[PATCH 2/5] nvme-fc: marginal path handling

[Hannes Reinecke]

FPIN LI (link integrity) messages are received when the attached
fabric detects hardware errors. In response to these messages I/O
should be directed away from the affected ports, and only used
if the 'optimized' paths are unavailable.
To handle this a new controller flag 'NVME_CTRL_MARGINAL' is added
which will cause the multipath scheduler to skip these paths when
checking for 'optimized' paths. They are, however, still eligible
for non-optimized path selected. The flag is cleared upon reset as then the
faulty hardware might be replaced.

Signed-off-by: Hannes Reinecke <hare at kernel.org>
---
 drivers/nvme/host/core.c      |  1 +
 drivers/nvme/host/fc.c        |  4 ++++
 drivers/nvme/host/multipath.c | 17 +++++++++++------
 drivers/nvme/host/nvme.h      |  6 ++++++
 4 files changed, 22 insertions(+), 6 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index eb6ea8acb3cc..ab851df98079 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4833,6 +4833,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	WRITE_ONCE(ctrl->state, NVME_CTRL_NEW);
 	ctrl->passthru_err_log_enabled = false;
 	clear_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags);
+	clear_bit(NVME_CTRL_MARGINAL, &ctrl->flags);
 	spin_lock_init(&ctrl->lock);
 	mutex_init(&ctrl->namespaces_lock);
 
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 2257c3c96dd2..df7900885060 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -786,6 +786,10 @@ nvme_fc_ctrl_connectivity_loss(struct nvme_fc_ctrl *ctrl)
 		"Reconnect", ctrl->cnum);
 
 	set_bit(ASSOC_FAILED, &ctrl->flags);
+
+	/* clear 'marginal' flag as controller will be reset */
+	clear_bit(NVME_CTRL_MARGINAL, &ctrl->flags);
+
 	nvme_reset_ctrl(&ctrl->ctrl);
 }
 
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 250f3da67cc9..6d7425d34dfc 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -273,11 +273,14 @@ static struct nvme_ns *__nvme_find_path(struct nvme_ns_head *head, int node)
 
 		switch (ns->ana_state) {
 		case NVME_ANA_OPTIMIZED:
-			if (distance < found_distance) {
-				found_distance = distance;
-				found = ns;
+			if (!nvme_ctrl_is_marginal(ns->ctrl)) {
+				if (distance < found_distance) {
+					found_distance = distance;
+					found = ns;
+				}
+				break;
 			}
-			break;
+			fallthrough;
 		case NVME_ANA_NONOPTIMIZED:
 			if (distance < fallback_distance) {
 				fallback_distance = distance;
@@ -330,7 +333,8 @@ static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head)
 
 		if (ns->ana_state == NVME_ANA_OPTIMIZED) {
 			found = ns;
-			goto out;
+			if (!nvme_ctrl_is_marginal(ns->ctrl))
+				goto out;
 		}
 		if (ns->ana_state == NVME_ANA_NONOPTIMIZED)
 			found = ns;
@@ -394,7 +398,8 @@ static struct nvme_ns *nvme_queue_depth_path(struct nvme_ns_head *head)
 static inline bool nvme_path_is_optimized(struct nvme_ns *ns)
 {
 	return nvme_ctrl_state(ns->ctrl) == NVME_CTRL_LIVE &&
-		ns->ana_state == NVME_ANA_OPTIMIZED;
+		ns->ana_state == NVME_ANA_OPTIMIZED &&
+		!nvme_ctrl_is_marginal(ns->ctrl);
 }
 
 static struct nvme_ns *nvme_numa_path(struct nvme_ns_head *head)
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 51e078642127..749ffbd155fc 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -275,6 +275,7 @@ enum nvme_ctrl_flags {
 	NVME_CTRL_SKIP_ID_CNS_CS	= 4,
 	NVME_CTRL_DIRTY_CAPABILITY	= 5,
 	NVME_CTRL_FROZEN		= 6,
+	NVME_CTRL_MARGINAL		= 7,
 };
 
 struct nvme_ctrl {
@@ -417,6 +418,11 @@ static inline enum nvme_ctrl_state nvme_ctrl_state(struct nvme_ctrl *ctrl)
 	return READ_ONCE(ctrl->state);
 }
 
+static inline bool nvme_ctrl_is_marginal(struct nvme_ctrl *ctrl)
+{
+	return test_bit(NVME_CTRL_MARGINAL, &ctrl->flags);
+}
+
 enum nvme_iopolicy {
 	NVME_IOPOLICY_NUMA,
 	NVME_IOPOLICY_RR,
-- 
2.35.3