Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking fixes from David Miller:

 1) Various netfilter fixlets from Pablo and the netfilter team.

 2) Fix regression in IPVS caused by lack of PMTU exceptions on local
    routes in ipv6, from Julian Anastasov.

 3) Check pskb_trim_rcsum for failure in DSA, from Zhouyang Jia.

 4) Don't crash on poll in TLS, from Daniel Borkmann.

 5) Revert SO_REUSE{ADDR,PORT} change, it regresses various things
    including Avahi mDNS. From Bart Van Assche.

 6) Missing of_node_put in qcom/emac driver, from Yue Haibing.

 7) We lack checking of the TCP checking in one special case during SYN
    receive, from Frank van der Linden.

 8) Fix module init error paths of mac80211 hwsim, from Johannes Berg.

 9) Handle 802.1ad properly in stmmac driver, from Elad Nachman.

10) Must grab HW caps before doing quirk checks in stmmac driver, from
    Jose Abreu.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (81 commits)
  net: stmmac: Run HWIF Quirks after getting HW caps
  neighbour: skip NTF_EXT_LEARNED entries during forced gc
  net: cxgb3: add error handling for sysfs_create_group
  tls: fix waitall behavior in tls_sw_recvmsg
  tls: fix use-after-free in tls_push_record
  l2tp: filter out non-PPP sessions in pppol2tp_tunnel_ioctl()
  l2tp: reject creation of non-PPP sessions on L2TPv2 tunnels
  mlxsw: spectrum_switchdev: Fix port_vlan refcounting
  mlxsw: spectrum_router: Align with new route replace logic
  mlxsw: spectrum_router: Allow appending to dev-only routes
  ipv6: Only emit append events for appended routes
  stmmac: added support for 802.1ad vlan stripping
  cfg80211: fix rcu in cfg80211_unregister_wdev
  mac80211: Move up init of TXQs
  mac80211_hwsim: fix module init error paths
  cfg80211: initialize sinfo in cfg80211_get_station
  nl80211: fix some kernel doc tag mistakes
  hv_netvsc: Fix the variable sizes in ipsecv2 and rsc offload
  rds: avoid unenecessary cong_update in loop transport
  l2tp: clean up stale tunnel or session in pppol2tp_connect's error path
  ...

16 files changed, 79 insertions, 33 deletions

diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index bbad940c0137..8a33dac4e805 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/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
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 0c03c0e16a96..dd21782e2f12 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/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);
 	/*
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index ba0a0fd045c8..473cce2a5231 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/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;
diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c
index 3b5059a8dcdd..d8383609fe28 100644
--- a/net/netfilter/nf_conncount.c
+++ b/net/netfilter/nf_conncount.c
@@ -46,6 +46,7 @@
 struct nf_conncount_tuple {
 	struct hlist_node		node;
 	struct nf_conntrack_tuple	tuple;
+	struct nf_conntrack_zone	zone;
 };
 
 struct nf_conncount_rb {
@@ -80,7 +81,8 @@ static int key_diff(const u32 *a, const u32 *b, unsigned int klen)
 }
 
 bool nf_conncount_add(struct hlist_head *head,
-		      const struct nf_conntrack_tuple *tuple)
+		      const struct nf_conntrack_tuple *tuple,
+		      const struct nf_conntrack_zone *zone)
 {
 	struct nf_conncount_tuple *conn;
 
@@ -88,6 +90,7 @@ bool nf_conncount_add(struct hlist_head *head,
 	if (conn == NULL)
 		return false;
 	conn->tuple = *tuple;
+	conn->zone = *zone;
 	hlist_add_head(&conn->node, head);
 	return true;
 }
@@ -108,7 +111,7 @@ unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head,
 
 	/* check the saved connections */
 	hlist_for_each_entry_safe(conn, n, head, node) {
-		found = nf_conntrack_find_get(net, zone, &conn->tuple);
+		found = nf_conntrack_find_get(net, &conn->zone, &conn->tuple);
 		if (found == NULL) {
 			hlist_del(&conn->node);
 			kmem_cache_free(conncount_conn_cachep, conn);
@@ -117,7 +120,8 @@ unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head,
 
 		found_ct = nf_ct_tuplehash_to_ctrack(found);
 
-		if (tuple && nf_ct_tuple_equal(&conn->tuple, tuple)) {
+		if (tuple && nf_ct_tuple_equal(&conn->tuple, tuple) &&
+		    nf_ct_zone_equal(found_ct, zone, zone->dir)) {
 			/*
 			 * Just to be sure we have it only once in the list.
 			 * We should not see tuples twice unless someone hooks
@@ -196,7 +200,7 @@ count_tree(struct net *net, struct rb_root *root,
 			if (!addit)
 				return count;
 
-			if (!nf_conncount_add(&rbconn->hhead, tuple))
+			if (!nf_conncount_add(&rbconn->hhead, tuple, zone))
 				return 0; /* hotdrop */
 
 			return count + 1;
@@ -238,6 +242,7 @@ count_tree(struct net *net, struct rb_root *root,
 	}
 
 	conn->tuple = *tuple;
+	conn->zone = *zone;
 	memcpy(rbconn->key, key, sizeof(u32) * keylen);
 
 	INIT_HLIST_HEAD(&rbconn->hhead);
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 39327a42879f..20a2e37c76d1 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1446,7 +1446,8 @@ ctnetlink_parse_nat_setup(struct nf_conn *ct,
 		}
 		nfnl_lock(NFNL_SUBSYS_CTNETLINK);
 		rcu_read_lock();
-		if (nat_hook->parse_nat_setup)
+		nat_hook = rcu_dereference(nf_nat_hook);
+		if (nat_hook)
 			return -EAGAIN;
 #endif
 		return -EOPNOTSUPP;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index f0411fbffe77..896d4a36081d 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/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);
 }
@@ -5836,18 +5837,23 @@ static int nf_tables_flowtable_event(struct notifier_block *this,
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct nft_flowtable *flowtable;
 	struct nft_table *table;
+	struct net *net;
 
 	if (event != NETDEV_UNREGISTER)
 		return 0;
 
+	net = maybe_get_net(dev_net(dev));
+	if (!net)
+		return 0;
+
 	nfnl_lock(NFNL_SUBSYS_NFTABLES);
-	list_for_each_entry(table, &dev_net(dev)->nft.tables, list) {
+	list_for_each_entry(table, &net->nft.tables, list) {
 		list_for_each_entry(flowtable, &table->flowtables, list) {
 			nft_flowtable_event(event, dev, flowtable);
 		}
 	}
 	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
-
+	put_net(net);
 	return NOTIFY_DONE;
 }
 
@@ -6438,7 +6444,7 @@ static void nf_tables_abort_release(struct nft_trans *trans)
 	kfree(trans);
 }
 
-static int nf_tables_abort(struct net *net, struct sk_buff *skb)
+static int __nf_tables_abort(struct net *net)
 {
 	struct nft_trans *trans, *next;
 	struct nft_trans_elem *te;
@@ -6554,6 +6560,11 @@ static void nf_tables_cleanup(struct net *net)
 	nft_validate_state_update(net, NFT_VALIDATE_SKIP);
 }
 
+static int nf_tables_abort(struct net *net, struct sk_buff *skb)
+{
+	return __nf_tables_abort(net);
+}
+
 static bool nf_tables_valid_genid(struct net *net, u32 genid)
 {
 	return net->nft.base_seq == genid;
@@ -7148,9 +7159,12 @@ static int __net_init nf_tables_init_net(struct net *net)
 
 static void __net_exit nf_tables_exit_net(struct net *net)
 {
+	nfnl_lock(NFNL_SUBSYS_NFTABLES);
+	if (!list_empty(&net->nft.commit_list))
+		__nf_tables_abort(net);
 	__nft_release_tables(net);
+	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
 	WARN_ON_ONCE(!list_empty(&net->nft.tables));
-	WARN_ON_ONCE(!list_empty(&net->nft.commit_list));
 }
 
 static struct pernet_operations nf_tables_net_ops = {
@@ -7192,13 +7206,13 @@ err1:
 
 static void __exit nf_tables_module_exit(void)
 {
-	unregister_pernet_subsys(&nf_tables_net_ops);
 	nfnetlink_subsys_unregister(&nf_tables_subsys);
 	unregister_netdevice_notifier(&nf_tables_flowtable_notifier);
+	nft_chain_filter_fini();
+	unregister_pernet_subsys(&nf_tables_net_ops);
 	rcu_barrier();
 	nf_tables_core_module_exit();
 	kfree(info);
-	nft_chain_filter_fini();
 }
 
 module_init(nf_tables_module_init);
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index deff10adef9c..8de912ca53d3 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -183,7 +183,8 @@ next_rule:
 
 	switch (regs.verdict.code) {
 	case NFT_JUMP:
-		BUG_ON(stackptr >= NFT_JUMP_STACK_SIZE);
+		if (WARN_ON_ONCE(stackptr >= NFT_JUMP_STACK_SIZE))
+			return NF_DROP;
 		jumpstack[stackptr].chain = chain;
 		jumpstack[stackptr].rules = rules + 1;
 		stackptr++;
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 4d0da7042aff..e1b6be29848d 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -429,7 +429,7 @@ replay:
 			 */
 			if (err == -EAGAIN) {
 				status |= NFNL_BATCH_REPLAY;
-				goto next;
+				goto done;
 			}
 		}
 ack:
@@ -456,7 +456,7 @@ ack:
 			if (err)
 				status |= NFNL_BATCH_FAILURE;
 		}
-next:
+
 		msglen = NLMSG_ALIGN(nlh->nlmsg_len);
 		if (msglen > skb->len)
 			msglen = skb->len;
@@ -464,7 +464,11 @@ next:
 	}
 done:
 	if (status & NFNL_BATCH_REPLAY) {
-		ss->abort(net, oskb);
+		const struct nfnetlink_subsystem *ss2;
+
+		ss2 = nfnl_dereference_protected(subsys_id);
+		if (ss2 == ss)
+			ss->abort(net, oskb);
 		nfnl_err_reset(&err_list);
 		nfnl_unlock(subsys_id);
 		kfree_skb(skb);
diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c
index 84c902477a91..d21834bed805 100644
--- a/net/netfilter/nft_chain_filter.c
+++ b/net/netfilter/nft_chain_filter.c
@@ -318,6 +318,10 @@ static int nf_tables_netdev_event(struct notifier_block *this,
 	    event != NETDEV_CHANGENAME)
 		return NOTIFY_DONE;
 
+	ctx.net = maybe_get_net(ctx.net);
+	if (!ctx.net)
+		return NOTIFY_DONE;
+
 	nfnl_lock(NFNL_SUBSYS_NFTABLES);
 	list_for_each_entry(table, &ctx.net->nft.tables, list) {
 		if (table->family != NFPROTO_NETDEV)
@@ -334,6 +338,7 @@ static int nf_tables_netdev_event(struct notifier_block *this,
 		}
 	}
 	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+	put_net(ctx.net);
 
 	return NOTIFY_DONE;
 }
diff --git a/net/netfilter/nft_connlimit.c b/net/netfilter/nft_connlimit.c
index 50c068d660e5..a832c59f0a9c 100644
--- a/net/netfilter/nft_connlimit.c
+++ b/net/netfilter/nft_connlimit.c
@@ -52,7 +52,7 @@ static inline void nft_connlimit_do_eval(struct nft_connlimit *priv,
 	if (!addit)
 		goto out;
 
-	if (!nf_conncount_add(&priv->hhead, tuple_ptr)) {
+	if (!nf_conncount_add(&priv->hhead, tuple_ptr, zone)) {
 		regs->verdict.code = NF_DROP;
 		spin_unlock_bh(&priv->lock);
 		return;
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index 4d49529cff61..27d7e4598ab6 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -203,9 +203,7 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
 				goto err1;
 			set->ops->gc_init(set);
 		}
-
-	} else if (set->flags & NFT_SET_EVAL)
-		return -EINVAL;
+	}
 
 	nft_set_ext_prepare(&priv->tmpl);
 	nft_set_ext_add_length(&priv->tmpl, NFT_SET_EXT_KEY, set->klen);
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index d260ce2d6671..7f3a9a211034 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/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;
diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c
index f28a0b944087..74e1b3bd6954 100644
--- a/net/netfilter/nft_socket.c
+++ b/net/netfilter/nft_socket.c
@@ -142,3 +142,4 @@ module_exit(nft_socket_module_exit);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Máté Eckl");
 MODULE_DESCRIPTION("nf_tables socket match module");
+MODULE_ALIAS_NFT_EXPR("socket");
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index 8790190c6feb..03b9a50ec93b 100644
--- a/net/netfilter/xt_CT.c
+++ b/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;
diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c
index 94df000abb92..29c38aa7f726 100644
--- a/net/netfilter/xt_connmark.c
+++ b/net/netfilter/xt_connmark.c
@@ -211,7 +211,7 @@ static int __init connmark_mt_init(void)
 static void __exit connmark_mt_exit(void)
 {
 	xt_unregister_match(&connmark_mt_reg);
-	xt_unregister_target(connmark_tg_reg);
+	xt_unregister_targets(connmark_tg_reg, ARRAY_SIZE(connmark_tg_reg));
 }
 
 module_init(connmark_mt_init);
diff --git a/net/netfilter/xt_set.c b/net/netfilter/xt_set.c
index 6f4c5217d835..bf2890b13212 100644
--- a/net/netfilter/xt_set.c
+++ b/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");