[PATCH net v4] ipv6: validate extension header length before copying to cmsg

[PATCH net v4] ipv6: validate extension header length before copying to cmsg

[Qi Tang]

ip6_datagram_recv_specific_ctl() builds IPV6_{HOPOPTS,DSTOPTS,RTHDR}
cmsgs (and their IPV6_2292* legacy counterparts) by trusting the
on-wire hdrlen byte (ptr[1]) when computing the put_cmsg() length.
The length was validated only at parse time (ipv6_parse_hopopts(),
etc.).  An nftables payload-write expression can rewrite hdrlen after
parsing and before the skb reaches recvmsg; the write itself is
in-bounds but put_cmsg() then reads up to ((hdrlen+1) << 3) = 2040
bytes from an 8-byte header.  nftables is reachable from an
unprivileged user namespace, so this is an unprivileged
slab-out-of-bounds read:

  BUG: KASAN: slab-out-of-bounds in put_cmsg+0x3ac/0x540
   put_cmsg+0x3ac/0x540
   udpv6_recvmsg+0xca0/0x1250
   sock_recvmsg+0xdf/0x190
   ____sys_recvmsg+0x1b1/0x620

Add ipv6_get_exthdr_len() which validates that at least two bytes
are accessible before reading the hdrlen field, then checks the
computed length against skb_tail_pointer(skb), returning 0 on
failure.  Extension headers are kept in the linear skb area by
pskb_may_pull() during input, so skb_tail_pointer() is the correct
bound.

Use ipv6_get_exthdr_len() at all non-AH call sites: the five
standalone cmsg blocks (HbH, 2292HbH, 2292DSTOPTS x2, 2292RTHDR)
and the three standard cases in the extension-header walk loop
(DSTOPTS, ROUTING, default).  AH retains an inline bounds check
because its length formula differs ((ptr[1]+2)<<2).

The walk loop also gets a pre-read bounds check at the top to
validate ptr before any case accesses ptr[0] or ptr[1].

When the walk loop detects a corrupted header, return from the
function instead of continuing to process later socket options.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Qi Tang <tpluszz77@gmail.com>
---
Changes v3 -> v4 (Paolo Abeni / Sashiko):
  - Validate ptr + 2 <= skb_tail_pointer(skb) before reading ptr[1]
    in ipv6_get_exthdr_len()
  - Add matching pre-read bounds check at the top of the walk loop

Changes v2 -> v3:
  - Resend as new thread (v2 was incorrectly sent as reply to v1)

Changes v1 -> v2 (Paolo Abeni):
  - Factor repeated bounds-check + put_cmsg into ipv6_get_exthdr_len()
  - Return from the function on corrupted walk-loop entry instead of
    goto + empty label

v3: https://lore.kernel.org/netdev/20260423103238.3987364-1-tpluszz77@gmail.com/
v2: https://lore.kernel.org/netdev/20260423102255.3752004-1-tpluszz77@gmail.com/
v1: https://lore.kernel.org/netdev/20260419150344.624673-1-tpluszz77@gmail.com/
 net/ipv6/datagram.c | 54 ++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 46 insertions(+), 8 deletions(-)

diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 972bf0426d599..f9ee1bf97f206 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -617,6 +617,18 @@ void ip6_datagram_recv_common_ctl(struct sock *sk, struct msghdr *msg,
 	}
 }
 
+static u16 ipv6_get_exthdr_len(const struct sk_buff *skb, const u8 *ptr)
+{
+	u16 len;
+
+	if (ptr + 2 > skb_tail_pointer(skb))
+		return 0;
+
+	len = (ptr[1] + 1) << 3;
+
+	return (ptr + len <= skb_tail_pointer(skb)) ? len : 0;
+}
+
 void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg,
 				    struct sk_buff *skb)
 {
@@ -643,7 +655,10 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg,
 	/* HbH is allowed only once */
 	if (np->rxopt.bits.hopopts && (opt->flags & IP6SKB_HOPBYHOP)) {
 		u8 *ptr = nh + sizeof(struct ipv6hdr);
-		put_cmsg(msg, SOL_IPV6, IPV6_HOPOPTS, (ptr[1]+1)<<3, ptr);
+		u16 len = ipv6_get_exthdr_len(skb, ptr);
+
+		if (len)
+			put_cmsg(msg, SOL_IPV6, IPV6_HOPOPTS, len, ptr);
 	}
 
 	if (opt->lastopt &&
@@ -664,26 +679,37 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg,
 			unsigned int len;
 			u8 *ptr = nh + off;
 
+			if (ptr + 2 > skb_tail_pointer(skb))
+				return;
+
 			switch (nexthdr) {
 			case IPPROTO_DSTOPTS:
 				nexthdr = ptr[0];
-				len = (ptr[1] + 1) << 3;
+				len = ipv6_get_exthdr_len(skb, ptr);
+				if (!len)
+					return;
 				if (np->rxopt.bits.dstopts)
 					put_cmsg(msg, SOL_IPV6, IPV6_DSTOPTS, len, ptr);
 				break;
 			case IPPROTO_ROUTING:
 				nexthdr = ptr[0];
-				len = (ptr[1] + 1) << 3;
+				len = ipv6_get_exthdr_len(skb, ptr);
+				if (!len)
+					return;
 				if (np->rxopt.bits.srcrt)
 					put_cmsg(msg, SOL_IPV6, IPV6_RTHDR, len, ptr);
 				break;
 			case IPPROTO_AH:
 				nexthdr = ptr[0];
 				len = (ptr[1] + 2) << 2;
+				if (ptr + len > skb_tail_pointer(skb))
+					return;
 				break;
 			default:
 				nexthdr = ptr[0];
-				len = (ptr[1] + 1) << 3;
+				len = ipv6_get_exthdr_len(skb, ptr);
+				if (!len)
+					return;
 				break;
 			}
 
@@ -705,19 +731,31 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg,
 	}
 	if (np->rxopt.bits.ohopopts && (opt->flags & IP6SKB_HOPBYHOP)) {
 		u8 *ptr = nh + sizeof(struct ipv6hdr);
-		put_cmsg(msg, SOL_IPV6, IPV6_2292HOPOPTS, (ptr[1]+1)<<3, ptr);
+		u16 len = ipv6_get_exthdr_len(skb, ptr);
+
+		if (len)
+			put_cmsg(msg, SOL_IPV6, IPV6_2292HOPOPTS, len, ptr);
 	}
 	if (np->rxopt.bits.odstopts && opt->dst0) {
 		u8 *ptr = nh + opt->dst0;
-		put_cmsg(msg, SOL_IPV6, IPV6_2292DSTOPTS, (ptr[1]+1)<<3, ptr);
+		u16 len = ipv6_get_exthdr_len(skb, ptr);
+
+		if (len)
+			put_cmsg(msg, SOL_IPV6, IPV6_2292DSTOPTS, len, ptr);
 	}
 	if (np->rxopt.bits.osrcrt && opt->srcrt) {
 		struct ipv6_rt_hdr *rthdr = (struct ipv6_rt_hdr *)(nh + opt->srcrt);
-		put_cmsg(msg, SOL_IPV6, IPV6_2292RTHDR, (rthdr->hdrlen+1) << 3, rthdr);
+		u16 len = ipv6_get_exthdr_len(skb, (u8 *)rthdr);
+
+		if (len)
+			put_cmsg(msg, SOL_IPV6, IPV6_2292RTHDR, len, rthdr);
 	}
 	if (np->rxopt.bits.odstopts && opt->dst1) {
 		u8 *ptr = nh + opt->dst1;
-		put_cmsg(msg, SOL_IPV6, IPV6_2292DSTOPTS, (ptr[1]+1)<<3, ptr);
+		u16 len = ipv6_get_exthdr_len(skb, ptr);
+
+		if (len)
+			put_cmsg(msg, SOL_IPV6, IPV6_2292DSTOPTS, len, ptr);
 	}
 	if (np->rxopt.bits.rxorigdstaddr) {
 		struct sockaddr_in6 sin6;
-- 
2.47.3