gro: Avoid copying headers of unmerged packets

Unfortunately simplicity isn't always the best.  The fraginfo
interface turned out to be suboptimal.  The problem was quite
obvious.  For every packet, we have to copy the headers from
the frags structure into skb->head, even though for 99% of the
packets this part is immediately thrown away after the merge.

LRO didn't have this problem because it directly read the headers
from the frags structure.

This patch attempts to address this by creating an interface
that allows GRO to access the headers in the first frag without
having to copy it.  Because all drivers that use frags place the
headers in the first frag this optimisation should be enough.

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

8 files changed, 111 insertions, 44 deletions

diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index 2eb057a..378fa69 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -98,6 +98,8 @@ drop:
 int vlan_gro_receive(struct napi_struct *napi, struct vlan_group *grp,
 		     unsigned int vlan_tci, struct sk_buff *skb)
 {
+	skb_gro_reset_offset(skb);
+
 	return napi_skb_finish(vlan_gro_common(napi, grp, vlan_tci, skb), skb);
 }
 EXPORT_SYMBOL(vlan_gro_receive);
diff --git a/net/core/dev.c b/net/core/dev.c
index cd23ae1..df406dc 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -215,6 +215,13 @@ static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex)
 	return &net->dev_index_head[ifindex & ((1 << NETDEV_HASHBITS) - 1)];
 }
 
+static inline void *skb_gro_mac_header(struct sk_buff *skb)
+{
+	return skb_headlen(skb) ? skb_mac_header(skb) :
+	       page_address(skb_shinfo(skb)->frags[0].page) +
+	       skb_shinfo(skb)->frags[0].page_offset;
+}
+
 /* Device list insertion */
 static int list_netdevice(struct net_device *dev)
 {
@@ -2350,7 +2357,6 @@ static int napi_gro_complete(struct sk_buff *skb)
 
 out:
 	skb_shinfo(skb)->gso_size = 0;
-	__skb_push(skb, -skb_network_offset(skb));
 	return netif_receive_skb(skb);
 }
 
@@ -2368,6 +2374,25 @@ void napi_gro_flush(struct napi_struct *napi)
 }
 EXPORT_SYMBOL(napi_gro_flush);
 
+void *skb_gro_header(struct sk_buff *skb, unsigned int hlen)
+{
+	unsigned int offset = skb_gro_offset(skb);
+
+	hlen += offset;
+	if (hlen <= skb_headlen(skb))
+		return skb->data + offset;
+
+	if (unlikely(!skb_shinfo(skb)->nr_frags ||
+		     skb_shinfo(skb)->frags[0].size <=
+		     hlen - skb_headlen(skb) ||
+		     PageHighMem(skb_shinfo(skb)->frags[0].page)))
+		return pskb_may_pull(skb, hlen) ? skb->data + offset : NULL;
+
+	return page_address(skb_shinfo(skb)->frags[0].page) +
+	       skb_shinfo(skb)->frags[0].page_offset + offset;
+}
+EXPORT_SYMBOL(skb_gro_header);
+
 int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
 	struct sk_buff **pp = NULL;
@@ -2388,11 +2413,13 @@ int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 	rcu_read_lock();
 	list_for_each_entry_rcu(ptype, head, list) {
 		struct sk_buff *p;
+		void *mac;
 
 		if (ptype->type != type || ptype->dev || !ptype->gro_receive)
 			continue;
 
-		skb_reset_network_header(skb);
+		skb_set_network_header(skb, skb_gro_offset(skb));
+		mac = skb_gro_mac_header(skb);
 		mac_len = skb->network_header - skb->mac_header;
 		skb->mac_len = mac_len;
 		NAPI_GRO_CB(skb)->same_flow = 0;
@@ -2406,8 +2433,7 @@ int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 				continue;
 
 			if (p->mac_len != mac_len ||
-			    memcmp(skb_mac_header(p), skb_mac_header(skb),
-				   mac_len))
+			    memcmp(skb_mac_header(p), mac, mac_len))
 				NAPI_GRO_CB(p)->same_flow = 0;
 		}
 
@@ -2434,13 +2460,11 @@ int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 	if (same_flow)
 		goto ok;
 
-	if (NAPI_GRO_CB(skb)->flush || count >= MAX_GRO_SKBS) {
-		__skb_push(skb, -skb_network_offset(skb));
+	if (NAPI_GRO_CB(skb)->flush || count >= MAX_GRO_SKBS)
 		goto normal;
-	}
 
 	NAPI_GRO_CB(skb)->count = 1;
-	skb_shinfo(skb)->gso_size = skb->len;
+	skb_shinfo(skb)->gso_size = skb_gro_len(skb);
 	skb->next = napi->gro_list;
 	napi->gro_list = skb;
 	ret = GRO_HELD;
@@ -2488,6 +2512,8 @@ EXPORT_SYMBOL(napi_skb_finish);
 
 int napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
+	skb_gro_reset_offset(skb);
+
 	return napi_skb_finish(__napi_gro_receive(napi, skb), skb);
 }
 EXPORT_SYMBOL(napi_gro_receive);
@@ -2506,6 +2532,7 @@ struct sk_buff *napi_fraginfo_skb(struct napi_struct *napi,
 {
 	struct net_device *dev = napi->dev;
 	struct sk_buff *skb = napi->skb;
+	struct ethhdr *eth;
 
 	napi->skb = NULL;
 
@@ -2525,13 +2552,23 @@ struct sk_buff *napi_fraginfo_skb(struct napi_struct *napi,
 	skb->len += info->len;
 	skb->truesize += info->len;
 
-	if (!pskb_may_pull(skb, ETH_HLEN)) {
+	skb_reset_mac_header(skb);
+	skb_gro_reset_offset(skb);
+
+	eth = skb_gro_header(skb, sizeof(*eth));
+	if (!eth) {
 		napi_reuse_skb(napi, skb);
 		skb = NULL;
 		goto out;
 	}
 
-	skb->protocol = eth_type_trans(skb, dev);
+	skb_gro_pull(skb, sizeof(*eth));
+
+	/*
+	 * This works because the only protocols we care about don't require
+	 * special handling.  We'll fix it up properly at the end.
+	 */
+	skb->protocol = eth->h_proto;
 
 	skb->ip_summed = info->ip_summed;
 	skb->csum = info->csum;
@@ -2544,10 +2581,21 @@ EXPORT_SYMBOL(napi_fraginfo_skb);
 int napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, int ret)
 {
 	int err = NET_RX_SUCCESS;
+	int may;
 
 	switch (ret) {
 	case GRO_NORMAL:
-		return netif_receive_skb(skb);
+	case GRO_HELD:
+		may = pskb_may_pull(skb, skb_gro_offset(skb));
+		BUG_ON(!may);
+
+		skb->protocol = eth_type_trans(skb, napi->dev);
+
+		if (ret == GRO_NORMAL)
+			return netif_receive_skb(skb);
+
+		skb_gro_pull(skb, -ETH_HLEN);
+		break;
 
 	case GRO_DROP:
 		err = NET_RX_DROP;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 2e5f2ca..f9f4065 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2584,17 +2584,21 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 	struct sk_buff *p = *head;
 	struct sk_buff *nskb;
 	unsigned int headroom;
-	unsigned int hlen = p->data - skb_mac_header(p);
-	unsigned int len = skb->len;
+	unsigned int len = skb_gro_len(skb);
 
-	if (hlen + p->len + len >= 65536)
+	if (p->len + len >= 65536)
 		return -E2BIG;
 
 	if (skb_shinfo(p)->frag_list)
 		goto merge;
-	else if (!skb_headlen(p) && !skb_headlen(skb) &&
-		 skb_shinfo(p)->nr_frags + skb_shinfo(skb)->nr_frags <
+	else if (skb_headlen(skb) <= skb_gro_offset(skb) &&
+		 skb_shinfo(p)->nr_frags + skb_shinfo(skb)->nr_frags <=
 		 MAX_SKB_FRAGS) {
+		skb_shinfo(skb)->frags[0].page_offset +=
+			skb_gro_offset(skb) - skb_headlen(skb);
+		skb_shinfo(skb)->frags[0].size -=
+			skb_gro_offset(skb) - skb_headlen(skb);
+
 		memcpy(skb_shinfo(p)->frags + skb_shinfo(p)->nr_frags,
 		       skb_shinfo(skb)->frags,
 		       skb_shinfo(skb)->nr_frags * sizeof(skb_frag_t));
@@ -2611,7 +2615,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 	}
 
 	headroom = skb_headroom(p);
-	nskb = netdev_alloc_skb(p->dev, headroom);
+	nskb = netdev_alloc_skb(p->dev, headroom + skb_gro_offset(p));
 	if (unlikely(!nskb))
 		return -ENOMEM;
 
@@ -2619,12 +2623,15 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 	nskb->mac_len = p->mac_len;
 
 	skb_reserve(nskb, headroom);
+	__skb_put(nskb, skb_gro_offset(p));
 
-	skb_set_mac_header(nskb, -hlen);
+	skb_set_mac_header(nskb, skb_mac_header(p) - p->data);
 	skb_set_network_header(nskb, skb_network_offset(p));
 	skb_set_transport_header(nskb, skb_transport_offset(p));
 
-	memcpy(skb_mac_header(nskb), skb_mac_header(p), hlen);
+	__skb_pull(p, skb_gro_offset(p));
+	memcpy(skb_mac_header(nskb), skb_mac_header(p),
+	       p->data - skb_mac_header(p));
 
 	*NAPI_GRO_CB(nskb) = *NAPI_GRO_CB(p);
 	skb_shinfo(nskb)->frag_list = p;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 743f554..d6770f2 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1253,10 +1253,10 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
 	int proto;
 	int id;
 
-	if (unlikely(!pskb_may_pull(skb, sizeof(*iph))))
+	iph = skb_gro_header(skb, sizeof(*iph));
+	if (unlikely(!iph))
 		goto out;
 
-	iph = ip_hdr(skb);
 	proto = iph->protocol & (MAX_INET_PROTOS - 1);
 
 	rcu_read_lock();
@@ -1270,7 +1270,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
 	if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
 		goto out_unlock;
 
-	flush = ntohs(iph->tot_len) != skb->len ||
+	flush = ntohs(iph->tot_len) != skb_gro_len(skb) ||
 		iph->frag_off != htons(IP_DF);
 	id = ntohs(iph->id);
 
@@ -1298,8 +1298,8 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
 	}
 
 	NAPI_GRO_CB(skb)->flush |= flush;
-	__skb_pull(skb, sizeof(*iph));
-	skb_reset_transport_header(skb);
+	skb_gro_pull(skb, sizeof(*iph));
+	skb_set_transport_header(skb, skb_gro_offset(skb));
 
 	pp = ops->gro_receive(head, skb);
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 0cd71b8..1cd6082 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2481,19 +2481,19 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 	unsigned int mss = 1;
 	int flush = 1;
 
-	if (!pskb_may_pull(skb, sizeof(*th)))
+	th = skb_gro_header(skb, sizeof(*th));
+	if (unlikely(!th))
 		goto out;
 
-	th = tcp_hdr(skb);
 	thlen = th->doff * 4;
 	if (thlen < sizeof(*th))
 		goto out;
 
-	if (!pskb_may_pull(skb, thlen))
+	th = skb_gro_header(skb, thlen);
+	if (unlikely(!th))
 		goto out;
 
-	th = tcp_hdr(skb);
-	__skb_pull(skb, thlen);
+	skb_gro_pull(skb, thlen);
 
 	flags = tcp_flag_word(th);
 
@@ -2521,10 +2521,10 @@ found:
 	flush |= th->ack_seq != th2->ack_seq || th->window != th2->window;
 	flush |= memcmp(th + 1, th2 + 1, thlen - sizeof(*th));
 
-	total = p->len;
+	total = skb_gro_len(p);
 	mss = skb_shinfo(p)->gso_size;
 
-	flush |= skb->len > mss || skb->len <= 0;
+	flush |= skb_gro_len(skb) > mss || !skb_gro_len(skb);
 	flush |= ntohl(th2->seq) + total != ntohl(th->seq);
 
 	if (flush || skb_gro_receive(head, skb)) {
@@ -2537,7 +2537,7 @@ found:
 	tcp_flag_word(th2) |= flags & (TCP_FLAG_FIN | TCP_FLAG_PSH);
 
 out_check_final:
-	flush = skb->len < mss;
+	flush = skb_gro_len(skb) < mss;
 	flush |= flags & (TCP_FLAG_URG | TCP_FLAG_PSH | TCP_FLAG_RST |
 			  TCP_FLAG_SYN | TCP_FLAG_FIN);
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 19d7b42..f6b962f 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2355,7 +2355,7 @@ struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 
 	switch (skb->ip_summed) {
 	case CHECKSUM_COMPLETE:
-		if (!tcp_v4_check(skb->len, iph->saddr, iph->daddr,
+		if (!tcp_v4_check(skb_gro_len(skb), iph->saddr, iph->daddr,
 				  skb->csum)) {
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 			break;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index c802bc1..bd91ead 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -799,24 +799,34 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 	int proto;
 	__wsum csum;
 
-	if (unlikely(!pskb_may_pull(skb, sizeof(*iph))))
+	iph = skb_gro_header(skb, sizeof(*iph));
+	if (unlikely(!iph))
 		goto out;
 
-	iph = ipv6_hdr(skb);
-	__skb_pull(skb, sizeof(*iph));
+	skb_gro_pull(skb, sizeof(*iph));
+	skb_set_transport_header(skb, skb_gro_offset(skb));
 
-	flush += ntohs(iph->payload_len) != skb->len;
+	flush += ntohs(iph->payload_len) != skb_gro_len(skb);
 
 	rcu_read_lock();
-	proto = ipv6_gso_pull_exthdrs(skb, iph->nexthdr);
-	iph = ipv6_hdr(skb);
-	IPV6_GRO_CB(skb)->proto = proto;
+	proto = iph->nexthdr;
 	ops = rcu_dereference(inet6_protos[proto]);
-	if (!ops || !ops->gro_receive)
-		goto out_unlock;
+	if (!ops || !ops->gro_receive) {
+		__pskb_pull(skb, skb_gro_offset(skb));
+		proto = ipv6_gso_pull_exthdrs(skb, proto);
+		skb_gro_pull(skb, -skb_transport_offset(skb));
+		skb_reset_transport_header(skb);
+		__skb_push(skb, skb_gro_offset(skb));
+
+		if (!ops || !ops->gro_receive)
+			goto out_unlock;
+
+		iph = ipv6_hdr(skb);
+	}
+
+	IPV6_GRO_CB(skb)->proto = proto;
 
 	flush--;
-	skb_reset_transport_header(skb);
 	nlen = skb_network_header_len(skb);
 
 	for (p = *head; p; p = p->next) {
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index e5b85d4..00f1269 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -948,7 +948,7 @@ struct sk_buff **tcp6_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 
 	switch (skb->ip_summed) {
 	case CHECKSUM_COMPLETE:
-		if (!tcp_v6_check(skb->len, &iph->saddr, &iph->daddr,
+		if (!tcp_v6_check(skb_gro_len(skb), &iph->saddr, &iph->daddr,
 				  skb->csum)) {
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 			break;