From: Mohamed Khalfella <mkhalfella@purestorage.com>
To: Keith Busch <kbusch@kernel.org>, Jens Axboe <axboe@kernel.dk>,
Christoph Hellwig <hch@lst.de>, Sagi Grimberg <sagi@grimberg.me>
Cc: Justin Tee <justin.tee@broadcom.com>,
Naresh Gottumukkala <nareshgottumukkala83@gmail.com>,
Paul Ely <paul.ely@broadcom.com>,
Hannes Reinecke <hare@kernel.org>,
Chaitanya Kulkarni <kch@nvidia.com>,
James Smart <jsmart833426@gmail.com>,
Randy Jennings <randyj@purestorage.com>,
Mohamed Khalfella <mkhalfella@purestorage.com>,
linux-nvme@lists.infradead.org, linux-kernel@vger.kernel.org
Subject: [PATCH 09/18] nvme: Implement cross-controller reset completion
Date: Fri, 18 Sep 2026 11:14:09 -0700 [thread overview]
Message-ID: <20260918181614.3947933-10-mkhalfella@purestorage.com> (raw)
In-Reply-To: <20260918181614.3947933-1-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
ctrl->ccr_work to read NVME_LOG_CCR logpage and wakeup threads waiting
on CCR completion.
Signed-off-by: Mohamed Khalfella <mkhalfella@purestorage.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
---
drivers/nvme/host/core.c | 50 +++++++++++++++++++++++++++++++++++++++-
drivers/nvme/host/nvme.h | 1 +
2 files changed, 50 insertions(+), 1 deletion(-)
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index c8e3129d84a8..5509b58b51db 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1959,7 +1959,8 @@ 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)
{
@@ -5023,6 +5024,48 @@ 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;
+ int num_entries, ret, i;
+ unsigned long flags;
+
+ log = kmalloc_obj(*log);
+ 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);
+ num_entries = min(le16_to_cpu(log->ne), NVMF_CCR_PER_PAGE);
+ for (i = 0; i < num_entries; i++) {
+ entry = &log->entries[i];
+ if (entry->ccrs == NVME_CCR_STATUS_IN_PROGRESS)
+ continue;
+
+ list_for_each_entry(ccr, &ctrl->ccr_list, 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,
@@ -5099,6 +5142,9 @@ 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);
}
@@ -5287,6 +5333,7 @@ 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);
}
@@ -5412,6 +5459,7 @@ 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 8da75a15ac04..7096f1e4f84e 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -431,6 +431,7 @@ 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;
--
2.55.0
next prev parent reply other threads:[~2026-09-18 18:17 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-09-18 18:14 [PATCH 00/18] TP8028 Rapid Path Failure Recovery Mohamed Khalfella
2026-09-18 18:14 ` [PATCH 01/18] nvmet: Rapid Path Failure Recovery set controller identify fields Mohamed Khalfella
2026-09-18 18:14 ` [PATCH 02/18] nvmet/debugfs: Export controller CIU and CIRN via debugfs Mohamed Khalfella
2026-09-18 18:14 ` [PATCH 03/18] nvmet: Implement CCR nvme command Mohamed Khalfella
2026-09-18 18:14 ` [PATCH 04/18] nvmet: Implement CCR logpage Mohamed Khalfella
2026-09-18 18:14 ` [PATCH 05/18] nvmet: Send an AEN on CCR completion Mohamed Khalfella
2026-09-18 18:14 ` [PATCH 06/18] nvme: Rapid Path Failure Recovery read controller identify fields Mohamed Khalfella
2026-09-18 18:14 ` [PATCH 07/18] nvme: Introduce FENCING and FENCED controller states Mohamed Khalfella
2026-09-18 18:14 ` [PATCH 08/18] nvme: Implement cross-controller reset recovery Mohamed Khalfella
2026-09-18 18:14 ` Mohamed Khalfella [this message]
2026-09-18 18:14 ` [PATCH 10/18] nvme-tcp: Use CCR to recover controller that hits an error Mohamed Khalfella
2026-09-18 18:14 ` [PATCH 11/18] nvme-rdma: " Mohamed Khalfella
2026-09-18 18:14 ` [PATCH 12/18] nvme-fc: start error recovery instead of aborting timed out IOs Mohamed Khalfella
2026-09-18 18:14 ` [PATCH 13/18] nvme-fc: perform error recovery directly from ioerr_work Mohamed Khalfella
2026-09-18 18:14 ` [PATCH 14/18] nvme-fc: Use CCR to recover controller that hits an error Mohamed Khalfella
2026-09-18 18:14 ` [PATCH 15/18] nvme-fc: Hold inflight requests while in FENCING state Mohamed Khalfella
2026-09-18 18:14 ` [PATCH 16/18] nvmet: Add support for CQT to nvme target Mohamed Khalfella
2026-09-18 18:14 ` [PATCH 17/18] nvme: Add support for CQT to nvme host Mohamed Khalfella
2026-09-18 18:14 ` [PATCH 18/18] nvme: let controller deletion wait out a fencing window 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=20260918181614.3947933-10-mkhalfella@purestorage.com \
--to=mkhalfella@purestorage.com \
--cc=axboe@kernel.dk \
--cc=hare@kernel.org \
--cc=hch@lst.de \
--cc=jsmart833426@gmail.com \
--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=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®