ipv6: Implement limits on extension header parsing

ipv6_{skip_exthdr,find_hdr}() and ip6_{tnl_parse_tlv_enc_lim,
protocol_deliver_rcu}() iterate over IPv6 extension headers until they
find a non-extension-header protocol or run out of packet data. The
loops have no iteration counter, relying solely on the packet length
to bound them. For a crafted packet with 8-byte extension headers
filling a 64KB jumbogram, this means a worst case of up to ~8k
iterations with a skb_header_pointer call each. ipv6_skip_exthdr(),
for example, is used where it parses the inner quoted packet inside
an incoming ICMPv6 error:

  - icmpv6_rcv
    - checksum validation
    - case ICMPV6_DEST_UNREACH
      - icmpv6_notify
        - pskb_may_pull()       <- pull inner IPv6 header
        - ipv6_skip_exthdr()    <- iterates here
        - pskb_may_pull()
        - ipprot->err_handler() <- sk lookup

The per-iteration cost of ipv6_skip_exthdr itself is generally
light, but skb_header_pointer becomes more costly on reassembled
packets: the first ~1232 bytes of the inner packet are in the skb's
linear area, but the remaining ~63KB are in the frag_list where
skb_copy_bits is needed to read data.

Initially, the idea was to add a configurable limit via a new
sysctl knob with default 8, in line with knobs from commit
47d3d7ac65 ("ipv6: Implement limits on Hop-by-Hop and Destination
options"), but two reasons eventually argued against it:

- It adds to UAPI that needs to be maintained forever, and
  upcoming work is restricting extension header ordering anyway,
  leaving little reason for another sysctl knob
- exthdrs_core.c is always built-in even when CONFIG_IPV6=n,
  where struct net has no .ipv6 member, so the read site would
  need an ifdef'd fallback to a constant anyway

Therefore, just use a constant (IP6_MAX_EXT_HDRS_CNT). All four
extension header walking functions are now bound by this limit.

Note that the check in ip6_protocol_deliver_rcu() happens right
before the goto resubmit, such that we don't have to have a test
for ipv6_ext_hdr() in the fast-path.

There's an ongoing IETF draft-iurman-6man-eh-occurrences to enforce
IPv6 extension headers ordering and occurrence. The latter also
discusses security implications. As per RFC8200 section 4.1, the
occurrence rules for extension headers provide a practical upper
bound which is 8. In order to be conservative, let's define
IP6_MAX_EXT_HDRS_CNT as 12 to leave enough room for quirky setups.
In the unlikely event that this is still not enough, then we might
need to reconsider a sysctl.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Justin Iurman <justin.iurman@gmail.com>
Link: https://patch.msgid.link/20260429154648.809751-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

include/net/dropreason-core.h

@@ -99,6 +99,7 @@
 	FN(FRAG_TOO_FAR)		\
 	FN(TCP_MINTTL)			\
 	FN(IPV6_BAD_EXTHDR)		\
+	FN(IPV6_TOO_MANY_EXTHDRS)	\
 	FN(IPV6_NDISC_FRAG)		\
 	FN(IPV6_NDISC_HOP_LIMIT)	\
 	FN(IPV6_NDISC_BAD_CODE)		\
@@ -494,6 +495,11 @@ enum skb_drop_reason {
 	SKB_DROP_REASON_TCP_MINTTL,
 	/** @SKB_DROP_REASON_IPV6_BAD_EXTHDR: Bad IPv6 extension header. */
 	SKB_DROP_REASON_IPV6_BAD_EXTHDR,
+	/**
+	 * @SKB_DROP_REASON_IPV6_TOO_MANY_EXTHDRS: Number of IPv6 extension
+	 * headers in the packet exceeds IP6_MAX_EXT_HDRS_CNT.
+	 */
+	SKB_DROP_REASON_IPV6_TOO_MANY_EXTHDRS,
 	/** @SKB_DROP_REASON_IPV6_NDISC_FRAG: invalid frag (suppress_frag_ndisc). */
 	SKB_DROP_REASON_IPV6_NDISC_FRAG,
 	/** @SKB_DROP_REASON_IPV6_NDISC_HOP_LIMIT: invalid hop limit. */

include/net/ipv6.h

@@ -90,6 +90,9 @@ struct ip_tunnel_info;
 #define IP6_DEFAULT_MAX_DST_OPTS_LEN	 INT_MAX /* No limit */
 #define IP6_DEFAULT_MAX_HBH_OPTS_LEN	 INT_MAX /* No limit */
 
+/* Hard limit on traversed IPv6 extension headers */
+#define IP6_MAX_EXT_HDRS_CNT		 12
+
 /*
  *	Addr type
  *	

net/ipv6/exthdrs_core.c

@@ -73,6 +73,7 @@ int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp,
 		     __be16 *frag_offp)
 {
 	u8 nexthdr = *nexthdrp;
+	int exthdr_cnt = 0;
 
 	*frag_offp = 0;
 
@@ -82,6 +83,8 @@ int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp,
 
 		if (nexthdr == NEXTHDR_NONE)
 			return -1;
+		if (unlikely(exthdr_cnt++ >= IP6_MAX_EXT_HDRS_CNT))
+			return -1;
 		hp = skb_header_pointer(skb, start, sizeof(_hdr), &_hdr);
 		if (!hp)
 			return -1;
@@ -190,6 +193,7 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
 {
 	unsigned int start = skb_network_offset(skb) + sizeof(struct ipv6hdr);
 	u8 nexthdr = ipv6_hdr(skb)->nexthdr;
+	int exthdr_cnt = 0;
 	bool found;
 
 	if (fragoff)
@@ -216,6 +220,9 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
 			return -ENOENT;
 		}
 
+		if (unlikely(exthdr_cnt++ >= IP6_MAX_EXT_HDRS_CNT))
+			return -EBADMSG;
+
 		hp = skb_header_pointer(skb, start, sizeof(_hdr), &_hdr);
 		if (!hp)
 			return -EBADMSG;

net/ipv6/ip6_input.c

@@ -403,6 +403,7 @@ INDIRECT_CALLABLE_DECLARE(int tcp_v6_rcv(struct sk_buff *));
 void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr,
 			      bool have_final)
 {
+	int exthdr_cnt = IP6CB(skb)->flags & IP6SKB_HOPBYHOP ? 1 : 0;
 	const struct inet6_protocol *ipprot;
 	struct inet6_dev *idev;
 	unsigned int nhoff;
@@ -487,6 +488,10 @@ void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr,
 				nexthdr = ret;
 				goto resubmit_final;
 			} else {
+				if (unlikely(exthdr_cnt++ >= IP6_MAX_EXT_HDRS_CNT)) {
+					SKB_DR_SET(reason, IPV6_TOO_MANY_EXTHDRS);
+					goto discard;
+				}
 				goto resubmit;
 			}
 		} else if (ret == 0) {

net/ipv6/ip6_tunnel.c

@@ -399,11 +399,15 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw)
 	unsigned int nhoff = raw - skb->data;
 	unsigned int off = nhoff + sizeof(*ipv6h);
 	u8 nexthdr = ipv6h->nexthdr;
+	int exthdr_cnt = 0;
 
 	while (ipv6_ext_hdr(nexthdr) && nexthdr != NEXTHDR_NONE) {
 		struct ipv6_opt_hdr *hdr;
 		u16 optlen;
 
+		if (unlikely(exthdr_cnt++ >= IP6_MAX_EXT_HDRS_CNT))
+			break;
+
 		if (!pskb_may_pull(skb, off + sizeof(*hdr)))
 			break;