ipvs: handle PARTIAL_CHECKSUM

Now that LVS can load balance locally generated traffic, packets may come
from the loopback device and thus may have a partial checksum.

The existing code allows for the case where there is no checksum at all for
TCP, however Herbert Xu has confirmed that this is not legal.

Signed-off-by: Simon Horman <horms@verge.net.au>
Acked-by: Julius Volz <juliusv@google.com>

2 files changed, 70 insertions, 4 deletions

diff --git a/net/ipv4/ipvs/ip_vs_proto_tcp.c b/net/ipv4/ipvs/ip_vs_proto_tcp.c
index 808e8be0280a..537f616776da 100644
--- a/net/ipv4/ipvs/ip_vs_proto_tcp.c
+++ b/net/ipv4/ipvs/ip_vs_proto_tcp.c
@@ -134,12 +134,34 @@ tcp_fast_csum_update(int af, struct tcphdr *tcph,
 }
 
 
+static inline void
+tcp_partial_csum_update(int af, struct tcphdr *tcph,
+		     const union nf_inet_addr *oldip,
+		     const union nf_inet_addr *newip,
+		     __be16 oldlen, __be16 newlen)
+{
+#ifdef CONFIG_IP_VS_IPV6
+	if (af == AF_INET6)
+		tcph->check =
+			csum_fold(ip_vs_check_diff16(oldip->ip6, newip->ip6,
+					 ip_vs_check_diff2(oldlen, newlen,
+						~csum_unfold(tcph->check))));
+	else
+#endif
+	tcph->check =
+		csum_fold(ip_vs_check_diff4(oldip->ip, newip->ip,
+				ip_vs_check_diff2(oldlen, newlen,
+						~csum_unfold(tcph->check))));
+}
+
+
 static int
 tcp_snat_handler(struct sk_buff *skb,
 		 struct ip_vs_protocol *pp, struct ip_vs_conn *cp)
 {
 	struct tcphdr *tcph;
 	unsigned int tcphoff;
+	int oldlen;
 
 #ifdef CONFIG_IP_VS_IPV6
 	if (cp->af == AF_INET6)
@@ -147,6 +169,7 @@ tcp_snat_handler(struct sk_buff *skb,
 	else
 #endif
 		tcphoff = ip_hdrlen(skb);
+	oldlen = skb->len - tcphoff;
 
 	/* csum_check requires unshared skb */
 	if (!skb_make_writable(skb, tcphoff+sizeof(*tcph)))
@@ -166,7 +189,11 @@ tcp_snat_handler(struct sk_buff *skb,
 	tcph->source = cp->vport;
 
 	/* Adjust TCP checksums */
-	if (!cp->app && (tcph->check != 0)) {
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		tcp_partial_csum_update(cp->af, tcph, &cp->daddr, &cp->vaddr,
+					htonl(oldlen),
+					htonl(skb->len - tcphoff));
+	} else if (!cp->app) {
 		/* Only port and addr are changed, do fast csum update */
 		tcp_fast_csum_update(cp->af, tcph, &cp->daddr, &cp->vaddr,
 				     cp->dport, cp->vport);
@@ -204,6 +231,7 @@ tcp_dnat_handler(struct sk_buff *skb,
 {
 	struct tcphdr *tcph;
 	unsigned int tcphoff;
+	int oldlen;
 
 #ifdef CONFIG_IP_VS_IPV6
 	if (cp->af == AF_INET6)
@@ -211,6 +239,7 @@ tcp_dnat_handler(struct sk_buff *skb,
 	else
 #endif
 		tcphoff = ip_hdrlen(skb);
+	oldlen = skb->len - tcphoff;
 
 	/* csum_check requires unshared skb */
 	if (!skb_make_writable(skb, tcphoff+sizeof(*tcph)))
@@ -235,7 +264,11 @@ tcp_dnat_handler(struct sk_buff *skb,
 	/*
 	 *	Adjust TCP checksums
 	 */
-	if (!cp->app && (tcph->check != 0)) {
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		tcp_partial_csum_update(cp->af, tcph, &cp->daddr, &cp->vaddr,
+					htonl(oldlen),
+					htonl(skb->len - tcphoff));
+	} else if (!cp->app) {
 		/* Only port and addr are changed, do fast csum update */
 		tcp_fast_csum_update(cp->af, tcph, &cp->vaddr, &cp->daddr,
 				     cp->vport, cp->dport);
diff --git a/net/ipv4/ipvs/ip_vs_proto_udp.c b/net/ipv4/ipvs/ip_vs_proto_udp.c
index 5f2073e41cf6..e3ee26bd1de7 100644
--- a/net/ipv4/ipvs/ip_vs_proto_udp.c
+++ b/net/ipv4/ipvs/ip_vs_proto_udp.c
@@ -141,12 +141,34 @@ udp_fast_csum_update(int af, struct udphdr *uhdr,
 		uhdr->check = CSUM_MANGLED_0;
 }
 
+static inline void
+udp_partial_csum_update(int af, struct udphdr *uhdr,
+		     const union nf_inet_addr *oldip,
+		     const union nf_inet_addr *newip,
+		     __be16 oldlen, __be16 newlen)
+{
+#ifdef CONFIG_IP_VS_IPV6
+	if (af == AF_INET6)
+		uhdr->check =
+			csum_fold(ip_vs_check_diff16(oldip->ip6, newip->ip6,
+					 ip_vs_check_diff2(oldlen, newlen,
+						~csum_unfold(uhdr->check))));
+	else
+#endif
+	uhdr->check =
+		csum_fold(ip_vs_check_diff4(oldip->ip, newip->ip,
+				ip_vs_check_diff2(oldlen, newlen,
+						~csum_unfold(uhdr->check))));
+}
+
+
 static int
 udp_snat_handler(struct sk_buff *skb,
 		 struct ip_vs_protocol *pp, struct ip_vs_conn *cp)
 {
 	struct udphdr *udph;
 	unsigned int udphoff;
+	int oldlen;
 
 #ifdef CONFIG_IP_VS_IPV6
 	if (cp->af == AF_INET6)
@@ -154,6 +176,7 @@ udp_snat_handler(struct sk_buff *skb,
 	else
 #endif
 		udphoff = ip_hdrlen(skb);
+	oldlen = skb->len - udphoff;
 
 	/* csum_check requires unshared skb */
 	if (!skb_make_writable(skb, udphoff+sizeof(*udph)))
@@ -177,7 +200,11 @@ udp_snat_handler(struct sk_buff *skb,
 	/*
 	 *	Adjust UDP checksums
 	 */
-	if (!cp->app && (udph->check != 0)) {
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		udp_partial_csum_update(cp->af, udph, &cp->daddr, &cp->vaddr,
+					htonl(oldlen),
+					htonl(skb->len - udphoff));
+	} else if (!cp->app && (udph->check != 0)) {
 		/* Only port and addr are changed, do fast csum update */
 		udp_fast_csum_update(cp->af, udph, &cp->daddr, &cp->vaddr,
 				     cp->dport, cp->vport);
@@ -216,6 +243,7 @@ udp_dnat_handler(struct sk_buff *skb,
 {
 	struct udphdr *udph;
 	unsigned int udphoff;
+	int oldlen;
 
 #ifdef CONFIG_IP_VS_IPV6
 	if (cp->af == AF_INET6)
@@ -223,6 +251,7 @@ udp_dnat_handler(struct sk_buff *skb,
 	else
 #endif
 		udphoff = ip_hdrlen(skb);
+	oldlen = skb->len - udphoff;
 
 	/* csum_check requires unshared skb */
 	if (!skb_make_writable(skb, udphoff+sizeof(*udph)))
@@ -247,7 +276,11 @@ udp_dnat_handler(struct sk_buff *skb,
 	/*
 	 *	Adjust UDP checksums
 	 */
-	if (!cp->app && (udph->check != 0)) {
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		udp_partial_csum_update(cp->af, udph, &cp->daddr, &cp->vaddr,
+					htonl(oldlen),
+					htonl(skb->len - udphoff));
+	} else if (!cp->app && (udph->check != 0)) {
 		/* Only port and addr are changed, do fast csum update */
 		udp_fast_csum_update(cp->af, udph, &cp->vaddr, &cp->daddr,
 				     cp->vport, cp->dport);