1 files changed, 99 insertions, 27 deletions

diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 5f9cc2e7ba71..c41a5392edc9 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -49,8 +49,7 @@
 
 MODULE_ALIAS_GENL_FAMILY(IPVS_GENL_NAME);
 
-/* semaphore for IPVS sockopts. And, [gs]etsockopt may sleep. */
-static DEFINE_MUTEX(__ip_vs_mutex);
+DEFINE_MUTEX(__ip_vs_mutex); /* Serialize configuration with sockopt/netlink */
 
 /* sysctl variables */
 
@@ -241,6 +240,47 @@ static void defense_work_handler(struct work_struct *work)
 }
 #endif
 
+static void est_reload_work_handler(struct work_struct *work)
+{
+	struct netns_ipvs *ipvs =
+		container_of(work, struct netns_ipvs, est_reload_work.work);
+	int genid_done = atomic_read(&ipvs->est_genid_done);
+	unsigned long delay = HZ / 10;	/* repeat startups after failure */
+	bool repeat = false;
+	int genid;
+	int id;
+
+	mutex_lock(&ipvs->est_mutex);
+	genid = atomic_read(&ipvs->est_genid);
+	for (id = 0; id < ipvs->est_kt_count; id++) {
+		struct ip_vs_est_kt_data *kd = ipvs->est_kt_arr[id];
+
+		/* netns clean up started, abort delayed work */
+		if (!ipvs->enable)
+			goto unlock;
+		if (!kd)
+			continue;
+		/* New config ? Stop kthread tasks */
+		if (genid != genid_done)
+			ip_vs_est_kthread_stop(kd);
+		if (!kd->task) {
+			/* Do not start kthreads above 0 in calc phase */
+			if ((!id || !ipvs->est_calc_phase) &&
+			    ip_vs_est_kthread_start(ipvs, kd) < 0)
+				repeat = true;
+		}
+	}
+
+	atomic_set(&ipvs->est_genid_done, genid);
+
+	if (repeat)
+		queue_delayed_work(system_long_wq, &ipvs->est_reload_work,
+				   delay);
+
+unlock:
+	mutex_unlock(&ipvs->est_mutex);
+}
+
 int
 ip_vs_use_count_inc(void)
 {
@@ -831,7 +871,7 @@ ip_vs_copy_stats(struct ip_vs_kstats *dst, struct ip_vs_stats *src)
 {
 #define IP_VS_SHOW_STATS_COUNTER(c) dst->c = src->kstats.c - src->kstats0.c
 
-	spin_lock_bh(&src->lock);
+	spin_lock(&src->lock);
 
 	IP_VS_SHOW_STATS_COUNTER(conns);
 	IP_VS_SHOW_STATS_COUNTER(inpkts);
@@ -841,7 +881,7 @@ ip_vs_copy_stats(struct ip_vs_kstats *dst, struct ip_vs_stats *src)
 
 	ip_vs_read_estimator(dst, src);
 
-	spin_unlock_bh(&src->lock);
+	spin_unlock(&src->lock);
 }
 
 static void
@@ -862,7 +902,7 @@ ip_vs_export_stats_user(struct ip_vs_stats_user *dst, struct ip_vs_kstats *src)
 static void
 ip_vs_zero_stats(struct ip_vs_stats *stats)
 {
-	spin_lock_bh(&stats->lock);
+	spin_lock(&stats->lock);
 
 	/* get current counters as zero point, rates are zeroed */
 
@@ -876,7 +916,7 @@ ip_vs_zero_stats(struct ip_vs_stats *stats)
 
 	ip_vs_zero_estimator(stats);
 
-	spin_unlock_bh(&stats->lock);
+	spin_unlock(&stats->lock);
 }
 
 /* Allocate fields after kzalloc */
@@ -998,7 +1038,6 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
 	spin_unlock_bh(&dest->dst_lock);
 
 	if (add) {
-		ip_vs_start_estimator(svc->ipvs, &dest->stats);
 		list_add_rcu(&dest->n_list, &svc->destinations);
 		svc->num_dests++;
 		sched = rcu_dereference_protected(svc->scheduler, 1);
@@ -1051,6 +1090,10 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
 	if (ret < 0)
 		goto err_alloc;
 
+	ret = ip_vs_start_estimator(svc->ipvs, &dest->stats);
+	if (ret < 0)
+		goto err_stats;
+
 	dest->af = udest->af;
 	dest->protocol = svc->protocol;
 	dest->vaddr = svc->addr;
@@ -1071,6 +1114,9 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
 	LeaveFunction(2);
 	return 0;
 
+err_stats:
+	ip_vs_stats_release(&dest->stats);
+
 err_alloc:
 	kfree(dest);
 	return ret;
@@ -1135,14 +1181,18 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
 			      IP_VS_DBG_ADDR(svc->af, &dest->vaddr),
 			      ntohs(dest->vport));
 
+		ret = ip_vs_start_estimator(svc->ipvs, &dest->stats);
+		if (ret < 0)
+			goto err;
 		__ip_vs_update_dest(svc, dest, udest, 1);
-		ret = 0;
 	} else {
 		/*
 		 * Allocate and initialize the dest structure
 		 */
 		ret = ip_vs_new_dest(svc, udest);
 	}
+
+err:
 	LeaveFunction(2);
 
 	return ret;
@@ -1420,6 +1470,10 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u,
 		sched = NULL;
 	}
 
+	ret = ip_vs_start_estimator(ipvs, &svc->stats);
+	if (ret < 0)
+		goto out_err;
+
 	/* Bind the ct retriever */
 	RCU_INIT_POINTER(svc->pe, pe);
 	pe = NULL;
@@ -1432,8 +1486,6 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u,
 	if (svc->pe && svc->pe->conn_out)
 		atomic_inc(&ipvs->conn_out_counter);
 
-	ip_vs_start_estimator(ipvs, &svc->stats);
-
 	/* Count only IPv4 services for old get/setsockopt interface */
 	if (svc->af == AF_INET)
 		ipvs->num_services++;
@@ -1444,8 +1496,15 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u,
 	ip_vs_svc_hash(svc);
 
 	*svc_p = svc;
-	/* Now there is a service - full throttle */
-	ipvs->enable = 1;
+
+	if (!ipvs->enable) {
+		/* Now there is a service - full throttle */
+		ipvs->enable = 1;
+
+		/* Start estimation for first time */
+		ip_vs_est_reload_start(ipvs);
+	}
+
 	return 0;
 
 
@@ -4065,13 +4124,16 @@ static void ip_vs_genl_unregister(void)
 static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs)
 {
 	struct net *net = ipvs->net;
-	int idx;
 	struct ctl_table *tbl;
+	int idx, ret;
 
 	atomic_set(&ipvs->dropentry, 0);
 	spin_lock_init(&ipvs->dropentry_lock);
 	spin_lock_init(&ipvs->droppacket_lock);
 	spin_lock_init(&ipvs->securetcp_lock);
+	INIT_DELAYED_WORK(&ipvs->defense_work, defense_work_handler);
+	INIT_DELAYED_WORK(&ipvs->expire_nodest_conn_work,
+			  expire_nodest_conn_handler);
 
 	if (!net_eq(net, &init_net)) {
 		tbl = kmemdup(vs_vars, sizeof(vs_vars), GFP_KERNEL);
@@ -4139,24 +4201,27 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs)
 		tbl[idx++].mode = 0444;
 #endif
 
+	ret = -ENOMEM;
 	ipvs->sysctl_hdr = register_net_sysctl(net, "net/ipv4/vs", tbl);
-	if (ipvs->sysctl_hdr == NULL) {
-		if (!net_eq(net, &init_net))
-			kfree(tbl);
-		return -ENOMEM;
-	}
+	if (!ipvs->sysctl_hdr)
+		goto err;
 	ipvs->sysctl_tbl = tbl;
+
+	ret = ip_vs_start_estimator(ipvs, &ipvs->tot_stats->s);
+	if (ret < 0)
+		goto err;
+
 	/* Schedule defense work */
-	INIT_DELAYED_WORK(&ipvs->defense_work, defense_work_handler);
 	queue_delayed_work(system_long_wq, &ipvs->defense_work,
 			   DEFENSE_TIMER_PERIOD);
 
-	/* Init delayed work for expiring no dest conn */
-	INIT_DELAYED_WORK(&ipvs->expire_nodest_conn_work,
-			  expire_nodest_conn_handler);
-
-	ip_vs_start_estimator(ipvs, &ipvs->tot_stats->s);
 	return 0;
+
+err:
+	unregister_net_sysctl_table(ipvs->sysctl_hdr);
+	if (!net_eq(net, &init_net))
+		kfree(tbl);
+	return ret;
 }
 
 static void __net_exit ip_vs_control_net_cleanup_sysctl(struct netns_ipvs *ipvs)
@@ -4189,6 +4254,7 @@ static struct notifier_block ip_vs_dst_notifier = {
 
 int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs)
 {
+	int ret = -ENOMEM;
 	int idx;
 
 	/* Initialize rs_table */
@@ -4202,10 +4268,12 @@ int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs)
 	atomic_set(&ipvs->nullsvc_counter, 0);
 	atomic_set(&ipvs->conn_out_counter, 0);
 
+	INIT_DELAYED_WORK(&ipvs->est_reload_work, est_reload_work_handler);
+
 	/* procfs stats */
 	ipvs->tot_stats = kzalloc(sizeof(*ipvs->tot_stats), GFP_KERNEL);
 	if (!ipvs->tot_stats)
-		return -ENOMEM;
+		goto out;
 	if (ip_vs_stats_init_alloc(&ipvs->tot_stats->s) < 0)
 		goto err_tot_stats;
 
@@ -4222,7 +4290,8 @@ int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs)
 		goto err_percpu;
 #endif
 
-	if (ip_vs_control_net_init_sysctl(ipvs))
+	ret = ip_vs_control_net_init_sysctl(ipvs);
+	if (ret < 0)
 		goto err;
 
 	return 0;
@@ -4243,13 +4312,16 @@ err_vs:
 
 err_tot_stats:
 	kfree(ipvs->tot_stats);
-	return -ENOMEM;
+
+out:
+	return ret;
 }
 
 void __net_exit ip_vs_control_net_cleanup(struct netns_ipvs *ipvs)
 {
 	ip_vs_trash_cleanup(ipvs);
 	ip_vs_control_net_cleanup_sysctl(ipvs);
+	cancel_delayed_work_sync(&ipvs->est_reload_work);
 #ifdef CONFIG_PROC_FS
 	remove_proc_entry("ip_vs_stats_percpu", ipvs->net->proc_net);
 	remove_proc_entry("ip_vs_stats", ipvs->net->proc_net);