1 files changed, 90 insertions, 66 deletions

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 7a1874b7b8fd..19ab78aca547 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -126,9 +126,6 @@
 static struct list_head inetsw[SOCK_MAX];
 static DEFINE_SPINLOCK(inetsw_lock);
 
-struct ipv4_config ipv4_config;
-EXPORT_SYMBOL(ipv4_config);
-
 /* New destruction routine */
 
 void inet_sock_destruct(struct sock *sk)
@@ -245,31 +242,6 @@ out:
 }
 EXPORT_SYMBOL(inet_listen);
 
-u32 inet_ehash_secret __read_mostly;
-EXPORT_SYMBOL(inet_ehash_secret);
-
-u32 ipv6_hash_secret __read_mostly;
-EXPORT_SYMBOL(ipv6_hash_secret);
-
-/*
- * inet_ehash_secret must be set exactly once, and to a non nul value
- * ipv6_hash_secret must be set exactly once.
- */
-void build_ehash_secret(void)
-{
-	u32 rnd;
-
-	do {
-		get_random_bytes(&rnd, sizeof(rnd));
-	} while (rnd == 0);
-
-	if (cmpxchg(&inet_ehash_secret, 0, rnd) == 0) {
-		get_random_bytes(&ipv6_hash_secret, sizeof(ipv6_hash_secret));
-		net_secret_init();
-	}
-}
-EXPORT_SYMBOL(build_ehash_secret);
-
 /*
  *	Create an inet socket.
  */
@@ -286,10 +258,6 @@ static int inet_create(struct net *net, struct socket *sock, int protocol,
 	int try_loading_module = 0;
 	int err;
 
-	if (unlikely(!inet_ehash_secret))
-		if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM)
-			build_ehash_secret();
-
 	sock->state = SS_UNCONNECTED;
 
 	/* Look for the requested type/protocol pair. */
@@ -371,7 +339,7 @@ lookup_protocol:
 			inet->hdrincl = 1;
 	}
 
-	if (ipv4_config.no_pmtu_disc)
+	if (net->ipv4.sysctl_ip_no_pmtu_disc)
 		inet->pmtudisc = IP_PMTUDISC_DONT;
 	else
 		inet->pmtudisc = IP_PMTUDISC_WANT;
@@ -1162,7 +1130,7 @@ static int inet_sk_reselect_saddr(struct sock *sk)
 	fl4 = &inet->cork.fl.u.ip4;
 	rt = ip_route_connect(fl4, daddr, 0, RT_CONN_FLAGS(sk),
 			      sk->sk_bound_dev_if, sk->sk_protocol,
-			      inet->inet_sport, inet->inet_dport, sk, false);
+			      inet->inet_sport, inet->inet_dport, sk);
 	if (IS_ERR(rt))
 		return PTR_ERR(rt);
 
@@ -1256,36 +1224,36 @@ static int inet_gso_send_check(struct sk_buff *skb)
 	if (ihl < sizeof(*iph))
 		goto out;
 
+	proto = iph->protocol;
+
+	/* Warning: after this point, iph might be no longer valid */
 	if (unlikely(!pskb_may_pull(skb, ihl)))
 		goto out;
-
 	__skb_pull(skb, ihl);
+
 	skb_reset_transport_header(skb);
-	iph = ip_hdr(skb);
-	proto = iph->protocol;
 	err = -EPROTONOSUPPORT;
 
-	rcu_read_lock();
 	ops = rcu_dereference(inet_offloads[proto]);
 	if (likely(ops && ops->callbacks.gso_send_check))
 		err = ops->callbacks.gso_send_check(skb);
-	rcu_read_unlock();
 
 out:
 	return err;
 }
 
 static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
-	netdev_features_t features)
+					netdev_features_t features)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	const struct net_offload *ops;
+	unsigned int offset = 0;
+	bool udpfrag, encap;
 	struct iphdr *iph;
 	int proto;
+	int nhoff;
 	int ihl;
 	int id;
-	unsigned int offset = 0;
-	bool tunnel;
 
 	if (unlikely(skb_shinfo(skb)->gso_type &
 		     ~(SKB_GSO_TCPV4 |
@@ -1293,12 +1261,16 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 		       SKB_GSO_DODGY |
 		       SKB_GSO_TCP_ECN |
 		       SKB_GSO_GRE |
+		       SKB_GSO_IPIP |
+		       SKB_GSO_SIT |
 		       SKB_GSO_TCPV6 |
 		       SKB_GSO_UDP_TUNNEL |
 		       SKB_GSO_MPLS |
 		       0)))
 		goto out;
 
+	skb_reset_network_header(skb);
+	nhoff = skb_network_header(skb) - skb_mac_header(skb);
 	if (unlikely(!pskb_may_pull(skb, sizeof(*iph))))
 		goto out;
 
@@ -1307,42 +1279,53 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 	if (ihl < sizeof(*iph))
 		goto out;
 
+	id = ntohs(iph->id);
+	proto = iph->protocol;
+
+	/* Warning: after this point, iph might be no longer valid */
 	if (unlikely(!pskb_may_pull(skb, ihl)))
 		goto out;
+	__skb_pull(skb, ihl);
 
-	tunnel = !!skb->encapsulation;
+	encap = SKB_GSO_CB(skb)->encap_level > 0;
+	if (encap)
+		features = skb->dev->hw_enc_features & netif_skb_features(skb);
+	SKB_GSO_CB(skb)->encap_level += ihl;
 
-	__skb_pull(skb, ihl);
 	skb_reset_transport_header(skb);
-	iph = ip_hdr(skb);
-	id = ntohs(iph->id);
-	proto = iph->protocol;
+
 	segs = ERR_PTR(-EPROTONOSUPPORT);
 
-	rcu_read_lock();
+	if (skb->encapsulation &&
+	    skb_shinfo(skb)->gso_type & (SKB_GSO_SIT|SKB_GSO_IPIP))
+		udpfrag = proto == IPPROTO_UDP && encap;
+	else
+		udpfrag = proto == IPPROTO_UDP && !skb->encapsulation;
+
 	ops = rcu_dereference(inet_offloads[proto]);
 	if (likely(ops && ops->callbacks.gso_segment))
 		segs = ops->callbacks.gso_segment(skb, features);
-	rcu_read_unlock();
 
 	if (IS_ERR_OR_NULL(segs))
 		goto out;
 
 	skb = segs;
 	do {
-		iph = ip_hdr(skb);
-		if (!tunnel && proto == IPPROTO_UDP) {
+		iph = (struct iphdr *)(skb_mac_header(skb) + nhoff);
+		if (udpfrag) {
 			iph->id = htons(id);
 			iph->frag_off = htons(offset >> 3);
 			if (skb->next != NULL)
 				iph->frag_off |= htons(IP_MF);
-			offset += (skb->len - skb->mac_len - iph->ihl * 4);
-		} else  {
+			offset += skb->len - nhoff - ihl;
+		} else {
 			iph->id = htons(id++);
 		}
-		iph->tot_len = htons(skb->len - skb->mac_len);
-		iph->check = 0;
-		iph->check = ip_fast_csum(skb_network_header(skb), iph->ihl);
+		iph->tot_len = htons(skb->len - nhoff);
+		ip_send_check(iph);
+		if (encap)
+			skb_reset_inner_headers(skb);
+		skb->network_header = (u8 *)iph - skb->head;
 	} while ((skb = skb->next));
 
 out:
@@ -1394,8 +1377,12 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
 		if (!NAPI_GRO_CB(p)->same_flow)
 			continue;
 
-		iph2 = ip_hdr(p);
-
+		iph2 = (struct iphdr *)(p->data + off);
+		/* The above works because, with the exception of the top
+		 * (inner most) layer, we only aggregate pkts with the same
+		 * hdr length so all the hdrs we'll need to verify will start
+		 * at the same offset.
+		 */
 		if ((iph->protocol ^ iph2->protocol) |
 		    ((__force u32)iph->saddr ^ (__force u32)iph2->saddr) |
 		    ((__force u32)iph->daddr ^ (__force u32)iph2->daddr)) {
@@ -1407,13 +1394,24 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
 		NAPI_GRO_CB(p)->flush |=
 			(iph->ttl ^ iph2->ttl) |
 			(iph->tos ^ iph2->tos) |
-			(__force int)((iph->frag_off ^ iph2->frag_off) & htons(IP_DF)) |
-			((u16)(ntohs(iph2->id) + NAPI_GRO_CB(p)->count) ^ id);
+			((iph->frag_off ^ iph2->frag_off) & htons(IP_DF));
 
+		/* Save the IP ID check to be included later when we get to
+		 * the transport layer so only the inner most IP ID is checked.
+		 * This is because some GSO/TSO implementations do not
+		 * correctly increment the IP ID for the outer hdrs.
+		 */
+		NAPI_GRO_CB(p)->flush_id =
+			    ((u16)(ntohs(iph2->id) + NAPI_GRO_CB(p)->count) ^ id);
 		NAPI_GRO_CB(p)->flush |= flush;
 	}
 
 	NAPI_GRO_CB(skb)->flush |= flush;
+	skb_set_network_header(skb, off);
+	/* The above will be needed by the transport layer if there is one
+	 * immediately following this IP hdr.
+	 */
+
 	skb_gro_pull(skb, sizeof(*iph));
 	skb_set_transport_header(skb, skb_gro_offset(skb));
 
@@ -1428,10 +1426,10 @@ out:
 	return pp;
 }
 
-static int inet_gro_complete(struct sk_buff *skb)
+static int inet_gro_complete(struct sk_buff *skb, int nhoff)
 {
-	__be16 newlen = htons(skb->len - skb_network_offset(skb));
-	struct iphdr *iph = ip_hdr(skb);
+	__be16 newlen = htons(skb->len - nhoff);
+	struct iphdr *iph = (struct iphdr *)(skb->data + nhoff);
 	const struct net_offload *ops;
 	int proto = iph->protocol;
 	int err = -ENOSYS;
@@ -1444,7 +1442,11 @@ static int inet_gro_complete(struct sk_buff *skb)
 	if (WARN_ON(!ops || !ops->callbacks.gro_complete))
 		goto out_unlock;
 
-	err = ops->callbacks.gro_complete(skb);
+	/* Only need to add sizeof(*iph) to get to the next hdr below
+	 * because any hdr with option will have been flushed in
+	 * inet_gro_receive().
+	 */
+	err = ops->callbacks.gro_complete(skb, nhoff + sizeof(*iph));
 
 out_unlock:
 	rcu_read_unlock();
@@ -1520,6 +1522,7 @@ int snmp_mib_init(void __percpu *ptr[2], size_t mibsize, size_t align)
 	ptr[0] = __alloc_percpu(mibsize, align);
 	if (!ptr[0])
 		return -ENOMEM;
+
 #if SNMP_ARRAY_SZ == 2
 	ptr[1] = __alloc_percpu(mibsize, align);
 	if (!ptr[1]) {
@@ -1545,9 +1548,11 @@ static const struct net_protocol tcp_protocol = {
 	.err_handler	=	tcp_v4_err,
 	.no_policy	=	1,
 	.netns_ok	=	1,
+	.icmp_strict_tag_validation = 1,
 };
 
 static const struct net_protocol udp_protocol = {
+	.early_demux =	udp_v4_early_demux,
 	.handler =	udp_rcv,
 	.err_handler =	udp_err,
 	.no_policy =	1,
@@ -1563,6 +1568,8 @@ static const struct net_protocol icmp_protocol = {
 
 static __net_init int ipv4_mib_init_net(struct net *net)
 {
+	int i;
+
 	if (snmp_mib_init((void __percpu **)net->mib.tcp_statistics,
 			  sizeof(struct tcp_mib),
 			  __alignof__(struct tcp_mib)) < 0)
@@ -1571,6 +1578,17 @@ static __net_init int ipv4_mib_init_net(struct net *net)
 			  sizeof(struct ipstats_mib),
 			  __alignof__(struct ipstats_mib)) < 0)
 		goto err_ip_mib;
+
+	for_each_possible_cpu(i) {
+		struct ipstats_mib *af_inet_stats;
+		af_inet_stats = per_cpu_ptr(net->mib.ip_statistics[0], i);
+		u64_stats_init(&af_inet_stats->syncp);
+#if SNMP_ARRAY_SZ == 2
+		af_inet_stats = per_cpu_ptr(net->mib.ip_statistics[1], i);
+		u64_stats_init(&af_inet_stats->syncp);
+#endif
+	}
+
 	if (snmp_mib_init((void __percpu **)net->mib.net_statistics,
 			  sizeof(struct linux_mib),
 			  __alignof__(struct linux_mib)) < 0)
@@ -1648,6 +1666,13 @@ static struct packet_offload ip_packet_offload __read_mostly = {
 	},
 };
 
+static const struct net_offload ipip_offload = {
+	.callbacks = {
+		.gso_send_check = inet_gso_send_check,
+		.gso_segment	= inet_gso_segment,
+	},
+};
+
 static int __init ipv4_offload_init(void)
 {
 	/*
@@ -1659,6 +1684,7 @@ static int __init ipv4_offload_init(void)
 		pr_crit("%s: Cannot add TCP protocol offload\n", __func__);
 
 	dev_add_offload(&ip_packet_offload);
+	inet_add_offload(&ipip_offload, IPPROTO_IPIP);
 	return 0;
 }
 
@@ -1707,8 +1733,6 @@ static int __init inet_init(void)
 	ip_static_sysctl_init();
 #endif
 
-	tcp_prot.sysctl_mem = init_net.ipv4.sysctl_tcp_mem;
-
 	/*
 	 *	Add all the base protocols.
 	 */