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

Pablo Neira Ayuso says:

====================
Netfilter/IPVS updates for net-next

The following patchset container Netfilter/IPVS update for net-next:

1) Add UDP tunnel support for ICMP errors in IPVS.

Julian Anastasov says:

This patchset is a followup to the commit that adds UDP/GUE tunnel:
"ipvs: allow tunneling with gue encapsulation".

What we do is to put tunnel real servers in hash table (patch 1),
add function to lookup tunnels (patch 2) and use it to strip the
embedded tunnel headers from ICMP errors (patch 3).

2) Extend xt_owner to match for supplementary groups, from
   Lukasz Pawelczyk.

3) Remove unused oif field in flow_offload_tuple object, from
   Taehee Yoo.

4) Release basechain counters from workqueue to skip synchronize_rcu()
   call. From Florian Westphal.

5) Replace skb_make_writable() by skb_ensure_writable(). Patchset
   from Florian Westphal.

6) Checksum support for gue encapsulation in IPVS, from Jacky Hu.
====================

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

Author: davem330

include/linux/netfilter.h

@@ -336,11 +336,6 @@ int compat_nf_getsockopt(struct sock *sk, u_int8_t pf, int optval,
 		char __user *opt, int *len);
 #endif
 
-/* Call this before modifying an existing packet: ensures it is
-   modifiable and linear to the point you care about (writable_len).
-   Returns true or false. */
-int skb_make_writable(struct sk_buff *skb, unsigned int writable_len);
-
 struct flowi;
 struct nf_queue_entry;
 

include/net/ip_vs.h

@@ -603,6 +603,7 @@ struct ip_vs_dest_user_kern {
 
 	u16			tun_type;	/* tunnel type */
 	__be16			tun_port;	/* tunnel port */
+	u16			tun_flags;	/* tunnel flags */
 };
 
 
@@ -665,6 +666,7 @@ struct ip_vs_dest {
 	atomic_t		last_weight;	/* server latest weight */
 	__u16			tun_type;	/* tunnel type */
 	__be16			tun_port;	/* tunnel port */
+	__u16			tun_flags;	/* tunnel flags */
 
 	refcount_t		refcnt;		/* reference counter */
 	struct ip_vs_stats      stats;          /* statistics */
@@ -1404,6 +1406,9 @@ bool ip_vs_has_real_service(struct netns_ipvs *ipvs, int af, __u16 protocol,
 struct ip_vs_dest *
 ip_vs_find_real_service(struct netns_ipvs *ipvs, int af, __u16 protocol,
 			const union nf_inet_addr *daddr, __be16 dport);
+struct ip_vs_dest *ip_vs_find_tunnel(struct netns_ipvs *ipvs, int af,
+				     const union nf_inet_addr *daddr,
+				     __be16 tun_port);
 
 int ip_vs_use_count_inc(void);
 void ip_vs_use_count_dec(void);
@@ -1497,6 +1502,9 @@ static inline int ip_vs_todrop(struct netns_ipvs *ipvs)
 static inline int ip_vs_todrop(struct netns_ipvs *ipvs) { return 0; }
 #endif
 
+#define IP_VS_DFWD_METHOD(dest) (atomic_read(&(dest)->conn_flags) & \
+				 IP_VS_CONN_F_FWD_MASK)
+
 /* ip_vs_fwd_tag returns the forwarding tag of the connection */
 #define IP_VS_FWD_METHOD(cp)  (cp->flags & IP_VS_CONN_F_FWD_MASK)
 

include/net/netfilter/nf_flow_table.h

@@ -53,8 +53,6 @@ struct flow_offload_tuple {
 	u8				l4proto;
 	u8				dir;
 
-	int				oifidx;
-
 	u16				mtu;
 
 	struct dst_entry		*dst_cache;

include/uapi/linux/ip_vs.h

@@ -131,6 +131,11 @@ enum {
 	IP_VS_CONN_F_TUNNEL_TYPE_MAX,
 };
 
+/* Tunnel encapsulation flags */
+#define IP_VS_TUNNEL_ENCAP_FLAG_NOCSUM		(0)
+#define IP_VS_TUNNEL_ENCAP_FLAG_CSUM		(1 << 0)
+#define IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM		(1 << 1)
+
 /*
  *	The struct ip_vs_service_user and struct ip_vs_dest_user are
  *	used to set IPVS rules through setsockopt.
@@ -403,6 +408,8 @@ enum {
 
 	IPVS_DEST_ATTR_TUN_PORT,	/* tunnel port */
 
+	IPVS_DEST_ATTR_TUN_FLAGS,	/* tunnel flags */
+
 	__IPVS_DEST_ATTR_MAX,
 };
 

include/uapi/linux/netfilter/xt_owner.h

@@ -5,9 +5,10 @@
 #include <linux/types.h>
 
 enum {
-	XT_OWNER_UID    = 1 << 0,
-	XT_OWNER_GID    = 1 << 1,
-	XT_OWNER_SOCKET = 1 << 2,
+	XT_OWNER_UID          = 1 << 0,
+	XT_OWNER_GID          = 1 << 1,
+	XT_OWNER_SOCKET       = 1 << 2,
+	XT_OWNER_SUPPL_GROUPS = 1 << 3,
 };
 
 struct xt_owner_match_info {

net/bridge/netfilter/ebt_dnat.c

@@ -22,7 +22,7 @@ ebt_dnat_tg(struct sk_buff *skb, const struct xt_action_param *par)
 	const struct ebt_nat_info *info = par->targinfo;
 	struct net_device *dev;
 
-	if (!skb_make_writable(skb, 0))
+	if (skb_ensure_writable(skb, ETH_ALEN))
 		return EBT_DROP;
 
 	ether_addr_copy(eth_hdr(skb)->h_dest, info->mac);

net/bridge/netfilter/ebt_redirect.c

@@ -21,7 +21,7 @@ ebt_redirect_tg(struct sk_buff *skb, const struct xt_action_param *par)
 {
 	const struct ebt_redirect_info *info = par->targinfo;
 
-	if (!skb_make_writable(skb, 0))
+	if (skb_ensure_writable(skb, ETH_ALEN))
 		return EBT_DROP;
 
 	if (xt_hooknum(par) != NF_BR_BROUTING)

net/bridge/netfilter/ebt_snat.c

@@ -22,7 +22,7 @@ ebt_snat_tg(struct sk_buff *skb, const struct xt_action_param *par)
 {
 	const struct ebt_nat_info *info = par->targinfo;
 
-	if (!skb_make_writable(skb, 0))
+	if (skb_ensure_writable(skb, ETH_ALEN * 2))
 		return EBT_DROP;
 
 	ether_addr_copy(eth_hdr(skb)->h_source, info->mac);

net/ipv4/netfilter/arpt_mangle.c

@@ -17,7 +17,7 @@ target(struct sk_buff *skb, const struct xt_action_param *par)
 	unsigned char *arpptr;
 	int pln, hln;
 
-	if (!skb_make_writable(skb, skb->len))
+	if (skb_ensure_writable(skb, skb->len))
 		return NF_DROP;
 
 	arp = arp_hdr(skb);

net/ipv4/netfilter/ipt_ECN.c

@@ -32,7 +32,7 @@ set_ect_ip(struct sk_buff *skb, const struct ipt_ECN_info *einfo)
 
 	if ((iph->tos & IPT_ECN_IP_MASK) != (einfo->ip_ect & IPT_ECN_IP_MASK)) {
 		__u8 oldtos;
-		if (!skb_make_writable(skb, sizeof(struct iphdr)))
+		if (skb_ensure_writable(skb, sizeof(struct iphdr)))
 			return false;
 		iph = ip_hdr(skb);
 		oldtos = iph->tos;
@@ -61,7 +61,7 @@ set_ect_tcp(struct sk_buff *skb, const struct ipt_ECN_info *einfo)
 	     tcph->cwr == einfo->proto.tcp.cwr))
 		return true;
 
-	if (!skb_make_writable(skb, ip_hdrlen(skb) + sizeof(*tcph)))
+	if (skb_ensure_writable(skb, ip_hdrlen(skb) + sizeof(*tcph)))
 		return false;
 	tcph = (void *)ip_hdr(skb) + ip_hdrlen(skb);
 

net/ipv4/netfilter/nf_nat_h323.c

@@ -59,7 +59,7 @@ static int set_addr(struct sk_buff *skb, unsigned int protoff,
 			net_notice_ratelimited("nf_nat_h323: nf_nat_mangle_udp_packet error\n");
 			return -1;
 		}
-		/* nf_nat_mangle_udp_packet uses skb_make_writable() to copy
+		/* nf_nat_mangle_udp_packet uses skb_ensure_writable() to copy
 		 * or pull everything in a linear buffer, so we can safely
 		 * use the skb pointers now */
 		*data = skb->data + ip_hdrlen(skb) + sizeof(struct udphdr);

net/ipv4/netfilter/nf_nat_snmp_basic_main.c

@@ -186,7 +186,7 @@ static int help(struct sk_buff *skb, unsigned int protoff,
 		return NF_DROP;
 	}
 
-	if (!skb_make_writable(skb, skb->len)) {
+	if (skb_ensure_writable(skb, skb->len)) {
 		nf_ct_helper_log(skb, ct, "cannot mangle packet");
 		return NF_DROP;
 	}

net/netfilter/core.c

@@ -536,28 +536,6 @@ int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state,
 }
 EXPORT_SYMBOL(nf_hook_slow);
 
-
-int skb_make_writable(struct sk_buff *skb, unsigned int writable_len)
-{
-	if (writable_len > skb->len)
-		return 0;
-
-	/* Not exclusive use of packet?  Must copy. */
-	if (!skb_cloned(skb)) {
-		if (writable_len <= skb_headlen(skb))
-			return 1;
-	} else if (skb_clone_writable(skb, writable_len))
-		return 1;
-
-	if (writable_len <= skb_headlen(skb))
-		writable_len = 0;
-	else
-		writable_len -= skb_headlen(skb);
-
-	return !!__pskb_pull_tail(skb, writable_len);
-}
-EXPORT_SYMBOL(skb_make_writable);
-
 /* This needs to be compiled in any case to avoid dependencies between the
  * nfnetlink_queue code and nf_conntrack.
  */

net/netfilter/ipvs/ip_vs_app.c

@@ -363,7 +363,7 @@ static inline int app_tcp_pkt_out(struct ip_vs_conn *cp, struct sk_buff *skb,
 	struct tcphdr *th;
 	__u32 seq;
 
-	if (!skb_make_writable(skb, tcp_offset + sizeof(*th)))
+	if (skb_ensure_writable(skb, tcp_offset + sizeof(*th)))
 		return 0;
 
 	th = (struct tcphdr *)(skb_network_header(skb) + tcp_offset);
@@ -440,7 +440,7 @@ static inline int app_tcp_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb,
 	struct tcphdr *th;
 	__u32 seq;
 
-	if (!skb_make_writable(skb, tcp_offset + sizeof(*th)))
+	if (skb_ensure_writable(skb, tcp_offset + sizeof(*th)))
 		return 0;
 
 	th = (struct tcphdr *)(skb_network_header(skb) + tcp_offset);

net/netfilter/ipvs/ip_vs_core.c

@@ -39,6 +39,7 @@
 #include <net/tcp.h>
 #include <net/udp.h>
 #include <net/icmp.h>                   /* for icmp_send */
+#include <net/gue.h>
 #include <net/route.h>
 #include <net/ip6_checksum.h>
 #include <net/netns/generic.h>		/* net_generic() */
@@ -897,7 +898,7 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
 	if (IPPROTO_TCP == protocol || IPPROTO_UDP == protocol ||
 	    IPPROTO_SCTP == protocol)
 		offset += 2 * sizeof(__u16);
-	if (!skb_make_writable(skb, offset))
+	if (skb_ensure_writable(skb, offset))
 		goto out;
 
 #ifdef CONFIG_IP_VS_IPV6
@@ -1287,7 +1288,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 
 	IP_VS_DBG_PKT(11, af, pp, skb, iph->off, "Outgoing packet");
 
-	if (!skb_make_writable(skb, iph->len))
+	if (skb_ensure_writable(skb, iph->len))
 		goto drop;
 
 	/* mangle the packet */
@@ -1579,6 +1580,41 @@ ip_vs_try_to_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb,
 	return 1;
 }
 
+/* Check the UDP tunnel and return its header length */
+static int ipvs_udp_decap(struct netns_ipvs *ipvs, struct sk_buff *skb,
+			  unsigned int offset, __u16 af,
+			  const union nf_inet_addr *daddr, __u8 *proto)
+{
+	struct udphdr _udph, *udph;
+	struct ip_vs_dest *dest;
+
+	udph = skb_header_pointer(skb, offset, sizeof(_udph), &_udph);
+	if (!udph)
+		goto unk;
+	offset += sizeof(struct udphdr);
+	dest = ip_vs_find_tunnel(ipvs, af, daddr, udph->dest);
+	if (!dest)
+		goto unk;
+	if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) {
+		struct guehdr _gueh, *gueh;
+
+		gueh = skb_header_pointer(skb, offset, sizeof(_gueh), &_gueh);
+		if (!gueh)
+			goto unk;
+		if (gueh->control != 0 || gueh->version != 0)
+			goto unk;
+		/* Later we can support also IPPROTO_IPV6 */
+		if (gueh->proto_ctype != IPPROTO_IPIP)
+			goto unk;
+		*proto = gueh->proto_ctype;
+		return sizeof(struct udphdr) + sizeof(struct guehdr) +
+		       (gueh->hlen << 2);
+	}
+
+unk:
+	return 0;
+}
+
 /*
  *	Handle ICMP messages in the outside-to-inside direction (incoming).
  *	Find any that might be relevant, check against existing connections,
@@ -1598,6 +1634,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
 	struct ip_vs_proto_data *pd;
 	unsigned int offset, offset2, ihl, verdict;
 	bool ipip, new_cp = false;
+	union nf_inet_addr *raddr;
 
 	*related = 1;
 
@@ -1636,20 +1673,51 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
 	cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph);
 	if (cih == NULL)
 		return NF_ACCEPT; /* The packet looks wrong, ignore */
+	raddr = (union nf_inet_addr *)&cih->daddr;
 
 	/* Special case for errors for IPIP packets */
 	ipip = false;
 	if (cih->protocol == IPPROTO_IPIP) {
+		struct ip_vs_dest *dest;
+
 		if (unlikely(cih->frag_off & htons(IP_OFFSET)))
 			return NF_ACCEPT;
 		/* Error for our IPIP must arrive at LOCAL_IN */
 		if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL))
 			return NF_ACCEPT;
+		dest = ip_vs_find_tunnel(ipvs, AF_INET, raddr, 0);
+		/* Only for known tunnel */
+		if (!dest || dest->tun_type != IP_VS_CONN_F_TUNNEL_TYPE_IPIP)
+			return NF_ACCEPT;
 		offset += cih->ihl * 4;
 		cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph);
 		if (cih == NULL)
 			return NF_ACCEPT; /* The packet looks wrong, ignore */
 		ipip = true;
+	} else if (cih->protocol == IPPROTO_UDP &&	/* Can be UDP encap */
+		   /* Error for our tunnel must arrive at LOCAL_IN */
+		   (skb_rtable(skb)->rt_flags & RTCF_LOCAL)) {
+		__u8 iproto;
+		int ulen;
+
+		/* Non-first fragment has no UDP header */
+		if (unlikely(cih->frag_off & htons(IP_OFFSET)))
+			return NF_ACCEPT;
+		offset2 = offset + cih->ihl * 4;
+		ulen = ipvs_udp_decap(ipvs, skb, offset2, AF_INET, raddr,
+				      &iproto);
+		if (ulen > 0) {
+			/* Skip IP and UDP tunnel headers */
+			offset = offset2 + ulen;
+			/* Now we should be at the original IP header */
+			cih = skb_header_pointer(skb, offset, sizeof(_ciph),
+						 &_ciph);
+			if (cih && cih->version == 4 && cih->ihl >= 5 &&
+			    iproto == IPPROTO_IPIP)
+				ipip = true;
+			else
+				return NF_ACCEPT;
+		}
 	}
 
 	pd = ip_vs_proto_data_get(ipvs, cih->protocol);