linux/include/net/dst_ops.h
Eric Dumazet 92f1655aa2 net: fix __dst_negative_advice() race
__dst_negative_advice() does not enforce proper RCU rules when
sk->dst_cache must be cleared, leading to possible UAF.

RCU rules are that we must first clear sk->sk_dst_cache,
then call dst_release(old_dst).

Note that sk_dst_reset(sk) is implementing this protocol correctly,
while __dst_negative_advice() uses the wrong order.

Given that ip6_negative_advice() has special logic
against RTF_CACHE, this means each of the three ->negative_advice()
existing methods must perform the sk_dst_reset() themselves.

Note the check against NULL dst is centralized in
__dst_negative_advice(), there is no need to duplicate
it in various callbacks.

Many thanks to Clement Lecigne for tracking this issue.

This old bug became visible after the blamed commit, using UDP sockets.

Fixes: a87cb3e48e ("net: Facility to report route quality of connected sockets")
Reported-by: Clement Lecigne <clecigne@google.com>
Diagnosed-by: Clement Lecigne <clecigne@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Tom Herbert <tom@herbertland.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20240528114353.1794151-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-05-29 17:34:49 -07:00

74 lines
2.1 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _NET_DST_OPS_H
#define _NET_DST_OPS_H
#include <linux/types.h>
#include <linux/percpu_counter.h>
#include <linux/cache.h>
struct dst_entry;
struct kmem_cachep;
struct net_device;
struct sk_buff;
struct sock;
struct net;
struct dst_ops {
unsigned short family;
unsigned int gc_thresh;
void (*gc)(struct dst_ops *ops);
struct dst_entry * (*check)(struct dst_entry *, __u32 cookie);
unsigned int (*default_advmss)(const struct dst_entry *);
unsigned int (*mtu)(const struct dst_entry *);
u32 * (*cow_metrics)(struct dst_entry *, unsigned long);
void (*destroy)(struct dst_entry *);
void (*ifdown)(struct dst_entry *,
struct net_device *dev);
void (*negative_advice)(struct sock *sk, struct dst_entry *);
void (*link_failure)(struct sk_buff *);
void (*update_pmtu)(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu,
bool confirm_neigh);
void (*redirect)(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb);
int (*local_out)(struct net *net, struct sock *sk, struct sk_buff *skb);
struct neighbour * (*neigh_lookup)(const struct dst_entry *dst,
struct sk_buff *skb,
const void *daddr);
void (*confirm_neigh)(const struct dst_entry *dst,
const void *daddr);
struct kmem_cache *kmem_cachep;
struct percpu_counter pcpuc_entries ____cacheline_aligned_in_smp;
};
static inline int dst_entries_get_fast(struct dst_ops *dst)
{
return percpu_counter_read_positive(&dst->pcpuc_entries);
}
static inline int dst_entries_get_slow(struct dst_ops *dst)
{
return percpu_counter_sum_positive(&dst->pcpuc_entries);
}
#define DST_PERCPU_COUNTER_BATCH 32
static inline void dst_entries_add(struct dst_ops *dst, int val)
{
percpu_counter_add_batch(&dst->pcpuc_entries, val,
DST_PERCPU_COUNTER_BATCH);
}
static inline int dst_entries_init(struct dst_ops *dst)
{
return percpu_counter_init(&dst->pcpuc_entries, 0, GFP_KERNEL);
}
static inline void dst_entries_destroy(struct dst_ops *dst)
{
percpu_counter_destroy(&dst->pcpuc_entries);
}
#endif