blk-mq: balance mapping between present CPUs and queues

Spread queues among present CPUs first, then building mapping on other
non-present CPUs.

So we can minimize count of dead queues which are mapped by un-present
CPUs only. Then bad IO performance can be avoided by unbalanced mapping
between present CPUs and queues.

The similar policy has been applied on Managed IRQ affinity.

Cc: Yi Zhang <yi.zhang@redhat.com>
Reported-by: Yi Zhang <yi.zhang@redhat.com>
Reviewed-by: Bob Liu <bob.liu@oracle.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c
index f945621..0157f2b 100644
--- a/block/blk-mq-cpumap.c
+++ b/block/blk-mq-cpumap.c
@@ -15,10 +15,10 @@
 #include "blk.h"
 #include "blk-mq.h"
 
-static int cpu_to_queue_index(struct blk_mq_queue_map *qmap,
-			      unsigned int nr_queues, const int cpu)
+static int queue_index(struct blk_mq_queue_map *qmap,
+		       unsigned int nr_queues, const int q)
 {
-	return qmap->queue_offset + (cpu % nr_queues);
+	return qmap->queue_offset + (q % nr_queues);
 }
 
 static int get_first_sibling(unsigned int cpu)
@@ -36,21 +36,36 @@ int blk_mq_map_queues(struct blk_mq_queue_map *qmap)
 {
 	unsigned int *map = qmap->mq_map;
 	unsigned int nr_queues = qmap->nr_queues;
-	unsigned int cpu, first_sibling;
+	unsigned int cpu, first_sibling, q = 0;
+
+	for_each_possible_cpu(cpu)
+		map[cpu] = -1;
+
+	/*
+	 * Spread queues among present CPUs first for minimizing
+	 * count of dead queues which are mapped by all un-present CPUs
+	 */
+	for_each_present_cpu(cpu) {
+		if (q >= nr_queues)
+			break;
+		map[cpu] = queue_index(qmap, nr_queues, q++);
+	}
 
 	for_each_possible_cpu(cpu) {
+		if (map[cpu] != -1)
+			continue;
 		/*
 		 * First do sequential mapping between CPUs and queues.
 		 * In case we still have CPUs to map, and we have some number of
 		 * threads per cores then map sibling threads to the same queue
 		 * for performance optimizations.
 		 */
-		if (cpu < nr_queues) {
-			map[cpu] = cpu_to_queue_index(qmap, nr_queues, cpu);
+		if (q < nr_queues) {
+			map[cpu] = queue_index(qmap, nr_queues, q++);
 		} else {
 			first_sibling = get_first_sibling(cpu);
 			if (first_sibling == cpu)
-				map[cpu] = cpu_to_queue_index(qmap, nr_queues, cpu);
+				map[cpu] = queue_index(qmap, nr_queues, q++);
 			else
 				map[cpu] = map[first_sibling];
 		}