From: Mike Snitzer <snitzer(a)redhat.com>
nvme: decouple basic ANA log page re-read support from native multipathing
BZ: 1948690
Upstream Status: RHEL-only
This commit offers a more refined version of this rhel-8.git commit:
b904f4b8e0f90 [nvme] nvme: decouple basic ANA log page re-read support from native
multipathing
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 is achieved by factoring out nvme_update_ana() and calling it in
nvme_complete_rq() for all FAILOVER requests.
This affords userspace access to the current ANA state independent of
which layer might be doing multipathing. This makes 'nvme list-subsys'
show ANA state for all NVMe subsystems with multiple controllers. It
also allows userspace 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(a)redhat.com>
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
@@ -340,6 +340,8 @@ static inline void nvme_end_req(struct request *req)
static inline void nvme_failup_req(struct request *req)
{
+ nvme_update_ana(req);
+
nvme_req(req)->status = NVME_SC_HOST_PATH_ERROR;
nvme_end_req(req);
}
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
@@ -65,13 +65,10 @@ void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
}
}
-void nvme_failover_req(struct request *req)
+void nvme_update_ana(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);
/*
* If we got back an ANA error, we know the controller is alive but not
@@ -82,6 +79,15 @@ void nvme_failover_req(struct request *req)
set_bit(NVME_NS_ANA_PENDING, &ns->flags);
queue_work(nvme_wq, &ns->ctrl->ana_work);
}
+}
+
+void nvme_failover_req(struct request *req)
+{
+ struct nvme_ns *ns = req->q->queuedata;
+ unsigned long flags;
+
+ nvme_mpath_clear_current_path(ns);
+ nvme_update_ana(req);
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