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
  ...

25 files changed, 610 insertions, 223 deletions

diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index e850e76acaaf..ad955817916d 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -10,6 +10,7 @@
 #include <linux/flex_proportions.h>
 #include <linux/timer.h>
 #include <linux/workqueue.h>
+#include <linux/kref.h>
 
 struct page;
 struct device;
@@ -144,6 +145,7 @@ struct backing_dev_info {
 
 	char *name;
 
+	struct kref refcnt;	/* Reference counter for the structure */
 	unsigned int capabilities; /* Device capabilities */
 	unsigned int min_ratio;
 	unsigned int max_ratio, max_prop_frac;
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 43b93a947e61..c52a48cb9a66 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -18,7 +18,14 @@
 #include <linux/slab.h>
 
 int __must_check bdi_init(struct backing_dev_info *bdi);
-void bdi_exit(struct backing_dev_info *bdi);
+
+static inline struct backing_dev_info *bdi_get(struct backing_dev_info *bdi)
+{
+	kref_get(&bdi->refcnt);
+	return bdi;
+}
+
+void bdi_put(struct backing_dev_info *bdi);
 
 __printf(3, 4)
 int bdi_register(struct backing_dev_info *bdi, struct device *parent,
@@ -29,6 +36,7 @@ void bdi_unregister(struct backing_dev_info *bdi);
 
 int __must_check bdi_setup_and_register(struct backing_dev_info *, char *);
 void bdi_destroy(struct backing_dev_info *bdi);
+struct backing_dev_info *bdi_alloc_node(gfp_t gfp_mask, int node_id);
 
 void wb_start_writeback(struct bdi_writeback *wb, long nr_pages,
 			bool range_cyclic, enum wb_reason reason);
@@ -183,7 +191,7 @@ static inline struct backing_dev_info *inode_to_bdi(struct inode *inode)
 	sb = inode->i_sb;
 #ifdef CONFIG_BLOCK
 	if (sb_is_blkdev_sb(sb))
-		return blk_get_backing_dev_info(I_BDEV(inode));
+		return I_BDEV(inode)->bd_bdi;
 #endif
 	return sb->s_bdi;
 }
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 4a2ab5d99ff7..8e4df3d6c8cd 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -22,6 +22,7 @@ struct blk_mq_hw_ctx {
 
 	unsigned long		flags;		/* BLK_MQ_F_* flags */
 
+	void			*sched_data;
 	struct request_queue	*queue;
 	struct blk_flush_queue	*fq;
 
@@ -35,6 +36,7 @@ struct blk_mq_hw_ctx {
 	atomic_t		wait_index;
 
 	struct blk_mq_tags	*tags;
+	struct blk_mq_tags	*sched_tags;
 
 	struct srcu_struct	queue_rq_srcu;
 
@@ -60,7 +62,7 @@ struct blk_mq_hw_ctx {
 
 struct blk_mq_tag_set {
 	unsigned int		*mq_map;
-	struct blk_mq_ops	*ops;
+	const struct blk_mq_ops	*ops;
 	unsigned int		nr_hw_queues;
 	unsigned int		queue_depth;	/* max hw supported */
 	unsigned int		reserved_tags;
@@ -151,11 +153,13 @@ enum {
 	BLK_MQ_F_SG_MERGE	= 1 << 2,
 	BLK_MQ_F_DEFER_ISSUE	= 1 << 4,
 	BLK_MQ_F_BLOCKING	= 1 << 5,
+	BLK_MQ_F_NO_SCHED	= 1 << 6,
 	BLK_MQ_F_ALLOC_POLICY_START_BIT = 8,
 	BLK_MQ_F_ALLOC_POLICY_BITS = 1,
 
 	BLK_MQ_S_STOPPED	= 0,
 	BLK_MQ_S_TAG_ACTIVE	= 1,
+	BLK_MQ_S_SCHED_RESTART	= 2,
 
 	BLK_MQ_MAX_DEPTH	= 10240,
 
@@ -179,14 +183,13 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set);
 
 void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);
 
-void blk_mq_insert_request(struct request *, bool, bool, bool);
 void blk_mq_free_request(struct request *rq);
-void blk_mq_free_hctx_request(struct blk_mq_hw_ctx *, struct request *rq);
 bool blk_mq_can_queue(struct blk_mq_hw_ctx *);
 
 enum {
 	BLK_MQ_REQ_NOWAIT	= (1 << 0), /* return when out of requests */
 	BLK_MQ_REQ_RESERVED	= (1 << 1), /* allocate from reserved pool */
+	BLK_MQ_REQ_INTERNAL	= (1 << 2), /* allocate internal/sched tag */
 };
 
 struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 519ea2c9df61..d703acb55d0f 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -162,6 +162,13 @@ enum req_opf {
 	/* write the zero filled sector many times */
 	REQ_OP_WRITE_ZEROES	= 8,
 
+	/* SCSI passthrough using struct scsi_request */
+	REQ_OP_SCSI_IN		= 32,
+	REQ_OP_SCSI_OUT		= 33,
+	/* Driver private requests */
+	REQ_OP_DRV_IN		= 34,
+	REQ_OP_DRV_OUT		= 35,
+
 	REQ_OP_LAST,
 };
 
@@ -221,6 +228,15 @@ static inline bool op_is_write(unsigned int op)
 }
 
 /*
+ * Check if the bio or request is one that needs special treatment in the
+ * flush state machine.
+ */
+static inline bool op_is_flush(unsigned int op)
+{
+	return op & (REQ_FUA | REQ_PREFLUSH);
+}
+
+/*
  * Reads are always treated as synchronous, as are requests with the FUA or
  * PREFLUSH flag.  Other operations may be marked as synchronous using the
  * REQ_SYNC flag.
@@ -232,22 +248,29 @@ static inline bool op_is_sync(unsigned int op)
 }
 
 typedef unsigned int blk_qc_t;
-#define BLK_QC_T_NONE	-1U
-#define BLK_QC_T_SHIFT	16
+#define BLK_QC_T_NONE		-1U
+#define BLK_QC_T_SHIFT		16
+#define BLK_QC_T_INTERNAL	(1U << 31)
 
 static inline bool blk_qc_t_valid(blk_qc_t cookie)
 {
 	return cookie != BLK_QC_T_NONE;
 }
 
-static inline blk_qc_t blk_tag_to_qc_t(unsigned int tag, unsigned int queue_num)
+static inline blk_qc_t blk_tag_to_qc_t(unsigned int tag, unsigned int queue_num,
+				       bool internal)
 {
-	return tag | (queue_num << BLK_QC_T_SHIFT);
+	blk_qc_t ret = tag | (queue_num << BLK_QC_T_SHIFT);
+
+	if (internal)
+		ret |= BLK_QC_T_INTERNAL;
+
+	return ret;
 }
 
 static inline unsigned int blk_qc_t_to_queue_num(blk_qc_t cookie)
 {
-	return cookie >> BLK_QC_T_SHIFT;
+	return (cookie & ~BLK_QC_T_INTERNAL) >> BLK_QC_T_SHIFT;
 }
 
 static inline unsigned int blk_qc_t_to_tag(blk_qc_t cookie)
@@ -255,6 +278,11 @@ static inline unsigned int blk_qc_t_to_tag(blk_qc_t cookie)
 	return cookie & ((1u << BLK_QC_T_SHIFT) - 1);
 }
 
+static inline bool blk_qc_t_is_internal(blk_qc_t cookie)
+{
+	return (cookie & BLK_QC_T_INTERNAL) != 0;
+}
+
 struct blk_issue_stat {
 	u64 time;
 };
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 1ca8e8fd1078..aecca0e7d9ca 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -71,15 +71,6 @@ struct request_list {
 };
 
 /*
- * request command types
- */
-enum rq_cmd_type_bits {
-	REQ_TYPE_FS		= 1,	/* fs request */
-	REQ_TYPE_BLOCK_PC,		/* scsi command */
-	REQ_TYPE_DRV_PRIV,		/* driver defined types from here */
-};
-
-/*
  * request flags */
 typedef __u32 __bitwise req_flags_t;
 
@@ -128,8 +119,6 @@ typedef __u32 __bitwise req_flags_t;
 #define RQF_NOMERGE_FLAGS \
 	(RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD)
 
-#define BLK_MAX_CDB	16
-
 /*
  * Try to put the fields that are referenced together in the same cacheline.
  *
@@ -147,13 +136,16 @@ struct request {
 	struct blk_mq_ctx *mq_ctx;
 
 	int cpu;
-	unsigned cmd_type;
 	unsigned int cmd_flags;		/* op and common flags */
 	req_flags_t rq_flags;
+
+	int internal_tag;
+
 	unsigned long atomic_flags;
 
 	/* the following two fields are internal, NEVER access directly */
 	unsigned int __data_len;	/* total data len */
+	int tag;
 	sector_t __sector;		/* sector cursor */
 
 	struct bio *bio;
@@ -222,20 +214,9 @@ struct request {
 
 	void *special;		/* opaque pointer available for LLD use */
 
-	int tag;
 	int errors;
 
-	/*
-	 * when request is used as a packet command carrier
-	 */
-	unsigned char __cmd[BLK_MAX_CDB];
-	unsigned char *cmd;
-	unsigned short cmd_len;
-
 	unsigned int extra_len;	/* length of alignment and padding */
-	unsigned int sense_len;
-	unsigned int resid_len;	/* residual count */
-	void *sense;
 
 	unsigned long deadline;
 	struct list_head timeout_list;
@@ -252,6 +233,21 @@ struct request {
 	struct request *next_rq;
 };
 
+static inline bool blk_rq_is_scsi(struct request *rq)
+{
+	return req_op(rq) == REQ_OP_SCSI_IN || req_op(rq) == REQ_OP_SCSI_OUT;
+}
+
+static inline bool blk_rq_is_private(struct request *rq)
+{
+	return req_op(rq) == REQ_OP_DRV_IN || req_op(rq) == REQ_OP_DRV_OUT;
+}
+
+static inline bool blk_rq_is_passthrough(struct request *rq)
+{
+	return blk_rq_is_scsi(rq) || blk_rq_is_private(rq);
+}
+
 static inline unsigned short req_get_ioprio(struct request *req)
 {
 	return req->ioprio;
@@ -271,6 +267,8 @@ typedef void (softirq_done_fn)(struct request *);
 typedef int (dma_drain_needed_fn)(struct request *);
 typedef int (lld_busy_fn) (struct request_queue *q);
 typedef int (bsg_job_fn) (struct bsg_job *);
+typedef int (init_rq_fn)(struct request_queue *, struct request *, gfp_t);
+typedef void (exit_rq_fn)(struct request_queue *, struct request *);
 
 enum blk_eh_timer_return {
 	BLK_EH_NOT_HANDLED,
@@ -333,6 +331,7 @@ struct queue_limits {
 	unsigned short		logical_block_size;
 	unsigned short		max_segments;
 	unsigned short		max_integrity_segments;
+	unsigned short		max_discard_segments;
 
 	unsigned char		misaligned;
 	unsigned char		discard_misaligned;
@@ -406,8 +405,10 @@ struct request_queue {
 	rq_timed_out_fn		*rq_timed_out_fn;
 	dma_drain_needed_fn	*dma_drain_needed;
 	lld_busy_fn		*lld_busy_fn;
+	init_rq_fn		*init_rq_fn;
+	exit_rq_fn		*exit_rq_fn;
 
-	struct blk_mq_ops	*mq_ops;
+	const struct blk_mq_ops	*mq_ops;
 
 	unsigned int		*mq_map;
 
@@ -432,7 +433,8 @@ struct request_queue {
 	 */
 	struct delayed_work	delay_work;
 
-	struct backing_dev_info	backing_dev_info;
+	struct backing_dev_info	*backing_dev_info;
+	struct disk_devt	*disk_devt;
 
 	/*
 	 * The queue owner gets to use this for whatever they like.
@@ -569,7 +571,15 @@ struct request_queue {
 	struct list_head	tag_set_list;
 	struct bio_set		*bio_split;
 
+#ifdef CONFIG_BLK_DEBUG_FS
+	struct dentry		*debugfs_dir;
+	struct dentry		*mq_debugfs_dir;
+#endif
+
 	bool			mq_sysfs_init_done;
+
+	size_t			cmd_size;
+	void			*rq_alloc_data;
 };
 
 #define QUEUE_FLAG_QUEUED	1	/* uses generic tag queueing */
@@ -600,6 +610,7 @@ struct request_queue {
 #define QUEUE_FLAG_FLUSH_NQ    25	/* flush not queueuable */
 #define QUEUE_FLAG_DAX         26	/* device supports DAX */
 #define QUEUE_FLAG_STATS       27	/* track rq completion times */
+#define QUEUE_FLAG_RESTART     28	/* queue needs restart at completion */
 
 #define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_STACKABLE)	|	\
@@ -695,9 +706,10 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 	((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \
 			     REQ_FAILFAST_DRIVER))
 
-#define blk_account_rq(rq) \
-	(((rq)->rq_flags & RQF_STARTED) && \
-	 ((rq)->cmd_type == REQ_TYPE_FS))
+static inline bool blk_account_rq(struct request *rq)
+{
+	return (rq->rq_flags & RQF_STARTED) && !blk_rq_is_passthrough(rq);
+}
 
 #define blk_rq_cpu_valid(rq)	((rq)->cpu != -1)
 #define blk_bidi_rq(rq)		((rq)->next_rq != NULL)
@@ -772,7 +784,7 @@ static inline void blk_clear_rl_full(struct request_list *rl, bool sync)
 
 static inline bool rq_mergeable(struct request *rq)
 {
-	if (rq->cmd_type != REQ_TYPE_FS)
+	if (blk_rq_is_passthrough(rq))
 		return false;
 
 	if (req_op(rq) == REQ_OP_FLUSH)
@@ -910,7 +922,6 @@ extern void blk_rq_init(struct request_queue *q, struct request *rq);
 extern void blk_put_request(struct request *);
 extern void __blk_put_request(struct request_queue *, struct request *);
 extern struct request *blk_get_request(struct request_queue *, int, gfp_t);
-extern void blk_rq_set_block_pc(struct request *);
 extern void blk_requeue_request(struct request_queue *, struct request *);
 extern int blk_lld_busy(struct request_queue *q);
 extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
@@ -1047,7 +1058,7 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq,
 {
 	struct request_queue *q = rq->q;
 
-	if (unlikely(rq->cmd_type != REQ_TYPE_FS))
+	if (blk_rq_is_passthrough(rq))
 		return q->limits.max_hw_sectors;
 
 	if (!q->limits.chunk_sectors ||
@@ -1129,14 +1140,15 @@ extern void blk_unprep_request(struct request *);
 extern struct request_queue *blk_init_queue_node(request_fn_proc *rfn,
 					spinlock_t *lock, int node_id);
 extern struct request_queue *blk_init_queue(request_fn_proc *, spinlock_t *);
-extern struct request_queue *blk_init_allocated_queue(struct request_queue *,
-						      request_fn_proc *, spinlock_t *);
+extern int blk_init_allocated_queue(struct request_queue *);
 extern void blk_cleanup_queue(struct request_queue *);
 extern void blk_queue_make_request(struct request_queue *, make_request_fn *);
 extern void blk_queue_bounce_limit(struct request_queue *, u64);
 extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int);
 extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int);
 extern void blk_queue_max_segments(struct request_queue *, unsigned short);
+extern void blk_queue_max_discard_segments(struct request_queue *,
+		unsigned short);
 extern void blk_queue_max_segment_size(struct request_queue *, unsigned int);
 extern void blk_queue_max_discard_sectors(struct request_queue *q,
 		unsigned int max_discard_sectors);
@@ -1179,8 +1191,16 @@ extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *);
 extern void blk_queue_rq_timeout(struct request_queue *, unsigned int);
 extern void blk_queue_flush_queueable(struct request_queue *q, bool queueable);
 extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua);
-extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev);
 
+/*
+ * Number of physical segments as sent to the device.
+ *
+ * Normally this is the number of discontiguous data segments sent by the
+ * submitter.  But for data-less command like discard we might have no
+ * actual data segments submitted, but the driver might have to add it's
+ * own special payload.  In that case we still return 1 here so that this
+ * special payload will be mapped.
+ */
 static inline unsigned short blk_rq_nr_phys_segments(struct request *rq)
 {
 	if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
@@ -1188,6 +1208,15 @@ static inline unsigned short blk_rq_nr_phys_segments(struct request *rq)
 	return rq->nr_phys_segments;
 }
 
+/*
+ * Number of discard segments (or ranges) the driver needs to fill in.
+ * Each discard bio merged into a request is counted as one segment.
+ */
+static inline unsigned short blk_rq_nr_discard_segments(struct request *rq)
+{
+	return max_t(unsigned short, rq->nr_phys_segments, 1);
+}
+
 extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *);
 extern void blk_dump_rq_flags(struct request *, char *);
 extern long nr_blockdev_pages(void);
@@ -1376,6 +1405,11 @@ static inline unsigned short queue_max_segments(struct request_queue *q)
 	return q->limits.max_segments;
 }
 
+static inline unsigned short queue_max_discard_segments(struct request_queue *q)
+{
+	return q->limits.max_discard_segments;
+}
+
 static inline unsigned int queue_max_segment_size(struct request_queue *q)
 {
 	return q->limits.max_segment_size;
@@ -1620,6 +1654,25 @@ static inline bool bvec_gap_to_prev(struct request_queue *q,
 	return __bvec_gap_to_prev(q, bprv, offset);
 }
 
+/*
+ * Check if the two bvecs from two bios can be merged to one segment.
+ * If yes, no need to check gap between the two bios since the 1st bio
+ * and the 1st bvec in the 2nd bio can be handled in one segment.
+ */
+static inline bool bios_segs_mergeable(struct request_queue *q,
+		struct bio *prev, struct bio_vec *prev_last_bv,
+		struct bio_vec *next_first_bv)
+{
+	if (!BIOVEC_PHYS_MERGEABLE(prev_last_bv, next_first_bv))
+		return false;
+	if (!BIOVEC_SEG_BOUNDARY(q, prev_last_bv, next_first_bv))
+		return false;
+	if (prev->bi_seg_back_size + next_first_bv->bv_len >
+			queue_max_segment_size(q))
+		return false;
+	return true;
+}
+
 static inline bool bio_will_gap(struct request_queue *q, struct bio *prev,
 			 struct bio *next)
 {
@@ -1629,7 +1682,8 @@ static inline bool bio_will_gap(struct request_queue *q, struct bio *prev,
 		bio_get_last_bvec(prev, &pb);
 		bio_get_first_bvec(next, &nb);
 
-		return __bvec_gap_to_prev(q, &pb, nb.bv_offset);
+		if (!bios_segs_mergeable(q, prev, &pb, &nb))
+			return __bvec_gap_to_prev(q, &pb, nb.bv_offset);
 	}
 
 	return false;
diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index e417f080219a..d2e908586e3d 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -30,9 +30,6 @@ struct blk_trace {
 
 extern int blk_trace_ioctl(struct block_device *, unsigned, char __user *);
 extern void blk_trace_shutdown(struct request_queue *);
-extern int do_blk_trace_setup(struct request_queue *q, char *name,
-			      dev_t dev, struct block_device *bdev,
-			      struct blk_user_trace_setup *buts);
 extern __printf(2, 3)
 void __trace_note_message(struct blk_trace *, const char *fmt, ...);
 
@@ -80,7 +77,6 @@ extern struct attribute_group blk_trace_attr_group;
 #else /* !CONFIG_BLK_DEV_IO_TRACE */
 # define blk_trace_ioctl(bdev, cmd, arg)		(-ENOTTY)
 # define blk_trace_shutdown(q)				do { } while (0)
-# define do_blk_trace_setup(q, name, dev, bdev, buts)	(-ENOTTY)
 # define blk_add_driver_data(q, rq, data, len)		do {} while (0)
 # define blk_trace_setup(q, name, dev, bdev, arg)	(-ENOTTY)
 # define blk_trace_startstop(q, start)			(-ENOTTY)
@@ -110,16 +106,16 @@ struct compat_blk_user_trace_setup {
 
 #endif
 
-#if defined(CONFIG_EVENT_TRACING) && defined(CONFIG_BLOCK)
+extern void blk_fill_rwbs(char *rwbs, unsigned int op, int bytes);
 
-static inline int blk_cmd_buf_len(struct request *rq)
+static inline sector_t blk_rq_trace_sector(struct request *rq)
 {
-	return (rq->cmd_type == REQ_TYPE_BLOCK_PC) ? rq->cmd_len * 3 : 1;
+	return blk_rq_is_passthrough(rq) ? 0 : blk_rq_pos(rq);
 }
 
-extern void blk_dump_cmd(char *buf, struct request *rq);
-extern void blk_fill_rwbs(char *rwbs, unsigned int op, int bytes);
-
-#endif /* CONFIG_EVENT_TRACING && CONFIG_BLOCK */
+static inline unsigned int blk_rq_trace_nr_sectors(struct request *rq)
+{
+	return blk_rq_is_passthrough(rq) ? 0 : blk_rq_sectors(rq);
+}
 
 #endif
diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h
index 657a718c27d2..e34dde2da0ef 100644
--- a/include/linux/bsg-lib.h
+++ b/include/linux/bsg-lib.h
@@ -66,9 +66,8 @@ struct bsg_job {
 
 void bsg_job_done(struct bsg_job *job, int result,
 		  unsigned int reply_payload_rcv_len);
-int bsg_setup_queue(struct device *dev, struct request_queue *q, char *name,
-		    bsg_job_fn *job_fn, int dd_job_size);
-void bsg_request_fn(struct request_queue *q);
+struct request_queue *bsg_setup_queue(struct device *dev, char *name,
+		bsg_job_fn *job_fn, int dd_job_size);
 void bsg_job_put(struct bsg_job *job);
 int __must_check bsg_job_get(struct bsg_job *job);
 
diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h
index 8609d577bb66..6e8f209a6dff 100644
--- a/include/linux/cdrom.h
+++ b/include/linux/cdrom.h
@@ -36,7 +36,7 @@ struct packet_command
 
 /* Uniform cdrom data structures for cdrom.c */
 struct cdrom_device_info {
-	struct cdrom_device_ops  *ops;  /* link to device_ops */
+	const struct cdrom_device_ops *ops; /* link to device_ops */
 	struct list_head list;		/* linked list of all device_info */
 	struct gendisk *disk;		/* matching block layer disk */
 	void *handle;		        /* driver-dependent data */
@@ -87,7 +87,6 @@ struct cdrom_device_ops {
 
 /* driver specifications */
 	const int capability;   /* capability flags */
-	int n_minors;           /* number of active minor devices */
 	/* handle uniform packets for scsi type devices (scsi,atapi) */
 	int (*generic_packet) (struct cdrom_device_info *,
 			       struct packet_command *);
@@ -123,6 +122,8 @@ extern int cdrom_mode_sense(struct cdrom_device_info *cdi,
 			    int page_code, int page_control);
 extern void init_cdrom_command(struct packet_command *cgc,
 			       void *buffer, int len, int type);
+extern int cdrom_dummy_generic_packet(struct cdrom_device_info *cdi,
+				      struct packet_command *cgc);
 
 /* The SCSI spec says there could be 256 slots. */
 #define CDROM_MAX_SLOTS	256
diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h
index 014cc564d1c4..c0befcf41b58 100644
--- a/include/linux/debugfs.h
+++ b/include/linux/debugfs.h
@@ -80,6 +80,8 @@ static const struct file_operations __fops = {				\
 
 #if defined(CONFIG_DEBUG_FS)
 
+struct dentry *debugfs_lookup(const char *name, struct dentry *parent);
+
 struct dentry *debugfs_create_file(const char *name, umode_t mode,
 				   struct dentry *parent, void *data,
 				   const struct file_operations *fops);
@@ -181,6 +183,12 @@ ssize_t debugfs_write_file_bool(struct file *file, const char __user *user_buf,
  * want to duplicate the design decision mistakes of procfs and devfs again.
  */
 
+static inline struct dentry *debugfs_lookup(const char *name,
+					    struct dentry *parent)
+{
+	return ERR_PTR(-ENODEV);
+}
+
 static inline struct dentry *debugfs_create_file(const char *name, umode_t mode,
 					struct dentry *parent, void *data,
 					const struct file_operations *fops)
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index ef7962e84444..a7e6903866fd 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -55,8 +55,6 @@ typedef void (*dm_dtr_fn) (struct dm_target *ti);
  * = 2: The target wants to push back the io
  */
 typedef int (*dm_map_fn) (struct dm_target *ti, struct bio *bio);
-typedef int (*dm_map_request_fn) (struct dm_target *ti, struct request *clone,
-				  union map_info *map_context);
 typedef int (*dm_clone_and_map_request_fn) (struct dm_target *ti,
 					    struct request *rq,
 					    union map_info *map_context,
@@ -163,7 +161,6 @@ struct target_type {
 	dm_ctr_fn ctr;
 	dm_dtr_fn dtr;
 	dm_map_fn map;
-	dm_map_request_fn map_rq;
 	dm_clone_and_map_request_fn clone_and_map_rq;
 	dm_release_clone_request_fn release_clone_rq;
 	dm_endio_fn end_io;
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index b276e9ef0e0b..aebecc4ed088 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -9,12 +9,22 @@
 struct io_cq;
 struct elevator_type;
 
-typedef int (elevator_merge_fn) (struct request_queue *, struct request **,
+/*
+ * Return values from elevator merger
+ */
+enum elv_merge {
+	ELEVATOR_NO_MERGE	= 0,
+	ELEVATOR_FRONT_MERGE	= 1,
+	ELEVATOR_BACK_MERGE	= 2,
+	ELEVATOR_DISCARD_MERGE	= 3,
+};
+
+typedef enum elv_merge (elevator_merge_fn) (struct request_queue *, struct request **,
 				 struct bio *);
 
 typedef void (elevator_merge_req_fn) (struct request_queue *, struct request *, struct request *);
 
-typedef void (elevator_merged_fn) (struct request_queue *, struct request *, int);
+typedef void (elevator_merged_fn) (struct request_queue *, struct request *, enum elv_merge);
 
 typedef int (elevator_allow_bio_merge_fn) (struct request_queue *,
 					   struct request *, struct bio *);
@@ -77,6 +87,34 @@ struct elevator_ops
 	elevator_registered_fn *elevator_registered_fn;
 };
 
+struct blk_mq_alloc_data;
+struct blk_mq_hw_ctx;
+
+struct elevator_mq_ops {
+	int (*init_sched)(struct request_queue *, struct elevator_type *);
+	void (*exit_sched)(struct elevator_queue *);
+
+	bool (*allow_merge)(struct request_queue *, struct request *, struct bio *);
+	bool (*bio_merge)(struct blk_mq_hw_ctx *, struct bio *);
+	int (*request_merge)(struct request_queue *q, struct request **, struct bio *);
+	void (*request_merged)(struct request_queue *, struct request *, enum elv_merge);
+	void (*requests_merged)(struct request_queue *, struct request *, struct request *);
+	struct request *(*get_request)(struct request_queue *, unsigned int, struct blk_mq_alloc_data *);
+	void (*put_request)(struct request *);
+	void (*insert_requests)(struct blk_mq_hw_ctx *, struct list_head *, bool);
+	struct request *(*dispatch_request)(struct blk_mq_hw_ctx *);
+	bool (*has_work)(struct blk_mq_hw_ctx *);
+	void (*completed_request)(struct blk_mq_hw_ctx *, struct request *);
+	void (*started_request)(struct request *);
+	void (*requeue_request)(struct request *);
+	struct request *(*former_request)(struct request_queue *, struct request *);
+	struct request *(*next_request)(struct request_queue *, struct request *);
+	int (*get_rq_priv)(struct request_queue *, struct request *, struct bio *);
+	void (*put_rq_priv)(struct request_queue *, struct request *);
+	void (*init_icq)(struct io_cq *);
+	void (*exit_icq)(struct io_cq *);
+};
+
 #define ELV_NAME_MAX	(16)
 
 struct elv_fs_entry {
@@ -94,12 +132,16 @@ struct elevator_type
 	struct kmem_cache *icq_cache;
 
 	/* fields provided by elevator implementation */
-	struct elevator_ops ops;
+	union {
+		struct elevator_ops sq;
+		struct elevator_mq_ops mq;
+	} ops;
 	size_t icq_size;	/* see iocontext.h */
 	size_t icq_align;	/* ditto */
 	struct elv_fs_entry *elevator_attrs;
 	char elevator_name[ELV_NAME_MAX];
 	struct module *elevator_owner;
+	bool uses_mq;
 
 	/* managed by elevator core */
 	char icq_cache_name[ELV_NAME_MAX + 5];	/* elvname + "_io_cq" */
@@ -123,6 +165,7 @@ struct elevator_queue
 	struct kobject kobj;
 	struct mutex sysfs_lock;
 	unsigned int registered:1;
+	unsigned int uses_mq:1;
 	DECLARE_HASHTABLE(hash, ELV_HASH_BITS);
 };
 
@@ -133,12 +176,15 @@ extern void elv_dispatch_sort(struct request_queue *, struct request *);
 extern void elv_dispatch_add_tail(struct request_queue *, struct request *);
 extern void elv_add_request(struct request_queue *, struct request *, int);
 extern void __elv_add_request(struct request_queue *, struct request *, int);
-extern int elv_merge(struct request_queue *, struct request **, struct bio *);
+extern enum elv_merge elv_merge(struct request_queue *, struct request **,
+		struct bio *);
 extern void elv_merge_requests(struct request_queue *, struct request *,
 			       struct request *);
-extern void elv_merged_request(struct request_queue *, struct request *, int);
+extern void elv_merged_request(struct request_queue *, struct request *,
+		enum elv_merge);
 extern void elv_bio_merged(struct request_queue *q, struct request *,
 				struct bio *);
+extern bool elv_attempt_insert_merge(struct request_queue *, struct request *);
 extern void elv_requeue_request(struct request_queue *, struct req