[PATCH v4 1/2] blk-mq: add async quiesce interface

[Sagi Grimberg]

>> +void blk_mq_quiesce_queue_async(struct request_queue *q)
>> +{
>> +	struct blk_mq_hw_ctx *hctx;
>> +	unsigned int i;
>> +	int rcu = false;
>> +
>> +	blk_mq_quiesce_queue_nowait(q);
>> +
>> +	queue_for_each_hw_ctx(q, hctx, i) {
>> +		hctx->rcu_sync = kmalloc(sizeof(*hctx->rcu_sync), GFP_KERNEL);
>> +		if (!hctx->rcu_sync) {
>> +			/* fallback to serial rcu sync */
>> +			if (hctx->flags & BLK_MQ_F_BLOCKING)
>> +				synchronize_srcu(hctx->srcu);
>> +			else
>> +				rcu = true;
>> +		} else {
>> +			init_completion(&hctx->rcu_sync->completion);
>> +			init_rcu_head(&hctx->rcu_sync->head);
>> +			if (hctx->flags & BLK_MQ_F_BLOCKING)
>> +				call_srcu(hctx->srcu, &hctx->rcu_sync->head,
>> +					wakeme_after_rcu);
>> +			else
>> +				call_rcu(&hctx->rcu_sync->head,
>> +					wakeme_after_rcu);
>> +		}
>> +	}
>> +	if (rcu)
>> +		synchronize_rcu();
>> +}
>> +EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue_async);
> 
> This won't always be async, and that might matter to some users. I think
> it'd be better to put the fallback path into the _wait() part instead,
> since the caller should expect that to be blocking/waiting as the name
> implies.
> 
> Nit picking, but...

Makes sense..

I thought more about Keith suggestion for an interface that accepts a
tagset. It allows us to decide what we do based on the tagset itself
which is now passed in the interface.

What do you think about:
--
diff --git a/block/blk-mq.c b/block/blk-mq.c
index abcf590f6238..d4b24aa1a766 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -209,6 +209,43 @@ void blk_mq_quiesce_queue_nowait(struct 
request_queue *q)
  }
  EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue_nowait);

+static void blk_mq_quiesce_queue_async(struct request_queue *q)
+{
+       struct blk_mq_hw_ctx *hctx;
+       unsigned int i;
+
+       blk_mq_quiesce_queue_nowait(q);
+
+       queue_for_each_hw_ctx(q, hctx, i) {
+               if (!(hctx->flags & BLK_MQ_F_BLOCKING))
+                       continue;
+
+               hctx->rcu_sync = kmalloc(sizeof(*hctx->rcu_sync), 
GFP_KERNEL);
+               if (!hctx->rcu_sync)
+                       continue;
+
+               init_completion(&hctx->rcu_sync->completion);
+               init_rcu_head(&hctx->rcu_sync->head);
+               call_srcu(hctx->srcu, &hctx->rcu_sync->head,
+                               wakeme_after_rcu);
+       }
+}
+
+static void blk_mq_quiesce_queue_async_wait(struct request_queue *q)
+{
+       struct blk_mq_hw_ctx *hctx;
+       unsigned int i;
+
+       queue_for_each_hw_ctx(q, hctx, i) {
+               if (!hctx->rcu_sync) {
+                       synchronize_srcu(hctx->srcu);
+                       continue;
+               }
+               wait_for_completion(&hctx->rcu_sync->completion);
+               destroy_rcu_head(&hctx->rcu_sync->head);
+       }
+}
+
  /**
   * blk_mq_quiesce_queue() - wait until all ongoing dispatches have 
finished
   * @q: request queue.
@@ -2884,6 +2921,39 @@ static void queue_set_hctx_shared(struct 
request_queue *q, bool shared)
         }
  }

+void blk_mq_quiesce_tagset(struct blk_mq_tag_set *set)
+{
+       struct request_queue *q;
+
+       mutex_lock(&set->tag_list_lock);
+       list_for_each_entry(q, &set->tag_list, tag_set_list) {
+               if (!(set->flags & BLK_MQ_F_BLOCKING))
+                       blk_mq_quiesce_queue_nowait(q);
+               else
+                       blk_mq_quiesce_queue_async(q);
+       }
+
+       if (!(set->flags & BLK_MQ_F_BLOCKING)) {
+               synchronize_rcu();
+       } else {
+               list_for_each_entry(q, &set->tag_list, tag_set_list)
+                       blk_mq_quiesce_queue_async_wait(q);
+       }
+       mutex_unlock(&set->tag_list_lock);
+}
+EXPORT_SYMBOL_GPL(blk_mq_quiesce_tagset);
+
+void blk_mq_unquiesce_tagset(struct blk_mq_tag_set *set)
+{
+       struct request_queue *q;
+
+       mutex_lock(&set->tag_list_lock);
+       list_for_each_entry(q, &set->tag_list, tag_set_list)
+               blk_mq_unquiesce_queue(q);
+       mutex_unlock(&set->tag_list_lock);
+}
+EXPORT_SYMBOL_GPL(blk_mq_unquiesce_tagset);
+
  static void blk_mq_update_tag_set_depth(struct blk_mq_tag_set *set,
                                         bool shared)
  {
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 23230c1d031e..a85f2dedc947 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -5,6 +5,7 @@
  #include <linux/blkdev.h>
  #include <linux/sbitmap.h>
  #include <linux/srcu.h>
+#include <linux/rcupdate_wait.h>

  struct blk_mq_tags;
  struct blk_flush_queue;
@@ -170,6 +171,7 @@ struct blk_mq_hw_ctx {
          */
         struct list_head        hctx_list;

+       struct rcu_synchronize  *rcu_sync;
         /**
          * @srcu: Sleepable RCU. Use as lock when type of the hardware 
queue is
          * blocking (BLK_MQ_F_BLOCKING). Must be the last member - see also
@@ -532,6 +534,8 @@ int blk_mq_map_queues(struct blk_mq_queue_map *qmap);
  void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int 
nr_hw_queues);

  void blk_mq_quiesce_queue_nowait(struct request_queue *q);
+void blk_mq_quiesce_tagset(struct request_queue *q);
+void blk_mq_unquiesce_tagset(struct request_queue *q);

  unsigned int blk_mq_rq_cpu(struct request *rq);
--


And then nvme will use it:
--
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 05aa568a60af..c41df20996d7 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4557,23 +4557,13 @@ EXPORT_SYMBOL_GPL(nvme_start_freeze);

  void nvme_stop_queues(struct nvme_ctrl *ctrl)
  {
-       struct nvme_ns *ns;
-
-       down_read(&ctrl->namespaces_rwsem);
-       list_for_each_entry(ns, &ctrl->namespaces, list)
-               blk_mq_quiesce_queue(ns->queue);
-       up_read(&ctrl->namespaces_rwsem);
+       blk_mq_quiesce_tagset(ctrl->tagset);
  }
  EXPORT_SYMBOL_GPL(nvme_stop_queues);

  void nvme_start_queues(struct nvme_ctrl *ctrl)
  {
-       struct nvme_ns *ns;
-
-       down_read(&ctrl->namespaces_rwsem);
-       list_for_each_entry(ns, &ctrl->namespaces, list)
-               blk_mq_unquiesce_queue(ns->queue);
-       up_read(&ctrl->namespaces_rwsem);
+       blk_mq_unquiesce_tagset(ctrl->tagset);
  }
  EXPORT_SYMBOL_GPL(nvme_start_queues);
--

Thoughts?