[PATCH] netfilter: fix bad checksum on IPv6 when NAT is performed

[PATCH] netfilter: fix bad checksum on IPv6 when NAT is performed

[Maxime Bizon]

With this setup:

* non IPv6 checksumming capable network hardware
* GRO off
* IPv6 SNAT

I get this when I receive an UDPv6 reply: "<unknown>: hw csum failure"

Call trace:

* nf_ip6_checksum() calls __skb_checksum_complete()
* nf_nat_ipv6_csum_update() & nf_nat_ipv6_manip_pkt()
* __udp6_lib_rcv() => udp6_csum_init()
* __skb_checksum_validate_complete() "fastpath" fails because
  skb->csum is incorrect.
* udpv6_recvmsg() => skb_copy_and_csum_datagram_msg()

The last call computes a valid checksum despite CHECKSUM_COMPLETE and
triggers the warning.

When we perform NAT on IPv4, we also update the IPv4 checksum, so
there is no side effect on skb->csum (since the csum over a valid IPv4
header area is zero).

But IPv6 doesn't have such header checksum, so when performing NAT we need to
update skb->csum.

Signed-off-by: Maxime Bizon <mbizon@freebox.fr>
---
 net/ipv6/netfilter/nf_nat_l3proto_ipv6.c | 23 +++++++++++++++++++----
 1 file changed, 19 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
index 70fbaed..e9917d74 100644
--- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
@@ -81,6 +81,8 @@ static bool nf_nat_ipv6_manip_pkt(struct sk_buff *skb,
 				  enum nf_nat_manip_type maniptype)
 {
 	struct ipv6hdr *ipv6h;
+	const __be32 *to;
+	__be32 *from;
 	__be16 frag_off;
 	int hdroff;
 	u8 nexthdr;
@@ -100,11 +102,24 @@ static bool nf_nat_ipv6_manip_pkt(struct sk_buff *skb,
 				target, maniptype))
 		return false;
 manip_addr:
-	if (maniptype == NF_NAT_MANIP_SRC)
-		ipv6h->saddr = target->src.u3.in6;
-	else
-		ipv6h->daddr = target->dst.u3.in6;
+	if (maniptype == NF_NAT_MANIP_SRC) {
+		from = ipv6h->saddr.s6_addr32;
+		to = target->src.u3.in6.s6_addr32;
+	} else {
+		from = ipv6h->daddr.s6_addr32;
+		to = target->src.u3.in6.s6_addr32;
+	}
+
+	if (skb->ip_summed == CHECKSUM_COMPLETE) {
+		__be32 diff[] = {
+			~from[0], ~from[1], ~from[2], ~from[3],
+			to[0], to[1], to[2], to[3],
+		};
+
+		skb->csum = ~csum_partial(diff, sizeof(diff), ~skb->csum);
+	}
 
+	memcpy(from, to, sizeof (struct in6_addr));
 	return true;
 }
 
-- 
1.9.1



-- 
Maxime

[PATCH] netfilter: fix bad checksum on IPv6 when NAT is performed

[Maxime Bizon]

With this setup:

* non IPv6 checksumming capable network hardware
* GRO off
* IPv6 SNAT

I get this when I receive an UDPv6 reply: "<unknown>: hw csum failure"

Call trace:

* nf_ip6_checksum() calls __skb_checksum_complete()
* nf_nat_ipv6_csum_update() & nf_nat_ipv6_manip_pkt()
* __udp6_lib_rcv() => udp6_csum_init()
* __skb_checksum_validate_complete() "fastpath" fails because
  skb->csum is incorrect.
* udpv6_recvmsg() => skb_copy_and_csum_datagram_msg()

The last call computes a valid checksum despite CHECKSUM_COMPLETE and
triggers the warning.

When we perform NAT on IPv4, we also update the IPv4 checksum, so
there is no side effect on skb->csum (since the csum over a valid IPv4
header area is zero).

But IPv6 doesn't have such header checksum, so when performing NAT we need to
update skb->csum.

Signed-off-by: Maxime Bizon <mbizon@freebox.fr>
---
 net/ipv6/netfilter/nf_nat_l3proto_ipv6.c | 23 +++++++++++++++++++----
 1 file changed, 19 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
index 70fbaed..e9917d74 100644
--- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
@@ -81,6 +81,8 @@ static bool nf_nat_ipv6_manip_pkt(struct sk_buff *skb,
 				  enum nf_nat_manip_type maniptype)
 {
 	struct ipv6hdr *ipv6h;
+	const __be32 *to;
+	__be32 *from;
 	__be16 frag_off;
 	int hdroff;
 	u8 nexthdr;
@@ -100,11 +102,24 @@ static bool nf_nat_ipv6_manip_pkt(struct sk_buff *skb,
 				target, maniptype))
 		return false;
 manip_addr:
-	if (maniptype == NF_NAT_MANIP_SRC)
-		ipv6h->saddr = target->src.u3.in6;
-	else
-		ipv6h->daddr = target->dst.u3.in6;
+	if (maniptype == NF_NAT_MANIP_SRC) {
+		from = ipv6h->saddr.s6_addr32;
+		to = target->src.u3.in6.s6_addr32;
+	} else {
+		from = ipv6h->daddr.s6_addr32;
+		to = target->src.u3.in6.s6_addr32;
+	}
+
+	if (skb->ip_summed == CHECKSUM_COMPLETE) {
+		__be32 diff[] = {
+			~from[0], ~from[1], ~from[2], ~from[3],
+			to[0], to[1], to[2], to[3],
+		};
+
+		skb->csum = ~csum_partial(diff, sizeof(diff), ~skb->csum);
+	}
 
+	memcpy(from, to, sizeof (struct in6_addr));
 	return true;
 }
 
-- 
1.9.1




-- 
Maxime

Re: [PATCH] netfilter: fix bad checksum on IPv6 when NAT is performed

[Pablo Neira Ayuso]

On Tue, Oct 06, 2015 at 04:10:52PM +0200, Maxime Bizon wrote:
> 
> With this setup:
> 
> * non IPv6 checksumming capable network hardware
> * GRO off
> * IPv6 SNAT
> 
> I get this when I receive an UDPv6 reply: "<unknown>: hw csum failure"
> 
> Call trace:
> 
> * nf_ip6_checksum() calls __skb_checksum_complete()
> * nf_nat_ipv6_csum_update() & nf_nat_ipv6_manip_pkt()
> * __udp6_lib_rcv() => udp6_csum_init()
> * __skb_checksum_validate_complete() "fastpath" fails because
>   skb->csum is incorrect.
> * udpv6_recvmsg() => skb_copy_and_csum_datagram_msg()
> 
> The last call computes a valid checksum despite CHECKSUM_COMPLETE and
> triggers the warning.
> 
> When we perform NAT on IPv4, we also update the IPv4 checksum, so
> there is no side effect on skb->csum (since the csum over a valid IPv4
> header area is zero).
> 
> But IPv6 doesn't have such header checksum, so when performing NAT we need to
> update skb->csum.

Please, resubmit and Cc netfilter-devel@vger.kernel.org.

Thanks.

Re: [PATCH] netfilter: fix bad checksum on IPv6 when NAT is performed

[Maxime Bizon]

On Tue, 2015-10-06 at 16:23 +0200, Maxime Bizon wrote:

> +	if (maniptype == NF_NAT_MANIP_SRC) {
> +		from = ipv6h->saddr.s6_addr32;
> +		to = target->src.u3.in6.s6_addr32;
> +	} else {
> +		from = ipv6h->daddr.s6_addr32;
> +		to = target->src.u3.in6.s6_addr32;
> +	}

stupid copy & paste error here, will send v2

-- 
Maxime