Merge branch 'for-4.16/block' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "This is the main pull request for block IO related changes for the
  4.16 kernel. Nothing major in this pull request, but a good amount of
  improvements and fixes all over the map. This contains:

   - BFQ improvements, fixes, and cleanups from Angelo, Chiara, and
     Paolo.

   - Support for SMR zones for deadline and mq-deadline from Damien and
     Christoph.

   - Set of fixes for bcache by way of Michael Lyle, including fixes
     from himself, Kent, Rui, Tang, and Coly.

   - Series from Matias for lightnvm with fixes from Hans Holmberg,
     Javier, and Matias. Mostly centered around pblk, and the removing
     rrpc 1.2 in preparation for supporting 2.0.

   - A couple of NVMe pull requests from Christoph. Nothing major in
     here, just fixes and cleanups, and support for command tracing from
     Johannes.

   - Support for blk-throttle for tracking reads and writes separately.
     From Joseph Qi. A few cleanups/fixes also for blk-throttle from
     Weiping.

   - Series from Mike Snitzer that enables dm to register its queue more
     logically, something that's alwways been problematic on dm since
     it's a stacked device.

   - Series from Ming cleaning up some of the bio accessor use, in
     preparation for supporting multipage bvecs.

   - Various fixes from Ming closing up holes around queue mapping and
     quiescing.

   - BSD partition fix from Richard Narron, fixing a problem where we
     can't mount newer (10/11) FreeBSD partitions.

   - Series from Tejun reworking blk-mq timeout handling. The previous
     scheme relied on atomic bits, but it had races where we would think
     a request had timed out if it to reused at the wrong time.

   - null_blk now supports faking timeouts, to enable us to better
     exercise and test that functionality separately. From me.

   - Kill the separate atomic poll bit in the request struct. After
     this, we don't use the atomic bits on blk-mq anymore at all. From
     me.

   - sgl_alloc/free helpers from Bart.

   - Heavily contended tag case scalability improvement from me.

   - Various little fixes and cleanups from Arnd, Bart, Corentin,
     Douglas, Eryu, Goldwyn, and myself"

* 'for-4.16/block' of git://git.kernel.dk/linux-block: (186 commits)
  block: remove smart1,2.h
  nvme: add tracepoint for nvme_complete_rq
  nvme: add tracepoint for nvme_setup_cmd
  nvme-pci: introduce RECONNECTING state to mark initializing procedure
  nvme-rdma: remove redundant boolean for inline_data
  nvme: don't free uuid pointer before printing it
  nvme-pci: Suspend queues after deleting them
  bsg: use pr_debug instead of hand crafted macros
  blk-mq-debugfs: don't allow write on attributes with seq_operations set
  nvme-pci: Fix queue double allocations
  block: Set BIO_TRACE_COMPLETION on new bio during split
  blk-throttle: use queue_is_rq_based
  block: Remove kblockd_schedule_delayed_work{,_on}()
  blk-mq: Avoid that blk_mq_delay_run_hw_queue() introduces unintended delays
  blk-mq: Rename blk_mq_request_direct_issue() into blk_mq_request_issue_directly()
  lib/scatterlist: Fix chaining support in sgl_alloc_order()
  blk-throttle: track read and write request individually
  block: add bdev_read_only() checks to common helpers
  block: fail op_is_write() requests to read-only partitions
  blk-throttle: export io_serviced_recursive, io_service_bytes_recursive
  ...

12 files changed, 299 insertions, 119 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index 23d29b39f71e..d0eb659fa733 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -300,6 +300,29 @@ static inline void bio_get_last_bvec(struct bio *bio, struct bio_vec *bv)
 		bv->bv_len = iter.bi_bvec_done;
 }
 
+static inline unsigned bio_pages_all(struct bio *bio)
+{
+	WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED));
+	return bio->bi_vcnt;
+}
+
+static inline struct bio_vec *bio_first_bvec_all(struct bio *bio)
+{
+	WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED));
+	return bio->bi_io_vec;
+}
+
+static inline struct page *bio_first_page_all(struct bio *bio)
+{
+	return bio_first_bvec_all(bio)->bv_page;
+}
+
+static inline struct bio_vec *bio_last_bvec_all(struct bio *bio)
+{
+	WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED));
+	return &bio->bi_io_vec[bio->bi_vcnt - 1];
+}
+
 enum bip_flags {
 	BIP_BLOCK_INTEGRITY	= 1 << 0, /* block layer owns integrity data */
 	BIP_MAPPED_INTEGRITY	= 1 << 1, /* ref tag has been remapped */
@@ -477,7 +500,6 @@ static inline void bio_flush_dcache_pages(struct bio *bi)
 #endif
 
 extern void bio_copy_data(struct bio *dst, struct bio *src);
-extern int bio_alloc_pages(struct bio *bio, gfp_t gfp);
 extern void bio_free_pages(struct bio *bio);
 
 extern struct bio *bio_copy_user_iov(struct request_queue *,
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index e9825ff57b15..69bea82ebeb1 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -660,12 +660,14 @@ static inline void blkg_rwstat_reset(struct blkg_rwstat *rwstat)
 static inline void blkg_rwstat_add_aux(struct blkg_rwstat *to,
 				       struct blkg_rwstat *from)
 {
-	struct blkg_rwstat v = blkg_rwstat_read(from);
+	u64 sum[BLKG_RWSTAT_NR];
 	int i;
 
 	for (i = 0; i < BLKG_RWSTAT_NR; i++)
-		atomic64_add(atomic64_read(&v.aux_cnt[i]) +
-			     atomic64_read(&from->aux_cnt[i]),
+		sum[i] = percpu_counter_sum_positive(&from->cpu_cnt[i]);
+
+	for (i = 0; i < BLKG_RWSTAT_NR; i++)
+		atomic64_add(sum[i] + atomic64_read(&from->aux_cnt[i]),
 			     &to->aux_cnt[i]);
 }
 
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 95c9a5c862e2..8efcf49796a3 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -51,6 +51,7 @@ struct blk_mq_hw_ctx {
 	unsigned int		queue_num;
 
 	atomic_t		nr_active;
+	unsigned int		nr_expired;
 
 	struct hlist_node	cpuhp_dead;
 	struct kobject		kobj;
@@ -65,7 +66,7 @@ struct blk_mq_hw_ctx {
 #endif
 
 	/* Must be the last member - see also blk_mq_hw_ctx_size(). */
-	struct srcu_struct	queue_rq_srcu[0];
+	struct srcu_struct	srcu[0];
 };
 
 struct blk_mq_tag_set {
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 9e7d8bd776d2..c5d3db0d83f8 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -39,6 +39,34 @@ typedef u8 __bitwise blk_status_t;
 
 #define BLK_STS_AGAIN		((__force blk_status_t)12)
 
+/**
+ * blk_path_error - returns true if error may be path related
+ * @error: status the request was completed with
+ *
+ * Description:
+ *     This classifies block error status into non-retryable errors and ones
+ *     that may be successful if retried on a failover path.
+ *
+ * Return:
+ *     %false - retrying failover path will not help
+ *     %true  - may succeed if retried
+ */
+static inline bool blk_path_error(blk_status_t error)
+{
+	switch (error) {
+	case BLK_STS_NOTSUPP:
+	case BLK_STS_NOSPC:
+	case BLK_STS_TARGET:
+	case BLK_STS_NEXUS:
+	case BLK_STS_MEDIUM:
+	case BLK_STS_PROTECTION:
+		return false;
+	}
+
+	/* Anything else could be a path failure, so should be retried */
+	return true;
+}
+
 struct blk_issue_stat {
 	u64 stat;
 };
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 0ce8a372d506..4f3df807cf8f 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -27,6 +27,8 @@
 #include <linux/percpu-refcount.h>
 #include <linux/scatterlist.h>
 #include <linux/blkzoned.h>
+#include <linux/seqlock.h>
+#include <linux/u64_stats_sync.h>
 
 struct module;
 struct scsi_ioctl_command;
@@ -121,6 +123,12 @@ typedef __u32 __bitwise req_flags_t;
 /* Look at ->special_vec for the actual data payload instead of the
    bio chain. */
 #define RQF_SPECIAL_PAYLOAD	((__force req_flags_t)(1 << 18))
+/* The per-zone write lock is held for this request */
+#define RQF_ZONE_WRITE_LOCKED	((__force req_flags_t)(1 << 19))
+/* timeout is expired */
+#define RQF_MQ_TIMEOUT_EXPIRED	((__force req_flags_t)(1 << 20))
+/* already slept for hybrid poll */
+#define RQF_MQ_POLL_SLEPT	((__force req_flags_t)(1 << 21))
 
 /* flags that prevent us from merging requests: */
 #define RQF_NOMERGE_FLAGS \
@@ -133,12 +141,6 @@ typedef __u32 __bitwise req_flags_t;
  * especially blk_mq_rq_ctx_init() to take care of the added fields.
  */
 struct request {
-	struct list_head queuelist;
-	union {
-		struct __call_single_data csd;
-		u64 fifo_time;
-	};
-
 	struct request_queue *q;
 	struct blk_mq_ctx *mq_ctx;
 
@@ -148,8 +150,6 @@ struct request {
 
 	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;
@@ -158,6 +158,8 @@ struct request {
 	struct bio *bio;
 	struct bio *biotail;
 
+	struct list_head queuelist;
+
 	/*
 	 * The hash is used inside the scheduler, and killed once the
 	 * request reaches the dispatch list. The ipi_list is only used
@@ -205,19 +207,16 @@ struct request {
 	struct hd_struct *part;
 	unsigned long start_time;
 	struct blk_issue_stat issue_stat;
-#ifdef CONFIG_BLK_CGROUP
-	struct request_list *rl;		/* rl this rq is alloced from */
-	unsigned long long start_time_ns;
-	unsigned long long io_start_time_ns;    /* when passed to hardware */
-#endif
 	/* Number of scatter-gather DMA addr+len pairs after
 	 * physical address coalescing is performed.
 	 */
 	unsigned short nr_phys_segments;
+
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 	unsigned short nr_integrity_segments;
 #endif
 
+	unsigned short write_hint;
 	unsigned short ioprio;
 
 	unsigned int timeout;
@@ -226,11 +225,37 @@ struct request {
 
 	unsigned int extra_len;	/* length of alignment and padding */
 
-	unsigned short write_hint;
+	/*
+	 * On blk-mq, the lower bits of ->gstate (generation number and
+	 * state) carry the MQ_RQ_* state value and the upper bits the
+	 * generation number which is monotonically incremented and used to
+	 * distinguish the reuse instances.
+	 *
+	 * ->gstate_seq allows updates to ->gstate and other fields
+	 * (currently ->deadline) during request start to be read
+	 * atomically from the timeout path, so that it can operate on a
+	 * coherent set of information.
+	 */
+	seqcount_t gstate_seq;
+	u64 gstate;
+
+	/*
+	 * ->aborted_gstate is used by the timeout to claim a specific
+	 * recycle instance of this request.  See blk_mq_timeout_work().
+	 */
+	struct u64_stats_sync aborted_gstate_sync;
+	u64 aborted_gstate;
+
+	/* access through blk_rq_set_deadline, blk_rq_deadline */
+	unsigned long __deadline;
 
-	unsigned long deadline;
 	struct list_head timeout_list;
 
+	union {
+		struct __call_single_data csd;
+		u64 fifo_time;
+	};
+
 	/*
 	 * completion callback.
 	 */
@@ -239,6 +264,12 @@ struct request {
 
 	/* for bidi */
 	struct request *next_rq;
+
+#ifdef CONFIG_BLK_CGROUP
+	struct request_list *rl;		/* rl this rq is alloced from */
+	unsigned long long start_time_ns;
+	unsigned long long io_start_time_ns;    /* when passed to hardware */
+#endif
 };
 
 static inline bool blk_op_is_scsi(unsigned int op)
@@ -564,6 +595,22 @@ struct request_queue {
 	struct queue_limits	limits;
 
 	/*
+	 * Zoned block device information for request dispatch control.
+	 * nr_zones is the total number of zones of the device. This is always
+	 * 0 for regular block devices. seq_zones_bitmap is a bitmap of nr_zones
+	 * bits which indicates if a zone is conventional (bit clear) or
+	 * sequential (bit set). seq_zones_wlock is a bitmap of nr_zones
+	 * bits which indicates if a zone is write locked, that is, if a write
+	 * request targeting the zone was dispatched. All three fields are
+	 * initialized by the low level device driver (e.g. scsi/sd.c).
+	 * Stacking drivers (device mappers) may or may not initialize
+	 * these fields.
+	 */
+	unsigned int		nr_zones;
+	unsigned long		*seq_zones_bitmap;
+	unsigned long		*seq_zones_wlock;
+
+	/*
 	 * sg stuff
 	 */
 	unsigned int		sg_timeout;
@@ -807,6 +854,27 @@ static inline unsigned int blk_queue_zone_sectors(struct request_queue *q)
 	return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0;
 }
 
+static inline unsigned int blk_queue_nr_zones(struct request_queue *q)
+{
+	return q->nr_zones;
+}
+
+static inline unsigned int blk_queue_zone_no(struct request_queue *q,
+					     sector_t sector)
+{
+	if (!blk_queue_is_zoned(q))
+		return 0;
+	return sector >> ilog2(q->limits.chunk_sectors);
+}
+
+static inline bool blk_queue_zone_is_seq(struct request_queue *q,
+					 sector_t sector)
+{
+	if (!blk_queue_is_zoned(q) || !q->seq_zones_bitmap)
+		return false;
+	return test_bit(blk_queue_zone_no(q, sector), q->seq_zones_bitmap);
+}
+
 static inline bool rq_is_sync(struct request *rq)
 {
 	return op_is_sync(rq->cmd_flags);
@@ -1046,6 +1114,16 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq)
 	return blk_rq_cur_bytes(rq) >> 9;
 }
 
+static inline unsigned int blk_rq_zone_no(struct request *rq)
+{
+	return blk_queue_zone_no(rq->q, blk_rq_pos(rq));
+}
+
+static inline unsigned int blk_rq_zone_is_seq(struct request *rq)
+{
+	return blk_queue_zone_is_seq(rq->q, blk_rq_pos(rq));
+}
+
 /*
  * Some commands like WRITE SAME have a payload or data transfer size which
  * is different from the size of the request.  Any driver that supports such
@@ -1595,7 +1673,15 @@ static inline unsigned int bdev_zone_sectors(struct block_device *bdev)
 
 	if (q)
 		return blk_queue_zone_sectors(q);
+	return 0;
+}
+
+static inline unsigned int bdev_nr_zones(struct block_device *bdev)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
 
+	if (q)
+		return blk_queue_nr_zones(q);
 	return 0;
 }
 
@@ -1731,8 +1817,6 @@ static inline bool req_gap_front_merge(struct request *req, struct bio *bio)
 
 int kblockd_schedule_work(struct work_struct *work);
 int kblockd_schedule_work_on(int cpu, struct work_struct *work);
-int kblockd_schedule_delayed_work(struct delayed_work *dwork, unsigned long delay);
-int kblockd_schedule_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay);
 int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay);
 
 #ifdef CONFIG_BLK_CGROUP
@@ -1971,6 +2055,60 @@ extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int,
 extern int bdev_read_page(struct block_device *, sector_t, struct page *);
 extern int bdev_write_page(struct block_device *, sector_t, struct page *,
 						struct writeback_control *);
+
+#ifdef CONFIG_BLK_DEV_ZONED
+bool blk_req_needs_zone_write_lock(struct request *rq);
+void __blk_req_zone_write_lock(struct request *rq);
+void __blk_req_zone_write_unlock(struct request *rq);
+
+static inline void blk_req_zone_write_lock(struct request *rq)
+{
+	if (blk_req_needs_zone_write_lock(rq))
+		__blk_req_zone_write_lock(rq);
+}
+
+static inline void blk_req_zone_write_unlock(struct request *rq)
+{
+	if (rq->rq_flags & RQF_ZONE_WRITE_LOCKED)
+		__blk_req_zone_write_unlock(rq);
+}
+
+static inline bool blk_req_zone_is_write_locked(struct request *rq)
+{
+	return rq->q->seq_zones_wlock &&
+		test_bit(blk_rq_zone_no(rq), rq->q->seq_zones_wlock);
+}
+
+static inline bool blk_req_can_dispatch_to_zone(struct request *rq)
+{
+	if (!blk_req_needs_zone_write_lock(rq))
+		return true;
+	return !blk_req_zone_is_write_locked(rq);
+}
+#else
+static inline bool blk_req_needs_zone_write_lock(struct request *rq)
+{
+	return false;
+}
+
+static inline void blk_req_zone_write_lock(struct request *rq)
+{
+}
+
+static inline void blk_req_zone_write_unlock(struct request *rq)
+{
+}
+static inline bool blk_req_zone_is_write_locked(struct request *rq)
+{
+	return false;
+}
+
+static inline bool blk_req_can_dispatch_to_zone(struct request *rq)
+{
+	return true;
+}
+#endif /* CONFIG_BLK_DEV_ZONED */
+
 #else /* CONFIG_BLOCK */
 
 struct block_device;
diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index ec8a4d7af6bd..fe7a22dd133b 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -125,4 +125,13 @@ static inline bool bvec_iter_rewind(const struct bio_vec *bv,
 		((bvl = bvec_iter_bvec((bio_vec), (iter))), 1);	\
 	     bvec_iter_advance((bio_vec), &(iter), (bvl).bv_len))
 
+/* for iterating one bio from start to end */
+#define BVEC_ITER_ALL_INIT (struct bvec_iter)				\
+{									\
+	.bi_sector	= 0,						\
+	.bi_size	= UINT_MAX,					\
+	.bi_idx		= 0,						\
+	.bi_bvec_done	= 0,						\
+}
+
 #endif /* __LINUX_BVEC_ITER_H */
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 3d794b3dc532..6d9e230dffd2 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -198,8 +198,6 @@ 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 *);
-extern int elv_register_queue(struct request_queue *q);
-extern void elv_unregister_queue(struct request_queue *q);
 extern int elv_may_queue(struct request_queue *, unsigned int);
 extern void elv_completed_request(struct request_queue *, struct request *);
 extern int elv_set_request(struct request_queue *q, struct request *rq,
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 5144ebe046c9..5e3531027b51 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -395,6 +395,11 @@ static inline void add_disk(struct gendisk *disk)
 {
 	device_add_disk(NULL, disk);
 }
+extern void device_add_disk_no_queue_reg(struct device *parent, struct gendisk *disk);
+static inline void add_disk_no_queue_reg(struct gendisk *disk)
+{
+	device_add_disk_no_queue_reg(NULL, disk);
+}
 
 extern void del_gendisk(struct gendisk *gp);
 extern struct gendisk *get_gendisk(dev_t dev, int *partno);
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index 2d1d9de06728..7f4b60abdf27 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -50,10 +50,7 @@ struct nvm_id;
 struct nvm_dev;
 struct nvm_tgt_dev;
 
-typedef int (nvm_l2p_update_fn)(u64, u32, __le64 *, void *);
 typedef int (nvm_id_fn)(struct nvm_dev *, struct nvm_id *);
-typedef int (nvm_get_l2p_tbl_fn)(struct nvm_dev *, u64, u32,
-				nvm_l2p_update_fn *, void *);
 typedef int (nvm_op_bb_tbl_fn)(struct nvm_dev *, struct ppa_addr, u8 *);
 typedef int (nvm_op_set_bb_fn)(struct nvm_dev *, struct ppa_addr *, int, int);
 typedef int (nvm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *);
@@ -66,7 +63,6 @@ typedef void (nvm_dev_dma_free_fn)(void *, void*, dma_addr_t);
 
 struct nvm_dev_ops {
 	nvm_id_fn		*identity;
-	nvm_get_l2p_tbl_fn	*get_l2p_tbl;
 	nvm_op_bb_tbl_fn	*get_bb_tbl;
 	nvm_op_set_bb_fn	*set_bb_tbl;
 
@@ -112,8 +108,6 @@ enum {
 	NVM_RSP_WARN_HIGHECC	= 0x4700,
 
 	/* Device opcodes */
-	NVM_OP_HBREAD		= 0x02,
-	NVM_OP_HBWRITE		= 0x81,
 	NVM_OP_PWRITE		= 0x91,
 	NVM_OP_PREAD		= 0x92,
 	NVM_OP_ERASE		= 0x90,
@@ -165,12 +159,16 @@ struct nvm_id_group {
 	u8	fmtype;
 	u8	num_ch;
 	u8	num_lun;
-	u8	num_pln;
-	u16	num_blk;
-	u16	num_pg;
-	u16	fpg_sz;
+	u16	num_chk;
+	u16	clba;
 	u16	csecs;
 	u16	sos;
+
+	u16	ws_min;
+	u16	ws_opt;
+	u16	ws_seq;
+	u16	ws_per_chk;
+
 	u32	trdt;
 	u32	trdm;
 	u32	tprt;
@@ -181,7 +179,10 @@ struct nvm_id_group {
 	u32	mccap;
 	u16	cpar;
 
-	struct nvm_id_lp_tbl lptbl;
+	/* 1.2 compatibility */
+	u8	num_pln;
+	u16	num_pg;
+	u16	fpg_sz;
 };
 
 struct nvm_addr_format {
@@ -217,6 +218,10 @@ struct nvm_target {
 
 #define ADDR_EMPTY (~0ULL)
 
+#define NVM_TARGET_DEFAULT_OP (101)
+#define NVM_TARGET_MIN_OP (3)
+#define NVM_TARGET_MAX_OP (80)
+
 #define NVM_VERSION_MAJOR 1
 #define NVM_VERSION_MINOR 0
 #define NVM_VERSION_PATCH 0
@@ -239,7 +244,6 @@ struct nvm_rq {
 	void *meta_list;
 	dma_addr_t dma_meta_list;
 
-	struct completion *wait;
 	nvm_end_io_fn *end_io;
 
 	uint8_t opcode;
@@ -268,31 +272,38 @@ enum {
 	NVM_BLK_ST_BAD =	0x8,	/* Bad block */
 };
 
+
 /* Device generic information */
 struct nvm_geo {
+	/* generic geometry */
 	int nr_chnls;
-	int nr_luns;
-	int luns_per_chnl; /* -1 if channels are not symmetric */
-	int nr_planes;
-	int sec_per_pg; /* only sectors for a single page */
-	int pgs_per_blk;
-	int blks_per_lun;
-	int fpg_size;
-	int pfpg_size; /* size of buffer if all pages are to be read */
+	int all_luns; /* across channels */
+	int nr_luns; /* per channel */
+	int nr_chks; /* per lun */
+
 	int sec_size;
 	int oob_size;
 	int mccap;
-	struct nvm_addr_format ppaf;
 
-	/* Calculated/Cached values. These do not reflect the actual usable
-	 * blocks at run-time.
-	 */
+	int sec_per_chk;
+	int sec_per_lun;
+
+	int ws_min;
+	int ws_opt;
+	int ws_seq;
+	int ws_per_chk;
+
 	int max_rq_size;
-	int plane_mode; /* drive device in single, double or quad mode */
 
+	int op;
+
+	struct nvm_addr_format ppaf;
+
+	/* Legacy 1.2 specific geometry */
+	int plane_mode; /* drive device in single, double or quad mode */
+	int nr_planes;
+	int sec_per_pg; /* only sectors for a single page */
 	int sec_per_pl; /* all sectors across planes */
-	int sec_per_blk;
-	int sec_per_lun;
 };
 
 /* sub-device structure */
@@ -320,10 +331,6 @@ struct nvm_dev {
 	/* Device information */
 	struct nvm_geo geo;
 
-	  /* lower page table */
-	int lps_per_blk;
-	int *lptbl;
-
 	unsigned long total_secs;
 
 	unsigned long *lun_map;
@@ -346,36 +353,6 @@ struct nvm_dev {
 	struct list_head targets;
 };
 
-static inline struct ppa_addr linear_to_generic_addr(struct nvm_geo *geo,
-						     u64 pba)
-{
-	struct ppa_addr l;
-	int secs, pgs, blks, luns;
-	sector_t ppa = pba;
-
-	l.ppa = 0;
-
-	div_u64_rem(ppa, geo->sec_per_pg, &secs);
-	l.g.sec = secs;
-
-	sector_div(ppa, geo->sec_per_pg);
-	div_u64_rem(ppa, geo->pgs_per_blk, &pgs);
-	l.g.pg = pgs;
-
-	sector_div(ppa, geo->pgs_per_blk);
-	div_u64_rem(ppa, geo->blks_per_lun, &blks);
-	l.g.blk = blks;
-
-	sector_div(ppa, geo->blks_per_lun);
-	div_u64_rem(ppa, geo->luns_per_chnl, &luns);
-	l.g.lun = luns;
-
-	sector_div(ppa, geo->luns_per_chnl);
-	l.g.ch = ppa;
-
-	return l;
-}
-
 static inline struct ppa_addr generic_to_dev_addr(struct nvm_tgt_dev *tgt_dev,
 						  struct ppa_addr r)
 {
@@ -418,25 +395,6 @@ static inline struct ppa_addr dev_to_generic_addr(struct nvm_tgt_dev *tgt_dev,
 	return l;
 }
 
-static inline int ppa_empty(struct ppa_addr ppa_addr)
-{
-	return (ppa_addr.ppa == ADDR_EMPTY);
-}
-
-static inline void ppa_set_empty(struct ppa_addr *ppa_addr)
-{
-	ppa_addr->ppa = ADDR_EMPTY;
-}
-
-static inline int ppa_cmp_blk(struct ppa_addr ppa1, struct ppa_addr ppa2)
-{
-	if (ppa_empty(ppa1) || ppa_empty(ppa2))
-		return 0;
-
-	return ((ppa1.g.ch == ppa2.g.ch) && (ppa1.g.lun == ppa2.g.lun) &&
-					(ppa1.g.blk == ppa2.g.blk));
-}
-
 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 *,
@@ -481,17 +439,10 @@ extern int nvm_set_tgt_bb_tbl(struct nvm_tgt_dev *, struct ppa_addr *,
 extern int nvm_max_phys_sects(struct nvm_tgt_dev *);
 extern int nvm_submit_io(struct nvm_tgt_dev *, struct nvm_rq *);
 extern int nvm_submit_io_sync(struct nvm_tgt_dev *, struct nvm_rq *);
-extern int nvm_erase_sync(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 *);
 extern int nvm_bb_tbl_fold(struct nvm_dev *, u8 *, int);
 extern int nvm_get_tgt_bb_tbl(struct nvm_tgt_dev *, struct ppa_addr, u8 *);
 
-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 aea87f0d917b..4112e2bd747f 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -124,14 +124,20 @@ enum {
 
 #define NVME_CMB_BIR(cmbloc)	((cmbloc) & 0x7)
 #define NVME_CMB_OFST(cmbloc)	(((cmbloc) >> 12) & 0xfffff)
-#define NVME_CMB_SZ(cmbsz)	(((cmbsz) >> 12) & 0xfffff)
-#define NVME_CMB_SZU(cmbsz)	(((cmbsz) >> 8) & 0xf)
-
-#define NVME_CMB_WDS(cmbsz)	((cmbsz) & 0x10)
-#define NVME_CMB_RDS(cmbsz)	((cmbsz) & 0x8)
-#define NVME_CMB_LISTS(cmbsz)	((cmbsz) & 0x4)
-#define NVME_CMB_CQS(cmbsz)	((cmbsz) & 0x2)
-#define NVME_CMB_SQS(cmbsz)	((cmbsz) & 0x1)
+
+enum {
+	NVME_CMBSZ_SQS		= 1 << 0,
+	NVME_CMBSZ_CQS		= 1 << 1,
+	NVME_CMBSZ_LISTS	= 1 << 2,
+	NVME_CMBSZ_RDS		= 1 << 3,
+	NVME_CMBSZ_WDS		= 1 << 4,
+
+	NVME_CMBSZ_SZ_SHIFT	= 12,
+	NVME_CMBSZ_SZ_MASK	= 0xfffff,
+
+	NVME_CMBSZ_SZU_SHIFT	= 8,
+	NVME_CMBSZ_SZU_MASK	= 0xf,
+};
 
 /*
  * Submission and Completion Queue Entry Sizes for the NVM command set.
diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
index b7c83254c566..22b2131bcdcd 100644
--- a/include/linux/scatterlist.h
+++ b/include/linux/scatterlist.h
@@ -276,6 +276,17 @@ int sg_alloc_table_from_pages(struct sg_table *sgt, struct page **pages,
 			      unsigned int n_pages, unsigned int offset,
 			      unsigned long size, gfp_t gfp_mask);
 
+#ifdef CONFIG_SGL_ALLOC
+struct scatterlist *sgl_alloc_order(unsigned long long length,
+				    unsigned int order, bool chainable,
+				    gfp_t gfp, unsigned int *nent_p);
+struct scatterlist *sgl_alloc(unsigned long long length, gfp_t gfp,
+			      unsigned int *nent_p);
+void sgl_free_n_order(struct scatterlist *sgl, int nents, int order);
+void sgl_free_order(struct scatterlist *sgl, int order);
+void sgl_free(struct scatterlist *sgl);
+#endif /* CONFIG_SGL_ALLOC */
+
 size_t sg_copy_buffer(struct scatterlist *sgl, unsigned int nents, void *buf,
 		      size_t buflen, off_t skip, bool to_buffer);
 
diff --git a/include/uapi/linux/lightnvm.h b/include/uapi/linux/lightnvm.h
index 42d1a434af29..f9a1be7fc696 100644
--- a/include/uapi/linux/lightnvm.h
+++ b/include/uapi/linux/lightnvm.h
@@ -75,14 +75,23 @@ struct nvm_ioctl_create_simple {
 	__u32 lun_end;
 };
 
+struct nvm_ioctl_create_extended {
+	__u16 lun_begin;
+	__u16 lun_end;
+	__u16 op;
+	__u16 rsv;
+};
+
 enum {
 	NVM_CONFIG_TYPE_SIMPLE = 0,
+	NVM_CONFIG_TYPE_EXTENDED = 1,
 };
 
 struct nvm_ioctl_create_conf {
 	__u32 type;
 	union {
 		struct nvm_ioctl_create_simple s;
+		struct nvm_ioctl_create_extended e;
 	};
 };