1 files changed, 49 insertions, 14 deletions

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index c2380bb1fdab..a0739ef47227 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -73,6 +73,8 @@
 #include <net/icmp.h>
 #include <net/checksum.h>
 #include <net/inetpeer.h>
+#include <net/inet_ecn.h>
+#include <linux/bpf-cgroup.h>
 #include <linux/igmp.h>
 #include <linux/netfilter_ipv4.h>
 #include <linux/netfilter_bridge.h>
@@ -154,12 +156,19 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk,
 	iph->daddr    = (opt && opt->opt.srr ? opt->opt.faddr : daddr);
 	iph->saddr    = saddr;
 	iph->protocol = sk->sk_protocol;
-	if (ip_dont_fragment(sk, &rt->dst)) {
+	/* Do not bother generating IPID for small packets (eg SYNACK) */
+	if (skb->len <= IPV4_MIN_MTU || ip_dont_fragment(sk, &rt->dst)) {
 		iph->frag_off = htons(IP_DF);
 		iph->id = 0;
 	} else {
 		iph->frag_off = 0;
-		__ip_select_ident(net, iph, 1);
+		/* TCP packets here are SYNACK with fat IPv4/TCP options.
+		 * Avoid using the hashed IP ident generator.
+		 */
+		if (sk->sk_protocol == IPPROTO_TCP)
+			iph->id = (__force __be16)prandom_u32();
+		else
+			__ip_select_ident(net, iph, 1);
 	}
 
 	if (opt && opt->opt.optlen) {
@@ -270,6 +279,13 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk,
 static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	unsigned int mtu;
+	int ret;
+
+	ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb);
+	if (ret) {
+		kfree_skb(skb);
+		return ret;
+	}
 
 #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
 	/* Policy lookup after SNAT yielded a new policy */
@@ -282,12 +298,26 @@ static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *sk
 	if (skb_is_gso(skb))
 		return ip_finish_output_gso(net, sk, skb, mtu);
 
-	if (skb->len > mtu || (IPCB(skb)->flags & IPSKB_FRAG_PMTU))
+	if (skb->len > mtu || IPCB(skb)->frag_max_size)
 		return ip_fragment(net, sk, skb, mtu, ip_finish_output2);
 
 	return ip_finish_output2(net, sk, skb);
 }
 
+static int ip_mc_finish_output(struct net *net, struct sock *sk,
+			       struct sk_buff *skb)
+{
+	int ret;
+
+	ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb);
+	if (ret) {
+		kfree_skb(skb);
+		return ret;
+	}
+
+	return dev_loopback_xmit(net, sk, skb);
+}
+
 int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	struct rtable *rt = skb_rtable(skb);
@@ -325,7 +355,7 @@ int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 			if (newskb)
 				NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING,
 					net, sk, newskb, NULL, newskb->dev,
-					dev_loopback_xmit);
+					ip_mc_finish_output);
 		}
 
 		/* Multicasts with ttl 0 must not go beyond the host */
@@ -341,7 +371,7 @@ int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 		if (newskb)
 			NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING,
 				net, sk, newskb, NULL, newskb->dev,
-				dev_loopback_xmit);
+				ip_mc_finish_output);
 	}
 
 	return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING,
@@ -375,8 +405,9 @@ static void ip_copy_addrs(struct iphdr *iph, const struct flowi4 *fl4)
 {
 	BUILD_BUG_ON(offsetof(typeof(*fl4), daddr) !=
 		     offsetof(typeof(*fl4), saddr) + sizeof(fl4->saddr));
-	memcpy(&iph->saddr, &fl4->saddr,
-	       sizeof(fl4->saddr) + sizeof(fl4->daddr));
+
+	iph->saddr = fl4->saddr;
+	iph->daddr = fl4->daddr;
 }
 
 /* Note: skb->sk can be different from sk, in case of tunnels */
@@ -1145,13 +1176,17 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 	rt = *rtp;
 	if (unlikely(!rt))
 		return -EFAULT;
-	/*
-	 * We steal reference to this route, caller should not release it
-	 */
-	*rtp = NULL;
+
 	cork->fragsize = ip_sk_use_pmtu(sk) ?
-			 dst_mtu(&rt->dst) : rt->dst.dev->mtu;
+			 dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu);
+
+	if (!inetdev_valid_mtu(cork->fragsize))
+		return -ENETUNREACH;
+
 	cork->dst = &rt->dst;
+	/* We stole this route, caller should not release it. */
+	*rtp = NULL;
+
 	cork->length = 0;
 	cork->ttl = ipc->ttl;
 	cork->tos = ipc->tos;
@@ -1589,12 +1624,12 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 			   daddr, saddr,
 			   tcp_hdr(skb)->source, tcp_hdr(skb)->dest,
 			   arg->uid);
-	security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
+	security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4));
 	rt = ip_route_output_key(net, &fl4);
 	if (IS_ERR(rt))
 		return;
 
-	inet_sk(sk)->tos = arg->tos;
+	inet_sk(sk)->tos = arg->tos & ~INET_ECN_MASK;
 
 	sk->sk_priority = skb->priority;
 	sk->sk_protocol = ip_hdr(skb)->protocol;