| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <e8264916-ca27-4a3a-8006-a6e348282fc3@suse.de>
Date: Tue, 1 Apr 2025 11:37:29 +0200
From: Hannes Reinecke <hare@...e.de>
To: Daniel Wagner <wagi@...nel.org>, Christoph Hellwig <hch@....de>,
Sagi Grimberg <sagi@...mberg.me>, Keith Busch <kbusch@...nel.org>,
John Meneghini <jmeneghi@...hat.com>, randyj@...estorage.com,
Mohamed Khalfella <mkhalfella@...estorage.com>
Cc: linux-nvme@...ts.infradead.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH RFC 3/3] nvme: delay failover by command quiesce timeout
On 3/24/25 13:07, 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@...nel.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);
> +
> + if (state == NVME_CTRL_DELETING) {
> + /*
> + * request which fail over in the DELETING state were
> + * canceled and blk_mq_tagset_wait_completed_request will
> + * block until they have been proceed. Though
> + * nvme_failover_work is already stopped. Thus schedule
> + * a failover; it's still necessary to delay these commands
> + * by CQT.
> + */
> + nvme_schedule_failover(ctrl);
> + }
> +}
> +
> +void nvme_flush_failover(struct nvme_ctrl *ctrl)
> +{
> + LIST_HEAD(failover_list);
> + struct request *rq;
> + bool kick = false;
> +
> + spin_lock_irq(&ctrl->lock);
> + list_splice_init(&ctrl->failover_list, &failover_list);
> + spin_unlock_irq(&ctrl->lock);
> +
> + while (!list_empty(&failover_list)) {
> + rq = list_entry(failover_list.next,
> + struct request, queuelist);
> + list_del_init(&rq->queuelist);
> +
> + nvme_req(rq)->status = 0;
> + nvme_end_req(rq);
> + kick = true;
> + }
> +
> + if (kick)
> + nvme_kick_requeue_lists(ctrl);
> +}
> +
> +void nvme_failover_work(struct work_struct *work)
> +{
> + struct nvme_ctrl *ctrl = container_of(to_delayed_work(work),
> + struct nvme_ctrl, failover_work);
> +
> + nvme_flush_failover(ctrl);
> }
>
> void nvme_mpath_start_request(struct request *rq)
> diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
> index 7563332b5b7b76fc6165ec8c6f2d144737d4fe85..10eb323bdaf139526959180c1e66ab4579bb145d 100644
> --- a/drivers/nvme/host/nvme.h
> +++ b/drivers/nvme/host/nvme.h
> @@ -411,6 +411,9 @@ struct nvme_ctrl {
>
> enum nvme_ctrl_type cntrltype;
> enum nvme_dctype dctype;
> +
> + struct delayed_work failover_work;
> + struct list_head failover_list;
> };
>
> static inline enum nvme_ctrl_state nvme_ctrl_state(struct nvme_ctrl *ctrl)
> @@ -954,6 +957,9 @@ void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys);
> void nvme_mpath_start_freeze(struct nvme_subsystem *subsys);
> void nvme_mpath_default_iopolicy(struct nvme_subsystem *subsys);
> void nvme_failover_req(struct request *req);
> +void nvme_failover_work(struct work_struct *work);
> +void nvme_schedule_failover(struct nvme_ctrl *ctrl);
> +void nvme_flush_failover(struct nvme_ctrl *ctrl);
> void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl);
> int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,struct nvme_ns_head *head);
> void nvme_mpath_add_disk(struct nvme_ns *ns, __le32 anagrpid);
> @@ -996,6 +1002,15 @@ static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
> static inline void nvme_failover_req(struct request *req)
> {
> }
> +static inline void nvme_failover_work(struct work_struct *work)
> +{
> +}
> +static inline void nvme_schedule_failover(struct nvme_ctrl *ctrl)
> +{
> +}
> +static inline void nvme_flush_failover(struct nvme_ctrl *ctrl)
> +{
> +}
> static inline void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
> {
> }
> diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
> index 86a2891d9bcc7a990cd214a7fe93fa5c55b292c7..9bee376f881b4c3ebe5502abf23a8e76829780ff 100644
> --- a/drivers/nvme/host/rdma.c
> +++ b/drivers/nvme/host/rdma.c
> @@ -1127,6 +1127,7 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work)
>
> nvme_stop_keep_alive(&ctrl->ctrl);
> flush_work(&ctrl->ctrl.async_event_work);
> + nvme_schedule_failover(&ctrl->ctrl);
> nvme_rdma_teardown_io_queues(ctrl, false);
> nvme_unquiesce_io_queues(&ctrl->ctrl);
> nvme_rdma_teardown_admin_queue(ctrl, false);
> @@ -2153,6 +2154,7 @@ static const struct blk_mq_ops nvme_rdma_admin_mq_ops = {
>
> static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl, bool shutdown)
> {
> + nvme_schedule_failover(&ctrl->ctrl);
> nvme_rdma_teardown_io_queues(ctrl, shutdown);
> nvme_quiesce_admin_queue(&ctrl->ctrl);
> nvme_disable_ctrl(&ctrl->ctrl, shutdown);
> diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
> index d0023bcfd8a79a193adf2807a24481c8c164a174..3a6c1d3febaf233996e4dcf684793327b5d1412f 100644
> --- a/drivers/nvme/host/tcp.c
> +++ b/drivers/nvme/host/tcp.c
> @@ -2345,6 +2345,7 @@ static void nvme_tcp_error_recovery_work(struct work_struct *work)
>
> nvme_stop_keep_alive(ctrl);
> flush_work(&ctrl->async_event_work);
> + nvme_schedule_failover(ctrl);
> nvme_tcp_teardown_io_queues(ctrl, false);
> /* unquiesce to fail fast pending requests */
> nvme_unquiesce_io_queues(ctrl);
>
Hmm. Rather not.
Why do we have to have a separate failover queue?
Can't we simply delay the error recovery by the cqt value?
Cheers,
Hannes
--
Dr. Hannes Reinecke Kernel Storage Architect
hare@...e.de +49 911 74053 688
SUSE Software Solutions GmbH, Frankenstr. 146, 90461 Nürnberg
HRB 36809 (AG Nürnberg), GF: I. Totev, A. McDonald, W. Knoblich
Powered by blists - more mailing lists