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) Fix crash when dumping rules after conversion to RCU,
   from Florian Westphal.

2) Fix incorrect hook reinjection from nf_queue in case NF_REPEAT,
   from Jagdish Motwani.

3) Fix check for route existence in fib extension, from Phil Sutter.

4) Fix use after free in ip_vs_in() hook, from YueHaibing.

5) Check for veth existence from netfilter selftests,
   from Jeffrin Jose T.

6) Checksum corruption in UDP NAT helpers due to typo,
   from Florian Westphal.

7) Pass up packets to classic forwarding path regardless of
   IPv4 DF bit, patch for the flowtable infrastructure from Florian.

8) Set liberal TCP tracking for flows that are placed in the
   flowtable, in case they need to go back to classic forwarding path,
   also from Florian.

9) Don't add flow with sequence adjustment to flowtable, from Florian.

10) Skip IPv4 options from IPv6 datapath in flowtable, from Florian.

11) Add selftest for the flowtable infrastructure, from Florian.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 39 insertions, 26 deletions

diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 14457551bcb4..8ebf21149ec3 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -2312,7 +2312,6 @@ static void __net_exit __ip_vs_cleanup(struct net *net)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
-	nf_unregister_net_hooks(net, ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
 	ip_vs_service_net_cleanup(ipvs);	/* ip_vs_flush() with locks */
 	ip_vs_conn_net_cleanup(ipvs);
 	ip_vs_app_net_cleanup(ipvs);
@@ -2327,6 +2326,7 @@ static void __net_exit __ip_vs_dev_cleanup(struct net *net)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
 	EnterFunction(2);
+	nf_unregister_net_hooks(net, ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
 	ipvs->enable = 0;	/* Disable packet reception */
 	smp_wmb();
 	ip_vs_sync_net_cleanup(ipvs);
diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index 96825e20368f..241317473114 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -244,8 +244,7 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
 	rt = (struct rtable *)flow->tuplehash[dir].tuple.dst_cache;
 	outdev = rt->dst.dev;
 
-	if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu)) &&
-	    (ip_hdr(skb)->frag_off & htons(IP_DF)) != 0)
+	if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu)))
 		return NF_ACCEPT;
 
 	if (skb_try_make_writable(skb, sizeof(*iph)))
diff --git a/net/netfilter/nf_nat_helper.c b/net/netfilter/nf_nat_helper.c
index ccc06f7539d7..53aeb12b70fb 100644
--- a/net/netfilter/nf_nat_helper.c
+++ b/net/netfilter/nf_nat_helper.c
@@ -170,7 +170,7 @@ nf_nat_mangle_udp_packet(struct sk_buff *skb,
 	if (!udph->check && skb->ip_summed != CHECKSUM_PARTIAL)
 		return true;
 
-	nf_nat_csum_recalc(skb, nf_ct_l3num(ct), IPPROTO_TCP,
+	nf_nat_csum_recalc(skb, nf_ct_l3num(ct), IPPROTO_UDP,
 			   udph, &udph->check, datalen, oldlen);
 
 	return true;
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 9dc1d6e04946..b5b2be55ca82 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -255,6 +255,7 @@ static unsigned int nf_iterate(struct sk_buff *skb,
 repeat:
 		verdict = nf_hook_entry_hookfn(hook, skb, state);
 		if (verdict != NF_ACCEPT) {
+			*index = i;
 			if (verdict != NF_REPEAT)
 				return verdict;
 			goto repeat;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 28241e82fd15..4b5159936034 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2270,13 +2270,13 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net,
 				    u32 flags, int family,
 				    const struct nft_table *table,
 				    const struct nft_chain *chain,
-				    const struct nft_rule *rule)
+				    const struct nft_rule *rule,
+				    const struct nft_rule *prule)
 {
 	struct nlmsghdr *nlh;
 	struct nfgenmsg *nfmsg;
 	const struct nft_expr *expr, *next;
 	struct nlattr *list;
-	const struct nft_rule *prule;
 	u16 type = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
 
 	nlh = nlmsg_put(skb, portid, seq, type, sizeof(struct nfgenmsg), flags);
@@ -2296,8 +2296,7 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net,
 			 NFTA_RULE_PAD))
 		goto nla_put_failure;
 
-	if ((event != NFT_MSG_DELRULE) && (rule->list.prev != &chain->rules)) {
-		prule = list_prev_entry(rule, list);
+	if (event != NFT_MSG_DELRULE && prule) {
 		if (nla_put_be64(skb, NFTA_RULE_POSITION,
 				 cpu_to_be64(prule->handle),
 				 NFTA_RULE_PAD))
@@ -2344,7 +2343,7 @@ static void nf_tables_rule_notify(const struct nft_ctx *ctx,
 
 	err = nf_tables_fill_rule_info(skb, ctx->net, ctx->portid, ctx->seq,
 				       event, 0, ctx->family, ctx->table,
-				       ctx->chain, rule);
+				       ctx->chain, rule, NULL);
 	if (err < 0) {
 		kfree_skb(skb);
 		goto err;
@@ -2369,12 +2368,13 @@ static int __nf_tables_dump_rules(struct sk_buff *skb,
 				  const struct nft_chain *chain)
 {
 	struct net *net = sock_net(skb->sk);
+	const struct nft_rule *rule, *prule;
 	unsigned int s_idx = cb->args[0];
-	const struct nft_rule *rule;
 
+	prule = NULL;
 	list_for_each_entry_rcu(rule, &chain->rules, list) {
 		if (!nft_is_active(net, rule))
-			goto cont;
+			goto cont_skip;
 		if (*idx < s_idx)
 			goto cont;
 		if (*idx > s_idx) {
@@ -2386,11 +2386,13 @@ static int __nf_tables_dump_rules(struct sk_buff *skb,
 					NFT_MSG_NEWRULE,
 					NLM_F_MULTI | NLM_F_APPEND,
 					table->family,
-					table, chain, rule) < 0)
+					table, chain, rule, prule) < 0)
 			return 1;
 
 		nl_dump_check_consistent(cb, nlmsg_hdr(skb));
 cont:
+		prule = rule;
+cont_skip:
 		(*idx)++;
 	}
 	return 0;
@@ -2546,7 +2548,7 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk,
 
 	err = nf_tables_fill_rule_info(skb2, net, NETLINK_CB(skb).portid,
 				       nlh->nlmsg_seq, NFT_MSG_NEWRULE, 0,
-				       family, table, chain, rule);
+				       family, table, chain, rule, NULL);
 	if (err < 0)
 		goto err;
 
diff --git a/net/netfilter/nft_fib.c b/net/netfilter/nft_fib.c
index 21df8cccea65..77f00a99dfab 100644
--- a/net/netfilter/nft_fib.c
+++ b/net/netfilter/nft_fib.c
@@ -135,17 +135,17 @@ int nft_fib_dump(struct sk_buff *skb, const struct nft_expr *expr)
 EXPORT_SYMBOL_GPL(nft_fib_dump);
 
 void nft_fib_store_result(void *reg, const struct nft_fib *priv,
-			  const struct nft_pktinfo *pkt, int index)
+			  const struct net_device *dev)
 {
-	struct net_device *dev;
 	u32 *dreg = reg;
+	int index;
 
 	switch (priv->result) {
 	case NFT_FIB_RESULT_OIF:
+		index = dev ? dev->ifindex : 0;
 		*dreg = (priv->flags & NFTA_FIB_F_PRESENT) ? !!index : index;
 		break;
 	case NFT_FIB_RESULT_OIFNAME:
-		dev = dev_get_by_index_rcu(nft_net(pkt), index);
 		if (priv->flags & NFTA_FIB_F_PRESENT)
 			*dreg = !!dev;
 		else
diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c
index ffb25d5e8dbe..aa5f571d4361 100644
--- a/net/netfilter/nft_flow_offload.c
+++ b/net/netfilter/nft_flow_offload.c
@@ -13,7 +13,6 @@
 #include <net/netfilter/nf_conntrack_core.h>
 #include <linux/netfilter/nf_conntrack_common.h>
 #include <net/netfilter/nf_flow_table.h>
-#include <net/netfilter/nf_conntrack_helper.h>
 
 struct nft_flow_offload {
 	struct nft_flowtable	*flowtable;
@@ -50,15 +49,20 @@ static int nft_flow_route(const struct nft_pktinfo *pkt,
 	return 0;
 }
 
-static bool nft_flow_offload_skip(struct sk_buff *skb)
+static bool nft_flow_offload_skip(struct sk_buff *skb, int family)
 {
-	struct ip_options *opt  = &(IPCB(skb)->opt);
-
-	if (unlikely(opt->optlen))
-		return true;
 	if (skb_sec_path(skb))
 		return true;
 
+	if (family == NFPROTO_IPV4) {
+		const struct ip_options *opt;
+
+		opt = &(IPCB(skb)->opt);
+
+		if (unlikely(opt->optlen))
+			return true;
+	}
+
 	return false;
 }
 
@@ -68,15 +72,15 @@ static void nft_flow_offload_eval(const struct nft_expr *expr,
 {
 	struct nft_flow_offload *priv = nft_expr_priv(expr);
 	struct nf_flowtable *flowtable = &priv->flowtable->data;
-	const struct nf_conn_help *help;
 	enum ip_conntrack_info ctinfo;
 	struct nf_flow_route route;
 	struct flow_offload *flow;
 	enum ip_conntrack_dir dir;
+	bool is_tcp = false;
 	struct nf_conn *ct;
 	int ret;
 
-	if (nft_flow_offload_skip(pkt->skb))
+	if (nft_flow_offload_skip(pkt->skb, nft_pf(pkt)))
 		goto out;
 
 	ct = nf_ct_get(pkt->skb, &ctinfo);
@@ -85,14 +89,16 @@ static void nft_flow_offload_eval(const struct nft_expr *expr,
 
 	switch (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum) {
 	case IPPROTO_TCP:
+		is_tcp = true;
+		break;
 	case IPPROTO_UDP:
 		break;
 	default:
 		goto out;
 	}
 
-	help = nfct_help(ct);
-	if (help)
+	if (nf_ct_ext_exist(ct, NF_CT_EXT_HELPER) ||
+	    ct->status & IPS_SEQ_ADJUST)
 		goto out;
 
 	if (!nf_ct_is_confirmed(ct))
@@ -109,6 +115,11 @@ static void nft_flow_offload_eval(const struct nft_expr *expr,
 	if (!flow)
 		goto err_flow_alloc;
 
+	if (is_tcp) {
+		ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL;
+		ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL;
+	}
+
 	ret = flow_offload_add(flowtable, flow);
 	if (ret < 0)
 		goto err_flow_add;