blk-mq: simplify queue mapping & schedule with each possisble CPU

The previous patch assigns interrupt vectors to all possible CPUs, so
now hctx can be mapped to possible CPUs, this patch applies this fact
to simplify queue mapping & schedule so that we don't need to handle
CPU hotplug for dealing with physical CPU plug & unplug. With this
simplication, we can work well on physical CPU plug & unplug, which
is a normal use case for VM at least.

Make sure we allocate blk_mq_ctx structures for all possible CPUs, and
set hctx->numa_node for possible CPUs which are mapped to this hctx. And
only choose the online CPUs for schedule.

Reported-by: Christian Borntraeger <borntraeger@de.ibm.com>
Tested-by: Christian Borntraeger <borntraeger@de.ibm.com>
Tested-by: Stefan Haberland <sth@linux.vnet.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Fixes: 4b855ad37194 ("blk-mq: Create hctx for each present CPU")
(merged the three into one because any single one may not work, and fix
selecting online CPUs for scheduler)
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/block/blk-mq.c b/block/blk-mq.c
index afccd08..b3b2003 100644 (file)
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -440,7 +440,7 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
                blk_queue_exit(q);
                return ERR_PTR(-EXDEV);
        }
-       cpu = cpumask_first(alloc_data.hctx->cpumask);
+       cpu = cpumask_first_and(alloc_data.hctx->cpumask, cpu_online_mask);
        alloc_data.ctx = __blk_mq_get_ctx(q, cpu);
 
        rq = blk_mq_get_request(q, NULL, op, &alloc_data);
@@ -1324,9 +1324,10 @@ static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx)
        if (--hctx->next_cpu_batch <= 0) {
                int next_cpu;
 
-               next_cpu = cpumask_next(hctx->next_cpu, hctx->cpumask);
+               next_cpu = cpumask_next_and(hctx->next_cpu, hctx->cpumask,
+                               cpu_online_mask);
                if (next_cpu >= nr_cpu_ids)
-                       next_cpu = cpumask_first(hctx->cpumask);
+                       next_cpu = cpumask_first_and(hctx->cpumask,cpu_online_mask);
 
                hctx->next_cpu = next_cpu;
                hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
@@ -2220,16 +2221,11 @@ static void blk_mq_init_cpu_queues(struct request_queue *q,
                INIT_LIST_HEAD(&__ctx->rq_list);
                __ctx->queue = q;
 
-               /* If the cpu isn't present, the cpu is mapped to first hctx */
-               if (!cpu_present(i))
-                       continue;
-
-               hctx = blk_mq_map_queue(q, i);
-
                /*
                 * Set local node, IFF we have more than one hw queue. If
                 * not, we remain on the home node of the device
                 */
+               hctx = blk_mq_map_queue(q, i);
                if (nr_hw_queues > 1 && hctx->numa_node == NUMA_NO_NODE)
                        hctx->numa_node = local_memory_node(cpu_to_node(i));
        }
@@ -2286,7 +2282,7 @@ static void blk_mq_map_swqueue(struct request_queue *q)
         *
         * If the cpu isn't present, the cpu is mapped to first hctx.
         */
-       for_each_present_cpu(i) {
+       for_each_possible_cpu(i) {
                hctx_idx = q->mq_map[i];
                /* unmapped hw queue can be remapped after CPU topo changed */
                if (!set->tags[hctx_idx] &&
@@ -2340,7 +2336,8 @@ static void blk_mq_map_swqueue(struct request_queue *q)
                /*
                 * Initialize batch roundrobin counts
                 */
-               hctx->next_cpu = cpumask_first(hctx->cpumask);
+               hctx->next_cpu = cpumask_first_and(hctx->cpumask,
+                               cpu_online_mask);
                hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
        }
 }