bridge: Validate and clean up IPv6 neighbour suppression

The bridge implements IPv6 neighbour suppression by snooping Neighbour Solicitation and Neighbour Advertisement messages, but it previously only checked the ICMPv6 type and code before acting on them. This leaves it open to acting on malformed or spoofed packets that any RFC 4861 compliant node should reject, and the option parsing in br_nd_send() open-codes a loop that has historically been a source of bugs.

This series hardens and cleans up that path:

Add ndisc_check_ns_na(), a standalone NS/NA validator modeled after ipv6_mc_check_mld(), implementing the RFC 4861 section 7.1.1 / 7.1.2 mandatory receive checks (hop limit, checksum, code, length, target and option validation). Wire the bridge into it so NS/NA messages are validated to the same standard MLD already enjoys.

Replace the manual ND option parsing loop in br_nd_send() with ndisc_parse_options() and ndisc_opt_addr_data(), and linearize the skb once it has been validated as an NS/NA message so that this and any future ND message handling operate on a linear buffer. The first patch is a small preparatory cleanup that drops the now-unnecessary skb_header_pointer() fallback from br_is_nd_neigh_msg().

No functional change is intended for well-formed packets.

Patchset overview:
Patch #1: drop the skb_header_pointer() fallback. Patches #2-#3: add ndisc_check_ns_na() and validate NS/NA with it. Patch #4: linearize once the ND message type is validated. Patch #5: parse options via ndisc_parse_options().

v2:
* Patches #2,#5:
* Use EXPORT_SYMBOL_GPL() instead of EXPORT_SYMBOL() to export ndisc_check_ns_na().
* Patch #4:
* Add a comment noting that br_is_nd_neigh_msg() also linearizes the skb.

Danielle Ratson (5):
bridge: Use direct pointer in br_is_nd_neigh_msg()
ipv6: ndisc: Add ndisc_check_ns_na() validation helper
bridge: Validate NS/NA messages using ndisc_check_ns_na()
bridge: Linearize skb once the ND message type is validated
bridge: Use ndisc_parse_options() to parse ND options in br_nd_send()

 include/net/ndisc.h          |   2 +
 net/bridge/br_arp_nd_proxy.c |  57 ++++++-----
 net/bridge/br_device.c       |   4 +-
 net/bridge/br_input.c        |   4 +-
 net/bridge/br_private.h      |   2 +-
 net/ipv6/Makefile            |   2 +-
 net/ipv6/ndisc.c             |   1 +
 net/ipv6/ndisc_snoop.c       | 190 +++++++++++++++++++++++++++++++++++
 8 files changed, 227 insertions(+), 35 deletions(-)
 create mode 100644 net/ipv6/ndisc_snoop.c

2.54.0

Both callers of br_is_nd_neigh_msg() already call pskb_may_pull() to ensure sizeof(struct ipv6hdr) + sizeof(struct nd_msg) bytes are in the linear area before invoking this function. The skb_header_pointer() call and its fallback buffer are therefore unnecessary.

Replace skb_header_pointer() with a direct cast to ipv6_hdr(skb) + 1 and drop the now-unused 'msg' parameter and its corresponding stack buffer from all callers.

---
 net/bridge/br_arp_nd_proxy.c | 9 ++-------
 net/bridge/br_device.c       | 4 ++--
 net/bridge/br_input.c        | 4 ++--
 net/bridge/br_private.h      | 2 +-
 4 files changed, 7 insertions(+), 12 deletions(-)

index 23eb6931a2b4..db08c3272001 100644
@@ -234,14 +234,9 @@ void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br,
 #endif
 
 #if IS_ENABLED(CONFIG_IPV6)
-struct nd_msg *br_is_nd_neigh_msg(const struct sk_buff *skb, struct nd_msg *msg)
+struct nd_msg *br_is_nd_neigh_msg(const struct sk_buff *skb)
 {
-	struct nd_msg *m;
-
-	m = skb_header_pointer(skb, skb_network_offset(skb) +
-			       sizeof(struct ipv6hdr), sizeof(*msg), msg);
-	if (!m)
-		return NULL;
+	struct nd_msg *m = (struct nd_msg *)(ipv6_hdr(skb) + 1);
 
 	if (m->icmph.icmp6_code != 0 ||
 	    (m->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION &&

index e7f343ab22d3..ff55dab73632 100644
@@ -80,9 +80,9 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 		   pskb_may_pull(skb, sizeof(struct ipv6hdr) +
 				 sizeof(struct nd_msg)) &&
 		   ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) {
-			struct nd_msg *msg, _msg;
+			struct nd_msg *msg;
 
-			msg = br_is_nd_neigh_msg(skb, &_msg);
+			msg = br_is_nd_neigh_msg(skb);
 			if (msg)
 				br_do_suppress_nd(skb, br, vid, NULL, msg);
 	}

index ddb8f002a40e..d87a5f9fa92b 100644
@@ -176,9 +176,9 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
 		   pskb_may_pull(skb, sizeof(struct ipv6hdr) +
 				 sizeof(struct nd_msg)) &&
 		   ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) {
-			struct nd_msg *msg, _msg;
+			struct nd_msg *msg;
 
-			msg = br_is_nd_neigh_msg(skb, &_msg);
+			msg = br_is_nd_neigh_msg(skb);
 			if (msg)
 				br_do_suppress_nd(skb, br, vid, p, msg);
 	}

index 4cf8b1ab9047..e31439cb4420 100644
@@ -2367,7 +2367,7 @@ void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br,
 			      u16 vid, struct net_bridge_port *p);
 void br_do_suppress_nd(struct sk_buff *skb, struct net_bridge *br,
 		       u16 vid, struct net_bridge_port *p, struct nd_msg *msg);
-struct nd_msg *br_is_nd_neigh_msg(const struct sk_buff *skb, struct nd_msg *m);
+struct nd_msg *br_is_nd_neigh_msg(const struct sk_buff *skb);
 bool br_is_neigh_suppress_enabled(const struct net_bridge_port *p, u16 vid);
 bool br_is_neigh_forward_grat_enabled(const struct net_bridge_port *p, u16 vid);
 #endif

2.54.0

Sashiko wrote:

"

        if ((dev->flags & IFF_NOARP) ||
            !pskb_may_pull(skb, arp_hdr_len(dev)))
                return;
        parp = arp_hdr(skb);

Add ndisc_check_ns_na(), a standalone NS/NA packet validator modeled after ipv6_mc_check_mld(). It performs the RFC 4861 section 7.1.1 (Neighbor Solicitation) and 7.1.2 (Neighbor Advertisement) mandatory checks that are relevant for software operating at the bridge level, where packets bypass the normal IPv6 stack path:

- Hop Limit must be 255 (packet was not forwarded by a router)
- ICMPv6 checksum is valid
- ICMP Code is 0
- ICMP length is at least 24 octets (sizeof(struct nd_msg))
- Target Address must not be a multicast address
- All included options have a length that is greater than zero
- NS/DAD: destination must be a solicited-node multicast address
- NS/DAD: no Source Link-Layer Address option when source is unspecified
- NA: Solicited flag must be 0 when IP Destination is multicast

On success the function sets the skb transport header and returns 0, matching the convention of ipv6_mc_check_mld().

---

Notes:

    v2:
    	* Use EXPORT_SYMBOL_GPL() instead of EXPORT_SYMBOL() to export
    	  ndisc_check_ns_na().

 include/net/ndisc.h    |   2 +
 net/ipv6/Makefile      |   2 +-
 net/ipv6/ndisc_snoop.c | 190 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 193 insertions(+), 1 deletion(-)
 create mode 100644 net/ipv6/ndisc_snoop.c

index 3da1a6f8d3f9..9e5379ad2d8e 100644
@@ -430,6 +430,8 @@ void ndisc_update(const struct net_device *dev, struct neighbour *neigh,
 		  const u8 *lladdr, u8 new, u32 flags, u8 icmp6_type,
 		  struct ndisc_options *ndopts);
 
+int ndisc_check_ns_na(struct sk_buff *skb);
+
 /*
  *	IGMP
  */

index 5b0cd6488021..cf5e01f83ce3 100644
@@ -51,7 +51,7 @@ obj-$(subst m,y,$(CONFIG_IPV6)) += inet6_hashtables.o
 
 ifneq ($(CONFIG_IPV6),)
 obj-$(CONFIG_NET_UDP_TUNNEL) += ip6_udp_tunnel.o
-obj-y += mcast_snoop.o
+obj-y += mcast_snoop.o ndisc_snoop.o
 obj-$(CONFIG_TCP_AO) += tcp_ao.o
 endif
 

2.54.0

Sashiko wrote:

"
--- Patch [2]: [PATCH net-next v2 2/5] ipv6: ndisc: Add ndisc_check_ns_na() validation helper --- commit 4031e051060238d9c59321eb3171c00634174182
Author: Danielle Ratson <[email protected]>
ipv6: ndisc: Add ndisc_check_ns_na() validation helper
This commit adds ndisc_check_ns_na(), a standalone validator for IPv6
Neighbor Solicitation and Neighbor Advertisement packets. It performs
mandatory RFC 4861 checks for software operating at the bridge level.

The bridge performs neighbor suppression by snooping NS/NA messages, but previously only checked the ICMPv6 type and code. This leaves it open to acting on malformed or spoofed packets that any RFC-compliant node should reject.

Wire br_is_nd_neigh_msg() into the new ndisc_check_ns_na() helper, which enforces the full RFC 4861 section 7.1.1/7.1.2 receive validation:
hop limit of 255, valid checksum, correct code, and type-specific rules (NS target not multicast; NA solicited flag clear for multicast destinations).

MLD messages are already validated by ipv6_mc_check_mld() before the bridge acts on them; this brings NS/NA to the same standard.

As a side effect, the skb parameter of br_is_nd_neigh_msg() changes from const to non-const, since ndisc_check_ns_na() may reallocate the skb head via pskb_may_pull() and sets the transport header. The returned pointer is now derived from skb_transport_header() rather than a direct cast.

---
 net/bridge/br_arp_nd_proxy.c | 11 ++++-------
 net/bridge/br_private.h      |  2 +-
 2 files changed, 5 insertions(+), 8 deletions(-)

index db08c3272001..445c930ed59b 100644
@@ -19,6 +19,7 @@
 #include <net/addrconf.h>
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ip6_checksum.h>
+#include <net/ndisc.h>
 #endif
 
 #include "br_private.h"

@@ -234,16 +235,12 @@ void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br,
 #endif
 
 #if IS_ENABLED(CONFIG_IPV6)
-struct nd_msg *br_is_nd_neigh_msg(const struct sk_buff *skb)
+struct nd_msg *br_is_nd_neigh_msg(struct sk_buff *skb)
 {
-	struct nd_msg *m = (struct nd_msg *)(ipv6_hdr(skb) + 1);
-
-	if (m->icmph.icmp6_code != 0 ||
-	    (m->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION &&
-	     m->icmph.icmp6_type != NDISC_NEIGHBOUR_ADVERTISEMENT))
+	if (ndisc_check_ns_na(skb))
 		return NULL;
 
-	return m;
+	return (struct nd_msg *)skb_transport_header(skb);
 }
 
 static void br_nd_send(struct net_bridge *br, struct net_bridge_port *p,

index e31439cb4420..d337b1cfb980 100644
@@ -2367,7 +2367,7 @@ void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br,
 			      u16 vid, struct net_bridge_port *p);
 void br_do_suppress_nd(struct sk_buff *skb, struct net_bridge *br,
 		       u16 vid, struct net_bridge_port *p, struct nd_msg *msg);
-struct nd_msg *br_is_nd_neigh_msg(const struct sk_buff *skb);
+struct nd_msg *br_is_nd_neigh_msg(struct sk_buff *skb);
 bool br_is_neigh_suppress_enabled(const struct net_bridge_port *p, u16 vid);
 bool br_is_neigh_forward_grat_enabled(const struct net_bridge_port *p, u16 vid);
 #endif

2.54.0

br_nd_send() parses ND options from ns->opt[] and therefore needs the skb to be linear. Commit a01aee7cafc5 ("bridge: br_nd_send: linearize skb before parsing ND options") ensured that by linearizing inside br_nd_send() itself.

Move the linearization up into br_is_nd_neigh_msg(), right after ndisc_check_ns_na() has validated the message as an NS/NA. This makes a linear buffer a property of every recognized ND message, so that this and any future ND message handling operate on a linear skb and cannot reintroduce that class of bug by forgetting to linearize.

Since the skb is now linear by the time br_nd_send() runs, drop the linearization there and derive ns from the transport header set by ndisc_check_ns_na(), instead of recomputing it from the network header.

If linearization fails under memory pressure, br_is_nd_neigh_msg() returns NULL and the packet falls back to normal forwarding rather than being suppressed.

---

Notes:
v2:
* Add a comment noting that br_is_nd_neigh_msg() also linearizes the skb.

 net/bridge/br_arp_nd_proxy.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

index 445c930ed59b..6b6de0eff38c 100644
@@ -235,11 +235,17 @@ void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br,
 #endif
 
 #if IS_ENABLED(CONFIG_IPV6)
+/* Validate skb as an NS/NA and linearize it for br_nd_send()'s ND
+ * option parsing; returns the nd_msg, or NULL on failure.
+ */
 struct nd_msg *br_is_nd_neigh_msg(struct sk_buff *skb)
 {
 	if (ndisc_check_ns_na(skb))
 		return NULL;
 
+	if (skb_linearize(skb))
+		return NULL;
+
 	return (struct nd_msg *)skb_transport_header(skb);
 }
 

@@ -259,7 +265,7 @@ static void br_nd_send(struct net_bridge *br, struct net_bridge_port *p,
 	bool dad;
 	u16 pvid;
 
-	if (!dev || skb_linearize(request))
+	if (!dev)
 		return;
 
 	len = LL_RESERVED_SPACE(dev) + sizeof(struct ipv6hdr) +

@@ -276,8 +282,7 @@ static void br_nd_send(struct net_bridge *br, struct net_bridge_port *p,
 	skb_set_mac_header(reply, 0);
 
 	daddr = eth_hdr(request)->h_source;
-	ns = (struct nd_msg *)(skb_network_header(request) +
-			       sizeof(struct ipv6hdr));
+	ns = (struct nd_msg *)skb_transport_header(request);
 
 	/* Do we need option processing ? */
 	ns_olen = request->len - (skb_network_offset(request) +

2.54.0

Thanks,

Replace the manual ND option parsing loop in br_nd_send() with ndisc_parse_options(), which provides proper validation and avoids the class of bugs that were fixed by commit 53fc685243bd ("bridge: Avoid infinite loop when suppressing NS messages with invalid options") and commit 850837965af1 ("bridge: br_nd_send: validate ND option lengths").

Use ndisc_opt_addr_data() to extract the source link-layer address from the parsed options, which correctly validates the option length for the underlying device type.

Export ndisc_parse_options() so that it can be resolved from the bridge when it is built as a module (CONFIG_BRIDGE=m); otherwise modpost fails with an undefined symbol.

---

Notes:
v2:
* Use EXPORT_SYMBOL_GPL() instead of EXPORT_SYMBOL() to export ndisc_parse_options().

 net/bridge/br_arp_nd_proxy.c | 32 +++++++++++++++++---------------
 net/ipv6/ndisc.c             |  1 +
 2 files changed, 18 insertions(+), 15 deletions(-)

index 6b6de0eff38c..b6e5a86b6a92 100644
@@ -255,15 +255,16 @@ static void br_nd_send(struct net_bridge *br, struct net_bridge_port *p,
 {
 	struct net_device *dev = request->dev;
 	struct net_bridge_vlan_group *vg;
+	struct ndisc_options ndopts;
 	struct nd_msg *na, *ns;
 	struct sk_buff *reply;
 	struct ipv6hdr *pip6;
 	int na_olen = 8; /* opt hdr + ETH_ALEN for target */
 	int ns_olen;
-	int i, len;
 	u8 *daddr;
 	bool dad;
 	u16 pvid;
+	int len;
 
 	if (!dev)
 		return;

@@ -284,20 +285,21 @@ static void br_nd_send(struct net_bridge *br, struct net_bridge_port *p,
 	daddr = eth_hdr(request)->h_source;
 	ns = (struct nd_msg *)skb_transport_header(request);
 
-	/* Do we need option processing ? */
-	ns_olen = request->len - (skb_network_offset(request) +
-				  sizeof(struct ipv6hdr)) - sizeof(*ns);
-	for (i = 0; i < ns_olen - 1; i += (ns->opt[i + 1] << 3)) {
-		if (!ns->opt[i + 1] || i + (ns->opt[i + 1] << 3) > ns_olen) {
-			kfree_skb(reply);
-			return;
-		}
-		if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) {
-			if ((ns->opt[i + 1] << 3) >=
-			    sizeof(struct nd_opt_hdr) + ETH_ALEN)
-				daddr = ns->opt + i + sizeof(struct nd_opt_hdr);
-			break;
-		}
+	/* Derive the option length from the IPv6 payload length so that any
+	 * trailing L2 padding in the skb is not parsed as ND options.
+	 */
+	ns_olen = ntohs(ipv6_hdr(request)->payload_len) - sizeof(*ns);
+	if (!ndisc_parse_options(dev, ns->opt, ns_olen, &ndopts)) {
+		kfree_skb(reply);
+		return;
+	}
+
+	if (ndopts.nd_opts_src_lladdr) {
+		u8 *lladdr;
+
+		lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr, dev);
+		if (lladdr)
+			daddr = lladdr;
 	}
 
 	dad = ipv6_addr_any(&ipv6_hdr(request)->saddr);

index fe36b3f51285..2ceb655c4229 100644
@@ -283,6 +283,7 @@ struct ndisc_options *ndisc_parse_options(const struct net_device *dev,
 	}
 	return ndopts;
 }
+EXPORT_SYMBOL_GPL(ndisc_parse_options);
 
 int ndisc_mc_map(const struct in6_addr *addr, char *buf, struct net_device *dev, int dir)
 {

2.54.0

Sashiko wrote:

"
--- Patch [5]: [PATCH net-next v2 5/5] bridge: Use ndisc_parse_options() to parse ND options in br_nd_send() --- commit a5e722187a4312d62366c8f19772265d9169d89e
Author: Danielle Ratson <[email protected]>
bridge: Use ndisc_parse_options() to parse ND options in br_nd_send()
This commit replaces the manual ND option parsing loop in br_nd_send()
with ndisc_parse_options() to provide proper validation. It also exports
ndisc_parse_options() from the IPv6 module so it can be called from the
bridge subsystem.

[ ... ]