Merge tag 'for-5.8/block-2020-06-01' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "Core block changes that have been queued up for this release:

   - Remove dead blk-throttle and blk-wbt code (Guoqing)

   - Include pid in blktrace note traces (Jan)

   - Don't spew I/O errors on wouldblock termination (me)

   - Zone append addition (Johannes, Keith, Damien)

   - IO accounting improvements (Konstantin, Christoph)

   - blk-mq hardware map update improvements (Ming)

   - Scheduler dispatch improvement (Salman)

   - Inline block encryption support (Satya)

   - Request map fixes and improvements (Weiping)

   - blk-iocost tweaks (Tejun)

   - Fix for timeout failing with error injection (Keith)

   - Queue re-run fixes (Douglas)

   - CPU hotplug improvements (Christoph)

   - Queue entry/exit improvements (Christoph)

   - Move DMA drain handling to the few drivers that use it (Christoph)

   - Partition handling cleanups (Christoph)"

* tag 'for-5.8/block-2020-06-01' of git://git.kernel.dk/linux-block: (127 commits)
  block: mark bio_wouldblock_error() bio with BIO_QUIET
  blk-wbt: rename __wbt_update_limits to wbt_update_limits
  blk-wbt: remove wbt_update_limits
  blk-throttle: remove tg_drain_bios
  blk-throttle: remove blk_throtl_drain
  null_blk: force complete for timeout request
  blk-mq: drain I/O when all CPUs in a hctx are offline
  blk-mq: add blk_mq_all_tag_iter
  blk-mq: open code __blk_mq_alloc_request in blk_mq_alloc_request_hctx
  blk-mq: use BLK_MQ_NO_TAG in more places
  blk-mq: rename BLK_MQ_TAG_FAIL to BLK_MQ_NO_TAG
  blk-mq: move more request initialization to blk_mq_rq_ctx_init
  blk-mq: simplify the blk_mq_get_request calling convention
  blk-mq: remove the bio argument to ->prepare_request
  nvme: force complete cancelled requests
  blk-mq: blk-mq: provide forced completion method
  block: fix a warning when blkdev.h is included for !CONFIG_BLOCK builds
  block: blk-crypto-fallback: remove redundant initialization of variable err
  block: reduce part_stat_lock() scope
  block: use __this_cpu_add() instead of access by smp_processor_id()
  ...

21 files changed, 484 insertions, 124 deletions

diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index 7367150f962a..90a7e844a098 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -193,8 +193,6 @@ struct backing_dev_info {
 	congested_fn *congested_fn; /* Function pointer if device is md/dm */
 	void *congested_data;	/* Pointer to aux data for congested func */
 
-	const char *name;
-
 	struct kref refcnt;	/* Reference counter for the structure */
 	unsigned int capabilities; /* Device capabilities */
 	unsigned int min_ratio;
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index c9ad5c3b7b4b..6b3504bf7a42 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -33,14 +33,10 @@ int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...);
 __printf(2, 0)
 int bdi_register_va(struct backing_dev_info *bdi, const char *fmt,
 		    va_list args);
-int bdi_register_owner(struct backing_dev_info *bdi, struct device *owner);
+void bdi_set_owner(struct backing_dev_info *bdi, struct device *owner);
 void bdi_unregister(struct backing_dev_info *bdi);
 
-struct backing_dev_info *bdi_alloc_node(gfp_t gfp_mask, int node_id);
-static inline struct backing_dev_info *bdi_alloc(gfp_t gfp_mask)
-{
-	return bdi_alloc_node(gfp_mask, NUMA_NO_NODE);
-}
+struct backing_dev_info *bdi_alloc(int node_id);
 
 void wb_start_background_writeback(struct bdi_writeback *wb);
 void wb_workfn(struct work_struct *work);
diff --git a/include/linux/bio.h b/include/linux/bio.h
index a0ee494a6329..683ff5fd8871 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -70,7 +70,7 @@ static inline bool bio_has_data(struct bio *bio)
 	return false;
 }
 
-static inline bool bio_no_advance_iter(struct bio *bio)
+static inline bool bio_no_advance_iter(const struct bio *bio)
 {
 	return bio_op(bio) == REQ_OP_DISCARD ||
 	       bio_op(bio) == REQ_OP_SECURE_ERASE ||
@@ -138,8 +138,8 @@ static inline bool bio_next_segment(const struct bio *bio,
 #define bio_for_each_segment_all(bvl, bio, iter) \
 	for (bvl = bvec_init_iter_all(&iter); bio_next_segment((bio), &iter); )
 
-static inline void bio_advance_iter(struct bio *bio, struct bvec_iter *iter,
-				    unsigned bytes)
+static inline void bio_advance_iter(const struct bio *bio,
+				    struct bvec_iter *iter, unsigned int bytes)
 {
 	iter->bi_sector += bytes >> 9;
 
@@ -417,6 +417,7 @@ static inline void bio_io_error(struct bio *bio)
 
 static inline void bio_wouldblock_error(struct bio *bio)
 {
+	bio_set_flag(bio, BIO_QUIET);
 	bio->bi_status = BLK_STS_AGAIN;
 	bio_endio(bio);
 }
@@ -444,12 +445,6 @@ void bio_release_pages(struct bio *bio, bool mark_dirty);
 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 op,
-				unsigned long sectors, struct hd_struct *part);
-void generic_end_io_acct(struct request_queue *q, int op,
-				struct hd_struct *part,
-				unsigned long start_time);
-
 extern void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter,
 			       struct bio *src, struct bvec_iter *src_iter);
 extern void bio_copy_data(struct bio *dst, struct bio *src);
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 35f8ffe92b70..a57ebe2f00ab 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -607,12 +607,14 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q,
 		u64_stats_update_begin(&bis->sync);
 
 		/*
-		 * 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 the bio is flagged with BIO_CGROUP_ACCT 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))
+		if (!bio_flagged(bio, BIO_CGROUP_ACCT)) {
+			bio_set_flag(bio, BIO_CGROUP_ACCT);
 			bis->cur.bytes[rwd] += bio->bi_iter.bi_size;
+		}
 		bis->cur.ios[rwd]++;
 
 		u64_stats_update_end(&bis->sync);
@@ -629,6 +631,8 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q,
 
 static inline void blkcg_use_delay(struct blkcg_gq *blkg)
 {
+	if (WARN_ON_ONCE(atomic_read(&blkg->use_delay) < 0))
+		return;
 	if (atomic_add_return(1, &blkg->use_delay) == 1)
 		atomic_inc(&blkg->blkcg->css.cgroup->congestion_count);
 }
@@ -637,6 +641,8 @@ static inline int blkcg_unuse_delay(struct blkcg_gq *blkg)
 {
 	int old = atomic_read(&blkg->use_delay);
 
+	if (WARN_ON_ONCE(old < 0))
+		return 0;
 	if (old == 0)
 		return 0;
 
@@ -661,20 +667,39 @@ static inline int blkcg_unuse_delay(struct blkcg_gq *blkg)
 	return 1;
 }
 
+/**
+ * blkcg_set_delay - Enable allocator delay mechanism with the specified delay amount
+ * @blkg: target blkg
+ * @delay: delay duration in nsecs
+ *
+ * When enabled with this function, the delay is not decayed and must be
+ * explicitly cleared with blkcg_clear_delay(). Must not be mixed with
+ * blkcg_[un]use_delay() and blkcg_add_delay() usages.
+ */
+static inline void blkcg_set_delay(struct blkcg_gq *blkg, u64 delay)
+{
+	int old = atomic_read(&blkg->use_delay);
+
+	/* We only want 1 person setting the congestion count for this blkg. */
+	if (!old && atomic_cmpxchg(&blkg->use_delay, old, -1) == old)
+		atomic_inc(&blkg->blkcg->css.cgroup->congestion_count);
+
+	atomic64_set(&blkg->delay_nsec, delay);
+}
+
+/**
+ * blkcg_clear_delay - Disable allocator delay mechanism
+ * @blkg: target blkg
+ *
+ * Disable use_delay mechanism. See blkcg_set_delay().
+ */
 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;
-	}
+	if (old && atomic_cmpxchg(&blkg->use_delay, old, 0) == old)
+		atomic_dec(&blkg->blkcg->css.cgroup->congestion_count);
 }
 
 void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta);
diff --git a/include/linux/blk-crypto.h b/include/linux/blk-crypto.h
new file mode 100644
index 000000000000..e82342907f2b
--- /dev/null
+++ b/include/linux/blk-crypto.h
@@ -0,0 +1,123 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright 2019 Google LLC
+ */
+
+#ifndef __LINUX_BLK_CRYPTO_H
+#define __LINUX_BLK_CRYPTO_H
+
+#include <linux/types.h>
+
+enum blk_crypto_mode_num {
+	BLK_ENCRYPTION_MODE_INVALID,
+	BLK_ENCRYPTION_MODE_AES_256_XTS,
+	BLK_ENCRYPTION_MODE_AES_128_CBC_ESSIV,
+	BLK_ENCRYPTION_MODE_ADIANTUM,
+	BLK_ENCRYPTION_MODE_MAX,
+};
+
+#define BLK_CRYPTO_MAX_KEY_SIZE		64
+/**
+ * struct blk_crypto_config - an inline encryption key's crypto configuration
+ * @crypto_mode: encryption algorithm this key is for
+ * @data_unit_size: the data unit size for all encryption/decryptions with this
+ *	key.  This is the size in bytes of each individual plaintext and
+ *	ciphertext.  This is always a power of 2.  It might be e.g. the
+ *	filesystem block size or the disk sector size.
+ * @dun_bytes: the maximum number of bytes of DUN used when using this key
+ */
+struct blk_crypto_config {
+	enum blk_crypto_mode_num crypto_mode;
+	unsigned int data_unit_size;
+	unsigned int dun_bytes;
+};
+
+/**
+ * struct blk_crypto_key - an inline encryption key
+ * @crypto_cfg: the crypto configuration (like crypto_mode, key size) for this
+ *		key
+ * @data_unit_size_bits: log2 of data_unit_size
+ * @size: size of this key in bytes (determined by @crypto_cfg.crypto_mode)
+ * @raw: the raw bytes of this key.  Only the first @size bytes are used.
+ *
+ * A blk_crypto_key is immutable once created, and many bios can reference it at
+ * the same time.  It must not be freed until all bios using it have completed
+ * and it has been evicted from all devices on which it may have been used.
+ */
+struct blk_crypto_key {
+	struct blk_crypto_config crypto_cfg;
+	unsigned int data_unit_size_bits;
+	unsigned int size;
+	u8 raw[BLK_CRYPTO_MAX_KEY_SIZE];
+};
+
+#define BLK_CRYPTO_MAX_IV_SIZE		32
+#define BLK_CRYPTO_DUN_ARRAY_SIZE	(BLK_CRYPTO_MAX_IV_SIZE / sizeof(u64))
+
+/**
+ * struct bio_crypt_ctx - an inline encryption context
+ * @bc_key: the key, algorithm, and data unit size to use
+ * @bc_dun: the data unit number (starting IV) to use
+ *
+ * A bio_crypt_ctx specifies that the contents of the bio will be encrypted (for
+ * write requests) or decrypted (for read requests) inline by the storage device
+ * or controller, or by the crypto API fallback.
+ */
+struct bio_crypt_ctx {
+	const struct blk_crypto_key	*bc_key;
+	u64				bc_dun[BLK_CRYPTO_DUN_ARRAY_SIZE];
+};
+
+#include <linux/blk_types.h>
+#include <linux/blkdev.h>
+
+struct request;
+struct request_queue;
+
+#ifdef CONFIG_BLK_INLINE_ENCRYPTION
+
+static inline bool bio_has_crypt_ctx(struct bio *bio)
+{
+	return bio->bi_crypt_context;
+}
+
+void bio_crypt_set_ctx(struct bio *bio, const struct blk_crypto_key *key,
+		       const u64 dun[BLK_CRYPTO_DUN_ARRAY_SIZE],
+		       gfp_t gfp_mask);
+
+bool bio_crypt_dun_is_contiguous(const struct bio_crypt_ctx *bc,
+				 unsigned int bytes,
+				 const u64 next_dun[BLK_CRYPTO_DUN_ARRAY_SIZE]);
+
+int blk_crypto_init_key(struct blk_crypto_key *blk_key, const u8 *raw_key,
+			enum blk_crypto_mode_num crypto_mode,
+			unsigned int dun_bytes,
+			unsigned int data_unit_size);
+
+int blk_crypto_start_using_key(const struct blk_crypto_key *key,
+			       struct request_queue *q);
+
+int blk_crypto_evict_key(struct request_queue *q,
+			 const struct blk_crypto_key *key);
+
+bool blk_crypto_config_supported(struct request_queue *q,
+				 const struct blk_crypto_config *cfg);
+
+#else /* CONFIG_BLK_INLINE_ENCRYPTION */
+
+static inline bool bio_has_crypt_ctx(struct bio *bio)
+{
+	return false;
+}
+
+#endif /* CONFIG_BLK_INLINE_ENCRYPTION */
+
+void __bio_crypt_clone(struct bio *dst, struct bio *src, gfp_t gfp_mask);
+static inline void bio_crypt_clone(struct bio *dst, struct bio *src,
+				   gfp_t gfp_mask)
+{
+	if (bio_has_crypt_ctx(src))
+		__bio_crypt_clone(dst, src, gfp_mask);
+}
+
+#endif /* __LINUX_BLK_CRYPTO_H */
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index b45148ba3291..d6fcae17da5a 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -140,6 +140,8 @@ struct blk_mq_hw_ctx {
 	 */
 	atomic_t		nr_active;
 
+	/** @cpuhp_online: List to store request if CPU is going to die */
+	struct hlist_node	cpuhp_online;
 	/** @cpuhp_dead: List to store request if some CPU die. */
 	struct hlist_node	cpuhp_dead;
 	/** @kobj: Kernel object for sysfs. */
@@ -391,6 +393,11 @@ struct blk_mq_ops {
 enum {
 	BLK_MQ_F_SHOULD_MERGE	= 1 << 0,
 	BLK_MQ_F_TAG_SHARED	= 1 << 1,
+	/*
+	 * Set when this device requires underlying blk-mq device for
+	 * completing IO:
+	 */
+	BLK_MQ_F_STACKING	= 1 << 2,
 	BLK_MQ_F_BLOCKING	= 1 << 5,
 	BLK_MQ_F_NO_SCHED	= 1 << 6,
 	BLK_MQ_F_ALLOC_POLICY_START_BIT = 8,
@@ -400,6 +407,9 @@ enum {
 	BLK_MQ_S_TAG_ACTIVE	= 1,
 	BLK_MQ_S_SCHED_RESTART	= 2,
 
+	/* hw queue is inactive after all its CPUs become offline */
+	BLK_MQ_S_INACTIVE	= 3,
+
 	BLK_MQ_MAX_DEPTH	= 10240,
 
 	BLK_MQ_CPU_WORK_BATCH	= 8,
@@ -494,6 +504,7 @@ void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list);
 void blk_mq_kick_requeue_list(struct request_queue *q);
 void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs);
 bool blk_mq_complete_request(struct request *rq);
+void blk_mq_force_complete_rq(struct request *rq);
 bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list,
 			   struct bio *bio, unsigned int nr_segs);
 bool blk_mq_queue_stopped(struct request_queue *q);
@@ -508,6 +519,7 @@ void blk_mq_unquiesce_queue(struct request_queue *q);
 void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
 void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
 void blk_mq_run_hw_queues(struct request_queue *q, bool async);
+void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs);
 void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
 		busy_tag_iter_fn *fn, void *priv);
 void blk_mq_tagset_wait_completed_request(struct blk_mq_tag_set *tagset);
@@ -577,4 +589,6 @@ static inline void blk_mq_cleanup_rq(struct request *rq)
 		rq->q->mq_ops->cleanup_rq(rq);
 }
 
+blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio);
+
 #endif
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 31eb92876be7..ccb895f911b1 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -18,6 +18,7 @@ struct block_device;
 struct io_context;
 struct cgroup_subsys_state;
 typedef void (bio_end_io_t) (struct bio *);
+struct bio_crypt_ctx;
 
 /*
  * Block error status values.  See block/blk-core:blk_errors for the details.
@@ -63,6 +64,18 @@ typedef u8 __bitwise blk_status_t;
  */
 #define BLK_STS_DEV_RESOURCE	((__force blk_status_t)13)
 
+/*
+ * BLK_STS_ZONE_RESOURCE is returned from the driver to the block layer if zone
+ * related resources are unavailable, but the driver can guarantee the queue
+ * will be rerun in the future once the resources become available again.
+ *
+ * This is different from BLK_STS_DEV_RESOURCE in that it explicitly references
+ * a zone specific resource and IO to a different zone on the same device could
+ * still be served. Examples of that are zones that are write-locked, but a read
+ * to the same zone could be served.
+ */
+#define BLK_STS_ZONE_RESOURCE	((__force blk_status_t)14)
+
 /**
  * blk_path_error - returns true if error may be path related
  * @error: status the request was completed with
@@ -173,6 +186,11 @@ struct bio {
 	u64			bi_iocost_cost;
 #endif
 #endif
+
+#ifdef CONFIG_BLK_INLINE_ENCRYPTION
+	struct bio_crypt_ctx	*bi_crypt_context;
+#endif
+
 	union {
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 		struct bio_integrity_payload *bi_integrity; /* data integrity */
@@ -220,7 +238,7 @@ enum {
 				 * throttling rules. Don't do it again. */
 	BIO_TRACE_COMPLETION,	/* bio_endio() should trace the final completion
 				 * of this bio. */
-	BIO_QUEUE_ENTERED,	/* can use blk_queue_enter_live() */
+	BIO_CGROUP_ACCT,	/* has been accounted to a cgroup */
 	BIO_TRACKED,		/* set if bio goes through the rq_qos path */
 	BIO_FLAG_LAST
 };
@@ -296,6 +314,8 @@ enum req_opf {
 	REQ_OP_ZONE_CLOSE	= 11,
 	/* Transition a zone to full */
 	REQ_OP_ZONE_FINISH	= 12,
+	/* write data at the current zone write pointer */
+	REQ_OP_ZONE_APPEND	= 13,
 
 	/* SCSI passthrough using struct scsi_request */
 	REQ_OP_SCSI_IN		= 32,
@@ -323,7 +343,6 @@ enum req_flag_bits {
 	__REQ_RAHEAD,		/* read ahead, can fail anytime */
 	__REQ_BACKGROUND,	/* background IO */
 	__REQ_NOWAIT,           /* Don't wait if request will block */
-	__REQ_NOWAIT_INLINE,	/* Return would-block error inline */
 	/*
 	 * When a shared kthread needs to issue a bio for a cgroup, doing
 	 * so synchronously can lead to priority inversions as the kthread
@@ -358,7 +377,6 @@ enum req_flag_bits {
 #define REQ_RAHEAD		(1ULL << __REQ_RAHEAD)
 #define REQ_BACKGROUND		(1ULL << __REQ_BACKGROUND)
 #define REQ_NOWAIT		(1ULL << __REQ_NOWAIT)
-#define REQ_NOWAIT_INLINE	(1ULL << __REQ_NOWAIT_INLINE)
 #define REQ_CGROUP_PUNT		(1ULL << __REQ_CGROUP_PUNT)
 
 #define REQ_NOUNMAP		(1ULL << __REQ_NOUNMAP)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 32868fbedc9e..8fd900998b4e 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -43,6 +43,7 @@ struct pr_ops;
 struct rq_qos;
 struct blk_queue_stats;
 struct blk_stat_callback;
+struct blk_keyslot_manager;
 
 #define BLKDEV_MIN_RQ	4
 #define BLKDEV_MAX_RQ	128	/* Default maximum */
@@ -82,8 +83,6 @@ typedef __u32 __bitwise req_flags_t;
 /* set for "ide_preempt" requests and also for requests for which the SCSI
    "quiesce" state must be ignored. */
 #define RQF_PREEMPT		((__force req_flags_t)(1 << 8))
-/* contains copies of user pages */
-#define RQF_COPY_USER		((__force req_flags_t)(1 << 9))
 /* vaguely specified driver internal error.  Ignored by the block layer */
 #define RQF_FAILED		((__force req_flags_t)(1 << 10))
 /* don't warn about errors */
@@ -223,11 +222,14 @@ struct request {
 	unsigned short nr_integrity_segments;
 #endif
 
+#ifdef CONFIG_BLK_INLINE_ENCRYPTION
+	struct bio_crypt_ctx *crypt_ctx;
+	struct blk_ksm_keyslot *crypt_keyslot;
+#endif
+
 	unsigned short write_hint;
 	unsigned short ioprio;
 
-	unsigned int extra_len;	/* length of alignment and padding */
-
 	enum mq_rq_state state;
 	refcount_t ref;
 
@@ -290,7 +292,6 @@ struct blk_queue_ctx;
 typedef blk_qc_t (make_request_fn) (struct request_queue *q, struct bio *bio);
 
 struct bio_vec;
-typedef int (dma_drain_needed_fn)(struct request *);
 
 enum blk_eh_timer_return {
 	BLK_EH_DONE,		/* drivers has completed the command */
@@ -336,6 +337,7 @@ struct queue_limits {
 	unsigned int		max_hw_discard_sectors;
 	unsigned int		max_write_same_sectors;
 	unsigned int		max_write_zeroes_sectors;
+	unsigned int		max_zone_append_sectors;
 	unsigned int		discard_granularity;
 	unsigned int		discard_alignment;
 
@@ -361,7 +363,8 @@ unsigned int blkdev_nr_zones(struct gendisk *disk);
 extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op,
 			    sector_t sectors, sector_t nr_sectors,
 			    gfp_t gfp_mask);
-extern int blk_revalidate_disk_zones(struct gendisk *disk);
+int blk_revalidate_disk_zones(struct gendisk *disk,
+			      void (*update_driver_data)(struct gendisk *disk));
 
 extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
 				     unsigned int cmd, unsigned long arg);
@@ -399,7 +402,6 @@ struct request_queue {
 	struct rq_qos		*rq_qos;
 
 	make_request_fn		*make_request_fn;
-	dma_drain_needed_fn	*dma_drain_needed;
 
 	const struct blk_mq_ops	*mq_ops;
 
@@ -469,11 +471,14 @@ struct request_queue {
 	 */
 	unsigned long		nr_requests;	/* Max # of requests */
 
-	unsigned int		dma_drain_size;
-	void			*dma_drain_buffer;
 	unsigned int		dma_pad_mask;
 	unsigned int		dma_alignment;
 
+#ifdef CONFIG_BLK_INLINE_ENCRYPTION
+	/* Inline crypto capabilities */
+	struct blk_keyslot_manager *ksm;
+#endif
+
 	unsigned int		rq_timeout;
 	int			poll_nsec;
 
@@ -729,6 +734,16 @@ static inline unsigned int blk_queue_nr_zones(struct request_queue *q)
 {
 	return 0;
 }
+static inline bool blk_queue_zone_is_seq(struct request_queue *q,
+					 sector_t sector)
+{
+	return false;
+}
+static inline unsigned int blk_queue_zone_no(struct request_queue *q,
+					     sector_t sector)
+{
+	return 0;
+}
 #endif /* CONFIG_BLK_DEV_ZONED */
 
 static inline bool rq_is_sync(struct request *rq)
@@ -747,6 +762,9 @@ static inline bool rq_mergeable(struct request *rq)
 	if (req_op(rq) == REQ_OP_WRITE_ZEROES)
 		return false;
 
+	if (req_op(rq) == REQ_OP_ZONE_APPEND)
+		return false;
+
 	if (rq->cmd_flags & REQ_NOMERGE_FLAGS)
 		return false;
 	if (rq->rq_flags & RQF_NOMERGE_FLAGS)
@@ -1081,6 +1099,8 @@ extern void blk_queue_max_write_same_sectors(struct request_queue *q,
 extern void blk_queue_max_write_zeroes_sectors(struct request_queue *q,
 		unsigned int max_write_same_sectors);
 extern void blk_queue_logical_block_size(struct request_queue *, unsigned int);
+extern void blk_queue_max_zone_append_sectors(struct request_queue *q,
+		unsigned int max_zone_append_sectors);
 extern void blk_queue_physical_block_size(struct request_queue *, unsigned int);
 extern void blk_queue_alignment_offset(struct request_queue *q,
 				       unsigned int alignment);
@@ -1099,9 +1119,6 @@ extern void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
 			      sector_t offset);
 extern void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b);
 extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int);
-extern int blk_queue_dma_drain(struct request_queue *q,
-			       dma_drain_needed_fn *dma_drain_needed,
-			       void *buf, unsigned int size);
 extern void blk_queue_segment_boundary(struct request_queue *, unsigned long);
 extern void blk_queue_virt_boundary(struct request_queue *, unsigned long);
 extern void blk_queue_dma_alignment(struct request_queue *, int);
@@ -1138,7 +1155,15 @@ static inline unsigned short blk_rq_nr_discard_segments(struct request *rq)
 	return max_t(unsigned short, rq->nr_phys_segments, 1);
 }
 
-extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *);
+int __blk_rq_map_sg(struct request_queue *q, struct request *rq,
+		struct scatterlist *sglist, struct scatterlist **last_sg);
+static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq,
+		struct scatterlist *sglist)
+{
+	struct scatterlist *last_sg = NULL;
+
+	return __blk_rq_map_sg(q, rq, sglist, &last_sg);
+}
 extern void blk_dump_rq_flags(struct request *, char *);
 extern long nr_blockdev_pages(void);
 
@@ -1206,7 +1231,9 @@ static inline bool blk_needs_flush_plug(struct task_struct *tsk)
 		 !list_empty(&plug->cb_list));
 }
 
-extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *);
+extern void blk_io_schedule(void);
+
+int blkdev_issue_flush(struct block_device *, gfp_t);
 extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, struct page *page);
 
@@ -1293,6 +1320,11 @@ static inline unsigned int queue_max_segment_size(const struct request_queue *q)
 	return q->limits.max_segment_size;
 }
 
+static inline unsigned int queue_max_zone_append_sectors(const struct request_queue *q)
+{
+	return q->limits.max_zone_append_sectors;
+}
+
 static inline unsigned queue_logical_block_size(const struct request_queue *q)
 {
 	int retval = 512;
@@ -1551,6 +1583,12 @@ struct blk_integrity *bdev_get_integrity(struct block_device *bdev)
 	return blk_get_integrity(bdev->bd_disk);
 }
 
+static inline bool
+blk_integrity_queue_supports_integrity(struct request_queue *q)
+{
+	return q->integrity.profile;
+}
+
 static inline bool blk_integrity_rq(struct request *rq)
 {
 	return rq->cmd_flags & REQ_INTEGRITY;
@@ -1631,6 +1669,11 @@ static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
 {
 	return NULL;
 }
+static inline bool
+blk_integrity_queue_supports_integrity(struct request_queue *q)
+{
+	return false;
+}
 static inline int blk_integrity_compare(struct gendisk *a, struct gendisk *b)
 {
 	return 0;
@@ -1682,6 +1725,25 @@ static inline struct bio_vec *rq_integrity_vec(struct request *rq)
 
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
+#ifdef CONFIG_BLK_INLINE_ENCRYPTION
+
+bool blk_ksm_register(struct blk_keyslot_manager *ksm, struct request_queue *q);
+
+void blk_ksm_unregister(struct request_queue *q);
+
+#else /* CONFIG_BLK_INLINE_ENCRYPTION */
+
+static inline bool blk_ksm_register(struct blk_keyslot_manager *ksm,
+				    struct request_queue *q)
+{
+	return true;
+}
+
+static inline void blk_ksm_unregister(struct request_queue *q) { }
+
+#endif /* CONFIG_BLK_INLINE_ENCRYPTION */
+
+
 struct block_device_operations {
 	int (*open) (struct block_device *, fmode_t);
 	void (*release) (struct gendisk *, fmode_t);
@@ -1719,6 +1781,7 @@ extern int bdev_write_page(struct block_device *, sector_t, struct page *,
 
 #ifdef CONFIG_BLK_DEV_ZONED
 bool blk_req_needs_zone_write_lock(struct request *rq);
+bool blk_req_zone_write_trylock(struct request *rq);
 void __blk_req_zone_write_lock(struct request *rq);
 void __blk_req_zone_write_unlock(struct request *rq);
 
@@ -1809,8 +1872,7 @@ static inline bool blk_needs_flush_plug(struct task_struct *tsk)
 	return false;
 }
 
-static inline int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask,
-				     sector_t *error_sector)
+static inline int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask)
 {
 	return 0;
 }
@@ -1830,4 +1892,32 @@ static inline void blk_wake_io_task(struct task_struct *waiter)
 		wake_up_process(waiter);
 }
 
+#ifdef CONFIG_BLOCK
+unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
+		unsigned int op);
+void disk_end_io_acct(struct gendisk *disk, unsigned int op,
+		unsigned long start_time);
+
+/**
+ * bio_start_io_acct - start I/O accounting for bio based drivers
+ * @bio:	bio to start account for
+ *
+ * Returns the start time that should be passed back to bio_end_io_acct().
+ */
+static inline unsigned long bio_start_io_acct(struct bio *bio)
+{
+	return disk_start_io_acct(bio->bi_disk, bio_sectors(bio), bio_op(bio));
+}
+
+/**
+ * bio_end_io_acct - end I/O accounting for bio based drivers
+ * @bio:	bio to end account for
+ * @start:	start time returned by bio_start_io_acct()
+ */
+static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time)
+{
+	return disk_end_io_acct(bio->bi_disk, bio_op(bio), start_time);
+}
+#endif /* CONFIG_BLOCK */
+
 #endif
diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index a81c13ac1972..ac0c7299d5b8 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -12,8 +12,17 @@
 #include <linux/errno.h>
 #include <linux/mm.h>
 
-/*
- * was unsigned short, but we might as well be ready for > 64kB I/O pages
+/**
+ * struct bio_vec - a contiguous range of physical memory addresses
+ * @bv_page:   First page associated with the address range.
+ * @bv_len:    Number of bytes in the address range.
+ * @bv_offset: Start of the address range relative to the start of @bv_page.
+ *
+ * The following holds for a bvec if n * PAGE_SIZE < bv_offset + bv_len:
+ *
+ *   nth_page(@bv_page, n) == @bv_page + n
+ *
+ * This holds because page_is_mergeable() checks the above property.
  */
 struct bio_vec {
 	struct page	*bv_page;
diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h
index 528271c60018..8543fa59da72 100644
--- a/include/linux/cdrom.h
+++ b/include/linux/cdrom.h
@@ -94,6 +94,11 @@ struct cdrom_device_ops {
 			       struct packet_command *);
 };
 
+int cdrom_multisession(struct cdrom_device_info *cdi,
+		struct cdrom_multisession *info);
+int cdrom_read_tocentry(struct cdrom_device_info *cdi,
+		struct cdrom_tocentry *entry);
+
 /* the general block_device operations structure: */
 extern int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev,
 			fmode_t mode);
@@ -104,7 +109,7 @@ extern unsigned int cdrom_check_events(struct cdrom_device_info *cdi,
 				       unsigned int clearing);
 extern int cdrom_media_changed(struct cdrom_device_info *);
 
-extern int register_cdrom(struct cdrom_device_info *cdi);
+extern int register_cdrom(struct gendisk *disk, struct cdrom_device_info *cdi);
 extern void unregister_cdrom(struct cdrom_device_info *cdi);
 
 typedef struct {
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 77d70b633531..24b3a77810b6 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -152,6 +152,7 @@ enum cpuhp_state {
 	CPUHP_AP_SMPBOOT_THREADS,
 	CPUHP_AP_X86_VDSO_VMA_ONLINE,
 	CPUHP_AP_IRQ_AFFINITY_ONLINE,
+	CPUHP_AP_BLK_MQ_ONLINE,
 	CPUHP_AP_ARM_MVEBU_SYNC_CLOCKS,
 	CPUHP_AP_X86_INTEL_EPB_ONLINE,
 	CPUHP_AP_PERF_ONLINE,
diff --git a/include/linux/device.h b/include/linux/device.h
index ac8e37cd716a..15460a5ac024 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -884,10 +884,6 @@ extern bool device_is_bound(struct device *dev);
 /*
  * Easy functions for dynamically creating devices on the fly
  */
-extern __printf(5, 0)
-struct device *device_create_vargs(struct class *cls, struct device *parent,
-				   dev_t devt, void *drvdata,
-				   const char *fmt, va_list vargs);
 extern __printf(5, 6)
 struct device *device_create(struct class *cls, struct device *parent,
 			     dev_t devt, void *drvdata,
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 901bda352dcb..bacc40a0bdf3 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -39,7 +39,7 @@ struct elevator_mq_ops {
 	void (*request_merged)(struct request_queue *, struct request *, enum elv_merge);
 	void (*requests_merged)(struct request_queue *, struct request *, struct request *);
 	void (*limit_depth)(unsigned int, struct blk_mq_alloc_data *);
-	void (*prepare_request)(struct request *, struct bio *bio);
+	void (*prepare_request)(struct request *);
 	void (*finish_request)(struct request *);
 	void (*insert_requests)(struct blk_mq_hw_ctx *, struct list_head *, bool);
 	struct request *(*dispatch_request)(struct blk_mq_hw_ctx *);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ef6acd2062eb..4fdd148dd763 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2591,7 +2591,6 @@ extern struct kmem_cache *names_cachep;
 #ifdef CONFIG_BLOCK
 extern int register_blkdev(unsigned int, const char *);
 extern void unregister_blkdev(unsigned int, const char *);
-extern void bdev_unhash_inode(dev_t dev);
 extern struct block_device *bdget(dev_t);
 extern struct block_device *bdgrab(struct block_device *bdev);
 extern void bd_set_size(struct block_device *, loff_t size);
@@ -2733,7 +2732,6 @@ extern bool is_bad_inode(struct inode *);
 extern int revalidate_disk(struct gendisk *);
 extern int check_disk_change(struct block_device *);
 extern int __invalidate_device(struct block_device *, bool);
-extern int invalidate_partition(struct gendisk *, int);
 #endif
 unsigned long invalidate_mapping_pages(struct address_space *mapping,
 					pgoff_t start, pgoff_t end);
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 9b3fffdf4011..f0d6d77309a5 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -39,15 +39,6 @@ extern struct class block_class;
 #include <linux/fs.h>
 #include <linux/workqueue.h>
 
-struct disk_stats {
-	u64 nsecs[NR_STAT_GROUPS];
-	unsigned long sectors[NR_STAT_GROUPS];
-	unsigned long ios[NR_STAT_GROUPS];
-	unsigned long merges[NR_STAT_GROUPS];
-	unsigned long io_ticks;
-	local_t in_flight[2];
-};
-
 #define PARTITION_META_INFO_VOLNAMELTH	64
 /*
  * Enough for the string representation of any kind of UUID plus NULL.
@@ -68,7 +59,13 @@ struct hd_struct {
 	 * can be non-atomic on 32bit machines with 64bit sector_t.
 	 */
 	sector_t nr_sects;
+#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
 	seqcount_t nr_sects_seq;
+#endif
+	unsigned long stamp;
+	struct disk_stats __percpu *dkstats;
+	struct percpu_ref ref;
+
 	sector_t alignment_offset;
 	unsigned int discard_alignment;
 	struct device __dev;
@@ -78,13 +75,6 @@ struct hd_struct {
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 	int make_it_fail;
 #endif
-	unsigned long stamp;
-#ifdef	CONFIG_SMP
-	struct disk_stats __percpu *dkstats;
-#else
-	struct disk_stats dkstats;
-#endif
-	struct percpu_ref ref;
 	struct rcu_work rcu_work;
 };
 
@@ -217,11 +207,20 @@ struct gendisk {
 #ifdef  CONFIG_BLK_DEV_INTEGRITY
 	struct kobject integrity_kobj;
 #endif	/* CONFIG_BLK_DEV_INTEGRITY */
+#if IS_ENABLED(CONFIG_CDROM)
+	struct cdrom_device_info *cdi;
+#endif
 	int node_id;
 	struct badblocks *bb;
 	struct lockdep_map lockdep_map;
 };
 
+#if IS_REACHABLE(CONFIG_CDROM)
+#define disk_to_cdi(disk)	((disk)->cdi)
+#else
+#define disk_to_cdi(disk)	NULL
+#endif
+
 static inline struct gendisk *part_to_disk(struct hd_struct *part)
 {
 	if (likely(part)) {
@@ -265,6 +264,13 @@ static inline void disk_put_part(struct hd_struct *part)
 		put_device(part_to_dev(part));
 }
 
+static inline void hd_sects_seq_init(struct hd_struct *p)
+{
+#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
+	seqcount_init(&p->nr_sects_seq);
+#endif
+}
+
 /*
  * Smarter partition iterator without context limits.
  */
@@ -339,7 +345,7 @@ extern dev_t blk_lookup_devt(const char *name, int partno);
 
 int bdev_disk_changed(struct block_device *bdev, bool invalidate);
 int blk_add_partitions(struct gendisk *disk, struct block_device *bdev);
-int blk_drop_partitions(struct gendisk *disk, struct block_device *bdev);
+int blk_drop_partitions(struct block_device *bdev);
 extern void printk_all_partitions(void);
 
 extern struct gendisk *__alloc_disk_node(int minors, int node_id);
diff --git a/include/linux/keyslot-manager.h b/include/linux/keyslot-manager.h
new file mode 100644
index 000000000000..18f3f5346843
--- /dev/null
+++ b/include/linux/keyslot-manager.h
@@ -0,0 +1,106 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright 2019 Google LLC
+ */
+
+#ifndef __LINUX_KEYSLOT_MANAGER_H
+#define __LINUX_KEYSLOT_MANAGER_H
+
+#include <linux/bio.h>
+#include <linux/blk-crypto.h>
+
+struct blk_keyslot_manager;
+
+/**
+ * struct blk_ksm_ll_ops - functions to manage keyslots in hardware
+ * @keyslot_program:	Program the specified key into the specified slot in the
+ *			inline encryption hardware.
+ * @keyslot_evict:	Evict key from the specified keyslot in the hardware.
+ *			The key is provided so that e.g. dm layers can evict
+ *			keys from the devices that they map over.
+ *			Returns 0 on success, -errno otherwise.
+ *
+ * This structure should be provided by storage device drivers when they set up
+ * a keyslot manager - this structure holds the function ptrs that the keyslot
+ * manager will use to manipulate keyslots in the hardware.
+ */
+struct blk_ksm_ll_ops {
+	int (*keyslot_program)(struct blk_keyslot_manager *ksm,
+			       const struct blk_crypto_key *key,
+			       unsigned int slot);
+	int (*keyslot_evict)(struct blk_keyslot_manager *ksm,
+			     const struct blk_crypto_key *key,
+			     unsigned int slot);
+};
+
+struct blk_keyslot_manager {
+	/*
+	 * The struct blk_ksm_ll_ops that this keyslot manager will use
+	 * to perform operations like programming and evicting keys on the
+	 * device
+	 */
+	struct blk_ksm_ll_ops ksm_ll_ops;
+
+	/*
+	 * The maximum number of bytes supported for specifying the data unit
+	 * number.
+	 */
+	unsigned int max_dun_bytes_supported;
+
+	/*
+	 * Array of size BLK_ENCRYPTION_MODE_MAX of bitmasks that represents
+	 * whether a crypto mode and data unit size are supported. The i'th
+	 * bit of crypto_mode_supported[crypto_mode] is set iff a data unit
+	 * size of (1 << i) is supported. We only support data unit sizes
+	 * that are powers of 2.
+	 */
+	unsigned int crypto_modes_supported[BLK_ENCRYPTION_MODE_MAX];
+
+	/* Device for runtime power management (NULL if none) */
+	struct device *dev;
+
+	/* Here onwards are *private* fields for internal keyslot manager use */
+
+	unsigned int num_slots;
+
+	/* Protects programming and evicting keys from the device */
+	struct rw_semaphore lock;
+
+	/* List of idle slots, with least recently used slot at front */
+	wait_queue_head_t idle_slots_wait_queue;
+	struct list_head idle_slots;
+	spinlock_t idle_slots_lock;
+
+	/*
+	 * Hash table which maps struct *blk_crypto_key to keyslots, so that we
+	 * can find a key's keyslot in O(1) time rather than O(num_slots).
+	 * Protected by 'lock'.
+	 */
+	struct hlist_head *slot_hashtable;
+	unsigned int log_slot_ht_size;
+
+	/* Per-keyslot data */
+	struct blk_ksm_keyslot *slots;
+};
+
+int blk_ksm_init(struct blk_keyslot_manager *ksm, unsigned int num_slots);
+
+blk_status_t blk_ksm_get_slot_for_key(struct blk_keyslot_manager *ksm,
+				      const struct blk_crypto_key *key,
+				      struct blk_ksm_keyslot **slot_ptr);
+
+unsigned int blk_ksm_get_slot_idx(struct blk_ksm_keyslot *slot);
+
+void blk_ksm_put_slot(struct blk_ksm_keyslot *slot);
+
+bool blk_ksm_crypto_cfg_supported(struct blk_keyslot_manager *ksm,
+				  const struct blk_crypto_config *cfg);
+
+int blk_ksm_evict_key(struct blk_keyslot_manager *ksm,
+		      const struct blk_crypto_key *key);
+
+void blk_ksm_reprogram_all_keys(struct blk_keyslot_manager *ksm);
+
+void blk_ksm_destroy(struct blk_keyslot_manager *ksm);
+
+#endif /* __LINUX_KEYSLOT_MANAGER_H */
diff --git a/include/linux/libata.h b/include/linux/libata.h
index cffa4714bfa8..af832852e620 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -1092,6 +1092,7 @@ extern int ata_scsi_ioctl(struct scsi_device *dev, unsigned int cmd,
 #define ATA_SCSI_COMPAT_IOCTL /* empty */
 #endif
 extern int ata_scsi_queuecmd(struct Scsi_Host *h, struct scsi_cmnd *cmd);
+bool ata_scsi_dma_need_drain(struct request *rq);
 extern int ata_sas_scsi_ioctl(struct ata_port *ap, struct scsi_device *dev,
 			    unsigned int cmd, void __user *arg);
 extern bool ata_link_online(struct ata_link *link);
@@ -1387,6 +1388,7 @@ extern struct device_attribute *ata_common_sdev_attrs[];
 	.ioctl			= ata_scsi_ioctl,		\
 	ATA_SCSI_COMPAT_IOCTL					\
 	.queuecommand		= ata_scsi_queuecmd,		\
+	.dma_need_drain		= ata_scsi_dma_need_drain,	\
 	.can_queue		= ATA_DEF_QUEUE,		\
 	.tag_alloc_policy	= BLK_TAG_ALLOC_RR,		\
 	.this_id		= ATA_SHT_THIS_ID,		\
diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h
index ece607607a86..24125778ef3e 100644
--- a/include/linux/part_stat.h
+++ b/include/linux/part_stat.h
@@ -4,21 +4,25 @@
 
 #include <linux/genhd.h>
 
+struct disk_stats {
+	u64 nsecs[NR_STAT_GROUPS];
+	unsigned long sectors[NR_STAT_GROUPS];
+	unsigned long ios[NR_STAT_GROUPS];
+	unsigned long merges[NR_STAT_GROUPS];
+	unsigned long io_ticks;
+	local_t in_flight[2];
+};
+
 /*
  * Macros to operate on percpu disk statistics:
  *
- * {disk|part|all}_stat_{add|sub|inc|dec}() modify the stat counters
- * and should be called between disk_stat_lock() and
- * disk_stat_unlock().
+ * {disk|part|all}_stat_{add|sub|inc|dec}() modify the stat counters and should
+ * be called between disk_stat_lock() and disk_stat_unlock().
  *
  * part_stat_read() can be called at any time.
- *
- * part_stat_{add|set_all}() and {init|free}_part_stats are for
- * internal use only.
  */
-#ifdef	CONFIG_SMP
-#define part_stat_lock()	({ rcu_read_lock(); get_cpu(); })
-#define part_stat_unlock()	do { put_cpu(); rcu_read_unlock(); } while (0)
+#define part_stat_lock()	preempt_disable()
+#define part_stat_unlock()	preempt_enable()
 
 #define part_stat_get_cpu(part, field, cpu)				\
 	(per_cpu_ptr((part)->dkstats, (cpu))->field)
@@ -44,50 +48,13 @@ static inline void part_stat_set_all(struct hd_struct *part, int value)
 				sizeof(struct disk_stats));
 }
 
-static inline int init_part_stats(struct hd_struct *part)
-{
-	part->dkstats = alloc_percpu(struct disk_stats);
-	if (!part->dkstats)
-		return 0;
-	return 1;
-}
-
-static inline void free_part_stats(struct hd_struct *part)
-{
-	free_percpu(part->dkstats);
-}
-
-#else /* !CONFIG_SMP */
-#define part_stat_lock()	({ rcu_read_lock(); 0; })
-#define part_stat_unlock()	rcu_read_unlock()
-
-#define part_stat_get(part, field)		((part)->dkstats.field)
-#define part_stat_get_cpu(part, field, cpu)	part_stat_get(part, field)
-#define part_stat_read(part, field)		part_stat_get(part, field)
-
-static inline void part_stat_set_all(struct hd_struct *part, int value)
-{
-	memset(&part->dkstats, value, sizeof(struct disk_stats));
-}
-
-static inline int init_part_stats(struct hd_struct *part)
-{
-	return 1;
-}
-
-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(part, field, addnd)				\
-	(part_stat_get(part, field) += (addnd))
+	__this_cpu_add((part)->dkstats->field, addnd)
 
 #define part_stat_add(part, field, addnd)	do {			\
 	__part_stat_add((part), field, addnd);				\
diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h
index 80ac89e47b47..f93c0b800790 100644
--- a/include/scsi/scsi_cmnd.h
+++ b/include/scsi/scsi_cmnd.h
@@ -142,6 +142,7 @@ struct scsi_cmnd {
 	unsigned long state;	/* Command completion state */
 
 	unsigned char tag;	/* SCSI-II queued command tag */
+	unsigned int extra_len;	/* length of alignment and padding */
 };
 
 /*
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index c3cba2aaf934..bc5909033d13 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -229,6 +229,9 @@ struct scsi_device {
 	struct scsi_device_handler *handler;
 	void			*handler_data;
 
+	size_t			dma_drain_len;
+	void			*dma_drain_buf;
+
 	unsigned char		access_state;
 	struct mutex		state_mutex;
 	enum scsi_device_state sdev_state;
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 822e8cda8d9b..46ef8cccc982 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -271,6 +271,13 @@ struct scsi_host_template {
 	int (* map_queues)(struct Scsi_Host *shost);
 
 	/*
+	 * Check if scatterlists need to be padded for DMA draining.
+	 *
+	 * Status: OPTIONAL
+	 */
+	bool (* dma_need_drain)(struct request *rq);
+
+	/*
 	 * This function determines the BIOS parameters for a given
 	 * harddisk.  These tend to be numbers that are made up by
 	 * the host adapter.  Parameters: