[PATCH V5 3/3] blk-mq: don't deactivate hctx if managed irq isn't used

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

blk-mq deactivates one hctx when the last CPU in hctx->cpumask become
offline by draining all requests originated from this hctx and moving new
allocation to other active hctx. This way is for avoiding inflight IO in
case of managed irq because managed irq is shutdown when the last CPU in
the irq's affinity becomes offline.

However, lots of drivers(nvme fc, rdma, tcp, loop, ...) don't use managed
irq, so they needn't to deactivate hctx when the last CPU becomes offline.
Also, some of them are the only user of blk_mq_alloc_request_hctx() which
is used for connecting io queue. And their requirement is that the connect
request needs to be submitted successfully via one specified hctx even though
all CPUs in this hctx->cpumask have become offline.

Addressing the requirement for nvme fc/rdma/loop by allowing to
allocate request from one hctx when all CPUs in this hctx are offline,
since these drivers don't use managed irq.

Finally don't deactivate one hctx when it doesn't use managed irq.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
---
 block/blk-mq.c | 27 +++++++++++++++++----------
 block/blk-mq.h |  8 ++++++++
 2 files changed, 25 insertions(+), 10 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 2c4ac51e54eb..591ab07c64d8 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -427,6 +427,15 @@ struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
 }
 EXPORT_SYMBOL(blk_mq_alloc_request);
 
+static inline int blk_mq_first_mapped_cpu(struct blk_mq_hw_ctx *hctx)
+{
+	int cpu = cpumask_first_and(hctx->cpumask, cpu_online_mask);
+
+	if (cpu >= nr_cpu_ids)
+		cpu = cpumask_first(hctx->cpumask);
+	return cpu;
+}
+
 struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 	unsigned int op, blk_mq_req_flags_t flags, unsigned int hctx_idx)
 {
@@ -468,7 +477,10 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 	data.hctx = q->queue_hw_ctx[hctx_idx];
 	if (!blk_mq_hw_queue_mapped(data.hctx))
 		goto out_queue_exit;
-	cpu = cpumask_first_and(data.hctx->cpumask, cpu_online_mask);
+
+	WARN_ON_ONCE(blk_mq_hctx_use_managed_irq(data.hctx));
+
+	cpu = blk_mq_first_mapped_cpu(data.hctx);
 	data.ctx = __blk_mq_get_ctx(q, cpu);
 
 	if (!q->elevator)
@@ -1501,15 +1513,6 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 	hctx_unlock(hctx, srcu_idx);
 }
 
-static inline int blk_mq_first_mapped_cpu(struct blk_mq_hw_ctx *hctx)
-{
-	int cpu = cpumask_first_and(hctx->cpumask, cpu_online_mask);
-
-	if (cpu >= nr_cpu_ids)
-		cpu = cpumask_first(hctx->cpumask);
-	return cpu;
-}
-
 /*
  * It'd be great if the workqueue API had a way to pass
  * in a mask and had some smarts for more clever placement.
@@ -2556,6 +2559,10 @@ static int blk_mq_hctx_notify_offline(unsigned int cpu, struct hlist_node *node)
 	struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node,
 			struct blk_mq_hw_ctx, cpuhp_online);
 
+	/* hctx needn't to be deactivated in case managed irq isn't used */
+	if (!blk_mq_hctx_use_managed_irq(hctx))
+		return 0;
+
 	if (!cpumask_test_cpu(cpu, hctx->cpumask) ||
 	    !blk_mq_last_cpu_in_hctx(cpu, hctx))
 		return 0;
diff --git a/block/blk-mq.h b/block/blk-mq.h
index d08779f77a26..7333b659d8f5 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -119,6 +119,14 @@ static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,
 	return ctx->hctxs[type];
 }
 
+static inline bool blk_mq_hctx_use_managed_irq(struct blk_mq_hw_ctx *hctx)
+{
+	if (hctx->type == HCTX_TYPE_POLL)
+		return false;
+
+	return hctx->queue->tag_set->map[hctx->type].use_managed_irq;
+}
+
 /*
  * sysfs helpers
  */
-- 
2.31.1