1 files changed, 143 insertions, 108 deletions

diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index d75eb39..1e27a1f 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -619,15 +619,21 @@ struct ip_vs_dest *ip_vs_find_dest(struct net  *net, int af,
 				   const union nf_inet_addr *daddr,
 				   __be16 dport,
 				   const union nf_inet_addr *vaddr,
-				   __be16 vport, __u16 protocol, __u32 fwmark)
+				   __be16 vport, __u16 protocol, __u32 fwmark,
+				   __u32 flags)
 {
 	struct ip_vs_dest *dest;
 	struct ip_vs_service *svc;
+	__be16 port = dport;
 
 	svc = ip_vs_service_get(net, af, fwmark, protocol, vaddr, vport);
 	if (!svc)
 		return NULL;
-	dest = ip_vs_lookup_dest(svc, daddr, dport);
+	if (fwmark && (flags & IP_VS_CONN_F_FWD_MASK) != IP_VS_CONN_F_MASQ)
+		port = 0;
+	dest = ip_vs_lookup_dest(svc, daddr, port);
+	if (!dest)
+		dest = ip_vs_lookup_dest(svc, daddr, port ^ dport);
 	if (dest)
 		atomic_inc(&dest->refcnt);
 	ip_vs_service_put(svc);
@@ -856,15 +862,12 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest,
 	}
 
 	dest = kzalloc(sizeof(struct ip_vs_dest), GFP_KERNEL);
-	if (dest == NULL) {
-		pr_err("%s(): no memory.\n", __func__);
+	if (dest == NULL)
 		return -ENOMEM;
-	}
+
 	dest->stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats);
-	if (!dest->stats.cpustats) {
-		pr_err("%s() alloc_percpu failed\n", __func__);
+	if (!dest->stats.cpustats)
 		goto err_alloc;
-	}
 
 	dest->af = svc->af;
 	dest->protocol = svc->protocol;
@@ -1168,10 +1171,8 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
 		goto out_err;
 	}
 	svc->stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats);
-	if (!svc->stats.cpustats) {
-		pr_err("%s() alloc_percpu failed\n", __func__);
+	if (!svc->stats.cpustats)
 		goto out_err;
-	}
 
 	/* I'm the first user of the service */
 	atomic_set(&svc->usecnt, 0);
@@ -1334,9 +1335,9 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u)
 		ip_vs_bind_pe(svc, pe);
 	}
 
-  out_unlock:
+out_unlock:
 	write_unlock_bh(&__ip_vs_svc_lock);
-  out:
+out:
 	ip_vs_scheduler_put(old_sched);
 	ip_vs_pe_put(old_pe);
 	return ret;
@@ -1483,7 +1484,7 @@ static int ip_vs_flush(struct net *net)
  *	Delete service by {netns} in the service table.
  *	Called by __ip_vs_cleanup()
  */
-void __ip_vs_service_cleanup(struct net *net)
+void ip_vs_service_net_cleanup(struct net *net)
 {
 	EnterFunction(2);
 	/* Check for "full" addressed entries */
@@ -1520,12 +1521,11 @@ static int ip_vs_dst_event(struct notifier_block *this, unsigned long event,
 {
 	struct net_device *dev = ptr;
 	struct net *net = dev_net(dev);
-	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct ip_vs_service *svc;
 	struct ip_vs_dest *dest;
 	unsigned int idx;
 
-	if (event != NETDEV_UNREGISTER || !ipvs)
+	if (event != NETDEV_UNREGISTER)
 		return NOTIFY_DONE;
 	IP_VS_DBG(3, "%s() dev=%s\n", __func__, dev->name);
 	EnterFunction(2);
@@ -1551,7 +1551,7 @@ static int ip_vs_dst_event(struct notifier_block *this, unsigned long event,
 		}
 	}
 
-	list_for_each_entry(dest, &ipvs->dest_trash, n_list) {
+	list_for_each_entry(dest, &net_ipvs(net)->dest_trash, n_list) {
 		__ip_vs_dev_reset(dest, dev);
 	}
 	mutex_unlock(&__ip_vs_mutex);
@@ -1663,7 +1663,7 @@ proc_do_sync_mode(ctl_table *table, int write,
 /*
  *	IPVS sysctl table (under the /proc/sys/net/ipv4/vs/)
  *	Do not change order or insert new entries without
- *	align with netns init in __ip_vs_control_init()
+ *	align with netns init in ip_vs_control_net_init()
  */
 
 static struct ctl_table vs_vars[] = {
@@ -2284,6 +2284,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 	struct ip_vs_service *svc;
 	struct ip_vs_dest_user *udest_compat;
 	struct ip_vs_dest_user_kern udest;
+	struct netns_ipvs *ipvs = net_ipvs(net);
 
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
@@ -2304,6 +2305,24 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 	/* increase the module use count */
 	ip_vs_use_count_inc();
 
+	/* Handle daemons since they have another lock */
+	if (cmd == IP_VS_SO_SET_STARTDAEMON ||
+	    cmd == IP_VS_SO_SET_STOPDAEMON) {
+		struct ip_vs_daemon_user *dm = (struct ip_vs_daemon_user *)arg;
+
+		if (mutex_lock_interruptible(&ipvs->sync_mutex)) {
+			ret = -ERESTARTSYS;
+			goto out_dec;
+		}
+		if (cmd == IP_VS_SO_SET_STARTDAEMON)
+			ret = start_sync_thread(net, dm->state, dm->mcast_ifn,
+						dm->syncid);
+		else
+			ret = stop_sync_thread(net, dm->state);
+		mutex_unlock(&ipvs->sync_mutex);
+		goto out_dec;
+	}
+
 	if (mutex_lock_interruptible(&__ip_vs_mutex)) {
 		ret = -ERESTARTSYS;
 		goto out_dec;
@@ -2317,15 +2336,6 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 		/* Set timeout values for (tcp tcpfin udp) */
 		ret = ip_vs_set_timeout(net, (struct ip_vs_timeout_user *)arg);
 		goto out_unlock;
-	} else if (cmd == IP_VS_SO_SET_STARTDAEMON) {
-		struct ip_vs_daemon_user *dm = (struct ip_vs_daemon_user *)arg;
-		ret = start_sync_thread(net, dm->state, dm->mcast_ifn,
-					dm->syncid);
-		goto out_unlock;
-	} else if (cmd == IP_VS_SO_SET_STOPDAEMON) {
-		struct ip_vs_daemon_user *dm = (struct ip_vs_daemon_user *)arg;
-		ret = stop_sync_thread(net, dm->state);
-		goto out_unlock;
 	}
 
 	usvc_compat = (struct ip_vs_service_user *)arg;
@@ -2470,7 +2480,7 @@ __ip_vs_get_service_entries(struct net *net,
 			count++;
 		}
 	}
-  out:
+out:
 	return ret;
 }
 
@@ -2585,6 +2595,33 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 
 	if (copy_from_user(arg, user, copylen) != 0)
 		return -EFAULT;
+	/*
+	 * Handle daemons first since it has its own locking
+	 */
+	if (cmd == IP_VS_SO_GET_DAEMON) {
+		struct ip_vs_daemon_user d[2];
+
+		memset(&d, 0, sizeof(d));
+		if (mutex_lock_interruptible(&ipvs->sync_mutex))
+			return -ERESTARTSYS;
+
+		if (ipvs->sync_state & IP_VS_STATE_MASTER) {
+			d[0].state = IP_VS_STATE_MASTER;
+			strlcpy(d[0].mcast_ifn, ipvs->master_mcast_ifn,
+				sizeof(d[0].mcast_ifn));
+			d[0].syncid = ipvs->master_syncid;
+		}
+		if (ipvs->sync_state & IP_VS_STATE_BACKUP) {
+			d[1].state = IP_VS_STATE_BACKUP;
+			strlcpy(d[1].mcast_ifn, ipvs->backup_mcast_ifn,
+				sizeof(d[1].mcast_ifn));
+			d[1].syncid = ipvs->backup_syncid;
+		}
+		if (copy_to_user(user, &d, sizeof(d)) != 0)
+			ret = -EFAULT;
+		mutex_unlock(&ipvs->sync_mutex);
+		return ret;
+	}
 
 	if (mutex_lock_interruptible(&__ip_vs_mutex))
 		return -ERESTARTSYS;
@@ -2683,33 +2720,11 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 	}
 	break;
 
-	case IP_VS_SO_GET_DAEMON:
-	{
-		struct ip_vs_daemon_user d[2];
-
-		memset(&d, 0, sizeof(d));
-		if (ipvs->sync_state & IP_VS_STATE_MASTER) {
-			d[0].state = IP_VS_STATE_MASTER;
-			strlcpy(d[0].mcast_ifn, ipvs->master_mcast_ifn,
-				sizeof(d[0].mcast_ifn));
-			d[0].syncid = ipvs->master_syncid;
-		}
-		if (ipvs->sync_state & IP_VS_STATE_BACKUP) {
-			d[1].state = IP_VS_STATE_BACKUP;
-			strlcpy(d[1].mcast_ifn, ipvs->backup_mcast_ifn,
-				sizeof(d[1].mcast_ifn));
-			d[1].syncid = ipvs->backup_syncid;
-		}
-		if (copy_to_user(user, &d, sizeof(d)) != 0)
-			ret = -EFAULT;
-	}
-	break;
-
 	default:
 		ret = -EINVAL;
 	}
 
-  out:
+out:
 	mutex_unlock(&__ip_vs_mutex);
 	return ret;
 }
@@ -3207,7 +3222,7 @@ static int ip_vs_genl_dump_daemons(struct sk_buff *skb,
 	struct net *net = skb_sknet(skb);
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
-	mutex_lock(&__ip_vs_mutex);
+	mutex_lock(&ipvs->sync_mutex);
 	if ((ipvs->sync_state & IP_VS_STATE_MASTER) && !cb->args[0]) {
 		if (ip_vs_genl_dump_daemon(skb, IP_VS_STATE_MASTER,
 					   ipvs->master_mcast_ifn,
@@ -3227,7 +3242,7 @@ static int ip_vs_genl_dump_daemons(struct sk_buff *skb,
 	}
 
 nla_put_failure:
-	mutex_unlock(&__ip_vs_mutex);
+	mutex_unlock(&ipvs->sync_mutex);
 
 	return skb->len;
 }
@@ -3273,13 +3288,9 @@ static int ip_vs_genl_set_config(struct net *net, struct nlattr **attrs)
 	return ip_vs_set_timeout(net, &t);
 }
 
-static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
+static int ip_vs_genl_set_daemon(struct sk_buff *skb, struct genl_info *info)
 {
-	struct ip_vs_service *svc = NULL;
-	struct ip_vs_service_user_kern usvc;
-	struct ip_vs_dest_user_kern udest;
 	int ret = 0, cmd;
-	int need_full_svc = 0, need_full_dest = 0;
 	struct net *net;
 	struct netns_ipvs *ipvs;
 
@@ -3287,19 +3298,10 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
 	ipvs = net_ipvs(net);
 	cmd = info->genlhdr->cmd;
 
-	mutex_lock(&__ip_vs_mutex);
-
-	if (cmd == IPVS_CMD_FLUSH) {
-		ret = ip_vs_flush(net);
-		goto out;
-	} else if (cmd == IPVS_CMD_SET_CONFIG) {
-		ret = ip_vs_genl_set_config(net, info->attrs);
-		goto out;
-	} else if (cmd == IPVS_CMD_NEW_DAEMON ||
-		   cmd == IPVS_CMD_DEL_DAEMON) {
-
+	if (cmd == IPVS_CMD_NEW_DAEMON || cmd == IPVS_CMD_DEL_DAEMON) {
 		struct nlattr *daemon_attrs[IPVS_DAEMON_ATTR_MAX + 1];
 
+		mutex_lock(&ipvs->sync_mutex);
 		if (!info->attrs[IPVS_CMD_ATTR_DAEMON] ||
 		    nla_parse_nested(daemon_attrs, IPVS_DAEMON_ATTR_MAX,
 				     info->attrs[IPVS_CMD_ATTR_DAEMON],
@@ -3312,6 +3314,31 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
 			ret = ip_vs_genl_new_daemon(net, daemon_attrs);
 		else
 			ret = ip_vs_genl_del_daemon(net, daemon_attrs);
+out:
+		mutex_unlock(&ipvs->sync_mutex);
+	}
+	return ret;
+}
+
+static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
+{
+	struct ip_vs_service *svc = NULL;
+	struct ip_vs_service_user_kern usvc;
+	struct ip_vs_dest_user_kern udest;
+	int ret = 0, cmd;
+	int need_full_svc = 0, need_full_dest = 0;
+	struct net *net;
+
+	net = skb_sknet(skb);
+	cmd = info->genlhdr->cmd;
+
+	mutex_lock(&__ip_vs_mutex);
+
+	if (cmd == IPVS_CMD_FLUSH) {
+		ret = ip_vs_flush(net);
+		goto out;
+	} else if (cmd == IPVS_CMD_SET_CONFIG) {
+		ret = ip_vs_genl_set_config(net, info->attrs);
 		goto out;
 	} else if (cmd == IPVS_CMD_ZERO &&
 		   !info->attrs[IPVS_CMD_ATTR_SERVICE]) {
@@ -3394,10 +3421,8 @@ static int ip_vs_genl_get_cmd(struct sk_buff *skb, struct genl_info *info)
 	void *reply;
 	int ret, cmd, reply_cmd;
 	struct net *net;
-	struct netns_ipvs *ipvs;
 
 	net = skb_sknet(skb);
-	ipvs = net_ipvs(net);
 	cmd = info->genlhdr->cmd;
 
 	if (cmd == IPVS_CMD_GET_SERVICE)
@@ -3538,13 +3563,13 @@ static struct genl_ops ip_vs_genl_ops[] __read_mostly = {
 		.cmd	= IPVS_CMD_NEW_DAEMON,
 		.flags	= GENL_ADMIN_PERM,
 		.policy	= ip_vs_cmd_policy,
-		.doit	= ip_vs_genl_set_cmd,
+		.doit	= ip_vs_genl_set_daemon,
 	},
 	{
 		.cmd	= IPVS_CMD_DEL_DAEMON,
 		.flags	= GENL_ADMIN_PERM,
 		.policy	= ip_vs_cmd_policy,
-		.doit	= ip_vs_genl_set_cmd,
+		.doit	= ip_vs_genl_set_daemon,
 	},
 	{
 		.cmd	= IPVS_CMD_GET_DAEMON,
@@ -3597,7 +3622,7 @@ static void ip_vs_genl_unregister(void)
  * per netns intit/exit func.
  */
 #ifdef CONFIG_SYSCTL
-int __net_init __ip_vs_control_init_sysctl(struct net *net)
+int __net_init ip_vs_control_net_init_sysctl(struct net *net)
 {
 	int idx;
 	struct netns_ipvs *ipvs = net_ipvs(net);
@@ -3656,19 +3681,23 @@ int __net_init __ip_vs_control_init_sysctl(struct net *net)
 	return 0;
 }
 
-void __net_init __ip_vs_control_cleanup_sysctl(struct net *net)
+void __net_init ip_vs_control_net_cleanup_sysctl(struct net *net)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
 	cancel_delayed_work_sync(&ipvs->defense_work);
 	cancel_work_sync(&ipvs->defense_work.work);
 	unregister_net_sysctl_table(ipvs->sysctl_hdr);
+	ip_vs_stop_estimator(net, &ipvs->tot_stats);
+
+	if (!net_eq(net, &init_net))
+		kfree(ipvs->sysctl_tbl);
 }
 
 #else
 
-int __net_init __ip_vs_control_init_sysctl(struct net *net) { return 0; }
-void __net_init __ip_vs_control_cleanup_sysctl(struct net *net) { }
+int __net_init ip_vs_control_net_init_sysctl(struct net *net) { return 0; }
+void __net_init ip_vs_control_net_cleanup_sysctl(struct net *net) { }
 
 #endif
 
@@ -3676,12 +3705,12 @@ static struct notifier_block ip_vs_dst_notifier = {
 	.notifier_call = ip_vs_dst_event,
 };
 
-int __net_init __ip_vs_control_init(struct net *net)
+int __net_init ip_vs_control_net_init(struct net *net)
 {
 	int idx;
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
-	ipvs->rs_lock = __RW_LOCK_UNLOCKED(ipvs->rs_lock);
+	rwlock_init(&ipvs->rs_lock);
 
 	/* Initialize rs_table */
 	for (idx = 0; idx < IP_VS_RTAB_SIZE; idx++)
@@ -3693,10 +3722,9 @@ int __net_init __ip_vs_control_init(struct net *net)
 
 	/* procfs stats */
 	ipvs->tot_stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats);
-	if (!ipvs->tot_stats.cpustats) {
-		pr_err("%s(): alloc_percpu.\n", __func__);
+	if (!ipvs->tot_stats.cpustats)
 		return -ENOMEM;
-	}
+
 	spin_lock_init(&ipvs->tot_stats.lock);
 
 	proc_net_fops_create(net, "ip_vs", 0, &ip_vs_info_fops);
@@ -3704,7 +3732,7 @@ int __net_init __ip_vs_control_init(struct net *net)
 	proc_net_fops_create(net, "ip_vs_stats_percpu", 0,
 			     &ip_vs_stats_percpu_fops);
 
-	if (__ip_vs_control_init_sysctl(net))
+	if (ip_vs_control_net_init_sysctl(net))
 		goto err;
 
 	return 0;
@@ -3714,34 +3742,22 @@ err:
 	return -ENOMEM;
 }
 
-void __net_exit __ip_vs_control_cleanup(struct net *net)
+void __net_exit ip_vs_control_net_cleanup(struct net *net)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
 	ip_vs_trash_cleanup(net);
-	ip_vs_stop_estimator(net, &ipvs->tot_stats);
-	__ip_vs_control_cleanup_sysctl(net);
+	ip_vs_control_net_cleanup_sysctl(net);
 	proc_net_remove(net, "ip_vs_stats_percpu");
 	proc_net_remove(net, "ip_vs_stats");
 	proc_net_remove(net, "ip_vs");
 	free_percpu(ipvs->tot_stats.cpustats);
 }
 
-int __init ip_vs_control_init(void)
+int __init ip_vs_register_nl_ioctl(void)
 {
-	int idx;
 	int ret;
 
-	EnterFunction(2);
-
-	/* Initialize svc_table, ip_vs_svc_fwm_table, rs_table */
-	for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++)  {
-		INIT_LIST_HEAD(&ip_vs_svc_table[idx]);
-		INIT_LIST_HEAD(&ip_vs_svc_fwm_table[idx]);
-	}
-
-	smp_wmb();	/* Do we really need it now ? */
-
 	ret = nf_register_sockopt(&ip_vs_sockopts);
 	if (ret) {
 		pr_err("cannot register sockopt.\n");
@@ -3753,28 +3769,47 @@ int __init ip_vs_control_init(void)
 		pr_err("cannot register Generic Netlink interface.\n");
 		goto err_genl;
 	}
-
-	ret = register_netdevice_notifier(&ip_vs_dst_notifier);
-	if (ret < 0)
-		goto err_notf;
-
-	LeaveFunction(2);
 	return 0;
 
-err_notf:
-	ip_vs_genl_unregister();
 err_genl:
 	nf_unregister_sockopt(&ip_vs_sockopts);
 err_sock:
 	return ret;
 }
 
+void ip_vs_unregister_nl_ioctl(void)
+{
+	ip_vs_genl_unregister();
+	nf_unregister_sockopt(&ip_vs_sockopts);
+}
+
+int __init ip_vs_control_init(void)
+{
+	int idx;
+	int ret;
+
+	EnterFunction(2);
+
+	/* Initialize svc_table, ip_vs_svc_fwm_table, rs_table */
+	for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
+		INIT_LIST_HEAD(&ip_vs_svc_table[idx]);
+		INIT_LIST_HEAD(&ip_vs_svc_fwm_table[idx]);
+	}
+
+	smp_wmb();	/* Do we really need it now ? */
+
+	ret = register_netdevice_notifier(&ip_vs_dst_notifier);
+	if (ret < 0)
+		return ret;
+
+	LeaveFunction(2);
+	return 0;
+}
+
 
 void ip_vs_control_cleanup(void)
 {
 	EnterFunction(2);
 	unregister_netdevice_notifier(&ip_vs_dst_notifier);
-	ip_vs_genl_unregister();
-	nf_unregister_sockopt(&ip_vs_sockopts);
 	LeaveFunction(2);
 }