Re: [PATCH RFC 3/3] nvme: delay failover by command quiesce timeout

[Mohamed Khalfella <mkhalfella@purestorage.com>]

On 2025-03-24 13:07:58 +0100, Daniel Wagner wrote:
> The TP4129 mendates that the failover should be delayed by CQT.  Thus when
> nvme_decide_disposition returns FAILOVER do not immediately re-queue it on
> the namespace level instead queue it on the ctrl's request_list and
> moved later to the namespace's requeue_list.
> 
> Signed-off-by: Daniel Wagner <wagi@kernel.org>
> ---
>  drivers/nvme/host/core.c      | 19 ++++++++++++++++
>  drivers/nvme/host/fc.c        |  4 ++++
>  drivers/nvme/host/multipath.c | 52 ++++++++++++++++++++++++++++++++++++++++---
>  drivers/nvme/host/nvme.h      | 15 +++++++++++++
>  drivers/nvme/host/rdma.c      |  2 ++
>  drivers/nvme/host/tcp.c       |  1 +
>  6 files changed, 90 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
> index 135045528ea1c79eac0d6d47d5f7f05a7c98acc4..f3155c7735e75e06c4359c26db8931142c067e1d 100644
> --- a/drivers/nvme/host/core.c
> +++ b/drivers/nvme/host/core.c
> @@ -239,6 +239,7 @@ static void nvme_do_delete_ctrl(struct nvme_ctrl *ctrl)
>  
>  	flush_work(&ctrl->reset_work);
>  	nvme_stop_ctrl(ctrl);
> +	nvme_flush_failover(ctrl);
>  	nvme_remove_namespaces(ctrl);
>  	ctrl->ops->delete_ctrl(ctrl);
>  	nvme_uninit_ctrl(ctrl);
> @@ -1310,6 +1311,19 @@ static void nvme_queue_keep_alive_work(struct nvme_ctrl *ctrl)
>  	queue_delayed_work(nvme_wq, &ctrl->ka_work, delay);
>  }
>  
> +void nvme_schedule_failover(struct nvme_ctrl *ctrl)
> +{
> +	unsigned long delay;
> +
> +	if (ctrl->cqt)
> +		delay = msecs_to_jiffies(ctrl->cqt);
> +	else
> +		delay = ctrl->kato * HZ;
> +
> +	queue_delayed_work(nvme_wq, &ctrl->failover_work, delay);
> +}
> +EXPORT_SYMBOL_GPL(nvme_schedule_failover);
> +
>  static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq,
>  						 blk_status_t status)
>  {
> @@ -1336,6 +1350,8 @@ static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq,
>  		dev_err(ctrl->device,
>  			"failed nvme_keep_alive_end_io error=%d\n",
>  				status);
> +
> +		nvme_schedule_failover(ctrl);
>  		return RQ_END_IO_NONE;
>  	}
>  
> @@ -4716,6 +4732,7 @@ EXPORT_SYMBOL_GPL(nvme_remove_io_tag_set);
>  
>  void nvme_stop_ctrl(struct nvme_ctrl *ctrl)
>  {
> +	nvme_schedule_failover(ctrl);
>  	nvme_mpath_stop(ctrl);
>  	nvme_auth_stop(ctrl);
>  	nvme_stop_failfast_work(ctrl);
> @@ -4842,6 +4859,8 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
>  
>  	INIT_DELAYED_WORK(&ctrl->ka_work, nvme_keep_alive_work);
>  	INIT_DELAYED_WORK(&ctrl->failfast_work, nvme_failfast_work);
> +	INIT_DELAYED_WORK(&ctrl->failover_work, nvme_failover_work);
> +	INIT_LIST_HEAD(&ctrl->failover_list);
>  	memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd));
>  	ctrl->ka_cmd.common.opcode = nvme_admin_keep_alive;
>  	ctrl->ka_last_check_time = jiffies;
> diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
> index cdc1ba277a5c23ef1afd26e6911b082f3d12b215..bd897b29cd286008b781bbcb4230e08019da6b6b 100644
> --- a/drivers/nvme/host/fc.c
> +++ b/drivers/nvme/host/fc.c
> @@ -2553,6 +2553,8 @@ nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg)
>  {
>  	enum nvme_ctrl_state state = nvme_ctrl_state(&ctrl->ctrl);
>  
> +	nvme_schedule_failover(&ctrl->ctrl);
> +
>  	/*
>  	 * if an error (io timeout, etc) while (re)connecting, the remote
>  	 * port requested terminating of the association (disconnect_ls)
> @@ -3378,6 +3380,8 @@ nvme_fc_reset_ctrl_work(struct work_struct *work)
>  	/* will block will waiting for io to terminate */
>  	nvme_fc_delete_association(ctrl);
>  
> +	nvme_schedule_failover(&ctrl->ctrl);
> +
>  	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING))
>  		dev_err(ctrl->ctrl.device,
>  			"NVME-FC{%d}: error_recovery: Couldn't change state "
> diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
> index 2a7635565083046c575efe1793362ae10581defd..a14b055796b982df96609f53174a5d1334c1c0c4 100644
> --- a/drivers/nvme/host/multipath.c
> +++ b/drivers/nvme/host/multipath.c
> @@ -86,9 +86,11 @@ void nvme_mpath_start_freeze(struct nvme_subsystem *subsys)
>  void nvme_failover_req(struct request *req)
>  {
>  	struct nvme_ns *ns = req->q->queuedata;
> +	struct nvme_ctrl *ctrl = nvme_req(req)->ctrl;
>  	u16 status = nvme_req(req)->status & NVME_SCT_SC_MASK;
>  	unsigned long flags;
>  	struct bio *bio;
> +	enum nvme_ctrl_state state = nvme_ctrl_state(ctrl);
>  
>  	nvme_mpath_clear_current_path(ns);
>  
> @@ -121,9 +123,53 @@ void nvme_failover_req(struct request *req)
>  	blk_steal_bios(&ns->head->requeue_list, req);
>  	spin_unlock_irqrestore(&ns->head->requeue_lock, flags);
>  
> -	nvme_req(req)->status = 0;
> -	nvme_end_req(req);
> -	kblockd_schedule_work(&ns->head->requeue_work);
> +	spin_lock_irqsave(&ctrl->lock, flags);
> +	list_add_tail(&req->queuelist, &ctrl->failover_list);
> +	spin_unlock_irqrestore(&ctrl->lock, flags);
> +

In case the delay in nvme_schedule_failover() is larget than request
timeout, is it possible for timeout callback to be called while a
request is sitting in failover_list?

Is there any guarantee to prevent this from happening? I understand from
the patch that we do not want this to happen, right?