Files
android_kernel_fxtec_sm6115/include/net/act_api.h
Jamal Hadi Salim 0c23ec2e23 net/sched: act_api: use RCU with deferred freeing for action lifecycle
[ Upstream commit 5057e1aca011e51ef51498c940ef96f3d3e8a305 ]

When NEWTFILTER and DELFILTER are run concurrently it is possible to create a
race with an associated action.

Let's illustrate with CPU0 running NEWTFILTER and CPU1 running DELFILTER:

 0: mutex_lock() <-- holds the idr lock
 0: rcu_read_lock()
 0: p = idr_find(idr, index) <-- action p is valid (RCU protects IDR)
 0: mutex_unlock() <-- releases the idr lock
 1: refcount_dec_and_mutex_lock() <-- refcnt 1->0, mutex held
 1: idr_remove(idr, index) <-- Action removed from IDR
 1: mutex_unlock() <-- mutex released allowing us to delete the action
 1: tcf_action_cleanup(p); kfree(p) <-- Kfrees p immediately, no deferral
 0: refcount_inc_not_zero(&p->tcfa_refcnt) <-- ouch, UAF p points to freed memory

This patch fixes the race condition between NEWTFILTER and DELFILTER by
adding struct rcu_head to tc_action used in the deferral and introducing a
call_rcu() in the delete path to defer the final kfree().

Note: this is a revert of commit d7fb60b9ca ("net_sched: get rid of tcfa_rcu")
but also modernization/simplification to directly use kfree_rcu().

Let's illustrate the new restored code path:

 0: rcu_read_lock()
 1: refcount_dec_and_mutex_lock() <-- refcnt 1->0, mutex held
 1: idr_remove(idr, index)
 1: mutex_unlock()
 1: call_rcu(&p->tcfa_rcu, tcf_action_rcu_free) <-- defer kfree after grace period
 0: p = idr_find(idr, index)
 0: refcount_inc_not_zero(&p->tcfa_refcnt) <-- fails, refcnt already 0
 1: rcu_read_unlock() <-- release so freeing can run after grace period

After CPU1 calls idr_remove(), the object is no longer reachable through the IDR.
CPU0's subsequent idr_find() will return NULL, and even if it still held a
stale pointer, the immediate kfree() is now deferred until after the RCU grace
period, so no UAF can occur.

Fixes: d7fb60b9ca ("net_sched: get rid of tcfa_rcu")
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Reported-by: Kyle Zeng <kylebot@openai.com>
Tested-by: Victor Nogueira <victor@mojatatu.com>
Tested-by: syzbot@syzkaller.appspotmail.com
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Tested-by: Kyle Zeng <kylebot@openai.com>
Reviewed-by: Pedro Tammela <pctammela@mojatatu.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Victor Nogueira <victor@mojatatu.com>
Link: https://patch.msgid.link/20260531160812.68020-1-jhs@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[uli: backport to 4.19]
Signed-off-by: Ulrich Hecht <uli@kernel.org>
Reviewed-by: Pavel Machek <pavel@nabladev.com>
2026-08-04 11:22:19 +02:00

232 lines
6.9 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __NET_ACT_API_H
#define __NET_ACT_API_H
/*
* Public action API for classifiers/qdiscs
*/
#include <linux/refcount.h>
#include <net/sch_generic.h>
#include <net/pkt_sched.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
struct tcf_idrinfo {
spinlock_t lock;
struct idr action_idr;
struct net *net;
};
struct tc_action_ops;
struct tc_action {
const struct tc_action_ops *ops;
__u32 type; /* for backward compat(TCA_OLD_COMPAT) */
__u32 order;
struct tcf_idrinfo *idrinfo;
u32 tcfa_index;
refcount_t tcfa_refcnt;
atomic_t tcfa_bindcnt;
int tcfa_action;
struct tcf_t tcfa_tm;
struct gnet_stats_basic_packed tcfa_bstats;
struct gnet_stats_queue tcfa_qstats;
struct net_rate_estimator __rcu *tcfa_rate_est;
spinlock_t tcfa_lock;
struct gnet_stats_basic_cpu __percpu *cpu_bstats;
struct gnet_stats_queue __percpu *cpu_qstats;
struct tc_cookie __rcu *act_cookie;
struct tcf_chain *goto_chain;
struct rcu_head tcfa_rcu;
};
#define tcf_index common.tcfa_index
#define tcf_refcnt common.tcfa_refcnt
#define tcf_bindcnt common.tcfa_bindcnt
#define tcf_action common.tcfa_action
#define tcf_tm common.tcfa_tm
#define tcf_bstats common.tcfa_bstats
#define tcf_qstats common.tcfa_qstats
#define tcf_rate_est common.tcfa_rate_est
#define tcf_lock common.tcfa_lock
/* Update lastuse only if needed, to avoid dirtying a cache line.
* We use a temp variable to avoid fetching jiffies twice.
*/
static inline void tcf_lastuse_update(struct tcf_t *tm)
{
unsigned long now = jiffies;
if (tm->lastuse != now)
tm->lastuse = now;
if (unlikely(!tm->firstuse))
tm->firstuse = now;
}
static inline void tcf_tm_dump(struct tcf_t *dtm, const struct tcf_t *stm)
{
dtm->install = jiffies_to_clock_t(jiffies - stm->install);
dtm->lastuse = jiffies_to_clock_t(jiffies - stm->lastuse);
dtm->firstuse = stm->firstuse ?
jiffies_to_clock_t(jiffies - stm->firstuse) : 0;
dtm->expires = jiffies_to_clock_t(stm->expires);
}
#ifdef CONFIG_NET_CLS_ACT
#define ACT_P_CREATED 1
#define ACT_P_DELETED 1
struct tc_action_ops {
struct list_head head;
char kind[IFNAMSIZ];
__u32 type; /* TBD to match kind */
size_t size;
struct module *owner;
int (*act)(struct sk_buff *, const struct tc_action *,
struct tcf_result *); /* called under RCU BH lock*/
int (*dump)(struct sk_buff *, struct tc_action *, int, int);
void (*cleanup)(struct tc_action *);
int (*lookup)(struct net *net, struct tc_action **a, u32 index,
struct netlink_ext_ack *extack);
int (*init)(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **act, int ovr,
int bind, bool rtnl_held,
struct netlink_ext_ack *extack);
int (*walk)(struct net *, struct sk_buff *,
struct netlink_callback *, int,
const struct tc_action_ops *,
struct netlink_ext_ack *);
void (*stats_update)(struct tc_action *, u64, u32, u64);
size_t (*get_fill_size)(const struct tc_action *act);
struct net_device *(*get_dev)(const struct tc_action *a);
void (*put_dev)(struct net_device *dev);
};
struct tc_action_net {
struct tcf_idrinfo *idrinfo;
const struct tc_action_ops *ops;
};
static inline
int tc_action_net_init(struct net *net, struct tc_action_net *tn,
const struct tc_action_ops *ops)
{
int err = 0;
tn->idrinfo = kmalloc(sizeof(*tn->idrinfo), GFP_KERNEL);
if (!tn->idrinfo)
return -ENOMEM;
tn->ops = ops;
tn->idrinfo->net = net;
spin_lock_init(&tn->idrinfo->lock);
idr_init(&tn->idrinfo->action_idr);
return err;
}
void tcf_idrinfo_destroy(const struct tc_action_ops *ops,
struct tcf_idrinfo *idrinfo);
static inline void tc_action_net_exit(struct list_head *net_list,
unsigned int id)
{
struct net *net;
rtnl_lock();
list_for_each_entry(net, net_list, exit_list) {
struct tc_action_net *tn = net_generic(net, id);
tcf_idrinfo_destroy(tn->ops, tn->idrinfo);
kfree(tn->idrinfo);
}
rtnl_unlock();
}
int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb,
struct netlink_callback *cb, int type,
const struct tc_action_ops *ops,
struct netlink_ext_ack *extack);
int tcf_idr_search(struct tc_action_net *tn, struct tc_action **a, u32 index);
int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
struct tc_action **a, const struct tc_action_ops *ops,
int bind, bool cpustats);
void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a);
void tcf_idr_cleanup(struct tc_action_net *tn, u32 index);
int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index,
struct tc_action **a, int bind);
int __tcf_idr_release(struct tc_action *a, bool bind, bool strict);
static inline int tcf_idr_release(struct tc_action *a, bool bind)
{
return __tcf_idr_release(a, bind, false);
}
int tcf_register_action(struct tc_action_ops *a, struct pernet_operations *ops);
int tcf_unregister_action(struct tc_action_ops *a,
struct pernet_operations *ops);
int tcf_action_destroy(struct tc_action *actions[], int bind);
int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions,
int nr_actions, struct tcf_result *res);
int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
struct nlattr *est, char *name, int ovr, int bind,
struct tc_action *actions[], size_t *attr_size,
bool rtnl_held, struct netlink_ext_ack *extack);
struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
struct nlattr *nla, struct nlattr *est,
char *name, int ovr, int bind,
bool rtnl_held,
struct netlink_ext_ack *extack);
int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[], int bind,
int ref);
int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int);
int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int);
int tcf_action_copy_stats(struct sk_buff *, struct tc_action *, int);
#endif /* CONFIG_NET_CLS_ACT */
static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes,
u64 packets, u64 lastuse)
{
#ifdef CONFIG_NET_CLS_ACT
if (!a->ops->stats_update)
return;
a->ops->stats_update(a, bytes, packets, lastuse);
#endif
}
#ifdef CONFIG_NET_CLS_ACT
int tc_setup_cb_egdev_register(const struct net_device *dev,
tc_setup_cb_t *cb, void *cb_priv);
void tc_setup_cb_egdev_unregister(const struct net_device *dev,
tc_setup_cb_t *cb, void *cb_priv);
int tc_setup_cb_egdev_call(const struct net_device *dev,
enum tc_setup_type type, void *type_data,
bool err_stop);
#else
static inline
int tc_setup_cb_egdev_register(const struct net_device *dev,
tc_setup_cb_t *cb, void *cb_priv)
{
return 0;
}
static inline
void tc_setup_cb_egdev_unregister(const struct net_device *dev,
tc_setup_cb_t *cb, void *cb_priv)
{
}
static inline
int tc_setup_cb_egdev_call(const struct net_device *dev,
enum tc_setup_type type, void *type_data,
bool err_stop)
{
return 0;
}
#endif
#endif