block: inherit CPU completion on bio->rq and rq->rq merges

Somewhat incomplete, as we do allow merges of requests and bios
that have different completion CPUs given. This is done on the
assumption that a larger IO is still more beneficial than CPU
locality.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
diff --git a/block/blk-core.c b/block/blk-core.c
index 5484838..b9a252c 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1134,6 +1134,8 @@
 		req->biotail = bio;
 		req->nr_sectors = req->hard_nr_sectors += nr_sectors;
 		req->ioprio = ioprio_best(req->ioprio, prio);
+		if (!blk_rq_cpu_valid(req))
+			req->cpu = bio->bi_comp_cpu;
 		drive_stat_acct(req, 0);
 		if (!attempt_back_merge(q, req))
 			elv_merged_request(q, req, el_ret);
@@ -1161,6 +1163,8 @@
 		req->sector = req->hard_sector = bio->bi_sector;
 		req->nr_sectors = req->hard_nr_sectors += nr_sectors;
 		req->ioprio = ioprio_best(req->ioprio, prio);
+		if (!blk_rq_cpu_valid(req))
+			req->cpu = bio->bi_comp_cpu;
 		drive_stat_acct(req, 0);
 		if (!attempt_front_merge(q, req))
 			elv_merged_request(q, req, el_ret);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index c77196d..908d3e1 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -400,6 +400,8 @@
 	}
 
 	req->ioprio = ioprio_best(req->ioprio, next->ioprio);
+	if (blk_rq_cpu_valid(next))
+		req->cpu = next->cpu;
 
 	__blk_put_request(q, next);
 	return 1;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 93204bf..12df8ef 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -545,6 +545,7 @@
 #define blk_pm_request(rq)	\
 	(blk_pm_suspend_request(rq) || blk_pm_resume_request(rq))
 
+#define blk_rq_cpu_valid(rq)	((rq)->cpu != -1)
 #define blk_sorted_rq(rq)	((rq)->cmd_flags & REQ_SORTED)
 #define blk_barrier_rq(rq)	((rq)->cmd_flags & REQ_HARDBARRIER)
 #define blk_fua_rq(rq)		((rq)->cmd_flags & REQ_FUA)