Re: [PATCH v5 09/16] nvme: Implement cross-controller reset completion

[Mohamed Khalfella <mkhalfella@purestorage.com>]

On Mon 2026-07-13 09:11:24 +0200, Hannes Reinecke wrote:
> On 7/12/26 4:23 AM, Mohamed Khalfella wrote:
> > 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>
> > ---
> >   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 a1deffc3cc00..18de3805eff8 100644
> > --- a/drivers/nvme/host/core.c
> > +++ b/drivers/nvme/host/core.c
> > @@ -1943,7 +1943,8 @@ 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)
> >   {
> > @@ -4974,6 +4975,48 @@ 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);
> 
> I _think_ we need a marker here to figure out if the completion was 
> already called. Depending on how often the log gets updated it might
> be that we're processing two AENs before the other thread in 
> nvme_issue_wait_ccr() is able to process the completion and remove the 
> element from the list, in which case we're issuing a double completion.

Yes, processing two AENs can result in double completing ccr->complete.
However, this is harmless. It causes complete->done to be incremented
twice which is not an issue.

> 
> > +		}
> > +	}
> > +	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,
> > @@ -5050,6 +5093,9 @@ 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);
> >   	}
> > @@ -5238,6 +5284,7 @@ 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);
> 
> Might be good to have a WARN_ON(!list_empty(&ctrl->ccr_list)) here.

I do not think we are missing a case where a CCR entry can be left in
ccr_list. The only place that adds/deletes CCRs is nvme_issue_wait_ccr()
which should be running while the controller in FENCING state.

If the statement above is wrong, then there is a bug I need to fix. I
think the code should be clear such that WARN_ON() is not needed.

> 
> >   	if (ctrl->ops->stop_ctrl)
> >   		ctrl->ops->stop_ctrl(ctrl);
> >   }
> > @@ -5363,6 +5410,7 @@ 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 90b989302e21..578fedda9946 100644
> > --- a/drivers/nvme/host/nvme.h
> > +++ b/drivers/nvme/host/nvme.h
> > @@ -422,6 +422,7 @@ 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;
> 
> 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