blk-mq: Build default queue map via group_cpus_evenly()

The default queue mapping builder of blk_mq_map_queues doesn't take NUMA
topo into account, so the built mapping is pretty bad, since CPUs
belonging to different NUMA node are assigned to same queue. It is
observed that IOPS drops by ~30% when running two jobs on same hctx
of null_blk from two CPUs belonging to two NUMA nodes compared with
from same NUMA node.

Address the issue by reusing group_cpus_evenly() for building queue mapping
since group_cpus_evenly() does group cpus according to CPU/NUMA locality.

Also performance data becomes more stable with this given correct queue
mapping is applied wrt. numa locality viewpoint, for example, on one two
nodes arm64 machine with 160 cpus, node 0(cpu 0~79), node 1(cpu 80~159):

1) modprobe null_blk nr_devices=1 submit_queues=2

2) run 'fio(t/io_uring -p 0 -n 4 -r 20 /dev/nullb0)', and observe that
IOPS becomes much stable on multiple tests:

 - unpatched: IOPS is 2.5M ~ 4.5M
 - patched:   IOPS is 4.3M ~ 5.0M

Lots of drivers may benefit from the change, such as nvme pci poll,
nvme tcp, ...
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Reviewed-by: Jens Axboe <axboe@kernel.dk>                                                                                                                                                                                                    
Link: https://lore.kernel.org/r/20221227022905.352674-7-ming.lei@redhat.com

block/blk-mq-cpumap.c

@@ -10,66 +10,29 @@
 #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 queue_index(struct blk_mq_queue_map *qmap,
-		       unsigned int nr_queues, const int q)
-{
-	return qmap->queue_offset + (q % 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;
-}
-
 void 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, 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++);
+	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;
 	}
 
-	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 (q < nr_queues) {
-			map[cpu] = queue_index(qmap, nr_queues, q++);
-		} else {
-			first_sibling = get_first_sibling(cpu);
-			if (first_sibling == cpu)
-				map[cpu] = queue_index(qmap, nr_queues, q++);
-			else
-				map[cpu] = map[first_sibling];
-		}
+	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);