From: Hannes Reinecke <hare@suse.de>
To: Mohamed Khalfella <mkhalfella@purestorage.com>,
Justin Tee <justin.tee@broadcom.com>,
Naresh Gottumukkala <nareshgottumukkala83@gmail.com>,
Paul Ely <paul.ely@broadcom.com>,
Chaitanya Kulkarni <kch@nvidia.com>,
Christoph Hellwig <hch@lst.de>, Jens Axboe <axboe@kernel.dk>,
Keith Busch <kbusch@kernel.org>, Sagi Grimberg <sagi@grimberg.me>
Cc: Aaron Dailey <adailey@purestorage.com>,
Randy Jennings <randyj@purestorage.com>,
Dhaval Giani <dgiani@purestorage.com>,
linux-nvme@lists.infradead.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH v2 13/14] nvme-fc: Use CCR to recover controller that hits an error
Date: Tue, 3 Feb 2026 06:43:30 +0100 [thread overview]
Message-ID: <c1cd6ce4-c06c-4504-8319-250e01350fec@suse.de> (raw)
In-Reply-To: <20260130223531.2478849-14-mkhalfella@purestorage.com>
On 1/30/26 23:34, Mohamed Khalfella wrote:
> An alive nvme controller that hits an error now will move to FENCING
> state instead of RESETTING state. ctrl->fencing_work attempts CCR to
> terminate inflight IOs. If CCR succeeds, switch to FENCED -> RESETTING
> and continue error recovery as usual. If CCR fails, the behavior depends
> on whether the subsystem supports CQT or not. If CQT is not supported
> then reset the controller immediately as if CCR succeeded in order to
> maintain the current behavior. If CQT is supported switch to time-based
> recovery. Schedule ctrl->fenced_work resets the controller when time
> based recovery finishes.
>
> Either ctrl->err_work or ctrl->reset_work can run after a controller is
> fenced. Flush fencing work when either work run.
>
> Signed-off-by: Mohamed Khalfella <mkhalfella@purestorage.com>
> ---
> drivers/nvme/host/fc.c | 60 ++++++++++++++++++++++++++++++++++++++++++
> 1 file changed, 60 insertions(+)
>
> diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
> index f8f6071b78ed..3a01aeb39081 100644
> --- a/drivers/nvme/host/fc.c
> +++ b/drivers/nvme/host/fc.c
> @@ -166,6 +166,8 @@ struct nvme_fc_ctrl {
> struct blk_mq_tag_set admin_tag_set;
> struct blk_mq_tag_set tag_set;
>
> + struct work_struct fencing_work;
> + struct delayed_work fenced_work;
> struct work_struct ioerr_work;
> struct delayed_work connect_work;
>
> @@ -1866,12 +1868,59 @@ __nvme_fc_fcpop_chk_teardowns(struct nvme_fc_ctrl *ctrl,
> }
> }
>
> +static void nvme_fc_fenced_work(struct work_struct *work)
> +{
> + struct nvme_fc_ctrl *fc_ctrl = container_of(to_delayed_work(work),
> + struct nvme_fc_ctrl, fenced_work);
> + struct nvme_ctrl *ctrl = &fc_ctrl->ctrl;
> +
> + nvme_change_ctrl_state(ctrl, NVME_CTRL_FENCED);
> + if (nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING))
> + queue_work(nvme_reset_wq, &fc_ctrl->ioerr_work);
> +}
> +
> +static void nvme_fc_fencing_work(struct work_struct *work)
> +{
> + struct nvme_fc_ctrl *fc_ctrl =
> + container_of(work, struct nvme_fc_ctrl, fencing_work);
> + struct nvme_ctrl *ctrl = &fc_ctrl->ctrl;
> + unsigned long rem;
> +
> + rem = nvme_fence_ctrl(ctrl);
> + if (!rem)
> + goto done;
> +
> + if (!ctrl->cqt) {
> + dev_info(ctrl->device,
> + "CCR failed, CQT not supported, skip time-based recovery\n");
> + goto done;
> + }
> +
> + dev_info(ctrl->device,
> + "CCR failed, switch to time-based recovery, timeout = %ums\n",
> + jiffies_to_msecs(rem));
> + queue_delayed_work(nvme_wq, &fc_ctrl->fenced_work, rem);
> + return;
> +
Same comments re fenced workqueue apply here.
> +done:
> + nvme_change_ctrl_state(ctrl, NVME_CTRL_FENCED);
> + if (nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING))
> + queue_work(nvme_reset_wq, &fc_ctrl->ioerr_work);
> +}
> +
> +static void nvme_fc_flush_fencing_work(struct nvme_fc_ctrl *ctrl)
> +{
> + flush_work(&ctrl->fencing_work);
> + flush_delayed_work(&ctrl->fenced_work);
> +}
> +
> static void
> nvme_fc_ctrl_ioerr_work(struct work_struct *work)
> {
> struct nvme_fc_ctrl *ctrl =
> container_of(work, struct nvme_fc_ctrl, ioerr_work);
>
> + nvme_fc_flush_fencing_work(ctrl);
> nvme_fc_error_recovery(ctrl);
> }
>
> @@ -1896,6 +1945,14 @@ EXPORT_SYMBOL_GPL(nvme_fc_io_getuuid);
> static void nvme_fc_start_ioerr_recovery(struct nvme_fc_ctrl *ctrl,
> char *errmsg)
> {
> + if (nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_FENCING)) {
> + dev_warn(ctrl->ctrl.device,
> + "NVME-FC{%d}: starting controller fencing %s\n",
> + ctrl->cnum, errmsg);
> + queue_work(nvme_wq, &ctrl->fencing_work);
> + return;
> + }
> +
> if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING))
> return;
>
> @@ -3297,6 +3354,7 @@ nvme_fc_reset_ctrl_work(struct work_struct *work)
> struct nvme_fc_ctrl *ctrl =
> container_of(work, struct nvme_fc_ctrl, ctrl.reset_work);
>
> + nvme_fc_flush_fencing_work(ctrl);
> nvme_stop_ctrl(&ctrl->ctrl);
>
> /* will block will waiting for io to terminate */
> @@ -3471,6 +3529,8 @@ nvme_fc_alloc_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
>
> INIT_WORK(&ctrl->ctrl.reset_work, nvme_fc_reset_ctrl_work);
> INIT_DELAYED_WORK(&ctrl->connect_work, nvme_fc_connect_ctrl_work);
> + INIT_DELAYED_WORK(&ctrl->fenced_work, nvme_fc_fenced_work);
> + INIT_WORK(&ctrl->fencing_work, nvme_fc_fencing_work);
> INIT_WORK(&ctrl->ioerr_work, nvme_fc_ctrl_ioerr_work);
> spin_lock_init(&ctrl->lock);
>
And, of course, the same comments about sending CCR in response to a
KATO timeout and not a command timeout apply.
Cheers,
Hannes
--
Dr. Hannes Reinecke Kernel Storage Architect
hare@suse.de +49 911 74053 688
SUSE Software Solutions GmbH, Frankenstr. 146, 90461 Nürnberg
HRB 36809 (AG Nürnberg), GF: I. Totev, A. McDonald, W. Knoblich
next prev parent reply other threads:[~2026-02-03 5:43 UTC|newest]
Thread overview: 82+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-01-30 22:34 [PATCH v2 00/14] TP8028 Rapid Path Failure Recovery Mohamed Khalfella
2026-01-30 22:34 ` [PATCH v2 01/14] nvmet: Rapid Path Failure Recovery set controller identify fields Mohamed Khalfella
2026-02-03 3:03 ` Hannes Reinecke
2026-02-03 18:14 ` Mohamed Khalfella
2026-02-04 0:34 ` Hannes Reinecke
2026-02-07 13:41 ` Sagi Grimberg
2026-02-14 0:42 ` Randy Jennings
2026-02-14 3:56 ` Mohamed Khalfella
2026-01-30 22:34 ` [PATCH v2 02/14] nvmet/debugfs: Add ctrl uniquifier and random values Mohamed Khalfella
2026-02-03 3:04 ` Hannes Reinecke
2026-02-07 13:47 ` Sagi Grimberg
2026-02-11 0:50 ` Randy Jennings
2026-02-11 1:02 ` Mohamed Khalfella
2026-01-30 22:34 ` [PATCH v2 03/14] nvmet: Implement CCR nvme command Mohamed Khalfella
2026-02-03 3:19 ` Hannes Reinecke
2026-02-03 18:40 ` Mohamed Khalfella
2026-02-04 0:38 ` Hannes Reinecke
2026-02-04 0:44 ` Mohamed Khalfella
2026-02-04 0:55 ` Hannes Reinecke
2026-02-04 17:52 ` Mohamed Khalfella
2026-02-07 13:58 ` Sagi Grimberg
2026-02-08 23:10 ` Mohamed Khalfella
2026-02-09 19:27 ` Mohamed Khalfella
2026-02-11 1:34 ` Randy Jennings
2026-02-07 14:11 ` Sagi Grimberg
2026-01-30 22:34 ` [PATCH v2 04/14] nvmet: Implement CCR logpage Mohamed Khalfella
2026-02-03 3:21 ` Hannes Reinecke
2026-02-07 14:11 ` Sagi Grimberg
2026-02-11 1:49 ` Randy Jennings
2026-01-30 22:34 ` [PATCH v2 05/14] nvmet: Send an AEN on CCR completion Mohamed Khalfella
2026-02-03 3:27 ` Hannes Reinecke
2026-02-03 18:48 ` Mohamed Khalfella
2026-02-04 0:43 ` Hannes Reinecke
2026-02-07 14:12 ` Sagi Grimberg
2026-02-11 1:52 ` Randy Jennings
2026-01-30 22:34 ` [PATCH v2 06/14] nvme: Rapid Path Failure Recovery read controller identify fields Mohamed Khalfella
2026-02-03 3:28 ` Hannes Reinecke
2026-02-07 14:13 ` Sagi Grimberg
2026-02-11 1:56 ` Randy Jennings
2026-01-30 22:34 ` [PATCH v2 07/14] nvme: Introduce FENCING and FENCED controller states Mohamed Khalfella
2026-02-03 5:07 ` Hannes Reinecke
2026-02-03 19:13 ` Mohamed Khalfella
2026-01-30 22:34 ` [PATCH v2 08/14] nvme: Implement cross-controller reset recovery Mohamed Khalfella
2026-02-03 5:19 ` Hannes Reinecke
2026-02-03 20:00 ` Mohamed Khalfella
2026-02-04 1:10 ` Hannes Reinecke
2026-02-04 23:24 ` Mohamed Khalfella
2026-02-11 3:44 ` Randy Jennings
2026-02-11 15:19 ` Hannes Reinecke
2026-02-10 22:09 ` James Smart
2026-02-10 22:27 ` Mohamed Khalfella
2026-02-10 22:49 ` James Smart
2026-02-10 23:25 ` Mohamed Khalfella
2026-02-11 0:12 ` Mohamed Khalfella
2026-02-11 3:33 ` Randy Jennings
2026-01-30 22:34 ` [PATCH v2 09/14] nvme: Implement cross-controller reset completion Mohamed Khalfella
2026-02-03 5:22 ` Hannes Reinecke
2026-02-03 20:07 ` Mohamed Khalfella
2026-01-30 22:34 ` [PATCH v2 10/14] nvme-tcp: Use CCR to recover controller that hits an error Mohamed Khalfella
2026-02-03 5:34 ` Hannes Reinecke
2026-02-03 21:24 ` Mohamed Khalfella
2026-02-04 0:48 ` Randy Jennings
2026-02-04 2:57 ` Hannes Reinecke
2026-02-10 1:39 ` Mohamed Khalfella
2026-01-30 22:34 ` [PATCH v2 11/14] nvme-rdma: " Mohamed Khalfella
2026-02-03 5:35 ` Hannes Reinecke
2026-01-30 22:34 ` [PATCH v2 12/14] nvme-fc: Decouple error recovery from controller reset Mohamed Khalfella
2026-02-03 5:40 ` Hannes Reinecke
2026-02-03 21:29 ` Mohamed Khalfella
2026-02-03 19:19 ` James Smart
2026-02-03 22:49 ` James Smart
2026-02-04 0:15 ` Mohamed Khalfella
2026-02-04 0:11 ` Mohamed Khalfella
2026-02-05 0:08 ` James Smart
2026-02-05 0:59 ` Mohamed Khalfella
2026-02-09 22:53 ` Mohamed Khalfella
2026-01-30 22:34 ` [PATCH v2 13/14] nvme-fc: Use CCR to recover controller that hits an error Mohamed Khalfella
2026-02-03 5:43 ` Hannes Reinecke [this message]
2026-02-10 22:12 ` James Smart
2026-02-10 22:20 ` Mohamed Khalfella
2026-02-13 19:29 ` Mohamed Khalfella
2026-01-30 22:34 ` [PATCH v2 14/14] nvme-fc: Hold inflight requests while in FENCING state Mohamed Khalfella
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=c1cd6ce4-c06c-4504-8319-250e01350fec@suse.de \
--to=hare@suse.de \
--cc=adailey@purestorage.com \
--cc=axboe@kernel.dk \
--cc=dgiani@purestorage.com \
--cc=hch@lst.de \
--cc=justin.tee@broadcom.com \
--cc=kbusch@kernel.org \
--cc=kch@nvidia.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=mkhalfella@purestorage.com \
--cc=nareshgottumukkala83@gmail.com \
--cc=paul.ely@broadcom.com \
--cc=randyj@purestorage.com \
--cc=sagi@grimberg.me \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®