The Linux Kernel Mailing List
 help / color / mirror / Atom feed
From: Mohamed Khalfella <mkhalfella@purestorage.com>
To: 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>,
	John Meneghini <jmeneghi@redhat.com>,
	Hannes Reinecke <hare@suse.de>,
	linux-nvme@lists.infradead.org, linux-kernel@vger.kernel.org,
	Mohamed Khalfella <mkhalfella@purestorage.com>
Subject: [RFC PATCH 09/14] nvme: Implement cross-controller reset completion
Date: Tue, 25 Nov 2025 18:11:56 -0800	[thread overview]
Message-ID: <20251126021250.2583630-10-mkhalfella@purestorage.com> (raw)
In-Reply-To: <20251126021250.2583630-1-mkhalfella@purestorage.com>

An nvme source controller that issues CCR command expects to receive an
NVME_AER_NOTICE_CCR_COMPLETED when pending CCR succeeds or fails. Add
sctrl->ccr_work to read NVME_LOG_CCR logpage and wakeup any thread
waiting on CCR completion.

Signed-off-by: Mohamed Khalfella <mkhalfella@purestorage.com>
---
 drivers/nvme/host/core.c | 49 +++++++++++++++++++++++++++++++++++++++-
 drivers/nvme/host/nvme.h |  1 +
 2 files changed, 49 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index f38b70ca9cee..467754e77a2d 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1894,7 +1894,8 @@ EXPORT_SYMBOL_GPL(nvme_set_queue_count);
 
 #define NVME_AEN_SUPPORTED \
 	(NVME_AEN_CFG_NS_ATTR | NVME_AEN_CFG_FW_ACT | \
-	 NVME_AEN_CFG_ANA_CHANGE | NVME_AEN_CFG_DISC_CHANGE)
+	 NVME_AEN_CFG_ANA_CHANGE | NVME_AEN_CFG_CCR_COMPLETE | \
+	 NVME_AEN_CFG_DISC_CHANGE)
 
 static void nvme_enable_aen(struct nvme_ctrl *ctrl)
 {
@@ -4860,6 +4861,47 @@ static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl)
 	kfree(log);
 }
 
+static void nvme_ccr_work(struct work_struct *work)
+{
+	struct nvme_ctrl *ctrl = container_of(work, struct nvme_ctrl, ccr_work);
+	struct nvme_ccr_entry *ccr;
+	struct nvme_ccr_log_entry *entry;
+	struct nvme_ccr_log *log;
+	unsigned long flags;
+	int ret, i;
+
+	log = kmalloc(sizeof(*log), GFP_KERNEL);
+	if (!log)
+		return;
+
+	ret = nvme_get_log(ctrl, 0, NVME_LOG_CCR, 0x01,
+			   0x00, log, sizeof(*log), 0);
+	if (ret)
+		goto out;
+
+	spin_lock_irqsave(&ctrl->lock, flags);
+	for (i = 0; i < le16_to_cpu(log->ne); i++) {
+		entry = &log->entries[i];
+		if (entry->ccrs == 0)	/* skip in progress entries */
+			continue;
+
+		list_for_each_entry(ccr, &ctrl->ccrs, list) {
+			struct nvme_ctrl *ictrl = ccr->ictrl;
+
+			if (ictrl->cntlid != le16_to_cpu(entry->icid) ||
+			    ictrl->ciu != entry->ciu)
+				continue;
+
+			/* Complete matching entry */
+			ccr->ccrs = entry->ccrs;
+			complete(&ccr->complete);
+		}
+	}
+	spin_unlock_irqrestore(&ctrl->lock, flags);
+out:
+	kfree(log);
+}
+
 static void nvme_fw_act_work(struct work_struct *work)
 {
 	struct nvme_ctrl *ctrl = container_of(work,
@@ -4936,6 +4978,9 @@ static bool nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result)
 	case NVME_AER_NOTICE_DISC_CHANGED:
 		ctrl->aen_result = result;
 		break;
+	case NVME_AER_NOTICE_CCR_COMPLETED:
+		queue_work(nvme_wq, &ctrl->ccr_work);
+		break;
 	default:
 		dev_warn(ctrl->device, "async event result %08x\n", result);
 	}
@@ -5126,6 +5171,7 @@ void nvme_stop_ctrl(struct nvme_ctrl *ctrl)
 	nvme_stop_failfast_work(ctrl);
 	flush_work(&ctrl->async_event_work);
 	cancel_work_sync(&ctrl->fw_act_work);
+	cancel_work_sync(&ctrl->ccr_work);
 	if (ctrl->ops->stop_ctrl)
 		ctrl->ops->stop_ctrl(ctrl);
 }
@@ -5247,6 +5293,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	ctrl->quirks = quirks;
 	ctrl->numa_node = NUMA_NO_NODE;
 	INIT_WORK(&ctrl->scan_work, nvme_scan_work);
+	INIT_WORK(&ctrl->ccr_work, nvme_ccr_work);
 	INIT_WORK(&ctrl->async_event_work, nvme_async_event_work);
 	INIT_WORK(&ctrl->fw_act_work, nvme_fw_act_work);
 	INIT_WORK(&ctrl->delete_work, nvme_delete_ctrl_work);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 1f8937fce9a7..3f5a0722304d 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -366,6 +366,7 @@ struct nvme_ctrl {
 	struct nvme_effects_log *effects;
 	struct xarray cels;
 	struct work_struct scan_work;
+	struct work_struct ccr_work;
 	struct work_struct async_event_work;
 	struct delayed_work ka_work;
 	struct delayed_work failfast_work;
-- 
2.51.2


  parent reply	other threads:[~2025-11-26  2:13 UTC|newest]

Thread overview: 68+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-11-26  2:11 [RFC PATCH 00/14] TP8028 Rapid Path Failure Recovery Mohamed Khalfella
2025-11-26  2:11 ` [RFC PATCH 01/14] nvmet: Rapid Path Failure Recovery set controller identify fields Mohamed Khalfella
2025-12-16  1:35   ` Randy Jennings
2025-11-26  2:11 ` [RFC PATCH 02/14] nvmet/debugfs: Add ctrl uniquifier and random values Mohamed Khalfella
2025-12-16  1:43   ` Randy Jennings
2025-11-26  2:11 ` [RFC PATCH 03/14] nvmet: Implement CCR nvme command Mohamed Khalfella
2025-12-16  3:01   ` Randy Jennings
2025-12-31 21:14     ` Mohamed Khalfella
2025-12-25 13:14   ` Sagi Grimberg
2025-12-25 17:33     ` Mohamed Khalfella
2025-12-27  9:39       ` Sagi Grimberg
2025-12-31 21:35         ` Mohamed Khalfella
2025-11-26  2:11 ` [RFC PATCH 04/14] nvmet: Implement CCR logpage Mohamed Khalfella
2025-12-16  3:11   ` Randy Jennings
2025-11-26  2:11 ` [RFC PATCH 05/14] nvmet: Send an AEN on CCR completion Mohamed Khalfella
2025-12-16  3:31   ` Randy Jennings
2025-12-25 13:23   ` Sagi Grimberg
2025-12-25 18:13     ` Mohamed Khalfella
2025-12-27  9:48       ` Sagi Grimberg
2025-12-31 22:00         ` Mohamed Khalfella
2026-01-04 21:09           ` Sagi Grimberg
2026-01-07  2:58             ` Randy Jennings
2026-01-30 22:31             ` Mohamed Khalfella
2025-11-26  2:11 ` [RFC PATCH 06/14] nvme: Rapid Path Failure Recovery read controller identify fields Mohamed Khalfella
2025-12-18 15:22   ` Randy Jennings
2025-12-31 22:26     ` Mohamed Khalfella
2026-01-02 19:06       ` Mohamed Khalfella
2025-11-26  2:11 ` [RFC PATCH 07/14] nvme: Add RECOVERING nvme controller state Mohamed Khalfella
2025-12-18 23:18   ` Randy Jennings
2025-12-19  1:39     ` Randy Jennings
2025-12-25 13:29   ` Sagi Grimberg
2025-12-25 17:17     ` Mohamed Khalfella
2025-12-27  9:52       ` Sagi Grimberg
2025-12-31 22:45         ` Mohamed Khalfella
2025-12-27  9:55       ` Sagi Grimberg
2025-12-31 22:36         ` Mohamed Khalfella
2025-12-31 23:04           ` Mohamed Khalfella
2025-11-26  2:11 ` [RFC PATCH 08/14] nvme: Implement cross-controller reset recovery Mohamed Khalfella
2025-12-19  1:21   ` Randy Jennings
2025-12-27 10:14   ` Sagi Grimberg
2025-12-31  0:04     ` Randy Jennings
2026-01-04 21:14       ` Sagi Grimberg
2026-01-07  3:16         ` Randy Jennings
2025-12-31 23:43     ` Mohamed Khalfella
2026-01-04 21:39       ` Sagi Grimberg
2026-01-30 22:01         ` Mohamed Khalfella
2025-11-26  2:11 ` Mohamed Khalfella [this message]
2025-12-19  1:31   ` [RFC PATCH 09/14] nvme: Implement cross-controller reset completion Randy Jennings
2025-12-27 10:24   ` Sagi Grimberg
2025-12-31 23:51     ` Mohamed Khalfella
2026-01-04 21:15       ` Sagi Grimberg
2026-01-30 22:32         ` Mohamed Khalfella
2025-11-26  2:11 ` [RFC PATCH 10/14] nvme-tcp: Use CCR to recover controller that hits an error Mohamed Khalfella
2025-12-19  2:06   ` Randy Jennings
2026-01-01  0:04     ` Mohamed Khalfella
2025-12-27 10:35   ` Sagi Grimberg
2025-12-31  0:13     ` Randy Jennings
2026-01-04 21:19       ` Sagi Grimberg
2026-01-01  0:27     ` Mohamed Khalfella
2025-11-26  2:11 ` [RFC PATCH 11/14] nvme-rdma: " Mohamed Khalfella
2025-12-19  2:16   ` Randy Jennings
2025-12-27 10:36   ` Sagi Grimberg
2025-11-26  2:11 ` [RFC PATCH 12/14] nvme-fc: Decouple error recovery from controller reset Mohamed Khalfella
2025-12-19  2:59   ` Randy Jennings
2025-11-26  2:12 ` [RFC PATCH 13/14] nvme-fc: Use CCR to recover controller that hits an error Mohamed Khalfella
2025-12-20  1:21   ` Randy Jennings
2025-11-26  2:12 ` [RFC PATCH 14/14] nvme-fc: Hold inflight requests while in RECOVERING state Mohamed Khalfella
2025-12-20  1:44   ` Randy Jennings

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=20251126021250.2583630-10-mkhalfella@purestorage.com \
    --to=mkhalfella@purestorage.com \
    --cc=adailey@purestorage.com \
    --cc=axboe@kernel.dk \
    --cc=hare@suse.de \
    --cc=hch@lst.de \
    --cc=jmeneghi@redhat.com \
    --cc=kbusch@kernel.org \
    --cc=kch@nvidia.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --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