xen/patches/linux-2.6.16.29/net-gso-2-checksum-fix.patch

diff -pruN ../orig-linux-2.6.16.29/drivers/net/bnx2.c ./drivers/net/bnx2.c
--- ../orig-linux-2.6.16.29/drivers/net/bnx2.c	2006-09-19 13:59:20.000000000 +0100
+++ ./drivers/net/bnx2.c	2006-09-19 13:59:46.000000000 +0100
@@ -1593,7 +1593,7 @@ bnx2_tx_int(struct bnx2 *bp)
 		skb = tx_buf->skb;
 #ifdef BCM_TSO 
 		/* partial BD completions possible with TSO packets */
-		if (skb_shinfo(skb)->gso_size) {
+		if (skb_is_gso(skb)) {
 			u16 last_idx, last_ring_idx;
 
 			last_idx = sw_cons +
diff -pruN ../orig-linux-2.6.16.29/drivers/net/chelsio/sge.c ./drivers/net/chelsio/sge.c
--- ../orig-linux-2.6.16.29/drivers/net/chelsio/sge.c	2006-09-19 13:59:20.000000000 +0100
+++ ./drivers/net/chelsio/sge.c	2006-09-19 13:59:46.000000000 +0100
@@ -1419,7 +1419,7 @@ int t1_start_xmit(struct sk_buff *skb, s
 	struct cpl_tx_pkt *cpl;
 
 #ifdef NETIF_F_TSO
-	if (skb_shinfo(skb)->gso_size) {
+	if (skb_is_gso(skb)) {
 		int eth_type;
 		struct cpl_tx_pkt_lso *hdr;
 
diff -pruN ../orig-linux-2.6.16.29/drivers/net/e1000/e1000_main.c ./drivers/net/e1000/e1000_main.c
--- ../orig-linux-2.6.16.29/drivers/net/e1000/e1000_main.c	2006-09-19 13:59:20.000000000 +0100
+++ ./drivers/net/e1000/e1000_main.c	2006-09-19 13:59:46.000000000 +0100
@@ -2526,7 +2526,7 @@ e1000_tso(struct e1000_adapter *adapter,
 	uint8_t ipcss, ipcso, tucss, tucso, hdr_len;
 	int err;
 
-	if (skb_shinfo(skb)->gso_size) {
+	if (skb_is_gso(skb)) {
 		if (skb_header_cloned(skb)) {
 			err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
 			if (err)
@@ -2651,7 +2651,7 @@ e1000_tx_map(struct e1000_adapter *adapt
 		 * tso gets written back prematurely before the data is fully
 		 * DMAd to the controller */
 		if (!skb->data_len && tx_ring->last_tx_tso &&
-				!skb_shinfo(skb)->gso_size) {
+		    !skb_is_gso(skb)) {
 			tx_ring->last_tx_tso = 0;
 			size -= 4;
 		}
@@ -2934,8 +2934,7 @@ e1000_xmit_frame(struct sk_buff *skb, st
 
 #ifdef NETIF_F_TSO
 	/* Controller Erratum workaround */
-	if (!skb->data_len && tx_ring->last_tx_tso &&
-		!skb_shinfo(skb)->gso_size)
+	if (!skb->data_len && tx_ring->last_tx_tso && !skb_is_gso(skb))
 		count++;
 #endif
 
diff -pruN ../orig-linux-2.6.16.29/drivers/net/forcedeth.c ./drivers/net/forcedeth.c
--- ../orig-linux-2.6.16.29/drivers/net/forcedeth.c	2006-09-19 13:59:20.000000000 +0100
+++ ./drivers/net/forcedeth.c	2006-09-19 13:59:46.000000000 +0100
@@ -1105,7 +1105,7 @@ static int nv_start_xmit(struct sk_buff 
 	np->tx_skbuff[nr] = skb;
 
 #ifdef NETIF_F_TSO
-	if (skb_shinfo(skb)->gso_size)
+	if (skb_is_gso(skb))
 		tx_flags_extra = NV_TX2_TSO | (skb_shinfo(skb)->gso_size << NV_TX2_TSO_SHIFT);
 	else
 #endif
diff -pruN ../orig-linux-2.6.16.29/drivers/net/ixgb/ixgb_main.c ./drivers/net/ixgb/ixgb_main.c
--- ../orig-linux-2.6.16.29/drivers/net/ixgb/ixgb_main.c	2006-09-19 13:59:20.000000000 +0100
+++ ./drivers/net/ixgb/ixgb_main.c	2006-09-19 13:59:46.000000000 +0100
@@ -1163,7 +1163,7 @@ ixgb_tso(struct ixgb_adapter *adapter, s
 	uint16_t ipcse, tucse, mss;
 	int err;
 
-	if(likely(skb_shinfo(skb)->gso_size)) {
+	if (likely(skb_is_gso(skb))) {
 		if (skb_header_cloned(skb)) {
 			err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
 			if (err)
diff -pruN ../orig-linux-2.6.16.29/drivers/net/loopback.c ./drivers/net/loopback.c
--- ../orig-linux-2.6.16.29/drivers/net/loopback.c	2006-09-19 13:59:20.000000000 +0100
+++ ./drivers/net/loopback.c	2006-09-19 13:59:46.000000000 +0100
@@ -139,7 +139,7 @@ static int loopback_xmit(struct sk_buff 
 #endif
 
 #ifdef LOOPBACK_TSO
-	if (skb_shinfo(skb)->gso_size) {
+	if (skb_is_gso(skb)) {
 		BUG_ON(skb->protocol != htons(ETH_P_IP));
 		BUG_ON(skb->nh.iph->protocol != IPPROTO_TCP);
 
diff -pruN ../orig-linux-2.6.16.29/drivers/net/sky2.c ./drivers/net/sky2.c
--- ../orig-linux-2.6.16.29/drivers/net/sky2.c	2006-09-19 13:59:20.000000000 +0100
+++ ./drivers/net/sky2.c	2006-09-19 13:59:46.000000000 +0100
@@ -1125,7 +1125,7 @@ static unsigned tx_le_req(const struct s
 	count = sizeof(dma_addr_t) / sizeof(u32);
 	count += skb_shinfo(skb)->nr_frags * count;
 
-	if (skb_shinfo(skb)->gso_size)
+	if (skb_is_gso(skb))
 		++count;
 
 	if (skb->ip_summed == CHECKSUM_HW)
diff -pruN ../orig-linux-2.6.16.29/drivers/net/typhoon.c ./drivers/net/typhoon.c
--- ../orig-linux-2.6.16.29/drivers/net/typhoon.c	2006-09-19 13:59:20.000000000 +0100
+++ ./drivers/net/typhoon.c	2006-09-19 13:59:46.000000000 +0100
@@ -805,7 +805,7 @@ typhoon_start_tx(struct sk_buff *skb, st
 	 * If problems develop with TSO, check this first.
 	 */
 	numDesc = skb_shinfo(skb)->nr_frags + 1;
-	if(skb_tso_size(skb))
+	if (skb_is_gso(skb))
 		numDesc++;
 
 	/* When checking for free space in the ring, we need to also
@@ -845,7 +845,7 @@ typhoon_start_tx(struct sk_buff *skb, st
 				TYPHOON_TX_PF_VLAN_TAG_SHIFT);
 	}
 
-	if(skb_tso_size(skb)) {
+	if (skb_is_gso(skb)) {
 		first_txd->processFlags |= TYPHOON_TX_PF_TCP_SEGMENT;
 		first_txd->numDesc++;
 
diff -pruN ../orig-linux-2.6.16.29/drivers/s390/net/qeth_main.c ./drivers/s390/net/qeth_main.c
--- ../orig-linux-2.6.16.29/drivers/s390/net/qeth_main.c	2006-09-19 13:59:20.000000000 +0100
+++ ./drivers/s390/net/qeth_main.c	2006-09-19 13:59:46.000000000 +0100
@@ -4454,7 +4454,7 @@ qeth_send_packet(struct qeth_card *card,
 	queue = card->qdio.out_qs
 		[qeth_get_priority_queue(card, skb, ipv, cast_type)];
 
-	if (skb_shinfo(skb)->gso_size)
+	if (skb_is_gso(skb))
 		large_send = card->options.large_send;
 
 	/*are we able to do TSO ? If so ,prepare and send it from here */
@@ -4501,8 +4501,7 @@ qeth_send_packet(struct qeth_card *card,
 		card->stats.tx_packets++;
 		card->stats.tx_bytes += skb->len;
 #ifdef CONFIG_QETH_PERF_STATS
-		if (skb_shinfo(skb)->gso_size &&
-		   !(large_send == QETH_LARGE_SEND_NO)) {
+		if (skb_is_gso(skb) && !(large_send == QETH_LARGE_SEND_NO)) {
 			card->perf_stats.large_send_bytes += skb->len;
 			card->perf_stats.large_send_cnt++;
 		}
diff -pruN ../orig-linux-2.6.16.29/include/linux/netdevice.h ./include/linux/netdevice.h
--- ../orig-linux-2.6.16.29/include/linux/netdevice.h	2006-09-19 13:59:20.000000000 +0100
+++ ./include/linux/netdevice.h	2006-09-19 13:59:46.000000000 +0100
@@ -541,6 +541,7 @@ struct packet_type {
 					 struct net_device *);
 	struct sk_buff		*(*gso_segment)(struct sk_buff *skb,
 						int features);
+	int			(*gso_send_check)(struct sk_buff *skb);
 	void			*af_packet_priv;
 	struct list_head	list;
 };
@@ -1001,14 +1002,15 @@ extern void linkwatch_run_queue(void);
 
 static inline int skb_gso_ok(struct sk_buff *skb, int features)
 {
-	int feature = skb_shinfo(skb)->gso_size ?
-		      skb_shinfo(skb)->gso_type << NETIF_F_GSO_SHIFT : 0;
+	int feature = skb_shinfo(skb)->gso_type << NETIF_F_GSO_SHIFT;
 	return (features & feature) == feature;
 }
 
 static inline int netif_needs_gso(struct net_device *dev, struct sk_buff *skb)
 {
-	return !skb_gso_ok(skb, dev->features);
+	return skb_is_gso(skb) &&
+	       (!skb_gso_ok(skb, dev->features) ||
+		unlikely(skb->ip_summed != CHECKSUM_HW));
 }
 
 #endif /* __KERNEL__ */
diff -pruN ../orig-linux-2.6.16.29/include/linux/skbuff.h ./include/linux/skbuff.h
--- ../orig-linux-2.6.16.29/include/linux/skbuff.h	2006-09-19 13:59:20.000000000 +0100
+++ ./include/linux/skbuff.h	2006-09-19 13:59:46.000000000 +0100
@@ -1403,5 +1403,10 @@ static inline void nf_bridge_get(struct 
 static inline void nf_reset(struct sk_buff *skb) {}
 #endif /* CONFIG_NETFILTER */
 
+static inline int skb_is_gso(const struct sk_buff *skb)
+{
+	return skb_shinfo(skb)->gso_size;
+}
+
 #endif	/* __KERNEL__ */
 #endif	/* _LINUX_SKBUFF_H */
diff -pruN ../orig-linux-2.6.16.29/include/net/protocol.h ./include/net/protocol.h
--- ../orig-linux-2.6.16.29/include/net/protocol.h	2006-09-19 13:59:20.000000000 +0100
+++ ./include/net/protocol.h	2006-09-19 13:59:46.000000000 +0100
@@ -37,6 +37,7 @@
 struct net_protocol {
 	int			(*handler)(struct sk_buff *skb);
 	void			(*err_handler)(struct sk_buff *skb, u32 info);
+	int			(*gso_send_check)(struct sk_buff *skb);
 	struct sk_buff	       *(*gso_segment)(struct sk_buff *skb,
 					       int features);
 	int			no_policy;
diff -pruN ../orig-linux-2.6.16.29/include/net/tcp.h ./include/net/tcp.h
--- ../orig-linux-2.6.16.29/include/net/tcp.h	2006-09-19 13:59:20.000000000 +0100
+++ ./include/net/tcp.h	2006-09-19 13:59:46.000000000 +0100
@@ -1063,6 +1063,7 @@ extern struct request_sock_ops tcp_reque
 
 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);
 
 #ifdef CONFIG_PROC_FS
diff -pruN ../orig-linux-2.6.16.29/net/bridge/br_forward.c ./net/bridge/br_forward.c
--- ../orig-linux-2.6.16.29/net/bridge/br_forward.c	2006-09-19 13:59:20.000000000 +0100
+++ ./net/bridge/br_forward.c	2006-09-19 13:59:46.000000000 +0100
@@ -32,7 +32,7 @@ static inline int should_deliver(const s
 int br_dev_queue_push_xmit(struct sk_buff *skb)
 {
 	/* drop mtu oversized packets except tso */
-	if (skb->len > skb->dev->mtu && !skb_shinfo(skb)->gso_size)
+	if (skb->len > skb->dev->mtu && !skb_is_gso(skb))
 		kfree_skb(skb);
 	else {
 #ifdef CONFIG_BRIDGE_NETFILTER
diff -pruN ../orig-linux-2.6.16.29/net/bridge/br_netfilter.c ./net/bridge/br_netfilter.c
--- ../orig-linux-2.6.16.29/net/bridge/br_netfilter.c	2006-09-19 13:59:20.000000000 +0100
+++ ./net/bridge/br_netfilter.c	2006-09-19 13:59:46.000000000 +0100
@@ -743,7 +743,7 @@ static int br_nf_dev_queue_xmit(struct s
 {
 	if (skb->protocol == htons(ETH_P_IP) &&
 	    skb->len > skb->dev->mtu &&
-	    !skb_shinfo(skb)->gso_size)
+	    !skb_is_gso(skb))
 		return ip_fragment(skb, br_dev_queue_push_xmit);
 	else
 		return br_dev_queue_push_xmit(skb);
diff -pruN ../orig-linux-2.6.16.29/net/core/dev.c ./net/core/dev.c
--- ../orig-linux-2.6.16.29/net/core/dev.c	2006-09-19 13:59:20.000000000 +0100
+++ ./net/core/dev.c	2006-09-19 13:59:46.000000000 +0100
@@ -1083,9 +1083,17 @@ int skb_checksum_help(struct sk_buff *sk
 	unsigned int csum;
 	int ret = 0, offset = skb->h.raw - skb->data;
 
-	if (inward) {
-		skb->ip_summed = CHECKSUM_NONE;
-		goto out;
+	if (inward)
+		goto out_set_summed;
+
+	if (unlikely(skb_shinfo(skb)->gso_size)) {
+		static int warned;
+
+		WARN_ON(!warned);
+		warned = 1;
+
+		/* Let GSO fix up the checksum. */
+		goto out_set_summed;
 	}
 
 	if (skb_cloned(skb)) {
@@ -1102,6 +1110,8 @@ int skb_checksum_help(struct sk_buff *sk
 	BUG_ON(skb->csum + 2 > offset);
 
 	*(u16*)(skb->h.raw + skb->csum) = csum_fold(csum);
+
+out_set_summed:
 	skb->ip_summed = CHECKSUM_NONE;
 out:	
 	return ret;
@@ -1122,17 +1132,35 @@ struct sk_buff *skb_gso_segment(struct s
 	struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
 	struct packet_type *ptype;
 	int type = skb->protocol;
+	int err;
 
 	BUG_ON(skb_shinfo(skb)->frag_list);
-	BUG_ON(skb->ip_summed != CHECKSUM_HW);
 
 	skb->mac.raw = skb->data;
 	skb->mac_len = skb->nh.raw - skb->data;
 	__skb_pull(skb, skb->mac_len);
 
+	if (unlikely(skb->ip_summed != CHECKSUM_HW)) {
+		static int warned;
+
+		WARN_ON(!warned);
+		warned = 1;
+
+		if (skb_header_cloned(skb) &&
+		    (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))
+			return ERR_PTR(err);
+	}
+
 	rcu_read_lock();
 	list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type) & 15], list) {
 		if (ptype->type == type && !ptype->dev && ptype->gso_segment) {
+			if (unlikely(skb->ip_summed != CHECKSUM_HW)) {
+				err = ptype->gso_send_check(skb);
+				segs = ERR_PTR(err);
+				if (err || skb_gso_ok(skb, features))
+					break;
+				__skb_push(skb, skb->data - skb->nh.raw);
+			}
 			segs = ptype->gso_segment(skb, features);
 			break;
 		}
diff -pruN ../orig-linux-2.6.16.29/net/ipv4/af_inet.c ./net/ipv4/af_inet.c
--- ../orig-linux-2.6.16.29/net/ipv4/af_inet.c	2006-09-19 13:59:20.000000000 +0100
+++ ./net/ipv4/af_inet.c	2006-09-19 13:59:46.000000000 +0100
@@ -1085,6 +1085,40 @@ int inet_sk_rebuild_header(struct sock *
 
 EXPORT_SYMBOL(inet_sk_rebuild_header);
 
+static int inet_gso_send_check(struct sk_buff *skb)
+{
+	struct iphdr *iph;
+	struct net_protocol *ops;
+	int proto;
+	int ihl;
+	int err = -EINVAL;
+
+	if (unlikely(!pskb_may_pull(skb, sizeof(*iph))))
+		goto out;
+
+	iph = skb->nh.iph;
+	ihl = iph->ihl * 4;
+	if (ihl < sizeof(*iph))
+		goto out;
+
+	if (unlikely(!pskb_may_pull(skb, ihl)))
+		goto out;
+
+	skb->h.raw = __skb_pull(skb, ihl);
+	iph = skb->nh.iph;
+	proto = iph->protocol & (MAX_INET_PROTOS - 1);
+	err = -EPROTONOSUPPORT;
+
+	rcu_read_lock();
+	ops = rcu_dereference(inet_protos[proto]);
+	if (likely(ops && ops->gso_send_check))
+		err = ops->gso_send_check(skb);
+	rcu_read_unlock();
+
+out:
+	return err;
+}
+
 static struct sk_buff *inet_gso_segment(struct sk_buff *skb, int features)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
@@ -1142,6 +1176,7 @@ static struct net_protocol igmp_protocol
 static struct net_protocol tcp_protocol = {
 	.handler =	tcp_v4_rcv,
 	.err_handler =	tcp_v4_err,
+	.gso_send_check = tcp_v4_gso_send_check,
 	.gso_segment =	tcp_tso_segment,
 	.no_policy =	1,
 };
@@ -1188,6 +1223,7 @@ static int ipv4_proc_init(void);
 static struct packet_type ip_packet_type = {
 	.type = __constant_htons(ETH_P_IP),
 	.func = ip_rcv,
+	.gso_send_check = inet_gso_send_check,
 	.gso_segment = inet_gso_segment,
 };
 
diff -pruN ../orig-linux-2.6.16.29/net/ipv4/ip_output.c ./net/ipv4/ip_output.c
--- ../orig-linux-2.6.16.29/net/ipv4/ip_output.c	2006-09-19 13:59:20.000000000 +0100
+++ ./net/ipv4/ip_output.c	2006-09-19 13:59:46.000000000 +0100
@@ -210,7 +210,7 @@ static inline int ip_finish_output(struc
 		return dst_output(skb);
 	}
 #endif
-	if (skb->len > dst_mtu(skb->dst) && !skb_shinfo(skb)->gso_size)
+	if (skb->len > dst_mtu(skb->dst) && !skb_is_gso(skb))
 		return ip_fragment(skb, ip_finish_output2);
 	else
 		return ip_finish_output2(skb);
@@ -1095,7 +1095,7 @@ ssize_t	ip_append_page(struct sock *sk, 
 	while (size > 0) {
 		int i;
 
-		if (skb_shinfo(skb)->gso_size)
+		if (skb_is_gso(skb))
 			len = size;
 		else {
 
diff -pruN ../orig-linux-2.6.16.29/net/ipv4/tcp_ipv4.c ./net/ipv4/tcp_ipv4.c
--- ../orig-linux-2.6.16.29/net/ipv4/tcp_ipv4.c	2006-09-12 19:02:10.000000000 +0100
+++ ./net/ipv4/tcp_ipv4.c	2006-09-19 13:59:46.000000000 +0100
@@ -495,6 +495,24 @@ void tcp_v4_send_check(struct sock *sk, 
 	}
 }
 
+int tcp_v4_gso_send_check(struct sk_buff *skb)
+{
+	struct iphdr *iph;
+	struct tcphdr *th;
+
+	if (!pskb_may_pull(skb, sizeof(*th)))
+		return -EINVAL;
+
+	iph = skb->nh.iph;
+	th = skb->h.th;
+
+	th->check = 0;
+	th->check = ~tcp_v4_check(th, skb->len, iph->saddr, iph->daddr, 0);
+	skb->csum = offsetof(struct tcphdr, check);
+	skb->ip_summed = CHECKSUM_HW;
+	return 0;
+}
+
 /*
  *	This routine will send an RST to the other tcp.
  *
diff -pruN ../orig-linux-2.6.16.29/net/ipv4/xfrm4_output.c ./net/ipv4/xfrm4_output.c
--- ../orig-linux-2.6.16.29/net/ipv4/xfrm4_output.c	2006-09-19 13:59:20.000000000 +0100
+++ ./net/ipv4/xfrm4_output.c	2006-09-19 13:59:46.000000000 +0100
@@ -195,7 +195,7 @@ static int xfrm4_output_finish(struct sk
 	}
 #endif
 
-	if (!skb_shinfo(skb)->gso_size)
+	if (!skb_is_gso(skb))
 		return xfrm4_output_finish2(skb);
 
 	skb->protocol = htons(ETH_P_IP);
diff -pruN ../orig-linux-2.6.16.29/net/ipv6/ip6_output.c ./net/ipv6/ip6_output.c
--- ../orig-linux-2.6.16.29/net/ipv6/ip6_output.c	2006-09-19 13:59:20.000000000 +0100
+++ ./net/ipv6/ip6_output.c	2006-09-19 13:59:46.000000000 +0100
@@ -147,7 +147,7 @@ static int ip6_output2(struct sk_buff *s
 
 int ip6_output(struct sk_buff *skb)
 {
-	if ((skb->len > dst_mtu(skb->dst) && !skb_shinfo(skb)->gso_size) ||
+	if ((skb->len > dst_mtu(skb->dst) && !skb_is_gso(skb)) ||
 				dst_allfrag(skb->dst))
 		return ip6_fragment(skb, ip6_output2);
 	else
diff -pruN ../orig-linux-2.6.16.29/net/ipv6/xfrm6_output.c ./net/ipv6/xfrm6_output.c
--- ../orig-linux-2.6.16.29/net/ipv6/xfrm6_output.c	2006-09-19 13:59:20.000000000 +0100
+++ ./net/ipv6/xfrm6_output.c	2006-09-19 13:59:46.000000000 +0100
@@ -179,7 +179,7 @@ static int xfrm6_output_finish(struct sk
 {
 	struct sk_buff *segs;
 
-	if (!skb_shinfo(skb)->gso_size)
+	if (!skb_is_gso(skb))
 		return xfrm6_output_finish2(skb);
 
 	skb->protocol = htons(ETH_P_IP);