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 on 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.
Preparing for addressing the requirement for nvme fc/rdma/loop by adding
BLK_MQ_F_MANAGED_IRQ to not deactivate hctxs if managed irq isn't used.
Finally, if one driver uses managed irq, it has to tell blk-mq via
BLK_MQ_F_MANAGED_IRQ.
Meantime blk-mq's cpu hotplug handling can be optimized a bit if managed
irq isn't used.
Given blk_mq_alloc_request_hctx() is always called by driver without
BLK_MQ_F_MANAGED_IRQ, it is safe to take one offline cpu for getting
the sw context.
Signed-off-by: Ming Lei <ming.lei@xxxxxxxxxx>
---
block/blk-mq-debugfs.c | 1 +
block/blk-mq.c | 23 +++++++++++++----------
include/linux/blk-mq.h | 1 +
3 files changed, 15 insertions(+), 10 deletions(-)
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 4b66d2776eda..17f57af3a4d6 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -247,6 +247,7 @@ static const char *const hctx_flag_name[] = {
HCTX_FLAG_NAME(NO_SCHED),
HCTX_FLAG_NAME(STACKING),
HCTX_FLAG_NAME(TAG_HCTX_SHARED),
+ HCTX_FLAG_NAME(MANAGED_IRQ),
};
#undef HCTX_FLAG_NAME
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 2e9fd0ec63d7..1d45d2922ca7 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(data.hctx->flags & BLK_MQ_F_MANAGED_IRQ);
+
+ 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.
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index fd2de2b422ed..62fc0393cc3a 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -403,6 +403,7 @@ enum {
*/
BLK_MQ_F_STACKING = 1 << 2,
BLK_MQ_F_TAG_HCTX_SHARED = 1 << 3,
+ BLK_MQ_F_MANAGED_IRQ = 1 << 4,
BLK_MQ_F_BLOCKING = 1 << 5,
BLK_MQ_F_NO_SCHED = 1 << 6,
BLK_MQ_F_ALLOC_POLICY_START_BIT = 8,
--
2.31.1
