net: add support for segmenting TCP fraglist GSO packets

Preparation for adding TCP fraglist GRO support. It expects packets to be
combined in a similar way as UDP fraglist GSO packets.
For IPv4 packets, NAT is handled in the same way as UDP fraglist GSO.

Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Reviewed-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index fab0973f995bf6edf2c3821ee34b6ece8a17ab78..affd4ed28cfed9937a5bba14e33e6438c5634798 100644 (file)
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -28,6 +28,70 @@ static void tcp_gso_tstamp(struct sk_buff *skb, unsigned int ts_seq,
        }
 }
 
+static void __tcpv4_gso_segment_csum(struct sk_buff *seg,
+                                    __be32 *oldip, __be32 newip,
+                                    __be16 *oldport, __be16 newport)
+{
+       struct tcphdr *th;
+       struct iphdr *iph;
+
+       if (*oldip == newip && *oldport == newport)
+               return;
+
+       th = tcp_hdr(seg);
+       iph = ip_hdr(seg);
+
+       inet_proto_csum_replace4(&th->check, seg, *oldip, newip, true);
+       inet_proto_csum_replace2(&th->check, seg, *oldport, newport, false);
+       *oldport = newport;
+
+       csum_replace4(&iph->check, *oldip, newip);
+       *oldip = newip;
+}
+
+static struct sk_buff *__tcpv4_gso_segment_list_csum(struct sk_buff *segs)
+{
+       const struct tcphdr *th;
+       const struct iphdr *iph;
+       struct sk_buff *seg;
+       struct tcphdr *th2;
+       struct iphdr *iph2;
+
+       seg = segs;
+       th = tcp_hdr(seg);
+       iph = ip_hdr(seg);
+       th2 = tcp_hdr(seg->next);
+       iph2 = ip_hdr(seg->next);
+
+       if (!(*(const u32 *)&th->source ^ *(const u32 *)&th2->source) &&
+           iph->daddr == iph2->daddr && iph->saddr == iph2->saddr)
+               return segs;
+
+       while ((seg = seg->next)) {
+               th2 = tcp_hdr(seg);
+               iph2 = ip_hdr(seg);
+
+               __tcpv4_gso_segment_csum(seg,
+                                        &iph2->saddr, iph->saddr,
+                                        &th2->source, th->source);
+               __tcpv4_gso_segment_csum(seg,
+                                        &iph2->daddr, iph->daddr,
+                                        &th2->dest, th->dest);
+       }
+
+       return segs;
+}
+
+static struct sk_buff *__tcp4_gso_segment_list(struct sk_buff *skb,
+                                             netdev_features_t features)
+{
+       skb = skb_segment_list(skb, features, skb_mac_header_len(skb));
+       if (IS_ERR(skb))
+               return skb;
+
+       return __tcpv4_gso_segment_list_csum(skb);
+}
+
 static struct sk_buff *tcp4_gso_segment(struct sk_buff *skb,
                                        netdev_features_t features)
 {
@@ -37,6 +101,9 @@ static struct sk_buff *tcp4_gso_segment(struct sk_buff *skb,
        if (!pskb_may_pull(skb, sizeof(struct tcphdr)))
                return ERR_PTR(-EINVAL);
 
+       if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)
+               return __tcp4_gso_segment_list(skb, features);
+
        if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) {
                const struct iphdr *iph = ip_hdr(skb);
                struct tcphdr *th = tcp_hdr(skb);

diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index 4b07d1e6c952957419924c83c5d3ac0e9d0b2565..7180c30dbbeffb66b0a108f743a795986452f3a0 100644 (file)
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -40,6 +40,61 @@ INDIRECT_CALLABLE_SCOPE int tcp6_gro_complete(struct sk_buff *skb, int thoff)
        return 0;
 }
 
+static void __tcpv6_gso_segment_csum(struct sk_buff *seg,
+                                    __be16 *oldport, __be16 newport)
+{
+       struct tcphdr *th;
+
+       if (*oldport == newport)
+               return;
+
+       th = tcp_hdr(seg);
+       inet_proto_csum_replace2(&th->check, seg, *oldport, newport, false);
+       *oldport = newport;
+}
+
+static struct sk_buff *__tcpv6_gso_segment_list_csum(struct sk_buff *segs)
+{
+       const struct tcphdr *th;
+       const struct ipv6hdr *iph;
+       struct sk_buff *seg;
+       struct tcphdr *th2;
+       struct ipv6hdr *iph2;
+
+       seg = segs;
+       th = tcp_hdr(seg);
+       iph = ipv6_hdr(seg);
+       th2 = tcp_hdr(seg->next);
+       iph2 = ipv6_hdr(seg->next);
+
+       if (!(*(const u32 *)&th->source ^ *(const u32 *)&th2->source) &&
+           ipv6_addr_equal(&iph->saddr, &iph2->saddr) &&
+           ipv6_addr_equal(&iph->daddr, &iph2->daddr))
+               return segs;
+
+       while ((seg = seg->next)) {
+               th2 = tcp_hdr(seg);
+               iph2 = ipv6_hdr(seg);
+
+               iph2->saddr = iph->saddr;
+               iph2->daddr = iph->daddr;
+               __tcpv6_gso_segment_csum(seg, &th2->source, th->source);
+               __tcpv6_gso_segment_csum(seg, &th2->dest, th->dest);
+       }
+
+       return segs;
+}
+
+static struct sk_buff *__tcp6_gso_segment_list(struct sk_buff *skb,
+                                             netdev_features_t features)
+{
+       skb = skb_segment_list(skb, features, skb_mac_header_len(skb));
+       if (IS_ERR(skb))
+               return skb;
+
+       return __tcpv6_gso_segment_list_csum(skb);
+}
+
 static struct sk_buff *tcp6_gso_segment(struct sk_buff *skb,
                                        netdev_features_t features)
 {
@@ -51,6 +106,9 @@ static struct sk_buff *tcp6_gso_segment(struct sk_buff *skb,
        if (!pskb_may_pull(skb, sizeof(*th)))
                return ERR_PTR(-EINVAL);
 
+       if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)
+               return __tcp6_gso_segment_list(skb, features);
+
        if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) {
                const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
                struct tcphdr *th = tcp_hdr(skb);