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
  ...

1 files changed, 39 insertions, 33 deletions

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;