blk-mq: Create hctx for each present CPU

Currently we only create hctx for online CPUs, which can lead to a lot
of churn due to frequent soft offline / online operations.  Instead
allocate one for each present CPU to avoid this and dramatically simplify
the code.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Cc: Keith Busch <keith.busch@intel.com>
Cc: linux-block@vger.kernel.org
Cc: linux-nvme@lists.infradead.org
Link: http://lkml.kernel.org/r/20170626102058.10200-3-hch@lst.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

block/blk-mq.c

@@ -37,9 +37,6 @@
 #include "blk-wbt.h"
 #include "blk-mq-sched.h"
 
-static DEFINE_MUTEX(all_q_mutex);
-static LIST_HEAD(all_q_list);
-
 static void blk_mq_poll_stats_start(struct request_queue *q);
 static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb);
 static void __blk_mq_stop_hw_queues(struct request_queue *q, bool sync);
@@ -1975,8 +1972,8 @@ 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 online, the cpu is mapped to first hctx */
-		if (!cpu_online(i))
+		/* 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);
@@ -2019,8 +2016,7 @@ static void blk_mq_free_map_and_requests(struct blk_mq_tag_set *set,
 	}
 }
 
-static void blk_mq_map_swqueue(struct request_queue *q,
-			       const struct cpumask *online_mask)
+static void blk_mq_map_swqueue(struct request_queue *q)
 {
 	unsigned int i, hctx_idx;
 	struct blk_mq_hw_ctx *hctx;
@@ -2038,13 +2034,11 @@ static void blk_mq_map_swqueue(struct request_queue *q,
 	}
 
 	/*
-	 * Map software to hardware queues
+	 * Map software to hardware queues.
+	 *
+	 * If the cpu isn't present, the cpu is mapped to first hctx.
 	 */
-	for_each_possible_cpu(i) {
-		/* If the cpu isn't online, the cpu is mapped to first hctx */
-		if (!cpumask_test_cpu(i, online_mask))
-			continue;
-
+	for_each_present_cpu(i) {
 		hctx_idx = q->mq_map[i];
 		/* unmapped hw queue can be remapped after CPU topo changed */
 		if (!set->tags[hctx_idx] &&
@@ -2330,16 +2324,8 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 		blk_queue_softirq_done(q, set->ops->complete);
 
 	blk_mq_init_cpu_queues(q, set->nr_hw_queues);
-
-	get_online_cpus();
-	mutex_lock(&all_q_mutex);
-
-	list_add_tail(&q->all_q_node, &all_q_list);
 	blk_mq_add_queue_tag_set(set, q);
-	blk_mq_map_swqueue(q, cpu_online_mask);
-
-	mutex_unlock(&all_q_mutex);
-	put_online_cpus();
+	blk_mq_map_swqueue(q);
 
 	if (!(set->flags & BLK_MQ_F_NO_SCHED)) {
 		int ret;
@@ -2365,18 +2351,12 @@ void blk_mq_free_queue(struct request_queue *q)
 {
 	struct blk_mq_tag_set	*set = q->tag_set;
 
-	mutex_lock(&all_q_mutex);
-	list_del_init(&q->all_q_node);
-	mutex_unlock(&all_q_mutex);
-
 	blk_mq_del_queue_tag_set(q);
-
 	blk_mq_exit_hw_queues(q, set, set->nr_hw_queues);
 }
 
 /* Basically redo blk_mq_init_queue with queue frozen */
-static void blk_mq_queue_reinit(struct request_queue *q,
-				const struct cpumask *online_mask)
+static void blk_mq_queue_reinit(struct request_queue *q)
 {
 	WARN_ON_ONCE(!atomic_read(&q->mq_freeze_depth));
 
@@ -2389,76 +2369,12 @@ static void blk_mq_queue_reinit(struct request_queue *q,
 	 * involves free and re-allocate memory, worthy doing?)
 	 */
 
-	blk_mq_map_swqueue(q, online_mask);
+	blk_mq_map_swqueue(q);
 
 	blk_mq_sysfs_register(q);
 	blk_mq_debugfs_register_hctxs(q);
 }
 
-/*
- * New online cpumask which is going to be set in this hotplug event.
- * Declare this cpumasks as global as cpu-hotplug operation is invoked
- * one-by-one and dynamically allocating this could result in a failure.
- */
-static struct cpumask cpuhp_online_new;
-
-static void blk_mq_queue_reinit_work(void)
-{
-	struct request_queue *q;
-
-	mutex_lock(&all_q_mutex);
-	/*
-	 * We need to freeze and reinit all existing queues.  Freezing
-	 * involves synchronous wait for an RCU grace period and doing it
-	 * one by one may take a long time.  Start freezing all queues in
-	 * one swoop and then wait for the completions so that freezing can
-	 * take place in parallel.
-	 */
-	list_for_each_entry(q, &all_q_list, all_q_node)
-		blk_freeze_queue_start(q);
-	list_for_each_entry(q, &all_q_list, all_q_node)
-		blk_mq_freeze_queue_wait(q);
-
-	list_for_each_entry(q, &all_q_list, all_q_node)
-		blk_mq_queue_reinit(q, &cpuhp_online_new);
-
-	list_for_each_entry(q, &all_q_list, all_q_node)
-		blk_mq_unfreeze_queue(q);
-
-	mutex_unlock(&all_q_mutex);
-}
-
-static int blk_mq_queue_reinit_dead(unsigned int cpu)
-{
-	cpumask_copy(&cpuhp_online_new, cpu_online_mask);
-	blk_mq_queue_reinit_work();
-	return 0;
-}
-
-/*
- * Before hotadded cpu starts handling requests, new mappings must be
- * established.  Otherwise, these requests in hw queue might never be
- * dispatched.
- *
- * For example, there is a single hw queue (hctx) and two CPU queues (ctx0
- * for CPU0, and ctx1 for CPU1).
- *
- * Now CPU1 is just onlined and a request is inserted into ctx1->rq_list
- * and set bit0 in pending bitmap as ctx1->index_hw is still zero.
- *
- * And then while running hw queue, blk_mq_flush_busy_ctxs() finds bit0 is set
- * in pending bitmap and tries to retrieve requests in hctx->ctxs[0]->rq_list.
- * But htx->ctxs[0] is a pointer to ctx0, so the request in ctx1->rq_list is
- * ignored.
- */
-static int blk_mq_queue_reinit_prepare(unsigned int cpu)
-{
-	cpumask_copy(&cpuhp_online_new, cpu_online_mask);
-	cpumask_set_cpu(cpu, &cpuhp_online_new);
-	blk_mq_queue_reinit_work();
-	return 0;
-}
-
 static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
 {
 	int i;
@@ -2669,7 +2585,7 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 	blk_mq_update_queue_map(set);
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
 		blk_mq_realloc_hw_ctxs(set, q);
-		blk_mq_queue_reinit(q, cpu_online_mask);
+		blk_mq_queue_reinit(q);
 	}
 
 	list_for_each_entry(q, &set->tag_list, tag_set_list)
@@ -2885,24 +2801,10 @@ bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie)
 }
 EXPORT_SYMBOL_GPL(blk_mq_poll);
 
-void blk_mq_disable_hotplug(void)
-{
-	mutex_lock(&all_q_mutex);
-}
-
-void blk_mq_enable_hotplug(void)
-{
-	mutex_unlock(&all_q_mutex);
-}
-
 static int __init blk_mq_init(void)
 {
 	cpuhp_setup_state_multi(CPUHP_BLK_MQ_DEAD, "block/mq:dead", NULL,
 				blk_mq_hctx_notify_dead);
-
-	cpuhp_setup_state_nocalls(CPUHP_BLK_MQ_PREPARE, "block/mq:prepare",
-				  blk_mq_queue_reinit_prepare,
-				  blk_mq_queue_reinit_dead);
 	return 0;
 }
 subsys_initcall(blk_mq_init);

block/blk-mq.h

@@ -56,11 +56,6 @@ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 				bool at_head);
 void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 				struct list_head *list);
-/*
- * CPU hotplug helpers
- */
-void blk_mq_enable_hotplug(void);
-void blk_mq_disable_hotplug(void);
 
 /*
  * CPU -> queue mappings

include/linux/cpuhotplug.h

@@ -58,7 +58,6 @@ enum cpuhp_state {
 	CPUHP_XEN_EVTCHN_PREPARE,
 	CPUHP_ARM_SHMOBILE_SCU_PREPARE,
 	CPUHP_SH_SH3X_PREPARE,
-	CPUHP_BLK_MQ_PREPARE,
 	CPUHP_NET_FLOW_PREPARE,
 	CPUHP_TOPOLOGY_PREPARE,
 	CPUHP_NET_IUCV_PREPARE,