Netdev List
 help / color / mirror / Atom feed
* [PATCH net v2] tcp_metrics: hash the destination address with SipHash
@ 2026-11-17  4:10 Juan Agustin Niccolini
  2026-11-17  9:20 ` Eric Dumazet
  2026-11-19 16:12 ` netdev-bot+sashiko
  0 siblings, 2 replies; 3+ messages in thread
From: Juan Agustin Niccolini @ 2026-11-17  4:10 UTC (permalink / raw)
  To: Eric Dumazet, Neal Cardwell, Kuniyuki Iwashima, David S. Miller,
	Jakub Kicinski, Paolo Abeni, Simon Horman
  Cc: netdev, linux-kernel

The tcp_metrics bucket is derived from a fold of the peer address.
For IPv4 the fold is ipv4_addr_hash(), which returns the address
unchanged. For IPv6 it is ipv6_addr_hash(), which XORs the four
32-bit words of the address. net_hash_mix() is only XORed in after
that fold, so two addresses of either family with the same fold share
a bucket in every netns.

A remote attacker with an IPv6 /64 can thus compute, without knowing
net_hash_mix(), addresses that collide with a chosen IPv4 or IPv6 address:

  w3 = w2 ^ p0 ^ p1 ^ target    /* p0, p1: prefix, w2: free */

A bucket holds six entries and the seventh insert replaces the oldest.
tcp_init_metrics() seeds the initial RTO from the cached RTT, so the
attacker can tell whether an entry it planted was evicted. Filling the
bucket of a chosen address with such entries reveals whether that
address, or another one in the same bucket, connected in the meantime.

The same test, with six entries of one fold and a seventh of another,
shows whether two folds share a bucket. Each answer rules out values
of net_hash_mix(), the only unknown, and since XOR and multiply is not
a PRF a few hundred answers recover it. The attacker can then fill
every bucket and see which one any client's connection evicts from.
The multiplication in hash_32() is invertible, so that bucket leaks
about 14 bits of the client's address, depending on the number of
buckets.

Hash the address with SipHash and a random key instead, as commit
2ee66e948717 ("inetpeer: randomize RB-tree node comparison using SipHash")
did for inet_peer. net_hash_mix() and hash_32() are kept, to separate
namespaces and to reduce the result to the table size.

Fixes: 51c5d0c4b169 ("tcp: Maintain dynamic metrics in local cache.")
Cc: stable@vger.kernel.org
Signed-off-by: Juan Agustin Niccolini <juanagusnicco@gmail.com>
---
v2: - use siphash_1u32() for IPv4, a4.vif is always zero in tcp_metrics
      (Kuniyuki)
    - call tcpm_addr_hash() once after the address family branches
    - changelog: explain more clearly why net_hash_mix() and addresses
      are recoverable
v1: https://lore.kernel.org/netdev/20261112064624.15245-1-juanagusnicco@gmail.com/

Comments below are the same as on v1.

This can be exploited remotely to recover a client's IPv4 address.
A single host narrows the address to about 262 thousand candidates,
and because each netns keys the hash differently, intersecting buckets
extracted from multiple hosts converges quickly into one candidate;
3-5 are enough. The net_hash_mix() value only needs to be extracted
once per boot per host.

Many common cases facilitate this. For instance, a browser loading
one page connects to several hosts within the same second. That
supplies the buckets needed to converge, and the shared timing shows
they belong to the same client.

I reproduced the bug on a QEMU guest running mainline (2a500a04d6f9) and
against Ubuntu 24.04 over the internet. With the patch applied, the
reproducer no longer finds addresses that share a bucket. The
reproducer is available on request.

For stable: 5.10 and 5.15 lack siphash_aligned_key_t;
"static siphash_key_t tcpm_hash_key __read_mostly __aligned(16);" can
be used there.

This bug was discovered during an LLM-based code review.

 net/ipv4/tcp_metrics.c | 28 +++++++++++++++++++++-------
 1 file changed, 21 insertions(+), 7 deletions(-)

--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -8,6 +8,7 @@
 #include <linux/init.h>
 #include <linux/tcp.h>
 #include <linux/hash.h>
+#include <linux/siphash.h>
 #include <linux/tcp_metrics.h>
 #include <linux/vmalloc.h>
 
@@ -94,6 +95,22 @@
 
 static DEFINE_SPINLOCK(tcp_metrics_lock);
 static DEFINE_SEQLOCK(fastopen_seqlock);
+
+static siphash_aligned_key_t tcpm_hash_key __read_mostly;
+
+static u32 tcpm_addr_hash(const struct inetpeer_addr *a)
+{
+	net_get_random_once(&tcpm_hash_key, sizeof(tcpm_hash_key));
+
+	if (a->family == AF_INET)
+		return siphash_1u32((__force u32)a->a4.addr, &tcpm_hash_key);
+
+	return siphash_4u32((__force u32)a->a6.s6_addr32[0],
+			    (__force u32)a->a6.s6_addr32[1],
+			    (__force u32)a->a6.s6_addr32[2],
+			    (__force u32)a->a6.s6_addr32[3],
+			    &tcpm_hash_key);
+}
 
 static void tcpm_suck_dst(struct tcp_metrics_block *tm,
 			  const struct dst_entry *dst,
@@ -270,13 +287,11 @@
 	case AF_INET:
 		inetpeer_set_addr_v4(&saddr, inet_rsk(req)->ir_loc_addr);
 		inetpeer_set_addr_v4(&daddr, inet_rsk(req)->ir_rmt_addr);
-		hash = ipv4_addr_hash(inet_rsk(req)->ir_rmt_addr);
 		break;
 #if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
 		inetpeer_set_addr_v6(&saddr, &inet_rsk(req)->ir_v6_loc_addr);
 		inetpeer_set_addr_v6(&daddr, &inet_rsk(req)->ir_v6_rmt_addr);
-		hash = ipv6_addr_hash(&inet_rsk(req)->ir_v6_rmt_addr);
 		break;
 #endif
 	default:
@@ -284,6 +299,7 @@
 	}
 
 	net = sock_net(req_to_sk(req));
+	hash = tcpm_addr_hash(&daddr);
 	hash ^= net_hash_mix(net);
 	hash = hash_32(hash, tcp_metrics_hash_log);
 
@@ -310,18 +326,15 @@
 	if (sk->sk_family == AF_INET) {
 		inetpeer_set_addr_v4(&saddr, inet_sk(sk)->inet_saddr);
 		inetpeer_set_addr_v4(&daddr, inet_sk(sk)->inet_daddr);
-		hash = ipv4_addr_hash(inet_sk(sk)->inet_daddr);
 	}
 #if IS_ENABLED(CONFIG_IPV6)
 	else if (sk->sk_family == AF_INET6) {
 		if (ipv6_addr_v4mapped(&sk->sk_v6_daddr)) {
 			inetpeer_set_addr_v4(&saddr, inet_sk(sk)->inet_saddr);
 			inetpeer_set_addr_v4(&daddr, inet_sk(sk)->inet_daddr);
-			hash = ipv4_addr_hash(inet_sk(sk)->inet_daddr);
 		} else {
 			inetpeer_set_addr_v6(&saddr, &sk->sk_v6_rcv_saddr);
 			inetpeer_set_addr_v6(&daddr, &sk->sk_v6_daddr);
-			hash = ipv6_addr_hash(&sk->sk_v6_daddr);
 		}
 	}
 #endif
@@ -329,6 +342,7 @@
 		return NULL;
 
 	net = sock_net(sk);
+	hash = tcpm_addr_hash(&daddr);
 	hash ^= net_hash_mix(net);
 	hash = hash_32(hash, tcp_metrics_hash_log);
 
@@ -819,7 +833,7 @@
 	if (a) {
 		inetpeer_set_addr_v4(addr, nla_get_in_addr(a));
 		if (hash)
-			*hash = ipv4_addr_hash(inetpeer_get_addr_v4(addr));
+			*hash = tcpm_addr_hash(addr);
 		return 0;
 	}
 	a = info->attrs[v6];
@@ -829,7 +843,7 @@
 		in6 = nla_get_in6_addr(a);
 		inetpeer_set_addr_v6(addr, &in6);
 		if (hash)
-			*hash = ipv6_addr_hash(inetpeer_get_addr_v6(addr));
+			*hash = tcpm_addr_hash(addr);
 		return 0;
 	}
 	return optional ? 1 : -EAFNOSUPPORT;

^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2026-11-19 16:12 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-11-17  4:10 [PATCH net v2] tcp_metrics: hash the destination address with SipHash Juan Agustin Niccolini
2026-11-17  9:20 ` Eric Dumazet
2026-11-19 16:12 ` netdev-bot+sashiko

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox