[PATCH 4/5] nvme: paring quiesce/unquiesce

[Sagi Grimberg]

On 9/29/21 7:15 AM, Ming Lei wrote:
> The current blk_mq_quiesce_queue() and blk_mq_unquiesce_queue() always
> stops and starts the queue unconditionally. And there can be concurrent
> quiesce/unquiesce coming from different unrelated code paths, so
> unquiesce may come unexpectedly and start queue too early.
> 
> Prepare for supporting nested / concurrent quiesce/unquiesce, so that we
> can address the above issue.
> 
> NVMe has very complicated quiesce/unquiesce use pattern, add one mutex
> and queue stopped state in nvme_ctrl, so that we can make sure that
> quiece/unquiesce is called in pair.
> 
> Signed-off-by: Ming Lei <ming.lei at redhat.com>
> ---
>   drivers/nvme/host/core.c | 51 ++++++++++++++++++++++++++++++++++++----
>   drivers/nvme/host/nvme.h |  4 ++++
>   2 files changed, 50 insertions(+), 5 deletions(-)
> 
> diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
> index 23fb746a8970..5d0b2eb38e43 100644
> --- a/drivers/nvme/host/core.c
> +++ b/drivers/nvme/host/core.c
> @@ -4375,6 +4375,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
>   	clear_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags);
>   	spin_lock_init(&ctrl->lock);
>   	mutex_init(&ctrl->scan_lock);
> +	mutex_init(&ctrl->queues_stop_lock);
>   	INIT_LIST_HEAD(&ctrl->namespaces);
>   	xa_init(&ctrl->cels);
>   	init_rwsem(&ctrl->namespaces_rwsem);
> @@ -4450,14 +4451,44 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
>   }
>   EXPORT_SYMBOL_GPL(nvme_init_ctrl);
>   
> +static void __nvme_stop_admin_queue(struct nvme_ctrl *ctrl)
> +{
> +	lockdep_assert_held(&ctrl->queues_stop_lock);
> +
> +	if (!ctrl->admin_queue_stopped) {
> +		blk_mq_quiesce_queue(ctrl->admin_q);
> +		ctrl->admin_queue_stopped = true;
> +	}
> +}
> +
> +static void __nvme_start_admin_queue(struct nvme_ctrl *ctrl)
> +{
> +	lockdep_assert_held(&ctrl->queues_stop_lock);
> +
> +	if (ctrl->admin_queue_stopped) {
> +		blk_mq_unquiesce_queue(ctrl->admin_q);
> +		ctrl->admin_queue_stopped = false;
> +	}
> +}

I'd make this a bit we can flip atomically.

> +
>   static void nvme_start_ns_queue(struct nvme_ns *ns)
>   {
> -	blk_mq_unquiesce_queue(ns->queue);
> +	lockdep_assert_held(&ns->ctrl->queues_stop_lock);
> +
> +	if (test_bit(NVME_NS_STOPPED, &ns->flags)) {
> +		blk_mq_unquiesce_queue(ns->queue);
> +		clear_bit(NVME_NS_STOPPED, &ns->flags);
> +	}
>   }
>   
>   static void nvme_stop_ns_queue(struct nvme_ns *ns)
>   {
> -	blk_mq_quiesce_queue(ns->queue);
> +	lockdep_assert_held(&ns->ctrl->queues_stop_lock);
> +
> +	if (!test_bit(NVME_NS_STOPPED, &ns->flags)) {
> +		blk_mq_quiesce_queue(ns->queue);
> +		set_bit(NVME_NS_STOPPED, &ns->flags);
> +	}
>   }

Why not use test_and_set_bit/test_and_clear_bit for serialization?

>   
>   /*
> @@ -4490,16 +4521,18 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl)
>   {
>   	struct nvme_ns *ns;
>   
> +	mutex_lock(&ctrl->queues_stop_lock);
>   	down_read(&ctrl->namespaces_rwsem);
>   
>   	/* Forcibly unquiesce queues to avoid blocking dispatch */
>   	if (ctrl->admin_q && !blk_queue_dying(ctrl->admin_q))
> -		nvme_start_admin_queue(ctrl);
> +		__nvme_start_admin_queue(ctrl);
>   
>   	list_for_each_entry(ns, &ctrl->namespaces, list)
>   		nvme_set_queue_dying(ns);
>   
>   	up_read(&ctrl->namespaces_rwsem);
> +	mutex_unlock(&ctrl->queues_stop_lock);

This extra lock wrapping the namespaces_rwsem is scary. The
ordering rules are not clear to me.