINVAL;
@@ -447,12 +449,14 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 
 	}
 
-	rq = blk_get_request(q, in_len ? WRITE : READ, __GFP_RECLAIM);
+	rq = blk_get_request(q, in_len ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN,
+			__GFP_RECLAIM);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto error_free_buffer;
 	}
-	blk_rq_set_block_pc(rq);
+	req = scsi_req(rq);
+	scsi_req_init(rq);
 
 	cmdlen = COMMAND_SIZE(opcode);
 
@@ -460,14 +464,14 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 	 * get command and data to send to device, if any
 	 */
 	err = -EFAULT;
-	rq->cmd_len = cmdlen;
-	if (copy_from_user(rq->cmd, sic->data, cmdlen))
+	req->cmd_len = cmdlen;
+	if (copy_from_user(req->cmd, sic->data, cmdlen))
 		goto error;
 
 	if (in_len && copy_from_user(buffer, sic->data + cmdlen, in_len))
 		goto error;
 
-	err = blk_verify_command(rq->cmd, mode & FMODE_WRITE);
+	err = blk_verify_command(req->cmd, mode & FMODE_WRITE);
 	if (err)
 		goto error;
 
@@ -503,18 +507,14 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 		goto error;
 	}
 
-	memset(sense, 0, sizeof(sense));
-	rq->sense = sense;
-	rq->sense_len = 0;
-
 	blk_execute_rq(q, disk, rq, 0);
 
 	err = rq->errors & 0xff;	/* only 8 bit SCSI status */
 	if (err) {
-		if (rq->sense_len && rq->sense) {
-			bytes = (OMAX_SB_LEN > rq->sense_len) ?
-				rq->sense_len : OMAX_SB_LEN;
-			if (copy_to_user(sic->data, rq->sense, bytes))
+		if (req->sense_len && req->sense) {
+			bytes = (OMAX_SB_LEN > req->sense_len) ?
+				req->sense_len : OMAX_SB_LEN;
+			if (copy_to_user(sic->data, req->sense, bytes))
 				err = -EFAULT;
 		}
 	} else {
@@ -539,14 +539,14 @@ static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk,
 	struct request *rq;
 	int err;
 
-	rq = blk_get_request(q, WRITE, __GFP_RECLAIM);
+	rq = blk_get_request(q, REQ_OP_SCSI_OUT, __GFP_RECLAIM);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
-	blk_rq_set_block_pc(rq);
+	scsi_req_init(rq);
 	rq->timeout = BLK_DEFAULT_SG_TIMEOUT;
-	rq->cmd[0] = cmd;
-	rq->cmd[4] = data;
-	rq->cmd_len = 6;
+	scsi_req(rq)->cmd[0] = cmd;
+	scsi_req(rq)->cmd[4] = data;
+	scsi_req(rq)->cmd_len = 6;
 	err = blk_execute_rq(q, bd_disk, rq, 0);
 	blk_put_request(rq);
 
@@ -743,6 +743,17 @@ int scsi_cmd_blk_ioctl(struct block_device *bd, fmode_t mode,
 }
 EXPORT_SYMBOL(scsi_cmd_blk_ioctl);
 
+void scsi_req_init(struct request *rq)
+{
+	struct scsi_request *req = scsi_req(rq);
+
+	memset(req->__cmd, 0, sizeof(req->__cmd));
+	req->cmd = req->__cmd;
+	req->cmd_len = BLK_MAX_CDB;
+	req->sense_len = 0;
+}
+EXPORT_SYMBOL(scsi_req_init);
+
 static int __init blk_scsi_ioctl_init(void)
 {
 	blk_set_cmd_filter_defaults(&blk_default_cmd_filter);
diff --git a/block/sed-opal.c b/block/sed-opal.c
new file mode 100644
index 000000000000..1e18dca360fc
--- /dev/null
+++ b/block/sed-opal.c
@@ -0,0 +1,2425 @@
+/*
+ * Copyright © 2016 Intel Corporation
+ *
+ * Authors:
+ *    Scott  Bauer      <scott.bauer@intel.com>
+ *    Rafael Antognolli <rafael.antognolli@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ":OPAL: " fmt
+
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/genhd.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <uapi/linux/sed-opal.h>
+#include <linux/sed-opal.h>
+#include <linux/string.h>
+#include <linux/kdev_t.h>
+
+#include "opal_proto.h"
+
+#define IO_BUFFER_LENGTH 2048
+#define MAX_TOKS 64
+
+struct opal_step {
+	int (*fn)(struct opal_dev *dev, void *data);
+	void *data;
+};
+typedef int (cont_fn)(struct opal_dev *dev);
+
+enum opal_atom_width {
+	OPAL_WIDTH_TINY,
+	OPAL_WIDTH_SHORT,
+	OPAL_WIDTH_MEDIUM,
+	OPAL_WIDTH_LONG,
+	OPAL_WIDTH_TOKEN
+};
+
+/*
+ * On the parsed response, we don't store again the toks that are already
+ * stored in the response buffer. Instead, for each token, we just store a
+ * pointer to the position in the buffer where the token starts, and the size
+ * of the token in bytes.
+ */
+struct opal_resp_tok {
+	const u8 *pos;
+	size_t len;
+	enum opal_response_token type;
+	enum opal_atom_width width;
+	union {
+		u64 u;
+		s64 s;
+	} stored;
+};
+
+/*
+ * From the response header it's not possible to know how many tokens there are
+ * on the payload. So we hardcode that the maximum will be MAX_TOKS, and later
+ * if we start dealing with messages that have more than that, we can increase
+ * this number. This is done to avoid having to make two passes through the
+ * response, the first one counting how many tokens we have and the second one
+ * actually storing the positions.
+ */
+struct parsed_resp {
+	int num;
+	struct opal_resp_tok toks[MAX_TOKS];
+};
+
+struct opal_dev {
+	bool supported;
+
+	void *data;
+	sec_send_recv *send_recv;
+
+	const struct opal_step *steps;
+	struct mutex dev_lock;
+	u16 comid;
+	u32 hsn;
+	u32 tsn;
+	u64 align;
+	u64 lowest_lba;
+
+	size_t pos;
+	u8 cmd[IO_BUFFER_LENGTH];
+	u8 resp[IO_BUFFER_LENGTH];
+
+	struct parsed_resp parsed;
+	size_t prev_d_len;
+	void *prev_data;
+
+	struct list_head unlk_lst;
+};
+
+
+static const u8 opaluid[][OPAL_UID_LENGTH] = {
+	/* users */
+	[OPAL_SMUID_UID] =
+		{ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff },
+	[OPAL_THISSP_UID] =
+		{ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01 },
+	[OPAL_ADMINSP_UID] =
+		{ 0x00, 0x00, 0x02, 0x05, 0x00, 0x00, 0x00, 0x01 },
+	[OPAL_LOCKINGSP_UID] =
+		{ 0x00, 0x00, 0x02, 0x05, 0x00, 0x00, 0x00, 0x02 },
+	[OPAL_ENTERPRISE_LOCKINGSP_UID] =
+		{ 0x00, 0x00, 0x02, 0x05, 0x00, 0x01, 0x00, 0x01 },
+	[OPAL_ANYBODY_UID] =
+		{ 0x00, 0x00, 0x00, 0x09, 0x00, 0x00, 0x00, 0x01 },
+	[OPAL_SID_UID] =
+		{ 0x00, 0x00, 0x00, 0x09, 0x00, 0x00, 0x00, 0x06 },
+	[OPAL_ADMIN1_UID] =
+		{ 0x00, 0x00, 0x00, 0x09, 0x00, 0x01, 0x00, 0x01 },
+	[OPAL_USER1_UID] =
+		{ 0x00, 0x00, 0x00, 0x09, 0x00, 0x03, 0x00, 0x01 },
+	[OPAL_USER2_UID] =
+		{ 0x00, 0x00, 0x00, 0x09, 0x00, 0x03, 0x00, 0x02 },
+	[OPAL_PSID_UID] =
+		{ 0x00, 0x00, 0x00, 0x09, 0x00, 0x01, 0xff, 0x01 },
+	[OPAL_ENTERPRISE_BANDMASTER0_UID] =
+		{ 0x00, 0x00, 0x00, 0x09, 0x00, 0x00, 0x80, 0x01 },
+	[OPAL_ENTERPRISE_ERASEMASTER_UID] =
+		{ 0x00, 0x00, 0x00, 0x09, 0x00, 0x00, 0x84, 0x01 },
+
+	/* tables */
+
+	[OPAL_LOCKINGRANGE_GLOBAL] =
+		{ 0x00, 0x00, 0x08, 0x02, 0x00, 0x00, 0x00, 0x01 },
+	[OPAL_LOCKINGRANGE_ACE_RDLOCKED] =
+		{ 0x00, 0x00, 0x00, 0x08, 0x00, 0x03, 0xE0, 0x01 },
+	[OPAL_LOCKINGRANGE_ACE_WRLOCKED] =
+		{ 0x00, 0x00, 0x00, 0x08, 0x00, 0x03, 0xE8, 0x01 },
+	[OPAL_MBRCONTROL] =
+		{ 0x00, 0x00, 0x08, 0x03, 0x00, 0x00, 0x00, 0x01 },
+	[OPAL_MBR] =
+		{ 0x00, 0x00, 0x08, 0x04, 0x00, 0x00, 0x00, 0x00 },
+	[OPAL_AUTHORITY_TABLE] =
+		{ 0x00, 0x00, 0x00, 0x09, 0x00, 0x00, 0x00, 0x00},
+	[OPAL_C_PIN_TABLE] =
+		{ 0x00, 0x00, 0x00, 0x0B, 0x00, 0x00, 0x00, 0x00},
+	[OPAL_LOCKING_INFO_TABLE] =
+		{ 0x00, 0x00, 0x08, 0x01, 0x00, 0x00, 0x00, 0x01 },
+	[OPAL_ENTERPRISE_LOCKING_INFO_TABLE] =
+		{ 0x00, 0x00, 0x08, 0x01, 0x00, 0x00, 0x00, 0x00 },
+
+	/* C_PIN_TABLE object ID's */
+
+        [OPAL_C_PIN_MSID] =
+		{ 0x00, 0x00, 0x00, 0x0B, 0x00, 0x00, 0x84, 0x02},
+	[OPAL_C_PIN_SID] =
+		{ 0x00, 0x00, 0x00, 0x0B, 0x00, 0x00, 0x00, 0x01},
+	[OPAL_C_PIN_ADMIN1] =
+		{ 0x00, 0x00, 0x00, 0x0B, 0x00, 0x01, 0x00, 0x01},
+
+	/* half UID's (only first 4 bytes used) */
+
+	[OPAL_HALF_UID_AUTHORITY_OBJ_REF] =
+		{ 0x00, 0x00, 0x0C, 0x05, 0xff, 0xff, 0xff, 0xff },
+	[OPAL_HALF_UID_BOOLEAN_ACE] =
+		{ 0x00, 0x00, 0x04, 0x0E, 0xff, 0xff, 0xff, 0xff },
+
+	/* special value for omitted optional parameter */
+	[OPAL_UID_HEXFF] =
+		{ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff},
+};
+
+/*
+ * TCG Storage SSC Methods.
+ * Derived from: TCG_Storage_Architecture_Core_Spec_v2.01_r1.00
+ * Section: 6.3 Assigned UIDs
+ */
+static const u8 opalmethod[][OPAL_UID_LENGTH] = {
+	[OPAL_PROPERTIES] =
+		{ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0x01 },
+	[OPAL_STARTSESSION] =
+		{ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0x02 },
+	[OPAL_REVERT] =
+		{ 0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x02, 0x02 },
+	[OPAL_ACTIVATE] =
+		{ 0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x02, 0x03 },
+	[OPAL_EGET] =
+		{ 0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x00, 0x06 },
+	[OPAL_ESET] =
+		{ 0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x00, 0x07 },
+	[OPAL_NEXT] =
+		{ 0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x00, 0x08 },
+	[OPAL_EAUTHENTICATE] =
+		{ 0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x00, 0x0c },
+	[OPAL_GETACL] =
+		{ 0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x00, 0x0d },
+	[OPAL_GENKEY] =
+		{ 0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x00, 0x10 },
+	[OPAL_REVERTSP] =
+		{ 0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x00, 0x11 },
+	[OPAL_GET] =
+		{ 0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x00, 0x16 },
+	[OPAL_SET] =
+		{ 0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x00, 0x17 },
+	[OPAL_AUTHENTICATE] =
+		{ 0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x00, 0x1c },
+	[OPAL_RANDOM] =
+		{ 0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x06, 0x01 },
+	[OPAL_ERASE] =
+		{ 0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x08, 0x03 },
+};
+
+static int end_opal_session_error(struct opal_dev *dev);
+
+struct opal_suspend_data {
+	struct opal_lock_unlock unlk;
+	u8 lr;
+	struct list_head node;
+};
+
+/*
+ * Derived from:
+ * TCG_Storage_Architecture_Core_Spec_v2.01_r1.00
+ * Section: 5.1.5 Method Status Codes
+ */
+static const char * const opal_errors[] = {
+	"Success",
+	"Not Authorized",
+	"Unknown Error",
+	"SP Busy",
+	"SP Failed",
+	"SP Disabled",
+	"SP Frozen",
+	"No Sessions Available",
+	"Uniqueness Conflict",
+	"Insufficient Space",
+	"Insufficient Rows",
+	"Invalid Function",
+	"Invalid Parameter",
+	"Invalid Reference",
+	"Unknown Error",
+	"TPER Malfunction",
+	"Transaction Failure",
+	"Response Overflow",
+	"Authority Locked Out",
+};
+
+static const char *opal_error_to_human(int error)
+{
+	if (error == 0x3f)
+		return "Failed";
+
+	if (error >= ARRAY_SIZE(opal_errors) || error < 0)
+		return "Unknown Error";
+
+	return opal_errors[error];
+}
+
+static void print_buffer(const u8 *ptr, u32 length)
+{
+#ifdef DEBUG
+	print_hex_dump_bytes("OPAL: ", DUMP_PREFIX_OFFSET, ptr, length);
+	pr_debug("\n");
+#endif
+}
+
+static bool check_tper(const void *data)
+{
+	const struct d0_tper_features *tper = data;
+	u8 flags = tper->supported_features;
+
+	if (!(flags & TPER_SYNC_SUPPORTED)) {
+		pr_err("TPer sync not supported. flags = %d\n",
+		       tper->supported_features);
+		return false;
+	}
+
+	return true;
+}
+
+static bool check_sum(const void *data)
+{
+	const struct d0_single_user_mode *sum = data;
+	u32 nlo = be32_to_cpu(sum->num_locking_objects);
+
+	if (nlo == 0) {
+		pr_err("Need at least one locking object.\n");
+		return false;
+	}
+
+	pr_debug("Number of locking objects: %d\n", nlo);
+
+	return true;
+}
+
+static u16 get_comid_v100(const void *data)
+{
+	const struct d0_opal_v100 *v100 = data;
+
+	return be16_to_cpu(v100->baseComID);
+}
+
+static u16 get_comid_v200(const void *data)
+{
+	const struct d0_opal_v200 *v200 = data;
+
+	return be16_to_cpu(v200->baseComID);
+}
+
+static int opal_send_cmd(struct opal_dev *dev)
+{
+	return dev->send_recv(dev->data, dev->comid, TCG_SECP_01,
+			      dev->cmd, IO_BUFFER_LENGTH,
+			      true);
+}
+
+static int opal_recv_cmd(struct opal_dev *dev)
+{
+	return dev->send_recv(dev->data, dev->comid, TCG_SECP_01,
+			      dev->resp, IO_BUFFER_LENGTH,
+			      false);
+}
+
+static int opal_recv_check(struct opal_dev *dev)
+{
+	size_t buflen = IO_BUFFER_LENGTH;
+	void *buffer = dev->resp;
+	struct opal_header *hdr = buffer;
+	int ret;
+
+	do {
+		pr_debug("Sent OPAL command: outstanding=%d, minTransfer=%d\n",
+			 hdr->cp.outstandingData,
+			 hdr->cp.minTransfer);
+
+		if (hdr->cp.outstandingData == 0 ||
+		    hdr->cp.minTransfer != 0)
+			return 0;
+
+		memset(buffer, 0, buflen);
+		ret = opal_recv_cmd(dev);
+	} while (!ret);
+
+	return ret;
+}
+
+static int opal_send_recv(struct opal_dev *dev, cont_fn *cont)
+{
+	int ret;
+
+	ret = opal_send_cmd(dev);
+	if (ret)
+		return ret;
+	ret = opal_recv_cmd(dev);
+	if (ret)
+		return ret;
+	ret = opal_recv_check(dev);
+	if (ret)
+		return ret;
+	return cont(dev);
+}
+
+static void check_geometry(struct opal_dev *dev, const void *data)
+{
+	const struct d0_geometry_features *geo = data;
+
+	dev->align = geo->alignment_granularity;
+	dev->lowest_lba = geo->lowest_aligned_lba;
+}
+
+static int next(struct opal_dev *dev)
+{
+	const struct opal_step *step;
+	int state = 0, error = 0;
+
+	do {
+		step = &dev->steps[state];
+		if (!step->fn)
+			break;
+
+		error = step->fn(dev, step->data);
+		if (error) {
+			pr_err("Error on step function: %d with error %d: %s\n",
+			       state, error,
+			       opal_error_to_human(error));
+
+			/* For each OPAL command we do a discovery0 then we
+			 * start some sort of session.
+			 * If we haven't passed state 1 then there was an error
+			 * on discovery0 or during the attempt to start a
+			 * session. Therefore we shouldn't attempt to terminate
+			 * a session, as one has not yet been created.
+			 */
+			if (state > 1) {
+				end_opal_session_error(dev);
+				return error;
+			}
+
+		}
+		state++;
+	} while (!error);
+
+	return error;
+}
+
+static int opal_discovery0_end(struct opal_dev *dev)
+{
+	bool found_com_id = false, supported = true, single_user = false;
+	const struct d0_header *hdr = (struct d0_header *)dev->resp;
+	const u8 *epos = dev->resp, *cpos = dev->resp;
+	u16 comid = 0;
+	u32 hlen = be32_to_cpu(hdr->length);
+
+	print_buffer(dev->resp, hlen);
+
+	if (hlen > IO_BUFFER_LENGTH - sizeof(*hdr)) {
+		pr_warn("Discovery length overflows buffer (%zu+%u)/%u\n",
+			sizeof(*hdr), hlen, IO_BUFFER_LENGTH);
+		return -EFAULT;
+	}
+
+	epos += hlen; /* end of buffer */
+	cpos += sizeof(*hdr); /* current position on buffer */
+
+	while (cpos < epos && supported) {
+		const struct d0_features *body =
+			(const struct d0_features *)cpos;
+
+		switch (be16_to_cpu(body->code)) {
+		case FC_TPER:
+			supported = check_tper(body->features);
+			break;
+		case FC_SINGLEUSER:
+			single_user = check_sum(body->features);
+			break;
+		case FC_GEOMETRY:
+			check_geometry(dev, body);
+			break;
+		case FC_LOCKING:
+		case FC_ENTERPRISE:
+		case FC_DATASTORE:
+			/* some ignored properties */
+			pr_debug("Found OPAL feature description: %d\n",
+				 be16_to_cpu(body->code));
+			break;
+		case FC_OPALV100:
+			comid = get_comid_v100(body->features);
+			found_com_id = true;
+			break;
+		case FC_OPALV200:
+			comid = get_comid_v200(body->features);
+			found_com_id = true;
+			break;
+		case 0xbfff ... 0xffff:
+			/* vendor specific, just ignore */
+			break;
+		default:
+			pr_debug("OPAL Unknown feature: %d\n",
+				 be16_to_cpu(body->code));
+
+		}
+		cpos += body->length + 4;
+	}
+
+	if (!supported) {
+		pr_debug("This device is not Opal enabled. Not Supported!\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (!single_user)
+		pr_debug("Device doesn't support single user mode\n");
+
+
+	if (!found_com_id) {
+		pr_debug("Could not find OPAL comid for device. Returning early\n");
+		return -EOPNOTSUPP;;
+	}
+
+	dev->comid = comid;
+
+	return 0;
+}
+
+static int opal_discovery0(struct opal_dev *dev, void *data)
+{
+	int ret;
+
+	memset(dev->resp, 0, IO_BUFFER_LENGTH);
+	dev->comid = OPAL_DISCOVERY_COMID;
+	ret = opal_recv_cmd(dev);
+	if (ret)
+		return ret;
+	return opal_discovery0_end(dev);
+}
+
+static void add_token_u8(int *err, struct opal_dev *cmd, u8 tok)
+{
+	if (*err)
+		return;
+	if (cmd->pos >= IO_BUFFER_LENGTH - 1) {
+		pr_err("Error adding u8: end of buffer.\n");
+		*err = -ERANGE;
+		return;
+	}
+	cmd->cmd[cmd->pos++] = tok;
+}
+
+static void add_short_atom_header(struct opal_dev *cmd, bool bytestring,
+				  bool has_sign, int len)
+{
+	u8 atom;
+	int err = 0;
+
+	atom = SHORT_ATOM_ID;
+	atom |= bytestring ? SHORT_ATOM_BYTESTRING : 0;
+	atom |= has_sign ? SHORT_ATOM_SIGNED : 0;
+	atom |= len & SHORT_ATOM_LEN_MASK;
+
+	add_token_u8(&err, cmd, atom);
+}
+
+static void add_medium_atom_header(struct opal_dev *cmd, bool bytestring,
+				   bool has_sign, int len)
+{
+	u8 header0;
+
+	header0 = MEDIUM_ATOM_ID;
+	header0 |= bytestring ? MEDIUM_ATOM_BYTESTRING : 0;
+	header0 |= has_sign ? MEDIUM_ATOM_SIGNED : 0;
+	header0 |= (len >> 8) & MEDIUM_ATOM_LEN_MASK;
+	cmd->cmd[cmd->pos++] = header0;
+	cmd->cmd[cmd->pos++] = len;
+}
+
+static void add_token_u64(int *err, struct opal_dev *cmd, u64 number)
+{
+
+	size_t len;
+	int msb;
+	u8 n;
+
+	if (!(number & ~TINY_ATOM_DATA_MASK)) {
+		add_token_u8(err, cmd, number);
+		return;
+	}
+
+	msb = fls(number);
+	len = DIV_ROUND_UP(msb, 4);
+
+	if (cmd->pos >= IO_BUFFER_LENGTH - len - 1) {
+		pr_err("Error adding u64: end of buffer.\n");
+		*err = -ERANGE;
+		return;
+	}
+	add_short_atom_header(cmd, false, false, len);
+	while (len--) {
+		n = number >> (len * 8);
+		add_token_u8(err, cmd, n);
+	}
+}
+
+static void add_token_bytestring(int *err, struct opal_dev *cmd,
+				 const u8 *bytestring, size_t len)
+{
+	size_t header_len = 1;
+	bool is_short_atom = true;
+
+	if (*err)
+		return;
+
+	if (len & ~SHORT_ATOM_LEN_MASK) {
+		header_len = 2;
+		is_short_atom = false;
+	}
+
+	if (len >= IO_BUFFER_LENGTH - cmd->pos - header_len) {
+		pr_err("Error adding bytestring: end of buffer.\n");
+		*err = -ERANGE;
+		return;
+	}
+
+	if (is_short_atom)
+		add_short_atom_header(cmd, true, false, len);
+	else
+		add_medium_atom_header(cmd, true, false, len);
+
+	memcpy(&cmd->cmd[cmd->pos], bytestring, len);
+	cmd->pos += len;
+
+}
+
+static int build_locking_range(u8 *buffer, size_t length, u8 lr)
+{
+	if (length > OPAL_UID_LENGTH) {
+		pr_err("Can't build locking range. Length OOB\n");
+		return -ERANGE;
+	}
+
+	memcpy(buffer, opaluid[OPAL_LOCKINGRANGE_GLOBAL], OPAL_UID_LENGTH);
+
+	if (lr == 0)
+		return 0;
+	buffer[5] = LOCKING_RANGE_NON_GLOBAL;
+	buffer[7] = lr;
+
+	return 0;
+}
+
+static int build_locking_user(u8 *buffer, size_t length, u8 lr)
+{
+	if (length > OPAL_UID_LENGTH) {
+		pr_err("Can't build locking range user, Length OOB\n");
+		return -ERANGE;
+	}
+
+	memcpy(buffer, opaluid[OPAL_USER1_UID], OPAL_UID_LENGTH);
+
+	buffer[7] = lr + 1;
+
+	return 0;
+}
+
+static void set_comid(struct opal_dev *cmd, u16 comid)
+{
+	struct opal_header *hdr = (struct opal_header *)cmd->cmd;
+
+	hdr->cp.extendedComID[0] = comid >> 8;
+	hdr->cp.extendedComID[1] = comid;
+	hdr->cp.extendedComID[2] = 0;
+	hdr->cp.extendedComID[3] = 0;
+}
+
+static int cmd_finalize(struct opal_dev *cmd, u32 hsn, u32 tsn)
+{
+	struct opal_header *hdr;
+	int err = 0;
+
+	add_token_u8(&err, cmd, OPAL_ENDOFDATA);
+	add_token_u8(&err, cmd, OPAL_STARTLIST);
+	add_token_u8(&err, cmd, 0);
+	add_token_u8(&err, cmd, 0);
+	add_token_u8(&err, cmd, 0);
+	add_token_u8(&err, cmd, OPAL_ENDLIST);
+
+	if (err) {
+		pr_err("Error finalizing command.\n");
+		return -EFAULT;
+	}
+
+	hdr = (struct opal_header *) cmd->cmd;
+
+	hdr->pkt.tsn = cpu_to_be32(tsn);
+	hdr->pkt.hsn = cpu_to_be32(hsn);
+
+	hdr->subpkt.length = cpu_to_be32(cmd->pos - sizeof(*hdr));
+	while (cmd->pos % 4) {
+		if (cmd->pos >= IO_BUFFER_LENGTH) {
+			pr_err("Error: Buffer overrun\n");
+			return -ERANGE;
+		}
+		cmd->cmd[cmd->pos++] = 0;
+	}
+	hdr->pkt.length = cpu_to_be32(cmd->pos - sizeof(hdr->cp) -
+				      sizeof(hdr->pkt));
+	hdr->cp.length = cpu_to_be32(cmd->pos - sizeof(hdr->cp));
+
+	return 0;
+}
+
+static const struct opal_resp_tok *response_get_token(
+				const struct parsed_resp *resp,
+				int n)
+{
+	const struct opal_resp_tok *tok;
+
+	if (n >= resp->num) {
+		pr_err("Token number doesn't exist: %d, resp: %d\n",
+		       n, resp->num);
+		return ERR_PTR(-EINVAL);
+	}
+
+	tok = &resp->toks[n];
+	if (tok->len == 0) {
+		pr_err("Token length must be non-zero\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	return tok;
+}
+
+static ssize_t response_parse_tiny(struct opal_resp_tok *tok,
+				   const u8 *pos)
+{
+	tok->pos = pos;
+	tok->len = 1;
+	tok->width = OPAL_WIDTH_TINY;
+
+	if (pos[0] & TINY_ATOM_SIGNED) {
+		tok->type = OPAL_DTA_TOKENID_SINT;
+	} else {
+		tok->type = OPAL_DTA_TOKENID_UINT;
+		tok->stored.u = pos[0] & 0x3f;
+	}
+
+	return tok->len;
+}
+
+static ssize_t response_parse_short(struct opal_resp_tok *tok,
+				    const u8 *pos)
+{
+	tok->pos = pos;
+	tok->len = (pos[0] & SHORT_ATOM_LEN_MASK) + 1;
+	tok->width = OPAL_WIDTH_SHORT;
+
+	if (pos[0] & SHORT_ATOM_BYTESTRING) {
+		tok->type = OPAL_DTA_TOKENID_BYTESTRING;
+	} else if (pos[0] & SHORT_ATOM_SIGNED) {
+		tok->type = OPAL_DTA_TOKENID_SINT;
+	} else {
+		u64 u_integer = 0;
+		ssize_t i, b = 0;
+
+		tok->type = OPAL_DTA_TOKENID_UINT;
+		if (tok->len > 9) {
+			pr_warn("uint64 with more than 8 bytes\n");
+			return -EINVAL;
+		}
+		for (i = tok->len - 1; i > 0; i--) {
+			u_integer |= ((u64)pos[i] << (8 * b));
+			b++;
+		}
+		tok->stored.u = u_integer;
+	}
+
+	return tok->len;
+}
+
+static ssize_t response_parse_medium(struct opal_resp_tok *tok,
+				     const u8 *pos)
+{
+	tok->pos = pos;
+	tok->len = (((pos[0] & MEDIUM_ATOM_LEN_MASK) << 8) | pos[1]) + 2;
+	tok->width = OPAL_WIDTH_MEDIUM;
+
+	if (pos[0] & MEDIUM_ATOM_BYTESTRING)
+		tok->type = OPAL_DTA_TOKENID_BYTESTRING;
+	else if (pos[0] & MEDIUM_ATOM_SIGNED)
+		tok->type = OPAL_DTA_TOKENID_SINT;
+	else
+		tok->type = OPAL_DTA_TOKENID_UINT;
+
+	return tok->len;
+}
+
+static ssize_t response_parse_long(struct opal_resp_tok *tok,
+				   const u8 *pos)
+{
+	tok->pos = pos;
+	tok->len = ((pos[1] << 16) | (pos[2] << 8) | pos[3]) + 4;
+	tok->width = OPAL_WIDTH_LONG;
+
+	if (pos[0] & LONG_ATOM_BYTESTRING)
+		tok->type = OPAL_DTA_TOKENID_BYTESTRING;
+	else if (pos[0] & LONG_ATOM_SIGNED)
+		tok->type = OPAL_DTA_TOKENID_SINT;
+	else
+		tok->type = OPAL_DTA_TOKENID_UINT;
+
+	return tok->len;
+}
+
+static ssize_t response_parse_token(struct opal_resp_tok *tok,
+				    const u8 *pos)
+{
+	tok->pos = pos;
+	tok->len = 1;
+	tok->type = OPAL_DTA_TOKENID_TOKEN;
+	tok->width = OPAL_WIDTH_TOKEN;
+
+	return tok->len;
+}
+
+static int response_parse(const u8 *buf, size_t length,
+			  struct parsed_resp *resp)
+{
+	const struct opal_header *hdr;
+	struct opal_resp_tok *iter;
+	int num_entries = 0;
+	int total;
+	ssize_t token_length;
+	const u8 *pos;
+	u32 clen, plen, slen;
+
+	if (!buf)
+		return -EFAULT;
+
+	if (!resp)
+		return -EFAULT;
+
+	hdr = (struct opal_header *)buf;
+	pos = buf;
+	pos += sizeof(*hdr);
+
+	clen = be32_to_cpu(hdr->cp.length);
+	plen = be32_to_cpu(hdr->pkt.length);
+	slen = be32_to_cpu(hdr->subpkt.length);
+	pr_debug("Response size: cp: %u, pkt: %u, subpkt: %u\n",
+		 clen, plen, slen);
+
+	if (clen == 0 || plen == 0 || slen == 0 ||
+	    slen > IO_BUFFER_LENGTH - sizeof(*hdr)) {
+		pr_err("Bad header length. cp: %u, pkt: %u, subpkt: %u\n",
+		       clen, plen, slen);
+		print_buffer(pos, sizeof(*hdr));
+		return -EINVAL;
+	}
+
+	if (pos > buf + length)
+		return -EFAULT;
+
+	iter = resp->toks;
+	total = slen;
+	print_buffer(pos, total);
+	while (total > 0) {
+		if (pos[0] <= TINY_ATOM_BYTE) /* tiny atom */
+			token_length = response_parse_tiny(iter, pos);
+		else if (pos[0] <= SHORT_ATOM_BYTE) /* short atom */
+			token_length = response_parse_short(iter, pos);
+		else if (pos[0] <= MEDIUM_ATOM_BYTE) /* medium atom */
+			token_length = response_parse_medium(iter, pos);
+		else if (pos[0] <= LONG_ATOM_BYTE) /* long atom */
+			token_length = response_parse_long(iter, pos);
+		else /* TOKEN */
+			token_length = response_parse_token(iter, pos);
+
+		if (token_length < 0)
+			return token_length;
+
+		pos += token_length;
+		total -= token_length;
+		iter++;
+		num_entries++;
+	}
+
+	if (num_entries == 0) {
+		pr_err("Couldn't parse response.\n");
+		return -EINVAL;
+	}
+	resp->num = num_entries;
+
+	return 0;
+}
+
+static size_t response_get_string(const struct parsed_resp *resp, int n,
+				  const char **store)
+{
+	*store = NULL;
+	if (!resp) {
+		pr_err("Response is NULL\n");
+		return 0;
+	}
+
+	if (n > resp->num) {
+		pr_err("Response has %d tokens. Can't access %d\n",
+		       resp->num, n);
+		return 0;
+	}
+
+	if (resp->toks[n].type != OPAL_DTA_TOKENID_BYTESTRING) {
+		pr_err("Token is not a byte string!\n");
+		return 0;
+	}
+
+	*store = resp->toks[n].pos + 1;
+	return resp->toks[n].len - 1;
+}
+
+static u64 response_get_u64(const struct parsed_resp *resp, int n)
+{
+	if (!resp) {
+		pr_err("Response is NULL\n");
+		return 0;
+	}
+
+	if (n > resp->num) {
+		pr_err("Response has %d tokens. Can't access %d\n",
+		       resp->num, n);
+		return 0;
+	}
+
+	if (resp->toks[n].type != OPAL_DTA_TOKENID_UINT) {
+		pr_err("Token is not unsigned it: %d\n",
+		       resp->toks[n].type);
+		return 0;
+	}
+
+	if (!(resp->toks[n].width == OPAL_WIDTH_TINY ||
+	      resp->toks[n].width == OPAL_WIDTH_SHORT)) {
+		pr_err("Atom is not short or tiny: %d\n",
+		       resp->toks[n].width);
+		return 0;
+	}
+
+	return resp->toks[n].stored.u;
+}
+
+static bool response_token_matches(const struct opal_resp_tok *token, u8 match)
+{
+	if (IS_ERR(token) ||
+	    token->type != OPAL_DTA_TOKENID_TOKEN ||
+	    token->pos[0] != match)
+		return false;
+	return true;
+}
+
+static u8 response_status(const struct parsed_resp *resp)
+{
+	const struct opal_resp_tok *tok;
+
+	tok = response_get_token(resp, 0);
+	if (response_token_matches(tok, OPAL_ENDOFSESSION))
+		return 0;
+
+	if (resp->num < 5)
+		return DTAERROR_NO_METHOD_STATUS;
+
+	tok = response_get_token(resp, resp->num - 5);
+	if (!response_token_matches(tok, OPAL_STARTLIST))
+		return DTAERROR_NO_METHOD_STATUS;
+
+	tok = response_get_token(resp, resp->num - 1);
+	if (!response_token_matches(tok, OPAL_ENDLIST))
+		return DTAERROR_NO_METHOD_STATUS;
+
+	return response_get_u64(resp, resp->num - 4);
+}
+
+/* Parses and checks for errors */
+static int parse_and_check_status(struct opal_dev *dev)
+{
+	int error;
+
+	print_buffer(dev->cmd, dev->pos);
+
+	error = response_parse(dev->resp, IO_BUFFER_LENGTH, &dev->parsed);
+	if (error) {
+		pr_err("Couldn't parse response.\n");
+		return error;
+	}
+
+	return response_status(&dev->parsed);
+}
+
+static void clear_opal_cmd(struct opal_dev *dev)
+{
+	dev->pos = sizeof(struct opal_header);
+	memset(dev->cmd, 0, IO_BUFFER_LENGTH);
+}
+
+static int start_opal_session_cont(struct opal_dev *dev)
+{
+	u32 hsn, tsn;
+	int error = 0;
+
+	error = parse_and_check_status(dev);
+	if (error)
+		return error;
+
+	hsn = response_get_u64(&dev->parsed, 4);
+	tsn = response_get_u64(&dev->parsed, 5);
+
+	if (hsn == 0 && tsn == 0) {
+		pr_err("Couldn't authenticate session\n");
+		return -EPERM;
+	}
+
+	dev->hsn = hsn;
+	dev->tsn = tsn;
+	return 0;
+}
+
+static void add_suspend_info(struct opal_dev *dev,
+			     struct opal_suspend_data *sus)
+{
+	struct opal_suspend_data *iter;
+
+	list_for_each_entry(iter, &dev->unlk_lst, node) {
+		if (iter->lr == sus->lr) {
+			list_del(&iter->node);
+			kfree(iter);
+			break;
+		}
+	}
+	list_add_tail(&sus->node, &dev->unlk_lst);
+}
+
+static int end_session_cont(struct opal_dev *dev)
+{
+	dev->hsn = 0;
+	dev->tsn = 0;
+	return parse_and_check_status(dev);
+}
+
+static int finalize_and_send(struct opal_dev *dev, cont_fn cont)
+{
+	int ret;
+
+	ret = cmd_finalize(dev, dev->hsn, dev->tsn);
+	if (ret) {
+		pr_err("Error finalizing command buffer: %d\n", ret);
+		return ret;
+	}
+
+	print_buffer(dev->cmd, dev->pos);
+
+	return opal_send_recv(dev, cont);
+}
+
+static int gen_key(struct opal_dev *dev, void *data)
+{
+	const u8 *method;
+	u8 uid[OPAL_UID_LENGTH];
+	int err = 0;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+
+	memcpy(uid, dev->prev_data, min(sizeof(uid), dev->prev_d_len));
+	method = opalmethod[OPAL_GENKEY];
+	kfree(dev->prev_data);
+	dev->prev_data = NULL;
+
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, uid, OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_GENKEY],
+			     OPAL_UID_LENGTH);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+
+	if (err) {
+		pr_err("Error building gen key command\n");
+		return err;
+
+	}
+	return finalize_and_send(dev, parse_and_check_status);
+}
+
+static int get_active_key_cont(struct opal_dev *dev)
+{
+	const char *activekey;
+	size_t keylen;
+	int error = 0;
+
+	error = parse_and_check_status(dev);
+	if (error)
+		return error;
+	keylen = response_get_string(&dev->parsed, 4, &activekey);
+	if (!activekey) {
+		pr_err("%s: Couldn't extract the Activekey from the response\n",
+		       __func__);
+		return OPAL_INVAL_PARAM;
+	}
+	dev->prev_data = kmemdup(activekey, keylen, GFP_KERNEL);
+
+	if (!dev->prev_data)
+		return -ENOMEM;
+
+	dev->prev_d_len = keylen;
+
+	return 0;
+}
+
+static int get_active_key(struct opal_dev *dev, void *data)
+{
+	u8 uid[OPAL_UID_LENGTH];
+	int err = 0;
+	u8 *lr = data;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+
+	err = build_locking_range(uid, sizeof(uid), *lr);
+	if (err)
+		return err;
+
+	err = 0;
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, uid, OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_GET], OPAL_UID_LENGTH);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, 3); /* startCloumn */
+	add_token_u8(&err, dev, 10); /* ActiveKey */
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, 4); /* endColumn */
+	add_token_u8(&err, dev, 10); /* ActiveKey */
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+	if (err) {
+		pr_err("Error building get active key command\n");
+		return err;
+	}
+
+	return finalize_and_send(dev, get_active_key_cont);
+}
+
+static int generic_lr_enable_disable(struct opal_dev *dev,
+				     u8 *uid, bool rle, bool wle,
+				     bool rl, bool wl)
+{
+	int err = 0;
+
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, uid, OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_SET], OPAL_UID_LENGTH);
+
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, OPAL_VALUES);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, 5); /* ReadLockEnabled */
+	add_token_u8(&err, dev, rle);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, 6); /* WriteLockEnabled */
+	add_token_u8(&err, dev, wle);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, OPAL_READLOCKED);
+	add_token_u8(&err, dev, rl);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, OPAL_WRITELOCKED);
+	add_token_u8(&err, dev, wl);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+	return err;
+}
+
+static inline int enable_global_lr(struct opal_dev *dev, u8 *uid,
+				   struct opal_user_lr_setup *setup)
+{
+	int err;
+
+	err = generic_lr_enable_disable(dev, uid, !!setup->RLE, !!setup->WLE,
+					0, 0);
+	if (err)
+		pr_err("Failed to create enable global lr command\n");
+	return err;
+}
+
+static int setup_locking_range(struct opal_dev *dev, void *data)
+{
+	u8 uid[OPAL_UID_LENGTH];
+	struct opal_user_lr_setup *setup = data;
+	u8 lr;
+	int err = 0;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+
+	lr = setup->session.opal_key.lr;
+	err = build_locking_range(uid, sizeof(uid), lr);
+	if (err)
+		return err;
+
+	if (lr == 0)
+		err = enable_global_lr(dev, uid, setup);
+	else {
+		add_token_u8(&err, dev, OPAL_CALL);
+		add_token_bytestring(&err, dev, uid, OPAL_UID_LENGTH);
+		add_token_bytestring(&err, dev, opalmethod[OPAL_SET],
+				     OPAL_UID_LENGTH);
+
+		add_token_u8(&err, dev, OPAL_STARTLIST);
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, OPAL_VALUES);
+		add_token_u8(&err, dev, OPAL_STARTLIST);
+
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, 3); /* Ranges Start */
+		add_token_u64(&err, dev, setup->range_start);
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, 4); /* Ranges length */
+		add_token_u64(&err, dev, setup->range_length);
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, 5); /*ReadLockEnabled */
+		add_token_u64(&err, dev, !!setup->RLE);
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, 6); /*WriteLockEnabled*/
+		add_token_u64(&err, dev, !!setup->WLE);
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+
+		add_token_u8(&err, dev, OPAL_ENDLIST);
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+		add_token_u8(&err, dev, OPAL_ENDLIST);
+
+	}
+	if (err) {
+		pr_err("Error building Setup Locking range command.\n");
+		return err;
+
+	}
+
+	return finalize_and_send(dev, parse_and_check_status);
+}
+
+static int start_generic_opal_session(struct opal_dev *dev,
+				      enum opal_uid auth,
+				      enum opal_uid sp_type,
+				      const char *key,
+				      u8 key_len)
+{
+	u32 hsn;
+	int err = 0;
+
+	if (key == NULL && auth != OPAL_ANYBODY_UID) {
+		pr_err("%s: Attempted to open ADMIN_SP Session without a Host" \
+		       "Challenge, and not as the Anybody UID\n", __func__);
+		return OPAL_INVAL_PARAM;
+	}
+
+	clear_opal_cmd(dev);
+
+	set_comid(dev, dev->comid);
+	hsn = GENERIC_HOST_SESSION_NUM;
+
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, opaluid[OPAL_SMUID_UID],
+			     OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_STARTSESSION],
+			     OPAL_UID_LENGTH);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u64(&err, dev, hsn);
+	add_token_bytestring(&err, dev, opaluid[sp_type], OPAL_UID_LENGTH);
+	add_token_u8(&err, dev, 1);
+
+	switch (auth) {
+	case OPAL_ANYBODY_UID:
+		add_token_u8(&err, dev, OPAL_ENDLIST);
+		break;
+	case OPAL_ADMIN1_UID:
+	case OPAL_SID_UID:
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, 0); /* HostChallenge */
+		add_token_bytestring(&err, dev, key, key_len);
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, 3); /* HostSignAuth */
+		add_token_bytestring(&err, dev, opaluid[auth],
+				     OPAL_UID_LENGTH);
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+		add_token_u8(&err, dev, OPAL_ENDLIST);
+		break;
+	default:
+		pr_err("Cannot start Admin SP session with auth %d\n", auth);
+		return OPAL_INVAL_PARAM;
+	}
+
+	if (err) {
+		pr_err("Error building start adminsp session command.\n");
+		return err;
+	}
+
+	return finalize_and_send(dev, start_opal_session_cont);
+}
+
+static int start_anybodyASP_opal_session(struct opal_dev *dev, void *data)
+{
+	return start_generic_opal_session(dev, OPAL_ANYBODY_UID,
+					  OPAL_ADMINSP_UID, NULL, 0);
+}
+
+static int start_SIDASP_opal_session(struct opal_dev *dev, void *data)
+{
+	int ret;
+	const u8 *key = dev->prev_data;
+
+	if (!key) {
+		const struct opal_key *okey = data;
+		ret = start_generic_opal_session(dev, OPAL_SID_UID,
+						 OPAL_ADMINSP_UID,
+						 okey->key,
+						 okey->key_len);
+	} else {
+		ret = start_generic_opal_session(dev, OPAL_SID_UID,
+						 OPAL_ADMINSP_UID,
+						 key, dev->prev_d_len);
+		kfree(key);
+		dev->prev_data = NULL;
+	}
+	return ret;
+}
+
+static int start_admin1LSP_opal_session(struct opal_dev *dev, void *data)
+{
+	struct opal_key *key = data;
+	return start_generic_opal_session(dev, OPAL_ADMIN1_UID,
+					  OPAL_LOCKINGSP_UID,
+					  key->key, key->key_len);
+}
+
+static int start_auth_opal_session(struct opal_dev *dev, void *data)
+{
+	struct opal_session_info *session = data;
+	u8 lk_ul_user[OPAL_UID_LENGTH];
+	size_t keylen = session->opal_key.key_len;
+	int err = 0;
+
+	u8 *key = session->opal_key.key;
+	u32 hsn = GENERIC_HOST_SESSION_NUM;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+
+	if (session->sum) {
+		err = build_locking_user(lk_ul_user, sizeof(lk_ul_user),
+					 session->opal_key.lr);
+		if (err)
+			return err;
+
+	} else if (session->who != OPAL_ADMIN1 && !session->sum) {
+		err = build_locking_user(lk_ul_user, sizeof(lk_ul_user),
+					 session->who - 1);
+		if (err)
+			return err;
+	} else
+		memcpy(lk_ul_user, opaluid[OPAL_ADMIN1_UID], OPAL_UID_LENGTH);
+
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, opaluid[OPAL_SMUID_UID],
+			     OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_STARTSESSION],
+			     OPAL_UID_LENGTH);
+
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u64(&err, dev, hsn);
+	add_token_bytestring(&err, dev, opaluid[OPAL_LOCKINGSP_UID],
+			     OPAL_UID_LENGTH);
+	add_token_u8(&err, dev, 1);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, 0);
+	add_token_bytestring(&err, dev, key, keylen);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, 3);
+	add_token_bytestring(&err, dev, lk_ul_user, OPAL_UID_LENGTH);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+
+	if (err) {
+		pr_err("Error building STARTSESSION command.\n");
+		return err;
+	}
+
+	return finalize_and_send(dev, start_opal_session_cont);
+}
+
+static int revert_tper(struct opal_dev *dev, void *data)
+{
+	int err = 0;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, opaluid[OPAL_ADMINSP_UID],
+			     OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_REVERT],
+			     OPAL_UID_LENGTH);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+	if (err) {
+		pr_err("Error building REVERT TPER command.\n");
+		return err;
+	}
+
+	return finalize_and_send(dev, parse_and_check_status);
+}
+
+static int internal_activate_user(struct opal_dev *dev, void *data)
+{
+	struct opal_session_info *session = data;
+	u8 uid[OPAL_UID_LENGTH];
+	int err = 0;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+
+	memcpy(uid, opaluid[OPAL_USER1_UID], OPAL_UID_LENGTH);
+	uid[7] = session->who;
+
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, uid, OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_SET], OPAL_UID_LENGTH);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, OPAL_VALUES);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, 5); /* Enabled */
+	add_token_u8(&err, dev, OPAL_TRUE);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+
+	if (err) {
+		pr_err("Error building Activate UserN command.\n");
+		return err;
+	}
+
+	return finalize_and_send(dev, parse_and_check_status);
+}
+
+static int erase_locking_range(struct opal_dev *dev, void *data)
+{
+	struct opal_session_info *session = data;
+	u8 uid[OPAL_UID_LENGTH];
+	int err = 0;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+
+	if (build_locking_range(uid, sizeof(uid), session->opal_key.lr) < 0)
+		return -ERANGE;
+
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, uid, OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_ERASE],
+			     OPAL_UID_LENGTH);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+
+	if (err) {
+		pr_err("Error building Erase Locking Range Command.\n");
+		return err;
+	}
+	return finalize_and_send(dev, parse_and_check_status);
+}
+
+static int set_mbr_done(struct opal_dev *dev, void *data)
+{
+	u8 *mbr_done_tf = data;
+	int err = 0;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, opaluid[OPAL_MBRCONTROL],
+			     OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_SET], OPAL_UID_LENGTH);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, OPAL_VALUES);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, 2); /* Done */
+	add_token_u8(&err, dev, *mbr_done_tf); /* Done T or F */
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+
+	if (err) {
+		pr_err("Error Building set MBR Done command\n");
+		return err;
+	}
+
+	return finalize_and_send(dev, parse_and_check_status);
+}
+
+static int set_mbr_enable_disable(struct opal_dev *dev, void *data)
+{
+	u8 *mbr_en_dis = data;
+	int err = 0;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, opaluid[OPAL_MBRCONTROL],
+			     OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_SET], OPAL_UID_LENGTH);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, OPAL_VALUES);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, 1);
+	add_token_u8(&err, dev, *mbr_en_dis);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+
+	if (err) {
+		pr_err("Error Building set MBR done command\n");
+		return err;
+	}
+
+	return finalize_and_send(dev, parse_and_check_status);
+}
+
+static int generic_pw_cmd(u8 *key, size_t key_len, u8 *cpin_uid,
+			  struct opal_dev *dev)
+{
+	int err = 0;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, cpin_uid, OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_SET],
+			     OPAL_UID_LENGTH);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, OPAL_VALUES);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, 3); /* PIN */
+	add_token_bytestring(&err, dev, key, key_len);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+
+	return err;
+}
+
+static int set_new_pw(struct opal_dev *dev, void *data)
+{
+	u8 cpin_uid[OPAL_UID_LENGTH];
+	struct opal_session_info *usr = data;
+
+	memcpy(cpin_uid, opaluid[OPAL_C_PIN_ADMIN1], OPAL_UID_LENGTH);
+
+	if (usr->who != OPAL_ADMIN1) {
+		cpin_uid[5] = 0x03;
+		if (usr->sum)
+			cpin_uid[7] = usr->opal_key.lr + 1;
+		else
+			cpin_uid[7] = usr->who;
+	}
+
+	if (generic_pw_cmd(usr->opal_key.key, usr->opal_key.key_len,
+			   cpin_uid, dev)) {
+		pr_err("Error building set password command.\n");
+		return -ERANGE;
+	}
+
+	return finalize_and_send(dev, parse_and_check_status);
+}
+
+static int set_sid_cpin_pin(struct opal_dev *dev, void *data)
+{
+	u8 cpin_uid[OPAL_UID_LENGTH];
+	struct opal_key *key = data;
+
+	memcpy(cpin_uid, opaluid[OPAL_C_PIN_SID], OPAL_UID_LENGTH);
+
+	if (generic_pw_cmd(key->key, key->key_len, cpin_uid, dev)) {
+		pr_err("Error building Set SID cpin\n");
+		return -ERANGE;
+	}
+	return finalize_and_send(dev, parse_and_check_status);
+}
+
+static int add_user_to_lr(struct opal_dev *dev, void *data)
+{
+	u8 lr_buffer[OPAL_UID_LENGTH];
+	u8 user_uid[OPAL_UID_LENGTH];
+	struct opal_lock_unlock *lkul = data;
+	int err = 0;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+
+	memcpy(lr_buffer, opaluid[OPAL_LOCKINGRANGE_ACE_RDLOCKED],
+	       OPAL_UID_LENGTH);
+
+	if (lkul->l_state == OPAL_RW)
+		memcpy(lr_buffer, opaluid[OPAL_LOCKINGRANGE_ACE_WRLOCKED],
+		       OPAL_UID_LENGTH);
+
+	lr_buffer[7] = lkul->session.opal_key.lr;
+
+	memcpy(user_uid, opaluid[OPAL_USER1_UID], OPAL_UID_LENGTH);
+
+	user_uid[7] = lkul->session.who;
+
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, lr_buffer, OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_SET],
+			     OPAL_UID_LENGTH);
+
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, OPAL_VALUES);
+
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, 3);
+
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+
+
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_bytestring(&err, dev,
+			     opaluid[OPAL_HALF_UID_AUTHORITY_OBJ_REF],
+			     OPAL_UID_LENGTH/2);
+	add_token_bytestring(&err, dev, user_uid, OPAL_UID_LENGTH);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+
+
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_bytestring(&err, dev,
+			     opaluid[OPAL_HALF_UID_AUTHORITY_OBJ_REF],
+			     OPAL_UID_LENGTH/2);
+	add_token_bytestring(&err, dev, user_uid, OPAL_UID_LENGTH);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+
+
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_bytestring(&err, dev, opaluid[OPAL_HALF_UID_BOOLEAN_ACE],
+			     OPAL_UID_LENGTH/2);
+	add_token_u8(&err, dev, 1);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+
+
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+
+	if (err) {
+		pr_err("Error building add user to locking range command.\n");
+		return err;
+	}
+
+	return finalize_and_send(dev, parse_and_check_status);
+}
+
+static int lock_unlock_locking_range(struct opal_dev *dev, void *data)
+{
+	u8 lr_buffer[OPAL_UID_LENGTH];
+	const u8 *method;
+	struct opal_lock_unlock *lkul = data;
+	u8 read_locked = 1, write_locked = 1;
+	int err = 0;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+
+	method = opalmethod[OPAL_SET];
+	if (build_locking_range(lr_buffer, sizeof(lr_buffer),
+				lkul->session.opal_key.lr) < 0)
+		return -ERANGE;
+
+	switch (lkul->l_state) {
+	case OPAL_RO:
+		read_locked = 0;
+		write_locked = 1;
+		break;
+	case OPAL_RW:
+		read_locked = 0;
+		write_locked = 0;
+		break;
+	case OPAL_LK:
+		/* vars are initalized to locked */
+		break;
+	default:
+		pr_err("Tried to set an invalid locking state... returning to uland\n");
+		return OPAL_INVAL_PARAM;
+	}
+
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, lr_buffer, OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_SET], OPAL_UID_LENGTH);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, OPAL_VALUES);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, OPAL_READLOCKED);
+	add_token_u8(&err, dev, read_locked);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, OPAL_WRITELOCKED);
+	add_token_u8(&err, dev, write_locked);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+
+	if (err) {
+		pr_err("Error building SET command.\n");
+		return err;
+	}
+	return finalize_and_send(dev, parse_and_check_status);
+}
+
+
+static int lock_unlock_locking_range_sum(struct opal_dev *dev, void *data)
+{
+	u8 lr_buffer[OPAL_UID_LENGTH];
+	u8 read_locked = 1, write_locked = 1;
+	const u8 *method;
+	struct opal_lock_unlock *lkul = data;
+	int ret;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+
+	method = opalmethod[OPAL_SET];
+	if (build_locking_range(lr_buffer, sizeof(lr_buffer),
+				lkul->session.opal_key.lr) < 0)
+		return -ERANGE;
+
+	switch (lkul->l_state) {
+	case OPAL_RO:
+		read_locked = 0;
+		write_locked = 1;
+		break;
+	case OPAL_RW:
+		read_locked = 0;
+		write_locked = 0;
+		break;
+	case OPAL_LK:
+		/* vars are initalized to locked */
+		break;
+	default:
+		pr_err("Tried to set an invalid locking state.\n");
+		return OPAL_INVAL_PARAM;
+	}
+	ret = generic_lr_enable_disable(dev, lr_buffer, 1, 1,
+					read_locked, write_locked);
+
+	if (ret < 0) {
+		pr_err("Error building SET command.\n");
+		return ret;
+	}
+	return finalize_and_send(dev, parse_and_check_status);
+}
+
+static int activate_lsp(struct opal_dev *dev, void *data)
+{
+	struct opal_lr_act *opal_act = data;
+	u8 user_lr[OPAL_UID_LENGTH];
+	u8 uint_3 = 0x83;
+	int err = 0, i;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, opaluid[OPAL_LOCKINGSP_UID],
+			     OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_ACTIVATE],
+			     OPAL_UID_LENGTH);
+
+
+	if (opal_act->sum) {
+		err = build_locking_range(user_lr, sizeof(user_lr),
+					  opal_act->lr[0]);
+		if (err)
+			return err;
+
+		add_token_u8(&err, dev, OPAL_STARTLIST);
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, uint_3);
+		add_token_u8(&err, dev, 6);
+		add_token_u8(&err, dev, 0);
+		add_token_u8(&err, dev, 0);
+
+		add_token_u8(&err, dev, OPAL_STARTLIST);
+		add_token_bytestring(&err, dev, user_lr, OPAL_UID_LENGTH);
+		for (i = 1; i < opal_act->num_lrs; i++) {
+			user_lr[7] = opal_act->lr[i];
+			add_token_bytestring(&err, dev, user_lr, OPAL_UID_LENGTH);
+		}
+		add_token_u8(&err, dev, OPAL_ENDLIST);
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+		add_token_u8(&err, dev, OPAL_ENDLIST);
+
+	} else {
+		add_token_u8(&err, dev, OPAL_STARTLIST);
+		add_token_u8(&err, dev, OPAL_ENDLIST);
+	}
+
+	if (err) {
+		pr_err("Error building Activate LockingSP command.\n");
+		return err;
+	}
+
+	return finalize_and_send(dev, parse_and_check_status);
+}
+
+static int get_lsp_lifecycle_cont(struct opal_dev *dev)
+{
+	u8 lc_status;
+	int error = 0;
+
+	error = parse_and_check_status(dev);
+	if (error)
+		return error;
+
+	lc_status = response_get_u64(&dev->parsed, 4);
+	/* 0x08 is Manufacured Inactive */
+	/* 0x09 is Manufactured */
+	if (lc_status != OPAL_MANUFACTURED_INACTIVE) {
+		pr_err("Couldn't determine the status of the Lifcycle state\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+/* Determine if we're in the Manufactured Inactive or Active state */
+static int get_lsp_lifecycle(struct opal_dev *dev, void *data)
+{
+	int err = 0;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, opaluid[OPAL_LOCKINGSP_UID],
+			     OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_GET], OPAL_UID_LENGTH);
+
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, 3); /* Start Column */
+	add_token_u8(&err, dev, 6); /* Lifecycle Column */
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, 4); /* End Column */
+	add_token_u8(&err, dev, 6); /* Lifecycle Column */
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+
+	if (err) {
+		pr_err("Error Building GET Lifecycle Status command\n");
+		return err;
+	}
+
+	return finalize_and_send(dev, get_lsp_lifecycle_cont);
+}
+
+static int get_msid_cpin_pin_cont(struct opal_dev *dev)
+{
+	const char *msid_pin;
+	size_t strlen;
+	int error = 0;
+
+	error = parse_and_check_status(dev);
+	if (error)
+		return error;
+
+	strlen = response_get_string(&dev->parsed, 4, &msid_pin);
+	if (!msid_pin) {
+		pr_err("%s: Couldn't extract PIN from response\n", __func__);
+		return OPAL_INVAL_PARAM;
+	}
+
+	dev->prev_data = kmemdup(msid_pin, strlen, GFP_KERNEL);
+	if (!dev->prev_data)
+		return -ENOMEM;
+
+	dev->prev_d_len = strlen;
+
+	return 0;
+}
+
+static int get_msid_cpin_pin(struct opal_dev *dev, void *data)
+{
+	int err = 0;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, opaluid[OPAL_C_PIN_MSID],
+			     OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_GET], OPAL_UID_LENGTH);
+
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, 3); /* Start Column */
+	add_token_u8(&err, dev, 3); /* PIN */
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, 4); /* End Column */
+	add_token_u8(&err, dev, 3); /* Lifecycle Column */
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+
+	if (err) {
+		pr_err("Error building Get MSID CPIN PIN command.\n");
+		return err;
+	}
+
+	return finalize_and_send(dev, get_msid_cpin_pin_cont);
+}
+
+static int end_opal_session(struct opal_dev *dev, void *data)
+{
+	int err = 0;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+	add_token_u8(&err, dev, OPAL_ENDOFSESSION);
+
+	if (err < 0)
+		return err;
+	return finalize_and_send(dev, end_session_cont);
+}
+
+static int end_opal_session_error(struct opal_dev *dev)
+{
+	const struct opal_step error_end_session[] = {
+		{ end_opal_session, },
+		{ NULL, }
+	};
+	dev->steps = error_end_session;
+	return next(dev);
+}
+
+static inline void setup_opal_dev(struct opal_dev *dev,
+				  const struct opal_step *steps)
+{
+	dev->steps = steps;
+	dev->tsn = 0;
+	dev->hsn = 0;
+	dev->prev_data = NULL;
+}
+
+static int check_opal_support(struct opal_dev *dev)
+{
+	const struct opal_step steps[] = {
+		{ opal_discovery0, },
+		{ NULL, }
+	};
+	int ret;
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev, steps);
+	ret = next(dev);
+	dev->supported = !ret;
+	mutex_unlock(&dev->dev_lock);
+	return ret;
+}
+
+static void clean_opal_dev(struct opal_dev *dev)
+{
+
+	struct opal_suspend_data *suspend, *next;
+
+	mutex_lock(&dev->dev_lock);
+	list_for_each_entry_safe(suspend, next, &dev->unlk_lst, node) {
+		list_del(&suspend->node);
+		kfree(suspend);
+	}
+	mutex_unlock(&dev->dev_lock);
+}
+
+void free_opal_dev(struct opal_dev *dev)
+{
+	if (!dev)
+		return;
+	clean_opal_dev(dev);
+	kfree(dev);
+}
+EXPORT_SYMBOL(free_opal_dev);
+
+struct opal_dev *init_opal_dev(void *data, sec_send_recv *send_recv)
+{
+	struct opal_dev *dev;
+
+	dev = kmalloc(sizeof(*dev), GFP_KERNEL);
+	if (!dev)
+		return NULL;
+
+	INIT_LIST_HEAD(&dev->unlk_lst);
+	mutex_init(&dev->dev_lock);
+	dev->data = data;
+	dev->send_recv = send_recv;
+	if (check_opal_support(dev) != 0) {
+		pr_debug("Opal is not supported on this device\n");
+		kfree(dev);
+		return NULL;
+	}
+	return dev;
+}
+EXPORT_SYMBOL(init_opal_dev);
+
+static int opal_secure_erase_locking_range(struct opal_dev *dev,
+					   struct opal_session_info *opal_session)
+{
+	const struct opal_step erase_steps[] = {
+		{ opal_discovery0, },
+		{ start_auth_opal_session, opal_session },
+		{ get_active_key, &opal_session->opal_key.lr },
+		{ gen_key, },
+		{ end_opal_session, },
+		{ NULL, }
+	};
+	int ret;
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev, erase_steps);
+	ret = next(dev);
+	mutex_unlock(&dev->dev_lock);
+	return ret;
+}
+
+static int opal_erase_locking_range(struct opal_dev *dev,
+				    struct opal_session_info *opal_session)
+{
+	const struct opal_step erase_steps[] = {
+		{ opal_discovery0, },
+		{ start_auth_opal_session, opal_session },
+		{ erase_locking_range, opal_session },
+		{ end_opal_session, },
+		{ NULL, }
+	};
+	int ret;
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev, erase_steps);
+	ret = next(dev);
+	mutex_unlock(&dev->dev_lock);
+	return ret;
+}
+
+static int opal_enable_disable_shadow_mbr(struct opal_dev *dev,
+					  struct opal_mbr_data *opal_mbr)
+{
+	const struct opal_step mbr_steps[] = {
+		{ opal_discovery0, },
+		{ start_admin1LSP_opal_session, &opal_mbr->key },
+		{ set_mbr_done, &opal_mbr->enable_disable },
+		{ end_opal_session, },
+		{ start_admin1LSP_opal_session, &opal_mbr->key },
+		{ set_mbr_enable_disable, &opal_mbr->enable_disable },
+		{ end_opal_session, },
+		{ NULL, }
+	};
+	int ret;
+
+	if (opal_mbr->enable_disable != OPAL_MBR_ENABLE &&
+	    opal_mbr->enable_disable != OPAL_MBR_DISABLE)
+		return -EINVAL;
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev, mbr_steps);
+	ret = next(dev);
+	mutex_unlock(&dev->dev_lock);
+	return ret;
+}
+
+static int opal_save(struct opal_dev *dev, struct opal_lock_unlock *lk_unlk)
+{
+	struct opal_suspend_data *suspend;
+
+	suspend = kzalloc(sizeof(*suspend), GFP_KERNEL);
+	if (!suspend)
+		return -ENOMEM;
+
+	suspend->unlk = *lk_unlk;
+	suspend->lr = lk_unlk->session.opal_key.lr;
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev, NULL);
+	add_suspend_info(dev, suspend);
+	mutex_unlock(&dev->dev_lock);
+	return 0;
+}
+
+static int opal_add_user_to_lr(struct opal_dev *dev,
+			       struct opal_lock_unlock *lk_unlk)
+{
+	const struct opal_step steps[] = {
+		{ opal_discovery0, },
+		{ start_admin1LSP_opal_session, &lk_unlk->session.opal_key },
+		{ add_user_to_lr, lk_unlk },
+		{ end_opal_session, },
+		{ NULL, }
+	};
+	int ret;
+
+	if (lk_unlk->l_state != OPAL_RO &&
+	    lk_unlk->l_state != OPAL_RW) {
+		pr_err("Locking state was not RO or RW\n");
+		return -EINVAL;
+	}
+	if (lk_unlk->session.who < OPAL_USER1 &&
+	    lk_unlk->session.who > OPAL_USER9) {
+		pr_err("Authority was not within the range of users: %d\n",
+		       lk_unlk->session.who);
+		return -EINVAL;
+	}
+	if (lk_unlk->session.sum) {
+		pr_err("%s not supported in sum. Use setup locking range\n",
+		       __func__);
+		return -EINVAL;
+	}
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev, steps);
+	ret = next(dev);
+	mutex_unlock(&dev->dev_lock);
+	return ret;
+}
+
+static int opal_reverttper(struct opal_dev *dev, struct opal_key *opal)
+{
+	const struct opal_step revert_steps[] = {
+		{ opal_discovery0, },
+		{ start_SIDASP_opal_session, opal },
+		{ revert_tper, }, /* controller will terminate session */
+		{ NULL, }
+	};
+	int ret;
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev, revert_steps);
+	ret = next(dev);
+	mutex_unlock(&dev->dev_lock);
+
+	/*
+	 * If we successfully reverted lets clean
+	 * any saved locking ranges.
+	 */
+	if (!ret)
+		clean_opal_dev(dev);
+
+	return ret;
+}
+
+static int __opal_lock_unlock(struct opal_dev *dev,
+			      struct opal_lock_unlock *lk_unlk)
+{
+	const struct opal_step unlock_steps[] = {
+		{ opal_discovery0, },
+		{ start_auth_opal_session, &lk_unlk->session },
+		{ lock_unlock_locking_range, lk_unlk },
+		{ end_opal_session, },
+		{ NULL, }
+	};
+	const struct opal_step unlock_sum_steps[] = {
+		{ opal_discovery0, },
+		{ start_auth_opal_session, &lk_unlk->session },
+		{ lock_unlock_locking_range_sum, lk_unlk },
+		{ end_opal_session, },
+		{ NULL, }
+	};
+
+	dev->steps = lk_unlk->session.sum ? unlock_sum_steps : unlock_steps;
+	return next(dev);
+}
+
+static int opal_lock_unlock(struct opal_dev *dev,
+			    struct opal_lock_unlock *lk_unlk)
+{
+	int ret;
+
+	if (lk_unlk->session.who < OPAL_ADMIN1 ||
+	    lk_unlk->session.who > OPAL_USER9)
+		return -EINVAL;
+
+	mutex_lock(&dev->dev_lock);
+	ret = __opal_lock_unlock(dev, lk_unlk);
+	mutex_unlock(&dev->dev_lock);
+	return ret;
+}
+
+static int opal_take_ownership(struct opal_dev *dev, struct opal_key *opal)
+{
+	const struct opal_step owner_steps[] = {
+		{ opal_discovery0, },
+		{ start_anybodyASP_opal_session, },
+		{ get_msid_cpin_pin, },
+		{ end_opal_session, },
+		{ start_SIDASP_opal_session, opal },
+		{ set_sid_cpin_pin, opal },
+		{ end_opal_session, },
+		{ NULL, }
+	};
+	int ret;
+
+	if (!dev)
+		return -ENODEV;
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev, owner_steps);
+	ret = next(dev);
+	mutex_unlock(&dev->dev_lock);
+	return ret;
+}
+
+static int opal_activate_lsp(struct opal_dev *dev, struct opal_lr_act *opal_lr_act)
+{
+	const struct opal_step active_steps[] = {
+		{ opal_discovery0, },
+		{ start_SIDASP_opal_session, &opal_lr_act->key },
+		{ get_lsp_lifecycle, },
+		{ activate_lsp, opal_lr_act },
+		{ end_opal_session, },
+		{ NULL, }
+	};
+	int ret;
+
+	if (!opal_lr_act->num_lrs || opal_lr_act->num_lrs > OPAL_MAX_LRS)
+		return -EINVAL;
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev, active_steps);
+	ret = next(dev);
+	mutex_unlock(&dev->dev_lock);
+	return ret;
+}
+
+static int opal_setup_locking_range(struct opal_dev *dev,
+				    struct opal_user_lr_setup *opal_lrs)
+{
+	const struct opal_step lr_steps[] = {
+		{ opal_discovery0, },
+		{ start_auth_opal_session, &opal_lrs->session },
+		{ setup_locking_range, opal_lrs },
+		{ end_opal_session, },
+		{ NULL, }
+	};
+	int ret;
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev, lr_steps);
+	ret = next(dev);
+	mutex_unlock(&dev->dev_lock);
+	return ret;
+}
+
+static int opal_set_new_pw(struct opal_dev *dev, struct opal_new_pw *opal_pw)
+{
+	const struct opal_step pw_steps[] = {
+		{ opal_discovery0, },
+		{ start_auth_opal_session, &opal_pw->session },
+		{ set_new_pw, &opal_pw->new_user_pw },
+		{ end_opal_session, },
+		{ NULL }
+	};
+	int ret;
+
+	if (opal_pw->session.who < OPAL_ADMIN1 ||
+	    opal_pw->session.who > OPAL_USER9  ||
+	    opal_pw->new_user_pw.who < OPAL_ADMIN1 ||
+	    opal_pw->new_user_pw.who > OPAL_USER9)
+		return -EINVAL;
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev, pw_steps);
+	ret = next(dev);
+	mutex_unlock(&dev->dev_lock);
+	return ret;
+}
+
+static int opal_activate_user(struct opal_dev *dev,
+			      struct opal_session_info *opal_session)
+{
+	const struct opal_step act_steps[] = {
+		{ opal_discovery0, },
+		{ start_admin1LSP_opal_session, &opal_session->opal_key },
+		{ internal_activate_user, opal_session },
+		{ end_opal_session, },
+		{ NULL, }
+	};
+	int ret;
+
+	/* We can't activate Admin1 it's active as manufactured */
+	if (opal_session->who < OPAL_USER1 &&
+	    opal_session->who > OPAL_USER9) {
+		pr_err("Who was not a valid user: %d\n", opal_session->who);
+		return -EINVAL;
+	}
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev, act_steps);
+	ret = next(dev);
+	mutex_unlock(&dev->dev_lock);
+	return ret;
+}
+
+bool opal_unlock_from_suspend(struct opal_dev *dev)
+{
+	struct opal_suspend_data *suspend;
+	bool was_failure = false;
+	int ret = 0;
+
+	if (!dev)
+		return false;
+	if (!dev->supported)
+		return false;
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev, NULL);
+
+	list_for_each_entry(suspend, &dev->unlk_lst, node) {
+		dev->tsn = 0;
+		dev->hsn = 0;
+
+		ret = __opal_lock_unlock(dev, &suspend->unlk);
+		if (ret) {
+			pr_warn("Failed to unlock LR %hhu with sum %d\n",
+				suspend->unlk.session.opal_key.lr,
+				suspend->unlk.session.sum);
+			was_failure = true;
+		}
+	}
+	mutex_unlock(&dev->dev_lock);
+	return was_failure;
+}
+EXPORT_SYMBOL(opal_unlock_from_suspend);
+
+int sed_ioctl(struct opal_dev *dev, unsigned int cmd, void __user *arg)
+{
+	void *p;
+	int ret = -ENOTTY;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+	if (!dev)
+		return -ENOTSUPP;
+	if (!dev->supported) {
+		pr_err("Not supported\n");
+		return -ENOTSUPP;
+	}
+
+	p = memdup_user(arg, _IOC_SIZE(cmd));
+	if (IS_ERR(p))
+		return PTR_ERR(p);
+
+	switch (cmd) {
+	case IOC_OPAL_SAVE:
+		ret = opal_save(dev, p);
+		break;
+	case IOC_OPAL_LOCK_UNLOCK:
+		ret = opal_lock_unlock(dev, p);
+		break;
+	case IOC_OPAL_TAKE_OWNERSHIP:
+		ret = opal_take_ownership(dev, p);
+		break;
+	case IOC_OPAL_ACTIVATE_LSP:
+		ret = opal_activate_lsp(dev, p);
+		break;
+	case IOC_OPAL_SET_PW:
+		ret = opal_set_new_pw(dev, p);
+		break;
+	case IOC_OPAL_ACTIVATE_USR:
+		ret = opal_activate_user(dev, p);
+		break;
+	case IOC_OPAL_REVERT_TPR:
+		ret = opal_reverttper(dev, p);
+		break;
+	case IOC_OPAL_LR_SETUP:
+		ret = opal_setup_locking_range(dev, p);
+		break;
+	case IOC_OPAL_ADD_USR_TO_LR:
+		ret = opal_add_user_to_lr(dev, p);
+		break;
+	case IOC_OPAL_ENABLE_DISABLE_MBR:
+		ret = opal_enable_disable_shadow_mbr(dev, p);
+		break;
+	case IOC_OPAL_ERASE_LR:
+		ret = opal_erase_locking_range(dev, p);
+		break;
+	case IOC_OPAL_SECURE_ERASE_LR:
+		ret = opal_secure_erase_locking_range(dev, p);
+		break;
+	default:
+		pr_warn("No such Opal Ioctl %u\n", cmd);
+	}
+
+	kfree(p);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(sed_ioctl);