mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2026-09-10 15:49:01 -04:00
The inetpeer rate limiting system stores peer entries in a Red-Black tree
keyed deterministically on the remote IP address. Because tree lookups walk
the RB-tree using standard lexicographical comparisons (inetpeer_addr_cmp),
an off-path adversary can predict the exact topology of the tree and the
sequence of nodes traversed during lookups (the gc_stack candidate list).
By combining deterministic tree traversal with aggressive garbage collection
(triggered when tree size exceeds inet_peer_threshold), an attacker can
selectively force the eviction of targeted inet_peer nodes. When an evicted
node is subsequently re-created upon receiving a new packet, its rate-limiting
token bucket (rate_tokens, rate_last) is reset to full capacity. This creates
a side-channel primitive allowing off-path attackers to bypass IP-keyed ICMP
rate limits and infer open UDP ports (similar to SAD DNS style attacks).
Mitigate this by randomizing the RB-tree node comparison logic using SipHash
with a secret key (inetpeer_hash_key) initialized via net_get_random_once().
Nodes are ordered in the tree by SipHash(addr, key) rather than raw IP
addresses. Because the secret key is unknown to external entities, the tree
layout and lookup traversal paths are unpredictable to off-path adversaries,
breaking the deterministic eviction gadget.
Cache the computed 64-bit SipHash (hash) in struct inet_peer and compute the
target hash (dhash) once at the beginning of inet_getpeer() to avoid recomputing
SipHash at every step of the RB-tree walk.
Fixes: b145425f26 ("inetpeer: remove AVL implementation in favor of RB tree")
Reported-by: Michael Blunt <michaelbblunt@gmail.com>
Suggested-by: Michael Blunt <michaelbblunt@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260818151213.3953963-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
155 lines
3.3 KiB
C
155 lines
3.3 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* INETPEER - A storage for permanent information about peers
|
|
*
|
|
* Authors: Andrey V. Savochkin <saw@msu.ru>
|
|
*/
|
|
|
|
#ifndef _NET_INETPEER_H
|
|
#define _NET_INETPEER_H
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/init.h>
|
|
#include <linux/jiffies.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/rtnetlink.h>
|
|
#include <net/ipv6.h>
|
|
#include <linux/atomic.h>
|
|
|
|
/* IPv4 address key for cache lookups */
|
|
struct ipv4_addr_key {
|
|
__be32 addr;
|
|
int vif;
|
|
};
|
|
|
|
#define INETPEER_MAXKEYSZ (sizeof(struct in6_addr) / sizeof(u32))
|
|
|
|
struct inetpeer_addr {
|
|
union {
|
|
struct ipv4_addr_key a4;
|
|
struct in6_addr a6;
|
|
u32 key[INETPEER_MAXKEYSZ];
|
|
};
|
|
__u16 family;
|
|
};
|
|
|
|
struct inet_peer {
|
|
struct rb_node rb_node;
|
|
u64 hash;
|
|
struct inetpeer_addr daddr;
|
|
|
|
u32 metrics[RTAX_MAX];
|
|
u32 rate_tokens; /* rate limiting for ICMP */
|
|
u32 n_redirects;
|
|
unsigned long rate_last;
|
|
/*
|
|
* Once inet_peer is queued for deletion (refcnt == 0), following field
|
|
* is not available: rid
|
|
* We can share memory with rcu_head to help keep inet_peer small.
|
|
*/
|
|
union {
|
|
struct {
|
|
atomic_t rid; /* Frag reception counter */
|
|
};
|
|
struct rcu_head rcu;
|
|
};
|
|
|
|
/* following fields might be frequently dirtied */
|
|
__u32 dtime; /* the time of last use of not referenced entries */
|
|
refcount_t refcnt;
|
|
};
|
|
|
|
struct inet_peer_base {
|
|
struct rb_root rb_root;
|
|
seqlock_t lock;
|
|
int total;
|
|
};
|
|
|
|
void inet_peer_base_init(struct inet_peer_base *);
|
|
|
|
void inet_initpeers(void) __init;
|
|
|
|
#define INETPEER_METRICS_NEW (~(u32) 0)
|
|
|
|
static inline void inetpeer_set_addr_v4(struct inetpeer_addr *iaddr, __be32 ip)
|
|
{
|
|
iaddr->a4.addr = ip;
|
|
iaddr->a4.vif = 0;
|
|
iaddr->family = AF_INET;
|
|
}
|
|
|
|
static inline __be32 inetpeer_get_addr_v4(struct inetpeer_addr *iaddr)
|
|
{
|
|
return iaddr->a4.addr;
|
|
}
|
|
|
|
static inline void inetpeer_set_addr_v6(struct inetpeer_addr *iaddr,
|
|
struct in6_addr *in6)
|
|
{
|
|
iaddr->a6 = *in6;
|
|
iaddr->family = AF_INET6;
|
|
}
|
|
|
|
static inline struct in6_addr *inetpeer_get_addr_v6(struct inetpeer_addr *iaddr)
|
|
{
|
|
return &iaddr->a6;
|
|
}
|
|
|
|
/* can be called with or without local BH being disabled */
|
|
struct inet_peer *inet_getpeer(struct inet_peer_base *base,
|
|
const struct inetpeer_addr *daddr);
|
|
|
|
static inline struct inet_peer *inet_getpeer_v4(struct inet_peer_base *base,
|
|
__be32 v4daddr,
|
|
int vif)
|
|
{
|
|
struct inetpeer_addr daddr;
|
|
|
|
daddr.a4.addr = v4daddr;
|
|
daddr.a4.vif = vif;
|
|
daddr.family = AF_INET;
|
|
return inet_getpeer(base, &daddr);
|
|
}
|
|
|
|
static inline struct inet_peer *inet_getpeer_v6(struct inet_peer_base *base,
|
|
const struct in6_addr *v6daddr)
|
|
{
|
|
struct inetpeer_addr daddr;
|
|
|
|
daddr.a6 = *v6daddr;
|
|
daddr.family = AF_INET6;
|
|
return inet_getpeer(base, &daddr);
|
|
}
|
|
|
|
static inline int inetpeer_addr_cmp(const struct inetpeer_addr *a,
|
|
const struct inetpeer_addr *b)
|
|
{
|
|
int i, n;
|
|
|
|
if (a->family != b->family)
|
|
return a->family < b->family ? -1 : 1;
|
|
|
|
if (a->family == AF_INET)
|
|
n = sizeof(a->a4) / sizeof(u32);
|
|
else
|
|
n = sizeof(a->a6) / sizeof(u32);
|
|
|
|
for (i = 0; i < n; i++) {
|
|
if (a->key[i] == b->key[i])
|
|
continue;
|
|
if (a->key[i] < b->key[i])
|
|
return -1;
|
|
return 1;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
/* can be called from BH context or outside */
|
|
void inet_putpeer(struct inet_peer *p);
|
|
bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout);
|
|
|
|
void inetpeer_invalidate_tree(struct inet_peer_base *);
|
|
|
|
#endif /* _NET_INETPEER_H */
|