Merge branch 'for-4.13/block' of git://git.kernel.dk/linux-block

Pull core block/IO updates from Jens Axboe:
 "This is the main pull request for the block layer for 4.13. Not a huge
  round in terms of features, but there's a lot of churn related to some
  core cleanups.

  Note this depends on the UUID tree pull request, that Christoph
  already sent out.

  This pull request contains:

   - A series from Christoph, unifying the error/stats codes in the
     block layer. We now use blk_status_t everywhere, instead of using
     different schemes for different places.

   - Also from Christoph, some cleanups around request allocation and IO
     scheduler interactions in blk-mq.

   - And yet another series from Christoph, cleaning up how we handle
     and do bounce buffering in the block layer.

   - A blk-mq debugfs series from Bart, further improving on the support
     we have for exporting internal information to aid debugging IO
     hangs or stalls.

   - Also from Bart, a series that cleans up the request initialization
     differences across types of devices.

   - A series from Goldwyn Rodrigues, allowing the block layer to return
     failure if we will block and the user asked for non-blocking.

   - Patch from Hannes for supporting setting loop devices block size to
     that of the underlying device.

   - Two series of patches from Javier, fixing various issues with
     lightnvm, particular around pblk.

   - A series from me, adding support for write hints. This comes with
     NVMe support as well, so applications can help guide data placement
     on flash to improve performance, latencies, and write
     amplification.

   - A series from Ming, improving and hardening blk-mq support for
     stopping/starting and quiescing hardware queues.

   - Two pull requests for NVMe updates. Nothing major on the feature
     side, but lots of cleanups and bug fixes. From the usual crew.

   - A series from Neil Brown, greatly improving the bio rescue set
     support. Most notably, this kills the bio rescue work queues, if we
     don't really need them.

   - Lots of other little bug fixes that are all over the place"

* 'for-4.13/block' of git://git.kernel.dk/linux-block: (217 commits)
  lightnvm: pblk: set line bitmap check under debug
  lightnvm: pblk: verify that cache read is still valid
  lightnvm: pblk: add initialization check
  lightnvm: pblk: remove target using async. I/Os
  lightnvm: pblk: use vmalloc for GC data buffer
  lightnvm: pblk: use right metadata buffer for recovery
  lightnvm: pblk: schedule if data is not ready
  lightnvm: pblk: remove unused return variable
  lightnvm: pblk: fix double-free on pblk init
  lightnvm: pblk: fix bad le64 assignations
  nvme: Makefile: remove dead build rule
  blk-mq: map all HWQ also in hyperthreaded system
  nvmet-rdma: register ib_client to not deadlock in device removal
  nvme_fc: fix error recovery on link down.
  nvmet_fc: fix crashes on bad opcodes
  nvme_fc: Fix crash when nvme controller connection fails.
  nvme_fc: replace ioabort msleep loop with completion
  nvme_fc: fix double calls to nvme_cleanup_cmd()
  nvme-fabrics: verify that a controller returns the correct NQN
  nvme: simplify nvme_dev_attrs_are_visible
  ...

20 files changed, 299 insertions, 87 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index a7e29fa0981f..664a27da276d 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -118,7 +118,6 @@ static inline void *bio_data(struct bio *bio)
 /*
  * will die
  */
-#define bio_to_phys(bio)	(page_to_phys(bio_page((bio))) + (unsigned long) bio_offset((bio)))
 #define bvec_to_phys(bv)	(page_to_phys((bv)->bv_page) + (unsigned long) (bv)->bv_offset)
 
 /*
@@ -373,8 +372,11 @@ static inline struct bio *bio_next_split(struct bio *bio, int sectors,
 	return bio_split(bio, sectors, gfp, bs);
 }
 
-extern struct bio_set *bioset_create(unsigned int, unsigned int);
-extern struct bio_set *bioset_create_nobvec(unsigned int, unsigned int);
+extern struct bio_set *bioset_create(unsigned int, unsigned int, int flags);
+enum {
+	BIOSET_NEED_BVECS = BIT(0),
+	BIOSET_NEED_RESCUER = BIT(1),
+};
 extern void bioset_free(struct bio_set *);
 extern mempool_t *biovec_create_pool(int pool_entries);
 
@@ -392,11 +394,6 @@ static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs)
 	return bio_alloc_bioset(gfp_mask, nr_iovecs, fs_bio_set);
 }
 
-static inline struct bio *bio_clone(struct bio *bio, gfp_t gfp_mask)
-{
-	return bio_clone_bioset(bio, gfp_mask, fs_bio_set);
-}
-
 static inline struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned int nr_iovecs)
 {
 	return bio_alloc_bioset(gfp_mask, nr_iovecs, NULL);
@@ -414,7 +411,13 @@ extern void bio_endio(struct bio *);
 
 static inline void bio_io_error(struct bio *bio)
 {
-	bio->bi_error = -EIO;
+	bio->bi_status = BLK_STS_IOERR;
+	bio_endio(bio);
+}
+
+static inline void bio_wouldblock_error(struct bio *bio)
+{
+	bio->bi_status = BLK_STS_AGAIN;
 	bio_endio(bio);
 }
 
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index fcd641032f8d..23d32ff0b462 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -39,8 +39,6 @@ struct blk_mq_hw_ctx {
 	struct blk_mq_tags	*tags;
 	struct blk_mq_tags	*sched_tags;
 
-	struct srcu_struct	queue_rq_srcu;
-
 	unsigned long		queued;
 	unsigned long		run;
 #define BLK_MQ_MAX_DISPATCH_ORDER	7
@@ -62,6 +60,9 @@ struct blk_mq_hw_ctx {
 	struct dentry		*debugfs_dir;
 	struct dentry		*sched_debugfs_dir;
 #endif
+
+	/* Must be the last member - see also blk_mq_hw_ctx_size(). */
+	struct srcu_struct	queue_rq_srcu[0];
 };
 
 struct blk_mq_tag_set {
@@ -87,7 +88,8 @@ struct blk_mq_queue_data {
 	bool last;
 };
 
-typedef int (queue_rq_fn)(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *);
+typedef blk_status_t (queue_rq_fn)(struct blk_mq_hw_ctx *,
+		const struct blk_mq_queue_data *);
 typedef enum blk_eh_timer_return (timeout_fn)(struct request *, bool);
 typedef int (init_hctx_fn)(struct blk_mq_hw_ctx *, void *, unsigned int);
 typedef void (exit_hctx_fn)(struct blk_mq_hw_ctx *, unsigned int);
@@ -142,6 +144,8 @@ struct blk_mq_ops {
 	init_request_fn		*init_request;
 	exit_request_fn		*exit_request;
 	reinit_request_fn	*reinit_request;
+	/* Called from inside blk_get_request() */
+	void (*initialize_rq_fn)(struct request *rq);
 
 	map_queues_fn		*map_queues;
 
@@ -155,10 +159,6 @@ struct blk_mq_ops {
 };
 
 enum {
-	BLK_MQ_RQ_QUEUE_OK	= 0,	/* queued fine */
-	BLK_MQ_RQ_QUEUE_BUSY	= 1,	/* requeue IO for later */
-	BLK_MQ_RQ_QUEUE_ERROR	= 2,	/* end IO with error */
-
 	BLK_MQ_F_SHOULD_MERGE	= 1 << 0,
 	BLK_MQ_F_TAG_SHARED	= 1 << 1,
 	BLK_MQ_F_SG_MERGE	= 1 << 2,
@@ -204,10 +204,10 @@ enum {
 	BLK_MQ_REQ_INTERNAL	= (1 << 2), /* allocate internal/sched tag */
 };
 
-struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
+struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
 		unsigned int flags);
-struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int op,
-		unsigned int flags, unsigned int hctx_idx);
+struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
+		unsigned int op, unsigned int flags, unsigned int hctx_idx);
 struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag);
 
 enum {
@@ -230,8 +230,8 @@ static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag)
 
 int blk_mq_request_started(struct request *rq);
 void blk_mq_start_request(struct request *rq);
-void blk_mq_end_request(struct request *rq, int error);
-void __blk_mq_end_request(struct request *rq, int error);
+void blk_mq_end_request(struct request *rq, blk_status_t error);
+void __blk_mq_end_request(struct request *rq, blk_status_t error);
 
 void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list);
 void blk_mq_add_to_requeue_list(struct request *rq, bool at_head,
@@ -247,6 +247,8 @@ void blk_mq_stop_hw_queues(struct request_queue *q);
 void blk_mq_start_hw_queues(struct request_queue *q);
 void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
 void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async);
+void blk_mq_quiesce_queue(struct request_queue *q);
+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);
@@ -264,6 +266,8 @@ int blk_mq_reinit_tagset(struct blk_mq_tag_set *set);
 int blk_mq_map_queues(struct blk_mq_tag_set *set);
 void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues);
 
+void blk_mq_quiesce_queue_nowait(struct request_queue *q);
+
 /*
  * Driver command data is immediately after the request. So subtract request
  * size to get back to the original request, add request size to get the PDU.
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 61339bc44400..d2eb87c84d82 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -17,6 +17,27 @@ struct io_context;
 struct cgroup_subsys_state;
 typedef void (bio_end_io_t) (struct bio *);
 
+/*
+ * Block error status values.  See block/blk-core:blk_errors for the details.
+ */
+typedef u8 __bitwise blk_status_t;
+#define	BLK_STS_OK 0
+#define BLK_STS_NOTSUPP		((__force blk_status_t)1)
+#define BLK_STS_TIMEOUT		((__force blk_status_t)2)
+#define BLK_STS_NOSPC		((__force blk_status_t)3)
+#define BLK_STS_TRANSPORT	((__force blk_status_t)4)
+#define BLK_STS_TARGET		((__force blk_status_t)5)
+#define BLK_STS_NEXUS		((__force blk_status_t)6)
+#define BLK_STS_MEDIUM		((__force blk_status_t)7)
+#define BLK_STS_PROTECTION	((__force blk_status_t)8)
+#define BLK_STS_RESOURCE	((__force blk_status_t)9)
+#define BLK_STS_IOERR		((__force blk_status_t)10)
+
+/* hack for device mapper, don't use elsewhere: */
+#define BLK_STS_DM_REQUEUE    ((__force blk_status_t)11)
+
+#define BLK_STS_AGAIN		((__force blk_status_t)12)
+
 struct blk_issue_stat {
 	u64 stat;
 };
@@ -28,13 +49,14 @@ struct blk_issue_stat {
 struct bio {
 	struct bio		*bi_next;	/* request queue link */
 	struct block_device	*bi_bdev;
-	int			bi_error;
+	blk_status_t		bi_status;
 	unsigned int		bi_opf;		/* bottom bits req flags,
 						 * top bits REQ_OP. Use
 						 * accessors.
 						 */
 	unsigned short		bi_flags;	/* status, etc and bvec pool number */
 	unsigned short		bi_ioprio;
+	unsigned short		bi_write_hint;
 
 	struct bvec_iter	bi_iter;
 
@@ -205,6 +227,7 @@ enum req_flag_bits {
 	/* command specific flags for REQ_OP_WRITE_ZEROES: */
 	__REQ_NOUNMAP,		/* do not free blocks when zeroing */
 
+	__REQ_NOWAIT,           /* Don't wait if request will block */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -223,6 +246,7 @@ enum req_flag_bits {
 #define REQ_BACKGROUND		(1ULL << __REQ_BACKGROUND)
 
 #define REQ_NOUNMAP		(1ULL << __REQ_NOUNMAP)
+#define REQ_NOWAIT		(1ULL << __REQ_NOWAIT)
 
 #define REQ_FAILFAST_MASK \
 	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 1ddd36bd2173..25f6a0cb27d3 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -55,7 +55,7 @@ struct blk_stat_callback;
  */
 #define BLKCG_MAX_POLS		3
 
-typedef void (rq_end_io_fn)(struct request *, int);
+typedef void (rq_end_io_fn)(struct request *, blk_status_t);
 
 #define BLK_RL_SYNCFULL		(1U << 0)
 #define BLK_RL_ASYNCFULL	(1U << 1)
@@ -225,6 +225,8 @@ struct request {
 
 	unsigned int extra_len;	/* length of alignment and padding */
 
+	unsigned short write_hint;
+
 	unsigned long deadline;
 	struct list_head timeout_list;
 
@@ -412,8 +414,12 @@ struct request_queue {
 	rq_timed_out_fn		*rq_timed_out_fn;
 	dma_drain_needed_fn	*dma_drain_needed;
 	lld_busy_fn		*lld_busy_fn;
+	/* Called just after a request is allocated */
 	init_rq_fn		*init_rq_fn;
+	/* Called just before a request is freed */
 	exit_rq_fn		*exit_rq_fn;
+	/* Called from inside blk_get_request() */
+	void (*initialize_rq_fn)(struct request *rq);
 
 	const struct blk_mq_ops	*mq_ops;
 
@@ -590,6 +596,9 @@ struct request_queue {
 	void			*rq_alloc_data;
 
 	struct work_struct	release_work;
+
+#define BLK_MAX_WRITE_HINTS	5
+	u64			write_hints[BLK_MAX_WRITE_HINTS];
 };
 
 #define QUEUE_FLAG_QUEUED	1	/* uses generic tag queueing */
@@ -622,6 +631,8 @@ struct request_queue {
 #define QUEUE_FLAG_STATS       27	/* track rq completion times */
 #define QUEUE_FLAG_POLL_STATS  28	/* collecting stats for hybrid polling */
 #define QUEUE_FLAG_REGISTERED  29	/* queue has been registered to a disk */
+#define QUEUE_FLAG_SCSI_PASSTHROUGH 30	/* queue supports SCSI commands */
+#define QUEUE_FLAG_QUIESCED    31	/* queue has been quiesced */
 
 #define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_STACKABLE)	|	\
@@ -633,6 +644,13 @@ struct request_queue {
 				 (1 << QUEUE_FLAG_SAME_COMP)	|	\
 				 (1 << QUEUE_FLAG_POLL))
 
+/*
+ * @q->queue_lock is set while a queue is being initialized. Since we know
+ * that no other threads access the queue object before @q->queue_lock has
+ * been set, it is safe to manipulate queue flags without holding the
+ * queue_lock if @q->queue_lock == NULL. See also blk_alloc_queue_node() and
+ * blk_init_allocated_queue().
+ */
 static inline void queue_lockdep_assert_held(struct request_queue *q)
 {
 	if (q->queue_lock)
@@ -712,10 +730,13 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 #define blk_queue_secure_erase(q) \
 	(test_bit(QUEUE_FLAG_SECERASE, &(q)->queue_flags))
 #define blk_queue_dax(q)	test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags)
+#define blk_queue_scsi_passthrough(q)	\
+	test_bit(QUEUE_FLAG_SCSI_PASSTHROUGH, &(q)->queue_flags)
 
 #define blk_noretry_request(rq) \
 	((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)
 
 static inline bool blk_account_rq(struct request *rq)
 {
@@ -814,7 +835,8 @@ static inline bool rq_mergeable(struct request *rq)
 
 static inline bool blk_write_same_mergeable(struct bio *a, struct bio *b)
 {
-	if (bio_data(a) == bio_data(b))
+	if (bio_page(a) == bio_page(b) &&
+	    bio_offset(a) == bio_offset(b))
 		return true;
 
 	return false;
@@ -862,19 +884,6 @@ extern unsigned long blk_max_low_pfn, blk_max_pfn;
 #define BLK_DEFAULT_SG_TIMEOUT	(60 * HZ)
 #define BLK_MIN_SG_TIMEOUT	(7 * HZ)
 
-#ifdef CONFIG_BOUNCE
-extern int init_emergency_isa_pool(void);
-extern void blk_queue_bounce(struct request_queue *q, struct bio **bio);
-#else
-static inline int init_emergency_isa_pool(void)
-{
-	return 0;
-}
-static inline void blk_queue_bounce(struct request_queue *q, struct bio **bio)
-{
-}
-#endif /* CONFIG_MMU */
-
 struct rq_map_data {
 	struct page **pages;
 	int page_order;
@@ -933,7 +942,8 @@ extern void blk_rq_init(struct request_queue *q, struct request *rq);
 extern void blk_init_request_from_bio(struct request *req, struct bio *bio);
 extern void blk_put_request(struct request *);
 extern void __blk_put_request(struct request_queue *, struct request *);
-extern struct request *blk_get_request(struct request_queue *, int, gfp_t);
+extern struct request *blk_get_request(struct request_queue *, unsigned int op,
+				       gfp_t gfp_mask);
 extern void blk_requeue_request(struct request_queue *, struct request *);
 extern int blk_lld_busy(struct request_queue *q);
 extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
@@ -941,12 +951,11 @@ extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
 			     int (*bio_ctr)(struct bio *, struct bio *, void *),
 			     void *data);
 extern void blk_rq_unprep_clone(struct request *rq);
-extern int blk_insert_cloned_request(struct request_queue *q,
+extern blk_status_t blk_insert_cloned_request(struct request_queue *q,
 				     struct request *rq);
 extern int blk_rq_append_bio(struct request *rq, struct bio *bio);
 extern void blk_delay_queue(struct request_queue *, unsigned long);
-extern void blk_queue_split(struct request_queue *, struct bio **,
-			    struct bio_set *);
+extern void blk_queue_split(struct request_queue *, struct bio **);
 extern void blk_recount_segments(struct request_queue *, struct bio *);
 extern int scsi_verify_blk_ioctl(struct block_device *, unsigned int);
 extern int scsi_cmd_blk_ioctl(struct block_device *, fmode_t,
@@ -967,7 +976,6 @@ extern void __blk_run_queue(struct request_queue *q);
 extern void __blk_run_queue_uncond(struct request_queue *q);
 extern void blk_run_queue(struct request_queue *);
 extern void blk_run_queue_async(struct request_queue *q);
-extern void blk_mq_quiesce_queue(struct request_queue *q);
 extern int blk_rq_map_user(struct request_queue *, struct request *,
 			   struct rq_map_data *, void __user *, unsigned long,
 			   gfp_t);
@@ -981,6 +989,9 @@ extern void blk_execute_rq(struct request_queue *, struct gendisk *,
 extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *,
 				  struct request *, int, rq_end_io_fn *);
 
+int blk_status_to_errno(blk_status_t status);
+blk_status_t errno_to_blk_status(int errno);
+
 bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie);
 
 static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
@@ -1113,16 +1124,16 @@ extern struct request *blk_fetch_request(struct request_queue *q);
  * blk_end_request() for parts of the original function.
  * This prevents code duplication in drivers.
  */
-extern bool blk_update_request(struct request *rq, int error,
+extern bool blk_update_request(struct request *rq, blk_status_t error,
 			       unsigned int nr_bytes);
-extern void blk_finish_request(struct request *rq, int error);
-extern bool blk_end_request(struct request *rq, int error,
+extern void blk_finish_request(struct request *rq, blk_status_t error);
+extern bool blk_end_request(struct request *rq, blk_status_t error,
 			    unsigned int nr_bytes);
-extern void blk_end_request_all(struct request *rq, int error);
-extern bool __blk_end_request(struct request *rq, int error,
+extern void blk_end_request_all(struct request *rq, blk_status_t error);
+extern bool __blk_end_request(struct request *rq, blk_status_t error,
 			      unsigned int nr_bytes);
-extern void __blk_end_request_all(struct request *rq, int error);
-extern bool __blk_end_request_cur(struct request *rq, int error);
+extern void __blk_end_request_all(struct request *rq, blk_status_t error);
+extern bool __blk_end_request_cur(struct request *rq, blk_status_t error);
 
 extern void blk_complete_request(struct request *);
 extern void __blk_complete_request(struct request *);
@@ -1374,11 +1385,6 @@ enum blk_default_limits {
 
 #define blkdev_entry_to_request(entry) list_entry((entry), struct request, queuelist)
 
-static inline unsigned long queue_bounce_pfn(struct request_queue *q)
-{
-	return q->limits.bounce_pfn;
-}
-
 static inline unsigned long queue_segment_boundary(struct request_queue *q)
 {
 	return q->limits.seg_boundary_mask;
@@ -1780,7 +1786,7 @@ struct blk_integrity_iter {
 	const char		*disk_name;
 };
 
-typedef int (integrity_processing_fn) (struct blk_integrity_iter *);
+typedef blk_status_t (integrity_processing_fn) (struct blk_integrity_iter *);
 
 struct blk_integrity_profile {
 	integrity_processing_fn		*generate_fn;
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index f4c639c0c362..456da5017b32 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -72,9 +72,9 @@ typedef void (*dm_release_clone_request_fn) (struct request *clone);
  * 2   : The target wants to push back the io
  */
 typedef int (*dm_endio_fn) (struct dm_target *ti,
-			    struct bio *bio, int error);
+			    struct bio *bio, blk_status_t *error);
 typedef int (*dm_request_endio_fn) (struct dm_target *ti,
-				    struct request *clone, int error,
+				    struct request *clone, blk_status_t error,
 				    union map_info *map_context);
 
 typedef void (*dm_presuspend_fn) (struct dm_target *ti);
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 0e306c5a86d6..5bc8f8682a3e 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -104,8 +104,9 @@ struct elevator_mq_ops {
 	int (*request_merge)(struct request_queue *q, struct request **, struct bio *);
 	void (*request_merged)(struct request_queue *, struct request *, enum elv_merge);
 	void (*requests_merged)(struct request_queue *, struct request *, struct request *);
-	struct request *(*get_request)(struct request_queue *, unsigned int, struct blk_mq_alloc_data *);
-	void (*put_request)(struct request *);
+	void (*limit_depth)(unsigned int, struct blk_mq_alloc_data *);
+	void (*prepare_request)(struct request *, struct bio *bio);
+	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 *);
 	bool (*has_work)(struct blk_mq_hw_ctx *);
@@ -114,8 +115,6 @@ struct elevator_mq_ops {
 	void (*requeue_request)(struct request *);
 	struct request *(*former_request)(struct request_queue *, struct request *);
 	struct request *(*next_request)(struct request_queue *, struct request *);
-	int (*get_rq_priv)(struct request_queue *, struct request *, struct bio *);
-	void (*put_rq_priv)(struct request_queue *, struct request *);
 	void (*init_icq)(struct io_cq *);
 	void (*exit_icq)(struct io_cq *);
 };
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3e68cabb8457..65adbddb3163 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -20,6 +20,7 @@
 #include <linux/rwsem.h>
 #include <linux/capability.h>
 #include <linux/semaphore.h>
+#include <linux/fcntl.h>
 #include <linux/fiemap.h>
 #include <linux/rculist_bl.h>
 #include <linux/atomic.h>
@@ -143,6 +144,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 /* File was opened by fanotify and shouldn't generate fanotify events */
 #define FMODE_NONOTIFY		((__force fmode_t)0x4000000)
 
+/* File is capable of returning -EAGAIN if AIO will block */
+#define FMODE_AIO_NOWAIT	((__force fmode_t)0x8000000)
+
 /*
  * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector
  * that indicates that they should check the contents of the iovec are
@@ -262,6 +266,18 @@ struct page;
 struct address_space;
 struct writeback_control;
 
+/*
+ * Write life time hint values.
+ */
+enum rw_hint {
+	WRITE_LIFE_NOT_SET	= 0,
+	WRITE_LIFE_NONE		= RWH_WRITE_LIFE_NONE,
+	WRITE_LIFE_SHORT	= RWH_WRITE_LIFE_SHORT,
+	WRITE_LIFE_MEDIUM	= RWH_WRITE_LIFE_MEDIUM,
+	WRITE_LIFE_LONG		= RWH_WRITE_LIFE_LONG,
+	WRITE_LIFE_EXTREME	= RWH_WRITE_LIFE_EXTREME,
+};
+
 #define IOCB_EVENTFD		(1 << 0)
 #define IOCB_APPEND		(1 << 1)
 #define IOCB_DIRECT		(1 << 2)
@@ -269,6 +285,7 @@ struct writeback_control;
 #define IOCB_DSYNC		(1 << 4)
 #define IOCB_SYNC		(1 << 5)
 #define IOCB_WRITE		(1 << 6)
+#define IOCB_NOWAIT		(1 << 7)
 
 struct kiocb {
 	struct file		*ki_filp;
@@ -276,6 +293,7 @@ struct kiocb {
 	void (*ki_complete)(struct kiocb *iocb, long ret, long ret2);
 	void			*private;
 	int			ki_flags;
+	enum rw_hint		ki_hint;
 };
 
 static inline bool is_sync_kiocb(struct kiocb *kiocb)
@@ -283,16 +301,6 @@ static inline bool is_sync_kiocb(struct kiocb *kiocb)
 	return kiocb->ki_complete == NULL;
 }
 
-static inline int iocb_flags(struct file *file);
-
-static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
-{
-	*kiocb = (struct kiocb) {
-		.ki_filp = filp,
-		.ki_flags = iocb_flags(filp),
-	};
-}
-
 /*
  * "descriptor" for what we're up to with a read.
  * This allows us to use the same read code yet
@@ -593,6 +601,7 @@ struct inode {
 	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
 	unsigned short          i_bytes;
 	unsigned int		i_blkbits;
+	enum rw_hint		i_write_hint;
 	blkcnt_t		i_blocks;
 
 #ifdef __NEED_I_SIZE_ORDERED
@@ -847,6 +856,7 @@ struct file {
 	 * Must not be taken from IRQ context.
 	 */
 	spinlock_t		f_lock;
+	enum rw_hint		f_write_hint;
 	atomic_long_t		f_count;
 	unsigned int 		f_flags;
 	fmode_t			f_mode;
@@ -1022,8 +1032,6 @@ struct file_lock_context {
 #define OFFT_OFFSET_MAX	INT_LIMIT(off_t)
 #endif
 
-#include <linux/fcntl.h>
-
 extern void send_sigio(struct fown_struct *fown, int fd, int band);
 
 /*
@@ -1874,6 +1882,25 @@ static inline bool HAS_UNMAPPED_ID(struct inode *inode)
 	return !uid_valid(inode->i_uid) || !gid_valid(inode->i_gid);
 }
 
+static inline enum rw_hint file_write_hint(struct file *file)
+{
+	if (file->f_write_hint != WRITE_LIFE_NOT_SET)
+		return file->f_write_hint;
+
+	return file_inode(file)->i_write_hint;
+}
+
+static inline int iocb_flags(struct file *file);
+
+static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
+{
+	*kiocb = (struct kiocb) {
+		.ki_filp = filp,
+		.ki_flags = iocb_flags(filp),
+		.ki_hint = file_write_hint(filp),
+	};
+}
+
 /*
  * Inode state bits.  Protected by inode->i_lock
  *
@@ -2518,6 +2545,8 @@ extern int filemap_fdatawait(struct address_space *);
 extern void filemap_fdatawait_keep_errors(struct address_space *);
 extern int filemap_fdatawait_range(struct address_space *, loff_t lstart,
 				   loff_t lend);
+extern bool filemap_range_has_page(struct address_space *, loff_t lstart,
+				  loff_t lend);
 extern int filemap_write_and_wait(struct address_space *mapping);
 extern int filemap_write_and_wait_range(struct address_space *mapping,
 				        loff_t lstart, loff_t lend);
@@ -2844,7 +2873,7 @@ enum {
 	DIO_SKIP_DIO_COUNT = 0x08,
 };
 
-void dio_end_io(struct bio *bio, int error);
+void dio_end_io(struct bio *bio);
 
 ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 			     struct block_device *bdev, struct iov_iter *iter,
@@ -3057,6 +3086,25 @@ static inline int iocb_flags(struct file *file)
 	return res;
 }
 
+static inline int kiocb_set_rw_flags(struct kiocb *ki, int flags)
+{
+	if (unlikely(flags & ~RWF_SUPPORTED))
+		return -EOPNOTSUPP;
+
+	if (flags & RWF_NOWAIT) {
+		if (!(ki->ki_filp->f_mode & FMODE_AIO_NOWAIT))
+			return -EOPNOTSUPP;
+		ki->ki_flags |= IOCB_NOWAIT;
+	}
+	if (flags & RWF_HIPRI)
+		ki->ki_flags |= IOCB_HIPRI;
+	if (flags & RWF_DSYNC)
+		ki->ki_flags |= IOCB_DSYNC;
+	if (flags & RWF_SYNC)
+		ki->ki_flags |= (IOCB_DSYNC | IOCB_SYNC);
+	return 0;
+}
+
 static inline ino_t parent_ino(struct dentry *dentry)
 {
 	ino_t res;
diff --git a/include/linux/ide.h b/include/linux/ide.h
index 6980ca322074..dc152e4b7f73 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -671,7 +671,7 @@ struct ide_port_ops {
 	void	(*init_dev)(ide_drive_t *);
 	void	(*set_pio_mode)(struct hwif_s *, ide_drive_t *);
 	void	(*set_dma_mode)(struct hwif_s *, ide_drive_t *);
-	int	(*reset_poll)(ide_drive_t *);
+	blk_status_t (*reset_poll)(ide_drive_t *);
 	void	(*pre_reset)(ide_drive_t *);
 	void	(*resetproc)(ide_drive_t *);
 	void	(*maskproc)(ide_drive_t *, int);
@@ -1092,7 +1092,7 @@ int generic_ide_ioctl(ide_drive_t *, struct block_device *, unsigned, unsigned l
 extern int ide_vlb_clk;
 extern int ide_pci_clk;
 
-int ide_end_rq(ide_drive_t *, struct request *, int, unsigned int);
+int ide_end_rq(ide_drive_t *, struct request *, blk_status_t, unsigned int);
 void ide_kill_rq(ide_drive_t *, struct request *);
 
 void __ide_set_handler(ide_drive_t *, ide_handler_t *, unsigned int);
@@ -1123,7 +1123,7 @@ extern int ide_devset_execute(ide_drive_t *drive,
 			      const struct ide_devset *setting, int arg);
 
 void ide_complete_cmd(ide_drive_t *, struct ide_cmd *, u8, u8);
-int ide_complete_rq(ide_drive_t *, int, unsigned int);
+int ide_complete_rq(ide_drive_t *, blk_status_t, unsigned int);
 
 void ide_tf_readback(ide_drive_t *drive, struct ide_cmd *cmd);
 void ide_tf_dump(const char *, struct ide_cmd *);
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index f753e788da31..69f4e9470084 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -52,6 +52,7 @@ struct iomap {
 #define IOMAP_REPORT		(1 << 2) /* report extent status, e.g. FIEMAP */
 #define IOMAP_FAULT		(1 << 3) /* mapping for page fault */
 #define IOMAP_DIRECT		(1 << 4) /* direct I/O */
+#define IOMAP_NOWAIT		(1 << 5) /* Don't wait for writeback */
 
 struct iomap_ops {
 	/*
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index e400a69fa1d3..6b8ee9e628e1 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -87,7 +87,7 @@ enum {
 	NVMF_RDMA_CMS_RDMA_CM	= 1, /* Sockets based endpoint addressing */
 };
 
-#define NVMF_AQ_DEPTH		32
+#define NVME_AQ_DEPTH		32
 
 enum {
 	NVME_REG_CAP	= 0x0000,	/* Controller Capabilities */
@@ -102,6 +102,7 @@ enum {
 	NVME_REG_ACQ	= 0x0030,	/* Admin CQ Base Address */
 	NVME_REG_CMBLOC = 0x0038,	/* Controller Memory Buffer Location */
 	NVME_REG_CMBSZ	= 0x003c,	/* Controller Memory Buffer Size */
+	NVME_REG_DBS	= 0x1000,	/* SQ 0 Tail Doorbell */
 };
 
 #define NVME_CAP_MQES(cap)	((cap) & 0xffff)
@@ -208,9 +209,15 @@ struct nvme_id_ctrl {
 	__u8			tnvmcap[16];
 	__u8			unvmcap[16];
 	__le32			rpmbs;
-	__u8			rsvd316[4];
+	__le16			edstt;
+	__u8			dsto;
+	__u8			fwug;
 	__le16			kas;
-	__u8			rsvd322[190];
+	__le16			hctma;
+	__le16			mntmt;
+	__le16			mxtmt;
+	__le32			sanicap;
+	__u8			rsvd332[180];
 	__u8			sqes;
 	__u8			cqes;
 	__le16			maxcmd;
@@ -246,6 +253,7 @@ enum {
 	NVME_CTRL_ONCS_WRITE_ZEROES		= 1 << 3,
 	NVME_CTRL_VWC_PRESENT			= 1 << 0,
 	NVME_CTRL_OACS_SEC_SUPP                 = 1 << 0,
+	NVME_CTRL_OACS_DIRECTIVES		= 1 << 5,
 	NVME_CTRL_OACS_DBBUF_SUPP		= 1 << 7,
 };
 
@@ -275,7 +283,7 @@ struct nvme_id_ns {
 	__le16			nabsn;
 	__le16			nabo;
 	__le16			nabspf;
-	__u16			rsvd46;
+	__le16			noiob;
 	__u8			nvmcap[16];
 	__u8			rsvd64[40];
 	__u8			nguid[16];
@@ -289,6 +297,7 @@ enum {
 	NVME_ID_CNS_NS			= 0x00,
 	NVME_ID_CNS_CTRL		= 0x01,
 	NVME_ID_CNS_NS_ACTIVE_LIST	= 0x02,
+	NVME_ID_CNS_NS_DESC_LIST	= 0x03,
 	NVME_ID_CNS_NS_PRESENT_LIST	= 0x10,
 	NVME_ID_CNS_NS_PRESENT		= 0x11,
 	NVME_ID_CNS_CTRL_NS_LIST	= 0x12,
@@ -296,6 +305,19 @@ enum {
 };
 
 enum {
+	NVME_DIR_IDENTIFY		= 0x00,
+	NVME_DIR_STREAMS		= 0x01,
+	NVME_DIR_SND_ID_OP_ENABLE	= 0x01,
+	NVME_DIR_SND_ST_OP_REL_ID	= 0x01,
+	NVME_DIR_SND_ST_OP_REL_RSC	= 0x02,
+	NVME_DIR_RCV_ID_OP_PARAM	= 0x01,
+	NVME_DIR_RCV_ST_OP_PARAM	= 0x01,
+	NVME_DIR_RCV_ST_OP_STATUS	= 0x02,
+	NVME_DIR_RCV_ST_OP_RESOURCE	= 0x03,
+	NVME_DIR_ENDIR			= 0x01,
+};
+
+enum {
 	NVME_NS_FEAT_THIN	= 1 << 0,
 	NVME_NS_FLBAS_LBA_MASK	= 0xf,
 	NVME_NS_FLBAS_META_EXT	= 0x10,
@@ -315,6 +337,22 @@ enum {
 	NVME_NS_DPS_PI_TYPE3	= 3,
 };
 
+struct nvme_ns_id_desc {
+	__u8 nidt;
+	__u8 nidl;
+	__le16 reserved;
+};
+
+#define NVME_NIDT_EUI64_LEN	8
+#define NVME_NIDT_NGUID_LEN	16
+#define NVME_NIDT_UUID_LEN	16
+
+enum {
+	NVME_NIDT_EUI64		= 0x01,
+	NVME_NIDT_NGUID		= 0x02,
+	NVME_NIDT_UUID		= 0x03,
+};
+
 struct nvme_smart_log {
 	__u8			critical_warning;
 	__u8			temperature[2];
@@ -536,6 +574,7 @@ enum {
 	NVME_RW_PRINFO_PRCHK_APP	= 1 << 11,
 	NVME_RW_PRINFO_PRCHK_GUARD	= 1 << 12,
 	NVME_RW_PRINFO_PRACT		= 1 << 13,
+	NVME_RW_DTYPE_STREAMS		= 1 << 4,
 };
 
 struct nvme_dsm_cmd {
@@ -587,6 +626,11 @@ struct nvme_feat_auto_pst {
 	__le64 entries[32];
 };
 
+enum {
+	NVME_HOST_MEM_ENABLE	= (1 << 0),
+	NVME_HOST_MEM_RETURN	= (1 << 1),
+};
+
 /* Admin commands */
 
 enum nvme_admin_opcode {
@@ -605,6 +649,8 @@ enum nvme_admin_opcode {
 	nvme_admin_download_fw		= 0x11,
 	nvme_admin_ns_attach		= 0x15,
 	nvme_admin_keep_alive		= 0x18,
+	nvme_admin_directive_send	= 0x19,
+	nvme_admin_directive_recv	= 0x1a,
 	nvme_admin_dbbuf		= 0x7C,
 	nvme_admin_format_nvm		= 0x80,
 	nvme_admin_security_send	= 0x81,
@@ -659,6 +705,8 @@ struct nvme_identify {
 	__u32			rsvd11[5];
 };
 
+#define NVME_IDENTIFY_DATA_SIZE 4096
+
 struct nvme_features {
 	__u8			opcode;
 	__u8			flags;
@@ -668,7 +716,16 @@ struct nvme_features {
 	union nvme_data_ptr	dptr;
 	__le32			fid;
 	__le32			dword11;
-	__u32			rsvd12[4];
+	__le32                  dword12;
+	__le32                  dword13;
+	__le32                  dword14;
+	__le32                  dword15;
+};
+
+struct nvme_host_mem_buf_desc {
+	__le64			addr;
+	__le32			size;
+	__u32			rsvd;
 };
 
 struct nvme_create_cq {
@@ -757,6 +814,24 @@ struct nvme_get_log_page_command {
 	__u32			rsvd14[2];
 };
 
+struct nvme_directive_cmd {
+	__u8			opcode;
+	__u8			flags;
+	__u16			command_id;
+	__le32			nsid;
+	__u64			rsvd2[2];
+	union nvme_data_ptr	dptr;
+	__le32			numd;
+	__u8			doper;
+	__u8			dtype;
+	__le16			dspec;
+	__u8			endir;
+	__u8			tdtype;
+	__u16			rsvd15;
+
+	__u32			rsvd16[3];
+};
+
 /*
  * Fabrics subcommands.
  */
@@ -887,6 +962,18 @@ struct nvme_dbbuf {
 	__u32			rsvd12[6];
 };
 
+struct streams_directive_params {
+	__u16	msl;
+	__u16	nssa;
+	__u16	nsso;
+	__u8	rsvd[10];
+	__u32	sws;
+	__u16	sgs;
+	__u16	nsa;
+	__u16	nso;
+	__u8	rsvd2[6];
+};
+
 struct nvme_command {
 	union {
 		struct nvme_common_command common;
@@ -907,6 +994,7 @@ struct nvme_command {
 		struct nvmf_property_set_command prop_set;
 		struct nvmf_property_get_command prop_get;
 		struct nvme_dbbuf dbbuf;
+		struct nvme_directive_cmd directive;
 	};
 };
 
@@ -1051,4 +1139,8 @@ struct nvme_completion {
 #define NVME_VS(major, minor, tertiary) \
 	(((major) << 16) | ((minor) << 8) | (tertiary))
 
+#define NVME_MAJOR(ver)		((ver) >> 16)
+#define NVME_MINOR(ver)		(((ver) >> 8) & 0xff)
+#define NVME_TERTIARY(ver)	((ver) & 0xff)
+
 #endif /* _LINUX_NVME_H */
diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
index cb3c8fe6acd7..4b3286ac60c8 100644
--- a/include/linux/scatterlist.h
+++ b/include/linux/scatterlist.h
@@ -278,6 +278,8 @@ size_t sg_pcopy_from_buffer(struct scatterlist *sgl, unsigned int nents,
 			    const void *buf, size_t buflen, off_t skip);
 size_t sg_pcopy_to_buffer(struct scatterlist *sgl, unsigned int nents,
 			  void *buf, size_t buflen, off_t skip);
+size_t sg_zero_buffer(struct scatterlist *sgl, unsigned int nents,
+		       size_t buflen, off_t skip);
 
 /*
  * Maximum number of entries that will be allocated in one piece, if
diff --git a/include/scsi/osd_initiator.h b/include/scsi/osd_initiator.h
index a09cca829082..a29d3086eb56 100644
--- a/include/scsi/osd_initiator.h
+++ b/include/scsi/osd_initiator.h
@@ -157,7 +157,7 @@ struct osd_request {
 
 	osd_req_done_fn *async_done;
 	void *async_private;
-	int async_error;
+	blk_status_t async_error;
 	int req_errors;
 };
 
diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h
index b379f93a2c48..da9bf2bcdf1a 100644
--- a/include/scsi/scsi_cmnd.h
+++ b/include/scsi/scsi_cmnd.h
@@ -166,6 +166,7 @@ extern void *scsi_kmap_atomic_sg(struct scatterlist *sg, int sg_count,
 extern void scsi_kunmap_atomic_sg(void *virt);
 
 extern int scsi_init_io(struct scsi_cmnd *cmd);
+extern void scsi_initialize_rq(struct request *rq);
 
 extern int scsi_dma_map(struct scsi_cmnd *cmd);
 extern void scsi_dma_unmap(struct scsi_cmnd *cmd);
diff --git a/include/scsi/scsi_request.h b/include/scsi/scsi_request.h
index f0c76f9dc285..e0afa445ee4e 100644
--- a/include/scsi/scsi_request.h
+++ b/include/scsi/scsi_request.h
@@ -27,6 +27,6 @@ static inline void scsi_req_free_cmd(struct scsi_request *req)
 		kfree(req->cmd);
 }
 
-void scsi_req_init(struct request *);
+void scsi_req_init(struct scsi_request *req);
 
 #endif /* _SCSI_SCSI_REQUEST_H */
diff --git a/include/uapi/linux/aio_abi.h b/include/uapi/linux/aio_abi.h
index bb2554f7fbd1..a2d4a8ac94ca 100644
--- a/include/uapi/linux/aio_abi.h
+++ b/include/uapi/linux/aio_abi.h
@@ -79,7 +79,7 @@ struct io_event {
 struct iocb {
 	/* these are internal to the kernel/libc. */
 	__u64	aio_data;	/* data to be returned in event's data */
-	__u32	PADDED(aio_key, aio_reserved1);
+	__u32	PADDED(aio_key, aio_rw_flags);
 				/* the kernel sets aio_key to the req # */
 
 	/* common fields */
diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h
index 4bf9f1eabffc..2f6c77aebe1a 100644
--- a/include/uapi/linux/dm-ioctl.h
+++ b/include/uapi/linux/dm-ioctl.h
@@ -267,9 +267,9 @@ enum {
 #define DM_DEV_SET_GEOMETRY	_IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl)
 
 #define DM_VERSION_MAJOR	4
-#define DM_VERSION_MINOR	35
+#define DM_VERSION_MINOR	36
 #define DM_VERSION_PATCHLEVEL	0
-#define DM_VERSION_EXTRA	"-ioctl (2016-06-23)"
+#define DM_VERSION_EXTRA	"-ioctl (2017-06-09)"
 
 /* Status bits */
 #define DM_READONLY_FLAG	(1 << 0) /* In/Out */
diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h
index 813afd6eee71..ec69d55bcec7 100644
--- a/include/uapi/linux/fcntl.h
+++ b/include/uapi/linux/fcntl.h
@@ -43,6 +43,27 @@
 /* (1U << 31) is reserved for signed error codes */
 
 /*
+ * Set/Get write life time hints. {GET,SET}_RW_HINT operate on the
+ * underlying inode, while {GET,SET}_FILE_RW_HINT operate only on
+ * the specific file.
+ */
+#define F_GET_RW_HINT		(F_LINUX_SPECIFIC_BASE + 11)
+#define F_SET_RW_HINT		(F_LINUX_SPECIFIC_BASE + 12)
+#define F_GET_FILE_RW_HINT	(F_LINUX_SPECIFIC_BASE + 13)
+#define F_SET_FILE_RW_HINT	(F_LINUX_SPECIFIC_BASE + 14)
+
+/*
+ * Valid hint values for F_{GET,SET}_RW_HINT. 0 is "not set", or can be
+ * used to clear any hints previously set.
+ */
+#define RWF_WRITE_LIFE_NOT_SET	0
+#define RWH_WRITE_LIFE_NONE	1
+#define RWH_WRITE_LIFE_SHORT	2
+#define RWH_WRITE_LIFE_MEDIUM	3
+#define RWH_WRITE_LIFE_LONG	4
+#define RWH_WRITE_LIFE_EXTREME	5
+
+/*
  * Types of directory notifications that may be requested.
  */
 #define DN_ACCESS	0x00000001	/* File accessed */
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 24e61a54feaa..27d8c36c04af 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -360,5 +360,9 @@ struct fscrypt_key {
 #define RWF_HIPRI			0x00000001 /* high priority request, poll if possible */
 #define RWF_DSYNC			0x00000002 /* per-IO O_DSYNC */
 #define RWF_SYNC			0x00000004 /* per-IO O_SYNC */
+#define RWF_NOWAIT			0x00000008 /* per-IO, return -EAGAIN if operation would block */
+
+#define RWF_SUPPORTED			(RWF_HIPRI | RWF_DSYNC | RWF_SYNC |\
+					 RWF_NOWAIT)
 
 #endif /* _UAPI_LINUX_FS_H */
diff --git a/include/uapi/linux/loop.h b/include/uapi/linux/loop.h
index c8125ec1f4f2..a3960f98679c 100644
--- a/include/uapi/linux/loop.h
+++ b/include/uapi/linux/loop.h
@@ -22,6 +22,7 @@ enum {
 	LO_FLAGS_AUTOCLEAR	= 4,
 	LO_FLAGS_PARTSCAN	= 8,
 	LO_FLAGS_DIRECT_IO	= 16,
+	LO_FLAGS_BLOCKSIZE	= 32,
 };
 
 #include <asm/posix_types.h>	/* for __kernel_old_dev_t */
@@ -59,6 +60,8 @@ struct loop_info64 {
 	__u64		   lo_init[2];
 };
 
+#define LO_INFO_BLOCKSIZE(l) (l)->lo_init[0]
+
 /*
  * Loop filter types
  */
diff --git a/include/uapi/linux/nbd.h b/include/uapi/linux/nbd.h
index 155e33f81913..a50527ebf671 100644
--- a/include/uapi/linux/nbd.h
+++ b/include/uapi/linux/nbd.h
@@ -41,10 +41,14 @@ enum {
 #define NBD_FLAG_HAS_FLAGS	(1 << 0) /* nbd-server supports flags */
 #define NBD_FLAG_READ_ONLY	(1 << 1) /* device is read-only */
 #define NBD_FLAG_SEND_FLUSH	(1 << 2) /* can flush writeback cache */
+#define NBD_FLAG_SEND_FUA	(1 << 3) /* send FUA (forced unit access) */
 /* there is a gap here to match userspace */
 #define NBD_FLAG_SEND_TRIM	(1 << 5) /* send trim/discard */
 #define NBD_FLAG_CAN_MULTI_CONN	(1 << 8)	/* Server supports multiple connections per export. */
 
+/* values for cmd flags in the upper 16 bits of request type */
+#define NBD_CMD_FLAG_FUA	(1 << 16) /* FUA (forced unit access) op */
+
 /* These are client behavior specific flags. */
 #define NBD_CFLAG_DESTROY_ON_DISCONNECT	(1 << 0) /* delete the nbd device on
 						    disconnect. */