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

Pull block layer fixes from Jens Axboe:
 "Final small batch of fixes to be included before -rc1.  Some general
  cleanups in here as well, but some of the blk-mq fixes we need for the
  NVMe conversion and/or scsi-mq.  The pull request contains:

   - Support for not merging across a specified "chunk size", if set by
     the driver.  Some NVMe devices perform poorly for IO that crosses
     such a chunk, so we need to support it generically as part of
     request merging avoid having to do complicated split logic.  From
     me.

   - Bump max tag depth to 10Ki tags.  Some scsi devices have a huge
     shared tag space.  Before we failed with EINVAL if a too large tag
     depth was specified, now we truncate it and pass back the actual
     value.  From me.

   - Various blk-mq rq init fixes from me and others.

   - A fix for enter on a dying queue for blk-mq from Keith.  This is
     needed to prevent oopsing on hot device removal.

   - Fixup for blk-mq timer addition from Ming Lei.

   - Small round of performance fixes for mtip32xx from Sam Bradshaw.

   - Minor stack leak fix from Rickard Strandqvist.

   - Two __init annotations from Fabian Frederick"

* 'for-linus' of git://git.kernel.dk/linux-block:
  block: add __init to blkcg_policy_register
  block: add __init to elv_register
  block: ensure that bio_add_page() always accepts a page for an empty bio
  blk-mq: add timer in blk_mq_start_request
  blk-mq: always initialize request->start_time
  block: blk-exec.c: Cleaning up local variable address returnd
  mtip32xx: minor performance enhancements
  blk-mq: ->timeout should be cleared in blk_mq_rq_ctx_init()
  blk-mq: don't allow queue entering for a dying queue
  blk-mq: bump max tag depth to 10K tags
  block: add blk_rq_set_block_pc()
  block: add notion of a chunk size for request merging

include/linux/blk-mq.h

@@ -135,7 +135,7 @@ enum {
 	BLK_MQ_S_STOPPED	= 0,
 	BLK_MQ_S_TAG_ACTIVE	= 1,
 
-	BLK_MQ_MAX_DEPTH	= 2048,
+	BLK_MQ_MAX_DEPTH	= 10240,
 
 	BLK_MQ_CPU_WORK_BATCH	= 8,
 };

include/linux/blkdev.h

@@ -280,6 +280,7 @@ struct queue_limits {
 	unsigned long		seg_boundary_mask;
 
 	unsigned int		max_hw_sectors;
+	unsigned int		chunk_sectors;
 	unsigned int		max_sectors;
 	unsigned int		max_segment_size;
 	unsigned int		physical_block_size;
@@ -795,6 +796,7 @@ 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_make_request(struct request_queue *, struct bio *,
 					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,
 		unsigned int len);
@@ -910,6 +912,20 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
 	return q->limits.max_sectors;
 }
 
+/*
+ * Return maximum size of a request at given offset. Only valid for
+ * file system requests.
+ */
+static inline unsigned int blk_max_size_offset(struct request_queue *q,
+					       sector_t offset)
+{
+	if (!q->limits.chunk_sectors)
+		return q->limits.max_hw_sectors;
+
+	return q->limits.chunk_sectors -
+			(offset & (q->limits.chunk_sectors - 1));
+}
+
 static inline unsigned int blk_rq_get_max_sectors(struct request *rq)
 {
 	struct request_queue *q = rq->q;
@@ -917,7 +933,11 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq)
 	if (unlikely(rq->cmd_type == REQ_TYPE_BLOCK_PC))
 		return q->limits.max_hw_sectors;
 
-	return blk_queue_get_max_sectors(q, rq->cmd_flags);
+	if (!q->limits.chunk_sectors)
+		return blk_queue_get_max_sectors(q, rq->cmd_flags);
+
+	return min(blk_max_size_offset(q, blk_rq_pos(rq)),
+			blk_queue_get_max_sectors(q, rq->cmd_flags));
 }
 
 static inline unsigned int blk_rq_count_bios(struct request *rq)
@@ -983,6 +1003,7 @@ extern void blk_queue_make_request(struct request_queue *, make_request_fn *);
 extern void blk_queue_bounce_limit(struct request_queue *, u64);
 extern void blk_limits_max_hw_sectors(struct queue_limits *, unsigned int);
 extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int);
+extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int);
 extern void blk_queue_max_segments(struct request_queue *, unsigned short);
 extern void blk_queue_max_segment_size(struct request_queue *, unsigned int);
 extern void blk_queue_max_discard_sectors(struct request_queue *q,

include/linux/elevator.h

@@ -144,7 +144,7 @@ extern void elv_drain_elevator(struct request_queue *);
  * io scheduler registration
  */
 extern void __init load_default_elevator_module(void);
-extern int elv_register(struct elevator_type *);
+extern int __init elv_register(struct elevator_type *);
 extern void elv_unregister(struct elevator_type *);
 
 /*