Merge branch 'master' of git://1984.lsi.us.es/net

include/net/netfilter/nf_conntrack_l4proto.h

@@ -118,6 +118,10 @@ extern struct nf_conntrack_l4proto nf_conntrack_l4proto_generic;
 extern struct nf_conntrack_l4proto *
 __nf_ct_l4proto_find(u_int16_t l3proto, u_int8_t l4proto);
 
+extern struct nf_conntrack_l4proto *
+nf_ct_l4proto_find_get(u_int16_t l3proto, u_int8_t l4proto);
+extern void nf_ct_l4proto_put(struct nf_conntrack_l4proto *p);
+
 /* Protocol registration. */
 extern int nf_conntrack_l4proto_register(struct nf_conntrack_l4proto *proto);
 extern void nf_conntrack_l4proto_unregister(struct nf_conntrack_l4proto *proto);

include/net/netfilter/nf_conntrack_timeout.h

@@ -15,7 +15,7 @@ struct ctnl_timeout {
 	atomic_t		refcnt;
 	char			name[CTNL_TIMEOUT_NAME_MAX];
 	__u16			l3num;
-	__u8			l4num;
+	struct nf_conntrack_l4proto *l4proto;
 	char			data[0];
 };
 

net/netfilter/nf_conntrack_core.c

@@ -768,8 +768,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 	       struct nf_conntrack_l3proto *l3proto,
 	       struct nf_conntrack_l4proto *l4proto,
 	       struct sk_buff *skb,
-	       unsigned int dataoff, u32 hash,
-	       unsigned int *timeouts)
+	       unsigned int dataoff, u32 hash)
 {
 	struct nf_conn *ct;
 	struct nf_conn_help *help;
@@ -777,6 +776,8 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 	struct nf_conntrack_ecache *ecache;
 	struct nf_conntrack_expect *exp;
 	u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE;
+	struct nf_conn_timeout *timeout_ext;
+	unsigned int *timeouts;
 
 	if (!nf_ct_invert_tuple(&repl_tuple, tuple, l3proto, l4proto)) {
 		pr_debug("Can't invert tuple.\n");
@@ -788,12 +789,21 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 	if (IS_ERR(ct))
 		return (struct nf_conntrack_tuple_hash *)ct;
 
+	timeout_ext = tmpl ? nf_ct_timeout_find(tmpl) : NULL;
+	if (timeout_ext)
+		timeouts = NF_CT_TIMEOUT_EXT_DATA(timeout_ext);
+	else
+		timeouts = l4proto->get_timeouts(net);
+
 	if (!l4proto->new(ct, skb, dataoff, timeouts)) {
 		nf_conntrack_free(ct);
 		pr_debug("init conntrack: can't track with proto module\n");
 		return NULL;
 	}
 
+	if (timeout_ext)
+		nf_ct_timeout_ext_add(ct, timeout_ext->timeout, GFP_ATOMIC);
+
 	nf_ct_acct_ext_add(ct, GFP_ATOMIC);
 	nf_ct_tstamp_ext_add(ct, GFP_ATOMIC);
 
@@ -854,8 +864,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
 		  struct nf_conntrack_l3proto *l3proto,
 		  struct nf_conntrack_l4proto *l4proto,
 		  int *set_reply,
-		  enum ip_conntrack_info *ctinfo,
-		  unsigned int *timeouts)
+		  enum ip_conntrack_info *ctinfo)
 {
 	struct nf_conntrack_tuple tuple;
 	struct nf_conntrack_tuple_hash *h;
@@ -875,7 +884,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
 	h = __nf_conntrack_find_get(net, zone, &tuple, hash);
 	if (!h) {
 		h = init_conntrack(net, tmpl, &tuple, l3proto, l4proto,
-				   skb, dataoff, hash, timeouts);
+				   skb, dataoff, hash);
 		if (!h)
 			return NULL;
 		if (IS_ERR(h))
@@ -964,19 +973,8 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
 			goto out;
 	}
 
-	/* Decide what timeout policy we want to apply to this flow. */
-	if (tmpl) {
-	        timeout_ext = nf_ct_timeout_find(tmpl);
-		if (timeout_ext)
-			timeouts = NF_CT_TIMEOUT_EXT_DATA(timeout_ext);
-		else
-			timeouts = l4proto->get_timeouts(net);
-	} else
-		timeouts = l4proto->get_timeouts(net);
-
 	ct = resolve_normal_ct(net, tmpl, skb, dataoff, pf, protonum,
-			       l3proto, l4proto, &set_reply, &ctinfo,
-			       timeouts);
+			       l3proto, l4proto, &set_reply, &ctinfo);
 	if (!ct) {
 		/* Not valid part of a connection */
 		NF_CT_STAT_INC_ATOMIC(net, invalid);
@@ -993,6 +991,13 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
 
 	NF_CT_ASSERT(skb->nfct);
 
+	/* Decide what timeout policy we want to apply to this flow. */
+	timeout_ext = nf_ct_timeout_find(ct);
+	if (timeout_ext)
+		timeouts = NF_CT_TIMEOUT_EXT_DATA(timeout_ext);
+	else
+		timeouts = l4proto->get_timeouts(net);
+
 	ret = l4proto->packet(ct, skb, dataoff, ctinfo, pf, hooknum, timeouts);
 	if (ret <= 0) {
 		/* Invalid: inverse of the return code tells

net/netfilter/nf_conntrack_proto.c

@@ -127,6 +127,27 @@ void nf_ct_l3proto_module_put(unsigned short l3proto)
 }
 EXPORT_SYMBOL_GPL(nf_ct_l3proto_module_put);
 
+struct nf_conntrack_l4proto *
+nf_ct_l4proto_find_get(u_int16_t l3num, u_int8_t l4num)
+{
+	struct nf_conntrack_l4proto *p;
+
+	rcu_read_lock();
+	p = __nf_ct_l4proto_find(l3num, l4num);
+	if (!try_module_get(p->me))
+		p = &nf_conntrack_l4proto_generic;
+	rcu_read_unlock();
+
+	return p;
+}
+EXPORT_SYMBOL_GPL(nf_ct_l4proto_find_get);
+
+void nf_ct_l4proto_put(struct nf_conntrack_l4proto *p)
+{
+	module_put(p->me);
+}
+EXPORT_SYMBOL_GPL(nf_ct_l4proto_put);
+
 static int kill_l3proto(struct nf_conn *i, void *data)
 {
 	return nf_ct_l3num(i) == ((struct nf_conntrack_l3proto *)data)->l3proto;

net/netfilter/nfnetlink_cttimeout.c

@@ -98,11 +98,13 @@ cttimeout_new_timeout(struct sock *ctnl, struct sk_buff *skb,
 		break;
 	}
 
-	l4proto = __nf_ct_l4proto_find(l3num, l4num);
+	l4proto = nf_ct_l4proto_find_get(l3num, l4num);
 
 	/* This protocol is not supportted, skip. */
-	if (l4proto->l4proto != l4num)
-		return -EOPNOTSUPP;
+	if (l4proto->l4proto != l4num) {
+		ret = -EOPNOTSUPP;
+		goto err_proto_put;
+	}
 
 	if (matching) {
 		if (nlh->nlmsg_flags & NLM_F_REPLACE) {
@@ -110,20 +112,25 @@ cttimeout_new_timeout(struct sock *ctnl, struct sk_buff *skb,
 			 * different kind, sorry.
 			 */
 			if (matching->l3num != l3num ||
-			    matching->l4num != l4num)
-				return -EINVAL;
+			    matching->l4proto->l4proto != l4num) {
+				ret = -EINVAL;
+				goto err_proto_put;
+			}
 
 			ret = ctnl_timeout_parse_policy(matching, l4proto,
 							cda[CTA_TIMEOUT_DATA]);
 			return ret;
 		}
-		return -EBUSY;
+		ret = -EBUSY;
+		goto err_proto_put;
 	}
 
 	timeout = kzalloc(sizeof(struct ctnl_timeout) +
 			  l4proto->ctnl_timeout.obj_size, GFP_KERNEL);
-	if (timeout == NULL)
-		return -ENOMEM;
+	if (timeout == NULL) {
+		ret = -ENOMEM;
+		goto err_proto_put;
+	}
 
 	ret = ctnl_timeout_parse_policy(timeout, l4proto,
 					cda[CTA_TIMEOUT_DATA]);
@@ -132,13 +139,15 @@ cttimeout_new_timeout(struct sock *ctnl, struct sk_buff *skb,
 
 	strcpy(timeout->name, nla_data(cda[CTA_TIMEOUT_NAME]));
 	timeout->l3num = l3num;
-	timeout->l4num = l4num;
+	timeout->l4proto = l4proto;
 	atomic_set(&timeout->refcnt, 1);
 	list_add_tail_rcu(&timeout->head, &cttimeout_list);
 
 	return 0;
 err:
 	kfree(timeout);
+err_proto_put:
+	nf_ct_l4proto_put(l4proto);
 	return ret;
 }
 
@@ -149,7 +158,7 @@ ctnl_timeout_fill_info(struct sk_buff *skb, u32 pid, u32 seq, u32 type,
 	struct nlmsghdr *nlh;
 	struct nfgenmsg *nfmsg;
 	unsigned int flags = pid ? NLM_F_MULTI : 0;
-	struct nf_conntrack_l4proto *l4proto;
+	struct nf_conntrack_l4proto *l4proto = timeout->l4proto;
 
 	event |= NFNL_SUBSYS_CTNETLINK_TIMEOUT << 8;
 	nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags);
@@ -163,20 +172,10 @@ ctnl_timeout_fill_info(struct sk_buff *skb, u32 pid, u32 seq, u32 type,
 
 	NLA_PUT_STRING(skb, CTA_TIMEOUT_NAME, timeout->name);
 	NLA_PUT_BE16(skb, CTA_TIMEOUT_L3PROTO, htons(timeout->l3num));
-	NLA_PUT_U8(skb, CTA_TIMEOUT_L4PROTO, timeout->l4num);
+	NLA_PUT_U8(skb, CTA_TIMEOUT_L4PROTO, timeout->l4proto->l4proto);
 	NLA_PUT_BE32(skb, CTA_TIMEOUT_USE,
 			htonl(atomic_read(&timeout->refcnt)));
 
-	l4proto = __nf_ct_l4proto_find(timeout->l3num, timeout->l4num);
-
-	/* If the timeout object does not match the layer 4 protocol tracker,
-	 * then skip dumping the data part since we don't know how to
-	 * interpret it. This may happen for UPDlite, SCTP and DCCP since
-	 * you can unload the module.
-	 */
-	if (timeout->l4num != l4proto->l4proto)
-		goto out;
-
 	if (likely(l4proto->ctnl_timeout.obj_to_nlattr)) {
 		struct nlattr *nest_parms;
 		int ret;
@@ -192,7 +191,7 @@ ctnl_timeout_fill_info(struct sk_buff *skb, u32 pid, u32 seq, u32 type,
 
 		nla_nest_end(skb, nest_parms);
 	}
-out:
+
 	nlmsg_end(skb, nlh);
 	return skb->len;
 
@@ -293,6 +292,7 @@ static int ctnl_timeout_try_del(struct ctnl_timeout *timeout)
 	if (atomic_dec_and_test(&timeout->refcnt)) {
 		/* We are protected by nfnl mutex. */
 		list_del_rcu(&timeout->head);
+		nf_ct_l4proto_put(timeout->l4proto);
 		kfree_rcu(timeout, rcu_head);
 	} else {
 		/* still in use, restore reference counter. */
@@ -417,6 +417,7 @@ static void __exit cttimeout_exit(void)
 		/* We are sure that our objects have no clients at this point,
 		 * it's safe to release them all without checking refcnt.
 		 */
+		nf_ct_l4proto_put(cur->l4proto);
 		kfree_rcu(cur, rcu_head);
 	}
 #ifdef CONFIG_NF_CONNTRACK_TIMEOUT

net/netfilter/xt_CT.c

@@ -14,8 +14,10 @@
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter/xt_CT.h>
 #include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_ecache.h>
+#include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_timeout.h>
 #include <net/netfilter/nf_conntrack_zones.h>
 
@@ -217,50 +219,59 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par)
 		struct ctnl_timeout *timeout;
 		struct nf_conn_timeout *timeout_ext;
 
+		rcu_read_lock();
 		timeout_find_get =
 			rcu_dereference(nf_ct_timeout_find_get_hook);
 
 		if (timeout_find_get) {
 			const struct ipt_entry *e = par->entryinfo;
+			struct nf_conntrack_l4proto *l4proto;
 
 			if (e->ip.invflags & IPT_INV_PROTO) {
 				ret = -EINVAL;
 				pr_info("You cannot use inversion on "
 					 "L4 protocol\n");
-				goto err3;
+				goto err4;
 			}
 			timeout = timeout_find_get(info->timeout);
 			if (timeout == NULL) {
 				ret = -ENOENT;
 				pr_info("No such timeout policy \"%s\"\n",
 					info->timeout);
-				goto err3;
+				goto err4;
 			}
 			if (timeout->l3num != par->family) {
 				ret = -EINVAL;
 				pr_info("Timeout policy `%s' can only be "
 					"used by L3 protocol number %d\n",
 					info->timeout, timeout->l3num);
-				goto err3;
+				goto err4;
 			}
-			if (timeout->l4num != e->ip.proto) {
+			/* Make sure the timeout policy matches any existing
+			 * protocol tracker, otherwise default to generic.
+			 */
+			l4proto = __nf_ct_l4proto_find(par->family,
+						       e->ip.proto);
+			if (timeout->l4proto->l4proto != l4proto->l4proto) {
 				ret = -EINVAL;
 				pr_info("Timeout policy `%s' can only be "
 					"used by L4 protocol number %d\n",
-					info->timeout, timeout->l4num);
-				goto err3;
+					info->timeout,
+					timeout->l4proto->l4proto);
+				goto err4;
 			}
 			timeout_ext = nf_ct_timeout_ext_add(ct, timeout,
 							    GFP_KERNEL);
 			if (timeout_ext == NULL) {
 				ret = -ENOMEM;
-				goto err3;
+				goto err4;
 			}
 		} else {
 			ret = -ENOENT;
 			pr_info("Timeout policy base is empty\n");
-			goto err3;
+			goto err4;
 		}
+		rcu_read_unlock();
 	}
 #endif
 
@@ -270,6 +281,8 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par)
 	info->ct = ct;
 	return 0;
 
+err4:
+	rcu_read_unlock();
 err3:
 	nf_conntrack_free(ct);
 err2:
@@ -311,6 +324,7 @@ static void xt_ct_tg_destroy_v1(const struct xt_tgdtor_param *par)
 		nf_ct_l3proto_module_put(par->family);
 
 #ifdef CONFIG_NF_CONNTRACK_TIMEOUT
+		rcu_read_lock();
 		timeout_put = rcu_dereference(nf_ct_timeout_put_hook);
 
 		if (timeout_put) {
@@ -318,6 +332,7 @@ static void xt_ct_tg_destroy_v1(const struct xt_tgdtor_param *par)
 			if (timeout_ext)
 				timeout_put(timeout_ext->timeout);
 		}
+		rcu_read_unlock();
 #endif
 	}
 	nf_ct_put(info->ct);

net/netfilter/xt_LOG.c

@@ -480,7 +480,7 @@ ipt_log_packet(u_int8_t pf,
 	sb_close(m);
 }
 
-#if IS_ENABLED(CONFIG_IPV6)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 /* One level of recursion won't kill us */
 static void dump_ipv6_packet(struct sbuff *m,
 			const struct nf_loginfo *info,
@@ -824,7 +824,7 @@ log_tg(struct sk_buff *skb, const struct xt_action_param *par)
 	if (par->family == NFPROTO_IPV4)
 		ipt_log_packet(NFPROTO_IPV4, par->hooknum, skb, par->in,
 			       par->out, &li, loginfo->prefix);
-#if IS_ENABLED(CONFIG_IPV6)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 	else if (par->family == NFPROTO_IPV6)
 		ip6t_log_packet(NFPROTO_IPV6, par->hooknum, skb, par->in,
 				par->out, &li, loginfo->prefix);
@@ -864,7 +864,7 @@ static struct xt_target log_tg_regs[] __read_mostly = {
 		.checkentry	= log_tg_check,
 		.me		= THIS_MODULE,
 	},
-#if IS_ENABLED(CONFIG_IPV6)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 	{
 		.name		= "LOG",
 		.family		= NFPROTO_IPV6,
@@ -882,7 +882,7 @@ static struct nf_logger ipt_log_logger __read_mostly = {
 	.me		= THIS_MODULE,
 };
 
-#if IS_ENABLED(CONFIG_IPV6)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 static struct nf_logger ip6t_log_logger __read_mostly = {
 	.name		= "ip6t_LOG",
 	.logfn		= &ip6t_log_packet,
@@ -899,7 +899,7 @@ static int __init log_tg_init(void)
 		return ret;
 
 	nf_log_register(NFPROTO_IPV4, &ipt_log_logger);
-#if IS_ENABLED(CONFIG_IPV6)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 	nf_log_register(NFPROTO_IPV6, &ip6t_log_logger);
 #endif
 	return 0;
@@ -908,7 +908,7 @@ static int __init log_tg_init(void)
 static void __exit log_tg_exit(void)
 {
 	nf_log_unregister(&ipt_log_logger);
-#if IS_ENABLED(CONFIG_IPV6)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 	nf_log_unregister(&ip6t_log_logger);
 #endif
 	xt_unregister_targets(log_tg_regs, ARRAY_SIZE(log_tg_regs));