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

BugLink: http://bugs.launchpad.net/bugs/1759723
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>
(cherry picked from commit 20e4d813931961fe26d26a1e98b3aba6ec00b130)
Signed-off-by: Jose Ricardo Ziviani <joserz@linux.ibm.com>
Acked-by: Kleber Sacilotto de Souza <kleber.souza@canonical.com>
Acked-by: Stefan Bader <stefan.bader@canonical.com>
Signed-off-by: Khalid Elmously <khalid.elmously@canonical.com>

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 8ed71e35e7c3ffee8dec44a5477253514a67ff84..8939e16b854628bc520be23254604866c9977d52 100644 (file)
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -443,7 +443,7 @@ 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);
@@ -1262,9 +1262,10 @@ 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;
@@ -2136,16 +2137,11 @@ 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));
        }
@@ -2202,7 +2198,7 @@ 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] &&
@@ -2256,7 +2252,8 @@ 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;
        }
 }