From: Mike Snitzer <snitzer@xxxxxxxxxx>
nvme: decouple basic ANA log page re-read support from native multipathing
BZ: 1948690
Upstream Status: RHEL-only
Signed-off-by: Mike Snitzer <snitzer@xxxxxxxxxx>
rhel-8.git commit b904f4b8e0f90613bf1b2b9d9ccad3c015741daf
Author: Mike Snitzer <snitzer@xxxxxxxxxx>
Date: Tue Aug 25 21:52:47 2020 -0400
[nvme] nvme: decouple basic ANA log page re-read support from native multipathing
Message-id: <20200825215248.2291-10-snitzer@xxxxxxxxxx>
Patchwork-id: 325179
Patchwork-instance: patchwork
O-Subject: [RHEL8.3 PATCH 09/10] nvme: decouple basic ANA log page re-read support from native multipathing
Bugzilla: 1843515
RH-Acked-by: David Milburn <dmilburn@xxxxxxxxxx>
RH-Acked-by: Gopal Tiwari <gtiwari@xxxxxxxxxx>
RH-Acked-by: Ewan Milne <emilne@xxxxxxxxxx>
BZ: 1843515
Upstream Status: RHEL-only
Whether or not ANA is present is a choice of the target implementation;
the host (and whether it supports multipathing) has _zero_ influence on
this. If the target declares a path as 'inaccessible' the path _is_
inaccessible to the host. As such, ANA support should be functional
even if native multipathing is not.
Introduce ability to always re-read ANA log page as required due to ANA
error and make current ANA state available via sysfs -- even if native
multipathing is disabled on the host (e.g. nvme_core.multipath=N).
This affords userspace access to the current ANA state independent of
which layer might be doing multipathing. It also allows multipath-tools
to rely on the NVMe driver for ANA support while dm-multipath takes care
of multipathing.
And as always, if embedded NVMe users do not want any performance
overhead associated with ANA or native NVMe multipathing they can
disable CONFIG_NVME_MULTIPATH.
Signed-off-by: Mike Snitzer <snitzer@xxxxxxxxxx>
Signed-off-by: Frantisek Hrbata <fhrbata@xxxxxxxxxx>
diff a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -347,6 +347,8 @@ static inline void nvme_end_req_with_failover(struct request *req)
if (unlikely(nvme_status & NVME_SC_DNR))
goto out;
+ nvme_update_ana(req);
+
if (!blk_path_error(status)) {
pr_debug("Request meant for failover but blk_status_t (errno=%d) was not retryable.\n",
blk_status_to_errno(status));
diff a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -65,10 +65,25 @@ void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
}
}
+static inline void __nvme_update_ana(struct nvme_ns *ns)
+{
+ if (!ns->ctrl->ana_log_buf)
+ return;
+
+ set_bit(NVME_NS_ANA_PENDING, &ns->flags);
+ queue_work(nvme_wq, &ns->ctrl->ana_work);
+}
+
+
+void nvme_update_ana(struct request *req)
+{
+ if (nvme_is_ana_error(nvme_req(req)->status))
+ __nvme_update_ana(req->q->queuedata);
+}
+
void nvme_failover_req(struct request *req)
{
struct nvme_ns *ns = req->q->queuedata;
- u16 status = nvme_req(req)->status & 0x7ff;
unsigned long flags;
nvme_mpath_clear_current_path(ns);
@@ -78,10 +93,8 @@ void nvme_failover_req(struct request *req)
* ready to serve this namespace. Kick of a re-read of the ANA
* information page, and just try any other available path for now.
*/
- if (nvme_is_ana_error(status) && ns->ctrl->ana_log_buf) {
- set_bit(NVME_NS_ANA_PENDING, &ns->flags);
- queue_work(nvme_wq, &ns->ctrl->ana_work);
- }
+ if (nvme_is_ana_error(nvme_req(req)->status))
+ __nvme_update_ana(ns);
spin_lock_irqsave(&ns->head->requeue_lock, flags);
blk_steal_bios(&ns->head->requeue_list, req);
diff a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -664,6 +664,7 @@ void nvme_mpath_start_freeze(struct nvme_subsystem *subsys);
void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
struct nvme_ctrl *ctrl, int *flags);
void nvme_failover_req(struct request *req);
+void nvme_update_ana(struct request *req);
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, struct nvme_id_ns *id);
@@ -714,6 +715,9 @@ static inline void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
static inline void nvme_failover_req(struct request *req)
{
}
+static inline void nvme_update_ana(struct request *req)
+{
+}
static inline void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
{
}
--
https://gitlab.com/cki-project/kernel-ark/-/merge_requests/1024
_______________________________________________
kernel mailing list -- kernel@xxxxxxxxxxxxxxxxxxxxxxx
To unsubscribe send an email to kernel-leave@xxxxxxxxxxxxxxxxxxxxxxx
Fedora Code of Conduct: https://docs.fedoraproject.org/en-US/project/code-of-conduct/
List Guidelines: https://fedoraproject.org/wiki/Mailing_list_guidelines
List Archives: https://lists.fedoraproject.org/archives/list/kernel@xxxxxxxxxxxxxxxxxxxxxxx
Do not reply to spam on the list, report it: https://pagure.io/fedora-infrastructure
