[PATCH V6 3/8] blk-mq: prepare for draining IO when hctx's all CPUs are offline

[Ming Lei <ming.lei@redhat.com>]

Most of blk-mq drivers depend on managed IRQ's auto-affinity to setup
up queue mapping. Thomas mentioned the following point[1]:

"
 That was the constraint of managed interrupts from the very beginning:

  The driver/subsystem has to quiesce the interrupt line and the associated
  queue _before_ it gets shutdown in CPU unplug and not fiddle with it
  until it's restarted by the core when the CPU is plugged in again.
"

However, current blk-mq implementation doesn't quiesce hw queue before
the last CPU in the hctx is shutdown. Even worse, CPUHP_BLK_MQ_DEAD is
one cpuhp state handled after the CPU is down, so there isn't any chance
to quiesce hctx for blk-mq wrt. CPU hotplug.

Add new cpuhp state of CPUHP_AP_BLK_MQ_ONLINE for blk-mq to stop queues
and wait for completion of in-flight requests.

We will stop hw queue and wait for completion of in-flight requests
when one hctx is becoming dead in the following patch. This way may
cause dead-lock for some stacking blk-mq drivers, such as dm-rq and
loop.

Add blk-mq flag of BLK_MQ_F_NO_MANAGED_IRQ and mark it for dm-rq and
loop, so we needn't to wait for completion of in-flight requests from
dm-rq & loop, then the potential dead-lock can be avoided.

[1] https://lore.kernel.org/linux-block/alpine.DEB.2.21.1904051331270.1802@nanos.tec.linutronix.de/

Cc: John Garry <john.garry@huawei.com>
Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
---
 block/blk-mq-debugfs.c     |  1 +
 block/blk-mq.c             | 13 +++++++++++++
 drivers/block/loop.c       |  2 +-
 drivers/md/dm-rq.c         |  2 +-
 include/linux/blk-mq.h     |  3 +++
 include/linux/cpuhotplug.h |  1 +
 6 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index d6de4f7f38cb..b62390918ca5 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -240,6 +240,7 @@ static const char *const hctx_flag_name[] = {
 	HCTX_FLAG_NAME(TAG_SHARED),
 	HCTX_FLAG_NAME(BLOCKING),
 	HCTX_FLAG_NAME(NO_SCHED),
+	HCTX_FLAG_NAME(NO_MANAGED_IRQ),
 };
 #undef HCTX_FLAG_NAME
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index f6f1ba3ff783..4ee8695142c0 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2249,6 +2249,11 @@ int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
 	return -ENOMEM;
 }
 
+static int blk_mq_hctx_notify_online(unsigned int cpu, struct hlist_node *node)
+{
+	return 0;
+}
+
 /*
  * 'cpu' is going away. splice any existing rq_list entries from this
  * software queue to the hw queue dispatch list, and ensure that it
@@ -2285,6 +2290,9 @@ static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node)
 
 static void blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx)
 {
+	if (!(hctx->flags & BLK_MQ_F_NO_MANAGED_IRQ))
+		cpuhp_state_remove_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE,
+						    &hctx->cpuhp_online);
 	cpuhp_state_remove_instance_nocalls(CPUHP_BLK_MQ_DEAD,
 					    &hctx->cpuhp_dead);
 }
@@ -2344,6 +2352,9 @@ static int blk_mq_init_hctx(struct request_queue *q,
 {
 	hctx->queue_num = hctx_idx;
 
+	if (!(hctx->flags & BLK_MQ_F_NO_MANAGED_IRQ))
+		cpuhp_state_add_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE,
+				&hctx->cpuhp_online);
 	cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead);
 
 	hctx->tags = set->tags[hctx_idx];
@@ -3588,6 +3599,8 @@ 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_multi(CPUHP_AP_BLK_MQ_ONLINE, "block/mq:online",
+				NULL, blk_mq_hctx_notify_online);
 	return 0;
 }
 subsys_initcall(blk_mq_init);
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 739b372a5112..651dadd9be12 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -2012,7 +2012,7 @@ static int loop_add(struct loop_device **l, int i)
 	lo->tag_set.queue_depth = 128;
 	lo->tag_set.numa_node = NUMA_NO_NODE;
 	lo->tag_set.cmd_size = sizeof(struct loop_cmd);
-	lo->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
+	lo->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_NO_MANAGED_IRQ;
 	lo->tag_set.driver_data = lo;
 
 	err = blk_mq_alloc_tag_set(&lo->tag_set);
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index 3f8577e2c13b..5f1ff70ac029 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -547,7 +547,7 @@ int dm_mq_init_request_queue(struct mapped_device *md, struct dm_table *t)
 	md->tag_set->ops = &dm_mq_ops;
 	md->tag_set->queue_depth = dm_get_blk_mq_queue_depth();
 	md->tag_set->numa_node = md->numa_node_id;
-	md->tag_set->flags = BLK_MQ_F_SHOULD_MERGE;
+	md->tag_set->flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_NO_MANAGED_IRQ;
 	md->tag_set->nr_hw_queues = dm_get_blk_mq_nr_hw_queues();
 	md->tag_set->driver_data = md;
 
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index b669e776d4cb..ca2201435a48 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -140,6 +140,8 @@ struct blk_mq_hw_ctx {
 	 */
 	atomic_t		nr_active;
 
+	/** @cpuhp_online: List to store request if CPU is going to die */
+	struct hlist_node	cpuhp_online;
 	/** @cpuhp_dead: List to store request if some CPU die. */
 	struct hlist_node	cpuhp_dead;
 	/** @kobj: Kernel object for sysfs. */
@@ -388,6 +390,7 @@ struct blk_mq_ops {
 enum {
 	BLK_MQ_F_SHOULD_MERGE	= 1 << 0,
 	BLK_MQ_F_TAG_SHARED	= 1 << 1,
+	BLK_MQ_F_NO_MANAGED_IRQ	= 1 << 2,
 	BLK_MQ_F_BLOCKING	= 1 << 5,
 	BLK_MQ_F_NO_SCHED	= 1 << 6,
 	BLK_MQ_F_ALLOC_POLICY_START_BIT = 8,
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index d37c17e68268..8bd2fea6cd59 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -151,6 +151,7 @@ enum cpuhp_state {
 	CPUHP_AP_SMPBOOT_THREADS,
 	CPUHP_AP_X86_VDSO_VMA_ONLINE,
 	CPUHP_AP_IRQ_AFFINITY_ONLINE,
+	CPUHP_AP_BLK_MQ_ONLINE,
 	CPUHP_AP_ARM_MVEBU_SYNC_CLOCKS,
 	CPUHP_AP_X86_INTEL_EPB_ONLINE,
 	CPUHP_AP_PERF_ONLINE,
-- 
2.25.2