On 10/20/22 13:56, Christoph Hellwig wrote:
From: Chao Leng <lengchao@xxxxxxxxxx>
All controller namespaces share the same tagset, so we can use this
interface which does the optimal operation for parallel quiesce based on
the tagset type(e.g. blocking tagsets and non-blocking tagsets).
nvme connect_q should not be quiesced when quiesce tagset, so set the
QUEUE_FLAG_SKIP_TAGSET_QUIESCE to skip it when init connect_q.
Currently we use NVME_NS_STOPPED to ensure pairing quiescing and
unquiescing. If use blk_mq_[un]quiesce_tagset, NVME_NS_STOPPED will be
invalided, so introduce NVME_CTRL_STOPPED to replace NVME_NS_STOPPED.
In addition, we never really quiesce a single namespace. It is a better
choice to move the flag from ns to ctrl.
Signed-off-by: Chao Leng <lengchao@xxxxxxxxxx>
[hch: rebased on top of prep patches]
Signed-off-by: Christoph Hellwig <hch@xxxxxx>
---
drivers/nvme/host/core.c | 38 +++++++++-----------------------------
drivers/nvme/host/nvme.h | 2 +-
2 files changed, 10 insertions(+), 30 deletions(-)
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 0ab3a18fd9f85..cc71f1001144f 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4891,6 +4891,7 @@ int nvme_alloc_io_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
ret = PTR_ERR(ctrl->connect_q);
goto out_free_tag_set;
}
+ blk_queue_flag_set(QUEUE_FLAG_SKIP_TAGSET_QUIESCE, ctrl->connect_q);
}
ctrl->tagset = set;
@@ -5090,20 +5091,6 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
}
EXPORT_SYMBOL_GPL(nvme_init_ctrl);
-static void nvme_start_ns_queue(struct nvme_ns *ns)
-{
- if (test_and_clear_bit(NVME_NS_STOPPED, &ns->flags))
- blk_mq_unquiesce_queue(ns->queue);
-}
-
-static void nvme_stop_ns_queue(struct nvme_ns *ns)
-{
- if (!test_and_set_bit(NVME_NS_STOPPED, &ns->flags))
- blk_mq_quiesce_queue(ns->queue);
- else
- blk_mq_wait_quiesce_done(ns->queue->tag_set);
-}
-
/**
* nvme_kill_queues(): Ends all namespace queues
* @ctrl: the dead controller that needs to end
@@ -5120,10 +5107,9 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl)
if (ctrl->admin_q && !blk_queue_dying(ctrl->admin_q))
nvme_start_admin_queue(ctrl);
if (!test_and_set_bit(NVME_CTRL_NS_DEAD, &ctrl->flags)) {
- list_for_each_entry(ns, &ctrl->namespaces, list) {
+ list_for_each_entry(ns, &ctrl->namespaces, list)
blk_mark_disk_dead(ns->disk);
- nvme_start_ns_queue(ns);
- }
+ nvme_start_queues(ctrl);
}
up_read(&ctrl->namespaces_rwsem);
}
@@ -5179,23 +5165,17 @@ 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)
- nvme_stop_ns_queue(ns);
- up_read(&ctrl->namespaces_rwsem);
+ if (!test_and_set_bit(NVME_CTRL_STOPPED, &ctrl->flags))
+ blk_mq_quiesce_tagset(ctrl->tagset);
+ else
+ blk_mq_wait_quiesce_done(ctrl->tagset);
Isn't blk_mq_quiesce_tagset already waits for the (s)rcu
grace? Is this to make a concurrent caller also wait?
I wish we would sort out all the concurrency issues in
the driver(s) instead of making core functions reentrant safe...
