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/IPVS fixes for your net tree:

1) Reject non-null terminated helper names from xt_CT, from Gao Feng.

2) Fix KASAN splat due to out-of-bound access from commit phase, from
   Alexey Kodanev.

3) Missing conntrack hook registration on IPVS FTP helper, from Julian
   Anastasov.

4) Incorrect skbuff allocation size in bridge nft_reject, from Taehee Yoo.

5) Fix inverted check on packet xmit to non-local addresses, also from
   Julian.

6) Fix ebtables alignment compat problems, from Alin Nastac.

7) Hook mask checks are not correct in xt_set, from Serhey Popovych.

8) Fix timeout listing of element in ipsets, from Jozsef.

9) Cap maximum timeout value in ipset, also from Jozsef.

10) Don't allow family option for hash:mac sets, from Florent Fourcot.

11) Restrict ebtables to work with NFPROTO_BRIDGE targets only, this
    Florian.

12) Another bug reported by KASAN in the rbtree set backend, from
    Taehee Yoo.

13) Missing __IPS_MAX_BIT update doesn't include IPS_OFFLOAD_BIT.
    From Gao Feng.

14) Missing initialization of match/target in ebtables, from Florian
    Westphal.

15) Remove useless nft_dup.h file in include path, from C. Labbe.
====================

Signed-off-by: David S. Miller <[email protected]>

include/linux/netfilter/ipset/ip_set_timeout.h

@@ -23,6 +23,9 @@
 /* Set is defined with timeout support: timeout value may be 0 */
 #define IPSET_NO_TIMEOUT	UINT_MAX
 
+/* Max timeout value, see msecs_to_jiffies() in jiffies.h */
+#define IPSET_MAX_TIMEOUT	(UINT_MAX >> 1)/MSEC_PER_SEC
+
 #define ip_set_adt_opt_timeout(opt, set)	\
 ((opt)->ext.timeout != IPSET_NO_TIMEOUT ? (opt)->ext.timeout : (set)->timeout)
 
@@ -32,11 +35,10 @@ ip_set_timeout_uget(struct nlattr *tb)
 	unsigned int timeout = ip_set_get_h32(tb);
 
 	/* Normalize to fit into jiffies */
-	if (timeout > UINT_MAX/MSEC_PER_SEC)
-		timeout = UINT_MAX/MSEC_PER_SEC;
+	if (timeout > IPSET_MAX_TIMEOUT)
+		timeout = IPSET_MAX_TIMEOUT;
 
-	/* Userspace supplied TIMEOUT parameter: adjust crazy size */
-	return timeout == IPSET_NO_TIMEOUT ? IPSET_NO_TIMEOUT - 1 : timeout;
+	return timeout;
 }
 
 static inline bool
@@ -65,8 +67,14 @@ ip_set_timeout_set(unsigned long *timeout, u32 value)
 static inline u32
 ip_set_timeout_get(const unsigned long *timeout)
 {
-	return *timeout == IPSET_ELEM_PERMANENT ? 0 :
-		jiffies_to_msecs(*timeout - jiffies)/MSEC_PER_SEC;
+	u32 t;
+
+	if (*timeout == IPSET_ELEM_PERMANENT)
+		return 0;
+
+	t = jiffies_to_msecs(*timeout - jiffies)/MSEC_PER_SEC;
+	/* Zero value in userspace means no timeout */
+	return t == 0 ? 1 : t;
 }
 
 #endif	/* __KERNEL__ */

include/net/ip_vs.h

@@ -631,6 +631,7 @@ struct ip_vs_service {
 
 	/* alternate persistence engine */
 	struct ip_vs_pe __rcu	*pe;
+	int			conntrack_afmask;
 
 	struct rcu_head		rcu_head;
 };
@@ -1611,6 +1612,35 @@ static inline bool ip_vs_conn_uses_conntrack(struct ip_vs_conn *cp,
 	return false;
 }
 
+static inline int ip_vs_register_conntrack(struct ip_vs_service *svc)
+{
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+	int afmask = (svc->af == AF_INET6) ? 2 : 1;
+	int ret = 0;
+
+	if (!(svc->conntrack_afmask & afmask)) {
+		ret = nf_ct_netns_get(svc->ipvs->net, svc->af);
+		if (ret >= 0)
+			svc->conntrack_afmask |= afmask;
+	}
+	return ret;
+#else
+	return 0;
+#endif
+}
+
+static inline void ip_vs_unregister_conntrack(struct ip_vs_service *svc)
+{
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+	int afmask = (svc->af == AF_INET6) ? 2 : 1;
+
+	if (svc->conntrack_afmask & afmask) {
+		nf_ct_netns_put(svc->ipvs->net, svc->af);
+		svc->conntrack_afmask &= ~afmask;
+	}
+#endif
+}
+
 static inline int
 ip_vs_dest_conn_overhead(struct ip_vs_dest *dest)
 {

include/uapi/linux/netfilter/nf_conntrack_common.h

@@ -112,7 +112,7 @@ enum ip_conntrack_status {
 				 IPS_EXPECTED | IPS_CONFIRMED | IPS_DYING |
 				 IPS_SEQ_ADJUST | IPS_TEMPLATE | IPS_OFFLOAD),
 
-	__IPS_MAX_BIT = 14,
+	__IPS_MAX_BIT = 15,
 };
 
 /* Connection tracking event types */

net/bridge/netfilter/ebtables.c

@@ -411,6 +411,12 @@ ebt_check_watcher(struct ebt_entry_watcher *w, struct xt_tgchk_param *par,
 	watcher = xt_request_find_target(NFPROTO_BRIDGE, w->u.name, 0);
 	if (IS_ERR(watcher))
 		return PTR_ERR(watcher);
+
+	if (watcher->family != NFPROTO_BRIDGE) {
+		module_put(watcher->me);
+		return -ENOENT;
+	}
+
 	w->u.watcher = watcher;
 
 	par->target   = watcher;
@@ -709,6 +715,8 @@ ebt_check_entry(struct ebt_entry *e, struct net *net,
 	}
 	i = 0;
 
+	memset(&mtpar, 0, sizeof(mtpar));
+	memset(&tgpar, 0, sizeof(tgpar));
 	mtpar.net	= tgpar.net       = net;
 	mtpar.table     = tgpar.table     = name;
 	mtpar.entryinfo = tgpar.entryinfo = e;
@@ -730,6 +738,13 @@ ebt_check_entry(struct ebt_entry *e, struct net *net,
 		goto cleanup_watchers;
 	}
 
+	/* Reject UNSPEC, xtables verdicts/return values are incompatible */
+	if (target->family != NFPROTO_BRIDGE) {
+		module_put(target->me);
+		ret = -ENOENT;
+		goto cleanup_watchers;
+	}
+
 	t->u.target = target;
 	if (t->u.target == &ebt_standard_target) {
 		if (gap < sizeof(struct ebt_standard_target)) {
@@ -1605,16 +1620,16 @@ struct compat_ebt_entry_mwt {
 		compat_uptr_t ptr;
 	} u;
 	compat_uint_t match_size;
-	compat_uint_t data[0];
+	compat_uint_t data[0] __attribute__ ((aligned (__alignof__(struct compat_ebt_replace))));
 };
 
 /* account for possible padding between match_size and ->data */
 static int ebt_compat_entry_padsize(void)
 {
-	BUILD_BUG_ON(XT_ALIGN(sizeof(struct ebt_entry_match)) <
-			COMPAT_XT_ALIGN(sizeof(struct compat_ebt_entry_mwt)));
-	return (int) XT_ALIGN(sizeof(struct ebt_entry_match)) -
-			COMPAT_XT_ALIGN(sizeof(struct compat_ebt_entry_mwt));
+	BUILD_BUG_ON(sizeof(struct ebt_entry_match) <
+			sizeof(struct compat_ebt_entry_mwt));
+	return (int) sizeof(struct ebt_entry_match) -
+			sizeof(struct compat_ebt_entry_mwt);
 }
 
 static int ebt_compat_match_offset(const struct xt_match *match,

net/bridge/netfilter/nft_reject_bridge.c

@@ -261,7 +261,7 @@ static void nft_reject_br_send_v6_unreach(struct net *net,
 	if (!reject6_br_csum_ok(oldskb, hook))
 		return;
 
-	nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct icmp6hdr) +
+	nskb = alloc_skb(sizeof(struct ipv6hdr) + sizeof(struct icmp6hdr) +
 			 LL_MAX_HEADER + len, GFP_ATOMIC);
 	if (!nskb)
 		return;

net/ipv4/netfilter/ip_tables.c

@@ -531,6 +531,7 @@ find_check_entry(struct ipt_entry *e, struct net *net, const char *name,
 		return -ENOMEM;
 
 	j = 0;
+	memset(&mtpar, 0, sizeof(mtpar));
 	mtpar.net	= net;
 	mtpar.table     = name;
 	mtpar.entryinfo = &e->ip;

net/ipv6/netfilter/ip6_tables.c

@@ -550,6 +550,7 @@ find_check_entry(struct ip6t_entry *e, struct net *net, const char *name,
 		return -ENOMEM;
 
 	j = 0;
+	memset(&mtpar, 0, sizeof(mtpar));
 	mtpar.net	= net;
 	mtpar.table     = name;
 	mtpar.entryinfo = &e->ipv6;

net/netfilter/ipset/ip_set_hash_gen.h

@@ -1234,7 +1234,10 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set,
 	pr_debug("Create set %s with family %s\n",
 		 set->name, set->family == NFPROTO_IPV4 ? "inet" : "inet6");
 
-#ifndef IP_SET_PROTO_UNDEF
+#ifdef IP_SET_PROTO_UNDEF
+	if (set->family != NFPROTO_UNSPEC)
+		return -IPSET_ERR_INVALID_FAMILY;
+#else
 	if (!(set->family == NFPROTO_IPV4 || set->family == NFPROTO_IPV6))
 		return -IPSET_ERR_INVALID_FAMILY;
 #endif

net/netfilter/ipvs/ip_vs_ctl.c

@@ -839,6 +839,9 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
 		 *    For now only for NAT!
 		 */
 		ip_vs_rs_hash(ipvs, dest);
+		/* FTP-NAT requires conntrack for mangling */
+		if (svc->port == FTPPORT)
+			ip_vs_register_conntrack(svc);
 	}
 	atomic_set(&dest->conn_flags, conn_flags);
 
@@ -1462,6 +1465,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup)
  */
 static void ip_vs_unlink_service(struct ip_vs_service *svc, bool cleanup)
 {
+	ip_vs_unregister_conntrack(svc);
 	/* Hold svc to avoid double release from dest_trash */
 	atomic_inc(&svc->refcnt);
 	/*

net/netfilter/ipvs/ip_vs_xmit.c

@@ -168,7 +168,7 @@ static inline bool crosses_local_route_boundary(int skb_af, struct sk_buff *skb,
 						bool new_rt_is_local)
 {
 	bool rt_mode_allow_local = !!(rt_mode & IP_VS_RT_MODE_LOCAL);
-	bool rt_mode_allow_non_local = !!(rt_mode & IP_VS_RT_MODE_LOCAL);
+	bool rt_mode_allow_non_local = !!(rt_mode & IP_VS_RT_MODE_NON_LOCAL);
 	bool rt_mode_allow_redirect = !!(rt_mode & IP_VS_RT_MODE_RDR);
 	bool source_is_loopback;
 	bool old_rt_is_local;

net/netfilter/nf_tables_api.c

@@ -2890,12 +2890,13 @@ static struct nft_set *nft_set_lookup_byid(const struct net *net,
 	u32 id = ntohl(nla_get_be32(nla));
 
 	list_for_each_entry(trans, &net->nft.commit_list, list) {
-		struct nft_set *set = nft_trans_set(trans);
+		if (trans->msg_type == NFT_MSG_NEWSET) {
+			struct nft_set *set = nft_trans_set(trans);
 
-		if (trans->msg_type == NFT_MSG_NEWSET &&
-		    id == nft_trans_set_id(trans) &&
-		    nft_active_genmask(set, genmask))
-			return set;
+			if (id == nft_trans_set_id(trans) &&
+			    nft_active_genmask(set, genmask))
+				return set;
+		}
 	}
 	return ERR_PTR(-ENOENT);
 }

net/netfilter/nft_set_rbtree.c

@@ -66,7 +66,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set
 			parent = rcu_dereference_raw(parent->rb_left);
 			if (interval &&
 			    nft_rbtree_equal(set, this, interval) &&
-			    nft_rbtree_interval_end(this) &&
+			    nft_rbtree_interval_end(rbe) &&
 			    !nft_rbtree_interval_end(interval))
 				continue;
 			interval = rbe;

net/netfilter/xt_CT.c

@@ -245,12 +245,22 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par,
 	}
 
 	if (info->helper[0]) {
+		if (strnlen(info->helper, sizeof(info->helper)) == sizeof(info->helper)) {
+			ret = -ENAMETOOLONG;
+			goto err3;
+		}
+
 		ret = xt_ct_set_helper(ct, info->helper, par);
 		if (ret < 0)
 			goto err3;
 	}
 
 	if (info->timeout[0]) {
+		if (strnlen(info->timeout, sizeof(info->timeout)) == sizeof(info->timeout)) {
+			ret = -ENAMETOOLONG;
+			goto err4;
+		}
+
 		ret = xt_ct_set_timeout(ct, par, info->timeout);
 		if (ret < 0)
 			goto err4;

net/netfilter/xt_set.c

@@ -372,8 +372,8 @@ set_target_v2(struct sk_buff *skb, const struct xt_action_param *par)
 
 	/* Normalize to fit into jiffies */
 	if (add_opt.ext.timeout != IPSET_NO_TIMEOUT &&
-	    add_opt.ext.timeout > UINT_MAX / MSEC_PER_SEC)
-		add_opt.ext.timeout = UINT_MAX / MSEC_PER_SEC;
+	    add_opt.ext.timeout > IPSET_MAX_TIMEOUT)
+		add_opt.ext.timeout = IPSET_MAX_TIMEOUT;
 	if (info->add_set.index != IPSET_INVALID_ID)
 		ip_set_add(info->add_set.index, skb, par, &add_opt);
 	if (info->del_set.index != IPSET_INVALID_ID)
@@ -407,8 +407,8 @@ set_target_v3(struct sk_buff *skb, const struct xt_action_param *par)
 
 	/* Normalize to fit into jiffies */
 	if (add_opt.ext.timeout != IPSET_NO_TIMEOUT &&
-	    add_opt.ext.timeout > UINT_MAX / MSEC_PER_SEC)
-		add_opt.ext.timeout = UINT_MAX / MSEC_PER_SEC;
+	    add_opt.ext.timeout > IPSET_MAX_TIMEOUT)
+		add_opt.ext.timeout = IPSET_MAX_TIMEOUT;
 	if (info->add_set.index != IPSET_INVALID_ID)
 		ip_set_add(info->add_set.index, skb, par, &add_opt);
 	if (info->del_set.index != IPSET_INVALID_ID)
@@ -470,7 +470,7 @@ set_target_v3_checkentry(const struct xt_tgchk_param *par)
 		}
 		if (((info->flags & IPSET_FLAG_MAP_SKBPRIO) |
 		     (info->flags & IPSET_FLAG_MAP_SKBQUEUE)) &&
-		     !(par->hook_mask & (1 << NF_INET_FORWARD |
+		     (par->hook_mask & ~(1 << NF_INET_FORWARD |
 					 1 << NF_INET_LOCAL_OUT |
 					 1 << NF_INET_POST_ROUTING))) {
 			pr_info_ratelimited("mapping of prio or/and queue is allowed only from OUTPUT/FORWARD/POSTROUTING chains\n");