Merge tag 'for-4.20/block-20181021' of git://git.kernel.dk/linux-block

Pull block layer updates from Jens Axboe:
 "This is the main pull request for block changes for 4.20. This
  contains:

   - Series enabling runtime PM for blk-mq (Bart).

   - Two pull requests from Christoph for NVMe, with items such as;
      - Better AEN tracking
      - Multipath improvements
      - RDMA fixes
      - Rework of FC for target removal
      - Fixes for issues identified by static checkers
      - Fabric cleanups, as prep for TCP transport
      - Various cleanups and bug fixes

   - Block merging cleanups (Christoph)

   - Conversion of drivers to generic DMA mapping API (Christoph)

   - Series fixing ref count issues with blkcg (Dennis)

   - Series improving BFQ heuristics (Paolo, et al)

   - Series improving heuristics for the Kyber IO scheduler (Omar)

   - Removal of dangerous bio_rewind_iter() API (Ming)

   - Apply single queue IPI redirection logic to blk-mq (Ming)

   - Set of fixes and improvements for bcache (Coly et al)

   - Series closing a hotplug race with sysfs group attributes (Hannes)

   - Set of patches for lightnvm:
      - pblk trace support (Hans)
      - SPDX license header update (Javier)
      - Tons of refactoring patches to cleanly abstract the 1.2 and 2.0
        specs behind a common core interface. (Javier, Matias)
      - Enable pblk to use a common interface to retrieve chunk metadata
        (Matias)
      - Bug fixes (Various)

   - Set of fixes and updates to the blk IO latency target (Josef)

   - blk-mq queue number updates fixes (Jianchao)

   - Convert a bunch of drivers from the old legacy IO interface to
     blk-mq. This will conclude with the removal of the legacy IO
     interface itself in 4.21, with the rest of the drivers (me, Omar)

   - Removal of the DAC960 driver. The SCSI tree will introduce two
     replacement drivers for this (Hannes)"

* tag 'for-4.20/block-20181021' of git://git.kernel.dk/linux-block: (204 commits)
  block: setup bounce bio_sets properly
  blkcg: reassociate bios when make_request() is called recursively
  blkcg: fix edge case for blk_get_rl() under memory pressure
  nvme-fabrics: move controller options matching to fabrics
  nvme-rdma: always have a valid trsvcid
  mtip32xx: fully switch to the generic DMA API
  rsxx: switch to the generic DMA API
  umem: switch to the generic DMA API
  sx8: switch to the generic DMA API
  sx8: remove dead IF_64BIT_DMA_IS_POSSIBLE code
  skd: switch to the generic DMA API
  ubd: remove use of blk_rq_map_sg
  nvme-pci: remove duplicate check
  drivers/block: Remove DAC960 driver
  nvme-pci: fix hot removal during error handling
  nvmet-fcloop: suppress a compiler warning
  nvme-core: make implicit seed truncation explicit
  nvmet-fc: fix kernel-doc headers
  nvme-fc: rework the request initialization code
  nvme-fc: introduce struct nvme_fcp_op_w_sgl
  ...

19 files changed, 431 insertions, 420 deletions

diff --git a/include/linux/amifd.h b/include/linux/amifd.h
deleted file mode 100644
index 202a77dbe46d..000000000000
--- a/include/linux/amifd.h
+++ /dev/null
@@ -1,63 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _AMIFD_H
-#define _AMIFD_H
-
-/* Definitions for the Amiga floppy driver */
-
-#include <linux/fd.h>
-
-#define FD_MAX_UNITS    4	/* Max. Number of drives */
-#define FLOPPY_MAX_SECTORS	22	/* Max. Number of sectors per track */
-
-#ifndef ASSEMBLER
-
-struct fd_data_type {
-    char *name;			/* description of data type */
-    int sects;			/* sectors per track */
-#ifdef __STDC__
-    int (*read_fkt)(int);
-    void (*write_fkt)(int);
-#else
-    int (*read_fkt)();		/* read whole track */
-    void (*write_fkt)();		/* write whole track */
-#endif
-};
-
-/*
-** Floppy type descriptions
-*/
-
-struct fd_drive_type {
-    unsigned long code;		/* code returned from drive */
-    char *name;			/* description of drive */
-    unsigned int tracks;	/* number of tracks */
-    unsigned int heads;		/* number of heads */
-    unsigned int read_size;	/* raw read size for one track */
-    unsigned int write_size;	/* raw write size for one track */
-    unsigned int sect_mult;	/* sectors and gap multiplier (HD = 2) */
-    unsigned int precomp1;	/* start track for precomp 1 */
-    unsigned int precomp2;	/* start track for precomp 2 */
-    unsigned int step_delay;	/* time (in ms) for delay after step */
-    unsigned int settle_time;	/* time to settle after dir change */
-    unsigned int side_time;	/* time needed to change sides */
-};
-
-struct amiga_floppy_struct {
-    struct fd_drive_type *type;	/* type of floppy for this unit */
-    struct fd_data_type *dtype;	/* type of floppy for this unit */
-    int track;			/* current track (-1 == unknown) */
-    unsigned char *trackbuf;    /* current track (kmaloc()'d */
-
-    int blocks;			/* total # blocks on disk */
-
-    int changed;		/* true when not known */
-    int disk;			/* disk in drive (-1 == unknown) */
-    int motor;			/* true when motor is at speed */
-    int busy;			/* true when drive is active */
-    int dirty;			/* true when trackbuf is not on disk */
-    int status;			/* current error code for unit */
-    struct gendisk *gendisk;
-};
-#endif
-
-#endif
diff --git a/include/linux/amifdreg.h b/include/linux/amifdreg.h
deleted file mode 100644
index 9b514d05ec70..000000000000
--- a/include/linux/amifdreg.h
+++ /dev/null
@@ -1,82 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_AMIFDREG_H
-#define _LINUX_AMIFDREG_H
-
-/*
-** CIAAPRA bits (read only)
-*/
-
-#define DSKRDY      (0x1<<5)        /* disk ready when low */
-#define DSKTRACK0   (0x1<<4)        /* head at track zero when low */
-#define DSKPROT     (0x1<<3)        /* disk protected when low */
-#define DSKCHANGE   (0x1<<2)        /* low when disk removed */
-
-/*
-** CIAAPRB bits (read/write)
-*/
-
-#define DSKMOTOR    (0x1<<7)        /* motor on when low */
-#define DSKSEL3     (0x1<<6)        /* select drive 3 when low */
-#define DSKSEL2     (0x1<<5)        /* select drive 2 when low */
-#define DSKSEL1     (0x1<<4)        /* select drive 1 when low */
-#define DSKSEL0     (0x1<<3)        /* select drive 0 when low */
-#define DSKSIDE     (0x1<<2)        /* side selection: 0 = upper, 1 = lower */
-#define DSKDIREC    (0x1<<1)        /* step direction: 0=in, 1=out (to trk 0) */
-#define DSKSTEP     (0x1)           /* pulse low to step head 1 track */
-
-/*
-** DSKBYTR bits (read only)
-*/
-
-#define DSKBYT      (1<<15)         /* register contains valid byte when set */
-#define DMAON       (1<<14)         /* disk DMA enabled */
-#define DISKWRITE   (1<<13)         /* disk write bit in DSKLEN enabled */
-#define WORDEQUAL   (1<<12)         /* DSKSYNC register match when true */
-/* bits 7-0 are data */
-
-/*
-** ADKCON/ADKCONR bits
-*/
-
-#ifndef SETCLR
-#define ADK_SETCLR      (1<<15)     /* control bit */
-#endif
-#define ADK_PRECOMP1    (1<<14)     /* precompensation selection */
-#define ADK_PRECOMP0    (1<<13)     /* 00=none, 01=140ns, 10=280ns, 11=500ns */
-#define ADK_MFMPREC     (1<<12)     /* 0=GCR precomp., 1=MFM precomp. */
-#define ADK_WORDSYNC    (1<<10)     /* enable DSKSYNC auto DMA */
-#define ADK_MSBSYNC     (1<<9)      /* when 1, enable sync on MSbit (for GCR) */
-#define ADK_FAST        (1<<8)      /* bit cell: 0=2us (GCR), 1=1us (MFM) */
- 
-/*
-** DSKLEN bits
-*/
-
-#define DSKLEN_DMAEN    (1<<15)
-#define DSKLEN_WRITE    (1<<14)
-
-/*
-** INTENA/INTREQ bits
-*/
-
-#define DSKINDEX    (0x1<<4)        /* DSKINDEX bit */
-
-/*
-** Misc
-*/
- 
-#define MFM_SYNC    0x4489          /* standard MFM sync value */
-
-/* Values for FD_COMMAND */
-#define FD_RECALIBRATE		0x07	/* move to track 0 */
-#define FD_SEEK			0x0F	/* seek track */
-#define FD_READ			0xE6	/* read with MT, MFM, SKip deleted */
-#define FD_WRITE		0xC5	/* write with MT, MFM */
-#define FD_SENSEI		0x08	/* Sense Interrupt Status */
-#define FD_SPECIFY		0x03	/* specify HUT etc */
-#define FD_FORMAT		0x4D	/* format one track */
-#define FD_VERSION		0x10	/* get version code */
-#define FD_CONFIGURE		0x13	/* configure FIFO operation */
-#define FD_PERPENDICULAR	0x12	/* perpendicular r/w mode */
-
-#endif /* _LINUX_AMIFDREG_H */
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 51371740d2a8..b47c7f716731 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -21,12 +21,8 @@
 #include <linux/highmem.h>
 #include <linux/mempool.h>
 #include <linux/ioprio.h>
-#include <linux/bug.h>
 
 #ifdef CONFIG_BLOCK
-
-#include <asm/io.h>
-
 /* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */
 #include <linux/blk_types.h>
 
@@ -133,32 +129,6 @@ static inline bool bio_full(struct bio *bio)
 }
 
 /*
- * will die
- */
-#define bvec_to_phys(bv)	(page_to_phys((bv)->bv_page) + (unsigned long) (bv)->bv_offset)
-
-/*
- * merge helpers etc
- */
-
-/* Default implementation of BIOVEC_PHYS_MERGEABLE */
-#define __BIOVEC_PHYS_MERGEABLE(vec1, vec2)	\
-	((bvec_to_phys((vec1)) + (vec1)->bv_len) == bvec_to_phys((vec2)))
-
-/*
- * allow arch override, for eg virtualized architectures (put in asm/io.h)
- */
-#ifndef BIOVEC_PHYS_MERGEABLE
-#define BIOVEC_PHYS_MERGEABLE(vec1, vec2)	\
-	__BIOVEC_PHYS_MERGEABLE(vec1, vec2)
-#endif
-
-#define __BIO_SEG_BOUNDARY(addr1, addr2, mask) \
-	(((addr1) | (mask)) == (((addr2) - 1) | (mask)))
-#define BIOVEC_SEG_BOUNDARY(q, b1, b2) \
-	__BIO_SEG_BOUNDARY(bvec_to_phys((b1)), bvec_to_phys((b2)) + (b2)->bv_len, queue_segment_boundary((q)))
-
-/*
  * drivers should _never_ use the all version - the bio may have been split
  * before it got to the driver and the driver won't own all of it
  */
@@ -170,27 +140,11 @@ static inline void bio_advance_iter(struct bio *bio, struct bvec_iter *iter,
 {
 	iter->bi_sector += bytes >> 9;
 
-	if (bio_no_advance_iter(bio)) {
+	if (bio_no_advance_iter(bio))
 		iter->bi_size -= bytes;
-		iter->bi_done += bytes;
-	} else {
+	else
 		bvec_iter_advance(bio->bi_io_vec, iter, bytes);
 		/* TODO: It is reasonable to complete bio with error here. */
-	}
-}
-
-static inline bool bio_rewind_iter(struct bio *bio, struct bvec_iter *iter,
-		unsigned int bytes)
-{
-	iter->bi_sector -= bytes >> 9;
-
-	if (bio_no_advance_iter(bio)) {
-		iter->bi_size += bytes;
-		iter->bi_done -= bytes;
-		return true;
-	}
-
-	return bvec_iter_rewind(bio->bi_io_vec, iter, bytes);
 }
 
 #define __bio_for_each_segment(bvl, bio, iter, start)			\
@@ -353,6 +307,8 @@ struct bio_integrity_payload {
 	unsigned short		bip_max_vcnt;	/* integrity bio_vec slots */
 	unsigned short		bip_flags;	/* control flags */
 
+	struct bvec_iter	bio_iter;	/* for rewinding parent bio */
+
 	struct work_struct	bip_work;	/* I/O completion */
 
 	struct bio_vec		*bip_vec;
@@ -547,23 +503,31 @@ do {						\
 	disk_devt((bio)->bi_disk)
 
 #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
-int bio_associate_blkcg_from_page(struct bio *bio, struct page *page);
+int bio_associate_blkg_from_page(struct bio *bio, struct page *page);
 #else
-static inline int bio_associate_blkcg_from_page(struct bio *bio,
-						struct page *page) {  return 0; }
+static inline int bio_associate_blkg_from_page(struct bio *bio,
+					       struct page *page) { return 0; }
 #endif
 
 #ifdef CONFIG_BLK_CGROUP
-int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css);
 int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg);
+int bio_associate_blkg_from_css(struct bio *bio,
+				struct cgroup_subsys_state *css);
+int bio_associate_create_blkg(struct request_queue *q, struct bio *bio);
+int bio_reassociate_blkg(struct request_queue *q, struct bio *bio);
 void bio_disassociate_task(struct bio *bio);
-void bio_clone_blkcg_association(struct bio *dst, struct bio *src);
+void bio_clone_blkg_association(struct bio *dst, struct bio *src);
 #else	/* CONFIG_BLK_CGROUP */
-static inline int bio_associate_blkcg(struct bio *bio,
-			struct cgroup_subsys_state *blkcg_css) { return 0; }
+static inline int bio_associate_blkg_from_css(struct bio *bio,
+					      struct cgroup_subsys_state *css)
+{ return 0; }
+static inline int bio_associate_create_blkg(struct request_queue *q,
+					    struct bio *bio) { return 0; }
+static inline int bio_reassociate_blkg(struct request_queue *q, struct bio *bio)
+{ return 0; }
 static inline void bio_disassociate_task(struct bio *bio) { }
-static inline void bio_clone_blkcg_association(struct bio *dst,
-			struct bio *src) { }
+static inline void bio_clone_blkg_association(struct bio *dst,
+					      struct bio *src) { }
 #endif	/* CONFIG_BLK_CGROUP */
 
 #ifdef CONFIG_HIGHMEM
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 6d766a19f2bb..1e76ceebeb5d 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -126,7 +126,7 @@ struct blkcg_gq {
 	struct request_list		rl;
 
 	/* reference count */
-	atomic_t			refcnt;
+	struct percpu_ref		refcnt;
 
 	/* is this blkg online? protected by both blkcg and q locks */
 	bool				online;
@@ -184,6 +184,8 @@ extern struct cgroup_subsys_state * const blkcg_root_css;
 
 struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg,
 				      struct request_queue *q, bool update_hint);
+struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg,
+				      struct request_queue *q);
 struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
 				    struct request_queue *q);
 int blkcg_init_queue(struct request_queue *q);
@@ -230,22 +232,59 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 		   char *input, struct blkg_conf_ctx *ctx);
 void blkg_conf_finish(struct blkg_conf_ctx *ctx);
 
+/**
+ * blkcg_css - find the current css
+ *
+ * Find the css associated with either the kthread or the current task.
+ * This may return a dying css, so it is up to the caller to use tryget logic
+ * to confirm it is alive and well.
+ */
+static inline struct cgroup_subsys_state *blkcg_css(void)
+{
+	struct cgroup_subsys_state *css;
+
+	css = kthread_blkcg();
+	if (css)
+		return css;
+	return task_css(current, io_cgrp_id);
+}
 
 static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css)
 {
 	return css ? container_of(css, struct blkcg, css) : NULL;
 }
 
-static inline struct blkcg *bio_blkcg(struct bio *bio)
+/**
+ * __bio_blkcg - internal version of bio_blkcg for bfq and cfq
+ *
+ * DO NOT USE.
+ * There is a flaw using this version of the function.  In particular, this was
+ * used in a broken paradigm where association was called on the given css.  It
+ * is possible though that the returned css from task_css() is in the process
+ * of dying due to migration of the current task.  So it is improper to assume
+ * *_get() is going to succeed.  Both BFQ and CFQ rely on this logic and will
+ * take additional work to handle more gracefully.
+ */
+static inline struct blkcg *__bio_blkcg(struct bio *bio)
 {
-	struct cgroup_subsys_state *css;
+	if (bio && bio->bi_blkg)
+		return bio->bi_blkg->blkcg;
+	return css_to_blkcg(blkcg_css());
+}
 
-	if (bio && bio->bi_css)
-		return css_to_blkcg(bio->bi_css);
-	css = kthread_blkcg();
-	if (css)
-		return css_to_blkcg(css);
-	return css_to_blkcg(task_css(current, io_cgrp_id));
+/**
+ * bio_blkcg - grab the blkcg associated with a bio
+ * @bio: target bio
+ *
+ * This returns the blkcg associated with a bio, NULL if not associated.
+ * Callers are expected to either handle NULL or know association has been
+ * done prior to calling this.
+ */
+static inline struct blkcg *bio_blkcg(struct bio *bio)
+{
+	if (bio && bio->bi_blkg)
+		return bio->bi_blkg->blkcg;
+	return NULL;
 }
 
 static inline bool blk_cgroup_congested(void)
@@ -451,26 +490,35 @@ static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen)
  */
 static inline void blkg_get(struct blkcg_gq *blkg)
 {
-	WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0);
-	atomic_inc(&blkg->refcnt);
+	percpu_ref_get(&blkg->refcnt);
 }
 
 /**
- * blkg_try_get - try and get a blkg reference
+ * blkg_tryget - try and get a blkg reference
  * @blkg: blkg to get
  *
  * This is for use when doing an RCU lookup of the blkg.  We may be in the midst
  * of freeing this blkg, so we can only use it if the refcnt is not zero.
  */
-static inline struct blkcg_gq *blkg_try_get(struct blkcg_gq *blkg)
+static inline bool blkg_tryget(struct blkcg_gq *blkg)
 {
-	if (atomic_inc_not_zero(&blkg->refcnt))
-		return blkg;
-	return NULL;
+	return percpu_ref_tryget(&blkg->refcnt);
 }
 
+/**
+ * blkg_tryget_closest - try and get a blkg ref on the closet blkg
+ * @blkg: blkg to get
+ *
+ * This walks up the blkg tree to find the closest non-dying blkg and returns
+ * the blkg that it did association with as it may not be the passed in blkg.
+ */
+static inline struct blkcg_gq *blkg_tryget_closest(struct blkcg_gq *blkg)
+{
+	while (!percpu_ref_tryget(&blkg->refcnt))
+		blkg = blkg->parent;
 
-void __blkg_release_rcu(struct rcu_head *rcu);
+	return blkg;
+}
 
 /**
  * blkg_put - put a blkg reference
@@ -478,9 +526,7 @@ void __blkg_release_rcu(struct rcu_head *rcu);
  */
 static inline void blkg_put(struct blkcg_gq *blkg)
 {
-	WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0);
-	if (atomic_dec_and_test(&blkg->refcnt))
-		call_rcu(&blkg->rcu_head, __blkg_release_rcu);
+	percpu_ref_put(&blkg->refcnt);
 }
 
 /**
@@ -533,25 +579,36 @@ static inline struct request_list *blk_get_rl(struct request_queue *q,
 
 	rcu_read_lock();
 
-	blkcg = bio_blkcg(bio);
+	if (bio && bio->bi_blkg) {
+		blkcg = bio->bi_blkg->blkcg;
+		if (blkcg == &blkcg_root)
+			goto rl_use_root;
+
+		blkg_get(bio->bi_blkg);
+		rcu_read_unlock();
+		return &bio->bi_blkg->rl;
+	}
 
-	/* bypass blkg lookup and use @q->root_rl directly for root */
+	blkcg = css_to_blkcg(blkcg_css());
 	if (blkcg == &blkcg_root)
-		goto root_rl;
+		goto rl_use_root;
 
-	/*
-	 * Try to use blkg->rl.  blkg lookup may fail under memory pressure
-	 * or if either the blkcg or queue is going away.  Fall back to
-	 * root_rl in such cases.
-	 */
 	blkg = blkg_lookup(blkcg, q);
 	if (unlikely(!blkg))
-		goto root_rl;
+		blkg = __blkg_lookup_create(blkcg, q);
+
+	if (blkg->blkcg == &blkcg_root || !blkg_tryget(blkg))
+		goto rl_use_root;
 
-	blkg_get(blkg);
 	rcu_read_unlock();
 	return &blkg->rl;
-root_rl:
+
+	/*
+	 * Each blkg has its own request_list, however, the root blkcg
+	 * uses the request_queue's root_rl.  This is to avoid most
+	 * overhead for the root blkcg.
+	 */
+rl_use_root:
 	rcu_read_unlock();
 	return &q->root_rl;
 }
@@ -797,32 +854,26 @@ static inline bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg
 				  struct bio *bio) { return false; }
 #endif
 
+
+static inline void blkcg_bio_issue_init(struct bio *bio)
+{
+	bio_issue_init(&bio->bi_issue, bio_sectors(bio));
+}
+
 static inline bool blkcg_bio_issue_check(struct request_queue *q,
 					 struct bio *bio)
 {
-	struct blkcg *blkcg;
 	struct blkcg_gq *blkg;
 	bool throtl = false;
 
 	rcu_read_lock();
-	blkcg = bio_blkcg(bio);
-
-	/* associate blkcg if bio hasn't attached one */
-	bio_associate_blkcg(bio, &blkcg->css);
 
-	blkg = blkg_lookup(blkcg, q);
-	if (unlikely(!blkg)) {
-		spin_lock_irq(q->queue_lock);
-		blkg = blkg_lookup_create(blkcg, q);
-		if (IS_ERR(blkg))
-			blkg = NULL;
-		spin_unlock_irq(q->queue_lock);
-	}
+	bio_associate_create_blkg(q, bio);
+	blkg = bio->bi_blkg;
 
 	throtl = blk_throtl_bio(q, blkg, bio);
 
 	if (!throtl) {
-		blkg = blkg ?: q->root_blkg;
 		/*
 		 * If the bio is flagged with BIO_QUEUE_ENTERED it means this
 		 * is a split bio and we would have already accounted for the
@@ -834,6 +885,8 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q,
 		blkg_rwstat_add(&blkg->stat_ios, bio->bi_opf, 1);
 	}
 
+	blkcg_bio_issue_init(bio);
+
 	rcu_read_unlock();
 	return !throtl;
 }
@@ -930,6 +983,7 @@ static inline int blkcg_activate_policy(struct request_queue *q,
 static inline void blkcg_deactivate_policy(struct request_queue *q,
 					   const struct blkcg_policy *pol) { }
 
+static inline struct blkcg *__bio_blkcg(struct bio *bio) { return NULL; }
 static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; }
 
 static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg,
@@ -945,6 +999,7 @@ static inline void blk_put_rl(struct request_list *rl) { }
 static inline void blk_rq_set_rl(struct request *rq, struct request_list *rl) { }
 static inline struct request_list *blk_rq_rl(struct request *rq) { return &rq->q->root_rl; }
 
+static inline void blkcg_bio_issue_init(struct bio *bio) { }
 static inline bool blkcg_bio_issue_check(struct request_queue *q,
 					 struct bio *bio) { return true; }
 
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 1da59c16f637..2286dc12c6bc 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -203,6 +203,10 @@ enum {
 struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *);
 struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 						  struct request_queue *q);
+struct request_queue *blk_mq_init_sq_queue(struct blk_mq_tag_set *set,
+						const struct blk_mq_ops *ops,
+						unsigned int queue_depth,
+						unsigned int set_flags);
 int blk_mq_register_dev(struct device *, struct request_queue *);
 void blk_mq_unregister_dev(struct device *, struct request_queue *);
 
diff --git a/include/linux/blk-pm.h b/include/linux/blk-pm.h
new file mode 100644
index 000000000000..b80c65aba249
--- /dev/null
+++ b/include/linux/blk-pm.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _BLK_PM_H_
+#define _BLK_PM_H_
+
+struct device;
+struct request_queue;
+
+/*
+ * block layer runtime pm functions
+ */
+#ifdef CONFIG_PM
+extern void blk_pm_runtime_init(struct request_queue *q, struct device *dev);
+extern int blk_pre_runtime_suspend(struct request_queue *q);
+extern void blk_post_runtime_suspend(struct request_queue *q, int err);
+extern void blk_pre_runtime_resume(struct request_queue *q);
+extern void blk_post_runtime_resume(struct request_queue *q, int err);
+extern void blk_set_runtime_active(struct request_queue *q);
+#else
+static inline void blk_pm_runtime_init(struct request_queue *q,
+				       struct device *dev) {}
+#endif
+
+#endif /* _BLK_PM_H_ */
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index f6dfb30737d8..9578c7ab1eb6 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -178,7 +178,6 @@ struct bio {
 	 * release.  Read comment on top of bio_associate_current().
 	 */
 	struct io_context	*bi_ioc;
-	struct cgroup_subsys_state *bi_css;
 	struct blkcg_gq		*bi_blkg;
 	struct bio_issue	bi_issue;
 #endif
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 6980014357d4..61207560e826 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -108,7 +108,7 @@ typedef __u32 __bitwise req_flags_t;
 #define RQF_QUIET		((__force req_flags_t)(1 << 11))
 /* elevator private data attached */
 #define RQF_ELVPRIV		((__force req_flags_t)(1 << 12))
-/* account I/O stat */
+/* account into disk and partition IO statistics */
 #define RQF_IO_STAT		((__force req_flags_t)(1 << 13))
 /* request came from our alloc pool */
 #define RQF_ALLOCED		((__force req_flags_t)(1 << 14))
@@ -116,7 +116,7 @@ typedef __u32 __bitwise req_flags_t;
 #define RQF_PM			((__force req_flags_t)(1 << 15))
 /* on IO scheduler merge hash */
 #define RQF_HASHED		((__force req_flags_t)(1 << 16))
-/* IO stats tracking on */
+/* track IO completion time */
 #define RQF_STATS		((__force req_flags_t)(1 << 17))
 /* Look at ->special_vec for the actual data payload instead of the
    bio chain. */
@@ -504,6 +504,12 @@ struct request_queue {
 	 * various queue flags, see QUEUE_* below
 	 */
 	unsigned long		queue_flags;
+	/*
+	 * Number of contexts that have called blk_set_pm_only(). If this
+	 * counter is above zero then only RQF_PM and RQF_PREEMPT requests are
+	 * processed.
+	 */
+	atomic_t		pm_only;
 
 	/*
 	 * ida allocated id for this queue.  Used to index queues from
@@ -679,7 +685,7 @@ struct request_queue {
 #define QUEUE_FLAG_FAIL_IO	7	/* fake timeout */
 #define QUEUE_FLAG_NONROT	9	/* non-rotational device (SSD) */
 #define QUEUE_FLAG_VIRT        QUEUE_FLAG_NONROT /* paravirt device */
-#define QUEUE_FLAG_IO_STAT     10	/* do IO stats */
+#define QUEUE_FLAG_IO_STAT     10	/* do disk/partitions IO accounting */
 #define QUEUE_FLAG_DISCARD     11	/* supports DISCARD */
 #define QUEUE_FLAG_NOXMERGES   12	/* No extended merges */
 #define QUEUE_FLAG_ADD_RANDOM  13	/* Contributes to random pool */
@@ -693,12 +699,11 @@ struct request_queue {
 #define QUEUE_FLAG_FUA	       21	/* device supports FUA writes */
 #define QUEUE_FLAG_FLUSH_NQ    22	/* flush not queueuable */
 #define QUEUE_FLAG_DAX         23	/* device supports DAX */
-#define QUEUE_FLAG_STATS       24	/* track rq completion times */
+#define QUEUE_FLAG_STATS       24	/* track IO start and completion times */
 #define QUEUE_FLAG_POLL_STATS  25	/* collecting stats for hybrid polling */
 #define QUEUE_FLAG_REGISTERED  26	/* queue has been registered to a disk */
 #define QUEUE_FLAG_SCSI_PASSTHROUGH 27	/* queue supports SCSI commands */
 #define QUEUE_FLAG_QUIESCED    28	/* queue has been quiesced */
-#define QUEUE_FLAG_PREEMPT_ONLY	29	/* only process REQ_PREEMPT requests */
 
 #define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_SAME_COMP)	|	\
@@ -736,12 +741,11 @@ bool blk_queue_flag_test_and_clear(unsigned int flag, struct request_queue *q);
 	((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \
 			     REQ_FAILFAST_DRIVER))
 #define blk_queue_quiesced(q)	test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags)
-#define blk_queue_preempt_only(q)				\
-	test_bit(QUEUE_FLAG_PREEMPT_ONLY, &(q)->queue_flags)
+#define blk_queue_pm_only(q)	atomic_read(&(q)->pm_only)
 #define blk_queue_fua(q)	test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags)
 
-extern int blk_set_preempt_only(struct request_queue *q);
-extern void blk_clear_preempt_only(struct request_queue *q);
+extern void blk_set_pm_only(struct request_queue *q);
+extern void blk_clear_pm_only(struct request_queue *q);
 
 static inline int queue_in_flight(struct request_queue *q)
 {
@@ -1281,29 +1285,6 @@ extern void blk_put_queue(struct request_queue *);
 extern void blk_set_queue_dying(struct request_queue *);
 
 /*
- * block layer runtime pm functions
- */
-#ifdef CONFIG_PM
-extern void blk_pm_runtime_init(struct request_queue *q, struct device *dev);
-extern int blk_pre_runtime_suspend(struct request_queue *q);
-extern void blk_post_runtime_suspend(struct request_queue *q, int err);
-extern void blk_pre_runtime_resume(struct request_queue *q);
-extern void blk_post_runtime_resume(struct request_queue *q, int err);
-extern void blk_set_runtime_active(struct request_queue *q);
-#else
-static inline void blk_pm_runtime_init(struct request_queue *q,
-	struct device *dev) {}
-static inline int blk_pre_runtime_suspend(struct request_queue *q)
-{
-	return -ENOSYS;
-}
-static inline void blk_post_runtime_suspend(struct request_queue *q, int err) {}
-static inline void blk_pre_runtime_resume(struct request_queue *q) {}
-static inline void blk_post_runtime_resume(struct request_queue *q, int err) {}
-static inline void blk_set_runtime_active(struct request_queue *q) {}
-#endif
-
-/*
  * blk_plug permits building a queue of related requests by holding the I/O
  * fragments for a short period. This allows merging of sequential requests
  * into single larger request. As the requests are moved from a per-task list to
@@ -1676,94 +1657,6 @@ static inline void put_dev_sector(Sector p)
 	put_page(p.v);
 }
 
-static inline bool __bvec_gap_to_prev(struct request_queue *q,
-				struct bio_vec *bprv, unsigned int offset)
-{
-	return offset ||
-		((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q));
-}
-
-/*
- * Check if adding a bio_vec after bprv with offset would create a gap in
- * the SG list. Most drivers don't care about this, but some do.
- */
-static inline bool bvec_gap_to_prev(struct request_queue *q,
-				struct bio_vec *bprv, unsigned int offset)
-{
-	if (!queue_virt_boundary(q))
-		return false;
-	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 request *prev_rq,
-				struct bio *prev,
-				struct bio *next)
-{
-	if (bio_has_data(prev) && queue_virt_boundary(q)) {
-		struct bio_vec pb, nb;
-
-		/*
-		 * don't merge if the 1st bio starts with non-zero
-		 * offset, otherwise it is quite difficult to respect
-		 * sg gap limit. We work hard to merge a huge number of small
-		 * single bios in case of mkfs.
-		 */
-		if (prev_rq)
-			bio_get_first_bvec(prev_rq->bio, &pb);
-		else
-			bio_get_first_bvec(prev, &pb);
-		if (pb.bv_offset)
-			return true;
-
-		/*
-		 * We don't need to worry about the situation that the
-		 * merged segment ends in unaligned virt boundary:
-		 *
-		 * - if 'pb' ends aligned, the merged segment ends aligned
-		 * - if 'pb' ends unaligned, the next bio must include
-		 *   one single bvec of 'nb', otherwise the 'nb' can't
-		 *   merge with 'pb'
-		 */
-		bio_get_last_bvec(prev, &pb);
-		bio_get_first_bvec(next, &nb);
-
-		if (!bios_segs_mergeable(q, prev, &pb, &nb))
-			return __bvec_gap_to_prev(q, &pb, nb.bv_offset);
-	}
-
-	return false;
-}
-
-static inline bool req_gap_back_merge(struct request *req, struct bio *bio)
-{
-	return bio_will_gap(req->q, req, req->biotail, bio);
-}
-
-static inline bool req_gap_front_merge(struct request *req, struct bio *bio)
-{
-	return bio_will_gap(req->q, NULL, bio, req->bio);
-}
-
 int kblockd_schedule_work(struct work_struct *work);
 int kblockd_schedule_work_on(int cpu, struct work_struct *work);
 int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay);
@@ -1843,26 +1736,6 @@ queue_max_integrity_segments(struct request_queue *q)
 	return q->limits.max_integrity_segments;
 }
 
-static inline bool integrity_req_gap_back_merge(struct request *req,
-						struct bio *next)
-{
-	struct bio_integrity_payload *bip = bio_integrity(req->bio);
-	struct bio_integrity_payload *bip_next = bio_integrity(next);
-
-	return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1],
-				bip_next->bip_vec[0].bv_offset);
-}
-
-static inline bool integrity_req_gap_front_merge(struct request *req,
-						 struct bio *bio)
-{
-	struct bio_integrity_payload *bip = bio_integrity(bio);
-	struct bio_integrity_payload *bip_next = bio_integrity(req->bio);
-
-	return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1],
-				bip_next->bip_vec[0].bv_offset);
-}
-
 /**
  * bio_integrity_intervals - Return number of integrity intervals for a bio
  * @bi:		blk_integrity profile for device
@@ -1947,17 +1820,6 @@ static inline bool blk_integrity_merge_bio(struct request_queue *rq,
 	return true;
 }
 
-static inline bool integrity_req_gap_back_merge(struct request *req,
-						struct bio *next)
-{
-	return false;
-}
-static inline bool integrity_req_gap_front_merge(struct request *req,
-						 struct bio *bio)
-{
-	return false;
-}
-
 static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
 						   unsigned int sectors)
 {
diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index fe7a22dd133b..02c73c6aa805 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -40,8 +40,6 @@ struct bvec_iter {
 
 	unsigned int		bi_idx;		/* current index into bvl_vec */
 
-	unsigned int            bi_done;	/* number of bytes completed */
-
 	unsigned int            bi_bvec_done;	/* number of bytes completed in
 						   current bvec */
 };
@@ -85,7 +83,6 @@ static inline bool bvec_iter_advance(const struct bio_vec *bv,
 		bytes -= len;
 		iter->bi_size -= len;
 		iter->bi_bvec_done += len;
-		iter->bi_done += len;
 
 		if (iter->bi_bvec_done == __bvec_iter_bvec(bv, *iter)->bv_len) {
 			iter->bi_bvec_done = 0;
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 32c553556bbd..b8bcbdeb2eac 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -93,6 +93,8 @@ extern struct css_set init_css_set;
 
 bool css_has_online_children(struct cgroup_subsys_state *css);
 struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss);
+struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgroup,
+					 struct cgroup_subsys *ss);
 struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup,
 					     struct cgroup_subsys *ss);
 struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry,
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index a02deea30185..015bb59c0331 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -111,7 +111,7 @@ struct elevator_mq_ops {
 	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 request *);
+	void (*completed_request)(struct request *, u64);
 	void (*started_request)(struct request *);
 	void (*requeue_request)(struct request *);
 	struct request *(*former_request)(struct request_queue *, struct request *);
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 25c08c6c7f99..70fc838e6773 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -402,10 +402,11 @@ static inline void free_part_info(struct hd_struct *part)
 extern void part_round_stats(struct request_queue *q, int cpu, struct hd_struct *part);
 
 /* block/genhd.c */
-extern void device_add_disk(struct device *parent, struct gendisk *disk);
+extern void device_add_disk(struct device *parent, struct gendisk *disk,
+			    const struct attribute_group **groups);
 static inline void add_disk(struct gendisk *disk)
 {
-	device_add_disk(NULL, disk);
+	device_add_disk(NULL, disk, NULL);
 }
 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)
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index e9e0d1c7eaf5..2fdeac1a420d 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -86,8 +86,8 @@ struct nvm_chk_meta;
 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_get_chk_meta_fn)(struct nvm_dev *, sector_t, int,
+							struct nvm_chk_meta *);
 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 *);
@@ -305,6 +305,8 @@ struct nvm_rq {
 	u64 ppa_status; /* ppa media status */
 	int error;
 
+	int is_seq; /* Sequential hint flag. 1.2 only */
+
 	void *private;
 };
 
@@ -318,6 +320,11 @@ static inline void *nvm_rq_to_pdu(struct nvm_rq *rqdata)
 	return rqdata + 1;
 }
 
+static inline struct ppa_addr *nvm_rq_to_ppa_list(struct nvm_rq *rqd)
+{
+	return (rqd->nr_ppas > 1) ? rqd->ppa_list : &rqd->ppa_addr;
+}
+
 enum {
 	NVM_BLK_ST_FREE =	0x1,	/* Free block */
 	NVM_BLK_ST_TGT =	0x2,	/* Block in use by target */
@@ -485,6 +492,144 @@ static inline struct ppa_addr dev_to_generic_addr(struct nvm_dev *dev,
 	return l;
 }
 
+static inline u64 dev_to_chunk_addr(struct nvm_dev *dev, void *addrf,
+				    struct ppa_addr p)
+{
+	struct nvm_geo *geo = &dev->geo;
+	u64 caddr;
+
+	if (geo->version == NVM_OCSSD_SPEC_12) {
+		struct nvm_addrf_12 *ppaf = (struct nvm_addrf_12 *)addrf;
+
+		caddr = (u64)p.g.pg << ppaf->pg_offset;
+		caddr |= (u64)p.g.pl << ppaf->pln_offset;
+		caddr |= (u64)p.g.sec << ppaf->sec_offset;
+	} else {
+		caddr = p.m.sec;
+	}
+
+	return caddr;
+}
+
+static inline struct ppa_addr nvm_ppa32_to_ppa64(struct nvm_dev *dev,
+						 void *addrf, u32 ppa32)
+{
+	struct ppa_addr ppa64;
+
+	ppa64.ppa = 0;
+
+	if (ppa32 == -1) {
+		ppa64.ppa = ADDR_EMPTY;
+	} else if (ppa32 & (1U << 31)) {
+		ppa64.c.line = ppa32 & ((~0U) >> 1);
+		ppa64.c.is_cached = 1;
+	} else {
+		struct nvm_geo *geo = &dev->geo;
+
+		if (geo->version == NVM_OCSSD_SPEC_12) {
+			struct nvm_addrf_12 *ppaf = addrf;
+
+			ppa64.g.ch = (ppa32 & ppaf->ch_mask) >>
+							ppaf->ch_offset;
+			ppa64.g.lun = (ppa32 & ppaf->lun_mask) >>
+							ppaf->lun_offset;
+			ppa64.g.blk = (ppa32 & ppaf->blk_mask) >>
+							ppaf->blk_offset;
+			ppa64.g.pg = (ppa32 & ppaf->pg_mask) >>
+							ppaf->pg_offset;
+			ppa64.g.pl = (ppa32 & ppaf->pln_mask) >>
+							ppaf->pln_offset;
+			ppa64.g.sec = (ppa32 & ppaf->sec_mask) >>
+							ppaf->sec_offset;
+		} else {
+			struct nvm_addrf *lbaf = addrf;
+
+			ppa64.m.grp = (ppa32 & lbaf->ch_mask) >>
+							lbaf->ch_offset;
+			ppa64.m.pu = (ppa32 & lbaf->lun_mask) >>
+							lbaf->lun_offset;
+			ppa64.m.chk = (ppa32 & lbaf->chk_mask) >>
+							lbaf->chk_offset;
+			ppa64.m.sec = (ppa32 & lbaf->sec_mask) >>
+							lbaf->sec_offset;
+		}
+	}
+
+	return ppa64;
+}
+
+static inline u32 nvm_ppa64_to_ppa32(struct nvm_dev *dev,
+				     void *addrf, struct ppa_addr ppa64)
+{
+	u32 ppa32 = 0;
+
+	if (ppa64.ppa == ADDR_EMPTY) {
+		ppa32 = ~0U;
+	} else if (ppa64.c.is_cached) {
+		ppa32 |= ppa64.c.line;
+		ppa32 |= 1U << 31;
+	} else {
+		struct nvm_geo *geo = &dev->geo;
+
+		if (geo->version == NVM_OCSSD_SPEC_12) {
+			struct nvm_addrf_12 *ppaf = addrf;
+
+			ppa32 |= ppa64.g.ch << ppaf->ch_offset;
+			ppa32 |= ppa64.g.lun << ppaf->lun_offset;
+			ppa32 |= ppa64.g.blk << ppaf->blk_offset;
+			ppa32 |= ppa64.g.pg << ppaf->pg_offset;
+			ppa32 |= ppa64.g.pl << ppaf->pln_offset;
+			ppa32 |= ppa64.g.sec << ppaf->sec_offset;
+		} else {
+			struct nvm_addrf *lbaf = addrf;
+
+			ppa32 |= ppa64.m.grp << lbaf->ch_offset;
+			ppa32 |= ppa64.m.pu << lbaf->lun_offset;
+			ppa32 |= ppa64.m.chk << lbaf->chk_offset;
+			ppa32 |= ppa64.m.sec << lbaf->sec_offset;
+		}
+	}
+
+	return ppa32;
+}
+
+static inline int nvm_next_ppa_in_chk(struct nvm_tgt_dev *dev,
+				      struct ppa_addr *ppa)
+{
+	struct nvm_geo *geo = &dev->geo;
+	int last = 0;
+
+	if (geo->version == NVM_OCSSD_SPEC_12) {
+		int sec = ppa->g.sec;
+
+		sec++;
+		if (sec == geo->ws_min) {
+			int pg = ppa->g.pg;
+
+			sec = 0;
+			pg++;
+			if (pg == geo->num_pg) {
+				int pl = ppa->g.pl;
+
+				pg = 0;
+				pl++;
+				if (pl == geo->num_pln)
+					last = 1;
+
+				ppa->g.pl = pl;
+			}
+			ppa->g.pg = pg;
+		}
+		ppa->g.sec = sec;
+	} else {
+		ppa->m.sec++;
+		if (ppa->m.sec == geo->clba)
+			last = 1;
+	}
+
+	return last;
+}
+
 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 *,
@@ -493,9 +638,15 @@ typedef void (nvm_tgt_exit_fn)(void *, bool);
 typedef int (nvm_tgt_sysfs_init_fn)(struct gendisk *);
 typedef void (nvm_tgt_sysfs_exit_fn)(struct gendisk *);
 
+enum {
+	NVM_TGT_F_DEV_L2P = 0,
+	NVM_TGT_F_HOST_L2P = 1 << 0,
+};
+
 struct nvm_tgt_type {
 	const char *name;
 	unsigned int version[3];
+	int flags;
 
 	/* target entry points */
 	nvm_tgt_make_rq_fn *make_rq;
@@ -524,18 +675,13 @@ 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 *,
+extern int nvm_get_chunk_meta(struct nvm_tgt_dev *, struct ppa_addr,
+			      int, struct nvm_chk_meta *);
+extern int nvm_set_chunk_meta(struct nvm_tgt_dev *, struct ppa_addr *,
 			      int, int);
 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 *);
-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 *);
 
 #else /* CONFIG_NVM */
 struct nvm_dev_ops;
diff --git a/include/linux/mtd/blktrans.h b/include/linux/mtd/blktrans.h
index e93837f647de..1d3ade69d39a 100644
--- a/include/linux/mtd/blktrans.h
+++ b/include/linux/mtd/blktrans.h
@@ -23,7 +23,6 @@
 #include <linux/mutex.h>
 #include <linux/kref.h>
 #include <linux/sysfs.h>
-#include <linux/workqueue.h>
 
 struct hd_geometry;
 struct mtd_info;
@@ -44,9 +43,9 @@ struct mtd_blktrans_dev {
 	struct kref ref;
 	struct gendisk *disk;
 	struct attribute_group *disk_attributes;
-	struct workqueue_struct *wq;
-	struct work_struct work;
 	struct request_queue *rq;
+	struct list_head rq_list;
+	struct blk_mq_tag_set *tag_set;
 	spinlock_t queue_lock;
 	void *priv;
 	fmode_t file_mode;
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 68e91ef5494c..818dbe9331be 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -1241,6 +1241,7 @@ enum {
 	NVME_SC_ANA_PERSISTENT_LOSS	= 0x301,
 	NVME_SC_ANA_INACCESSIBLE	= 0x302,
 	NVME_SC_ANA_TRANSITION		= 0x303,
+	NVME_SC_HOST_PATH_ERROR		= 0x370,
 
 	NVME_SC_DNR			= 0x4000,
 };
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 009cdf3d65b6..b297cd1cd4f1 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -108,6 +108,7 @@ void percpu_ref_switch_to_atomic_sync(struct percpu_ref *ref);
 void percpu_ref_switch_to_percpu(struct percpu_ref *ref);
 void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
 				 percpu_ref_func_t *confirm_kill);
+void percpu_ref_resurrect(struct percpu_ref *ref);
 void percpu_ref_reinit(struct percpu_ref *ref);
 
 /**
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index fdfd04e348f6..738a0c24874f 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -246,7 +246,8 @@ static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc,
  *
  * @bio is a part of the writeback in progress controlled by @wbc.  Perform
  * writeback specific initialization.  This is used to apply the cgroup
- * writeback context.
+ * writeback context.  Must be called after the bio has been associated with
+ * a device.
  */
 static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio)
 {
@@ -257,7 +258,7 @@ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio)
 	 * regular writeback instead of writing things out itself.
 	 */
 	if (wbc->wb)
-		bio_associate_blkcg(bio, wbc->wb->blkcg_css);
+		bio_associate_blkg_from_css(bio, wbc->wb->blkcg_css);
 }
 
 #else	/* CONFIG_CGROUP_WRITEBACK */
diff --git a/include/trace/events/kyber.h b/include/trace/events/kyber.h
new file mode 100644
index 000000000000..a9834c37ac40
--- /dev/null
+++ b/include/trace/events/kyber.h
@@ -0,0 +1,96 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kyber
+
+#if !defined(_TRACE_KYBER_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_KYBER_H
+
+#include <linux/blkdev.h>
+#include <linux/tracepoint.h>
+
+#define DOMAIN_LEN		16
+#define LATENCY_TYPE_LEN	8
+
+TRACE_EVENT(kyber_latency,
+
+	TP_PROTO(struct request_queue *q, const char *domain, const char *type,
+		 unsigned int percentile, unsigned int numerator,
+		 unsigned int denominator, unsigned int samples),
+
+	TP_ARGS(q, domain, type, percentile, numerator, denominator, samples),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev				)
+		__array(	char,	domain,	DOMAIN_LEN		)
+		__array(	char,	type,	LATENCY_TYPE_LEN	)
+		__field(	u8,	percentile			)
+		__field(	u8,	numerator			)
+		__field(	u8,	denominator			)
+		__field(	unsigned int,	samples			)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= disk_devt(dev_to_disk(kobj_to_dev(q->kobj.parent)));
+		strlcpy(__entry->domain, domain, DOMAIN_LEN);
+		strlcpy(__entry->type, type, DOMAIN_LEN);
+		__entry->percentile	= percentile;
+		__entry->numerator	= numerator;
+		__entry->denominator	= denominator;
+		__entry->samples	= samples;
+	),
+
+	TP_printk("%d,%d %s %s p%u %u/%u samples=%u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->domain,
+		  __entry->type, __entry->percentile, __entry->numerator,
+		  __entry->denominator, __entry->samples)
+);
+
+TRACE_EVENT(kyber_adjust,
+
+	TP_PROTO(struct request_queue *q, const char *domain,
+		 unsigned int depth),
+
+	TP_ARGS(q, domain, depth),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__array(	char,	domain,	DOMAIN_LEN	)
+		__field(	unsigned int,	depth		)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= disk_devt(dev_to_disk(kobj_to_dev(q->kobj.parent)));
+		strlcpy(__entry->domain, domain, DOMAIN_LEN);
+		__entry->depth		= depth;
+	),
+
+	TP_printk("%d,%d %s %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->domain,
+		  __entry->depth)
+);
+
+TRACE_EVENT(kyber_throttled,
+
+	TP_PROTO(struct request_queue *q, const char *domain),
+
+	TP_ARGS(q, domain),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__array(	char,	domain,	DOMAIN_LEN	)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= disk_devt(dev_to_disk(kobj_to_dev(q->kobj.parent)));
+		strlcpy(__entry->domain, domain, DOMAIN_LEN);
+	),
+
+	TP_printk("%d,%d %s", MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->domain)
+);
+
+#define _TRACE_KYBER_H
+#endif /* _TRACE_KYBER_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/xen/xen.h b/include/xen/xen.h
index 1e1d9bd0bd37..d7a2678da77f 100644
--- a/include/xen/xen.h
+++ b/include/xen/xen.h
@@ -39,4 +39,8 @@ extern uint32_t xen_start_flags;
 #define xen_initial_domain()	(0)
 #endif	/* CONFIG_XEN_DOM0 */
 
+struct bio_vec;
+bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
+		const struct bio_vec *vec2);
+
 #endif	/* _XEN_XEN_H */