1 files changed, 16 insertions, 41 deletions

diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c
index f945621a0e8f..9638b25fd521 100644
--- a/block/blk-mq-cpumap.c
+++ b/block/blk-mq-cpumap.c
@@ -10,53 +10,28 @@
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/cpu.h>
+#include <linux/group_cpus.h>
 
-#include <linux/blk-mq.h>
 #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)
+void blk_mq_map_queues(struct blk_mq_queue_map *qmap)
 {
-	return qmap->queue_offset + (cpu % nr_queues);
-}
-
-static int get_first_sibling(unsigned int cpu)
-{
-	unsigned int ret;
-
-	ret = cpumask_first(topology_sibling_cpumask(cpu));
-	if (ret < nr_cpu_ids)
-		return ret;
-
-	return cpu;
-}
-
-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;
-
-	for_each_possible_cpu(cpu) {
-		/*
-		 * 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);
-		} else {
-			first_sibling = get_first_sibling(cpu);
-			if (first_sibling == cpu)
-				map[cpu] = cpu_to_queue_index(qmap, nr_queues, cpu);
-			else
-				map[cpu] = map[first_sibling];
-		}
+	const struct cpumask *masks;
+	unsigned int queue, cpu;
+
+	masks = group_cpus_evenly(qmap->nr_queues);
+	if (!masks) {
+		for_each_possible_cpu(cpu)
+			qmap->mq_map[cpu] = qmap->queue_offset;
+		return;
 	}
 
-	return 0;
+	for (queue = 0; queue < qmap->nr_queues; queue++) {
+		for_each_cpu(cpu, &masks[queue])
+			qmap->mq_map[cpu] = qmap->queue_offset + queue;
+	}
+	kfree(masks);
 }
 EXPORT_SYMBOL_GPL(blk_mq_map_queues);
 
@@ -74,7 +49,7 @@ int blk_mq_hw_queue_to_node(struct blk_mq_queue_map *qmap, unsigned int index)
 
 	for_each_possible_cpu(i) {
 		if (index == qmap->mq_map[i])
-			return local_memory_node(cpu_to_node(i));
+			return cpu_to_node(i);
 	}
 
 	return NUMA_NO_NODE;