Merge branch 'for-3.15/core' of git://git.kernel.dk/linux-block

Pull core block layer updates from Jens Axboe:
 "This is the pull request for the core block IO bits for the 3.15
  kernel.  It's a smaller round this time, it contains:

   - Various little blk-mq fixes and additions from Christoph and
     myself.

   - Cleanup of the IPI usage from the block layer, and associated
     helper code.  From Frederic Weisbecker and Jan Kara.

   - Duplicate code cleanup in bio-integrity from Gu Zheng.  This will
     give you a merge conflict, but that should be easy to resolve.

   - blk-mq notify spinlock fix for RT from Mike Galbraith.

   - A blktrace partial accounting bug fix from Roman Pen.

   - Missing REQ_SYNC detection fix for blk-mq from Shaohua Li"

* 'for-3.15/core' of git://git.kernel.dk/linux-block: (25 commits)
  blk-mq: add REQ_SYNC early
  rt,blk,mq: Make blk_mq_cpu_notify_lock a raw spinlock
  blk-mq: support partial I/O completions
  blk-mq: merge blk_mq_insert_request and blk_mq_run_request
  blk-mq: remove blk_mq_alloc_rq
  blk-mq: don't dump CPU -> hw queue map on driver load
  blk-mq: fix wrong usage of hctx->state vs hctx->flags
  blk-mq: allow blk_mq_init_commands() to return failure
  block: remove old blk_iopoll_enabled variable
  blktrace: fix accounting of partially completed requests
  smp: Rename __smp_call_function_single() to smp_call_function_single_async()
  smp: Remove wait argument from __smp_call_function_single()
  watchdog: Simplify a little the IPI call
  smp: Move __smp_call_function_single() below its safe version
  smp: Consolidate the various smp_call_function_single() declensions
  smp: Teach __smp_call_function_single() to check for offline cpus
  smp: Remove unused list_head from csd
  smp: Iterate functions through llist_for_each_entry_safe()
  block: Stop abusing rq->csd.list in blk-softirq
  block: Remove useless IPI struct initialization
  ...

include/trace/events/block.h

@@ -132,6 +132,7 @@ DEFINE_EVENT(block_rq_with_error, block_rq_requeue,
  * block_rq_complete - block IO operation completed by device driver
  * @q: queue containing the block operation request
  * @rq: block operations request
+ * @nr_bytes: number of completed bytes
  *
  * The block_rq_complete tracepoint event indicates that some portion
  * of operation request has been completed by the device driver.  If
@@ -139,11 +140,37 @@ DEFINE_EVENT(block_rq_with_error, block_rq_requeue,
  * do for the request. If @rq->bio is non-NULL then there is
  * additional work required to complete the request.
  */
-DEFINE_EVENT(block_rq_with_error, block_rq_complete,
+TRACE_EVENT(block_rq_complete,
 
-	TP_PROTO(struct request_queue *q, struct request *rq),
+	TP_PROTO(struct request_queue *q, struct request *rq,
+		 unsigned int nr_bytes),
 
-	TP_ARGS(q, rq)
+	TP_ARGS(q, rq, nr_bytes),
+
+	TP_STRUCT__entry(
+		__field(  dev_t,	dev			)
+		__field(  sector_t,	sector			)
+		__field(  unsigned int,	nr_sector		)
+		__field(  int,		errors			)
+		__array(  char,		rwbs,	RWBS_LEN	)
+		__dynamic_array( char,	cmd,	blk_cmd_buf_len(rq)	)
+	),
+
+	TP_fast_assign(
+		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+		__entry->sector    = blk_rq_pos(rq);
+		__entry->nr_sector = nr_bytes >> 9;
+		__entry->errors    = rq->errors;
+
+		blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, nr_bytes);
+		blk_dump_cmd(__get_str(cmd), rq);
+	),
+
+	TP_printk("%d,%d %s (%s) %llu + %u [%d]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rwbs, __get_str(cmd),
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->errors)
 );
 
 DECLARE_EVENT_CLASS(block_rq,