Merge git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf

Pablo Neira Ayuso says:

====================
Netfilter/IPVS fixes for net

The following patchset contains Netfilter fixes for net:

1) Fix memleak reported by syzkaller when registering IPVS hooks,
   patch from Julian Anastasov.

2) Fix memory leak in start_sync_thread, also from Julian.

3) Fix conntrack deletion via ctnetlink, from Felix Kaechele.

4) Fix reject for ICMP due to incorrect checksum handling, from
   He Zhe.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/ip_vs.h

@@ -808,11 +808,12 @@ struct ipvs_master_sync_state {
 	struct ip_vs_sync_buff	*sync_buff;
 	unsigned long		sync_queue_len;
 	unsigned int		sync_queue_delay;
-	struct task_struct	*master_thread;
 	struct delayed_work	master_wakeup_work;
 	struct netns_ipvs	*ipvs;
 };
 
+struct ip_vs_sync_thread_data;
+
 /* How much time to keep dests in trash */
 #define IP_VS_DEST_TRASH_PERIOD		(120 * HZ)
 
@@ -943,7 +944,8 @@ struct netns_ipvs {
 	spinlock_t		sync_lock;
 	struct ipvs_master_sync_state *ms;
 	spinlock_t		sync_buff_lock;
-	struct task_struct	**backup_threads;
+	struct ip_vs_sync_thread_data *master_tinfo;
+	struct ip_vs_sync_thread_data *backup_tinfo;
 	int			threads_mask;
 	volatile int		sync_state;
 	struct mutex		sync_mutex;

net/netfilter/ipvs/ip_vs_core.c

@@ -2245,7 +2245,6 @@ static const struct nf_hook_ops ip_vs_ops[] = {
 static int __net_init __ip_vs_init(struct net *net)
 {
 	struct netns_ipvs *ipvs;
-	int ret;
 
 	ipvs = net_generic(net, ip_vs_net_id);
 	if (ipvs == NULL)
@@ -2277,17 +2276,11 @@ static int __net_init __ip_vs_init(struct net *net)
 	if (ip_vs_sync_net_init(ipvs) < 0)
 		goto sync_fail;
 
-	ret = nf_register_net_hooks(net, ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
-	if (ret < 0)
-		goto hook_fail;
-
 	return 0;
 /*
  * Error handling
  */
 
-hook_fail:
-	ip_vs_sync_net_cleanup(ipvs);
 sync_fail:
 	ip_vs_conn_net_cleanup(ipvs);
 conn_fail:
@@ -2317,6 +2310,19 @@ static void __net_exit __ip_vs_cleanup(struct net *net)
 	net->ipvs = NULL;
 }
 
+static int __net_init __ip_vs_dev_init(struct net *net)
+{
+	int ret;
+
+	ret = nf_register_net_hooks(net, ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
+	if (ret < 0)
+		goto hook_fail;
+	return 0;
+
+hook_fail:
+	return ret;
+}
+
 static void __net_exit __ip_vs_dev_cleanup(struct net *net)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
@@ -2336,6 +2342,7 @@ static struct pernet_operations ipvs_core_ops = {
 };
 
 static struct pernet_operations ipvs_core_dev_ops = {
+	.init = __ip_vs_dev_init,
 	.exit = __ip_vs_dev_cleanup,
 };
 

net/netfilter/ipvs/ip_vs_ctl.c

@@ -2396,9 +2396,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 			cfg.syncid = dm->syncid;
 			ret = start_sync_thread(ipvs, &cfg, dm->state);
 		} else {
-			mutex_lock(&ipvs->sync_mutex);
 			ret = stop_sync_thread(ipvs, dm->state);
-			mutex_unlock(&ipvs->sync_mutex);
 		}
 		goto out_dec;
 	}
@@ -3515,10 +3513,8 @@ static int ip_vs_genl_del_daemon(struct netns_ipvs *ipvs, struct nlattr **attrs)
 	if (!attrs[IPVS_DAEMON_ATTR_STATE])
 		return -EINVAL;
 
-	mutex_lock(&ipvs->sync_mutex);
 	ret = stop_sync_thread(ipvs,
 			       nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]));
-	mutex_unlock(&ipvs->sync_mutex);
 	return ret;
 }
 

net/netfilter/ipvs/ip_vs_sync.c

@@ -195,6 +195,7 @@ union ip_vs_sync_conn {
 #define IPVS_OPT_F_PARAM	(1 << (IPVS_OPT_PARAM-1))
 
 struct ip_vs_sync_thread_data {
+	struct task_struct *task;
 	struct netns_ipvs *ipvs;
 	struct socket *sock;
 	char *buf;
@@ -374,8 +375,11 @@ static inline void sb_queue_tail(struct netns_ipvs *ipvs,
 					      max(IPVS_SYNC_SEND_DELAY, 1));
 		ms->sync_queue_len++;
 		list_add_tail(&sb->list, &ms->sync_queue);
-		if ((++ms->sync_queue_delay) == IPVS_SYNC_WAKEUP_RATE)
-			wake_up_process(ms->master_thread);
+		if ((++ms->sync_queue_delay) == IPVS_SYNC_WAKEUP_RATE) {
+			int id = (int)(ms - ipvs->ms);
+
+			wake_up_process(ipvs->master_tinfo[id].task);
+		}
 	} else
 		ip_vs_sync_buff_release(sb);
 	spin_unlock(&ipvs->sync_lock);
@@ -1636,8 +1640,10 @@ static void master_wakeup_work_handler(struct work_struct *work)
 	spin_lock_bh(&ipvs->sync_lock);
 	if (ms->sync_queue_len &&
 	    ms->sync_queue_delay < IPVS_SYNC_WAKEUP_RATE) {
+		int id = (int)(ms - ipvs->ms);
+
 		ms->sync_queue_delay = IPVS_SYNC_WAKEUP_RATE;
-		wake_up_process(ms->master_thread);
+		wake_up_process(ipvs->master_tinfo[id].task);
 	}
 	spin_unlock_bh(&ipvs->sync_lock);
 }
@@ -1703,10 +1709,6 @@ static int sync_thread_master(void *data)
 	if (sb)
 		ip_vs_sync_buff_release(sb);
 
-	/* release the sending multicast socket */
-	sock_release(tinfo->sock);
-	kfree(tinfo);
-
 	return 0;
 }
 
@@ -1740,11 +1742,6 @@ static int sync_thread_backup(void *data)
 		}
 	}
 
-	/* release the sending multicast socket */
-	sock_release(tinfo->sock);
-	kfree(tinfo->buf);
-	kfree(tinfo);
-
 	return 0;
 }
 
@@ -1752,8 +1749,8 @@ static int sync_thread_backup(void *data)
 int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
 		      int state)
 {
-	struct ip_vs_sync_thread_data *tinfo = NULL;
-	struct task_struct **array = NULL, *task;
+	struct ip_vs_sync_thread_data *ti = NULL, *tinfo;
+	struct task_struct *task;
 	struct net_device *dev;
 	char *name;
 	int (*threadfn)(void *data);
@@ -1822,7 +1819,7 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
 		threadfn = sync_thread_master;
 	} else if (state == IP_VS_STATE_BACKUP) {
 		result = -EEXIST;
-		if (ipvs->backup_threads)
+		if (ipvs->backup_tinfo)
 			goto out_early;
 
 		ipvs->bcfg = *c;
@@ -1849,28 +1846,22 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
 					  master_wakeup_work_handler);
 			ms->ipvs = ipvs;
 		}
-	} else {
-		array = kcalloc(count, sizeof(struct task_struct *),
-				GFP_KERNEL);
-		result = -ENOMEM;
-		if (!array)
-			goto out;
 	}
+	result = -ENOMEM;
+	ti = kcalloc(count, sizeof(struct ip_vs_sync_thread_data),
+		     GFP_KERNEL);
+	if (!ti)
+		goto out;
 
 	for (id = 0; id < count; id++) {
-		result = -ENOMEM;
-		tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL);
-		if (!tinfo)
-			goto out;
+		tinfo = &ti[id];
 		tinfo->ipvs = ipvs;
-		tinfo->sock = NULL;
 		if (state == IP_VS_STATE_BACKUP) {
+			result = -ENOMEM;
 			tinfo->buf = kmalloc(ipvs->bcfg.sync_maxlen,
 					     GFP_KERNEL);
 			if (!tinfo->buf)
 				goto out;
-		} else {
-			tinfo->buf = NULL;
 		}
 		tinfo->id = id;
 		if (state == IP_VS_STATE_MASTER)
@@ -1885,17 +1876,15 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
 			result = PTR_ERR(task);
 			goto out;
 		}
-		tinfo = NULL;
-		if (state == IP_VS_STATE_MASTER)
-			ipvs->ms[id].master_thread = task;
-		else
-			array[id] = task;
+		tinfo->task = task;
 	}
 
 	/* mark as active */
 
-	if (state == IP_VS_STATE_BACKUP)
-		ipvs->backup_threads = array;
+	if (state == IP_VS_STATE_MASTER)
+		ipvs->master_tinfo = ti;
+	else
+		ipvs->backup_tinfo = ti;
 	spin_lock_bh(&ipvs->sync_buff_lock);
 	ipvs->sync_state |= state;
 	spin_unlock_bh(&ipvs->sync_buff_lock);
@@ -1910,29 +1899,31 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
 
 out:
 	/* We do not need RTNL lock anymore, release it here so that
-	 * sock_release below and in the kthreads can use rtnl_lock
-	 * to leave the mcast group.
+	 * sock_release below can use rtnl_lock to leave the mcast group.
 	 */
 	rtnl_unlock();
-	count = id;
-	while (count-- > 0) {
-		if (state == IP_VS_STATE_MASTER)
-			kthread_stop(ipvs->ms[count].master_thread);
-		else
-			kthread_stop(array[count]);
+	id = min(id, count - 1);
+	if (ti) {
+		for (tinfo = ti + id; tinfo >= ti; tinfo--) {
+			if (tinfo->task)
+				kthread_stop(tinfo->task);
+		}
 	}
 	if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) {
 		kfree(ipvs->ms);
 		ipvs->ms = NULL;
 	}
 	mutex_unlock(&ipvs->sync_mutex);
-	if (tinfo) {
-		if (tinfo->sock)
-			sock_release(tinfo->sock);
-		kfree(tinfo->buf);
-		kfree(tinfo);
+
+	/* No more mutexes, release socks */
+	if (ti) {
+		for (tinfo = ti + id; tinfo >= ti; tinfo--) {
+			if (tinfo->sock)
+				sock_release(tinfo->sock);
+			kfree(tinfo->buf);
+		}
+		kfree(ti);
 	}
-	kfree(array);
 	return result;
 
 out_early:
@@ -1944,15 +1935,18 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
 
 int stop_sync_thread(struct netns_ipvs *ipvs, int state)
 {
-	struct task_struct **array;
+	struct ip_vs_sync_thread_data *ti, *tinfo;
 	int id;
 	int retc = -EINVAL;
 
 	IP_VS_DBG(7, "%s(): pid %d\n", __func__, task_pid_nr(current));
 
+	mutex_lock(&ipvs->sync_mutex);
 	if (state == IP_VS_STATE_MASTER) {
+		retc = -ESRCH;
 		if (!ipvs->ms)
-			return -ESRCH;
+			goto err;
+		ti = ipvs->master_tinfo;
 
 		/*
 		 * The lock synchronizes with sb_queue_tail(), so that we don't
@@ -1971,38 +1965,56 @@ int stop_sync_thread(struct netns_ipvs *ipvs, int state)
 			struct ipvs_master_sync_state *ms = &ipvs->ms[id];
 			int ret;
 
+			tinfo = &ti[id];
 			pr_info("stopping master sync thread %d ...\n",
-				task_pid_nr(ms->master_thread));
+				task_pid_nr(tinfo->task));
 			cancel_delayed_work_sync(&ms->master_wakeup_work);
-			ret = kthread_stop(ms->master_thread);
+			ret = kthread_stop(tinfo->task);
 			if (retc >= 0)
 				retc = ret;
 		}
 		kfree(ipvs->ms);
 		ipvs->ms = NULL;
+		ipvs->master_tinfo = NULL;
 	} else if (state == IP_VS_STATE_BACKUP) {
-		if (!ipvs->backup_threads)
-			return -ESRCH;
+		retc = -ESRCH;
+		if (!ipvs->backup_tinfo)
+			goto err;
+		ti = ipvs->backup_tinfo;
 
 		ipvs->sync_state &= ~IP_VS_STATE_BACKUP;
-		array = ipvs->backup_threads;
 		retc = 0;
 		for (id = ipvs->threads_mask; id >= 0; id--) {
 			int ret;
 
+			tinfo = &ti[id];
 			pr_info("stopping backup sync thread %d ...\n",
-				task_pid_nr(array[id]));
-			ret = kthread_stop(array[id]);
+				task_pid_nr(tinfo->task));
+			ret = kthread_stop(tinfo->task);
 			if (retc >= 0)
 				retc = ret;
 		}
-		kfree(array);
-		ipvs->backup_threads = NULL;
+		ipvs->backup_tinfo = NULL;
+	} else {
+		goto err;
 	}
+	id = ipvs->threads_mask;
+	mutex_unlock(&ipvs->sync_mutex);
+
+	/* No more mutexes, release socks */
+	for (tinfo = ti + id; tinfo >= ti; tinfo--) {
+		if (tinfo->sock)
+			sock_release(tinfo->sock);
+		kfree(tinfo->buf);
+	}
+	kfree(ti);
 
 	/* decrease the module use count */
 	ip_vs_use_count_dec();
+	return retc;
 
+err:
+	mutex_unlock(&ipvs->sync_mutex);
 	return retc;
 }
 
@@ -2021,7 +2033,6 @@ void ip_vs_sync_net_cleanup(struct netns_ipvs *ipvs)
 {
 	int retc;
 
-	mutex_lock(&ipvs->sync_mutex);
 	retc = stop_sync_thread(ipvs, IP_VS_STATE_MASTER);
 	if (retc && retc != -ESRCH)
 		pr_err("Failed to stop Master Daemon\n");
@@ -2029,5 +2040,4 @@ void ip_vs_sync_net_cleanup(struct netns_ipvs *ipvs)
 	retc = stop_sync_thread(ipvs, IP_VS_STATE_BACKUP);
 	if (retc && retc != -ESRCH)
 		pr_err("Failed to stop Backup Daemon\n");
-	mutex_unlock(&ipvs->sync_mutex);
 }

net/netfilter/nf_conntrack_netlink.c

@@ -1256,7 +1256,6 @@ static int ctnetlink_del_conntrack(struct net *net, struct sock *ctnl,
 	struct nf_conntrack_tuple tuple;
 	struct nf_conn *ct;
 	struct nfgenmsg *nfmsg = nlmsg_data(nlh);
-	u_int8_t u3 = nfmsg->version ? nfmsg->nfgen_family : AF_UNSPEC;
 	struct nf_conntrack_zone zone;
 	int err;
 
@@ -1266,11 +1265,13 @@ static int ctnetlink_del_conntrack(struct net *net, struct sock *ctnl,
 
 	if (cda[CTA_TUPLE_ORIG])
 		err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG,
-					    u3, &zone);
+					    nfmsg->nfgen_family, &zone);
 	else if (cda[CTA_TUPLE_REPLY])
 		err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY,
-					    u3, &zone);
+					    nfmsg->nfgen_family, &zone);
 	else {
+		u_int8_t u3 = nfmsg->version ? nfmsg->nfgen_family : AF_UNSPEC;
+
 		return ctnetlink_flush_conntrack(net, cda,
 						 NETLINK_CB(skb).portid,
 						 nlmsg_report(nlh), u3);

net/netfilter/nf_conntrack_proto_icmp.c

@@ -218,7 +218,7 @@ int nf_conntrack_icmpv4_error(struct nf_conn *tmpl,
 	/* See ip_conntrack_proto_tcp.c */
 	if (state->net->ct.sysctl_checksum &&
 	    state->hook == NF_INET_PRE_ROUTING &&
-	    nf_ip_checksum(skb, state->hook, dataoff, 0)) {
+	    nf_ip_checksum(skb, state->hook, dataoff, IPPROTO_ICMP)) {
 		icmp_error_log(skb, state, "bad hw icmp checksum");
 		return -NF_ACCEPT;
 	}

net/netfilter/nf_nat_proto.c

@@ -564,7 +564,7 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb,
 
 	if (!skb_make_writable(skb, hdrlen + sizeof(*inside)))
 		return 0;
-	if (nf_ip_checksum(skb, hooknum, hdrlen, 0))
+	if (nf_ip_checksum(skb, hooknum, hdrlen, IPPROTO_ICMP))
 		return 0;
 
 	inside = (void *)skb->data + hdrlen;

net/netfilter/utils.c

@@ -17,7 +17,8 @@ __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook,
 	case CHECKSUM_COMPLETE:
 		if (hook != NF_INET_PRE_ROUTING && hook != NF_INET_LOCAL_IN)
 			break;
-		if ((protocol == 0 && !csum_fold(skb->csum)) ||
+		if ((protocol != IPPROTO_TCP && protocol != IPPROTO_UDP &&
+		    !csum_fold(skb->csum)) ||
 		    !csum_tcpudp_magic(iph->saddr, iph->daddr,
 				       skb->len - dataoff, protocol,
 				       skb->csum)) {
@@ -26,7 +27,7 @@ __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook,
 		}
 		/* fall through */
 	case CHECKSUM_NONE:
-		if (protocol == 0)
+		if (protocol != IPPROTO_TCP && protocol != IPPROTO_UDP)
 			skb->csum = 0;
 		else
 			skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr,