From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Wed, 27 May 2009 15:31:19 +1000
Subject: [net] tcp: add GRO support
Message-id: E1M9BjT-0002CB-GA@gondolin.me.apana.org.au
O-Subject: [PATCH 14/17] tcp: Add GRO support
Bugzilla: 499347
RH-Acked-by: David Miller <davem@redhat.com>
RH-Acked-by: Neil Horman <nhorman@redhat.com>
RH-Acked-by: Thomas Graf <tgraf@redhat.com>

RHEL5 bugzilla #499347

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 7811568..4990c84 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1094,6 +1094,12 @@ extern int 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 ce3ac46..f2df5ce 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1307,6 +1307,11 @@ static struct net_protocol tcp_protocol = {
 	.no_policy =	1,
 };
 
+static struct net_gro_protocol tcp_gro_protocol = {
+	.gro_receive =	tcp4_gro_receive,
+	.gro_complete =	tcp4_gro_complete,
+};
+
 static struct net_protocol udp_protocol = {
 	.handler =	udp_rcv,
 	.err_handler =	udp_err,
@@ -1403,6 +1408,8 @@ static int __init inet_init(void)
 		printk(KERN_CRIT "inet_init: Cannot add UDP protocol\n");
 	if (inet_add_protocol(&tcp_protocol, IPPROTO_TCP) < 0)
 		printk(KERN_CRIT "inet_init: Cannot add TCP protocol\n");
+	if (inet_add_gro_protocol(&tcp_gro_protocol, IPPROTO_TCP) < 0)
+		printk(KERN_CRIT "inet_init: Cannot add TCP protocol\n");
 #ifdef CONFIG_IP_MULTICAST
 	if (inet_add_protocol(&igmp_protocol, IPPROTO_IGMP) < 0)
 		printk(KERN_CRIT "inet_init: Cannot add IGMP protocol\n");
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 567fd5d..b04bfea 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2243,6 +2243,114 @@ 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 len;
+	unsigned int thlen;
+	unsigned int flags;
+	unsigned int mss = 1;
+	unsigned int hlen;
+	unsigned int off;
+	int flush = 1;
+	int i;
+
+	off = skb_gro_offset(skb);
+	hlen = off + sizeof(*th);
+	th = skb_gro_header_fast(skb, off);
+	if (skb_gro_header_hard(skb, hlen)) {
+		th = skb_gro_header_slow(skb, hlen, off);
+		if (unlikely(!th))
+			goto out;
+	}
+
+	thlen = th->doff * 4;
+	if (thlen < sizeof(*th))
+		goto out;
+
+	hlen = off + thlen;
+	if (skb_gro_header_hard(skb, hlen)) {
+		th = skb_gro_header_slow(skb, hlen, off);
+		if (unlikely(!th))
+			goto out;
+	}
+
+	skb_gro_pull(skb, thlen);
+
+	len = skb_gro_len(skb);
+	flags = tcp_flag_word(th);
+
+	for (; (p = *head); head = &p->next) {
+		if (!NAPI_GRO_CB(p)->same_flow)
+			continue;
+
+		th2 = tcp_hdr(p);
+
+		if (*(u32 *)&th->source ^ *(u32 *)&th2->source) {
+			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;
+	for (i = sizeof(*th); i < thlen; i += 4)
+		flush |= *(u32 *)((u8 *)th + i) ^
+			 *(u32 *)((u8 *)th2 + i);
+
+	mss = skb_shinfo(p)->gso_size;
+
+	flush |= (len - 1) >= mss;
+	flush |= (ntohl(th2->seq) + skb_gro_len(p)) ^ 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 = 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;
+}
+EXPORT_SYMBOL(tcp_gro_receive);
+
+int tcp_gro_complete(struct sk_buff *skb)
+{
+	struct tcphdr *th = tcp_hdr(skb);
+
+	skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
+
+	if (th->cwr)
+		skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
+
+	return 0;
+}
+EXPORT_SYMBOL(tcp_gro_complete);
+
 extern void __skb_cb_too_small_for_tcp(int, int);
 extern struct tcp_congestion_ops tcp_reno;
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 4f58a8d..01583da 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1838,6 +1838,41 @@ 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 = skb_gro_network_header(skb);
+
+	switch (skb->ip_summed) {
+	case CHECKSUM_COMPLETE:
+		if (!tcp_v4_check(NULL, skb_gro_len(skb), 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(NULL, 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,