[PATCH V4 3/5] blk-mq: stop to handle IO and drain IO before hctx becomes dead

[Ming Lei <ming.lei@xxxxxxxxxx>]

Before one CPU becomes offline, check if it is the last online CPU
of hctx. If yes, mark this hctx as BLK_MQ_S_INTERNAL_STOPPED, meantime
wait for completion of all in-flight IOs originated from this hctx.

This way guarantees that there isn't any inflight IO before shutdowning
the managed IRQ line.

Cc: John Garry <john.garry@xxxxxxxxxx>
Cc: Bart Van Assche <bvanassche@xxxxxxx>
Cc: Hannes Reinecke <hare@xxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Keith Busch <keith.busch@xxxxxxxxx>
Signed-off-by: Ming Lei <ming.lei@xxxxxxxxxx>
---
 block/blk-mq-tag.c |  2 +-
 block/blk-mq-tag.h |  2 ++
 block/blk-mq.c     | 40 ++++++++++++++++++++++++++++++++++++++++
 3 files changed, 43 insertions(+), 1 deletion(-)

diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 008388e82b5c..31828b82552b 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -325,7 +325,7 @@ static void bt_tags_for_each(struct blk_mq_tags *tags, struct sbitmap_queue *bt,
  *		true to continue iterating tags, false to stop.
  * @priv:	Will be passed as second argument to @fn.
  */
-static void blk_mq_all_tag_busy_iter(struct blk_mq_tags *tags,
+void blk_mq_all_tag_busy_iter(struct blk_mq_tags *tags,
 		busy_tag_iter_fn *fn, void *priv)
 {
 	if (tags->nr_reserved_tags)
diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h
index 61deab0b5a5a..321fd6f440e6 100644
--- a/block/blk-mq-tag.h
+++ b/block/blk-mq-tag.h
@@ -35,6 +35,8 @@ extern int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
 extern void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool);
 void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
 		void *priv);
+void blk_mq_all_tag_busy_iter(struct blk_mq_tags *tags,
+		busy_tag_iter_fn *fn, void *priv);
 
 static inline struct sbq_wait_state *bt_wait_ptr(struct sbitmap_queue *bt,
 						 struct blk_mq_hw_ctx *hctx)
diff --git a/block/blk-mq.c b/block/blk-mq.c
index a664f196782a..3384242202eb 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2225,8 +2225,46 @@ int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
 	return -ENOMEM;
 }
 
+static bool blk_mq_count_inflight_rq(struct request *rq, void *data,
+				     bool reserved)
+{
+	unsigned *count = data;
+
+	if ((blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT))
+		(*count)++;
+
+	return true;
+}
+
+static unsigned blk_mq_tags_inflight_rqs(struct blk_mq_tags *tags)
+{
+	unsigned count = 0;
+
+	blk_mq_all_tag_busy_iter(tags, blk_mq_count_inflight_rq, &count);
+
+	return count;
+}
+
+static void blk_mq_hctx_drain_inflight_rqs(struct blk_mq_hw_ctx *hctx)
+{
+	while (1) {
+		if (!blk_mq_tags_inflight_rqs(hctx->tags))
+			break;
+		msleep(5);
+	}
+}
+
 static int blk_mq_hctx_notify_online(unsigned int cpu, struct hlist_node *node)
 {
+	struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node,
+			struct blk_mq_hw_ctx, cpuhp_online);
+
+	if ((cpumask_next_and(-1, hctx->cpumask, cpu_online_mask) == cpu) &&
+	    (cpumask_next_and(cpu, hctx->cpumask, cpu_online_mask) >=
+	     nr_cpu_ids)) {
+		set_bit(BLK_MQ_S_INTERNAL_STOPPED, &hctx->state);
+		blk_mq_hctx_drain_inflight_rqs(hctx);
+        }
 	return 0;
 }
 
@@ -2246,6 +2284,8 @@ static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node)
 	ctx = __blk_mq_get_ctx(hctx->queue, cpu);
 	type = hctx->type;
 
+	clear_bit(BLK_MQ_S_INTERNAL_STOPPED, &hctx->state);
+
 	spin_lock(&ctx->lock);
 	if (!list_empty(&ctx->rq_lists[type])) {
 		list_splice_init(&ctx->rq_lists[type], &tmp);
-- 
2.20.1