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

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

11 files changed, 395 insertions, 128 deletions

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..37c9a43c5e78 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -221,6 +221,15 @@ 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 +241,29 @@ 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 +271,11 @@ 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..05675b1dfd20 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -154,6 +154,7 @@ struct request {
 
 	/* 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;
@@ -220,9 +221,10 @@ struct request {
 
 	unsigned short ioprio;
 
+	int internal_tag;
+
 	void *special;		/* opaque pointer available for LLD use */
 
-	int tag;
 	int errors;
 
 	/*
@@ -407,7 +409,7 @@ struct request_queue {
 	dma_drain_needed_fn	*dma_drain_needed;
 	lld_busy_fn		*lld_busy_fn;
 
-	struct blk_mq_ops	*mq_ops;
+	const struct blk_mq_ops	*mq_ops;
 
 	unsigned int		*mq_map;
 
@@ -569,6 +571,11 @@ struct request_queue {
 	struct list_head	tag_set_list;
 	struct bio_set		*bio_split;
 
+#ifdef CONFIG_DEBUG_FS
+	struct dentry		*debugfs_dir;
+	struct dentry		*mq_debugfs_dir;
+#endif
+
 	bool			mq_sysfs_init_done;
 };
 
@@ -600,6 +607,7 @@ 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)	|	\
@@ -1620,6 +1628,25 @@ 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 +1656,8 @@ 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/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/elevator.h b/include/linux/elevator.h
index b276e9ef0e0b..b5825c4f06f7 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -77,6 +77,34 @@ 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 *, int);
+	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 *);
+	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 +122,16 @@ 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 +155,7 @@ 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);
 };
 
@@ -139,6 +172,7 @@ extern void elv_merge_requests(struct request_queue *, struct request *,
 extern void elv_merged_request(struct request_queue *, struct request *, int);
 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 request *);
 extern struct request *elv_former_request(struct request_queue *, struct request *);
 extern struct request *elv_latter_request(struct request_queue *, struct request *);
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index 7c273bbc5351..ca45e4a088a9 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -80,8 +80,6 @@ struct nvm_dev_ops {
 	unsigned int		max_phys_sect;
 };
 
-
-
 #ifdef CONFIG_NVM
 
 #include <linux/blkdev.h>
@@ -109,6 +107,7 @@ enum {
 	NVM_RSP_ERR_FAILWRITE	= 0x40ff,
 	NVM_RSP_ERR_EMPTYPAGE	= 0x42ff,
 	NVM_RSP_ERR_FAILECC	= 0x4281,
+	NVM_RSP_ERR_FAILCRC	= 0x4004,
 	NVM_RSP_WARN_HIGHECC	= 0x4700,
 
 	/* Device opcodes */
@@ -202,11 +201,10 @@ struct nvm_addr_format {
 struct nvm_id {
 	u8	ver_id;
 	u8	vmnt;
-	u8	cgrps;
 	u32	cap;
 	u32	dom;
 	struct nvm_addr_format ppaf;
-	struct nvm_id_group groups[4];
+	struct nvm_id_group grp;
 } __packed;
 
 struct nvm_target {
@@ -216,10 +214,6 @@ struct nvm_target {
 	struct gendisk *disk;
 };
 
-struct nvm_tgt_instance {
-	struct nvm_tgt_type *tt;
-};
-
 #define ADDR_EMPTY (~0ULL)
 
 #define NVM_VERSION_MAJOR 1
@@ -230,7 +224,6 @@ struct nvm_rq;
 typedef void (nvm_end_io_fn)(struct nvm_rq *);
 
 struct nvm_rq {
-	struct nvm_tgt_instance *ins;
 	struct nvm_tgt_dev *dev;
 
 	struct bio *bio;
@@ -254,6 +247,8 @@ struct nvm_rq {
 
 	u64 ppa_status; /* ppa media status */
 	int error;
+
+	void *private;
 };
 
 static inline struct nvm_rq *nvm_rq_from_pdu(void *pdu)
@@ -272,15 +267,6 @@ enum {
 	NVM_BLK_ST_BAD =	0x8,	/* Bad block */
 };
 
-/* system block cpu representation */
-struct nvm_sb_info {
-	unsigned long		seqnr;
-	unsigned long		erase_cnt;
-	unsigned int		version;
-	char			mmtype[NVM_MMTYPE_LEN];
-	struct ppa_addr		fs_ppa;
-};
-
 /* Device generic information */
 struct nvm_geo {
 	int nr_chnls;
@@ -308,6 +294,7 @@ struct nvm_geo {
 	int sec_per_lun;
 };
 
+/* sub-device structure */
 struct nvm_tgt_dev {
 	/* Device information */
 	struct nvm_geo geo;
@@ -329,17 +316,10 @@ struct nvm_dev {
 
 	struct list_head devices;
 
-	/* Media manager */
-	struct nvmm_type *mt;
-	void *mp;
-
-	/* System blocks */
-	struct nvm_sb_info sb;
-
 	/* Device information */
 	struct nvm_geo geo;
 
-	/* lower page table */
+	  /* lower page table */
 	int lps_per_blk;
 	int *lptbl;
 
@@ -359,6 +339,10 @@ struct nvm_dev {
 
 	struct mutex mlock;
 	spinlock_t lock;
+
+	/* target management */
+	struct list_head area_list;
+	struct list_head targets;
 };
 
 static inline struct ppa_addr linear_to_generic_addr(struct nvm_geo *geo,
@@ -391,10 +375,10 @@ static inline struct ppa_addr linear_to_generic_addr(struct nvm_geo *geo,
 	return l;
 }
 
-static inline struct ppa_addr generic_to_dev_addr(struct nvm_dev *dev,
-						struct ppa_addr r)
+static inline struct ppa_addr generic_to_dev_addr(struct nvm_tgt_dev *tgt_dev,
+						  struct ppa_addr r)
 {
-	struct nvm_geo *geo = &dev->geo;
+	struct nvm_geo *geo = &tgt_dev->geo;
 	struct ppa_addr l;
 
 	l.ppa = ((u64)r.g.blk) << geo->ppaf.blk_offset;
@@ -407,10 +391,10 @@ static inline struct ppa_addr generic_to_dev_addr(struct nvm_dev *dev,
 	return l;
 }
 
-static inline struct ppa_addr dev_to_generic_addr(struct nvm_dev *dev,
-						struct ppa_addr r)
+static inline struct ppa_addr dev_to_generic_addr(struct nvm_tgt_dev *tgt_dev,
+						  struct ppa_addr r)
 {
-	struct nvm_geo *geo = &dev->geo;
+	struct nvm_geo *geo = &tgt_dev->geo;
 	struct ppa_addr l;
 
 	l.ppa = 0;
@@ -452,15 +436,12 @@ static inline int ppa_cmp_blk(struct ppa_addr ppa1, struct ppa_addr ppa2)
 					(ppa1.g.blk == ppa2.g.blk));
 }
 
-static inline int ppa_to_slc(struct nvm_dev *dev, int slc_pg)
-{
-	return dev->lptbl[slc_pg];
-}
-
 typedef blk_qc_t (nvm_tgt_make_rq_fn)(struct request_queue *, struct bio *);
 typedef sector_t (nvm_tgt_capacity_fn)(void *);
 typedef void *(nvm_tgt_init_fn)(struct nvm_tgt_dev *, struct gendisk *);
 typedef void (nvm_tgt_exit_fn)(void *);
+typedef int (nvm_tgt_sysfs_init_fn)(struct gendisk *);
+typedef void (nvm_tgt_sysfs_exit_fn)(struct gendisk *);
 
 struct nvm_tgt_type {
 	const char *name;
@@ -469,12 +450,15 @@ struct nvm_tgt_type {
 	/* target entry points */
 	nvm_tgt_make_rq_fn *make_rq;
 	nvm_tgt_capacity_fn *capacity;
-	nvm_end_io_fn *end_io;
 
 	/* module-specific init/teardown */
 	nvm_tgt_init_fn *init;
 	nvm_tgt_exit_fn *exit;
 
+	/* sysfs */
+	nvm_tgt_sysfs_init_fn *sysfs_init;
+	nvm_tgt_sysfs_exit_fn *sysfs_exit;
+
 	/* For internal use */
 	struct list_head list;
 };
@@ -487,103 +471,29 @@ extern void nvm_unregister_tgt_type(struct nvm_tgt_type *);
 extern void *nvm_dev_dma_alloc(struct nvm_dev *, gfp_t, dma_addr_t *);
 extern void nvm_dev_dma_free(struct nvm_dev *, void *, dma_addr_t);
 
-typedef int (nvmm_register_fn)(struct nvm_dev *);
-typedef void (nvmm_unregister_fn)(struct nvm_dev *);
-
-typedef int (nvmm_create_tgt_fn)(struct nvm_dev *, struct nvm_ioctl_create *);
-typedef int (nvmm_remove_tgt_fn)(struct nvm_dev *, struct nvm_ioctl_remove *);
-typedef int (nvmm_submit_io_fn)(struct nvm_tgt_dev *, struct nvm_rq *);
-typedef int (nvmm_erase_blk_fn)(struct nvm_tgt_dev *, struct ppa_addr *, int);
-typedef int (nvmm_get_area_fn)(struct nvm_dev *, sector_t *, sector_t);
-typedef void (nvmm_put_area_fn)(struct nvm_dev *, sector_t);
-typedef struct ppa_addr (nvmm_trans_ppa_fn)(struct nvm_tgt_dev *,
-					    struct ppa_addr, int);
-typedef void (nvmm_part_to_tgt_fn)(struct nvm_dev *, sector_t*, int);
-
-enum {
-	TRANS_TGT_TO_DEV =	0x0,
-	TRANS_DEV_TO_TGT =	0x1,
-};
-
-struct nvmm_type {
-	const char *name;
-	unsigned int version[3];
-
-	nvmm_register_fn *register_mgr;
-	nvmm_unregister_fn *unregister_mgr;
-
-	nvmm_create_tgt_fn *create_tgt;
-	nvmm_remove_tgt_fn *remove_tgt;
-
-	nvmm_submit_io_fn *submit_io;
-	nvmm_erase_blk_fn *erase_blk;
-
-	nvmm_get_area_fn *get_area;
-	nvmm_put_area_fn *put_area;
-
-	nvmm_trans_ppa_fn *trans_ppa;
-	nvmm_part_to_tgt_fn *part_to_tgt;
-
-	struct list_head list;
-};
-
-extern int nvm_register_mgr(struct nvmm_type *);
-extern void nvm_unregister_mgr(struct nvmm_type *);
-
 extern struct nvm_dev *nvm_alloc_dev(int);
 extern int nvm_register(struct nvm_dev *);
 extern void nvm_unregister(struct nvm_dev *);
 
-extern int nvm_set_bb_tbl(struct nvm_dev *, struct ppa_addr *, int, int);
 extern int nvm_set_tgt_bb_tbl(struct nvm_tgt_dev *, struct ppa_addr *,
 			      int, int);
 extern int nvm_max_phys_sects(struct nvm_tgt_dev *);
 extern int nvm_submit_io(struct nvm_tgt_dev *, struct nvm_rq *);
-extern void nvm_generic_to_addr_mode(struct nvm_dev *, struct nvm_rq *);
-extern void nvm_addr_to_generic_mode(struct nvm_dev *, struct nvm_rq *);
 extern int nvm_set_rqd_ppalist(struct nvm_dev *, struct nvm_rq *,
 					const struct ppa_addr *, int, int);
 extern void nvm_free_rqd_ppalist(struct nvm_dev *, struct nvm_rq *);
-extern int nvm_erase_ppa(struct nvm_dev *, struct ppa_addr *, int, int);
 extern int nvm_erase_blk(struct nvm_tgt_dev *, struct ppa_addr *, int);
 extern int nvm_get_l2p_tbl(struct nvm_tgt_dev *, u64, u32, nvm_l2p_update_fn *,
 			   void *);
 extern int nvm_get_area(struct nvm_tgt_dev *, sector_t *, sector_t);
 extern void nvm_put_area(struct nvm_tgt_dev *, sector_t);
-extern void nvm_end_io(struct nvm_rq *, int);
-extern int nvm_submit_ppa(struct nvm_dev *, struct ppa_addr *, int, int, int,
-								void *, int);
-extern int nvm_submit_ppa_list(struct nvm_dev *, struct ppa_addr *, int, int,
-							int, void *, int);
+extern void nvm_end_io(struct nvm_rq *);
 extern int nvm_bb_tbl_fold(struct nvm_dev *, u8 *, int);
-extern int nvm_get_bb_tbl(struct nvm_dev *, struct ppa_addr, u8 *);
 extern int nvm_get_tgt_bb_tbl(struct nvm_tgt_dev *, struct ppa_addr, u8 *);
 
-/* sysblk.c */
-#define NVM_SYSBLK_MAGIC 0x4E564D53 /* "NVMS" */
-
-/* system block on disk representation */
-struct nvm_system_block {
-	__be32			magic;		/* magic signature */
-	__be32			seqnr;		/* sequence number */
-	__be32			erase_cnt;	/* erase count */
-	__be16			version;	/* version number */
-	u8			mmtype[NVM_MMTYPE_LEN]; /* media manager name */
-	__be64			fs_ppa;		/* PPA for media manager
-						 * superblock */
-};
-
-extern int nvm_get_sysblock(struct nvm_dev *, struct nvm_sb_info *);
-extern int nvm_update_sysblock(struct nvm_dev *, struct nvm_sb_info *);
-extern int nvm_init_sysblock(struct nvm_dev *, struct nvm_sb_info *);
-
 extern int nvm_dev_factory(struct nvm_dev *, int flags);
 
-#define nvm_for_each_lun_ppa(geo, ppa, chid, lunid)			\
-	for ((chid) = 0, (ppa).ppa = 0; (chid) < (geo)->nr_chnls;	\
-					(chid)++, (ppa).g.ch = (chid))	\
-		for ((lunid) = 0; (lunid) < (geo)->luns_per_chnl;	\
-					(lunid)++, (ppa).g.lun = (lunid))
+extern void nvm_part_to_tgt(struct nvm_dev *, sector_t *, int);
 
 #else /* CONFIG_NVM */
 struct nvm_dev_ops;
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 3d1c6f1b15c9..00eac863a9c7 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -244,6 +244,7 @@ enum {
 	NVME_CTRL_ONCS_DSM			= 1 << 2,
 	NVME_CTRL_ONCS_WRITE_ZEROES		= 1 << 3,
 	NVME_CTRL_VWC_PRESENT			= 1 << 0,
+	NVME_CTRL_OACS_SEC_SUPP                 = 1 << 0,
 };
 
 struct nvme_lbaf {
diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h
index f017fd6e69c4..d4e0a204c118 100644
--- a/include/linux/sbitmap.h
+++ b/include/linux/sbitmap.h
@@ -259,6 +259,26 @@ static inline int sbitmap_test_bit(struct sbitmap *sb, unsigned int bitnr)
 unsigned int sbitmap_weight(const struct sbitmap *sb);
 
 /**
+ * sbitmap_show() - Dump &struct sbitmap information to a &struct seq_file.
+ * @sb: Bitmap to show.
+ * @m: struct seq_file to write to.
+ *
+ * This is intended for debugging. The format may change at any time.
+ */
+void sbitmap_show(struct sbitmap *sb, struct seq_file *m);
+
+/**
+ * sbitmap_bitmap_show() - Write a hex dump of a &struct sbitmap to a &struct
+ * seq_file.
+ * @sb: Bitmap to show.
+ * @m: struct seq_file to write to.
+ *
+ * This is intended for debugging. The output isn't guaranteed to be internally
+ * consistent.
+ */
+void sbitmap_bitmap_show(struct sbitmap *sb, struct seq_file *m);
+
+/**
  * sbitmap_queue_init_node() - Initialize a &struct sbitmap_queue on a specific
  * memory node.
  * @sbq: Bitmap queue to initialize.
@@ -370,4 +390,14 @@ static inline struct sbq_wait_state *sbq_wait_ptr(struct sbitmap_queue *sbq,
  */
 void sbitmap_queue_wake_all(struct sbitmap_queue *sbq);
 
+/**
+ * sbitmap_queue_show() - Dump &struct sbitmap_queue information to a &struct
+ * seq_file.
+ * @sbq: Bitmap queue to show.
+ * @m: struct seq_file to write to.
+ *
+ * This is intended for debugging. The format may change at any time.
+ */
+void sbitmap_queue_show(struct sbitmap_queue *sbq, struct seq_file *m);
+
 #endif /* __LINUX_SCALE_BITMAP_H */
diff --git a/include/linux/sed-opal.h b/include/linux/sed-opal.h
new file mode 100644
index 000000000000..deee23d012e7
--- /dev/null
+++ b/include/linux/sed-opal.h
@@ -0,0 +1,70 @@
+/*
+ * Copyright © 2016 Intel Corporation
+ *
+ * Authors:
+ *    Rafael Antognolli <rafael.antognolli@intel.com>
+ *    Scott  Bauer      <scott.bauer@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef LINUX_OPAL_H
+#define LINUX_OPAL_H
+
+#include <uapi/linux/sed-opal.h>
+#include <linux/kernel.h>
+
+struct opal_dev;
+
+typedef int (sec_send_recv)(void *data, u16 spsp, u8 secp, void *buffer,
+		size_t len, bool send);
+
+#ifdef CONFIG_BLK_SED_OPAL
+bool opal_unlock_from_suspend(struct opal_dev *dev);
+struct opal_dev *init_opal_dev(void *data, sec_send_recv *send_recv);
+int sed_ioctl(struct opal_dev *dev, unsigned int cmd, void __user *ioctl_ptr);
+
+static inline bool is_sed_ioctl(unsigned int cmd)
+{
+	switch (cmd) {
+	case IOC_OPAL_SAVE:
+	case IOC_OPAL_LOCK_UNLOCK:
+	case IOC_OPAL_TAKE_OWNERSHIP:
+	case IOC_OPAL_ACTIVATE_LSP:
+	case IOC_OPAL_SET_PW:
+	case IOC_OPAL_ACTIVATE_USR:
+	case IOC_OPAL_REVERT_TPR:
+	case IOC_OPAL_LR_SETUP:
+	case IOC_OPAL_ADD_USR_TO_LR:
+	case IOC_OPAL_ENABLE_DISABLE_MBR:
+	case IOC_OPAL_ERASE_LR:
+	case IOC_OPAL_SECURE_ERASE_LR:
+		return true;
+	}
+	return false;
+}
+#else
+static inline bool is_sed_ioctl(unsigned int cmd)
+{
+	return false;
+}
+
+static inline int sed_ioctl(struct opal_dev *dev, unsigned int cmd,
+			    void __user *ioctl_ptr)
+{
+	return 0;
+}
+static inline bool opal_unlock_from_suspend(struct opal_dev *dev)
+{
+	return false;
+}
+#define init_opal_dev(data, send_recv)		NULL
+#endif /* CONFIG_BLK_SED_OPAL */
+#endif /* LINUX_OPAL_H */
diff --git a/include/uapi/linux/lightnvm.h b/include/uapi/linux/lightnvm.h
index 774a43128a7a..fd19f36b3129 100644
--- a/include/uapi/linux/lightnvm.h
+++ b/include/uapi/linux/lightnvm.h
@@ -122,6 +122,44 @@ struct nvm_ioctl_dev_factory {
 	__u32 flags;
 };
 
+struct nvm_user_vio {
+	__u8 opcode;
+	__u8 flags;
+	__u16 control;
+	__u16 nppas;
+	__u16 rsvd;
+	__u64 metadata;
+	__u64 addr;
+	__u64 ppa_list;
+	__u32 metadata_len;
+	__u32 data_len;
+	__u64 status;
+	__u32 result;
+	__u32 rsvd3[3];
+};
+
+struct nvm_passthru_vio {
+	__u8 opcode;
+	__u8 flags;
+	__u8 rsvd[2];
+	__u32 nsid;
+	__u32 cdw2;
+	__u32 cdw3;
+	__u64 metadata;
+	__u64 addr;
+	__u32 metadata_len;
+	__u32 data_len;
+	__u64 ppa_list;
+	__u16 nppas;
+	__u16 control;
+	__u32 cdw13;
+	__u32 cdw14;
+	__u32 cdw15;
+	__u64 status;
+	__u32 result;
+	__u32 timeout_ms;
+};
+
 /* The ioctl type, 'L', 0x20 - 0x2F documented in ioctl-number.txt */
 enum {
 	/* top level cmds */
@@ -137,6 +175,11 @@ enum {
 
 	/* Factory reset device */
 	NVM_DEV_FACTORY_CMD,
+
+	/* Vector user I/O */
+	NVM_DEV_VIO_ADMIN_CMD = 0x41,
+	NVM_DEV_VIO_CMD = 0x42,
+	NVM_DEV_VIO_USER_CMD = 0x43,
 };
 
 #define NVM_IOCTL 'L' /* 0x4c */
@@ -154,6 +197,13 @@ enum {
 #define NVM_DEV_FACTORY		_IOW(NVM_IOCTL, NVM_DEV_FACTORY_CMD, \
 						struct nvm_ioctl_dev_factory)
 
+#define NVME_NVM_IOCTL_IO_VIO		_IOWR(NVM_IOCTL, NVM_DEV_VIO_USER_CMD, \
+						struct nvm_passthru_vio)
+#define NVME_NVM_IOCTL_ADMIN_VIO	_IOWR(NVM_IOCTL, NVM_DEV_VIO_ADMIN_CMD,\
+						struct nvm_passthru_vio)
+#define NVME_NVM_IOCTL_SUBMIT_VIO	_IOWR(NVM_IOCTL, NVM_DEV_VIO_CMD,\
+						struct nvm_user_vio)
+
 #define NVM_VERSION_MAJOR	1
 #define NVM_VERSION_MINOR	0
 #define NVM_VERSION_PATCHLEVEL	0
diff --git a/include/uapi/linux/sed-opal.h b/include/uapi/linux/sed-opal.h
new file mode 100644
index 000000000000..c72e0735532d
--- /dev/null
+++ b/include/uapi/linux/sed-opal.h
@@ -0,0 +1,119 @@
+/*
+ * Copyright © 2016 Intel Corporation
+ *
+ * Authors:
+ *    Rafael Antognolli <rafael.antognolli@intel.com>
+ *    Scott  Bauer      <scott.bauer@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef _UAPI_SED_OPAL_H
+#define _UAPI_SED_OPAL_H
+
+#include <linux/types.h>
+
+#define OPAL_KEY_MAX 256
+#define OPAL_MAX_LRS 9
+
+enum opal_mbr {
+	OPAL_MBR_ENABLE = 0x0,
+	OPAL_MBR_DISABLE = 0x01,
+};
+
+enum opal_user {
+	OPAL_ADMIN1 = 0x0,
+	OPAL_USER1 = 0x01,
+	OPAL_USER2 = 0x02,
+	OPAL_USER3 = 0x03,
+	OPAL_USER4 = 0x04,
+	OPAL_USER5 = 0x05,
+	OPAL_USER6 = 0x06,
+	OPAL_USER7 = 0x07,
+	OPAL_USER8 = 0x08,
+	OPAL_USER9 = 0x09,
+};
+
+enum opal_lock_state {
+	OPAL_RO = 0x01, /* 0001 */
+	OPAL_RW = 0x02, /* 0010 */
+	OPAL_LK = 0x04, /* 0100 */
+};
+
+struct opal_key {
+	__u8 lr;
+	__u8 key_len;
+	__u8 __align[6];
+	__u8 key[OPAL_KEY_MAX];
+};
+
+struct opal_lr_act {
+	struct opal_key key;
+	__u32 sum;
+	__u8    num_lrs;
+	__u8 lr[OPAL_MAX_LRS];
+	__u8 align[2]; /* Align to 8 byte boundary */
+};
+
+struct opal_session_info {
+	__u32 sum;
+	__u32 who;
+	struct opal_key opal_key;
+};
+
+struct opal_user_lr_setup {
+	__u64 range_start;
+	__u64 range_length;
+	__u32 RLE; /* Read Lock enabled */
+	__u32 WLE; /* Write Lock Enabled */
+	struct opal_session_info session;
+};
+
+struct opal_lock_unlock {
+	struct opal_session_info session;
+	__u32 l_state;
+	__u8 __align[4];
+};
+
+struct opal_new_pw {
+	struct opal_session_info session;
+
+	/* When we're not operating in sum, and we first set
+	 * passwords we need to set them via ADMIN authority.
+	 * After passwords are changed, we can set them via,
+	 * User authorities.
+	 * Because of this restriction we need to know about
+	 * Two different users. One in 'session' which we will use
+	 * to start the session and new_userr_pw as the user we're
+	 * chaning the pw for.
+	 */
+	struct opal_session_info new_user_pw;
+};
+
+struct opal_mbr_data {
+	struct opal_key key;
+	__u8 enable_disable;
+	__u8 __align[7];
+};
+
+#define IOC_OPAL_SAVE		    _IOW('p', 220, struct opal_lock_unlock)
+#define IOC_OPAL_LOCK_UNLOCK	    _IOW('p', 221, struct opal_lock_unlock)
+#define IOC_OPAL_TAKE_OWNERSHIP	    _IOW('p', 222, struct opal_key)
+#define IOC_OPAL_ACTIVATE_LSP       _IOW('p', 223, struct opal_lr_act)
+#define IOC_OPAL_SET_PW             _IOW('p', 224, struct opal_new_pw)
+#define IOC_OPAL_ACTIVATE_USR       _IOW('p', 225, struct opal_session_info)
+#define IOC_OPAL_REVERT_TPR         _IOW('p', 226, struct opal_key)
+#define IOC_OPAL_LR_SETUP           _IOW('p', 227, struct opal_user_lr_setup)
+#define IOC_OPAL_ADD_USR_TO_LR      _IOW('p', 228, struct opal_lock_unlock)
+#define IOC_OPAL_ENABLE_DISABLE_MBR _IOW('p', 229, struct opal_mbr_data)
+#define IOC_OPAL_ERASE_LR           _IOW('p', 230, struct opal_session_info)
+#define IOC_OPAL_SECURE_ERASE_LR    _IOW('p', 231, struct opal_session_info)
+
+#endif /* _UAPI_SED_OPAL_H */