Merge tag 'for-4.19/block-20180812' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "First pull request for this merge window, there will also be a
  followup request with some stragglers.

  This pull request contains:

   - Fix for a thundering heard issue in the wbt block code (Anchal
     Agarwal)

   - A few NVMe pull requests:
      * Improved tracepoints (Keith)
      * Larger inline data support for RDMA (Steve Wise)
      * RDMA setup/teardown fixes (Sagi)
      * Effects log suppor for NVMe target (Chaitanya Kulkarni)
      * Buffered IO suppor for NVMe target (Chaitanya Kulkarni)
      * TP4004 (ANA) support (Christoph)
      * Various NVMe fixes

   - Block io-latency controller support. Much needed support for
     properly containing block devices. (Josef)

   - Series improving how we handle sense information on the stack
     (Kees)

   - Lightnvm fixes and updates/improvements (Mathias/Javier et al)

   - Zoned device support for null_blk (Matias)

   - AIX partition fixes (Mauricio Faria de Oliveira)

   - DIF checksum code made generic (Max Gurtovoy)

   - Add support for discard in iostats (Michael Callahan / Tejun)

   - Set of updates for BFQ (Paolo)

   - Removal of async write support for bsg (Christoph)

   - Bio page dirtying and clone fixups (Christoph)

   - Set of bcache fix/changes (via Coly)

   - Series improving blk-mq queue setup/teardown speed (Ming)

   - Series improving merging performance on blk-mq (Ming)

   - Lots of other fixes and cleanups from a slew of folks"

* tag 'for-4.19/block-20180812' of git://git.kernel.dk/linux-block: (190 commits)
  blkcg: Make blkg_root_lookup() work for queues in bypass mode
  bcache: fix error setting writeback_rate through sysfs interface
  null_blk: add lock drop/acquire annotation
  Blk-throttle: reduce tail io latency when iops limit is enforced
  block: paride: pd: mark expected switch fall-throughs
  block: Ensure that a request queue is dissociated from the cgroup controller
  block: Introduce blk_exit_queue()
  blkcg: Introduce blkg_root_lookup()
  block: Remove two superfluous #include directives
  blk-mq: count the hctx as active before allocating tag
  block: bvec_nr_vecs() returns value for wrong slab
  bcache: trivial - remove tailing backslash in macro BTREE_FLAG
  bcache: make the pr_err statement used for ENOENT only in sysfs_attatch section
  bcache: set max writeback rate when I/O request is idle
  bcache: add code comments for bset.c
  bcache: fix mistaken comments in request.c
  bcache: fix mistaken code comments in bcache.h
  bcache: add a comment in super.c
  bcache: avoid unncessary cache prefetch bch_btree_node_get()
  bcache: display rate debug parameters to 0 when writeback is not running
  ...

14 files changed, 361 insertions, 51 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index f08f5fe7bd08..51371740d2a8 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -429,7 +429,6 @@ extern void bio_put(struct bio *);
 
 extern void __bio_clone_fast(struct bio *, struct bio *);
 extern struct bio *bio_clone_fast(struct bio *, gfp_t, struct bio_set *);
-extern struct bio *bio_clone_bioset(struct bio *, gfp_t, struct bio_set *bs);
 
 extern struct bio_set fs_bio_set;
 
@@ -443,12 +442,6 @@ static inline struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned int nr_iovecs)
 	return bio_alloc_bioset(gfp_mask, nr_iovecs, NULL);
 }
 
-static inline struct bio *bio_clone_kmalloc(struct bio *bio, gfp_t gfp_mask)
-{
-	return bio_clone_bioset(bio, gfp_mask, NULL);
-
-}
-
 extern blk_qc_t submit_bio(struct bio *);
 
 extern void bio_endio(struct bio *);
@@ -496,9 +489,9 @@ extern struct bio *bio_copy_kern(struct request_queue *, void *, unsigned int,
 extern void bio_set_pages_dirty(struct bio *bio);
 extern void bio_check_pages_dirty(struct bio *bio);
 
-void generic_start_io_acct(struct request_queue *q, int rw,
+void generic_start_io_acct(struct request_queue *q, int op,
 				unsigned long sectors, struct hd_struct *part);
-void generic_end_io_acct(struct request_queue *q, int rw,
+void generic_end_io_acct(struct request_queue *q, int op,
 				struct hd_struct *part,
 				unsigned long start_time);
 
@@ -553,8 +546,16 @@ do {						\
 #define bio_dev(bio) \
 	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);
+#else
+static inline int bio_associate_blkcg_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);
 void bio_disassociate_task(struct bio *bio);
 void bio_clone_blkcg_association(struct bio *dst, struct bio *src);
 #else	/* CONFIG_BLK_CGROUP */
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 6c666fd7de3c..34aec30e06c7 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -35,6 +35,7 @@ enum blkg_rwstat_type {
 	BLKG_RWSTAT_WRITE,
 	BLKG_RWSTAT_SYNC,
 	BLKG_RWSTAT_ASYNC,
+	BLKG_RWSTAT_DISCARD,
 
 	BLKG_RWSTAT_NR,
 	BLKG_RWSTAT_TOTAL = BLKG_RWSTAT_NR,
@@ -136,6 +137,12 @@ struct blkcg_gq {
 	struct blkg_policy_data		*pd[BLKCG_MAX_POLS];
 
 	struct rcu_head			rcu_head;
+
+	atomic_t			use_delay;
+	atomic64_t			delay_nsec;
+	atomic64_t			delay_start;
+	u64				last_delay;
+	int				last_use;
 };
 
 typedef struct blkcg_policy_data *(blkcg_pol_alloc_cpd_fn)(gfp_t gfp);
@@ -148,6 +155,8 @@ typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd);
 typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd);
 typedef void (blkcg_pol_free_pd_fn)(struct blkg_policy_data *pd);
 typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkg_policy_data *pd);
+typedef size_t (blkcg_pol_stat_pd_fn)(struct blkg_policy_data *pd, char *buf,
+				      size_t size);
 
 struct blkcg_policy {
 	int				plid;
@@ -167,6 +176,7 @@ struct blkcg_policy {
 	blkcg_pol_offline_pd_fn		*pd_offline_fn;
 	blkcg_pol_free_pd_fn		*pd_free_fn;
 	blkcg_pol_reset_pd_stats_fn	*pd_reset_stats_fn;
+	blkcg_pol_stat_pd_fn		*pd_stat_fn;
 };
 
 extern struct blkcg blkcg_root;
@@ -238,6 +248,42 @@ static inline struct blkcg *bio_blkcg(struct bio *bio)
 	return css_to_blkcg(task_css(current, io_cgrp_id));
 }
 
+static inline bool blk_cgroup_congested(void)
+{
+	struct cgroup_subsys_state *css;
+	bool ret = false;
+
+	rcu_read_lock();
+	css = kthread_blkcg();
+	if (!css)
+		css = task_css(current, io_cgrp_id);
+	while (css) {
+		if (atomic_read(&css->cgroup->congestion_count)) {
+			ret = true;
+			break;
+		}
+		css = css->parent;
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
+/**
+ * bio_issue_as_root_blkg - see if this bio needs to be issued as root blkg
+ * @return: true if this bio needs to be submitted with the root blkg context.
+ *
+ * In order to avoid priority inversions we sometimes need to issue a bio as if
+ * it were attached to the root blkg, and then backcharge to the actual owning
+ * blkg.  The idea is we do bio_blkcg() to look up the actual context for the
+ * bio and attach the appropriate blkg to the bio.  Then we call this helper and
+ * if it is true run with the root blkg for that queue and then do any
+ * backcharging to the originating cgroup once the io is complete.
+ */
+static inline bool bio_issue_as_root_blkg(struct bio *bio)
+{
+	return (bio->bi_opf & (REQ_META | REQ_SWAP)) != 0;
+}
+
 /**
  * blkcg_parent - get the parent of a blkcg
  * @blkcg: blkcg of interest
@@ -296,6 +342,17 @@ static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg,
 }
 
 /**
+ * blk_queue_root_blkg - return blkg for the (blkcg_root, @q) pair
+ * @q: request_queue of interest
+ *
+ * Lookup blkg for @q at the root level. See also blkg_lookup().
+ */
+static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q)
+{
+	return q->root_blkg;
+}
+
+/**
  * blkg_to_pdata - get policy private data
  * @blkg: blkg of interest
  * @pol: policy of interest
@@ -355,6 +412,21 @@ static inline void blkg_get(struct blkcg_gq *blkg)
 	atomic_inc(&blkg->refcnt);
 }
 
+/**
+ * blkg_try_get - 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)
+{
+	if (atomic_inc_not_zero(&blkg->refcnt))
+		return blkg;
+	return NULL;
+}
+
+
 void __blkg_release_rcu(struct rcu_head *rcu);
 
 /**
@@ -589,7 +661,9 @@ static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat,
 {
 	struct percpu_counter *cnt;
 
-	if (op_is_write(op))
+	if (op_is_discard(op))
+		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_DISCARD];
+	else if (op_is_write(op))
 		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_WRITE];
 	else
 		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ];
@@ -706,8 +780,14 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q,
 
 	if (!throtl) {
 		blkg = blkg ?: q->root_blkg;
-		blkg_rwstat_add(&blkg->stat_bytes, bio->bi_opf,
-				bio->bi_iter.bi_size);
+		/*
+		 * If the bio is flagged with BIO_QUEUE_ENTERED it means this
+		 * is a split bio and we would have already accounted for the
+		 * size of the bio.
+		 */
+		if (!bio_flagged(bio, BIO_QUEUE_ENTERED))
+			blkg_rwstat_add(&blkg->stat_bytes, bio->bi_opf,
+					bio->bi_iter.bi_size);
 		blkg_rwstat_add(&blkg->stat_ios, bio->bi_opf, 1);
 	}
 
@@ -715,6 +795,59 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q,
 	return !throtl;
 }
 
+static inline void blkcg_use_delay(struct blkcg_gq *blkg)
+{
+	if (atomic_add_return(1, &blkg->use_delay) == 1)
+		atomic_inc(&blkg->blkcg->css.cgroup->congestion_count);
+}
+
+static inline int blkcg_unuse_delay(struct blkcg_gq *blkg)
+{
+	int old = atomic_read(&blkg->use_delay);
+
+	if (old == 0)
+		return 0;
+
+	/*
+	 * We do this song and dance because we can race with somebody else
+	 * adding or removing delay.  If we just did an atomic_dec we'd end up
+	 * negative and we'd already be in trouble.  We need to subtract 1 and
+	 * then check to see if we were the last delay so we can drop the
+	 * congestion count on the cgroup.
+	 */
+	while (old) {
+		int cur = atomic_cmpxchg(&blkg->use_delay, old, old - 1);
+		if (cur == old)
+			break;
+		old = cur;
+	}
+
+	if (old == 0)
+		return 0;
+	if (old == 1)
+		atomic_dec(&blkg->blkcg->css.cgroup->congestion_count);
+	return 1;
+}
+
+static inline void blkcg_clear_delay(struct blkcg_gq *blkg)
+{
+	int old = atomic_read(&blkg->use_delay);
+	if (!old)
+		return;
+	/* We only want 1 person clearing the congestion count for this blkg. */
+	while (old) {
+		int cur = atomic_cmpxchg(&blkg->use_delay, old, 0);
+		if (cur == old) {
+			atomic_dec(&blkg->blkcg->css.cgroup->congestion_count);
+			break;
+		}
+		old = cur;
+	}
+}
+
+void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta);
+void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay);
+void blkcg_maybe_throttle_current(void);
 #else	/* CONFIG_BLK_CGROUP */
 
 struct blkcg {
@@ -734,9 +867,16 @@ struct blkcg_policy {
 
 #define blkcg_root_css	((struct cgroup_subsys_state *)ERR_PTR(-EINVAL))
 
+static inline void blkcg_maybe_throttle_current(void) { }
+static inline bool blk_cgroup_congested(void) { return false; }
+
 #ifdef CONFIG_BLOCK
 
+static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { }
+
 static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; }
+static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q)
+{ return NULL; }
 static inline int blkcg_init_queue(struct request_queue *q) { return 0; }
 static inline void blkcg_drain_queue(struct request_queue *q) { }
 static inline void blkcg_exit_queue(struct request_queue *q) { }
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index ca3f2c2edd85..1da59c16f637 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -35,10 +35,12 @@ struct blk_mq_hw_ctx {
 	struct sbitmap		ctx_map;
 
 	struct blk_mq_ctx	*dispatch_from;
+	unsigned int		dispatch_busy;
 
-	struct blk_mq_ctx	**ctxs;
 	unsigned int		nr_ctx;
+	struct blk_mq_ctx	**ctxs;
 
+	spinlock_t		dispatch_wait_lock;
 	wait_queue_entry_t	dispatch_wait;
 	atomic_t		wait_index;
 
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 3c4f390aea4b..f6dfb30737d8 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -179,11 +179,9 @@ struct bio {
 	 */
 	struct io_context	*bi_ioc;
 	struct cgroup_subsys_state *bi_css;
-#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
-	void			*bi_cg_private;
+	struct blkcg_gq		*bi_blkg;
 	struct bio_issue	bi_issue;
 #endif
-#endif
 	union {
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 		struct bio_integrity_payload *bi_integrity; /* data integrity */
@@ -329,7 +327,7 @@ enum req_flag_bits {
 
 	/* for driver use */
 	__REQ_DRV,
-
+	__REQ_SWAP,		/* swapping request. */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -351,6 +349,7 @@ enum req_flag_bits {
 #define REQ_NOUNMAP		(1ULL << __REQ_NOUNMAP)
 
 #define REQ_DRV			(1ULL << __REQ_DRV)
+#define REQ_SWAP		(1ULL << __REQ_SWAP)
 
 #define REQ_FAILFAST_MASK \
 	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
@@ -358,6 +357,14 @@ enum req_flag_bits {
 #define REQ_NOMERGE_FLAGS \
 	(REQ_NOMERGE | REQ_PREFLUSH | REQ_FUA)
 
+enum stat_group {
+	STAT_READ,
+	STAT_WRITE,
+	STAT_DISCARD,
+
+	NR_STAT_GROUPS
+};
+
 #define bio_op(bio) \
 	((bio)->bi_opf & REQ_OP_MASK)
 #define req_op(req) \
@@ -395,6 +402,18 @@ static inline bool op_is_sync(unsigned int op)
 		(op & (REQ_SYNC | REQ_FUA | REQ_PREFLUSH));
 }
 
+static inline bool op_is_discard(unsigned int op)
+{
+	return (op & REQ_OP_MASK) == REQ_OP_DISCARD;
+}
+
+static inline int op_stat_group(unsigned int op)
+{
+	if (op_is_discard(op))
+		return STAT_DISCARD;
+	return op_is_write(op);
+}
+
 typedef unsigned int blk_qc_t;
 #define BLK_QC_T_NONE		-1U
 #define BLK_QC_T_SHIFT		16
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 79226ca8f80f..d6869e0e2b64 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -27,8 +27,6 @@
 #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;
@@ -42,7 +40,7 @@ struct bsg_job;
 struct blkcg_gq;
 struct blk_flush_queue;
 struct pr_ops;
-struct rq_wb;
+struct rq_qos;
 struct blk_queue_stats;
 struct blk_stat_callback;
 
@@ -442,10 +440,8 @@ struct request_queue {
 	int			nr_rqs[2];	/* # allocated [a]sync rqs */
 	int			nr_rqs_elvpriv;	/* # allocated rqs w/ elvpriv */
 
-	atomic_t		shared_hctx_restart;
-
 	struct blk_queue_stats	*stats;
-	struct rq_wb		*rq_wb;
+	struct rq_qos		*rq_qos;
 
 	/*
 	 * If blkcg is not used, @q->root_rl serves all requests.  If blkcg
@@ -592,6 +588,7 @@ struct request_queue {
 
 	struct queue_limits	limits;
 
+#ifdef CONFIG_BLK_DEV_ZONED
 	/*
 	 * Zoned block device information for request dispatch control.
 	 * nr_zones is the total number of zones of the device. This is always
@@ -612,6 +609,7 @@ struct request_queue {
 	unsigned int		nr_zones;
 	unsigned long		*seq_zones_bitmap;
 	unsigned long		*seq_zones_wlock;
+#endif /* CONFIG_BLK_DEV_ZONED */
 
 	/*
 	 * sg stuff
@@ -800,11 +798,7 @@ 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;
-}
-
+#ifdef CONFIG_BLK_DEV_ZONED
 static inline unsigned int blk_queue_zone_no(struct request_queue *q,
 					     sector_t sector)
 {
@@ -820,6 +814,7 @@ static inline bool blk_queue_zone_is_seq(struct request_queue *q,
 		return false;
 	return test_bit(blk_queue_zone_no(q, sector), q->seq_zones_bitmap);
 }
+#endif /* CONFIG_BLK_DEV_ZONED */
 
 static inline bool rq_is_sync(struct request *rq)
 {
@@ -1070,6 +1065,7 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq)
 	return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT;
 }
 
+#ifdef CONFIG_BLK_DEV_ZONED
 static inline unsigned int blk_rq_zone_no(struct request *rq)
 {
 	return blk_queue_zone_no(rq->q, blk_rq_pos(rq));
@@ -1079,6 +1075,7 @@ static inline unsigned int blk_rq_zone_is_seq(struct request *rq)
 {
 	return blk_queue_zone_is_seq(rq->q, blk_rq_pos(rq));
 }
+#endif /* CONFIG_BLK_DEV_ZONED */
 
 /*
  * Some commands like WRITE SAME have a payload or data transfer size which
@@ -1437,8 +1434,6 @@ enum blk_default_limits {
 	BLK_SEG_BOUNDARY_MASK	= 0xFFFFFFFFUL,
 };
 
-#define blkdev_entry_to_request(entry) list_entry((entry), struct request, queuelist)
-
 static inline unsigned long queue_segment_boundary(struct request_queue *q)
 {
 	return q->limits.seg_boundary_mask;
@@ -1639,15 +1634,6 @@ static inline unsigned int bdev_zone_sectors(struct block_device *bdev)
 	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;
-}
-
 static inline int queue_dma_alignment(struct request_queue *q)
 {
 	return q ? q->dma_alignment : 511;
@@ -1877,6 +1863,28 @@ static inline bool integrity_req_gap_front_merge(struct request *req,
 				bip_next->bip_vec[0].bv_offset);
 }
 
+/**
+ * bio_integrity_intervals - Return number of integrity intervals for a bio
+ * @bi:		blk_integrity profile for device
+ * @sectors:	Size of the bio in 512-byte sectors
+ *
+ * Description: The block layer calculates everything in 512 byte
+ * sectors but integrity metadata is done in terms of the data integrity
+ * interval size of the storage device.  Convert the block layer sectors
+ * to the appropriate number of integrity intervals.
+ */
+static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
+						   unsigned int sectors)
+{
+	return sectors >> (bi->interval_exp - 9);
+}
+
+static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
+					       unsigned int sectors)
+{
+	return bio_integrity_intervals(bi, sectors) * bi->tuple_size;
+}
+
 #else /* CONFIG_BLK_DEV_INTEGRITY */
 
 struct bio;
@@ -1950,12 +1958,24 @@ static inline bool integrity_req_gap_front_merge(struct request *req,
 	return false;
 }
 
+static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
+						   unsigned int sectors)
+{
+	return 0;
+}
+
+static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
+					       unsigned int sectors)
+{
+	return 0;
+}
+
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
 struct block_device_operations {
 	int (*open) (struct block_device *, fmode_t);
 	void (*release) (struct gendisk *, fmode_t);
-	int (*rw_page)(struct block_device *, sector_t, struct page *, bool);
+	int (*rw_page)(struct block_device *, sector_t, struct page *, unsigned int);
 	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	unsigned int (*check_events) (struct gendisk *disk,
diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h
index e75dfd1f1dec..528271c60018 100644
--- a/include/linux/cdrom.h
+++ b/include/linux/cdrom.h
@@ -13,6 +13,7 @@
 
 #include <linux/fs.h>		/* not really needed, later.. */
 #include <linux/list.h>
+#include <scsi/scsi_common.h>
 #include <uapi/linux/cdrom.h>
 
 struct packet_command
@@ -21,7 +22,7 @@ struct packet_command
 	unsigned char 		*buffer;
 	unsigned int 		buflen;
 	int			stat;
-	struct request_sense	*sense;
+	struct scsi_sense_hdr	*sshdr;
 	unsigned char		data_direction;
 	int			quiet;
 	int			timeout;
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index c0e68f903011..ff20b677fb9f 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -438,6 +438,9 @@ struct cgroup {
 	/* used to store eBPF programs */
 	struct cgroup_bpf bpf;
 
+	/* If there is block congestion on this cgroup. */
+	atomic_t congestion_count;
+
 	/* ids of the ancestors at each level including self */
 	int ancestor_ids[];
 };
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 6cb8a5789668..57864422a2c8 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -16,6 +16,7 @@
 #include <linux/slab.h>
 #include <linux/percpu-refcount.h>
 #include <linux/uuid.h>
+#include <linux/blk_types.h>
 
 #ifdef CONFIG_BLOCK
 
@@ -82,10 +83,10 @@ struct partition {
 } __attribute__((packed));
 
 struct disk_stats {
-	unsigned long sectors[2];	/* READs and WRITEs */
-	unsigned long ios[2];
-	unsigned long merges[2];
-	unsigned long ticks[2];
+	unsigned long sectors[NR_STAT_GROUPS];
+	unsigned long ios[NR_STAT_GROUPS];
+	unsigned long merges[NR_STAT_GROUPS];
+	unsigned long ticks[NR_STAT_GROUPS];
 	unsigned long io_ticks;
 	unsigned long time_in_queue;
 };
@@ -353,6 +354,11 @@ static inline void free_part_stats(struct hd_struct *part)
 
 #endif /* CONFIG_SMP */
 
+#define part_stat_read_accum(part, field)				\
+	(part_stat_read(part, field[STAT_READ]) +			\
+	 part_stat_read(part, field[STAT_WRITE]) +			\
+	 part_stat_read(part, field[STAT_DISCARD]))
+
 #define part_stat_add(cpu, part, field, addnd)	do {			\
 	__part_stat_add((cpu), (part), field, addnd);			\
 	if ((part)->partno)						\
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 6c6fb116e925..680d3395fc83 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -317,6 +317,9 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
 int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
 			  gfp_t gfp_mask, struct mem_cgroup **memcgp,
 			  bool compound);
+int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm,
+			  gfp_t gfp_mask, struct mem_cgroup **memcgp,
+			  bool compound);
 void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg,
 			      bool lrucare, bool compound);
 void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg,
@@ -789,6 +792,16 @@ static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
 	return 0;
 }
 
+static inline int mem_cgroup_try_charge_delay(struct page *page,
+					      struct mm_struct *mm,
+					      gfp_t gfp_mask,
+					      struct mem_cgroup **memcgp,
+					      bool compound)
+{
+	*memcgp = NULL;
+	return 0;
+}
+
 static inline void mem_cgroup_commit_charge(struct page *page,
 					    struct mem_cgroup *memcg,
 					    bool lrucare, bool compound)
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 2950ce957656..68e91ef5494c 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -242,7 +242,12 @@ struct nvme_id_ctrl {
 	__le32			sanicap;
 	__le32			hmminds;
 	__le16			hmmaxd;
-	__u8			rsvd338[174];
+	__u8			rsvd338[4];
+	__u8			anatt;
+	__u8			anacap;
+	__le32			anagrpmax;
+	__le32			nanagrpid;
+	__u8			rsvd352[160];
 	__u8			sqes;
 	__u8			cqes;
 	__le16			maxcmd;
@@ -254,11 +259,12 @@ struct nvme_id_ctrl {
 	__le16			awun;
 	__le16			awupf;
 	__u8			nvscc;
-	__u8			rsvd531;
+	__u8			nwpc;
 	__le16			acwu;
 	__u8			rsvd534[2];
 	__le32			sgls;
-	__u8			rsvd540[228];
+	__le32			mnan;
+	__u8			rsvd544[224];
 	char			subnqn[256];
 	__u8			rsvd1024[768];
 	__le32			ioccsz;
@@ -312,7 +318,11 @@ struct nvme_id_ns {
 	__le16			nabspf;
 	__le16			noiob;
 	__u8			nvmcap[16];
-	__u8			rsvd64[40];
+	__u8			rsvd64[28];
+	__le32			anagrpid;
+	__u8			rsvd96[3];
+	__u8			nsattr;
+	__u8			rsvd100[4];
 	__u8			nguid[16];
 	__u8			eui64[8];
 	struct nvme_lbaf	lbaf[16];
@@ -425,6 +435,32 @@ struct nvme_effects_log {
 	__u8   resv[2048];
 };
 
+enum nvme_ana_state {
+	NVME_ANA_OPTIMIZED		= 0x01,
+	NVME_ANA_NONOPTIMIZED		= 0x02,
+	NVME_ANA_INACCESSIBLE		= 0x03,
+	NVME_ANA_PERSISTENT_LOSS	= 0x04,
+	NVME_ANA_CHANGE			= 0x0f,
+};
+
+struct nvme_ana_group_desc {
+	__le32	grpid;
+	__le32	nnsids;
+	__le64	chgcnt;
+	__u8	state;
+	__u8	rsvd17[15];
+	__le32	nsids[];
+};
+
+/* flag for the log specific field of the ANA log */
+#define NVME_ANA_LOG_RGO	(1 << 0)
+
+struct nvme_ana_rsp_hdr {
+	__le64	chgcnt;
+	__le16	ngrps;
+	__le16	rsvd10[3];
+};
+
 enum {
 	NVME_SMART_CRIT_SPARE		= 1 << 0,
 	NVME_SMART_CRIT_TEMPERATURE	= 1 << 1,
@@ -444,11 +480,13 @@ enum {
 enum {
 	NVME_AER_NOTICE_NS_CHANGED	= 0x00,
 	NVME_AER_NOTICE_FW_ACT_STARTING = 0x01,
+	NVME_AER_NOTICE_ANA		= 0x03,
 };
 
 enum {
 	NVME_AEN_CFG_NS_ATTR		= 1 << 8,
 	NVME_AEN_CFG_FW_ACT		= 1 << 9,
+	NVME_AEN_CFG_ANA_CHANGE		= 1 << 11,
 };
 
 struct nvme_lba_range_type {
@@ -749,15 +787,22 @@ enum {
 	NVME_FEAT_HOST_MEM_BUF	= 0x0d,
 	NVME_FEAT_TIMESTAMP	= 0x0e,
 	NVME_FEAT_KATO		= 0x0f,
+	NVME_FEAT_HCTM		= 0x10,
+	NVME_FEAT_NOPSC		= 0x11,
+	NVME_FEAT_RRL		= 0x12,
+	NVME_FEAT_PLM_CONFIG	= 0x13,
+	NVME_FEAT_PLM_WINDOW	= 0x14,
 	NVME_FEAT_SW_PROGRESS	= 0x80,
 	NVME_FEAT_HOST_ID	= 0x81,
 	NVME_FEAT_RESV_MASK	= 0x82,
 	NVME_FEAT_RESV_PERSIST	= 0x83,
+	NVME_FEAT_WRITE_PROTECT	= 0x84,
 	NVME_LOG_ERROR		= 0x01,
 	NVME_LOG_SMART		= 0x02,
 	NVME_LOG_FW_SLOT	= 0x03,
 	NVME_LOG_CHANGED_NS	= 0x04,
 	NVME_LOG_CMD_EFFECTS	= 0x05,
+	NVME_LOG_ANA		= 0x0c,
 	NVME_LOG_DISC		= 0x70,
 	NVME_LOG_RESERVATION	= 0x80,
 	NVME_FWACT_REPL		= (0 << 3),
@@ -765,6 +810,14 @@ enum {
 	NVME_FWACT_ACTV		= (2 << 3),
 };
 
+/* NVMe Namespace Write Protect State */
+enum {
+	NVME_NS_NO_WRITE_PROTECT = 0,
+	NVME_NS_WRITE_PROTECT,
+	NVME_NS_WRITE_PROTECT_POWER_CYCLE,
+	NVME_NS_WRITE_PROTECT_PERMANENT,
+};
+
 #define NVME_MAX_CHANGED_NAMESPACES	1024
 
 struct nvme_identify {
@@ -880,7 +933,7 @@ struct nvme_get_log_page_command {
 	__u64			rsvd2[2];
 	union nvme_data_ptr	dptr;
 	__u8			lid;
-	__u8			rsvd10;
+	__u8			lsp; /* upper 4 bits reserved */
 	__le16			numdl;
 	__le16			numdu;
 	__u16			rsvd11;
@@ -1111,6 +1164,8 @@ enum {
 	NVME_SC_SGL_INVALID_OFFSET	= 0x16,
 	NVME_SC_SGL_INVALID_SUBTYPE	= 0x17,
 
+	NVME_SC_NS_WRITE_PROTECTED	= 0x20,
+
 	NVME_SC_LBA_RANGE		= 0x80,
 	NVME_SC_CAP_EXCEEDED		= 0x81,
 	NVME_SC_NS_NOT_READY		= 0x82,
@@ -1180,6 +1235,13 @@ enum {
 	NVME_SC_ACCESS_DENIED		= 0x286,
 	NVME_SC_UNWRITTEN_BLOCK		= 0x287,
 
+	/*
+	 * Path-related Errors:
+	 */
+	NVME_SC_ANA_PERSISTENT_LOSS	= 0x301,
+	NVME_SC_ANA_INACCESSIBLE	= 0x302,
+	NVME_SC_ANA_TRANSITION		= 0x303,
+
 	NVME_SC_DNR			= 0x4000,
 };
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index dac5086e3815..95a5018c338e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -734,6 +734,10 @@ struct task_struct {
 	/* disallow userland-initiated cgroup migration */
 	unsigned			no_cgroup_migration:1;
 #endif
+#ifdef CONFIG_BLK_CGROUP
+	/* to be used once the psi infrastructure lands upstream. */
+	unsigned			use_memdelay:1;
+#endif
 
 	unsigned long			atomic_flags; /* Flags requiring atomic access. */
 
@@ -1150,6 +1154,10 @@ struct task_struct {
 	unsigned int			memcg_nr_pages_over_high;
 #endif
 
+#ifdef CONFIG_BLK_CGROUP
+	struct request_queue		*throttle_queue;
+#endif
+
 #ifdef CONFIG_UPROBES
 	struct uprobe_task		*utask;
 #endif
diff --git a/include/linux/swap.h b/include/linux/swap.h
index c063443d8638..1a8bd05a335e 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -629,7 +629,6 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg)
 
 	return memcg->swappiness;
 }
-
 #else
 static inline int mem_cgroup_swappiness(struct mem_cgroup *mem)
 {
@@ -637,6 +636,16 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *mem)
 }
 #endif
 
+#if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
+extern void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg, int node,
+					 gfp_t gfp_mask);
+#else
+static inline void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg,
+						int node, gfp_t gfp_mask)
+{
+}
+#endif
+
 #ifdef CONFIG_MEMCG_SWAP
 extern void mem_cgroup_swapout(struct page *page, swp_entry_t entry);
 extern int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry);
diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h
index c6aa8a3c42ed..b9626aa7e90c 100644
--- a/include/linux/t10-pi.h
+++ b/include/linux/t10-pi.h
@@ -37,9 +37,33 @@ struct t10_pi_tuple {
 #define T10_PI_APP_ESCAPE cpu_to_be16(0xffff)
 #define T10_PI_REF_ESCAPE cpu_to_be32(0xffffffff)
 
+static inline u32 t10_pi_ref_tag(struct request *rq)
+{
+#ifdef CONFIG_BLK_DEV_INTEGRITY
+	return blk_rq_pos(rq) >>
+		(rq->q->integrity.interval_exp - 9) & 0xffffffff;
+#else
+	return -1U;
+#endif
+}
+
 extern const struct blk_integrity_profile t10_pi_type1_crc;
 extern const struct blk_integrity_profile t10_pi_type1_ip;
 extern const struct blk_integrity_profile t10_pi_type3_crc;
 extern const struct blk_integrity_profile t10_pi_type3_ip;
 
+#ifdef CONFIG_BLK_DEV_INTEGRITY
+extern void t10_pi_prepare(struct request *rq, u8 protection_type);
+extern void t10_pi_complete(struct request *rq, u8 protection_type,
+			    unsigned int intervals);
+#else
+static inline void t10_pi_complete(struct request *rq, u8 protection_type,
+				   unsigned int intervals)
+{
+}
+static inline void t10_pi_prepare(struct request *rq, u8 protection_type)
+{
+}
+#endif
+
 #endif
diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h
index 4a8841963c2e..05589a3e37f4 100644
--- a/include/linux/tracehook.h
+++ b/include/linux/tracehook.h
@@ -51,6 +51,7 @@
 #include <linux/security.h>
 #include <linux/task_work.h>
 #include <linux/memcontrol.h>
+#include <linux/blk-cgroup.h>
 struct linux_binprm;
 
 /*
@@ -192,6 +193,7 @@ static inline void tracehook_notify_resume(struct pt_regs *regs)
 		task_work_run();
 
 	mem_cgroup_handle_over_high();
+	blkcg_maybe_throttle_current();
 }
 
 #endif	/* <linux/tracehook.h> */