1 files changed, 193 insertions, 22 deletions

diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index e101eda05d55..9c464d24beec 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -29,6 +29,7 @@
 #include <linux/tcp.h>                  /* for tcphdr */
 #include <net/ip.h>
 #include <net/gue.h>
+#include <net/gre.h>
 #include <net/tcp.h>                    /* for csum_tcpudp_magic */
 #include <net/udp.h>
 #include <net/icmp.h>                   /* for icmp_send */
@@ -36,6 +37,7 @@
 #include <net/ipv6.h>
 #include <net/ip6_route.h>
 #include <net/ip_tunnels.h>
+#include <net/ip6_checksum.h>
 #include <net/addrconf.h>
 #include <linux/icmpv6.h>
 #include <linux/netfilter.h>
@@ -275,7 +277,7 @@ static inline bool decrement_ttl(struct netns_ipvs *ipvs,
 		}
 
 		/* don't propagate ttl change to cloned packets */
-		if (!skb_make_writable(skb, sizeof(struct ipv6hdr)))
+		if (skb_ensure_writable(skb, sizeof(struct ipv6hdr)))
 			return false;
 
 		ipv6_hdr(skb)->hop_limit--;
@@ -290,7 +292,7 @@ static inline bool decrement_ttl(struct netns_ipvs *ipvs,
 		}
 
 		/* don't propagate ttl change to cloned packets */
-		if (!skb_make_writable(skb, sizeof(struct iphdr)))
+		if (skb_ensure_writable(skb, sizeof(struct iphdr)))
 			return false;
 
 		/* Decrease ttl */
@@ -381,8 +383,19 @@ __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb,
 		mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr);
 		if (!dest)
 			goto err_put;
-		if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
+		if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) {
 			mtu -= sizeof(struct udphdr) + sizeof(struct guehdr);
+			if ((dest->tun_flags &
+			     IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM) &&
+			    skb->ip_summed == CHECKSUM_PARTIAL)
+				mtu -= GUE_PLEN_REMCSUM + GUE_LEN_PRIV;
+		} else if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) {
+			__be16 tflags = 0;
+
+			if (dest->tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM)
+				tflags |= TUNNEL_CSUM;
+			mtu -= gre_calc_hlen(tflags);
+		}
 		if (mtu < 68) {
 			IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__);
 			goto err_put;
@@ -536,8 +549,19 @@ __ip_vs_get_out_rt_v6(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb,
 		mtu = dst_mtu(&rt->dst) - sizeof(struct ipv6hdr);
 		if (!dest)
 			goto err_put;
-		if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
+		if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) {
 			mtu -= sizeof(struct udphdr) + sizeof(struct guehdr);
+			if ((dest->tun_flags &
+			     IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM) &&
+			    skb->ip_summed == CHECKSUM_PARTIAL)
+				mtu -= GUE_PLEN_REMCSUM + GUE_LEN_PRIV;
+		} else if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) {
+			__be16 tflags = 0;
+
+			if (dest->tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM)
+				tflags |= TUNNEL_CSUM;
+			mtu -= gre_calc_hlen(tflags);
+		}
 		if (mtu < IPV6_MIN_MTU) {
 			IP_VS_DBG_RL("%s(): mtu less than %d\n", __func__,
 				     IPV6_MIN_MTU);
@@ -792,7 +816,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	}
 
 	/* copy-on-write the packet before mangling it */
-	if (!skb_make_writable(skb, sizeof(struct iphdr)))
+	if (skb_ensure_writable(skb, sizeof(struct iphdr)))
 		goto tx_error;
 
 	if (skb_cow(skb, rt->dst.dev->hard_header_len))
@@ -881,7 +905,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	}
 
 	/* copy-on-write the packet before mangling it */
-	if (!skb_make_writable(skb, sizeof(struct ipv6hdr)))
+	if (skb_ensure_writable(skb, sizeof(struct ipv6hdr)))
 		goto tx_error;
 
 	if (skb_cow(skb, rt->dst.dev->hard_header_len))
@@ -1002,17 +1026,56 @@ ipvs_gue_encap(struct net *net, struct sk_buff *skb,
 	__be16 sport = udp_flow_src_port(net, skb, 0, 0, false);
 	struct udphdr  *udph;	/* Our new UDP header */
 	struct guehdr  *gueh;	/* Our new GUE header */
+	size_t hdrlen, optlen = 0;
+	void *data;
+	bool need_priv = false;
+
+	if ((cp->dest->tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM) &&
+	    skb->ip_summed == CHECKSUM_PARTIAL) {
+		optlen += GUE_PLEN_REMCSUM + GUE_LEN_PRIV;
+		need_priv = true;
+	}
 
-	skb_push(skb, sizeof(struct guehdr));
+	hdrlen = sizeof(struct guehdr) + optlen;
+
+	skb_push(skb, hdrlen);
 
 	gueh = (struct guehdr *)skb->data;
 
 	gueh->control = 0;
 	gueh->version = 0;
-	gueh->hlen = 0;
+	gueh->hlen = optlen >> 2;
 	gueh->flags = 0;
 	gueh->proto_ctype = *next_protocol;
 
+	data = &gueh[1];
+
+	if (need_priv) {
+		__be32 *flags = data;
+		u16 csum_start = skb_checksum_start_offset(skb);
+		__be16 *pd;
+
+		gueh->flags |= GUE_FLAG_PRIV;
+		*flags = 0;
+		data += GUE_LEN_PRIV;
+
+		if (csum_start < hdrlen)
+			return -EINVAL;
+
+		csum_start -= hdrlen;
+		pd = data;
+		pd[0] = htons(csum_start);
+		pd[1] = htons(csum_start + skb->csum_offset);
+
+		if (!skb_is_gso(skb)) {
+			skb->ip_summed = CHECKSUM_NONE;
+			skb->encapsulation = 0;
+		}
+
+		*flags |= GUE_PFLAG_REMCSUM;
+		data += GUE_PLEN_REMCSUM;
+	}
+
 	skb_push(skb, sizeof(struct udphdr));
 	skb_reset_transport_header(skb);
 
@@ -1029,6 +1092,24 @@ ipvs_gue_encap(struct net *net, struct sk_buff *skb,
 	return 0;
 }
 
+static void
+ipvs_gre_encap(struct net *net, struct sk_buff *skb,
+	       struct ip_vs_conn *cp, __u8 *next_protocol)
+{
+	__be16 proto = *next_protocol == IPPROTO_IPIP ?
+				htons(ETH_P_IP) : htons(ETH_P_IPV6);
+	__be16 tflags = 0;
+	size_t hdrlen;
+
+	if (cp->dest->tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM)
+		tflags |= TUNNEL_CSUM;
+
+	hdrlen = gre_calc_hlen(tflags);
+	gre_build_header(skb, hdrlen, tflags, proto, 0, 0);
+
+	*next_protocol = IPPROTO_GRE;
+}
+
 /*
  *   IP Tunneling transmitter
  *
@@ -1066,6 +1147,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	unsigned int max_headroom;		/* The extra header space needed */
 	int ret, local;
 	int tun_type, gso_type;
+	int tun_flags;
 
 	EnterFunction(10);
 
@@ -1088,9 +1170,28 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct iphdr);
 
 	tun_type = cp->dest->tun_type;
+	tun_flags = cp->dest->tun_flags;
+
+	if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) {
+		size_t gue_hdrlen, gue_optlen = 0;
+
+		if ((tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM) &&
+		    skb->ip_summed == CHECKSUM_PARTIAL) {
+			gue_optlen += GUE_PLEN_REMCSUM + GUE_LEN_PRIV;
+		}
+		gue_hdrlen = sizeof(struct guehdr) + gue_optlen;
+
+		max_headroom += sizeof(struct udphdr) + gue_hdrlen;
+	} else if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) {
+		size_t gre_hdrlen;
+		__be16 tflags = 0;
 
-	if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
-		max_headroom += sizeof(struct udphdr) + sizeof(struct guehdr);
+		if (tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM)
+			tflags |= TUNNEL_CSUM;
+		gre_hdrlen = gre_calc_hlen(tflags);
+
+		max_headroom += gre_hdrlen;
+	}
 
 	/* We only care about the df field if sysctl_pmtu_disc(ipvs) is set */
 	dfp = sysctl_pmtu_disc(ipvs) ? &df : NULL;
@@ -1101,8 +1202,22 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 		goto tx_error;
 
 	gso_type = __tun_gso_type_mask(AF_INET, cp->af);
-	if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
-		gso_type |= SKB_GSO_UDP_TUNNEL;
+	if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) {
+		if ((tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM) ||
+		    (tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM))
+			gso_type |= SKB_GSO_UDP_TUNNEL_CSUM;
+		else
+			gso_type |= SKB_GSO_UDP_TUNNEL;
+		if ((tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM) &&
+		    skb->ip_summed == CHECKSUM_PARTIAL) {
+			gso_type |= SKB_GSO_TUNNEL_REMCSUM;
+		}
+	} else if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) {
+		if (tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM)
+			gso_type |= SKB_GSO_GRE_CSUM;
+		else
+			gso_type |= SKB_GSO_GRE;
+	}
 
 	if (iptunnel_handle_offloads(skb, gso_type))
 		goto tx_error;
@@ -1111,8 +1226,19 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 	skb_set_inner_ipproto(skb, next_protocol);
 
-	if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
-		ipvs_gue_encap(net, skb, cp, &next_protocol);
+	if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) {
+		bool check = false;
+
+		if (ipvs_gue_encap(net, skb, cp, &next_protocol))
+			goto tx_error;
+
+		if ((tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM) ||
+		    (tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM))
+			check = true;
+
+		udp_set_csum(!check, skb, saddr, cp->daddr.ip, skb->len);
+	} else if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE)
+		ipvs_gre_encap(net, skb, cp, &next_protocol);
 
 	skb_push(skb, sizeof(struct iphdr));
 	skb_reset_network_header(skb);
@@ -1170,6 +1296,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	unsigned int max_headroom;	/* The extra header space needed */
 	int ret, local;
 	int tun_type, gso_type;
+	int tun_flags;
 
 	EnterFunction(10);
 
@@ -1193,9 +1320,28 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct ipv6hdr);
 
 	tun_type = cp->dest->tun_type;
+	tun_flags = cp->dest->tun_flags;
+
+	if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) {
+		size_t gue_hdrlen, gue_optlen = 0;
+
+		if ((tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM) &&
+		    skb->ip_summed == CHECKSUM_PARTIAL) {
+			gue_optlen += GUE_PLEN_REMCSUM + GUE_LEN_PRIV;
+		}
+		gue_hdrlen = sizeof(struct guehdr) + gue_optlen;
+
+		max_headroom += sizeof(struct udphdr) + gue_hdrlen;
+	} else if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) {
+		size_t gre_hdrlen;
+		__be16 tflags = 0;
+
+		if (tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM)
+			tflags |= TUNNEL_CSUM;
+		gre_hdrlen = gre_calc_hlen(tflags);
 
-	if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
-		max_headroom += sizeof(struct udphdr) + sizeof(struct guehdr);
+		max_headroom += gre_hdrlen;
+	}
 
 	skb = ip_vs_prepare_tunneled_skb(skb, cp->af, max_headroom,
 					 &next_protocol, &payload_len,
@@ -1204,8 +1350,22 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 		goto tx_error;
 
 	gso_type = __tun_gso_type_mask(AF_INET6, cp->af);
-	if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
-		gso_type |= SKB_GSO_UDP_TUNNEL;
+	if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) {
+		if ((tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM) ||
+		    (tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM))
+			gso_type |= SKB_GSO_UDP_TUNNEL_CSUM;
+		else
+			gso_type |= SKB_GSO_UDP_TUNNEL;
+		if ((tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM) &&
+		    skb->ip_summed == CHECKSUM_PARTIAL) {
+			gso_type |= SKB_GSO_TUNNEL_REMCSUM;
+		}
+	} else if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) {
+		if (tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM)
+			gso_type |= SKB_GSO_GRE_CSUM;
+		else
+			gso_type |= SKB_GSO_GRE;
+	}
 
 	if (iptunnel_handle_offloads(skb, gso_type))
 		goto tx_error;
@@ -1214,8 +1374,19 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 	skb_set_inner_ipproto(skb, next_protocol);
 
-	if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
-		ipvs_gue_encap(net, skb, cp, &next_protocol);
+	if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) {
+		bool check = false;
+
+		if (ipvs_gue_encap(net, skb, cp, &next_protocol))
+			goto tx_error;
+
+		if ((tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM) ||
+		    (tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM))
+			check = true;
+
+		udp6_set_csum(!check, skb, &saddr, &cp->daddr.in6, skb->len);
+	} else if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE)
+		ipvs_gre_encap(net, skb, cp, &next_protocol);
 
 	skb_push(skb, sizeof(struct ipv6hdr));
 	skb_reset_network_header(skb);
@@ -1400,7 +1571,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	}
 
 	/* copy-on-write the packet before mangling it */
-	if (!skb_make_writable(skb, offset))
+	if (skb_ensure_writable(skb, offset))
 		goto tx_error;
 
 	if (skb_cow(skb, rt->dst.dev->hard_header_len))
@@ -1489,7 +1660,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	}
 
 	/* copy-on-write the packet before mangling it */
-	if (!skb_make_writable(skb, offset))
+	if (skb_ensure_writable(skb, offset))
 		goto tx_error;
 
 	if (skb_cow(skb, rt->dst.dev->hard_header_len))