Merge branch 'for-4.11/next' into for-4.11/linus-merge

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

31 files changed, 640 insertions, 509 deletions

diff --git a/block/Kconfig b/block/Kconfig
index 1aef809affae..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.
diff --git a/block/Makefile b/block/Makefile
index 6ba1b1bc9529..2ad7c304e3f5 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -7,10 +7,11 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-tag.o blk-sysfs.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 blk-mq-sched.o ioctl.o \
-			genhd.o scsi_ioctl.o partition-generic.o ioprio.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
diff --git a/block/bio.c b/block/bio.c
index d3c26d1cb1da..4b564d0c3e29 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1227,9 +1227,6 @@ 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) {
@@ -1394,12 +1391,6 @@ 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);
 
 	/*
@@ -1590,7 +1581,6 @@ 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 fb59a3edc778..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;
diff --git a/block/blk-core.c b/block/blk-core.c
index b2df55a65250..b9e857f4afe8 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -33,6 +33,7 @@
 #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>
@@ -42,6 +43,10 @@
 #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);
@@ -75,7 +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
 }
 
@@ -86,7 +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
 }
 
@@ -105,22 +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));
@@ -132,8 +121,6 @@ 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;
@@ -160,10 +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",
@@ -171,13 +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);
 
@@ -588,7 +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)
@@ -600,7 +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);
@@ -608,17 +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)
 {
@@ -631,10 +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;
 
@@ -697,7 +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);
@@ -712,17 +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);
@@ -772,7 +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:
@@ -825,15 +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;
 }
@@ -841,30 +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
 	 */
@@ -878,17 +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);
 
@@ -1024,25 +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 (op_is_flush(bio->bi_opf))
-		return false;
-
-	return true;
-}
-
 /**
  * __get_request - get a free request
  * @rl: request list to allocate from
@@ -1121,10 +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)
@@ -1184,7 +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;
@@ -1278,8 +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);
 
@@ -1309,18 +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
@@ -1510,6 +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
@@ -1538,12 +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)
@@ -1552,7 +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)++;
@@ -1568,19 +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)
@@ -1609,7 +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;
 
@@ -1623,8 +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;
 
@@ -1661,21 +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:
@@ -2452,14 +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);
 }
@@ -2530,10 +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;
 
@@ -2605,7 +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 */
@@ -2683,8 +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);
 
@@ -3007,8 +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;
@@ -3484,5 +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 ed1f10165268..8cd0e9bc8dc8 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -11,11 +11,6 @@
 #include "blk.h"
 #include "blk-mq-sched.h"
 
-/*
- * for max sense size
- */
-#include <scsi/scsi_cmnd.h>
-
 /**
  * blk_end_sync_rq - executes a completion event on a request
  * @rq: request to complete
@@ -56,7 +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;
@@ -101,16 +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);
 
@@ -124,11 +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 4427896641ac..0d5a9c1da1fc 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -297,8 +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;
@@ -327,7 +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;
@@ -547,11 +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 fe186a9eade9..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;
@@ -166,6 +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;
 
@@ -184,13 +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);
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 6aa43dec5af4..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->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
index 5cd2b435a9f5..f6d917977b33 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -19,6 +19,7 @@
 #include <linux/debugfs.h>
 
 #include <linux/blk-mq.h>
+#include "blk.h"
 #include "blk-mq.h"
 #include "blk-mq-tag.h"
 
@@ -28,8 +29,6 @@ struct blk_mq_debugfs_attr {
 	const struct file_operations *fops;
 };
 
-static struct dentry *block_debugfs_root;
-
 static int blk_mq_debugfs_seq_open(struct inode *inode, struct file *file,
 				   const struct seq_operations *ops)
 {
@@ -88,13 +87,14 @@ static int blk_mq_debugfs_rq_show(struct seq_file *m, void *v)
 {
 	struct request *rq = list_entry_rq(v);
 
-	seq_printf(m, "%p {.cmd_type=%u, .cmd_flags=0x%x, .rq_flags=0x%x, .tag=%d, .internal_tag=%d}\n",
-		   rq, rq->cmd_type, rq->cmd_flags, (unsigned int)rq->rq_flags,
+	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;
 
@@ -110,6 +110,7 @@ static void *hctx_dispatch_next(struct seq_file *m, void *v, loff_t *pos)
 }
 
 static void hctx_dispatch_stop(struct seq_file *m, void *v)
+	__releases(&hctx->lock)
 {
 	struct blk_mq_hw_ctx *hctx = m->private;
 
@@ -176,13 +177,17 @@ 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;
 
-	mutex_lock(&q->sysfs_lock);
+	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);
 
-	return 0;
+out:
+	return res;
 }
 
 static int hctx_tags_open(struct inode *inode, struct file *file)
@@ -201,12 +206,17 @@ 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;
 
-	mutex_lock(&q->sysfs_lock);
+	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);
-	return 0;
+
+out:
+	return res;
 }
 
 static int hctx_tags_bitmap_open(struct inode *inode, struct file *file)
@@ -225,13 +235,17 @@ 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;
 
-	mutex_lock(&q->sysfs_lock);
+	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);
 
-	return 0;
+out:
+	return res;
 }
 
 static int hctx_sched_tags_open(struct inode *inode, struct file *file)
@@ -250,12 +264,17 @@ 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;
 
-	mutex_lock(&q->sysfs_lock);
+	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);
-	return 0;
+
+out:
+	return res;
 }
 
 static int hctx_sched_tags_bitmap_open(struct inode *inode, struct file *file)
@@ -482,6 +501,7 @@ static const struct file_operations hctx_active_fops = {
 };
 
 static void *ctx_rq_list_start(struct seq_file *m, loff_t *pos)
+	__acquires(&ctx->lock)
 {
 	struct blk_mq_ctx *ctx = m->private;
 
@@ -497,6 +517,7 @@ static void *ctx_rq_list_next(struct seq_file *m, void *v, loff_t *pos)
 }
 
 static void ctx_rq_list_stop(struct seq_file *m, void *v)
+	__releases(&ctx->lock)
 {
 	struct blk_mq_ctx *ctx = m->private;
 
@@ -630,6 +651,7 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = {
 	{"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[] = {
@@ -637,14 +659,15 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_ctx_attrs[] = {
 	{"dispatched", 0600, &ctx_dispatched_fops},
 	{"merged", 0600, &ctx_merged_fops},
 	{"completed", 0600, &ctx_completed_fops},
+	{},
 };
 
 int blk_mq_debugfs_register(struct request_queue *q, const char *name)
 {
-	if (!block_debugfs_root)
+	if (!blk_debugfs_root)
 		return -ENOENT;
 
-	q->debugfs_dir = debugfs_create_dir(name, block_debugfs_root);
+	q->debugfs_dir = debugfs_create_dir(name, blk_debugfs_root);
 	if (!q->debugfs_dir)
 		goto err;
 
@@ -665,27 +688,31 @@ void blk_mq_debugfs_unregister(struct request_queue *q)
 	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];
-	int i;
 
 	snprintf(name, sizeof(name), "cpu%u", ctx->cpu);
 	ctx_dir = debugfs_create_dir(name, hctx_dir);
 	if (!ctx_dir)
 		return -ENOMEM;
 
-	for (i = 0; i < ARRAY_SIZE(blk_mq_debugfs_ctx_attrs); i++) {
-		const struct blk_mq_debugfs_attr *attr;
-
-		attr = &blk_mq_debugfs_ctx_attrs[i];
-		if (!debugfs_create_file(attr->name, attr->mode, ctx_dir, ctx,
-					 attr->fops))
-			return -ENOMEM;
-	}
+	if (!debugfs_create_files(ctx_dir, ctx, blk_mq_debugfs_ctx_attrs))
+		return -ENOMEM;
 
 	return 0;
 }
@@ -703,14 +730,8 @@ static int blk_mq_debugfs_register_hctx(struct request_queue *q,
 	if (!hctx_dir)
 		return -ENOMEM;
 
-	for (i = 0; i < ARRAY_SIZE(blk_mq_debugfs_hctx_attrs); i++) {
-		const struct blk_mq_debugfs_attr *attr;
-
-		attr = &blk_mq_debugfs_hctx_attrs[i];
-		if (!debugfs_create_file(attr->name, attr->mode, hctx_dir, hctx,
-					 attr->fops))
-			return -ENOMEM;
-	}
+	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))
@@ -749,8 +770,3 @@ void blk_mq_debugfs_unregister_hctxs(struct request_queue *q)
 	debugfs_remove_recursive(q->mq_debugfs_dir);
 	q->mq_debugfs_dir = NULL;
 }
-
-void blk_mq_debugfs_init(void)
-{
-	block_debugfs_root = debugfs_create_dir("block", NULL);
-}
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 114814ec3d49..9e8d6795a8c1 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -68,7 +68,9 @@ error:
 EXPORT_SYMBOL_GPL(blk_mq_sched_init_hctx_data);
 
 static void __blk_mq_sched_assign_ioc(struct request_queue *q,
-				      struct request *rq, struct io_context *ioc)
+				      struct request *rq,
+				      struct bio *bio,
+				      struct io_context *ioc)
 {
 	struct io_cq *icq;
 
@@ -83,7 +85,7 @@ static void __blk_mq_sched_assign_ioc(struct request_queue *q,
 	}
 
 	rq->elv.icq = icq;
-	if (!blk_mq_sched_get_rq_priv(q, rq)) {
+	if (!blk_mq_sched_get_rq_priv(q, rq, bio)) {
 		rq->rq_flags |= RQF_ELVPRIV;
 		get_io_context(icq->ioc);
 		return;
@@ -99,7 +101,7 @@ static void blk_mq_sched_assign_ioc(struct request_queue *q,
 
 	ioc = rq_ioc(bio);
 	if (ioc)
-		__blk_mq_sched_assign_ioc(q, rq, ioc);
+		__blk_mq_sched_assign_ioc(q, rq, bio, ioc);
 }
 
 struct request *blk_mq_sched_get_request(struct request_queue *q,
@@ -173,6 +175,8 @@ void blk_mq_sched_put_request(struct 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)))
@@ -202,11 +206,18 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 	 */
 	if (!list_empty(&rq_list)) {
 		blk_mq_sched_mark_restart(hctx);
-		blk_mq_dispatch_rq_list(hctx, &rq_list);
-	} else if (!e || !e->type->ops.mq.dispatch_request) {
+		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);
-	} else {
+	}
+
+	/*
+	 * 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;
 
@@ -234,31 +245,33 @@ void blk_mq_sched_move_to_dispatch(struct blk_mq_hw_ctx *hctx,
 }
 EXPORT_SYMBOL_GPL(blk_mq_sched_move_to_dispatch);
 
-bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio)
+bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
+			    struct request **merged_request)
 {
 	struct request *rq;
-	int ret;
 
-	ret = elv_merge(q, &rq, bio);
-	if (ret == ELEVATOR_BACK_MERGE) {
+	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)) {
-			if (!attempt_back_merge(q, rq))
-				elv_merged_request(q, rq, ret);
-			return true;
-		}
-	} else if (ret == ELEVATOR_FRONT_MERGE) {
+		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)) {
-			if (!attempt_front_merge(q, rq))
-				elv_merged_request(q, rq, ret);
-			return true;
-		}
+		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;
 	}
-
-	return false;
 }
 EXPORT_SYMBOL_GPL(blk_mq_sched_try_merge);
 
@@ -289,7 +302,8 @@ void blk_mq_sched_request_inserted(struct request *rq)
 }
 EXPORT_SYMBOL_GPL(blk_mq_sched_request_inserted);
 
-bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx, struct request *rq)
+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;
@@ -305,7 +319,6 @@ bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx, struct request *rq)
 	spin_unlock(&hctx->lock);
 	return true;
 }
-EXPORT_SYMBOL_GPL(blk_mq_sched_bypass_insert);
 
 static void blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx)
 {
@@ -347,7 +360,7 @@ static void blk_mq_sched_insert_flush(struct blk_mq_hw_ctx *hctx,
 		blk_insert_flush(rq);
 		blk_mq_run_hw_queue(hctx, true);
 	} else
-		blk_mq_add_to_requeue_list(rq, true, true);
+		blk_mq_add_to_requeue_list(rq, false, true);
 }
 
 void blk_mq_sched_insert_request(struct request *rq, bool at_head,
@@ -363,6 +376,9 @@ void blk_mq_sched_insert_request(struct request *rq, bool at_head,
 		return;
 	}
 
+	if (e && blk_mq_sched_bypass_insert(hctx, rq))
+		goto run;
+
 	if (e && e->type->ops.mq.insert_requests) {
 		LIST_HEAD(list);
 
@@ -374,6 +390,7 @@ void blk_mq_sched_insert_request(struct request *rq, bool at_head,
 		spin_unlock(&ctx->lock);
 	}
 
+run:
 	if (run_queue)
 		blk_mq_run_hw_queue(hctx, async);
 }
@@ -385,6 +402,23 @@ void blk_mq_sched_insert_requests(struct request_queue *q,
 	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
diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h
index 9478aaeb48c5..7b5f3b95c78e 100644
--- a/block/blk-mq-sched.h
+++ b/block/blk-mq-sched.h
@@ -15,8 +15,8 @@ struct request *blk_mq_sched_get_request(struct request_queue *q, struct bio *bi
 void blk_mq_sched_put_request(struct request *rq);
 
 void blk_mq_sched_request_inserted(struct request *rq);
-bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx, struct request *rq);
-bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio);
+bool blk_mq_sched_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);
@@ -49,12 +49,13 @@ blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
 }
 
 static inline int blk_mq_sched_get_rq_priv(struct request_queue *q,
-					   struct request *rq)
+					   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);
+		return e->type->ops.mq.get_rq_priv(q, rq, bio);
 
 	return 0;
 }
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index 308b3f4fc310..295e69670c39 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -254,7 +254,7 @@ static void __blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
 		kobject_put(&hctx->kobj);
 	}
 
-	blk_mq_debugfs_unregister(q);
+	blk_mq_debugfs_unregister_hctxs(q);
 
 	kobject_uevent(&q->mq_kobj, KOBJ_REMOVE);
 	kobject_del(&q->mq_kobj);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 489076e7ae15..b29e7dc7b309 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -199,13 +199,7 @@ 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;
@@ -487,10 +481,6 @@ void blk_mq_start_request(struct request *rq)
 
 	trace_block_rq_issue(q, 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);
-
 	if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
 		blk_stat_set_issue_time(&rq->issue_stat);
 		rq->rq_flags |= RQF_STATS;
@@ -773,7 +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;
@@ -781,26 +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_NO_MERGE)
-			continue;
-
-		if (!blk_mq_sched_allow_merge(q, rq, bio))
+		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;
-
-		if (el_ret == ELEVATOR_BACK_MERGE) {
-			if (bio_attempt_back_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;
-		} else if (el_ret == ELEVATOR_FRONT_MERGE) {
-			if (bio_attempt_front_merge(q, rq, bio)) {
-				ctx->rq_merged++;
-				return true;
-			}
+		case ELEVATOR_DISCARD_MERGE:
+			merged = bio_attempt_discard_merge(q, rq, bio);
 			break;
+		default:
+			continue;
 		}
+
+		if (merged)
+			ctx->rq_merged++;
+		return merged;
 	}
 
 	return false;
@@ -1013,7 +1002,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 			blk_mq_run_hw_queue(hctx, true);
 	}
 
-	return ret != BLK_MQ_RQ_QUEUE_BUSY;
+	return queued != 0;
 }
 
 static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
@@ -1442,12 +1431,11 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	cookie = request_to_qc_t(data.hctx, rq);
 
 	if (unlikely(is_flush_fua)) {
-		blk_mq_put_ctx(data.ctx);
+		if (q->elevator)
+			goto elv_insert;
 		blk_mq_bio_to_request(rq, bio);
-		blk_mq_get_driver_tag(rq, NULL, true);
 		blk_insert_flush(rq);
-		blk_mq_run_hw_queue(data.hctx, true);
-		goto done;
+		goto run_queue;
 	}
 
 	plug = current->plug;
@@ -1497,6 +1485,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	}
 
 	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,
@@ -1510,6 +1499,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		 * latter allows for merging opportunities and more efficient
 		 * dispatching.
 		 */
+run_queue:
 		blk_mq_run_hw_queue(data.hctx, !is_sync || is_flush_fua);
 	}
 	blk_mq_put_ctx(data.ctx);
@@ -1565,12 +1555,11 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 	cookie = request_to_qc_t(data.hctx, rq);
 
 	if (unlikely(is_flush_fua)) {
-		blk_mq_put_ctx(data.ctx);
+		if (q->elevator)
+			goto elv_insert;
 		blk_mq_bio_to_request(rq, bio);
-		blk_mq_get_driver_tag(rq, NULL, true);
 		blk_insert_flush(rq);
-		blk_mq_run_hw_queue(data.hctx, true);
-		goto done;
+		goto run_queue;
 	}
 
 	/*
@@ -1608,6 +1597,7 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 	}
 
 	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,
@@ -1621,6 +1611,7 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 		 * latter allows for merging opportunities and more efficient
 		 * dispatching.
 		 */
+run_queue:
 		blk_mq_run_hw_queue(data.hctx, !is_sync || is_flush_fua);
 	}
 
@@ -2637,10 +2628,14 @@ 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);
 	}
@@ -2824,8 +2819,6 @@ void blk_mq_enable_hotplug(void)
 
 static int __init blk_mq_init(void)
 {
-	blk_mq_debugfs_init();
-
 	cpuhp_setup_state_multi(CPUHP_BLK_MQ_DEAD, "block/mq:dead", NULL,
 				blk_mq_hctx_notify_dead);
 
diff --git a/block/blk-mq.h b/block/blk-mq.h
index b52abd62b1b0..24b2256186f3 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -85,16 +85,11 @@ extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
  * debugfs helpers
  */
 #ifdef CONFIG_BLK_DEBUG_FS
-void blk_mq_debugfs_init(void);
 int blk_mq_debugfs_register(struct request_queue *q, const char *name);
 void blk_mq_debugfs_unregister(struct request_queue *q);
 int blk_mq_debugfs_register_hctxs(struct request_queue *q);
 void blk_mq_debugfs_unregister_hctxs(struct request_queue *q);
 #else
-static inline void blk_mq_debugfs_init(void)
-{
-}
-
 static inline int blk_mq_debugfs_register(struct request_queue *q,
 					  const char *name)
 {
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-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 9a716b5925a4..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);
@@ -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;
 }
 
 /*
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..a9a8b8e0446f 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;
@@ -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;
@@ -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 f0f29ee731e1..921262770636 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);
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 05fc0ea25a98..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;
 
diff --git a/block/elevator.c b/block/elevator.c
index b2a55167f0c2..699d10f71a2c 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -428,11 +428,11 @@ 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:
@@ -447,7 +447,8 @@ 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;
@@ -515,7 +516,8 @@ bool elv_attempt_insert_merge(struct request_queue *q, struct request *rq)
 	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;
 
@@ -539,7 +541,7 @@ void elv_merge_requests(struct request_queue *q, struct request *rq,
 	if (e->uses_mq && e->type->ops.mq.requests_merged)
 		e->type->ops.mq.requests_merged(q, rq, next);
 	else if (e->type->ops.sq.elevator_merge_req_fn) {
-		next_sorted = next->rq_flags & RQF_SORTED;
+		next_sorted = (__force bool)(next->rq_flags & RQF_SORTED);
 		if (next_sorted)
 			e->type->ops.sq.elevator_merge_req_fn(q, rq, next);
 	}
@@ -635,7 +637,7 @@ 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;
 		}
@@ -677,7 +679,7 @@ 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)) {
diff --git a/block/genhd.c b/block/genhd.c
index fcd6d4fae657..3631cd480295 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,
@@ -648,6 +669,8 @@ void del_gendisk(struct gendisk *disk)
 	disk_part_iter_init(&piter, disk,
 			     DISK_PITER_INCL_EMPTY | DISK_PITER_REVERSE);
 	while ((part = disk_part_iter_next(&piter))) {
+		bdev_unhash_inode(MKDEV(disk->major,
+					disk->first_minor + part->partno));
 		invalidate_partition(disk, part->partno);
 		delete_partition(disk, part->partno);
 	}
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/mq-deadline.c b/block/mq-deadline.c
index d93ec713fa62..236121633ca0 100644
--- a/block/mq-deadline.c
+++ b/block/mq-deadline.c
@@ -121,7 +121,7 @@ static void deadline_remove_request(struct request_queue *q, struct request *rq)
 }
 
 static void dd_request_merged(struct request_queue *q, struct request *req,
-			      int type)
+			      enum elv_merge type)
 {
 	struct deadline_data *dd = q->elevator->elevator_data;
 
@@ -371,12 +371,16 @@ static bool dd_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio)
 {
 	struct request_queue *q = hctx->queue;
 	struct deadline_data *dd = q->elevator->elevator_data;
-	int ret;
+	struct request *free = NULL;
+	bool ret;
 
 	spin_lock(&dd->lock);
-	ret = blk_mq_sched_try_merge(q, bio);
+	ret = blk_mq_sched_try_merge(q, bio, &free);
 	spin_unlock(&dd->lock);
 
+	if (free)
+		blk_mq_free_request(free);
+
 	return ret;
 }
 
@@ -395,10 +399,7 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 
 	blk_mq_sched_request_inserted(rq);
 
-	if (blk_mq_sched_bypass_insert(hctx, rq))
-		return;
-
-	if (at_head || rq->cmd_type != REQ_TYPE_FS) {
+	if (at_head || blk_rq_is_passthrough(rq)) {
 		if (at_head)
 			list_add(&rq->queuelist, &dd->dispatch);
 		else
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);