Merge branch 'for-4.10/block' of git://git.kernel.dk/linux-block

Pull block layer updates from Jens Axboe:
 "This is the main block pull request this series. Contrary to previous
  release, I've kept the core and driver changes in the same branch. We
  always ended up having dependencies between the two for obvious
  reasons, so makes more sense to keep them together. That said, I'll
  probably try and keep more topical branches going forward, especially
  for cycles that end up being as busy as this one.

  The major parts of this pull request is:

   - Improved support for O_DIRECT on block devices, with a small
     private implementation instead of using the pig that is
     fs/direct-io.c. From Christoph.

   - Request completion tracking in a scalable fashion. This is utilized
     by two components in this pull, the new hybrid polling and the
     writeback queue throttling code.

   - Improved support for polling with O_DIRECT, adding a hybrid mode
     that combines pure polling with an initial sleep. From me.

   - Support for automatic throttling of writeback queues on the block
     side. This uses feedback from the device completion latencies to
     scale the queue on the block side up or down. From me.

   - Support from SMR drives in the block layer and for SD. From Hannes
     and Shaun.

   - Multi-connection support for nbd. From Josef.

   - Cleanup of request and bio flags, so we have a clear split between
     which are bio (or rq) private, and which ones are shared. From
     Christoph.

   - A set of patches from Bart, that improve how we handle queue
     stopping and starting in blk-mq.

   - Support for WRITE_ZEROES from Chaitanya.

   - Lightnvm updates from Javier/Matias.

   - Supoort for FC for the nvme-over-fabrics code. From James Smart.

   - A bunch of fixes from a whole slew of people, too many to name
     here"

* 'for-4.10/block' of git://git.kernel.dk/linux-block: (182 commits)
  blk-stat: fix a few cases of missing batch flushing
  blk-flush: run the queue when inserting blk-mq flush
  elevator: make the rqhash helpers exported
  blk-mq: abstract out blk_mq_dispatch_rq_list() helper
  blk-mq: add blk_mq_start_stopped_hw_queue()
  block: improve handling of the magic discard payload
  blk-wbt: don't throttle discard or write zeroes
  nbd: use dev_err_ratelimited in io path
  nbd: reset the setup task for NBD_CLEAR_SOCK
  nvme-fabrics: Add FC LLDD loopback driver to test FC-NVME
  nvme-fabrics: Add target support for FC transport
  nvme-fabrics: Add host support for FC transport
  nvme-fabrics: Add FC transport LLDD api definitions
  nvme-fabrics: Add FC transport FC-NVME definitions
  nvme-fabrics: Add FC transport error codes to nvme.h
  Add type 0x28 NVME type code to scsi fc headers
  nvme-fabrics: patch target code in prep for FC transport support
  nvme-fabrics: set sqe.command_id in core not transports
  parser: add u64 number parser
  nvme-rdma: align to generic ib_event logging helper
  ...

1 files changed, 205 insertions, 26 deletions

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c47c358ba052..c5393766909d 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -24,6 +24,7 @@
 #include <linux/rcupdate.h>
 #include <linux/percpu-refcount.h>
 #include <linux/scatterlist.h>
+#include <linux/blkzoned.h>
 
 struct module;
 struct scsi_ioctl_command;
@@ -37,6 +38,7 @@ struct bsg_job;
 struct blkcg_gq;
 struct blk_flush_queue;
 struct pr_ops;
+struct rq_wb;
 
 #define BLKDEV_MIN_RQ	4
 #define BLKDEV_MAX_RQ	128	/* Default maximum */
@@ -77,6 +79,55 @@ enum rq_cmd_type_bits {
 	REQ_TYPE_DRV_PRIV,		/* driver defined types from here */
 };
 
+/*
+ * request flags */
+typedef __u32 __bitwise req_flags_t;
+
+/* elevator knows about this request */
+#define RQF_SORTED		((__force req_flags_t)(1 << 0))
+/* drive already may have started this one */
+#define RQF_STARTED		((__force req_flags_t)(1 << 1))
+/* uses tagged queueing */
+#define RQF_QUEUED		((__force req_flags_t)(1 << 2))
+/* may not be passed by ioscheduler */
+#define RQF_SOFTBARRIER		((__force req_flags_t)(1 << 3))
+/* request for flush sequence */
+#define RQF_FLUSH_SEQ		((__force req_flags_t)(1 << 4))
+/* merge of different types, fail separately */
+#define RQF_MIXED_MERGE		((__force req_flags_t)(1 << 5))
+/* track inflight for MQ */
+#define RQF_MQ_INFLIGHT		((__force req_flags_t)(1 << 6))
+/* don't call prep for this one */
+#define RQF_DONTPREP		((__force req_flags_t)(1 << 7))
+/* 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 */
+#define RQF_QUIET		((__force req_flags_t)(1 << 11))
+/* elevator private data attached */
+#define RQF_ELVPRIV		((__force req_flags_t)(1 << 12))
+/* account I/O stat */
+#define RQF_IO_STAT		((__force req_flags_t)(1 << 13))
+/* request came from our alloc pool */
+#define RQF_ALLOCED		((__force req_flags_t)(1 << 14))
+/* runtime pm request */
+#define RQF_PM			((__force req_flags_t)(1 << 15))
+/* on IO scheduler merge hash */
+#define RQF_HASHED		((__force req_flags_t)(1 << 16))
+/* IO stats tracking on */
+#define RQF_STATS		((__force req_flags_t)(1 << 17))
+/* Look at ->special_vec for the actual data payload instead of the
+   bio chain. */
+#define RQF_SPECIAL_PAYLOAD	((__force req_flags_t)(1 << 18))
+
+/* flags that prevent us from merging requests: */
+#define RQF_NOMERGE_FLAGS \
+	(RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD)
+
 #define BLK_MAX_CDB	16
 
 /*
@@ -97,7 +148,8 @@ struct request {
 
 	int cpu;
 	unsigned cmd_type;
-	u64 cmd_flags;
+	unsigned int cmd_flags;		/* op and common flags */
+	req_flags_t rq_flags;
 	unsigned long atomic_flags;
 
 	/* the following two fields are internal, NEVER access directly */
@@ -126,6 +178,7 @@ struct request {
 	 */
 	union {
 		struct rb_node rb_node;	/* sort/lookup */
+		struct bio_vec special_vec;
 		void *completion_data;
 	};
 
@@ -151,6 +204,7 @@ struct request {
 	struct gendisk *rq_disk;
 	struct hd_struct *part;
 	unsigned long start_time;
+	struct blk_issue_stat issue_stat;
 #ifdef CONFIG_BLK_CGROUP
 	struct request_list *rl;		/* rl this rq is alloced from */
 	unsigned long long start_time_ns;
@@ -198,20 +252,6 @@ struct request {
 	struct request *next_rq;
 };
 
-#define REQ_OP_SHIFT (8 * sizeof(u64) - REQ_OP_BITS)
-#define req_op(req)  ((req)->cmd_flags >> REQ_OP_SHIFT)
-
-#define req_set_op(req, op) do {				\
-	WARN_ON(op >= (1 << REQ_OP_BITS));			\
-	(req)->cmd_flags &= ((1ULL << REQ_OP_SHIFT) - 1);	\
-	(req)->cmd_flags |= ((u64) (op) << REQ_OP_SHIFT);	\
-} while (0)
-
-#define req_set_op_attrs(req, op, flags) do {	\
-	req_set_op(req, op);			\
-	(req)->cmd_flags |= flags;		\
-} while (0)
-
 static inline unsigned short req_get_ioprio(struct request *req)
 {
 	return req->ioprio;
@@ -261,6 +301,15 @@ struct blk_queue_tag {
 #define BLK_SCSI_MAX_CMDS	(256)
 #define BLK_SCSI_CMD_PER_LONG	(BLK_SCSI_MAX_CMDS / (sizeof(long) * 8))
 
+/*
+ * Zoned block device models (zoned limit).
+ */
+enum blk_zoned_model {
+	BLK_ZONED_NONE,	/* Regular block device */
+	BLK_ZONED_HA,	/* Host-aware zoned block device */
+	BLK_ZONED_HM,	/* Host-managed zoned block device */
+};
+
 struct queue_limits {
 	unsigned long		bounce_pfn;
 	unsigned long		seg_boundary_mask;
@@ -278,6 +327,7 @@ struct queue_limits {
 	unsigned int		max_discard_sectors;
 	unsigned int		max_hw_discard_sectors;
 	unsigned int		max_write_same_sectors;
+	unsigned int		max_write_zeroes_sectors;
 	unsigned int		discard_granularity;
 	unsigned int		discard_alignment;
 
@@ -290,8 +340,45 @@ struct queue_limits {
 	unsigned char		cluster;
 	unsigned char		discard_zeroes_data;
 	unsigned char		raid_partial_stripes_expensive;
+	enum blk_zoned_model	zoned;
 };
 
+#ifdef CONFIG_BLK_DEV_ZONED
+
+struct blk_zone_report_hdr {
+	unsigned int	nr_zones;
+	u8		padding[60];
+};
+
+extern int blkdev_report_zones(struct block_device *bdev,
+			       sector_t sector, struct blk_zone *zones,
+			       unsigned int *nr_zones, gfp_t gfp_mask);
+extern int blkdev_reset_zones(struct block_device *bdev, sector_t sectors,
+			      sector_t nr_sectors, gfp_t gfp_mask);
+
+extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
+				     unsigned int cmd, unsigned long arg);
+extern int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode,
+				    unsigned int cmd, unsigned long arg);
+
+#else /* CONFIG_BLK_DEV_ZONED */
+
+static inline int blkdev_report_zones_ioctl(struct block_device *bdev,
+					    fmode_t mode, unsigned int cmd,
+					    unsigned long arg)
+{
+	return -ENOTTY;
+}
+
+static inline int blkdev_reset_zones_ioctl(struct block_device *bdev,
+					   fmode_t mode, unsigned int cmd,
+					   unsigned long arg)
+{
+	return -ENOTTY;
+}
+
+#endif /* CONFIG_BLK_DEV_ZONED */
+
 struct request_queue {
 	/*
 	 * Together with queue_head for cacheline sharing
@@ -302,6 +389,8 @@ struct request_queue {
 	int			nr_rqs[2];	/* # allocated [a]sync rqs */
 	int			nr_rqs_elvpriv;	/* # allocated rqs w/ elvpriv */
 
+	struct rq_wb		*rq_wb;
+
 	/*
 	 * If blkcg is not used, @q->root_rl serves all requests.  If blkcg
 	 * is used, root blkg allocates from @q->root_rl and all other
@@ -327,6 +416,8 @@ struct request_queue {
 	struct blk_mq_ctx __percpu	*queue_ctx;
 	unsigned int		nr_queues;
 
+	unsigned int		queue_depth;
+
 	/* hw dispatch queues */
 	struct blk_mq_hw_ctx	**queue_hw_ctx;
 	unsigned int		nr_hw_queues;
@@ -412,6 +503,9 @@ struct request_queue {
 
 	unsigned int		nr_sorted;
 	unsigned int		in_flight[2];
+
+	struct blk_rq_stat	rq_stats[2];
+
 	/*
 	 * Number of active block driver functions for which blk_drain_queue()
 	 * must wait. Must be incremented around functions that unlock the
@@ -420,6 +514,7 @@ struct request_queue {
 	unsigned int		request_fn_active;
 
 	unsigned int		rq_timeout;
+	int			poll_nsec;
 	struct timer_list	timeout;
 	struct work_struct	timeout_work;
 	struct list_head	timeout_list;
@@ -505,6 +600,7 @@ struct request_queue {
 #define QUEUE_FLAG_FUA	       24	/* device supports FUA writes */
 #define QUEUE_FLAG_FLUSH_NQ    25	/* flush not queueuable */
 #define QUEUE_FLAG_DAX         26	/* device supports DAX */
+#define QUEUE_FLAG_STATS       27	/* track rq completion times */
 
 #define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_STACKABLE)	|	\
@@ -601,7 +697,7 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 			     REQ_FAILFAST_DRIVER))
 
 #define blk_account_rq(rq) \
-	(((rq)->cmd_flags & REQ_STARTED) && \
+	(((rq)->rq_flags & RQF_STARTED) && \
 	 ((rq)->cmd_type == REQ_TYPE_FS))
 
 #define blk_rq_cpu_valid(rq)	((rq)->cpu != -1)
@@ -627,17 +723,31 @@ static inline unsigned int blk_queue_cluster(struct request_queue *q)
 	return q->limits.cluster;
 }
 
-/*
- * We regard a request as sync, if either a read or a sync write
- */
-static inline bool rw_is_sync(int op, unsigned int rw_flags)
+static inline enum blk_zoned_model
+blk_queue_zoned_model(struct request_queue *q)
 {
-	return op == REQ_OP_READ || (rw_flags & REQ_SYNC);
+	return q->limits.zoned;
+}
+
+static inline bool blk_queue_is_zoned(struct request_queue *q)
+{
+	switch (blk_queue_zoned_model(q)) {
+	case BLK_ZONED_HA:
+	case BLK_ZONED_HM:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static inline unsigned int blk_queue_zone_size(struct request_queue *q)
+{
+	return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0;
 }
 
 static inline bool rq_is_sync(struct request *rq)
 {
-	return rw_is_sync(req_op(rq), rq->cmd_flags);
+	return op_is_sync(rq->cmd_flags);
 }
 
 static inline bool blk_rl_full(struct request_list *rl, bool sync)
@@ -669,8 +779,13 @@ static inline bool rq_mergeable(struct request *rq)
 	if (req_op(rq) == REQ_OP_FLUSH)
 		return false;
 
+	if (req_op(rq) == REQ_OP_WRITE_ZEROES)
+		return false;
+
 	if (rq->cmd_flags & REQ_NOMERGE_FLAGS)
 		return false;
+	if (rq->rq_flags & RQF_NOMERGE_FLAGS)
+		return false;
 
 	return true;
 }
@@ -683,6 +798,14 @@ static inline bool blk_write_same_mergeable(struct bio *a, struct bio *b)
 	return false;
 }
 
+static inline unsigned int blk_queue_depth(struct request_queue *q)
+{
+	if (q->queue_depth)
+		return q->queue_depth;
+
+	return q->nr_requests;
+}
+
 /*
  * q->prep_rq_fn return values
  */
@@ -790,8 +913,6 @@ extern void __blk_put_request(struct request_queue *, struct request *);
 extern struct request *blk_get_request(struct request_queue *, int, gfp_t);
 extern void blk_rq_set_block_pc(struct request *);
 extern void blk_requeue_request(struct request_queue *, struct request *);
-extern void blk_add_request_payload(struct request *rq, struct page *page,
-		int offset, unsigned int len);
 extern int blk_lld_busy(struct request_queue *q);
 extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
 			     struct bio_set *bs, gfp_t gfp_mask,
@@ -824,6 +945,7 @@ 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);
@@ -837,7 +959,7 @@ extern int 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 *);
 
-bool blk_poll(struct request_queue *q, blk_qc_t cookie);
+bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie);
 
 static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
 {
@@ -888,6 +1010,9 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
 	if (unlikely(op == REQ_OP_WRITE_SAME))
 		return q->limits.max_write_same_sectors;
 
+	if (unlikely(op == REQ_OP_WRITE_ZEROES))
+		return q->limits.max_write_zeroes_sectors;
+
 	return q->limits.max_sectors;
 }
 
@@ -991,6 +1116,8 @@ extern void blk_queue_max_discard_sectors(struct request_queue *q,
 		unsigned int max_discard_sectors);
 extern void blk_queue_max_write_same_sectors(struct request_queue *q,
 		unsigned int max_write_same_sectors);
+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 short);
 extern void blk_queue_physical_block_size(struct request_queue *, unsigned int);
 extern void blk_queue_alignment_offset(struct request_queue *q,
@@ -999,6 +1126,7 @@ extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min);
 extern void blk_queue_io_min(struct request_queue *q, unsigned int min);
 extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt);
 extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt);
+extern void blk_set_queue_depth(struct request_queue *q, unsigned int depth);
 extern void blk_set_default_limits(struct queue_limits *lim);
 extern void blk_set_stacking_limits(struct queue_limits *lim);
 extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
@@ -1027,6 +1155,13 @@ extern void blk_queue_flush_queueable(struct request_queue *q, bool queueable);
 extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua);
 extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev);
 
+static inline unsigned short blk_rq_nr_phys_segments(struct request *rq)
+{
+	if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
+		return 1;
+	return rq->nr_phys_segments;
+}
+
 extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *);
 extern void blk_dump_rq_flags(struct request *, char *);
 extern long nr_blockdev_pages(void);
@@ -1057,7 +1192,7 @@ static inline int blk_pre_runtime_suspend(struct request_queue *q)
 static inline void blk_post_runtime_suspend(struct request_queue *q, int err) {}
 static inline void blk_pre_runtime_resume(struct request_queue *q) {}
 static inline void blk_post_runtime_resume(struct request_queue *q, int err) {}
-extern inline void blk_set_runtime_active(struct request_queue *q) {}
+static inline void blk_set_runtime_active(struct request_queue *q) {}
 #endif
 
 /*
@@ -1078,6 +1213,7 @@ struct blk_plug {
 	struct list_head cb_list; /* md requires an unplug callback */
 };
 #define BLK_MAX_REQUEST_COUNT 16
+#define BLK_PLUG_FLUSH_SIZE (128 * 1024)
 
 struct blk_plug_cb;
 typedef void (*blk_plug_cb_fn)(struct blk_plug_cb *, bool);
@@ -1151,6 +1287,9 @@ extern int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		struct bio **biop);
 extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, struct page *page);
+extern int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
+		sector_t nr_sects, gfp_t gfp_mask, struct bio **biop,
+		bool discard);
 extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, bool discard);
 static inline int sb_issue_discard(struct super_block *sb, sector_t block,
@@ -1354,6 +1493,46 @@ static inline unsigned int bdev_write_same(struct block_device *bdev)
 	return 0;
 }
 
+static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
+
+	if (q)
+		return q->limits.max_write_zeroes_sectors;
+
+	return 0;
+}
+
+static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
+
+	if (q)
+		return blk_queue_zoned_model(q);
+
+	return BLK_ZONED_NONE;
+}
+
+static inline bool bdev_is_zoned(struct block_device *bdev)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
+
+	if (q)
+		return blk_queue_is_zoned(q);
+
+	return false;
+}
+
+static inline unsigned int bdev_zone_size(struct block_device *bdev)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
+
+	if (q)
+		return blk_queue_zone_size(q);
+
+	return 0;
+}
+
 static inline int queue_dma_alignment(struct request_queue *q)
 {
 	return q ? q->dma_alignment : 511;