[PATCH net 09/13] ipvs: fix the checksum validations

@@ -25,7 +25,9 @@
 #include <linux/netfilter.h>		/* for union nf_inet_addr */
 #include <linux/ip.h>
 #include <linux/ipv6.h>			/* for struct ipv6hdr */
+#include <net/route.h>
 #include <net/ipv6.h>
+#include <net/ip6_fib.h>
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 #include <net/netfilter/nf_conntrack.h>
 #endif

@@ -2066,8 +2068,6 @@ void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp,
 		       struct ip_vs_conn *cp, int dir);
 #endif
 
-__sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset);
-
 static inline __wsum ip_vs_check_diff4(__be32 old, __be32 new, __wsum oldsum)
 {
 	__be32 diff[2] = { ~old, new };

@@ -2093,6 +2093,33 @@ static inline __wsum ip_vs_check_diff2(__be16 old, __be16 new, __wsum oldsum)
 	return csum_partial(diff, sizeof(diff), oldsum);
 }
 
+static inline bool ip_vs_checksum_needed(struct sk_buff *skb, int af)
+{
+	/* Checksum unnecessary or already validated? */
+	if (skb_csum_unnecessary(skb))
+		return false;
+	/* LOCAL_OUT ? */
+	if (!skb->dev || skb->dev->flags & IFF_LOOPBACK)
+		return false;
+	/* !LOCAL_IN (FORWARD) ? */
+	if (af == AF_INET6) {
+		if (!(dst_rt6_info(skb_dst(skb))->rt6i_flags & RTF_LOCAL))
+			return false;
+	} else {
+		if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL))
+			return false;
+	}
+	return true;
+}
+
+static inline bool ip_vs_checksum_common_check(struct sk_buff *skb,
+					       int offset, int proto, int af)
+{
+	if (!ip_vs_checksum_needed(skb, af))
+		return true;
+	return !nf_checksum(skb, NF_INET_LOCAL_IN, offset, proto, af);
+}
+
 /* Forget current conntrack (unconfirmed) and attach notrack entry */
 static inline void ip_vs_notrack(struct sk_buff *skb)
 {

@@ -867,7 +867,7 @@ static int sysctl_nat_icmp_send(struct netns_ipvs *ipvs) { return 0; }
 
 #endif
 
-__sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset)
+static __sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset)
 {
 	return csum_fold(skb_checksum(skb, offset, skb->len - offset, 0));
 }

@@ -1038,13 +1038,14 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
 				unsigned int offset, unsigned int ihl,
 				unsigned int hooknum)
 {
+	int iproto = af == AF_INET6 ? IPPROTO_ICMPV6 : IPPROTO_ICMP;
 	unsigned int verdict = NF_DROP;
 
 	if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)
 		goto after_nat;
 
 	/* Ensure the checksum is correct */
-	if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) {
+	if (!ip_vs_checksum_common_check(skb, ihl, iproto, af)) {
 		/* Failed checksum! */
 		IP_VS_DBG_BUF(1, "Forward ICMP: failed checksum from %s!\n",
 			      IP_VS_DBG_ADDR(af, snet));

@@ -1898,7 +1899,8 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
 	verdict = NF_DROP;
 
 	/* Ensure the checksum is correct */
-	if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) {
+	if ((IP_VS_FWD_METHOD(cp) == IP_VS_CONN_F_MASQ || tunnel) &&
+	    !ip_vs_checksum_common_check(skb, ihl, IPPROTO_ICMP, AF_INET)) {
 		/* Failed checksum! */
 		IP_VS_DBG(1, "Incoming ICMP: failed checksum from %pI4!\n",
 			  &iph->saddr);

@@ -2064,6 +2066,18 @@ static int ip_vs_in_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb,
 		goto out;
 	}
 
+	verdict = NF_DROP;
+
+	/* Ensure the checksum is correct */
+	if (IP_VS_FWD_METHOD(cp) == IP_VS_CONN_F_MASQ &&
+	    !ip_vs_checksum_common_check(skb, iph->len, IPPROTO_ICMPV6,
+					 AF_INET6)) {
+		/* Failed checksum! */
+		IP_VS_DBG(1, "Incoming ICMPv6: failed checksum from %pI6c!\n",
+			  &iph->saddr);
+		goto out;
+	}
+
 	/* do the statistics and put it back */
 	ip_vs_in_stats(cp, skb);
 

@@ -11,7 +11,7 @@
 
 static int
 sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
-		unsigned int sctphoff);
+		struct ip_vs_iphdr *iph);
 
 static int
 sctp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb,

@@ -109,7 +109,7 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
 		int ret;
 
 		/* Some checks before mangling */
-		if (!sctp_csum_check(cp->af, skb, pp, sctphoff))
+		if (!sctp_csum_check(cp->af, skb, pp, iph))
 			return 0;
 
 		/* Call application helper if needed */

@@ -157,7 +157,7 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
 		int ret;
 
 		/* Some checks before mangling */
-		if (!sctp_csum_check(cp->af, skb, pp, sctphoff))
+		if (!sctp_csum_check(cp->af, skb, pp, iph))
 			return 0;
 
 		/* Call application helper if needed */

@@ -187,19 +187,22 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
 
 static int
 sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
-		unsigned int sctphoff)
+		struct ip_vs_iphdr *iph)
 {
+	unsigned int sctphoff = iph->len;
 	struct sctphdr *sh;
 	__le32 cmp, val;
 
+	if (!ip_vs_checksum_needed(skb, af))
+		return 1;
 	sh = (struct sctphdr *)(skb->data + sctphoff);
 	cmp = sh->checksum;
 	val = sctp_compute_cksum(skb, sctphoff);
 
 	if (val != cmp) {
 		/* CRC failure, dump it. */
-		IP_VS_DBG_RL_PKT(0, af, pp, skb, 0,
-				"Failed checksum for");
+		IP_VS_DBG_RL_PKT(0, af, pp, skb, iph->off,
+				 "Failed checksum for");
 		return 0;
 	}
 	return 1;

@@ -29,7 +29,7 @@
 
 static int
 tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
-	       unsigned int tcphoff);
+	       struct ip_vs_iphdr *iph);
 
 static int
 tcp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb,

@@ -166,7 +166,7 @@ tcp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
 		int ret;
 
 		/* Some checks before mangling */
-		if (!tcp_csum_check(cp->af, skb, pp, tcphoff))
+		if (!tcp_csum_check(cp->af, skb, pp, iph))
 			return 0;
 
 		/* Call application helper if needed */

@@ -244,7 +244,7 @@ tcp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
 		int ret;
 
 		/* Some checks before mangling */
-		if (!tcp_csum_check(cp->af, skb, pp, tcphoff))
+		if (!tcp_csum_check(cp->af, skb, pp, iph))
 			return 0;
 
 		/*

@@ -302,41 +302,13 @@ tcp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
 
 static int
 tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
-	       unsigned int tcphoff)
+	       struct ip_vs_iphdr *iph)
 {
-	switch (skb->ip_summed) {
-	case CHECKSUM_NONE:
-		skb->csum = skb_checksum(skb, tcphoff, skb->len - tcphoff, 0);
-		fallthrough;
-	case CHECKSUM_COMPLETE:
-#ifdef CONFIG_IP_VS_IPV6
-		if (af == AF_INET6) {
-			if (csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
-					    &ipv6_hdr(skb)->daddr,
-					    skb->len - tcphoff,
-					    IPPROTO_TCP,
-					    skb->csum)) {
-				IP_VS_DBG_RL_PKT(0, af, pp, skb, 0,
-						 "Failed checksum for");
-				return 0;
-			}
-		} else
-#endif
-			if (csum_tcpudp_magic(ip_hdr(skb)->saddr,
-					      ip_hdr(skb)->daddr,
-					      skb->len - tcphoff,
-					      ip_hdr(skb)->protocol,
-					      skb->csum)) {
-				IP_VS_DBG_RL_PKT(0, af, pp, skb, 0,
-						 "Failed checksum for");
-				return 0;
-			}
-		break;
-	default:
-		/* No need to checksum. */
-		break;
+	if (!ip_vs_checksum_common_check(skb, iph->len, IPPROTO_TCP, af)) {
+		IP_VS_DBG_RL_PKT(0, af, pp, skb, iph->off,
+				 "Failed checksum for");
+		return 0;
 	}
-
 	return 1;
 }
 

@@ -25,7 +25,7 @@
 
 static int
 udp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
-	       unsigned int udphoff);
+	       struct ip_vs_iphdr *iph);
 
 static int
 udp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb,

@@ -155,7 +155,7 @@ udp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
 		int ret;
 
 		/* Some checks before mangling */
-		if (!udp_csum_check(cp->af, skb, pp, udphoff))
+		if (!udp_csum_check(cp->af, skb, pp, iph))
 			return 0;
 
 		/*

@@ -238,7 +238,7 @@ udp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
 		int ret;
 
 		/* Some checks before mangling */
-		if (!udp_csum_check(cp->af, skb, pp, udphoff))
+		if (!udp_csum_check(cp->af, skb, pp, iph))
 			return 0;
 
 		/*

@@ -298,48 +298,20 @@ udp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
 
 static int
 udp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
-	       unsigned int udphoff)
+	       struct ip_vs_iphdr *iph)
 {
 	struct udphdr _udph, *uh;
 
-	uh = skb_header_pointer(skb, udphoff, sizeof(_udph), &_udph);
+	uh = skb_header_pointer(skb, iph->len, sizeof(_udph), &_udph);
 	if (uh == NULL)
 		return 0;
 
-	if (uh->check != 0) {
-		switch (skb->ip_summed) {
-		case CHECKSUM_NONE:
-			skb->csum = skb_checksum(skb, udphoff,
-						 skb->len - udphoff, 0);
-			fallthrough;
-		case CHECKSUM_COMPLETE:
-#ifdef CONFIG_IP_VS_IPV6
-			if (af == AF_INET6) {
-				if (csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
-						    &ipv6_hdr(skb)->daddr,
-						    skb->len - udphoff,
-						    IPPROTO_UDP,
-						    skb->csum)) {
-					IP_VS_DBG_RL_PKT(0, af, pp, skb, 0,
-							 "Failed checksum for");
-					return 0;
-				}
-			} else
-#endif
-				if (csum_tcpudp_magic(ip_hdr(skb)->saddr,
-						      ip_hdr(skb)->daddr,
-						      skb->len - udphoff,
-						      ip_hdr(skb)->protocol,
-						      skb->csum)) {
-					IP_VS_DBG_RL_PKT(0, af, pp, skb, 0,
-							 "Failed checksum for");
-					return 0;
-				}
-			break;
-		default:
-			/* No need to checksum. */
-			break;
-		}
+	if (!uh->check)
+		return 1;
+	if (!ip_vs_checksum_common_check(skb, iph->len, IPPROTO_UDP, af)) {
+		IP_VS_DBG_RL_PKT(0, af, pp, skb, iph->off,
+				 "Failed checksum for");
+		return 0;
 	}
 	return 1;
 }