tcp: Add GRO support

This patch adds the TCP-specific portion of GRO.  The criterion for
merging is extremely strict (the TCP header must match exactly apart
from the checksum) so as to allow refragmentation.  Otherwise this
is pretty much identical to LRO, except that we support the merging
of ECN packets.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/tcp.h b/include/net/tcp.h
index de1e91d..218235d 100644 (file)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1358,6 +1358,12 @@ extern void tcp_v4_destroy_sock(struct sock *sk);
 
 extern int tcp_v4_gso_send_check(struct sk_buff *skb);
 extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features);
+extern struct sk_buff **tcp_gro_receive(struct sk_buff **head,
+                                       struct sk_buff *skb);
+extern struct sk_buff **tcp4_gro_receive(struct sk_buff **head,
+                                        struct sk_buff *skb);
+extern int tcp_gro_complete(struct sk_buff *skb);
+extern int tcp4_gro_complete(struct sk_buff *skb);
 
 #ifdef CONFIG_PROC_FS
 extern int  tcp4_proc_init(void);

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index a855953..664ff0e 100644 (file)
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1410,6 +1410,8 @@ static struct net_protocol tcp_protocol = {
        .err_handler =  tcp_v4_err,
        .gso_send_check = tcp_v4_gso_send_check,
        .gso_segment =  tcp_tso_segment,
+       .gro_receive =  tcp4_gro_receive,
+       .gro_complete = tcp4_gro_complete,
        .no_policy =    1,
        .netns_ok =     1,
 };

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 0192434..1f3d529 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2465,6 +2465,106 @@ out:
 }
 EXPORT_SYMBOL(tcp_tso_segment);
 
+struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
+{
+       struct sk_buff **pp = NULL;
+       struct sk_buff *p;
+       struct tcphdr *th;
+       struct tcphdr *th2;
+       unsigned int thlen;
+       unsigned int flags;
+       unsigned int total;
+       unsigned int mss = 1;
+       int flush = 1;
+
+       if (!pskb_may_pull(skb, sizeof(*th)))
+               goto out;
+
+       th = tcp_hdr(skb);
+       thlen = th->doff * 4;
+       if (thlen < sizeof(*th))
+               goto out;
+
+       if (!pskb_may_pull(skb, thlen))
+               goto out;
+
+       th = tcp_hdr(skb);
+       __skb_pull(skb, thlen);
+
+       flags = tcp_flag_word(th);
+
+       for (; (p = *head); head = &p->next) {
+               if (!NAPI_GRO_CB(p)->same_flow)
+                       continue;
+
+               th2 = tcp_hdr(p);
+
+               if (th->source != th2->source || th->dest != th2->dest) {
+                       NAPI_GRO_CB(p)->same_flow = 0;
+                       continue;
+               }
+
+               goto found;
+       }
+
+       goto out_check_final;
+
+found:
+       flush = NAPI_GRO_CB(p)->flush;
+       flush |= flags & TCP_FLAG_CWR;
+       flush |= (flags ^ tcp_flag_word(th2)) &
+                 ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH);
+       flush |= th->ack_seq != th2->ack_seq || th->window != th2->window;
+       flush |= memcmp(th + 1, th2 + 1, thlen - sizeof(*th));
+
+       total = p->len;
+       mss = total;
+       if (skb_shinfo(p)->frag_list)
+               mss = skb_shinfo(p)->frag_list->len;
+
+       flush |= skb->len > mss || skb->len <= 0;
+       flush |= ntohl(th2->seq) + total != ntohl(th->seq);
+
+       if (flush || skb_gro_receive(head, skb)) {
+               mss = 1;
+               goto out_check_final;
+       }
+
+       p = *head;
+       th2 = tcp_hdr(p);
+       tcp_flag_word(th2) |= flags & (TCP_FLAG_FIN | TCP_FLAG_PSH);
+
+out_check_final:
+       flush = skb->len < mss;
+       flush |= flags & (TCP_FLAG_URG | TCP_FLAG_PSH | TCP_FLAG_RST |
+                         TCP_FLAG_SYN | TCP_FLAG_FIN);
+
+       if (p && (!NAPI_GRO_CB(skb)->same_flow || flush))
+               pp = head;
+
+out:
+       NAPI_GRO_CB(skb)->flush |= flush;
+
+       return pp;
+}
+
+int tcp_gro_complete(struct sk_buff *skb)
+{
+       struct tcphdr *th = tcp_hdr(skb);
+
+       skb->csum_start = skb_transport_header(skb) - skb->head;
+       skb->csum_offset = offsetof(struct tcphdr, check);
+       skb->ip_summed = CHECKSUM_PARTIAL;
+
+       skb_shinfo(skb)->gso_size = skb_shinfo(skb)->frag_list->len;
+       skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
+
+       if (th->cwr)
+               skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
+
+       return 0;
+}
+
 #ifdef CONFIG_TCP_MD5SIG
 static unsigned long tcp_md5sig_users;
 static struct tcp_md5sig_pool **tcp_md5sig_pool;

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 26b9030..1017248 100644 (file)
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2346,6 +2346,41 @@ void tcp4_proc_exit(void)
 }
 #endif /* CONFIG_PROC_FS */
 
+struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb)
+{
+       struct iphdr *iph = ip_hdr(skb);
+
+       switch (skb->ip_summed) {
+       case CHECKSUM_COMPLETE:
+               if (!tcp_v4_check(skb->len, iph->saddr, iph->daddr,
+                                 skb->csum)) {
+                       skb->ip_summed = CHECKSUM_UNNECESSARY;
+                       break;
+               }
+
+               /* fall through */
+       case CHECKSUM_NONE:
+               NAPI_GRO_CB(skb)->flush = 1;
+               return NULL;
+       }
+
+       return tcp_gro_receive(head, skb);
+}
+EXPORT_SYMBOL(tcp4_gro_receive);
+
+int tcp4_gro_complete(struct sk_buff *skb)
+{
+       struct iphdr *iph = ip_hdr(skb);
+       struct tcphdr *th = tcp_hdr(skb);
+
+       th->check = ~tcp_v4_check(skb->len - skb_transport_offset(skb),
+                                 iph->saddr, iph->daddr, 0);
+       skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
+
+       return tcp_gro_complete(skb);
+}
+EXPORT_SYMBOL(tcp4_gro_complete);
+
 struct proto tcp_prot = {
        .name                   = "TCP",
        .owner                  = THIS_MODULE,