[PATCH] make blk_mq_map_queues more friendly for cpu topology

[luferry]

under virtual machine environment, cpu topology may differ
from normal physical server.

for example (machine with 4 cores, 2 threads per core):

normal physical server:
core-id   thread-0-id  thread-1-id
0         0            4
1         1            5
2         2            6
3         3            7

virtual machine:
core-id   thread-0-id  thread-1-id
0         0            1
1         2            3
2         4            5
3         6            7

If we attach disk with multi queues to virtual machine,
blk_mq_map_queues can cause serious imbalance.this will lead to
performance impact on system IO.

Here is the qemu cmdline:
"-smp 8,sockets=1,cores=8,threads=2"
"-device virtio-blk-pci,drive=drive0,id=device0,num-queues=4,vectors=2"

when vectors less than num-queues, virtio-blk will fallback to
blk_mq_map_queues

Before this patch:
[root@blk-mq ~]# cat /sys/block/vd*/mq/*/cpu_list
0, 4, 5, 8, 9, 12, 13
1
2, 6, 7, 10, 11, 14, 15
3

After this patch:
[root@blk-mq ~]# cat /sys/block/vd*/mq/*/cpu_list
0, 1, 8, 9
2, 3, 10, 11
4, 5, 12, 13
6, 7, 14, 15

Signed-off-by: luferry <luferry@xxxxxxx>
---
 block/blk-mq-cpumap.c | 31 +++++++++++++++++++++++--------
 1 file changed, 23 insertions(+), 8 deletions(-)

diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c
index 03a534820271..2eb78ad4a49b 100644
--- a/block/blk-mq-cpumap.c
+++ b/block/blk-mq-cpumap.c
@@ -35,22 +35,37 @@ 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, core = 0;
+	bool core_map = false;
 
+	/*
+	 * If core num is euqal or over nr_queues,
+	 * there be sure at least per core per queue
+	 */
+	for_each_possible_cpu(cpu) {
+		if (get_first_sibling(cpu) == cpu)
+			core++;
+	}
+	if (core >= nr_queues)
+		core_map = true;
+
+	core = 0;
 	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
+		 * If cores is enough, just do map between cores and queues
+		 * else will do sequential mapping between CPUs and queues first.
+		 * For other cpus, we have some number of threads per cores
+		 * then map sibling threads to the same queue for
 		 * performace optimizations.
 		 */
-		if (cpu < nr_queues) {
+		if (!core_map && 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
+			if (first_sibling == cpu) {
+				map[cpu] = cpu_to_queue_index(qmap, nr_queues, core);
+				core++;
+			} else
 				map[cpu] = map[first_sibling];
 		}
 	}
-- 
2.14.1.40.g8e62ba1