blktrace: Provide event for request merging

Currently blk-mq does not report any event when two requests get merged
in the elevator. This then results in difficult to understand sequence
of events like:

...
  8,0   34     1579     0.608765271  2718  I  WS 215023504 + 40 [dbench]
  8,0   34     1584     0.609184613  2719  A  WS 215023544 + 56 <- (8,4) 2160568
  8,0   34     1585     0.609184850  2719  Q  WS 215023544 + 56 [dbench]
  8,0   34     1586     0.609188524  2719  G  WS 215023544 + 56 [dbench]
  8,0    3      602     0.609684162   773  D  WS 215023504 + 96 [kworker/3:1H]
  8,0   34     1591     0.609843593     0  C  WS 215023504 + 96 [0]

and you can only guess (after quite some headscratching since the above
excerpt is intermixed with a lot of other IO) that request 215023544+56
got merged to request 215023504+40. Provide proper event for request
merging like we used to do in the legacy block layer.
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block/blk-merge.c

@@ -793,6 +793,8 @@ static struct request *attempt_merge(struct request_queue *q,
 	 */
 	blk_account_io_merge_request(next);
 
+	trace_block_rq_merge(q, next);
+
 	/*
 	 * ownership of bio passed from next to req, return 'next' for
 	 * the caller to free

include/trace/events/block.h

@@ -211,6 +211,21 @@ DEFINE_EVENT(block_rq, block_rq_issue,
 	TP_ARGS(q, rq)
 );
 
+/**
+ * block_rq_merge - merge request with another one in the elevator
+ * @q: queue holding operation
+ * @rq: block IO operation operation request
+ *
+ * Called when block operation request @rq from queue @q is merged to another
+ * request queued in the elevator.
+ */
+DEFINE_EVENT(block_rq, block_rq_merge,
+
+	TP_PROTO(struct request_queue *q, struct request *rq),
+
+	TP_ARGS(q, rq)
+);
+
 /**
  * block_bio_bounce - used bounce buffer when processing block operation
  * @q: queue holding the block operation

kernel/trace/blktrace.c

@@ -860,6 +860,13 @@ static void blk_add_trace_rq_issue(void *ignore,
 			 blk_trace_request_get_cgid(q, rq));
 }
 
+static void blk_add_trace_rq_merge(void *ignore,
+				   struct request_queue *q, struct request *rq)
+{
+	blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_BACKMERGE,
+			 blk_trace_request_get_cgid(q, rq));
+}
+
 static void blk_add_trace_rq_requeue(void *ignore,
 				     struct request_queue *q,
 				     struct request *rq)
@@ -1144,6 +1151,8 @@ static void blk_register_tracepoints(void)
 	WARN_ON(ret);
 	ret = register_trace_block_rq_issue(blk_add_trace_rq_issue, NULL);
 	WARN_ON(ret);
+	ret = register_trace_block_rq_merge(blk_add_trace_rq_merge, NULL);
+	WARN_ON(ret);
 	ret = register_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL);
 	WARN_ON(ret);
 	ret = register_trace_block_rq_complete(blk_add_trace_rq_complete, NULL);
@@ -1190,6 +1199,7 @@ static void blk_unregister_tracepoints(void)
 	unregister_trace_block_bio_bounce(blk_add_trace_bio_bounce, NULL);
 	unregister_trace_block_rq_complete(blk_add_trace_rq_complete, NULL);
 	unregister_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL);
+	unregister_trace_block_rq_merge(blk_add_trace_rq_merge, NULL);
 	unregister_trace_block_rq_issue(blk_add_trace_rq_issue, NULL);
 	unregister_trace_block_rq_insert(blk_add_trace_rq_insert, NULL);