[PATCH] nvme: allow ANA support to be independent of native multipathing

From: Mike Snitzer
Date: Thu Nov 15 2018 - 12:46:13 EST


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.

While implementing these changes care was taken to preserve the exact
ANA functionality and code sequence native multipathing has provided.
This manifests as native multipathing's nvme_failover_req() being
tweaked to call __nvme_update_ana() which was factored out to allow
nvme_update_ana() to be called independent of nvme_failover_req().

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>
---
drivers/nvme/host/core.c | 10 +++++----
drivers/nvme/host/multipath.c | 49 +++++++++++++++++++++++++++++++++----------
drivers/nvme/host/nvme.h | 4 ++++
3 files changed, 48 insertions(+), 15 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index fe957166c4a9..3df607905628 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -255,10 +255,12 @@ void nvme_complete_rq(struct request *req)
nvme_req(req)->ctrl->comp_seen = true;

if (unlikely(status != BLK_STS_OK && nvme_req_needs_retry(req))) {
- if ((req->cmd_flags & REQ_NVME_MPATH) &&
- blk_path_error(status)) {
- nvme_failover_req(req);
- return;
+ if (blk_path_error(status)) {
+ if (req->cmd_flags & REQ_NVME_MPATH) {
+ nvme_failover_req(req);
+ return;
+ }
+ nvme_update_ana(req);
}

if (!blk_queue_dying(req->q)) {
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 8e03cda770c5..0adbcff5fba2 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -22,7 +22,7 @@ MODULE_PARM_DESC(multipath,

inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
{
- return multipath && ctrl->subsys && (ctrl->subsys->cmic & (1 << 3));
+ return ctrl->subsys && (ctrl->subsys->cmic & (1 << 3));
}

/*
@@ -47,6 +47,35 @@ void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
}
}

+static bool nvme_ana_error(u16 status)
+{
+ switch (status & 0x7ff) {
+ case NVME_SC_ANA_TRANSITION:
+ case NVME_SC_ANA_INACCESSIBLE:
+ case NVME_SC_ANA_PERSISTENT_LOSS:
+ return true;
+ }
+ return false;
+}
+
+static 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)
+{
+ struct nvme_ns *ns = req->q->queuedata;
+ u16 status = nvme_req(req)->status;
+
+ if (nvme_ana_error(status))
+ __nvme_update_ana(ns);
+}
+
void nvme_failover_req(struct request *req)
{
struct nvme_ns *ns = req->q->queuedata;
@@ -58,25 +87,22 @@ void nvme_failover_req(struct request *req)
spin_unlock_irqrestore(&ns->head->requeue_lock, flags);
blk_mq_end_request(req, 0);

- switch (status & 0x7ff) {
- case NVME_SC_ANA_TRANSITION:
- case NVME_SC_ANA_INACCESSIBLE:
- case NVME_SC_ANA_PERSISTENT_LOSS:
+ if (nvme_ana_error(status)) {
/*
* If we got back an ANA error we know the controller is alive,
* but not ready to serve this namespaces. The spec suggests
* we should update our general state here, but due to the fact
* that the admin and I/O queues are not serialized that is
* fundamentally racy. So instead just clear the current path,
- * mark the the path as pending and kick of a re-read of the ANA
+ * mark the path as pending and kick off a re-read of the ANA
* log page ASAP.
*/
nvme_mpath_clear_current_path(ns);
- if (ns->ctrl->ana_log_buf) {
- set_bit(NVME_NS_ANA_PENDING, &ns->flags);
- queue_work(nvme_wq, &ns->ctrl->ana_work);
- }
- break;
+ __nvme_update_ana(ns);
+ goto kick_requeue;
+ }
+
+ switch (status & 0x7ff) {
case NVME_SC_HOST_PATH_ERROR:
/*
* Temporary transport disruption in talking to the controller.
@@ -93,6 +119,7 @@ void nvme_failover_req(struct request *req)
break;
}

+kick_requeue:
kblockd_schedule_work(&ns->head->requeue_work);
}

diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 27663ce3044e..cbe4253f2d02 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -471,6 +471,7 @@ bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl);
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);
@@ -510,6 +511,9 @@ 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)
{
}
--
2.15.0