1 files changed, 104 insertions, 47 deletions

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 9ee17e3d11c..8d3b6b0e985 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)
 {
@@ -148,7 +148,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
 	iph->daddr    = (opt && opt->opt.srr ? opt->opt.faddr : daddr);
 	iph->saddr    = saddr;
 	iph->protocol = sk->sk_protocol;
-	ip_select_ident(iph, &rt->dst, sk);
+	ip_select_ident(skb, sk);
 
 	if (opt && opt->opt.optlen) {
 		iph->ihl += opt->opt.optlen>>2;
@@ -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;
@@ -371,7 +415,7 @@ packet_routed:
 	skb_reset_network_header(skb);
 	iph = ip_hdr(skb);
 	*((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (inet->tos & 0xff));
-	if (ip_dont_fragment(sk, &rt->dst) && !skb->local_df)
+	if (ip_dont_fragment(sk, &rt->dst) && !skb->ignore_df)
 		iph->frag_off = htons(IP_DF);
 	else
 		iph->frag_off = 0;
@@ -386,9 +430,9 @@ packet_routed:
 		ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0);
 	}
 
-	ip_select_ident_more(iph, &rt->dst, sk,
-			     (skb_shinfo(skb)->gso_segs ?: 1) - 1);
+	ip_select_ident_segs(skb, sk, skb_shinfo(skb)->gso_segs ?: 1);
 
+	/* TODO : should we use skb->sk here instead of sk ? */
 	skb->priority = sk->sk_priority;
 	skb->mark = sk->sk_mark;
 
@@ -422,9 +466,6 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	to->tc_index = from->tc_index;
 #endif
 	nf_copy(to, from);
-#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
-	to->nf_trace = from->nf_trace;
-#endif
 #if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
 	to->ipvs_property = from->ipvs_property;
 #endif
@@ -458,12 +499,13 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 
 	iph = ip_hdr(skb);
 
-	if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->local_df) ||
+	mtu = ip_skb_dst_mtu(skb);
+	if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) ||
 		     (IPCB(skb)->frag_max_size &&
-		      IPCB(skb)->frag_max_size > dst_mtu(&rt->dst)))) {
+		      IPCB(skb)->frag_max_size > mtu))) {
 		IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
 		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
-			  htonl(ip_skb_dst_mtu(skb)));
+			  htonl(mtu));
 		kfree_skb(skb);
 		return -EMSGSIZE;
 	}
@@ -473,7 +515,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 	 */
 
 	hlen = iph->ihl * 4;
-	mtu = dst_mtu(&rt->dst) - hlen;	/* Size of data space */
+	mtu = mtu - hlen;	/* Size of data space */
 #ifdef CONFIG_BRIDGE_NETFILTER
 	if (skb->nf_bridge)
 		mtu -= nf_bridge_mtu_reduction(skb);
@@ -772,15 +814,20 @@ static inline int ip_ufo_append_data(struct sock *sk,
 		/* initialize protocol header pointer */
 		skb->transport_header = skb->network_header + fragheaderlen;
 
-		skb->ip_summed = CHECKSUM_PARTIAL;
 		skb->csum = 0;
 
-		/* specify the length of each IP datagram fragment */
-		skb_shinfo(skb)->gso_size = maxfraglen - fragheaderlen;
-		skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
+
 		__skb_queue_tail(queue, skb);
+	} else if (skb_is_gso(skb)) {
+		goto append;
 	}
 
+	skb->ip_summed = CHECKSUM_PARTIAL;
+	/* specify the length of each IP datagram fragment */
+	skb_shinfo(skb)->gso_size = maxfraglen - fragheaderlen;
+	skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
+
+append:
 	return skb_append_datato_frags(sk, skb, getfrag, from,
 				       (length - transhdrlen));
 }
@@ -805,7 +852,7 @@ static int __ip_append_data(struct sock *sk,
 	int copy;
 	int err;
 	int offset = 0;
-	unsigned int maxfraglen, fragheaderlen;
+	unsigned int maxfraglen, fragheaderlen, maxnonfragsize;
 	int csummode = CHECKSUM_NONE;
 	struct rtable *rt = (struct rtable *)cork->dst;
 
@@ -818,10 +865,11 @@ static int __ip_append_data(struct sock *sk,
 
 	fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
 	maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
+	maxnonfragsize = ip_sk_ignore_df(sk) ? 0xFFFF : mtu;
 
-	if (cork->length + length > 0xFFFF - fragheaderlen) {
+	if (cork->length + length > maxnonfragsize - fragheaderlen) {
 		ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
-			       mtu-exthdrlen);
+			       mtu - (opt ? opt->optlen : 0));
 		return -EMSGSIZE;
 	}
 
@@ -1030,7 +1078,6 @@ error:
 static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 			 struct ipcm_cookie *ipc, struct rtable **rtp)
 {
-	struct inet_sock *inet = inet_sk(sk);
 	struct ip_options_rcu *opt;
 	struct rtable *rt;
 
@@ -1056,10 +1103,13 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 	 * We steal reference to this route, caller should not release it
 	 */
 	*rtp = NULL;
-	cork->fragsize = inet->pmtudisc == IP_PMTUDISC_PROBE ?
-			 rt->dst.dev->mtu : dst_mtu(&rt->dst);
+	cork->fragsize = ip_sk_use_pmtu(sk) ?
+			 dst_mtu(&rt->dst) : rt->dst.dev->mtu;
 	cork->dst = &rt->dst;
 	cork->length = 0;
+	cork->ttl = ipc->ttl;
+	cork->tos = ipc->tos;
+	cork->priority = ipc->priority;
 	cork->tx_flags = ipc->tx_flags;
 
 	return 0;
@@ -1114,7 +1164,7 @@ ssize_t	ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
 	int mtu;
 	int len;
 	int err;
-	unsigned int maxfraglen, fragheaderlen, fraggap;
+	unsigned int maxfraglen, fragheaderlen, fraggap, maxnonfragsize;
 
 	if (inet->hdrincl)
 		return -EPERM;
@@ -1138,9 +1188,11 @@ 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 = ip_sk_ignore_df(sk) ? 0xFFFF : mtu;
 
-	if (cork->length + size > 0xFFFF - fragheaderlen) {
-		ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, mtu);
+	if (cork->length + size > maxnonfragsize - fragheaderlen) {
+		ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
+			       mtu - (opt ? opt->optlen : 0));
 		return -EMSGSIZE;
 	}
 
@@ -1297,13 +1349,13 @@ 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->ignore_df = ip_sk_ignore_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
+	 * If ignore_df is set too, we still allow to fragment this frame
 	 * locally. */
-	if (inet->pmtudisc >= IP_PMTUDISC_DO ||
+	if (inet->pmtudisc == IP_PMTUDISC_DO ||
+	    inet->pmtudisc == IP_PMTUDISC_PROBE ||
 	    (skb->len <= dst_mtu(&rt->dst) &&
 	     ip_dont_fragment(sk, &rt->dst)))
 		df = htons(IP_DF);
@@ -1311,27 +1363,29 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	if (cork->flags & IPCORK_OPT)
 		opt = cork->opt;
 
-	if (rt->rt_type == RTN_MULTICAST)
+	if (cork->ttl != 0)
+		ttl = cork->ttl;
+	else if (rt->rt_type == RTN_MULTICAST)
 		ttl = inet->mc_ttl;
 	else
 		ttl = ip_select_ttl(inet, &rt->dst);
 
-	iph = (struct iphdr *)skb->data;
+	iph = ip_hdr(skb);
 	iph->version = 4;
 	iph->ihl = 5;
-	iph->tos = inet->tos;
+	iph->tos = (cork->tos != -1) ? cork->tos : inet->tos;
 	iph->frag_off = df;
 	iph->ttl = ttl;
 	iph->protocol = sk->sk_protocol;
 	ip_copy_addrs(iph, fl4);
-	ip_select_ident(iph, &rt->dst, sk);
+	ip_select_ident(skb, sk);
 
 	if (opt) {
 		iph->ihl += opt->optlen>>2;
 		ip_options_build(skb, opt, cork->addr, rt, 0);
 	}
 
-	skb->priority = sk->sk_priority;
+	skb->priority = (cork->tos != -1) ? cork->priority: sk->sk_priority;
 	skb->mark = sk->sk_mark;
 	/*
 	 * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec
@@ -1481,6 +1535,8 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
 	ipc.addr = daddr;
 	ipc.opt = NULL;
 	ipc.tx_flags = 0;
+	ipc.ttl = 0;
+	ipc.tos = -1;
 
 	if (replyopts.opt.opt.optlen) {
 		ipc.opt = &replyopts.opt;
@@ -1489,7 +1545,8 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
 			daddr = replyopts.opt.opt.faddr;
 	}
 
-	flowi4_init_output(&fl4, arg->bound_dev_if, 0,
+	flowi4_init_output(&fl4, arg->bound_dev_if,
+			   IP4_REPLY_MARK(net, skb->mark),
 			   RT_TOS(arg->tos),
 			   RT_SCOPE_UNIVERSE, ip_hdr(skb)->protocol,
 			   ip_reply_arg_flowi_flags(arg),
@@ -1534,7 +1591,7 @@ void __init ip_init(void)
 	ip_rt_init();
 	inet_initpeers();
 
-#if defined(CONFIG_IP_MULTICAST) && defined(CONFIG_PROC_FS)
-	igmp_mc_proc_init();
+#if defined(CONFIG_IP_MULTICAST)
+	igmp_mc_init();
 #endif
 }