Fpin v10 patches

drivers/nvme/host/core.c

@@ -5074,6 +5074,7 @@ 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);
 

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);
 }
 
@@ -3726,6 +3730,82 @@ static struct nvmf_transport_ops nvme_fc_transport = {
 	.create_ctrl	= nvme_fc_create_ctrl,
 };
 
+static struct nvme_fc_rport *nvme_fc_rport_from_wwpn(struct nvme_fc_lport *lport,
+		u64 rport_wwpn)
+{
+	struct nvme_fc_rport *rport;
+	unsigned long flags;
+
+	spin_lock_irqsave(&nvme_fc_lock, flags);
+	list_for_each_entry(rport, &lport->endp_list, endp_list) {
+		if (!nvme_fc_rport_get(rport))
+			continue;
+		if (rport->remoteport.port_name == rport_wwpn &&
+		    rport->remoteport.port_role & FC_PORT_ROLE_NVME_TARGET) {
+			spin_unlock_irqrestore(&nvme_fc_lock, flags);
+			return rport;
+		}
+		nvme_fc_rport_put(rport);
+	}
+	spin_unlock_irqrestore(&nvme_fc_lock, flags);
+	return NULL;
+}
+
+static struct nvme_fc_lport *
+nvme_fc_lport_from_wwpn(u64 wwpn)
+{
+	struct nvme_fc_lport *lport;
+	unsigned long flags;
+
+	spin_lock_irqsave(&nvme_fc_lock, flags);
+	list_for_each_entry(lport, &nvme_fc_lport_list, port_list) {
+		if (lport->localport.port_name == wwpn &&
+		    lport->localport.port_state == FC_OBJSTATE_ONLINE) {
+			if (nvme_fc_lport_get(lport)) {
+				spin_unlock_irqrestore(&nvme_fc_lock, flags);
+				return lport;
+			}
+		}
+	}
+	spin_unlock_irqrestore(&nvme_fc_lock, flags);
+	return NULL;
+}
+
+static void
+nvme_fc_fpin_set_state(struct nvme_fc_lport *lport, u64 wwpn, bool marginal)
+{
+	struct nvme_fc_rport *rport;
+	struct nvme_fc_ctrl *ctrl;
+
+	rport = nvme_fc_rport_from_wwpn(lport, wwpn);
+	if (!rport)
+		return;
+
+	spin_lock_irq(&rport->lock);
+	list_for_each_entry(ctrl, &rport->ctrl_list, ctrl_list) {
+		if (marginal)
+			set_bit(NVME_CTRL_MARGINAL, &ctrl->ctrl.flags);
+		else
+			clear_bit(NVME_CTRL_MARGINAL, &ctrl->ctrl.flags);
+	}
+	spin_unlock_irq(&rport->lock);
+	nvme_fc_rport_put(rport);
+}
+
+void
+nvme_fc_modify_rport_fpin_state(u64 local_wwpn, u64 remote_wwpn, bool marginal)
+{
+	struct nvme_fc_lport *lport;
+
+	lport = nvme_fc_lport_from_wwpn(local_wwpn);
+	if (!lport)
+		return;
+
+	nvme_fc_fpin_set_state(lport, remote_wwpn, marginal);
+	nvme_fc_lport_put(lport);
+}
+EXPORT_SYMBOL_GPL(nvme_fc_modify_rport_fpin_state);
+
 /* Arbitrary successive failures max. With lots of subsystems could be high */
 #define DISCOVERY_MAX_FAIL	20
 

drivers/nvme/host/multipath.c

@@ -324,11 +324,14 @@ 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;
@@ -381,7 +384,8 @@ 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;
@@ -416,6 +420,9 @@ static struct nvme_ns *nvme_queue_depth_path(struct nvme_ns_head *head)
 		if (nvme_path_is_disabled(ns))
 			continue;
 
+		if (nvme_ctrl_is_marginal(ns->ctrl))
+			continue;
+
 		depth = atomic_read(&ns->ctrl->nr_active);
 
 		switch (ns->ana_state) {
@@ -439,13 +446,16 @@ static struct nvme_ns *nvme_queue_depth_path(struct nvme_ns_head *head)
 			return best_opt;
 	}
 
-	return best_opt ? best_opt : best_nonopt;
+	best_opt = (best_opt) ? best_opt : best_nonopt;
+
+	return best_opt ? best_opt : __nvme_find_path(head, numa_node_id());
 }
 
 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)

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,

drivers/nvme/host/sysfs.c

@@ -430,7 +430,9 @@ static ssize_t nvme_sysfs_show_state(struct device *dev,
 	};
 
 	if (state < ARRAY_SIZE(state_name) && state_name[state])
-		return sysfs_emit(buf, "%s\n", state_name[state]);
+		return sysfs_emit(buf, "%s\n",
+			(nvme_ctrl_is_marginal(ctrl)) ? "marginal" :
+			state_name[state]);
 
 	return sysfs_emit(buf, "unknown state\n");
 }