X-Git-Url: https://git.whamcloud.com/?a=blobdiff_plain;f=lnet%2Flnet%2Fapi-ni.c;h=d94f9f385cea6f77884e823d2b455519884f0c71;hb=9283e2ed6655e89fe693d35313c9dcf1d5a6703a;hp=e0b2a222b7cdec189f24133f6f749ed2c0e69a76;hpb=c0ad398fd71610c42b7ed06f8d2ca722daa01391;p=fs%2Flustre-release.git

diff --git a/lnet/lnet/api-ni.c b/lnet/lnet/api-ni.c
index e0b2a22..d94f9f3 100644
--- a/lnet/lnet/api-ni.c
+++ b/lnet/lnet/api-ni.c
@@ -80,18 +80,18 @@ MODULE_PARM_DESC(lnet_numa_range,
 
 /*
  * lnet_health_sensitivity determines by how much we decrement the health
- * value on sending error. The value defaults to 0, which means health
- * checking is turned off by default.
+ * value on sending error. The value defaults to 100, which means health
+ * interface health is decremented by 100 points every failure.
  */
-unsigned int lnet_health_sensitivity = 0;
+unsigned int lnet_health_sensitivity = 100;
 static int sensitivity_set(const char *val, cfs_kernel_param_arg_t *kp);
+#ifdef HAVE_KERNEL_PARAM_OPS
 static struct kernel_param_ops param_ops_health_sensitivity = {
 	.set = sensitivity_set,
 	.get = param_get_int,
 };
 #define param_check_health_sensitivity(name, p) \
 		__param_check(name, p, int)
-#ifdef HAVE_KERNEL_PARAM_OPS
 module_param(lnet_health_sensitivity, health_sensitivity, S_IRUGO|S_IWUSR);
 #else
 module_param_call(lnet_health_sensitivity, sensitivity_set, param_get_int,
@@ -100,6 +100,27 @@ module_param_call(lnet_health_sensitivity, sensitivity_set, param_get_int,
 MODULE_PARM_DESC(lnet_health_sensitivity,
 		"Value to decrement the health value by on error");
 
+/*
+ * lnet_recovery_interval determines how often we should perform recovery
+ * on unhealthy interfaces.
+ */
+unsigned int lnet_recovery_interval = 1;
+static int recovery_interval_set(const char *val, cfs_kernel_param_arg_t *kp);
+#ifdef HAVE_KERNEL_PARAM_OPS
+static struct kernel_param_ops param_ops_recovery_interval = {
+	.set = recovery_interval_set,
+	.get = param_get_int,
+};
+#define param_check_recovery_interval(name, p) \
+		__param_check(name, p, int)
+module_param(lnet_recovery_interval, recovery_interval, S_IRUGO|S_IWUSR);
+#else
+module_param_call(lnet_recovery_interval, recovery_interval_set, param_get_int,
+		  &lnet_recovery_interval, S_IRUGO|S_IWUSR);
+#endif
+MODULE_PARM_DESC(lnet_recovery_interval,
+		"Interval to recover unhealthy interfaces in seconds");
+
 static int lnet_interfaces_max = LNET_INTERFACES_MAX_DEFAULT;
 static int intf_max_set(const char *val, cfs_kernel_param_arg_t *kp);
 
@@ -139,8 +160,31 @@ module_param_call(lnet_peer_discovery_disabled, discovery_set, param_get_int,
 MODULE_PARM_DESC(lnet_peer_discovery_disabled,
 		"Set to 1 to disable peer discovery on this node.");
 
-unsigned lnet_transaction_timeout = 5;
+unsigned int lnet_drop_asym_route;
+static int drop_asym_route_set(const char *val, cfs_kernel_param_arg_t *kp);
+
+static struct kernel_param_ops param_ops_drop_asym_route = {
+	.set = drop_asym_route_set,
+	.get = param_get_int,
+};
+
+#define param_check_drop_asym_route(name, p)	\
+	__param_check(name, p, int)
+#ifdef HAVE_KERNEL_PARAM_OPS
+module_param(lnet_drop_asym_route, drop_asym_route, 0644);
+#else
+module_param_call(lnet_drop_asym_route, drop_asym_route_set, param_get_int,
+		  &param_ops_drop_asym_route, 0644);
+#endif
+MODULE_PARM_DESC(lnet_drop_asym_route,
+		 "Set to 1 to drop asymmetrical route messages.");
+
+#define LNET_TRANSACTION_TIMEOUT_NO_HEALTH_DEFAULT 50
+#define LNET_TRANSACTION_TIMEOUT_HEALTH_DEFAULT 10
+
+unsigned lnet_transaction_timeout = LNET_TRANSACTION_TIMEOUT_HEALTH_DEFAULT;
 static int transaction_to_set(const char *val, cfs_kernel_param_arg_t *kp);
+#ifdef HAVE_KERNEL_PARAM_OPS
 static struct kernel_param_ops param_ops_transaction_timeout = {
 	.set = transaction_to_set,
 	.get = param_get_int,
@@ -148,17 +192,18 @@ static struct kernel_param_ops param_ops_transaction_timeout = {
 
 #define param_check_transaction_timeout(name, p) \
 		__param_check(name, p, int)
-#ifdef HAVE_KERNEL_PARAM_OPS
 module_param(lnet_transaction_timeout, transaction_timeout, S_IRUGO|S_IWUSR);
 #else
 module_param_call(lnet_transaction_timeout, transaction_to_set, param_get_int,
 		  &lnet_transaction_timeout, S_IRUGO|S_IWUSR);
 #endif
-MODULE_PARM_DESC(lnet_peer_discovery_disabled,
-		"Set to 1 to disable peer discovery on this node.");
+MODULE_PARM_DESC(lnet_transaction_timeout,
+		"Maximum number of seconds to wait for a peer response.");
 
-unsigned lnet_retry_count = 0;
+#define LNET_RETRY_COUNT_HEALTH_DEFAULT 3
+unsigned lnet_retry_count = LNET_RETRY_COUNT_HEALTH_DEFAULT;
 static int retry_count_set(const char *val, cfs_kernel_param_arg_t *kp);
+#ifdef HAVE_KERNEL_PARAM_OPS
 static struct kernel_param_ops param_ops_retry_count = {
 	.set = retry_count_set,
 	.get = param_get_int,
@@ -166,7 +211,6 @@ static struct kernel_param_ops param_ops_retry_count = {
 
 #define param_check_retry_count(name, p) \
 		__param_check(name, p, int)
-#ifdef HAVE_KERNEL_PARAM_OPS
 module_param(lnet_retry_count, retry_count, S_IRUGO|S_IWUSR);
 #else
 module_param_call(lnet_retry_count, retry_count_set, param_get_int,
@@ -177,6 +221,7 @@ MODULE_PARM_DESC(lnet_retry_count,
 
 
 unsigned lnet_lnd_timeout = LNET_LND_DEFAULT_TIMEOUT;
+unsigned int lnet_current_net_count;
 
 /*
  * This sequence number keeps track of how many times DLC was used to
@@ -212,14 +257,28 @@ sensitivity_set(const char *val, cfs_kernel_param_arg_t *kp)
 	 */
 	mutex_lock(&the_lnet.ln_api_mutex);
 
-	if (the_lnet.ln_state != LNET_STATE_RUNNING) {
+	if (value > LNET_MAX_HEALTH_VALUE) {
 		mutex_unlock(&the_lnet.ln_api_mutex);
-		return 0;
+		CERROR("Invalid health value. Maximum: %d value = %lu\n",
+		       LNET_MAX_HEALTH_VALUE, value);
+		return -EINVAL;
 	}
 
-	if (value == *sensitivity) {
-		mutex_unlock(&the_lnet.ln_api_mutex);
-		return 0;
+	/*
+	 * if we're turning on health then use the health timeout
+	 * defaults.
+	 */
+	if (*sensitivity == 0 && value != 0) {
+		lnet_transaction_timeout = LNET_TRANSACTION_TIMEOUT_HEALTH_DEFAULT;
+		lnet_retry_count = LNET_RETRY_COUNT_HEALTH_DEFAULT;
+	/*
+	 * if we're turning off health then use the no health timeout
+	 * default.
+	 */
+	} else if (*sensitivity != 0 && value == 0) {
+		lnet_transaction_timeout =
+			LNET_TRANSACTION_TIMEOUT_NO_HEALTH_DEFAULT;
+		lnet_retry_count = 0;
 	}
 
 	*sensitivity = value;
@@ -230,6 +289,37 @@ sensitivity_set(const char *val, cfs_kernel_param_arg_t *kp)
 }
 
 static int
+recovery_interval_set(const char *val, cfs_kernel_param_arg_t *kp)
+{
+	int rc;
+	unsigned *interval = (unsigned *)kp->arg;
+	unsigned long value;
+
+	rc = kstrtoul(val, 0, &value);
+	if (rc) {
+		CERROR("Invalid module parameter value for 'lnet_recovery_interval'\n");
+		return rc;
+	}
+
+	if (value < 1) {
+		CERROR("lnet_recovery_interval must be at least 1 second\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * The purpose of locking the api_mutex here is to ensure that
+	 * the correct value ends up stored properly.
+	 */
+	mutex_lock(&the_lnet.ln_api_mutex);
+
+	*interval = value;
+
+	mutex_unlock(&the_lnet.ln_api_mutex);
+
+	return 0;
+}
+
+static int
 discovery_set(const char *val, cfs_kernel_param_arg_t *kp)
 {
 	int rc;
@@ -280,15 +370,16 @@ discovery_set(const char *val, cfs_kernel_param_arg_t *kp)
 }
 
 static int
-transaction_to_set(const char *val, cfs_kernel_param_arg_t *kp)
+drop_asym_route_set(const char *val, cfs_kernel_param_arg_t *kp)
 {
 	int rc;
-	unsigned *transaction_to = (unsigned *)kp->arg;
+	unsigned int *drop_asym_route = (unsigned int *)kp->arg;
 	unsigned long value;
 
 	rc = kstrtoul(val, 0, &value);
 	if (rc) {
-		CERROR("Invalid module parameter value for 'lnet_transaction_timeout'\n");
+		CERROR("Invalid module parameter value for "
+		       "'lnet_drop_asym_route'\n");
 		return rc;
 	}
 
@@ -298,11 +389,37 @@ transaction_to_set(const char *val, cfs_kernel_param_arg_t *kp)
 	 */
 	mutex_lock(&the_lnet.ln_api_mutex);
 
-	if (the_lnet.ln_state != LNET_STATE_RUNNING) {
+	if (value == *drop_asym_route) {
 		mutex_unlock(&the_lnet.ln_api_mutex);
 		return 0;
 	}
 
+	*drop_asym_route = value;
+
+	mutex_unlock(&the_lnet.ln_api_mutex);
+
+	return 0;
+}
+
+static int
+transaction_to_set(const char *val, cfs_kernel_param_arg_t *kp)
+{
+	int rc;
+	unsigned *transaction_to = (unsigned *)kp->arg;
+	unsigned long value;
+
+	rc = kstrtoul(val, 0, &value);
+	if (rc) {
+		CERROR("Invalid module parameter value for 'lnet_transaction_timeout'\n");
+		return rc;
+	}
+
+	/*
+	 * The purpose of locking the api_mutex here is to ensure that
+	 * the correct value ends up stored properly.
+	 */
+	mutex_lock(&the_lnet.ln_api_mutex);
+
 	if (value < lnet_retry_count || value == 0) {
 		mutex_unlock(&the_lnet.ln_api_mutex);
 		CERROR("Invalid value for lnet_transaction_timeout (%lu). "
@@ -346,9 +463,10 @@ retry_count_set(const char *val, cfs_kernel_param_arg_t *kp)
 	 */
 	mutex_lock(&the_lnet.ln_api_mutex);
 
-	if (the_lnet.ln_state != LNET_STATE_RUNNING) {
+	if (lnet_health_sensitivity == 0) {
 		mutex_unlock(&the_lnet.ln_api_mutex);
-		return 0;
+		CERROR("Can not set retry_count when health feature is turned off\n");
+		return -EINVAL;
 	}
 
 	if (value > lnet_transaction_timeout) {
@@ -359,11 +477,6 @@ retry_count_set(const char *val, cfs_kernel_param_arg_t *kp)
 		return -EINVAL;
 	}
 
-	if (value == *retry_count) {
-		mutex_unlock(&the_lnet.ln_api_mutex);
-		return 0;
-	}
-
 	*retry_count = value;
 
 	if (value == 0)
@@ -739,28 +852,70 @@ lnet_unregister_lnd(struct lnet_lnd *lnd)
 EXPORT_SYMBOL(lnet_unregister_lnd);
 
 void
+lnet_counters_get_common(struct lnet_counters_common *common)
+{
+	struct lnet_counters *ctr;
+	int i;
+
+	memset(common, 0, sizeof(*common));
+
+	lnet_net_lock(LNET_LOCK_EX);
+
+	cfs_percpt_for_each(ctr, i, the_lnet.ln_counters) {
+		common->lcc_msgs_max     += ctr->lct_common.lcc_msgs_max;
+		common->lcc_msgs_alloc   += ctr->lct_common.lcc_msgs_alloc;
+		common->lcc_errors       += ctr->lct_common.lcc_errors;
+		common->lcc_send_count   += ctr->lct_common.lcc_send_count;
+		common->lcc_recv_count   += ctr->lct_common.lcc_recv_count;
+		common->lcc_route_count  += ctr->lct_common.lcc_route_count;
+		common->lcc_drop_count   += ctr->lct_common.lcc_drop_count;
+		common->lcc_send_length  += ctr->lct_common.lcc_send_length;
+		common->lcc_recv_length  += ctr->lct_common.lcc_recv_length;
+		common->lcc_route_length += ctr->lct_common.lcc_route_length;
+		common->lcc_drop_length  += ctr->lct_common.lcc_drop_length;
+	}
+	lnet_net_unlock(LNET_LOCK_EX);
+}
+EXPORT_SYMBOL(lnet_counters_get_common);
+
+void
 lnet_counters_get(struct lnet_counters *counters)
 {
 	struct lnet_counters *ctr;
+	struct lnet_counters_health *health = &counters->lct_health;
 	int		i;
 
 	memset(counters, 0, sizeof(*counters));
 
+	lnet_counters_get_common(&counters->lct_common);
+
 	lnet_net_lock(LNET_LOCK_EX);
 
 	cfs_percpt_for_each(ctr, i, the_lnet.ln_counters) {
-		counters->msgs_max     += ctr->msgs_max;
-		counters->msgs_alloc   += ctr->msgs_alloc;
-		counters->errors       += ctr->errors;
-		counters->send_count   += ctr->send_count;
-		counters->recv_count   += ctr->recv_count;
-		counters->route_count  += ctr->route_count;
-		counters->drop_count   += ctr->drop_count;
-		counters->send_length  += ctr->send_length;
-		counters->recv_length  += ctr->recv_length;
-		counters->route_length += ctr->route_length;
-		counters->drop_length  += ctr->drop_length;
-
+		health->lch_rst_alloc    += ctr->lct_health.lch_rst_alloc;
+		health->lch_resend_count += ctr->lct_health.lch_resend_count;
+		health->lch_response_timeout_count +=
+				ctr->lct_health.lch_response_timeout_count;
+		health->lch_local_interrupt_count +=
+				ctr->lct_health.lch_local_interrupt_count;
+		health->lch_local_dropped_count +=
+				ctr->lct_health.lch_local_dropped_count;
+		health->lch_local_aborted_count +=
+				ctr->lct_health.lch_local_aborted_count;
+		health->lch_local_no_route_count +=
+				ctr->lct_health.lch_local_no_route_count;
+		health->lch_local_timeout_count +=
+				ctr->lct_health.lch_local_timeout_count;
+		health->lch_local_error_count +=
+				ctr->lct_health.lch_local_error_count;
+		health->lch_remote_dropped_count +=
+				ctr->lct_health.lch_remote_dropped_count;
+		health->lch_remote_error_count +=
+				ctr->lct_health.lch_remote_error_count;
+		health->lch_remote_timeout_count +=
+				ctr->lct_health.lch_remote_timeout_count;
+		health->lch_network_timeout_count +=
+				ctr->lct_health.lch_network_timeout_count;
 	}
 	lnet_net_unlock(LNET_LOCK_EX);
 }
@@ -978,6 +1133,8 @@ lnet_prepare(lnet_pid_t requested_pid)
 	INIT_LIST_HEAD(&the_lnet.ln_mt_localNIRecovq);
 	INIT_LIST_HEAD(&the_lnet.ln_mt_peerNIRecovq);
 	init_waitqueue_head(&the_lnet.ln_dc_waitq);
+	LNetInvalidateEQHandle(&the_lnet.ln_mt_eqh);
+	init_completion(&the_lnet.ln_started);
 
 	rc = lnet_descriptor_setup();
 	if (rc != 0)
@@ -1046,6 +1203,8 @@ lnet_prepare(lnet_pid_t requested_pid)
 static int
 lnet_unprepare (void)
 {
+	int rc;
+
 	/* NB no LNET_LOCK since this is the last reference.  All LND instances
 	 * have shut down already, so it is safe to unlink and free all
 	 * descriptors, even those that appear committed to a network op (eg MD
@@ -1057,6 +1216,12 @@ lnet_unprepare (void)
 	LASSERT(list_empty(&the_lnet.ln_test_peers));
 	LASSERT(list_empty(&the_lnet.ln_nets));
 
+	if (!LNetEQHandleIsInvalid(the_lnet.ln_mt_eqh)) {
+		rc = LNetEQFree(the_lnet.ln_mt_eqh);
+		LNetInvalidateEQHandle(&the_lnet.ln_mt_eqh);
+		LASSERT(rc == 0);
+	}
+
 	lnet_portals_destroy();
 
 	if (the_lnet.ln_md_containers != NULL) {
@@ -1205,18 +1370,28 @@ lnet_cpt_of_nid(lnet_nid_t nid, struct lnet_ni *ni)
 EXPORT_SYMBOL(lnet_cpt_of_nid);
 
 int
-lnet_islocalnet(__u32 net_id)
+lnet_islocalnet_locked(__u32 net_id)
 {
 	struct lnet_net *net;
-	int		cpt;
-	bool		local;
-
-	cpt = lnet_net_lock_current();
+	bool local;
 
 	net = lnet_get_net_locked(net_id);
 
 	local = net != NULL;
 
+	return local;
+}
+
+int
+lnet_islocalnet(__u32 net_id)
+{
+	int cpt;
+	bool local;
+
+	cpt = lnet_net_lock_current();
+
+	local = lnet_islocalnet_locked(net_id);
+
 	lnet_net_unlock(cpt);
 
 	return local;
@@ -1374,6 +1549,45 @@ lnet_get_ni_count(void)
 }
 
 int
+lnet_get_net_count(void)
+{
+	struct lnet_net *net;
+	int count = 0;
+
+	lnet_net_lock(0);
+
+	list_for_each_entry(net, &the_lnet.ln_nets, net_list) {
+		count++;
+	}
+
+	lnet_net_unlock(0);
+
+	return count;
+}
+
+void
+lnet_swap_pinginfo(struct lnet_ping_buffer *pbuf)
+{
+	struct lnet_ni_status *stat;
+	int nnis;
+	int i;
+
+	__swab32s(&pbuf->pb_info.pi_magic);
+	__swab32s(&pbuf->pb_info.pi_features);
+	__swab32s(&pbuf->pb_info.pi_pid);
+	__swab32s(&pbuf->pb_info.pi_nnis);
+	nnis = pbuf->pb_info.pi_nnis;
+	if (nnis > pbuf->pb_nnis)
+		nnis = pbuf->pb_nnis;
+	for (i = 0; i < nnis; i++) {
+		stat = &pbuf->pb_info.pi_ni[i];
+		__swab64s(&stat->ns_nid);
+		__swab32s(&stat->ns_status);
+	}
+	return;
+}
+
+int
 lnet_ping_info_validate(struct lnet_ping_info *pinfo)
 {
 	if (!pinfo)
@@ -1770,11 +1984,6 @@ lnet_ni_tq_credits(struct lnet_ni *ni)
 static void
 lnet_ni_unlink_locked(struct lnet_ni *ni)
 {
-	if (!list_empty(&ni->ni_cptlist)) {
-		list_del_init(&ni->ni_cptlist);
-		lnet_ni_decref_locked(ni, 0);
-	}
-
 	/* move it to zombie list and nobody can find it anymore */
 	LASSERT(!list_empty(&ni->ni_netlist));
 	list_move(&ni->ni_netlist, &ni->ni_net->net_ni_zombie);
@@ -1803,7 +2012,7 @@ lnet_clear_zombies_nis_locked(struct lnet_net *net)
 		list_del_init(&ni->ni_netlist);
 		/* the ni should be in deleting state. If it's not it's
 		 * a bug */
-		LASSERT(ni->ni_state & LNET_NI_STATE_DELETING);
+		LASSERT(ni->ni_state == LNET_NI_STATE_DELETING);
 		cfs_percpt_for_each(ref, j, ni->ni_refs) {
 			if (*ref == 0)
 				continue;
@@ -1852,8 +2061,7 @@ lnet_shutdown_lndni(struct lnet_ni *ni)
 
 	lnet_net_lock(LNET_LOCK_EX);
 	lnet_ni_lock(ni);
-	ni->ni_state |= LNET_NI_STATE_DELETING;
-	ni->ni_state &= ~LNET_NI_STATE_ACTIVE;
+	ni->ni_state = LNET_NI_STATE_DELETING;
 	lnet_ni_unlock(ni);
 	lnet_ni_unlink_locked(ni);
 	lnet_incr_dlc_seq();
@@ -1991,8 +2199,7 @@ lnet_startup_lndni(struct lnet_ni *ni, struct lnet_lnd_tunables *tun)
 	}
 
 	lnet_ni_lock(ni);
-	ni->ni_state |= LNET_NI_STATE_ACTIVE;
-	ni->ni_state &= ~LNET_NI_STATE_INIT;
+	ni->ni_state = LNET_NI_STATE_ACTIVE;
 	lnet_ni_unlock(ni);
 
 	/* We keep a reference on the loopback net through the loopback NI */
@@ -2204,6 +2411,9 @@ lnet_startup_lndnet(struct lnet_net *net, struct lnet_lnd_tunables *tun)
 		lnet_net_unlock(LNET_LOCK_EX);
 	}
 
+	/* update net count */
+	lnet_current_net_count = lnet_get_net_count();
+
 	return ni_count;
 
 failed1:
@@ -2298,12 +2508,9 @@ int lnet_lib_init(void)
 	}
 
 	the_lnet.ln_refcount = 0;
-	LNetInvalidateEQHandle(&the_lnet.ln_rc_eqh);
 	INIT_LIST_HEAD(&the_lnet.ln_lnds);
 	INIT_LIST_HEAD(&the_lnet.ln_net_zombie);
-	INIT_LIST_HEAD(&the_lnet.ln_rcd_zombie);
 	INIT_LIST_HEAD(&the_lnet.ln_msg_resend);
-	INIT_LIST_HEAD(&the_lnet.ln_rcd_deathrow);
 
 	/* The hash table size is the number of bits it takes to express the set
 	 * ln_num_routes, minus 1 (better to under estimate than over so we
@@ -2419,10 +2626,6 @@ LNetNIInit(lnet_pid_t requested_pid)
 		if (rc != 0)
 			goto err_shutdown_lndnis;
 
-		rc = lnet_check_routes();
-		if (rc != 0)
-			goto err_destroy_routes;
-
 		rc = lnet_rtrpools_alloc(im_a_router);
 		if (rc != 0)
 			goto err_destroy_routes;
@@ -2441,29 +2644,40 @@ LNetNIInit(lnet_pid_t requested_pid)
 
 	lnet_ping_target_update(pbuf, ping_mdh);
 
-	rc = lnet_monitor_thr_start();
-	if (rc != 0)
+	rc = LNetEQAlloc(0, lnet_mt_event_handler, &the_lnet.ln_mt_eqh);
+	if (rc != 0) {
+		CERROR("Can't allocate monitor thread EQ: %d\n", rc);
 		goto err_stop_ping;
+	}
 
 	rc = lnet_push_target_init();
 	if (rc != 0)
-		goto err_stop_monitor_thr;
+		goto err_stop_ping;
 
 	rc = lnet_peer_discovery_start();
 	if (rc != 0)
 		goto err_destroy_push_target;
 
+	rc = lnet_monitor_thr_start();
+	if (rc != 0)
+		goto err_stop_discovery_thr;
+
 	lnet_fault_init();
 	lnet_router_debugfs_init();
 
 	mutex_unlock(&the_lnet.ln_api_mutex);
 
+	complete_all(&the_lnet.ln_started);
+
+	/* wait for all routers to start */
+	lnet_wait_router_start();
+
 	return 0;
 
+err_stop_discovery_thr:
+	lnet_peer_discovery_stop();
 err_destroy_push_target:
 	lnet_push_target_fini();
-err_stop_monitor_thr:
-	lnet_monitor_thr_stop();
 err_stop_ping:
 	lnet_ping_target_fini();
 err_acceptor_stop:
@@ -2512,10 +2726,10 @@ LNetNIFini()
 
 		lnet_fault_fini();
 
-		lnet_router_debugfs_init();
+		lnet_router_debugfs_fini();
+		lnet_monitor_thr_stop();
 		lnet_peer_discovery_stop();
 		lnet_push_target_fini();
-		lnet_monitor_thr_stop();
 		lnet_ping_target_fini();
 
 		/* Teardown fns that use my own API functions BEFORE here */
@@ -3290,6 +3504,44 @@ unlock:
 	return rc;
 }
 
+static int
+lnet_get_local_ni_recovery_list(struct lnet_ioctl_recovery_list *list)
+{
+	struct lnet_ni *ni;
+	int i = 0;
+
+	lnet_net_lock(LNET_LOCK_EX);
+	list_for_each_entry(ni, &the_lnet.ln_mt_localNIRecovq, ni_recovery) {
+		list->rlst_nid_array[i] = ni->ni_nid;
+		i++;
+		if (i >= LNET_MAX_SHOW_NUM_NID)
+			break;
+	}
+	lnet_net_unlock(LNET_LOCK_EX);
+	list->rlst_num_nids = i;
+
+	return 0;
+}
+
+static int
+lnet_get_peer_ni_recovery_list(struct lnet_ioctl_recovery_list *list)
+{
+	struct lnet_peer_ni *lpni;
+	int i = 0;
+
+	lnet_net_lock(LNET_LOCK_EX);
+	list_for_each_entry(lpni, &the_lnet.ln_mt_peerNIRecovq, lpni_recovery) {
+		list->rlst_nid_array[i] = lpni->lpni_nid;
+		i++;
+		if (i >= LNET_MAX_SHOW_NUM_NID)
+			break;
+	}
+	lnet_net_unlock(LNET_LOCK_EX);
+	list->rlst_num_nids = i;
+
+	return 0;
+}
+
 /**
  * LNet ioctl handler.
  *
@@ -3315,26 +3567,28 @@ LNetCtl(unsigned int cmd, void *arg)
 	case IOC_LIBCFS_FAIL_NID:
 		return lnet_fail_nid(data->ioc_nid, data->ioc_count);
 
-	case IOC_LIBCFS_ADD_ROUTE:
+	case IOC_LIBCFS_ADD_ROUTE: {
+		/* default router sensitivity to 1 */
+		unsigned int sensitivity = 1;
 		config = arg;
 
 		if (config->cfg_hdr.ioc_len < sizeof(*config))
 			return -EINVAL;
 
+		if (config->cfg_config_u.cfg_route.rtr_sensitivity) {
+			sensitivity =
+			  config->cfg_config_u.cfg_route.rtr_sensitivity;
+		}
+
 		mutex_lock(&the_lnet.ln_api_mutex);
 		rc = lnet_add_route(config->cfg_net,
 				    config->cfg_config_u.cfg_route.rtr_hop,
 				    config->cfg_nid,
 				    config->cfg_config_u.cfg_route.
-					rtr_priority);
-		if (rc == 0) {
-			rc = lnet_check_routes();
-			if (rc != 0)
-				lnet_del_route(config->cfg_net,
-					       config->cfg_nid);
-		}
+					rtr_priority, sensitivity);
 		mutex_unlock(&the_lnet.ln_api_mutex);
 		return rc;
+	}
 
 	case IOC_LIBCFS_DEL_ROUTE:
 		config = arg;
@@ -3360,7 +3614,9 @@ LNetCtl(unsigned int cmd, void *arg)
 				    &config->cfg_nid,
 				    &config->cfg_config_u.cfg_route.rtr_flags,
 				    &config->cfg_config_u.cfg_route.
-					rtr_priority);
+					rtr_priority,
+				    &config->cfg_config_u.cfg_route.
+					rtr_sensitivity);
 		mutex_unlock(&the_lnet.ln_api_mutex);
 		return rc;
 
@@ -3513,6 +3769,20 @@ LNetCtl(unsigned int cmd, void *arg)
 		return rc;
 	}
 
+	case IOC_LIBCFS_GET_RECOVERY_QUEUE: {
+		struct lnet_ioctl_recovery_list *list = arg;
+		if (list->rlst_hdr.ioc_len < sizeof(*list))
+			return -EINVAL;
+
+		mutex_lock(&the_lnet.ln_api_mutex);
+		if (list->rlst_type == LNET_HEALTH_TYPE_LOCAL_NI)
+			rc = lnet_get_local_ni_recovery_list(list);
+		else
+			rc = lnet_get_peer_ni_recovery_list(list);
+		mutex_unlock(&the_lnet.ln_api_mutex);
+		return rc;
+	}
+
 	case IOC_LIBCFS_ADD_PEER_NI: {
 		struct lnet_ioctl_peer_cfg *cfg = arg;
 
@@ -3609,6 +3879,7 @@ LNetCtl(unsigned int cmd, void *arg)
 			lnet_peer_ni_set_healthv(cfg->rh_nid, value,
 						  cfg->rh_all);
 		mutex_unlock(&the_lnet.ln_api_mutex);
+		return 0;
 	}
 
 	case IOC_LIBCFS_NOTIFY_ROUTER: {
@@ -3619,7 +3890,7 @@ LNetCtl(unsigned int cmd, void *arg)
 		 * that deadline to the wall clock.
 		 */
 		deadline += ktime_get_seconds();
-		return lnet_notify(NULL, data->ioc_nid, data->ioc_flags,
+		return lnet_notify(NULL, data->ioc_nid, data->ioc_flags, false,
 				   deadline);
 	}
 
@@ -3649,9 +3920,9 @@ LNetCtl(unsigned int cmd, void *arg)
 		/* If timeout is negative then set default of 3 minutes */
 		if (((s32)data->ioc_u32[1] <= 0) ||
 		    data->ioc_u32[1] > (DEFAULT_PEER_TIMEOUT * MSEC_PER_SEC))
-			timeout = msecs_to_jiffies(DEFAULT_PEER_TIMEOUT * MSEC_PER_SEC);
+			timeout = cfs_time_seconds(DEFAULT_PEER_TIMEOUT);
 		else
-			timeout = msecs_to_jiffies(data->ioc_u32[1]);
+			timeout = nsecs_to_jiffies(data->ioc_u32[1] * NSEC_PER_MSEC);
 
 		rc = lnet_ping(id, timeout, data->ioc_pbuf1,
 			       data->ioc_plen1 / sizeof(struct lnet_process_id));
@@ -3671,9 +3942,9 @@ LNetCtl(unsigned int cmd, void *arg)
 		/* If timeout is negative then set default of 3 minutes */
 		if (((s32)ping->op_param) <= 0 ||
 		    ping->op_param > (DEFAULT_PEER_TIMEOUT * MSEC_PER_SEC))
-			timeout = msecs_to_jiffies(DEFAULT_PEER_TIMEOUT * MSEC_PER_SEC);
+			timeout = cfs_time_seconds(DEFAULT_PEER_TIMEOUT);
 		else
-			timeout = msecs_to_jiffies(ping->op_param);
+			timeout = nsecs_to_jiffies(ping->op_param * NSEC_PER_MSEC);
 
 		rc = lnet_ping(ping->ping_id, timeout,
 			       ping->ping_buf,
@@ -3819,7 +4090,7 @@ static int lnet_ping(struct lnet_process_id id, signed long timeout,
 	int which;
 	int unlinked = 0;
 	int replied = 0;
-	const signed long a_long_time = msecs_to_jiffies(60 * MSEC_PER_SEC);
+	const signed long a_long_time = cfs_time_seconds(60);
 	struct lnet_ping_buffer *pbuf;
 	struct lnet_process_id tmpid;
 	int i;
@@ -4082,3 +4353,16 @@ out:
 
 	return rc;
 }
+
+/**
+ * Retrieve peer discovery status.
+ *
+ * \retval 1 if lnet_peer_discovery_disabled is 0
+ * \retval 0 if lnet_peer_discovery_disabled is 1
+ */
+int
+LNetGetPeerDiscoveryStatus(void)
+{
+	return !lnet_peer_discovery_disabled;
+}
+EXPORT_SYMBOL(LNetGetPeerDiscoveryStatus);