Merge tag 'for-4.17/block-20180402' of git://git.kernel.dk/linux-block

Pull block layer updates from Jens Axboe:
 "It's a pretty quiet round this time, which is nice. This contains:

   - series from Bart, cleaning up the way we set/test/clear atomic
     queue flags.

   - series from Bart, fixing races between gendisk and queue
     registration and removal.

   - set of bcache fixes and improvements from various folks, by way of
     Michael Lyle.

   - set of lightnvm updates from Matias, most of it being the 1.2 to
     2.0 transition.

   - removal of unused DIO flags from Nikolay.

   - blk-mq/sbitmap memory ordering fixes from Omar.

   - divide-by-zero fix for BFQ from Paolo.

   - minor documentation patches from Randy.

   - timeout fix from Tejun.

   - Alpha "can't write a char atomically" fix from Mikulas.

   - set of NVMe fixes by way of Keith.

   - bsg and bsg-lib improvements from Christoph.

   - a few sed-opal fixes from Jonas.

   - cdrom check-disk-change deadlock fix from Maurizio.

   - various little fixes, comment fixes, etc from various folks"

* tag 'for-4.17/block-20180402' of git://git.kernel.dk/linux-block: (139 commits)
  blk-mq: Directly schedule q->timeout_work when aborting a request
  blktrace: fix comment in blktrace_api.h
  lightnvm: remove function name in strings
  lightnvm: pblk: remove some unnecessary NULL checks
  lightnvm: pblk: don't recover unwritten lines
  lightnvm: pblk: implement 2.0 support
  lightnvm: pblk: implement get log report chunk
  lightnvm: pblk: rename ppaf* to addrf*
  lightnvm: pblk: check for supported version
  lightnvm: implement get log report chunk helpers
  lightnvm: make address conversions depend on generic device
  lightnvm: add support for 2.0 address format
  lightnvm: normalize geometry nomenclature
  lightnvm: complete geo structure with maxoc*
  lightnvm: add shorten OCSSD version in geo
  lightnvm: add minor version to generic geometry
  lightnvm: simplify geometry structure
  lightnvm: pblk: refactor init/exit sequences
  lightnvm: Avoid validation of default op value
  lightnvm: centralize permission check for lightnvm ioctl
  ...

14 files changed, 319 insertions, 240 deletions

diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 69bea82ebeb1..6c666fd7de3c 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -88,6 +88,7 @@ struct blkg_policy_data {
 	/* the blkg and policy id this per-policy data belongs to */
 	struct blkcg_gq			*blkg;
 	int				plid;
+	bool				offline;
 };
 
 /*
diff --git a/include/linux/blk-mq-pci.h b/include/linux/blk-mq-pci.h
index 6338551e0fb9..9f4c17f0d2d8 100644
--- a/include/linux/blk-mq-pci.h
+++ b/include/linux/blk-mq-pci.h
@@ -5,6 +5,7 @@
 struct blk_mq_tag_set;
 struct pci_dev;
 
-int blk_mq_pci_map_queues(struct blk_mq_tag_set *set, struct pci_dev *pdev);
+int blk_mq_pci_map_queues(struct blk_mq_tag_set *set, struct pci_dev *pdev,
+			  int offset);
 
 #endif /* _LINUX_BLK_MQ_PCI_H */
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index bf18b95ed92d..17b18b91ebac 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -20,8 +20,13 @@ typedef void (bio_end_io_t) (struct bio *);
 
 /*
  * Block error status values.  See block/blk-core:blk_errors for the details.
+ * Alpha cannot write a byte atomically, so we need to use 32-bit value.
  */
+#if defined(CONFIG_ALPHA) && !defined(__alpha_bwx__)
+typedef u32 __bitwise blk_status_t;
+#else
 typedef u8 __bitwise blk_status_t;
+#endif
 #define	BLK_STS_OK 0
 #define BLK_STS_NOTSUPP		((__force blk_status_t)1)
 #define BLK_STS_TIMEOUT		((__force blk_status_t)2)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index ed63f3b69c12..9af3e0f430bc 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -707,73 +707,10 @@ struct request_queue {
 				 (1 << QUEUE_FLAG_SAME_COMP)	|	\
 				 (1 << QUEUE_FLAG_POLL))
 
-/*
- * @q->queue_lock is set while a queue is being initialized. Since we know
- * that no other threads access the queue object before @q->queue_lock has
- * been set, it is safe to manipulate queue flags without holding the
- * queue_lock if @q->queue_lock == NULL. See also blk_alloc_queue_node() and
- * blk_init_allocated_queue().
- */
-static inline void queue_lockdep_assert_held(struct request_queue *q)
-{
-	if (q->queue_lock)
-		lockdep_assert_held(q->queue_lock);
-}
-
-static inline void queue_flag_set_unlocked(unsigned int flag,
-					   struct request_queue *q)
-{
-	__set_bit(flag, &q->queue_flags);
-}
-
-static inline int queue_flag_test_and_clear(unsigned int flag,
-					    struct request_queue *q)
-{
-	queue_lockdep_assert_held(q);
-
-	if (test_bit(flag, &q->queue_flags)) {
-		__clear_bit(flag, &q->queue_flags);
-		return 1;
-	}
-
-	return 0;
-}
-
-static inline int queue_flag_test_and_set(unsigned int flag,
-					  struct request_queue *q)
-{
-	queue_lockdep_assert_held(q);
-
-	if (!test_bit(flag, &q->queue_flags)) {
-		__set_bit(flag, &q->queue_flags);
-		return 0;
-	}
-
-	return 1;
-}
-
-static inline void queue_flag_set(unsigned int flag, struct request_queue *q)
-{
-	queue_lockdep_assert_held(q);
-	__set_bit(flag, &q->queue_flags);
-}
-
-static inline void queue_flag_clear_unlocked(unsigned int flag,
-					     struct request_queue *q)
-{
-	__clear_bit(flag, &q->queue_flags);
-}
-
-static inline int queue_in_flight(struct request_queue *q)
-{
-	return q->in_flight[0] + q->in_flight[1];
-}
-
-static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
-{
-	queue_lockdep_assert_held(q);
-	__clear_bit(flag, &q->queue_flags);
-}
+void blk_queue_flag_set(unsigned int flag, struct request_queue *q);
+void blk_queue_flag_clear(unsigned int flag, struct request_queue *q);
+bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
+bool blk_queue_flag_test_and_clear(unsigned int flag, struct request_queue *q);
 
 #define blk_queue_tagged(q)	test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags)
 #define blk_queue_stopped(q)	test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
@@ -804,6 +741,11 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 extern int blk_set_preempt_only(struct request_queue *q);
 extern void blk_clear_preempt_only(struct request_queue *q);
 
+static inline int queue_in_flight(struct request_queue *q)
+{
+	return q->in_flight[0] + q->in_flight[1];
+}
+
 static inline bool blk_account_rq(struct request *rq)
 {
 	return (rq->rq_flags & RQF_STARTED) && !blk_rq_is_passthrough(rq);
@@ -1080,6 +1022,19 @@ static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
 }
 
 /*
+ * The basic unit of block I/O is a sector. It is used in a number of contexts
+ * in Linux (blk, bio, genhd). The size of one sector is 512 = 2**9
+ * bytes. Variables of type sector_t represent an offset or size that is a
+ * multiple of 512 bytes. Hence these two constants.
+ */
+#ifndef SECTOR_SHIFT
+#define SECTOR_SHIFT 9
+#endif
+#ifndef SECTOR_SIZE
+#define SECTOR_SIZE (1 << SECTOR_SHIFT)
+#endif
+
+/*
  * blk_rq_pos()			: the current sector
  * blk_rq_bytes()		: bytes left in the entire request
  * blk_rq_cur_bytes()		: bytes left in the current segment
@@ -1106,12 +1061,12 @@ extern unsigned int blk_rq_err_bytes(const struct request *rq);
 
 static inline unsigned int blk_rq_sectors(const struct request *rq)
 {
-	return blk_rq_bytes(rq) >> 9;
+	return blk_rq_bytes(rq) >> SECTOR_SHIFT;
 }
 
 static inline unsigned int blk_rq_cur_sectors(const struct request *rq)
 {
-	return blk_rq_cur_bytes(rq) >> 9;
+	return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT;
 }
 
 static inline unsigned int blk_rq_zone_no(struct request *rq)
@@ -1141,7 +1096,8 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
 						     int op)
 {
 	if (unlikely(op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE))
-		return min(q->limits.max_discard_sectors, UINT_MAX >> 9);
+		return min(q->limits.max_discard_sectors,
+			   UINT_MAX >> SECTOR_SHIFT);
 
 	if (unlikely(op == REQ_OP_WRITE_SAME))
 		return q->limits.max_write_same_sectors;
@@ -1321,7 +1277,8 @@ extern long nr_blockdev_pages(void);
 
 bool __must_check blk_get_queue(struct request_queue *);
 struct request_queue *blk_alloc_queue(gfp_t);
-struct request_queue *blk_alloc_queue_node(gfp_t, int);
+struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id,
+					   spinlock_t *lock);
 extern void blk_put_queue(struct request_queue *);
 extern void blk_set_queue_dying(struct request_queue *);
 
@@ -1452,16 +1409,21 @@ extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 static inline int sb_issue_discard(struct super_block *sb, sector_t block,
 		sector_t nr_blocks, gfp_t gfp_mask, unsigned long flags)
 {
-	return blkdev_issue_discard(sb->s_bdev, block << (sb->s_blocksize_bits - 9),
-				    nr_blocks << (sb->s_blocksize_bits - 9),
+	return blkdev_issue_discard(sb->s_bdev,
+				    block << (sb->s_blocksize_bits -
+					      SECTOR_SHIFT),
+				    nr_blocks << (sb->s_blocksize_bits -
+						  SECTOR_SHIFT),
 				    gfp_mask, flags);
 }
 static inline int sb_issue_zeroout(struct super_block *sb, sector_t block,
 		sector_t nr_blocks, gfp_t gfp_mask)
 {
 	return blkdev_issue_zeroout(sb->s_bdev,
-				    block << (sb->s_blocksize_bits - 9),
-				    nr_blocks << (sb->s_blocksize_bits - 9),
+				    block << (sb->s_blocksize_bits -
+					      SECTOR_SHIFT),
+				    nr_blocks << (sb->s_blocksize_bits -
+						  SECTOR_SHIFT),
 				    gfp_mask, 0);
 }
 
@@ -1568,7 +1530,8 @@ static inline int queue_alignment_offset(struct request_queue *q)
 static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector)
 {
 	unsigned int granularity = max(lim->physical_block_size, lim->io_min);
-	unsigned int alignment = sector_div(sector, granularity >> 9) << 9;
+	unsigned int alignment = sector_div(sector, granularity >> SECTOR_SHIFT)
+		<< SECTOR_SHIFT;
 
 	return (granularity + lim->alignment_offset - alignment) % granularity;
 }
@@ -1602,8 +1565,8 @@ static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector
 		return 0;
 
 	/* Why are these in bytes, not sectors? */
-	alignment = lim->discard_alignment >> 9;
-	granularity = lim->discard_granularity >> 9;
+	alignment = lim->discard_alignment >> SECTOR_SHIFT;
+	granularity = lim->discard_granularity >> SECTOR_SHIFT;
 	if (!granularity)
 		return 0;
 
@@ -1614,7 +1577,7 @@ static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector
 	offset = (granularity + alignment - offset) % granularity;
 
 	/* Turn it back into bytes, gaah */
-	return offset << 9;
+	return offset << SECTOR_SHIFT;
 }
 
 static inline int bdev_discard_alignment(struct block_device *bdev)
diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h
index b1be0233ce35..28a7ccc55c89 100644
--- a/include/linux/bsg-lib.h
+++ b/include/linux/bsg-lib.h
@@ -38,12 +38,12 @@ struct bsg_buffer {
 };
 
 struct bsg_job {
-	struct scsi_request sreq;
 	struct device *dev;
-	struct request *req;
 
 	struct kref kref;
 
+	unsigned int timeout;
+
 	/* Transport/driver specific request/reply structs */
 	void *request;
 	void *reply;
@@ -63,6 +63,9 @@ struct bsg_job {
 	struct bsg_buffer request_payload;
 	struct bsg_buffer reply_payload;
 
+	int result;
+	unsigned int reply_payload_rcv_len;
+
 	void *dd_data;		/* Used for driver-specific storage */
 };
 
diff --git a/include/linux/bsg.h b/include/linux/bsg.h
index 2a202e41a3af..0c7dd9ceb139 100644
--- a/include/linux/bsg.h
+++ b/include/linux/bsg.h
@@ -1,34 +1,43 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef BSG_H
-#define BSG_H
+#ifndef _LINUX_BSG_H
+#define _LINUX_BSG_H
 
 #include <uapi/linux/bsg.h>
 
+struct request;
+
+#ifdef CONFIG_BLK_DEV_BSG
+struct bsg_ops {
+	int	(*check_proto)(struct sg_io_v4 *hdr);
+	int	(*fill_hdr)(struct request *rq, struct sg_io_v4 *hdr,
+				fmode_t mode);
+	int	(*complete_rq)(struct request *rq, struct sg_io_v4 *hdr);
+	void	(*free_rq)(struct request *rq);
+};
 
-#if defined(CONFIG_BLK_DEV_BSG)
 struct bsg_class_device {
 	struct device *class_dev;
 	struct device *parent;
 	int minor;
 	struct request_queue *queue;
 	struct kref ref;
+	const struct bsg_ops *ops;
 	void (*release)(struct device *);
 };
 
-extern int bsg_register_queue(struct request_queue *q,
-			      struct device *parent, const char *name,
-			      void (*release)(struct device *));
-extern void bsg_unregister_queue(struct request_queue *);
+int bsg_register_queue(struct request_queue *q, struct device *parent,
+		const char *name, const struct bsg_ops *ops,
+		void (*release)(struct device *));
+int bsg_scsi_register_queue(struct request_queue *q, struct device *parent);
+void bsg_unregister_queue(struct request_queue *q);
 #else
-static inline int bsg_register_queue(struct request_queue *q,
-				     struct device *parent, const char *name,
-				     void (*release)(struct device *))
+static inline int bsg_scsi_register_queue(struct request_queue *q,
+		struct device *parent)
 {
 	return 0;
 }
 static inline void bsg_unregister_queue(struct request_queue *q)
 {
 }
-#endif
-
-#endif
+#endif /* CONFIG_BLK_DEV_BSG */
+#endif /* _LINUX_BSG_H */
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index da83f64952e7..4384433b50e7 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -542,8 +542,6 @@ do {									\
 #define DMEMIT(x...) sz += ((sz >= maxlen) ? \
 			  0 : scnprintf(result + sz, maxlen - sz, x))
 
-#define SECTOR_SHIFT 9
-
 /*
  * Definitions of return values from target end_io function.
  */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index c6baf767619e..070807ce3e41 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2977,12 +2977,6 @@ enum {
 
 	/* filesystem does not support filling holes */
 	DIO_SKIP_HOLES	= 0x02,
-
-	/* filesystem can handle aio writes beyond i_size */
-	DIO_ASYNC_EXTEND = 0x04,
-
-	/* inode/fs/bdev does not need truncate protection */
-	DIO_SKIP_DIO_COUNT = 0x08,
 };
 
 void dio_end_io(struct bio *bio);
diff --git a/include/linux/ide.h b/include/linux/ide.h
index 1d6f16110eae..ca9d34feb572 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -160,7 +160,6 @@ struct ide_io_ports {
  */
 #define PARTN_BITS	6	/* number of minor dev bits for partitions */
 #define MAX_DRIVES	2	/* per interface; 2 assumed by lots of code */
-#define SECTOR_SIZE	512
 
 /*
  * Timeouts for various operations:
diff --git a/include/linux/inet.h b/include/linux/inet.h
index 636ebe87e6f8..97defc1139e9 100644
--- a/include/linux/inet.h
+++ b/include/linux/inet.h
@@ -59,5 +59,6 @@ extern int in6_pton(const char *src, int srclen, u8 *dst, int delim, const char
 
 extern int inet_pton_with_scope(struct net *net, unsigned short af,
 		const char *src, const char *port, struct sockaddr_storage *addr);
+extern bool inet_addr_is_any(struct sockaddr *addr);
 
 #endif	/* _LINUX_INET_H */
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index 7f4b60abdf27..6e0859b9d4d2 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -16,26 +16,58 @@ enum {
 	NVM_IOTYPE_GC = 1,
 };
 
-#define NVM_BLK_BITS (16)
-#define NVM_PG_BITS  (16)
-#define NVM_SEC_BITS (8)
-#define NVM_PL_BITS  (8)
-#define NVM_LUN_BITS (8)
-#define NVM_CH_BITS  (7)
+/* common format */
+#define NVM_GEN_CH_BITS  (8)
+#define NVM_GEN_LUN_BITS (8)
+#define NVM_GEN_BLK_BITS (16)
+#define NVM_GEN_RESERVED (32)
+
+/* 1.2 format */
+#define NVM_12_PG_BITS  (16)
+#define NVM_12_PL_BITS  (4)
+#define NVM_12_SEC_BITS (4)
+#define NVM_12_RESERVED (8)
+
+/* 2.0 format */
+#define NVM_20_SEC_BITS (24)
+#define NVM_20_RESERVED (8)
+
+enum {
+	NVM_OCSSD_SPEC_12 = 12,
+	NVM_OCSSD_SPEC_20 = 20,
+};
 
 struct ppa_addr {
 	/* Generic structure for all addresses */
 	union {
+		/* generic device format */
+		struct {
+			u64 ch		: NVM_GEN_CH_BITS;
+			u64 lun		: NVM_GEN_LUN_BITS;
+			u64 blk		: NVM_GEN_BLK_BITS;
+			u64 reserved	: NVM_GEN_RESERVED;
+		} a;
+
+		/* 1.2 device format */
 		struct {
-			u64 blk		: NVM_BLK_BITS;
-			u64 pg		: NVM_PG_BITS;
-			u64 sec		: NVM_SEC_BITS;
-			u64 pl		: NVM_PL_BITS;
-			u64 lun		: NVM_LUN_BITS;
-			u64 ch		: NVM_CH_BITS;
-			u64 reserved	: 1;
+			u64 ch		: NVM_GEN_CH_BITS;
+			u64 lun		: NVM_GEN_LUN_BITS;
+			u64 blk		: NVM_GEN_BLK_BITS;
+			u64 pg		: NVM_12_PG_BITS;
+			u64 pl		: NVM_12_PL_BITS;
+			u64 sec		: NVM_12_SEC_BITS;
+			u64 reserved	: NVM_12_RESERVED;
 		} g;
 
+		/* 2.0 device format */
+		struct {
+			u64 grp		: NVM_GEN_CH_BITS;
+			u64 pu		: NVM_GEN_LUN_BITS;
+			u64 chk		: NVM_GEN_BLK_BITS;
+			u64 sec		: NVM_20_SEC_BITS;
+			u64 reserved	: NVM_20_RESERVED;
+		} m;
+
 		struct {
 			u64 line	: 63;
 			u64 is_cached	: 1;
@@ -49,10 +81,13 @@ struct nvm_rq;
 struct nvm_id;
 struct nvm_dev;
 struct nvm_tgt_dev;
+struct nvm_chk_meta;
 
-typedef int (nvm_id_fn)(struct nvm_dev *, struct nvm_id *);
+typedef int (nvm_id_fn)(struct nvm_dev *);
 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_get_chk_meta_fn)(struct nvm_dev *, struct nvm_chk_meta *,
+								sector_t, int);
 typedef int (nvm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *);
 typedef int (nvm_submit_io_sync_fn)(struct nvm_dev *, struct nvm_rq *);
 typedef void *(nvm_create_dma_pool_fn)(struct nvm_dev *, char *);
@@ -66,6 +101,8 @@ struct nvm_dev_ops {
 	nvm_op_bb_tbl_fn	*get_bb_tbl;
 	nvm_op_set_bb_fn	*set_bb_tbl;
 
+	nvm_get_chk_meta_fn	*get_chk_meta;
+
 	nvm_submit_io_fn	*submit_io;
 	nvm_submit_io_sync_fn	*submit_io_sync;
 
@@ -73,8 +110,6 @@ struct nvm_dev_ops {
 	nvm_destroy_dma_pool_fn	*destroy_dma_pool;
 	nvm_dev_dma_alloc_fn	*dev_dma_alloc;
 	nvm_dev_dma_free_fn	*dev_dma_free;
-
-	unsigned int		max_phys_sect;
 };
 
 #ifdef CONFIG_NVM
@@ -154,60 +189,75 @@ struct nvm_id_lp_tbl {
 	struct nvm_id_lp_mlc mlc;
 };
 
-struct nvm_id_group {
-	u8	mtype;
-	u8	fmtype;
-	u8	num_ch;
-	u8	num_lun;
-	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;
-	u32	tprm;
-	u32	tbet;
-	u32	tbem;
-	u32	mpos;
-	u32	mccap;
-	u16	cpar;
-
-	/* 1.2 compatibility */
-	u8	num_pln;
-	u16	num_pg;
-	u16	fpg_sz;
-};
-
-struct nvm_addr_format {
-	u8	ch_offset;
+struct nvm_addrf_12 {
 	u8	ch_len;
-	u8	lun_offset;
 	u8	lun_len;
-	u8	pln_offset;
+	u8	blk_len;
+	u8	pg_len;
 	u8	pln_len;
+	u8	sec_len;
+
+	u8	ch_offset;
+	u8	lun_offset;
 	u8	blk_offset;
-	u8	blk_len;
 	u8	pg_offset;
-	u8	pg_len;
-	u8	sect_offset;
-	u8	sect_len;
+	u8	pln_offset;
+	u8	sec_offset;
+
+	u64	ch_mask;
+	u64	lun_mask;
+	u64	blk_mask;
+	u64	pg_mask;
+	u64	pln_mask;
+	u64	sec_mask;
 };
 
-struct nvm_id {
-	u8	ver_id;
-	u8	vmnt;
-	u32	cap;
-	u32	dom;
-	struct nvm_addr_format ppaf;
-	struct nvm_id_group grp;
-} __packed;
+struct nvm_addrf {
+	u8	ch_len;
+	u8	lun_len;
+	u8	chk_len;
+	u8	sec_len;
+	u8	rsv_len[2];
+
+	u8	ch_offset;
+	u8	lun_offset;
+	u8	chk_offset;
+	u8	sec_offset;
+	u8	rsv_off[2];
+
+	u64	ch_mask;
+	u64	lun_mask;
+	u64	chk_mask;
+	u64	sec_mask;
+	u64	rsv_mask[2];
+};
+
+enum {
+	/* Chunk states */
+	NVM_CHK_ST_FREE =	1 << 0,
+	NVM_CHK_ST_CLOSED =	1 << 1,
+	NVM_CHK_ST_OPEN =	1 << 2,
+	NVM_CHK_ST_OFFLINE =	1 << 3,
+
+	/* Chunk types */
+	NVM_CHK_TP_W_SEQ =	1 << 0,
+	NVM_CHK_TP_W_RAN =	1 << 1,
+	NVM_CHK_TP_SZ_SPEC =	1 << 4,
+};
+
+/*
+ * Note: The structure size is linked to nvme_nvm_chk_meta such that the same
+ * buffer can be used when converting from little endian to cpu addressing.
+ */
+struct nvm_chk_meta {
+	u8	state;
+	u8	type;
+	u8	wi;
+	u8	rsvd[5];
+	u64	slba;
+	u64	cnlb;
+	u64	wp;
+};
 
 struct nvm_target {
 	struct list_head list;
@@ -226,6 +276,8 @@ struct nvm_target {
 #define NVM_VERSION_MINOR 0
 #define NVM_VERSION_PATCH 0
 
+#define NVM_MAX_VLBA (64) /* max logical blocks in a vector command */
+
 struct nvm_rq;
 typedef void (nvm_end_io_fn)(struct nvm_rq *);
 
@@ -272,38 +324,69 @@ enum {
 	NVM_BLK_ST_BAD =	0x8,	/* Bad block */
 };
 
-
-/* Device generic information */
+/* Instance geometry */
 struct nvm_geo {
-	/* generic geometry */
-	int nr_chnls;
-	int all_luns; /* across channels */
-	int nr_luns; /* per channel */
-	int nr_chks; /* per lun */
+	/* device reported version */
+	u8	major_ver_id;
+	u8	minor_ver_id;
+
+	/* kernel short version */
+	u8	version;
 
-	int sec_size;
-	int oob_size;
-	int mccap;
+	/* instance specific geometry */
+	int num_ch;
+	int num_lun;		/* per channel */
 
-	int sec_per_chk;
-	int sec_per_lun;
+	/* calculated values */
+	int all_luns;		/* across channels */
+	int all_chunks;		/* across channels */
 
-	int ws_min;
-	int ws_opt;
-	int ws_seq;
-	int ws_per_chk;
+	int op;			/* over-provision in instance */
 
-	int max_rq_size;
+	sector_t total_secs;	/* across channels */
+
+	/* chunk geometry */
+	u32	num_chk;	/* chunks per lun */
+	u32	clba;		/* sectors per chunk */
+	u16	csecs;		/* sector size */
+	u16	sos;		/* out-of-band area size */
+
+	/* device write constrains */
+	u32	ws_min;		/* minimum write size */
+	u32	ws_opt;		/* optimal write size */
+	u32	mw_cunits;	/* distance required for successful read */
+	u32	maxoc;		/* maximum open chunks */
+	u32	maxocpu;	/* maximum open chunks per parallel unit */
+
+	/* device capabilities */
+	u32	mccap;
+
+	/* device timings */
+	u32	trdt;		/* Avg. Tread (ns) */
+	u32	trdm;		/* Max Tread (ns) */
+	u32	tprt;		/* Avg. Tprog (ns) */
+	u32	tprm;		/* Max Tprog (ns) */
+	u32	tbet;		/* Avg. Terase (ns) */
+	u32	tbem;		/* Max Terase (ns) */
+
+	/* generic address format */
+	struct nvm_addrf addrf;
+
+	/* 1.2 compatibility */
+	u8	vmnt;
+	u32	cap;
+	u32	dom;
 
-	int op;
+	u8	mtype;
+	u8	fmtype;
 
-	struct nvm_addr_format ppaf;
+	u16	cpar;
+	u32	mpos;
 
-	/* 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 */
+	u8	num_pln;
+	u8	pln_mode;
+	u16	num_pg;
+	u16	fpg_sz;
 };
 
 /* sub-device structure */
@@ -314,9 +397,6 @@ struct nvm_tgt_dev {
 	/* Base ppas for target LUNs */
 	struct ppa_addr *luns;
 
-	sector_t total_secs;
-
-	struct nvm_id identity;
 	struct request_queue *q;
 
 	struct nvm_dev *parent;
@@ -331,13 +411,9 @@ struct nvm_dev {
 	/* Device information */
 	struct nvm_geo geo;
 
-	unsigned long total_secs;
-
 	unsigned long *lun_map;
 	void *dma_pool;
 
-	struct nvm_id identity;
-
 	/* Backend device */
 	struct request_queue *q;
 	char name[DISK_NAME_LEN];
@@ -353,44 +429,58 @@ struct nvm_dev {
 	struct list_head targets;
 };
 
-static inline struct ppa_addr generic_to_dev_addr(struct nvm_tgt_dev *tgt_dev,
+static inline struct ppa_addr generic_to_dev_addr(struct nvm_dev *dev,
 						  struct ppa_addr r)
 {
-	struct nvm_geo *geo = &tgt_dev->geo;
+	struct nvm_geo *geo = &dev->geo;
 	struct ppa_addr l;
 
-	l.ppa = ((u64)r.g.blk) << geo->ppaf.blk_offset;
-	l.ppa |= ((u64)r.g.pg) << geo->ppaf.pg_offset;
-	l.ppa |= ((u64)r.g.sec) << geo->ppaf.sect_offset;
-	l.ppa |= ((u64)r.g.pl) << geo->ppaf.pln_offset;
-	l.ppa |= ((u64)r.g.lun) << geo->ppaf.lun_offset;
-	l.ppa |= ((u64)r.g.ch) << geo->ppaf.ch_offset;
+	if (geo->version == NVM_OCSSD_SPEC_12) {
+		struct nvm_addrf_12 *ppaf = (struct nvm_addrf_12 *)&geo->addrf;
+
+		l.ppa = ((u64)r.g.ch) << ppaf->ch_offset;
+		l.ppa |= ((u64)r.g.lun) << ppaf->lun_offset;
+		l.ppa |= ((u64)r.g.blk) << ppaf->blk_offset;
+		l.ppa |= ((u64)r.g.pg) << ppaf->pg_offset;
+		l.ppa |= ((u64)r.g.pl) << ppaf->pln_offset;
+		l.ppa |= ((u64)r.g.sec) << ppaf->sec_offset;
+	} else {
+		struct nvm_addrf *lbaf = &geo->addrf;
+
+		l.ppa = ((u64)r.m.grp) << lbaf->ch_offset;
+		l.ppa |= ((u64)r.m.pu) << lbaf->lun_offset;
+		l.ppa |= ((u64)r.m.chk) << lbaf->chk_offset;
+		l.ppa |= ((u64)r.m.sec) << lbaf->sec_offset;
+	}
 
 	return l;
 }
 
-static inline struct ppa_addr dev_to_generic_addr(struct nvm_tgt_dev *tgt_dev,
+static inline struct ppa_addr dev_to_generic_addr(struct nvm_dev *dev,
 						  struct ppa_addr r)
 {
-	struct nvm_geo *geo = &tgt_dev->geo;
+	struct nvm_geo *geo = &dev->geo;
 	struct ppa_addr l;
 
 	l.ppa = 0;
-	/*
-	 * (r.ppa << X offset) & X len bitmask. X eq. blk, pg, etc.
-	 */
-	l.g.blk = (r.ppa >> geo->ppaf.blk_offset) &
-					(((1 << geo->ppaf.blk_len) - 1));
-	l.g.pg |= (r.ppa >> geo->ppaf.pg_offset) &
-					(((1 << geo->ppaf.pg_len) - 1));
-	l.g.sec |= (r.ppa >> geo->ppaf.sect_offset) &
-					(((1 << geo->ppaf.sect_len) - 1));
-	l.g.pl |= (r.ppa >> geo->ppaf.pln_offset) &
-					(((1 << geo->ppaf.pln_len) - 1));
-	l.g.lun |= (r.ppa >> geo->ppaf.lun_offset) &
-					(((1 << geo->ppaf.lun_len) - 1));
-	l.g.ch |= (r.ppa >> geo->ppaf.ch_offset) &
-					(((1 << geo->ppaf.ch_len) - 1));
+
+	if (geo->version == NVM_OCSSD_SPEC_12) {
+		struct nvm_addrf_12 *ppaf = (struct nvm_addrf_12 *)&geo->addrf;
+
+		l.g.ch = (r.ppa & ppaf->ch_mask) >> ppaf->ch_offset;
+		l.g.lun = (r.ppa & ppaf->lun_mask) >> ppaf->lun_offset;
+		l.g.blk = (r.ppa & ppaf->blk_mask) >> ppaf->blk_offset;
+		l.g.pg = (r.ppa & ppaf->pg_mask) >> ppaf->pg_offset;
+		l.g.pl = (r.ppa & ppaf->pln_mask) >> ppaf->pln_offset;
+		l.g.sec = (r.ppa & ppaf->sec_mask) >> ppaf->sec_offset;
+	} else {
+		struct nvm_addrf *lbaf = &geo->addrf;
+
+		l.m.grp = (r.ppa & lbaf->ch_mask) >> lbaf->ch_offset;
+		l.m.pu = (r.ppa & lbaf->lun_mask) >> lbaf->lun_offset;
+		l.m.chk = (r.ppa & lbaf->chk_mask) >> lbaf->chk_offset;
+		l.m.sec = (r.ppa & lbaf->sec_mask) >> lbaf->sec_offset;
+	}
 
 	return l;
 }
@@ -434,9 +524,13 @@ 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_get_chunk_meta(struct nvm_tgt_dev *tgt_dev,
+			      struct nvm_chk_meta *meta, struct ppa_addr ppa,
+			      int nchks);
+
 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 int nvm_submit_io_sync(struct nvm_tgt_dev *, struct nvm_rq *);
 extern void nvm_end_io(struct nvm_rq *);
diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h
index 478acf6efac6..e964bbd03fc2 100644
--- a/include/linux/rtsx_pci.h
+++ b/include/linux/rtsx_pci.h
@@ -36,12 +36,12 @@
 #define   CHECK_REG_CMD			2
 
 #define RTSX_HDBAR			0x08
-#define   SG_INT			0x04
-#define   SG_END			0x02
-#define   SG_VALID			0x01
-#define   SG_NO_OP			0x00
-#define   SG_TRANS_DATA			(0x02 << 4)
-#define   SG_LINK_DESC			(0x03 << 4)
+#define   RTSX_SG_INT			0x04
+#define   RTSX_SG_END			0x02
+#define   RTSX_SG_VALID			0x01
+#define   RTSX_SG_NO_OP			0x00
+#define   RTSX_SG_TRANS_DATA		(0x02 << 4)
+#define   RTSX_SG_LINK_DESC		(0x03 << 4)
 #define RTSX_HDBCTLR			0x0C
 #define   SDMA_MODE			0x00
 #define   ADMA_MODE			(0x02 << 26)
diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h
index 0dcc60e820de..841585f6e5f2 100644
--- a/include/linux/sbitmap.h
+++ b/include/linux/sbitmap.h
@@ -171,6 +171,8 @@ void sbitmap_resize(struct sbitmap *sb, unsigned int depth);
  *               starting from the last allocated bit. This is less efficient
  *               than the default behavior (false).
  *
+ * This operation provides acquire barrier semantics if it succeeds.
+ *
  * Return: Non-negative allocated bit number if successful, -1 otherwise.
  */
 int sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint, bool round_robin);
@@ -300,6 +302,12 @@ static inline void sbitmap_clear_bit(struct sbitmap *sb, unsigned int bitnr)
 	clear_bit(SB_NR_TO_BIT(sb, bitnr), __sbitmap_word(sb, bitnr));
 }
 
+static inline void sbitmap_clear_bit_unlock(struct sbitmap *sb,
+					    unsigned int bitnr)
+{
+	clear_bit_unlock(SB_NR_TO_BIT(sb, bitnr), __sbitmap_word(sb, bitnr));
+}
+
 static inline int sbitmap_test_bit(struct sbitmap *sb, unsigned int bitnr)
 {
 	return test_bit(SB_NR_TO_BIT(sb, bitnr), __sbitmap_word(sb, bitnr));
diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
index aa5d4eb725f5..51f52020ad5f 100644
--- a/include/linux/scatterlist.h
+++ b/include/linux/scatterlist.h
@@ -65,16 +65,18 @@ struct sg_table {
  */
 
 #define SG_MAGIC	0x87654321
+#define SG_CHAIN	0x01UL
+#define SG_END		0x02UL
 
 /*
  * We overload the LSB of the page pointer to indicate whether it's
  * a valid sg entry, or whether it points to the start of a new scatterlist.
  * Those low bits are there for everyone! (thanks mason :-)
  */
-#define sg_is_chain(sg)		((sg)->page_link & 0x01)
-#define sg_is_last(sg)		((sg)->page_link & 0x02)
+#define sg_is_chain(sg)		((sg)->page_link & SG_CHAIN)
+#define sg_is_last(sg)		((sg)->page_link & SG_END)
 #define sg_chain_ptr(sg)	\
-	((struct scatterlist *) ((sg)->page_link & ~0x03))
+	((struct scatterlist *) ((sg)->page_link & ~(SG_CHAIN | SG_END)))
 
 /**
  * sg_assign_page - Assign a given page to an SG entry
@@ -88,13 +90,13 @@ struct sg_table {
  **/
 static inline void sg_assign_page(struct scatterlist *sg, struct page *page)
 {
-	unsigned long page_link = sg->page_link & 0x3;
+	unsigned long page_link = sg->page_link & (SG_CHAIN | SG_END);
 
 	/*
 	 * In order for the low bit stealing approach to work, pages
 	 * must be aligned at a 32-bit boundary as a minimum.
 	 */
-	BUG_ON((unsigned long) page & 0x03);
+	BUG_ON((unsigned long) page & (SG_CHAIN | SG_END));
 #ifdef CONFIG_DEBUG_SG
 	BUG_ON(sg->sg_magic != SG_MAGIC);
 	BUG_ON(sg_is_chain(sg));
@@ -130,7 +132,7 @@ static inline struct page *sg_page(struct scatterlist *sg)
 	BUG_ON(sg->sg_magic != SG_MAGIC);
 	BUG_ON(sg_is_chain(sg));
 #endif
-	return (struct page *)((sg)->page_link & ~0x3);
+	return (struct page *)((sg)->page_link & ~(SG_CHAIN | SG_END));
 }
 
 /**
@@ -178,7 +180,8 @@ static inline void sg_chain(struct scatterlist *prv, unsigned int prv_nents,
 	 * Set lowest bit to indicate a link pointer, and make sure to clear
 	 * the termination bit if it happens to be set.
 	 */
-	prv[prv_nents - 1].page_link = ((unsigned long) sgl | 0x01) & ~0x02;
+	prv[prv_nents - 1].page_link = ((unsigned long) sgl | SG_CHAIN)
+					& ~SG_END;
 }
 
 /**
@@ -198,8 +201,8 @@ static inline void sg_mark_end(struct scatterlist *sg)
 	/*
 	 * Set termination bit, clear potential chain bit
 	 */
-	sg->page_link |= 0x02;
-	sg->page_link &= ~0x01;
+	sg->page_link |= SG_END;
+	sg->page_link &= ~SG_CHAIN;
 }
 
 /**
@@ -215,7 +218,7 @@ static inline void sg_unmark_end(struct scatterlist *sg)
 #ifdef CONFIG_DEBUG_SG
 	BUG_ON(sg->sg_magic != SG_MAGIC);
 #endif
-	sg->page_link &= ~0x02;
+	sg->page_link &= ~SG_END;
 }
 
 /**