Merge tag 'for-4.11/linus-merge-signed' of git://git.kernel.dk/linux-block

Pull block layer updates from Jens Axboe:

 - blk-mq scheduling framework from me and Omar, with a port of the
   deadline scheduler for this framework. A port of BFQ from Paolo is in
   the works, and should be ready for 4.12.

 - Various fixups and improvements to the above scheduling framework
   from Omar, Paolo, Bart, me, others.

 - Cleanup of the exported sysfs blk-mq data into debugfs, from Omar.
   This allows us to export more information that helps debug hangs or
   performance issues, without cluttering or abusing the sysfs API.

 - Fixes for the sbitmap code, the scalable bitmap code that was
   migrated from blk-mq, from Omar.

 - Removal of the BLOCK_PC support in struct request, and refactoring of
   carrying SCSI payloads in the block layer. This cleans up the code
   nicely, and enables us to kill the SCSI specific parts of struct
   request, shrinking it down nicely. From Christoph mainly, with help
   from Hannes.

 - Support for ranged discard requests and discard merging, also from
   Christoph.

 - Support for OPAL in the block layer, and for NVMe as well. Mainly
   from Scott Bauer, with fixes/updates from various others folks.

 - Error code fixup for gdrom from Christophe.

 - cciss pci irq allocation cleanup from Christoph.

 - Making the cdrom device operations read only, from Kees Cook.

 - Fixes for duplicate bdi registrations and bdi/queue life time
   problems from Jan and Dan.

 - Set of fixes and updates for lightnvm, from Matias and Javier.

 - A few fixes for nbd from Josef, using idr to name devices and a
   workqueue deadlock fix on receive. Also marks Josef as the current
   maintainer of nbd.

 - Fix from Josef, overwriting queue settings when the number of
   hardware queues is updated for a blk-mq device.

 - NVMe fix from Keith, ensuring that we don't repeatedly mark and IO
   aborted, if we didn't end up aborting it.

 - SG gap merging fix from Ming Lei for block.

 - Loop fix also from Ming, fixing a race and crash between setting loop
   status and IO.

 - Two block race fixes from Tahsin, fixing request list iteration and
   fixing a race between device registration and udev device add
   notifiations.

 - Double free fix from cgroup writeback, from Tejun.

 - Another double free fix in blkcg, from Hou Tao.

 - Partition overflow fix for EFI from Alden Tondettar.

* tag 'for-4.11/linus-merge-signed' of git://git.kernel.dk/linux-block: (156 commits)
  nvme: Check for Security send/recv support before issuing commands.
  block/sed-opal: allocate struct opal_dev dynamically
  block/sed-opal: tone down not supported warnings
  block: don't defer flushes on blk-mq + scheduling
  blk-mq-sched: ask scheduler for work, if we failed dispatching leftovers
  blk-mq: don't special case flush inserts for blk-mq-sched
  blk-mq-sched: don't add flushes to the head of requeue queue
  blk-mq: have blk_mq_dispatch_rq_list() return if we queued IO or not
  block: do not allow updates through sysfs until registration completes
  lightnvm: set default lun range when no luns are specified
  lightnvm: fix off-by-one error on target initialization
  Maintainers: Modify SED list from nvme to block
  Move stack parameters for sed_ioctl to prevent oversized stack with CONFIG_KASAN
  uapi: sed-opal fix IOW for activate lsp to use correct struct
  cdrom: Make device operations read-only
  elevator: fix loading wrong elevator type for blk-mq devices
  cciss: switch to pci_irq_alloc_vectors
  block/loop: fix race between I/O and set_status
  blk-mq-sched: don't hold queue_lock when calling exit_icq
  block: set make_request_fn manually in blk_mq_update_nr_hw_queues
  ...

40 files changed, 6322 insertions, 1050 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..0715ce93daef 100644
--- a/block/Kconfig.iosched
+++ b/block/Kconfig.iosched
@@ -63,6 +63,56 @@ config DEFAULT_IOSCHED
 	default "cfq" if DEFAULT_CFQ
 	default "noop" if DEFAULT_NOOP
 
+config MQ_IOSCHED_DEADLINE
+	tristate "MQ deadline I/O scheduler"
+	default y
+	---help---
+	  MQ version of the deadline IO scheduler.
+
+config MQ_IOSCHED_NONE
+	bool
+	default y
+
+choice
+	prompt "Default single-queue blk-mq I/O scheduler"
+	default DEFAULT_SQ_NONE
+	help
+	  Select the I/O scheduler which will be used by default for blk-mq
+	  managed block devices with a single queue.
+
+	config DEFAULT_SQ_DEADLINE
+		bool "MQ Deadline" if MQ_IOSCHED_DEADLINE=y
+
+	config DEFAULT_SQ_NONE
+		bool "None"
+
+endchoice
+
+config DEFAULT_SQ_IOSCHED
+	string
+	default "mq-deadline" if DEFAULT_SQ_DEADLINE
+	default "none" if DEFAULT_SQ_NONE
+
+choice
+	prompt "Default multi-queue blk-mq I/O scheduler"
+	default DEFAULT_MQ_NONE
+	help
+	  Select the I/O scheduler which will be used by default for blk-mq
+	  managed block devices with multiple queues.
+
+	config DEFAULT_MQ_DEADLINE
+		bool "MQ Deadline" if MQ_IOSCHED_DEADLINE=y
+
+	config DEFAULT_MQ_NONE
+		bool "None"
+
+endchoice
+
+config DEFAULT_MQ_IOSCHED
+	string
+	default "mq-deadline" if DEFAULT_MQ_DEADLINE
+	default "none" if DEFAULT_MQ_NONE
+
 endmenu
 
 endif
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..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) {
@@ -1394,16 +1391,10 @@ 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 +1436,8 @@ 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 +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 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;