ipvs: add checksum support for gue encapsulation

Add checksum support for gue encapsulation with the tun_flags parameter,
which could be one of the values below:
IP_VS_TUNNEL_ENCAP_FLAG_NOCSUM
IP_VS_TUNNEL_ENCAP_FLAG_CSUM
IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM

Signed-off-by: Jacky Hu <hengqing.hu@gmail.com>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

1 files changed, 127 insertions, 16 deletions

diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 0b41d0504429..af3379d5e5bc 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -40,6 +40,7 @@
 #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>
@@ -385,8 +386,13 @@ __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;
+		}
 		if (mtu < 68) {
 			IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__);
 			goto err_put;
@@ -540,8 +546,13 @@ __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;
+		}
 		if (mtu < IPV6_MIN_MTU) {
 			IP_VS_DBG_RL("%s(): mtu less than %d\n", __func__,
 				     IPV6_MIN_MTU);
@@ -1006,17 +1017,56 @@ 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);
 
@@ -1070,6 +1120,7 @@ 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);
 
@@ -1092,9 +1143,19 @@ 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)
-		max_headroom += sizeof(struct udphdr) + sizeof(struct guehdr);
+	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;
+	}
 
 	/* We only care about the df field if sysctl_pmtu_disc(ipvs) is set */
 	dfp = sysctl_pmtu_disc(ipvs) ? &df : NULL;
@@ -1105,8 +1166,17 @@ 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;
+		}
+	}
 
 	if (iptunnel_handle_offloads(skb, gso_type))
 		goto tx_error;
@@ -1115,8 +1185,19 @@ 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);
+	}
+
 
 	skb_push(skb, sizeof(struct iphdr));
 	skb_reset_network_header(skb);
@@ -1174,6 +1255,7 @@ 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);
 
@@ -1197,9 +1279,19 @@ 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)
-		max_headroom += sizeof(struct udphdr) + sizeof(struct guehdr);
+	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;
+	}
 
 	skb = ip_vs_prepare_tunneled_skb(skb, cp->af, max_headroom,
 					 &next_protocol, &payload_len,
@@ -1208,8 +1300,17 @@ 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;
+		}
+	}
 
 	if (iptunnel_handle_offloads(skb, gso_type))
 		goto tx_error;
@@ -1218,8 +1319,18 @@ 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);
+	}
 
 	skb_push(skb, sizeof(struct ipv6hdr));
 	skb_reset_network_header(skb);