ipv6: Add fragment reporting to ipv6_skip_exthdr().

While parsing through IPv6 extension headers, fragment headers are
skipped making them invisible to the caller.  This reports the
fragment offset of the last header in order to make it possible to
determine whether the packet is fragmented and, if so whether it is
a first or last fragment.

Signed-off-by: Jesse Gross <jesse@nicira.com>

14 files changed, 40 insertions, 16 deletions

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 7743e0d109ea..375417e633c9 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1458,6 +1458,7 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br,
 	const struct ipv6hdr *ip6h;
 	u8 icmp6_type;
 	u8 nexthdr;
+	__be16 frag_off;
 	unsigned len;
 	int offset;
 	int err;
@@ -1483,7 +1484,7 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br,
 		return -EINVAL;
 
 	nexthdr = ip6h->nexthdr;
-	offset = ipv6_skip_exthdr(skb, sizeof(*ip6h), &nexthdr);
+	offset = ipv6_skip_exthdr(skb, sizeof(*ip6h), &nexthdr, &frag_off);
 
 	if (offset < 0 || nexthdr != IPPROTO_ICMPV6)
 		return 0;
diff --git a/net/bridge/netfilter/ebt_ip6.c b/net/bridge/netfilter/ebt_ip6.c
index 2ed0056a39a8..99c85668f551 100644
--- a/net/bridge/netfilter/ebt_ip6.c
+++ b/net/bridge/netfilter/ebt_ip6.c
@@ -55,9 +55,10 @@ ebt_ip6_mt(const struct sk_buff *skb, struct xt_action_param *par)
 		return false;
 	if (info->bitmask & EBT_IP6_PROTO) {
 		uint8_t nexthdr = ih6->nexthdr;
+		__be16 frag_off;
 		int offset_ph;
 
-		offset_ph = ipv6_skip_exthdr(skb, sizeof(_ip6h), &nexthdr);
+		offset_ph = ipv6_skip_exthdr(skb, sizeof(_ip6h), &nexthdr, &frag_off);
 		if (offset_ph == -1)
 			return false;
 		if (FWINV(info->protocol != nexthdr, EBT_IP6_PROTO))
diff --git a/net/bridge/netfilter/ebt_log.c b/net/bridge/netfilter/ebt_log.c
index 6e5a8bb9b940..88d7d1d1cb1b 100644
--- a/net/bridge/netfilter/ebt_log.c
+++ b/net/bridge/netfilter/ebt_log.c
@@ -113,6 +113,7 @@ ebt_log_packet(u_int8_t pf, unsigned int hooknum,
 		const struct ipv6hdr *ih;
 		struct ipv6hdr _iph;
 		uint8_t nexthdr;
+		__be16 frag_off;
 		int offset_ph;
 
 		ih = skb_header_pointer(skb, 0, sizeof(_iph), &_iph);
@@ -123,7 +124,7 @@ ebt_log_packet(u_int8_t pf, unsigned int hooknum,
 		printk(" IPv6 SRC=%pI6 IPv6 DST=%pI6, IPv6 priority=0x%01X, Next Header=%d",
 		       &ih->saddr, &ih->daddr, ih->priority, ih->nexthdr);
 		nexthdr = ih->nexthdr;
-		offset_ph = ipv6_skip_exthdr(skb, sizeof(_iph), &nexthdr);
+		offset_ph = ipv6_skip_exthdr(skb, sizeof(_iph), &nexthdr, &frag_off);
 		if (offset_ph == -1)
 			goto out;
 		print_ports(skb, nexthdr, offset_ph);
diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index 37f548b7f6dc..72957f4a7c6c 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -57,6 +57,9 @@ int ipv6_ext_hdr(u8 nexthdr)
  *	    it returns NULL.
  *	  - First fragment header is skipped, not-first ones
  *	    are considered as unparsable.
+ *	  - Reports the offset field of the final fragment header so it is
+ *	    possible to tell whether this is a first fragment, later fragment,
+ *	    or not fragmented.
  *	  - ESP is unparsable for now and considered like
  *	    normal payload protocol.
  *	  - Note also special handling of AUTH header. Thanks to IPsec wizards.
@@ -64,10 +67,13 @@ int ipv6_ext_hdr(u8 nexthdr)
  * --ANK (980726)
  */
 
-int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp)
+int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp,
+		     __be16 *frag_offp)
 {
 	u8 nexthdr = *nexthdrp;
 
+	*frag_offp = 0;
+
 	while (ipv6_ext_hdr(nexthdr)) {
 		struct ipv6_opt_hdr _hdr, *hp;
 		int hdrlen;
@@ -87,7 +93,8 @@ int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp)
 			if (fp == NULL)
 				return -1;
 
-			if (ntohs(*fp) & ~0x7)
+			*frag_offp = *fp;
+			if (ntohs(*frag_offp) & ~0x7)
 				break;
 			hdrlen = 8;
 		} else if (nexthdr == NEXTHDR_AUTH)
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 9e2bdccf9143..01d46bff63c3 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -135,11 +135,12 @@ static int is_ineligible(struct sk_buff *skb)
 	int ptr = (u8 *)(ipv6_hdr(skb) + 1) - skb->data;
 	int len = skb->len - ptr;
 	__u8 nexthdr = ipv6_hdr(skb)->nexthdr;
+	__be16 frag_off;
 
 	if (len < 0)
 		return 1;
 
-	ptr = ipv6_skip_exthdr(skb, ptr, &nexthdr);
+	ptr = ipv6_skip_exthdr(skb, ptr, &nexthdr, &frag_off);
 	if (ptr < 0)
 		return 0;
 	if (nexthdr == IPPROTO_ICMPV6) {
@@ -596,6 +597,7 @@ static void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info)
 	int inner_offset;
 	int hash;
 	u8 nexthdr;
+	__be16 frag_off;
 
 	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
 		return;
@@ -603,7 +605,8 @@ static void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info)
 	nexthdr = ((struct ipv6hdr *)skb->data)->nexthdr;
 	if (ipv6_ext_hdr(nexthdr)) {
 		/* now skip over extension headers */
-		inner_offset = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr);
+		inner_offset = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr),
+						&nexthdr, &frag_off);
 		if (inner_offset<0)
 			return;
 	} else {
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index a46c64eb0a66..1ca5d45a12e8 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -280,6 +280,7 @@ int ip6_mc_input(struct sk_buff *skb)
 			u8 *ptr = skb_network_header(skb) + opt->ra;
 			struct icmp6hdr *icmp6;
 			u8 nexthdr = hdr->nexthdr;
+			__be16 frag_off;
 			int offset;
 
 			/* Check if the value of Router Alert
@@ -293,7 +294,7 @@ int ip6_mc_input(struct sk_buff *skb)
 					goto out;
 				}
 				offset = ipv6_skip_exthdr(skb, sizeof(*hdr),
-							  &nexthdr);
+							  &nexthdr, &frag_off);
 				if (offset < 0)
 					goto out;
 
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index a24e15557843..3221bc675654 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -329,10 +329,11 @@ static int ip6_forward_proxy_check(struct sk_buff *skb)
 {
 	struct ipv6hdr *hdr = ipv6_hdr(skb);
 	u8 nexthdr = hdr->nexthdr;
+	__be16 frag_off;
 	int offset;
 
 	if (ipv6_ext_hdr(nexthdr)) {
-		offset = ipv6_skip_exthdr(skb, sizeof(*hdr), &nexthdr);
+		offset = ipv6_skip_exthdr(skb, sizeof(*hdr), &nexthdr, &frag_off);
 		if (offset < 0)
 			return 0;
 	} else
diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c
index b5a2aa58a03a..aad2fa41cf46 100644
--- a/net/ipv6/netfilter/ip6t_REJECT.c
+++ b/net/ipv6/netfilter/ip6t_REJECT.c
@@ -49,6 +49,7 @@ static void send_reset(struct net *net, struct sk_buff *oldskb)
 	const __u8 tclass = DEFAULT_TOS_VALUE;
 	struct dst_entry *dst = NULL;
 	u8 proto;
+	__be16 frag_off;
 	struct flowi6 fl6;
 
 	if ((!(ipv6_addr_type(&oip6h->saddr) & IPV6_ADDR_UNICAST)) ||
@@ -58,7 +59,7 @@ static void send_reset(struct net *net, struct sk_buff *oldskb)
 	}
 
 	proto = oip6h->nexthdr;
-	tcphoff = ipv6_skip_exthdr(oldskb, ((u8*)(oip6h+1) - oldskb->data), &proto);
+	tcphoff = ipv6_skip_exthdr(oldskb, ((u8*)(oip6h+1) - oldskb->data), &proto, &frag_off);
 
 	if ((tcphoff < 0) || (tcphoff > oldskb->len)) {
 		pr_debug("Cannot get TCP header.\n");
diff --git a/net/netfilter/ipset/ip_set_getport.c b/net/netfilter/ipset/ip_set_getport.c
index 052579fe389a..b71a6e7ab0a5 100644
--- a/net/netfilter/ipset/ip_set_getport.c
+++ b/net/netfilter/ipset/ip_set_getport.c
@@ -116,9 +116,11 @@ ip_set_get_ip6_port(const struct sk_buff *skb, bool src,
 {
 	int protoff;
 	u8 nexthdr;
+	__be16 frag_off;
 
 	nexthdr = ipv6_hdr(skb)->nexthdr;
-	protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr);
+	protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr,
+				   &frag_off);
 	if (protoff < 0)
 		return false;
 
diff --git a/net/netfilter/xt_AUDIT.c b/net/netfilter/xt_AUDIT.c
index 4bca15a0c385..ba92824086f3 100644
--- a/net/netfilter/xt_AUDIT.c
+++ b/net/netfilter/xt_AUDIT.c
@@ -98,6 +98,7 @@ static void audit_ip6(struct audit_buffer *ab, struct sk_buff *skb)
 	struct ipv6hdr _ip6h;
 	const struct ipv6hdr *ih;
 	u8 nexthdr;
+	__be16 frag_off;
 	int offset;
 
 	ih = skb_header_pointer(skb, skb_network_offset(skb), sizeof(_ip6h), &_ip6h);
@@ -108,7 +109,7 @@ static void audit_ip6(struct audit_buffer *ab, struct sk_buff *skb)
 
 	nexthdr = ih->nexthdr;
 	offset = ipv6_skip_exthdr(skb, skb_network_offset(skb) + sizeof(_ip6h),
-				  &nexthdr);
+				  &nexthdr, &frag_off);
 
 	audit_log_format(ab, " saddr=%pI6c daddr=%pI6c proto=%hhu",
 			 &ih->saddr, &ih->daddr, nexthdr);
diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c
index 3ecade3966d5..ba722621ed25 100644
--- a/net/netfilter/xt_TCPMSS.c
+++ b/net/netfilter/xt_TCPMSS.c
@@ -204,11 +204,12 @@ tcpmss_tg6(struct sk_buff *skb, const struct xt_action_param *par)
 {
 	struct ipv6hdr *ipv6h = ipv6_hdr(skb);
 	u8 nexthdr;
+	__be16 frag_off;
 	int tcphoff;
 	int ret;
 
 	nexthdr = ipv6h->nexthdr;
-	tcphoff = ipv6_skip_exthdr(skb, sizeof(*ipv6h), &nexthdr);
+	tcphoff = ipv6_skip_exthdr(skb, sizeof(*ipv6h), &nexthdr, &frag_off);
 	if (tcphoff < 0)
 		return NF_DROP;
 	ret = tcpmss_mangle_packet(skb, par->targinfo,
diff --git a/net/netfilter/xt_TCPOPTSTRIP.c b/net/netfilter/xt_TCPOPTSTRIP.c
index 9dc9ecfdd546..3a295cc734bd 100644
--- a/net/netfilter/xt_TCPOPTSTRIP.c
+++ b/net/netfilter/xt_TCPOPTSTRIP.c
@@ -87,9 +87,10 @@ tcpoptstrip_tg6(struct sk_buff *skb, const struct xt_action_param *par)
 	struct ipv6hdr *ipv6h = ipv6_hdr(skb);
 	int tcphoff;
 	u_int8_t nexthdr;
+	__be16 frag_off;
 
 	nexthdr = ipv6h->nexthdr;
-	tcphoff = ipv6_skip_exthdr(skb, sizeof(*ipv6h), &nexthdr);
+	tcphoff = ipv6_skip_exthdr(skb, sizeof(*ipv6h), &nexthdr, &frag_off);
 	if (tcphoff < 0)
 		return NF_DROP;
 
diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c
index dfd52bad1523..068698f64791 100644
--- a/net/netfilter/xt_hashlimit.c
+++ b/net/netfilter/xt_hashlimit.c
@@ -445,6 +445,7 @@ hashlimit_init_dst(const struct xt_hashlimit_htable *hinfo,
 {
 	__be16 _ports[2], *ports;
 	u8 nexthdr;
+	__be16 frag_off;
 	int poff;
 
 	memset(dst, 0, sizeof(*dst));
@@ -480,7 +481,7 @@ hashlimit_init_dst(const struct xt_hashlimit_htable *hinfo,
 		      (XT_HASHLIMIT_HASH_DPT | XT_HASHLIMIT_HASH_SPT)))
 			return 0;
 		nexthdr = ipv6_hdr(skb)->nexthdr;
-		protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr);
+		protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, &frag_off);
 		if ((int)protoff < 0)
 			return -1;
 		break;
diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c
index fe39f7e913df..c302e30dc50c 100644
--- a/net/netfilter/xt_socket.c
+++ b/net/netfilter/xt_socket.c
@@ -214,6 +214,7 @@ extract_icmp6_fields(const struct sk_buff *skb,
 	struct icmp6hdr *icmph, _icmph;
 	__be16 *ports, _ports[2];
 	u8 inside_nexthdr;
+	__be16 inside_fragoff;
 	int inside_hdrlen;
 
 	icmph = skb_header_pointer(skb, outside_hdrlen,
@@ -229,7 +230,8 @@ extract_icmp6_fields(const struct sk_buff *skb,
 		return 1;
 	inside_nexthdr = inside_iph->nexthdr;
 
-	inside_hdrlen = ipv6_skip_exthdr(skb, outside_hdrlen + sizeof(_icmph) + sizeof(_inside_iph), &inside_nexthdr);
+	inside_hdrlen = ipv6_skip_exthdr(skb, outside_hdrlen + sizeof(_icmph) + sizeof(_inside_iph),
+					 &inside_nexthdr, &inside_fragoff);
 	if (inside_hdrlen < 0)
 		return 1; /* hjm: Packet has no/incomplete transport layer headers. */