Merge branch 'for-4.9/block-smp' of git://git.kernel.dk/linux-block

Pull blk-mq CPU hotplug update from Jens Axboe:
 "This is the conversion of blk-mq to the new hotplug state machine"

* 'for-4.9/block-smp' of git://git.kernel.dk/linux-block:
  blk-mq: fixup "Convert to new hotplug state machine"
  blk-mq: Convert to new hotplug state machine
  blk-mq/cpu-notif: Convert to new hotplug state machine

5 files changed, 58 insertions, 149 deletions

diff --git a/block/Makefile b/block/Makefile
index 37a0d93f97bb..36acdd7545be 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -6,7 +6,7 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-tag.o blk-sysfs.o \
 			blk-flush.o blk-settings.o blk-ioc.o blk-map.o \
 			blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \
 			blk-lib.o blk-mq.o blk-mq-tag.o \
-			blk-mq-sysfs.o blk-mq-cpu.o blk-mq-cpumap.o ioctl.o \
+			blk-mq-sysfs.o blk-mq-cpumap.o ioctl.o \
 			genhd.o scsi_ioctl.o partition-generic.o ioprio.o \
 			badblocks.o partitions/
 
diff --git a/block/blk-mq-cpu.c b/block/blk-mq-cpu.c
deleted file mode 100644
index bb3ed488f7b5..000000000000
--- a/block/blk-mq-cpu.c
+++ /dev/null
@@ -1,67 +0,0 @@
-/*
- * CPU notifier helper code for blk-mq
- *
- * Copyright (C) 2013-2014 Jens Axboe
- */
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/blkdev.h>
-#include <linux/list.h>
-#include <linux/llist.h>
-#include <linux/smp.h>
-#include <linux/cpu.h>
-
-#include <linux/blk-mq.h>
-#include "blk-mq.h"
-
-static LIST_HEAD(blk_mq_cpu_notify_list);
-static DEFINE_RAW_SPINLOCK(blk_mq_cpu_notify_lock);
-
-static int blk_mq_main_cpu_notify(struct notifier_block *self,
-				  unsigned long action, void *hcpu)
-{
-	unsigned int cpu = (unsigned long) hcpu;
-	struct blk_mq_cpu_notifier *notify;
-	int ret = NOTIFY_OK;
-
-	raw_spin_lock(&blk_mq_cpu_notify_lock);
-
-	list_for_each_entry(notify, &blk_mq_cpu_notify_list, list) {
-		ret = notify->notify(notify->data, action, cpu);
-		if (ret != NOTIFY_OK)
-			break;
-	}
-
-	raw_spin_unlock(&blk_mq_cpu_notify_lock);
-	return ret;
-}
-
-void blk_mq_register_cpu_notifier(struct blk_mq_cpu_notifier *notifier)
-{
-	BUG_ON(!notifier->notify);
-
-	raw_spin_lock(&blk_mq_cpu_notify_lock);
-	list_add_tail(&notifier->list, &blk_mq_cpu_notify_list);
-	raw_spin_unlock(&blk_mq_cpu_notify_lock);
-}
-
-void blk_mq_unregister_cpu_notifier(struct blk_mq_cpu_notifier *notifier)
-{
-	raw_spin_lock(&blk_mq_cpu_notify_lock);
-	list_del(&notifier->list);
-	raw_spin_unlock(&blk_mq_cpu_notify_lock);
-}
-
-void blk_mq_init_cpu_notifier(struct blk_mq_cpu_notifier *notifier,
-			      int (*fn)(void *, unsigned long, unsigned int),
-			      void *data)
-{
-	notifier->notify = fn;
-	notifier->data = data;
-}
-
-void __init blk_mq_cpu_init(void)
-{
-	hotcpu_notifier(blk_mq_main_cpu_notify, 0);
-}
diff --git a/block/blk-mq.c b/block/blk-mq.c
index b65f572a4faf..ddc2eed64771 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1563,11 +1563,13 @@ fail:
  * software queue to the hw queue dispatch list, and ensure that it
  * gets run.
  */
-static int blk_mq_hctx_cpu_offline(struct blk_mq_hw_ctx *hctx, int cpu)
+static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node)
 {
+	struct blk_mq_hw_ctx *hctx;
 	struct blk_mq_ctx *ctx;
 	LIST_HEAD(tmp);
 
+	hctx = hlist_entry_safe(node, struct blk_mq_hw_ctx, cpuhp_dead);
 	ctx = __blk_mq_get_ctx(hctx->queue, cpu);
 
 	spin_lock(&ctx->lock);
@@ -1578,30 +1580,20 @@ static int blk_mq_hctx_cpu_offline(struct blk_mq_hw_ctx *hctx, int cpu)
 	spin_unlock(&ctx->lock);
 
 	if (list_empty(&tmp))
-		return NOTIFY_OK;
+		return 0;
 
 	spin_lock(&hctx->lock);
 	list_splice_tail_init(&tmp, &hctx->dispatch);
 	spin_unlock(&hctx->lock);
 
 	blk_mq_run_hw_queue(hctx, true);
-	return NOTIFY_OK;
+	return 0;
 }
 
-static int blk_mq_hctx_notify(void *data, unsigned long action,
-			      unsigned int cpu)
+static void blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx)
 {
-	struct blk_mq_hw_ctx *hctx = data;
-
-	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN)
-		return blk_mq_hctx_cpu_offline(hctx, cpu);
-
-	/*
-	 * In case of CPU online, tags may be reallocated
-	 * in blk_mq_map_swqueue() after mapping is updated.
-	 */
-
-	return NOTIFY_OK;
+	cpuhp_state_remove_instance_nocalls(CPUHP_BLK_MQ_DEAD,
+					    &hctx->cpuhp_dead);
 }
 
 /* hctx->ctxs will be freed in queue's release handler */
@@ -1621,7 +1613,7 @@ static void blk_mq_exit_hctx(struct request_queue *q,
 	if (set->ops->exit_hctx)
 		set->ops->exit_hctx(hctx, hctx_idx);
 
-	blk_mq_unregister_cpu_notifier(&hctx->cpu_notifier);
+	blk_mq_remove_cpuhp(hctx);
 	blk_free_flush_queue(hctx->fq);
 	sbitmap_free(&hctx->ctx_map);
 }
@@ -1668,9 +1660,7 @@ static int blk_mq_init_hctx(struct request_queue *q,
 	hctx->queue_num = hctx_idx;
 	hctx->flags = set->flags & ~BLK_MQ_F_TAG_SHARED;
 
-	blk_mq_init_cpu_notifier(&hctx->cpu_notifier,
-					blk_mq_hctx_notify, hctx);
-	blk_mq_register_cpu_notifier(&hctx->cpu_notifier);
+	cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead);
 
 	hctx->tags = set->tags[hctx_idx];
 
@@ -1715,8 +1705,7 @@ static int blk_mq_init_hctx(struct request_queue *q,
  free_ctxs:
 	kfree(hctx->ctxs);
  unregister_cpu_notifier:
-	blk_mq_unregister_cpu_notifier(&hctx->cpu_notifier);
-
+	blk_mq_remove_cpuhp(hctx);
 	return -1;
 }
 
@@ -2089,50 +2078,18 @@ static void blk_mq_queue_reinit(struct request_queue *q,
 	blk_mq_sysfs_register(q);
 }
 
-static int blk_mq_queue_reinit_notify(struct notifier_block *nb,
-				      unsigned long action, void *hcpu)
+/*
+ * 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;
-	int cpu = (unsigned long)hcpu;
-	/*
-	 * 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 online_new;
-
-	/*
-	 * 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, 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.
-	 */
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_DEAD:
-	case CPU_UP_CANCELED:
-		cpumask_copy(&online_new, cpu_online_mask);
-		break;
-	case CPU_UP_PREPARE:
-		cpumask_copy(&online_new, cpu_online_mask);
-		cpumask_set_cpu(cpu, &online_new);
-		break;
-	default:
-		return NOTIFY_OK;
-	}
 
 	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
@@ -2153,13 +2110,43 @@ static int blk_mq_queue_reinit_notify(struct notifier_block *nb,
 	}
 
 	list_for_each_entry(q, &all_q_list, all_q_node)
-		blk_mq_queue_reinit(q, &online_new);
+		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);
-	return NOTIFY_OK;
+}
+
+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, 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)
@@ -2378,10 +2365,12 @@ void blk_mq_enable_hotplug(void)
 
 static int __init blk_mq_init(void)
 {
-	blk_mq_cpu_init();
-
-	hotcpu_notifier(blk_mq_queue_reinit_notify, 0);
+	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);
diff --git a/block/blk-mq.h b/block/blk-mq.h
index df6474cb5a4c..e5d25249028c 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -32,13 +32,6 @@ void blk_mq_wake_waiters(struct request_queue *q);
 /*
  * CPU hotplug helpers
  */
-struct blk_mq_cpu_notifier;
-void blk_mq_init_cpu_notifier(struct blk_mq_cpu_notifier *notifier,
-			      int (*fn)(void *, unsigned long, unsigned int),
-			      void *data);
-void blk_mq_register_cpu_notifier(struct blk_mq_cpu_notifier *notifier);
-void blk_mq_unregister_cpu_notifier(struct blk_mq_cpu_notifier *notifier);
-void blk_mq_cpu_init(void);
 void blk_mq_enable_hotplug(void);
 void blk_mq_disable_hotplug(void);
 
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index ef6aebf291ed..535ab2e13d2e 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -7,12 +7,6 @@
 struct blk_mq_tags;
 struct blk_flush_queue;
 
-struct blk_mq_cpu_notifier {
-	struct list_head list;
-	void *data;
-	int (*notify)(void *data, unsigned long action, unsigned int cpu);
-};
-
 struct blk_mq_hw_ctx {
 	struct {
 		spinlock_t		lock;
@@ -53,7 +47,7 @@ struct blk_mq_hw_ctx {
 
 	struct delayed_work	delay_work;
 
-	struct blk_mq_cpu_notifier	cpu_notifier;
+	struct hlist_node	cpuhp_dead;
 	struct kobject		kobj;
 
 	unsigned long		poll_considered;