block: strict rq_affinity

Some systems benefit from completions always being steered to the strict
requester cpu rather than the looser "per-socket" steering that
blk_cpu_to_group() attempts by default. This is because the first
CPU in the group mask ends up being completely overloaded with work,
while the others (including the original submitter) has power left
to spare.

Allow the strict mode to be set by writing '2' to the sysfs control
file. This is identical to the scheme used for the nomerges file,
where '2' is a more aggressive setting than just being turned on.

echo 2 > /sys/block/<bdev>/queue/rq_affinity

Cc: Christoph Hellwig <hch@infradead.org>
Cc: Roland Dreier <roland@purestorage.com>
Tested-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index ee9c216..475fab8 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -103,22 +103,25 @@
 
 void __blk_complete_request(struct request *req)
 {
+	int ccpu, cpu, group_cpu = NR_CPUS;
 	struct request_queue *q = req->q;
 	unsigned long flags;
-	int ccpu, cpu, group_cpu;
 
 	BUG_ON(!q->softirq_done_fn);
 
 	local_irq_save(flags);
 	cpu = smp_processor_id();
-	group_cpu = blk_cpu_to_group(cpu);
 
 	/*
 	 * Select completion CPU
 	 */
-	if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags) && req->cpu != -1)
+	if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags) && req->cpu != -1) {
 		ccpu = req->cpu;
-	else
+		if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags)) {
+			ccpu = blk_cpu_to_group(ccpu);
+			group_cpu = blk_cpu_to_group(cpu);
+		}
+	} else
 		ccpu = cpu;
 
 	if (ccpu == cpu || ccpu == group_cpu) {