Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

6 files changed, 47 insertions, 10 deletions

diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index ec448b71bf9a..8956144ea65e 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -158,7 +158,13 @@ static bool is_ineligible(const struct sk_buff *skb)
 		tp = skb_header_pointer(skb,
 			ptr+offsetof(struct icmp6hdr, icmp6_type),
 			sizeof(_type), &_type);
-		if (!tp || !(*tp & ICMPV6_INFOMSG_MASK))
+
+		/* Based on RFC 8200, Section 4.5 Fragment Header, return
+		 * false if this is a fragment packet with no icmp header info.
+		 */
+		if (!tp && frag_off != 0)
+			return false;
+		else if (!tp || !(*tp & ICMPV6_INFOMSG_MASK))
 			return true;
 	}
 	return false;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index e3e7859e2ef7..74a6ea9f8862 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1270,6 +1270,8 @@ route_lookup:
 	if (max_headroom > dev->needed_headroom)
 		dev->needed_headroom = max_headroom;
 
+	skb_set_inner_ipproto(skb, proto);
+
 	err = ip6_tnl_encap(skb, t, &proto, fl6);
 	if (err)
 		return err;
@@ -1279,8 +1281,6 @@ route_lookup:
 		ipv6_push_frag_opts(skb, &opt.ops, &proto);
 	}
 
-	skb_set_inner_ipproto(skb, proto);
-
 	skb_push(skb, sizeof(struct ipv6hdr));
 	skb_reset_network_header(skb);
 	ipv6h = ipv6_hdr(skb);
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 6d0e942d082d..ab9a279dd6d4 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -20,10 +20,10 @@
 #include <net/netfilter/ipv6/nf_defrag_ipv6.h>
 #include "../bridge/br_private.h"
 
-int ip6_route_me_harder(struct net *net, struct sk_buff *skb)
+int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff *skb)
 {
 	const struct ipv6hdr *iph = ipv6_hdr(skb);
-	struct sock *sk = sk_to_full_sk(skb->sk);
+	struct sock *sk = sk_to_full_sk(sk_partial);
 	unsigned int hh_len;
 	struct dst_entry *dst;
 	int strict = (ipv6_addr_type(&iph->daddr) &
@@ -84,7 +84,7 @@ static int nf_ip6_reroute(struct sk_buff *skb,
 		if (!ipv6_addr_equal(&iph->daddr, &rt_info->daddr) ||
 		    !ipv6_addr_equal(&iph->saddr, &rt_info->saddr) ||
 		    skb->mark != rt_info->mark)
-			return ip6_route_me_harder(entry->state.net, skb);
+			return ip6_route_me_harder(entry->state.net, entry->state.sk, skb);
 	}
 	return 0;
 }
diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c
index 1a2748611e00..cee74803d7a1 100644
--- a/net/ipv6/netfilter/ip6table_mangle.c
+++ b/net/ipv6/netfilter/ip6table_mangle.c
@@ -57,7 +57,7 @@ ip6t_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state)
 	     skb->mark != mark ||
 	     ipv6_hdr(skb)->hop_limit != hop_limit ||
 	     flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) {
-		err = ip6_route_me_harder(state->net, skb);
+		err = ip6_route_me_harder(state->net, state->sk, skb);
 		if (err < 0)
 			ret = NF_DROP_ERR(err);
 	}
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 1f5d4d196dcc..c8cf1bbad74a 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -42,6 +42,8 @@
 #include <linux/skbuff.h>
 #include <linux/slab.h>
 #include <linux/export.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
 
 #include <net/sock.h>
 #include <net/snmp.h>
@@ -322,7 +324,9 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 	struct frag_queue *fq;
 	const struct ipv6hdr *hdr = ipv6_hdr(skb);
 	struct net *net = dev_net(skb_dst(skb)->dev);
-	int iif;
+	__be16 frag_off;
+	int iif, offset;
+	u8 nexthdr;
 
 	if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED)
 		goto fail_hdr;
@@ -351,6 +355,33 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 		return 1;
 	}
 
+	/* RFC 8200, Section 4.5 Fragment Header:
+	 * If the first fragment does not include all headers through an
+	 * Upper-Layer header, then that fragment should be discarded and
+	 * an ICMP Parameter Problem, Code 3, message should be sent to
+	 * the source of the fragment, with the Pointer field set to zero.
+	 */
+	nexthdr = hdr->nexthdr;
+	offset = ipv6_skip_exthdr(skb, skb_transport_offset(skb), &nexthdr, &frag_off);
+	if (offset >= 0) {
+		/* Check some common protocols' header */
+		if (nexthdr == IPPROTO_TCP)
+			offset += sizeof(struct tcphdr);
+		else if (nexthdr == IPPROTO_UDP)
+			offset += sizeof(struct udphdr);
+		else if (nexthdr == IPPROTO_ICMPV6)
+			offset += sizeof(struct icmp6hdr);
+		else
+			offset += 1;
+
+		if (!(frag_off & htons(IP6_OFFSET)) && offset > skb->len) {
+			__IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev),
+					IPSTATS_MIB_INHDRERRORS);
+			icmpv6_param_prob(skb, ICMPV6_HDR_INCOMP, 0);
+			return -1;
+		}
+	}
+
 	iif = skb->dev ? skb->dev->ifindex : 0;
 	fq = fq_find(net, fhdr->identification, hdr, iif);
 	if (fq) {
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index 25b7ebda2fab..f696d46e6910 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -303,13 +303,13 @@ static const struct xfrm_type xfrm6_tunnel_type = {
 static struct xfrm6_tunnel xfrm6_tunnel_handler __read_mostly = {
 	.handler	= xfrm6_tunnel_rcv,
 	.err_handler	= xfrm6_tunnel_err,
-	.priority	= 2,
+	.priority	= 3,
 };
 
 static struct xfrm6_tunnel xfrm46_tunnel_handler __read_mostly = {
 	.handler	= xfrm6_tunnel_rcv,
 	.err_handler	= xfrm6_tunnel_err,
-	.priority	= 2,
+	.priority	= 3,
 };
 
 static int __net_init xfrm6_tunnel_net_init(struct net *net)