1 files changed, 60 insertions, 19 deletions

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 73c6b63bba7..a52f50187b5 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -101,17 +101,17 @@ int __ip_local_out(struct sk_buff *skb)
 		       skb_dst(skb)->dev, dst_output);
 }
 
-int ip_local_out(struct sk_buff *skb)
+int ip_local_out_sk(struct sock *sk, struct sk_buff *skb)
 {
 	int err;
 
 	err = __ip_local_out(skb);
 	if (likely(err == 1))
-		err = dst_output(skb);
+		err = dst_output_sk(sk, skb);
 
 	return err;
 }
-EXPORT_SYMBOL_GPL(ip_local_out);
+EXPORT_SYMBOL_GPL(ip_local_out_sk);
 
 static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst)
 {
@@ -211,6 +211,48 @@ static inline int ip_finish_output2(struct sk_buff *skb)
 	return -EINVAL;
 }
 
+static int ip_finish_output_gso(struct sk_buff *skb)
+{
+	netdev_features_t features;
+	struct sk_buff *segs;
+	int ret = 0;
+
+	/* common case: locally created skb or seglen is <= mtu */
+	if (((IPCB(skb)->flags & IPSKB_FORWARDED) == 0) ||
+	      skb_gso_network_seglen(skb) <= ip_skb_dst_mtu(skb))
+		return ip_finish_output2(skb);
+
+	/* Slowpath -  GSO segment length is exceeding the dst MTU.
+	 *
+	 * This can happen in two cases:
+	 * 1) TCP GRO packet, DF bit not set
+	 * 2) skb arrived via virtio-net, we thus get TSO/GSO skbs directly
+	 * from host network stack.
+	 */
+	features = netif_skb_features(skb);
+	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+	if (IS_ERR(segs)) {
+		kfree_skb(skb);
+		return -ENOMEM;
+	}
+
+	consume_skb(skb);
+
+	do {
+		struct sk_buff *nskb = segs->next;
+		int err;
+
+		segs->next = NULL;
+		err = ip_fragment(segs, ip_finish_output2);
+
+		if (err && ret == 0)
+			ret = err;
+		segs = nskb;
+	} while (segs);
+
+	return ret;
+}
+
 static int ip_finish_output(struct sk_buff *skb)
 {
 #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
@@ -220,15 +262,17 @@ static int ip_finish_output(struct sk_buff *skb)
 		return dst_output(skb);
 	}
 #endif
-	if (skb->len > ip_skb_dst_mtu(skb) && !skb_is_gso(skb))
+	if (skb_is_gso(skb))
+		return ip_finish_output_gso(skb);
+
+	if (skb->len > ip_skb_dst_mtu(skb))
 		return ip_fragment(skb, ip_finish_output2);
-	else
-		return ip_finish_output2(skb);
+
+	return ip_finish_output2(skb);
 }
 
-int ip_mc_output(struct sk_buff *skb)
+int ip_mc_output(struct sock *sk, struct sk_buff *skb)
 {
-	struct sock *sk = skb->sk;
 	struct rtable *rt = skb_rtable(skb);
 	struct net_device *dev = rt->dst.dev;
 
@@ -287,7 +331,7 @@ int ip_mc_output(struct sk_buff *skb)
 			    !(IPCB(skb)->flags & IPSKB_REROUTED));
 }
 
-int ip_output(struct sk_buff *skb)
+int ip_output(struct sock *sk, struct sk_buff *skb)
 {
 	struct net_device *dev = skb_dst(skb)->dev;
 
@@ -315,9 +359,9 @@ static void ip_copy_addrs(struct iphdr *iph, const struct flowi4 *fl4)
 	       sizeof(fl4->saddr) + sizeof(fl4->daddr));
 }
 
-int ip_queue_xmit(struct sk_buff *skb, struct flowi *fl)
+/* Note: skb->sk can be different from sk, in case of tunnels */
+int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl)
 {
-	struct sock *sk = skb->sk;
 	struct inet_sock *inet = inet_sk(sk);
 	struct ip_options_rcu *inet_opt;
 	struct flowi4 *fl4;
@@ -389,6 +433,7 @@ packet_routed:
 	ip_select_ident_more(skb, &rt->dst, sk,
 			     (skb_shinfo(skb)->gso_segs ?: 1) - 1);
 
+	/* TODO : should we use skb->sk here instead of sk ? */
 	skb->priority = sk->sk_priority;
 	skb->mark = sk->sk_mark;
 
@@ -446,7 +491,6 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 	__be16 not_last_frag;
 	struct rtable *rt = skb_rtable(skb);
 	int err = 0;
-	bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED;
 
 	dev = rt->dst.dev;
 
@@ -456,7 +500,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 
 	iph = ip_hdr(skb);
 
-	mtu = ip_dst_mtu_maybe_forward(&rt->dst, forwarding);
+	mtu = ip_skb_dst_mtu(skb);
 	if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->local_df) ||
 		     (IPCB(skb)->frag_max_size &&
 		      IPCB(skb)->frag_max_size > mtu))) {
@@ -822,8 +866,7 @@ static int __ip_append_data(struct sock *sk,
 
 	fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
 	maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
-	maxnonfragsize = (inet->pmtudisc >= IP_PMTUDISC_DO) ?
-			 mtu : 0xFFFF;
+	maxnonfragsize = ip_sk_local_df(sk) ? 0xFFFF : mtu;
 
 	if (cork->length + length > maxnonfragsize - fragheaderlen) {
 		ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
@@ -1146,8 +1189,7 @@ ssize_t	ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
 
 	fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
 	maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
-	maxnonfragsize = (inet->pmtudisc >= IP_PMTUDISC_DO) ?
-			 mtu : 0xFFFF;
+	maxnonfragsize = ip_sk_local_df(sk) ? 0xFFFF : mtu;
 
 	if (cork->length + size > maxnonfragsize - fragheaderlen) {
 		ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
@@ -1308,8 +1350,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	 * to fragment the frame generated here. No matter, what transforms
 	 * how transforms change size of the packet, it will come out.
 	 */
-	if (inet->pmtudisc < IP_PMTUDISC_DO)
-		skb->local_df = 1;
+	skb->local_df = ip_sk_local_df(sk);
 
 	/* DF bit is set when we want to see DF on outgoing frames.
 	 * If local_df is set too, we still allow to fragment this frame