[PATCH net v2] ipv6: Implement limits on extension header parsing

[Daniel Borkmann <daniel@iogearbox.net>]

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.

Add a configurable limit via a new sysctl net.ipv6.max_ext_hdrs_number
(default 8, minimum 1). All four extension header walking functions
are bound by this limit. The sysctl is in line with commit 47d3d7ac656a
("ipv6: Implement limits on Hop-by-Hop and Destination options").
As documented, init_net is used to derive max_ext_hdrs_number to
be consistent given a net cannot always reliably be retrieved.

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, thus 8 was used as the default.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 v1->v2:
   - Set the default to 8 (Justin)
   - Update IETF references (Justin)
   - Add core path coverage as well (Justin)

 Documentation/networking/ip-sysctl.rst |  7 +++++++
 include/net/dropreason-core.h          |  6 ++++++
 include/net/ipv6.h                     |  2 ++
 include/net/netns/ipv6.h               |  1 +
 net/ipv6/af_inet6.c                    |  1 +
 net/ipv6/exthdrs_core.c                | 11 +++++++++++
 net/ipv6/ip6_input.c                   |  6 ++++++
 net/ipv6/ip6_tunnel.c                  |  5 +++++
 net/ipv6/sysctl_net_ipv6.c             |  8 ++++++++
 9 files changed, 47 insertions(+)

diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index 2e3a746fcc6d..f7412f4049d1 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -2537,6 +2537,13 @@ max_hbh_length - INTEGER
 
 	Default: INT_MAX (unlimited)
 
+max_ext_hdrs_number - INTEGER
+	Maximum number of IPv6 extension headers allowed in a packet.
+	Limits how many extension headers will be traversed. The value
+	is read from the initial netns.
+
+	Default: 8
+
 skip_notify_on_dev_down - BOOLEAN
 	Controls whether an RTM_DELROUTE message is generated for routes
 	removed when a device is taken down or deleted. IPv4 does not
diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h
index e0ca3904ff8e..1fd91e59b84e 100644
--- a/include/net/dropreason-core.h
+++ b/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 net.ipv6.max_ext_hdrs_number.
+	 */
+	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. */
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index d042afe7a245..c540b750726e 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -90,6 +90,8 @@ 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 */
 
+#define IP6_DEFAULT_MAX_EXT_HDRS_CNT	 8
+
 /*
  *	Addr type
  *	
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index 499e4288170f..2cea457bddb4 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -54,6 +54,7 @@ struct netns_sysctl_ipv6 {
 	int max_hbh_opts_cnt;
 	int max_dst_opts_len;
 	int max_hbh_opts_len;
+	int max_ext_hdrs_cnt;
 	int seg6_flowlabel;
 	u32 ioam6_id;
 	u64 ioam6_id_wide;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 0a88b376141d..19424c3f2dfc 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -945,6 +945,7 @@ static int __net_init inet6_net_init(struct net *net)
 	net->ipv6.sysctl.flowlabel_state_ranges = 0;
 	net->ipv6.sysctl.max_dst_opts_cnt = IP6_DEFAULT_MAX_DST_OPTS_CNT;
 	net->ipv6.sysctl.max_hbh_opts_cnt = IP6_DEFAULT_MAX_HBH_OPTS_CNT;
+	net->ipv6.sysctl.max_ext_hdrs_cnt = IP6_DEFAULT_MAX_EXT_HDRS_CNT;
 	net->ipv6.sysctl.max_dst_opts_len = IP6_DEFAULT_MAX_DST_OPTS_LEN;
 	net->ipv6.sysctl.max_hbh_opts_len = IP6_DEFAULT_MAX_HBH_OPTS_LEN;
 	net->ipv6.sysctl.fib_notify_on_flag_change = 0;
diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index 49e31e4ae7b7..9df892e7f7fb 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -4,6 +4,8 @@
  * not configured or static.
  */
 #include <linux/export.h>
+
+#include <net/net_namespace.h>
 #include <net/ipv6.h>
 
 /*
@@ -72,7 +74,9 @@ EXPORT_SYMBOL(ipv6_ext_hdr);
 int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp,
 		     __be16 *frag_offp)
 {
+	int exthdr_max = READ_ONCE(init_net.ipv6.sysctl.max_ext_hdrs_cnt);
 	u8 nexthdr = *nexthdrp;
+	int exthdr_cnt = 0;
 
 	*frag_offp = 0;
 
@@ -82,6 +86,8 @@ int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp,
 
 		if (nexthdr == NEXTHDR_NONE)
 			return -1;
+		if (unlikely(exthdr_cnt++ >= exthdr_max))
+			return -1;
 		hp = skb_header_pointer(skb, start, sizeof(_hdr), &_hdr);
 		if (!hp)
 			return -1;
@@ -188,8 +194,10 @@ EXPORT_SYMBOL_GPL(ipv6_find_tlv);
 int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
 		  int target, unsigned short *fragoff, int *flags)
 {
+	int exthdr_max = READ_ONCE(init_net.ipv6.sysctl.max_ext_hdrs_cnt);
 	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 +224,9 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
 			return -ENOENT;
 		}
 
+		if (unlikely(exthdr_cnt++ >= exthdr_max))
+			return -EBADMSG;
+
 		hp = skb_header_pointer(skb, start, sizeof(_hdr), &_hdr);
 		if (!hp)
 			return -EBADMSG;
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 967b07aeb683..a5bbbc16e8d7 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -403,8 +403,10 @@ 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_max = READ_ONCE(init_net.ipv6.sysctl.max_ext_hdrs_cnt);
 	const struct inet6_protocol *ipprot;
 	struct inet6_dev *idev;
+	int exthdr_cnt = 0;
 	unsigned int nhoff;
 	SKB_DR(reason);
 	bool raw;
@@ -487,6 +489,10 @@ void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr,
 				nexthdr = ret;
 				goto resubmit_final;
 			} else {
+				if (unlikely(exthdr_cnt++ >= exthdr_max)) {
+					SKB_DR_SET(reason, IPV6_TOO_MANY_EXTHDRS);
+					goto discard;
+				}
 				goto resubmit;
 			}
 		} else if (ret == 0) {
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index c468c83af0f2..4546a60942ab 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -395,15 +395,20 @@ ip6_tnl_dev_uninit(struct net_device *dev)
 
 __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw)
 {
+	int exthdr_max = READ_ONCE(init_net.ipv6.sysctl.max_ext_hdrs_cnt);
 	const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)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++ >= exthdr_max))
+			break;
+
 		if (!pskb_may_pull(skb, off + sizeof(*hdr)))
 			break;
 
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index d2cd33e2698d..93f865545a7c 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -135,6 +135,14 @@ static struct ctl_table ipv6_table_template[] = {
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= &flowlabel_reflect_max,
 	},
+	{
+		.procname	= "max_ext_hdrs_number",
+		.data		= &init_net.ipv6.sysctl.max_ext_hdrs_cnt,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ONE,
+	},
 	{
 		.procname	= "max_dst_opts_number",
 		.data		= &init_net.ipv6.sysctl.max_dst_opts_cnt,
-- 
2.43.0