nagai/kernel
3
0
Fork 0
forked from mirrors/linux
Code Pull requests Activity
kernel/include/linux/if_bridge.h
Kuniyuki Iwashima ed3ba9b6e2 net: Remove RTNL dance for SIOCBRADDIF and SIOCBRDELIF. 
SIOCBRDELIF is passed to dev_ioctl() first and later forwarded to
br_ioctl_call(), which causes unnecessary RTNL dance and the splat
below [0] under RTNL pressure.

Let's say Thread A is trying to detach a device from a bridge and
Thread B is trying to remove the bridge.

In dev_ioctl(), Thread A bumps the bridge device's refcnt by
netdev_hold() and releases RTNL because the following br_ioctl_call()
also re-acquires RTNL.

In the race window, Thread B could acquire RTNL and try to remove
the bridge device.  Then, rtnl_unlock() by Thread B will release RTNL
and wait for netdev_put() by Thread A.

Thread A, however, must hold RTNL after the unlock in dev_ifsioc(),
which may take long under RTNL pressure, resulting in the splat by
Thread B.

  Thread A (SIOCBRDELIF)           Thread B (SIOCBRDELBR)
  ----------------------           ----------------------
  sock_ioctl                       sock_ioctl
  `- sock_do_ioctl                 `- br_ioctl_call
     `- dev_ioctl                     `- br_ioctl_stub
        |- rtnl_lock                     |
        |- dev_ifsioc                    '
        '  |- dev = __dev_get_by_name(...)
           |- netdev_hold(dev, ...)      .
       /   |- rtnl_unlock  ------.       |
       |   |- br_ioctl_call       `--->  |- rtnl_lock
  Race |   |  `- br_ioctl_stub           |- br_del_bridge
  Window   |     |                       |  |- dev = __dev_get_by_name(...)
       |   |     |  May take long        |  `- br_dev_delete(dev, ...)
       |   |     |  under RTNL pressure  |     `- unregister_netdevice_queue(dev, ...)
       |   |     |               |       `- rtnl_unlock
       \   |     |- rtnl_lock  <-'          `- netdev_run_todo
           |     |- ...                        `- netdev_run_todo
           |     `- rtnl_unlock                   |- __rtnl_unlock
           |                                      |- netdev_wait_allrefs_any
           |- netdev_put(dev, ...)  <----------------'
                                                Wait refcnt decrement
                                                and log splat below

To avoid blocking SIOCBRDELBR unnecessarily, let's not call
dev_ioctl() for SIOCBRADDIF and SIOCBRDELIF.

In the dev_ioctl() path, we do the following:

  1. Copy struct ifreq by get_user_ifreq in sock_do_ioctl()
  2. Check CAP_NET_ADMIN in dev_ioctl()
  3. Call dev_load() in dev_ioctl()
  4. Fetch the master dev from ifr.ifr_name in dev_ifsioc()

3. can be done by request_module() in br_ioctl_call(), so we move
1., 2., and 4. to br_ioctl_stub().

Note that 2. is also checked later in add_del_if(), but it's better
performed before RTNL.

SIOCBRADDIF and SIOCBRDELIF have been processed in dev_ioctl() since
the pre-git era, and there seems to be no specific reason to process
them there.

[0]:
unregister_netdevice: waiting for wpan3 to become free. Usage count = 2
ref_tracker: wpan3@ffff8880662d8608 has 1/1 users at
     __netdev_tracker_alloc include/linux/netdevice.h:4282 [inline]
     netdev_hold include/linux/netdevice.h:4311 [inline]
     dev_ifsioc+0xc6a/0x1160 net/core/dev_ioctl.c:624
     dev_ioctl+0x255/0x10c0 net/core/dev_ioctl.c:826
     sock_do_ioctl+0x1ca/0x260 net/socket.c:1213
     sock_ioctl+0x23a/0x6c0 net/socket.c:1318
     vfs_ioctl fs/ioctl.c:51 [inline]
     __do_sys_ioctl fs/ioctl.c:906 [inline]
     __se_sys_ioctl fs/ioctl.c:892 [inline]
     __x64_sys_ioctl+0x1a4/0x210 fs/ioctl.c:892
     do_syscall_x64 arch/x86/entry/common.c:52 [inline]
     do_syscall_64+0xcb/0x250 arch/x86/entry/common.c:83
     entry_SYSCALL_64_after_hwframe+0x77/0x7f

Fixes: 893b195875 ("net: bridge: fix ioctl locking")
Reported-by: syzkaller <syzkaller@googlegroups.com>
Reported-by: yan kang <kangyan91@outlook.com>
Reported-by: yue sun <samsun1006219@gmail.com>
Closes: https://lore.kernel.org/netdev/SY8P300MB0421225D54EB92762AE8F0F2A1D32@SY8P300MB0421.AUSP300.PROD.OUTLOOK.COM/
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20250316192851.19781-1-kuniyu@amazon.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2025-03-21 22:10:06 +01:00

213 lines
5.4 KiB
C
Raw Blame History

/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* Linux ethernet bridge
*
* Authors:
* Lennert Buytenhek <buytenh@gnu.org>
*/
#ifndef _LINUX_IF_BRIDGE_H
#define _LINUX_IF_BRIDGE_H
#include <linux/netdevice.h>
#include <uapi/linux/if_bridge.h>
#include <linux/bitops.h>
struct br_ip {
union {
__be32 ip4;
#if IS_ENABLED(CONFIG_IPV6)
struct in6_addr ip6;
#endif
} src;
union {
__be32 ip4;
#if IS_ENABLED(CONFIG_IPV6)
struct in6_addr ip6;
#endif
unsigned char mac_addr[ETH_ALEN];
} dst;
__be16 proto;
__u16 vid;
};
struct br_ip_list {
struct list_head list;
struct br_ip addr;
};
#define BR_HAIRPIN_MODE BIT(0)
#define BR_BPDU_GUARD BIT(1)
#define BR_ROOT_BLOCK BIT(2)
#define BR_MULTICAST_FAST_LEAVE BIT(3)
#define BR_ADMIN_COST BIT(4)
#define BR_LEARNING BIT(5)
#define BR_FLOOD BIT(6)
#define BR_AUTO_MASK (BR_FLOOD | BR_LEARNING)
#define BR_PROMISC BIT(7)
#define BR_PROXYARP BIT(8)
#define BR_LEARNING_SYNC BIT(9)
#define BR_PROXYARP_WIFI BIT(10)
#define BR_MCAST_FLOOD BIT(11)
#define BR_MULTICAST_TO_UNICAST BIT(12)
#define BR_VLAN_TUNNEL BIT(13)
#define BR_BCAST_FLOOD BIT(14)
#define BR_NEIGH_SUPPRESS BIT(15)
#define BR_ISOLATED BIT(16)
#define BR_MRP_AWARE BIT(17)
#define BR_MRP_LOST_CONT BIT(18)
#define BR_MRP_LOST_IN_CONT BIT(19)
#define BR_TX_FWD_OFFLOAD BIT(20)
#define BR_PORT_LOCKED BIT(21)
#define BR_PORT_MAB BIT(22)
#define BR_NEIGH_VLAN_SUPPRESS BIT(23)
#define BR_DEFAULT_AGEING_TIME (300 * HZ)
struct net_bridge;
void brioctl_set(int (*hook)(struct net *net, unsigned int cmd,
void __user *uarg));
int br_ioctl_call(struct net *net, unsigned int cmd, void __user *uarg);
#if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_IGMP_SNOOPING)
int br_multicast_list_adjacent(struct net_device *dev,
struct list_head *br_ip_list);
bool br_multicast_has_querier_anywhere(struct net_device *dev, int proto);
bool br_multicast_has_querier_adjacent(struct net_device *dev, int proto);
bool br_multicast_has_router_adjacent(struct net_device *dev, int proto);
bool br_multicast_enabled(const struct net_device *dev);
bool br_multicast_router(const struct net_device *dev);
#else
static inline int br_multicast_list_adjacent(struct net_device *dev,
struct list_head *br_ip_list)
{
return 0;
}
static inline bool br_multicast_has_querier_anywhere(struct net_device *dev,
int proto)
{
return false;
}
static inline bool br_multicast_has_querier_adjacent(struct net_device *dev,
int proto)
{
return false;
}
static inline bool br_multicast_has_router_adjacent(struct net_device *dev,
int proto)
{
return true;
}
static inline bool br_multicast_enabled(const struct net_device *dev)
{
return false;
}
static inline bool br_multicast_router(const struct net_device *dev)
{
return false;
}
#endif
#if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_VLAN_FILTERING)
bool br_vlan_enabled(const struct net_device *dev);
int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid);
int br_vlan_get_pvid_rcu(const struct net_device *dev, u16 *p_pvid);
int br_vlan_get_proto(const struct net_device *dev, u16 *p_proto);
int br_vlan_get_info(const struct net_device *dev, u16 vid,
struct bridge_vlan_info *p_vinfo);
int br_vlan_get_info_rcu(const struct net_device *dev, u16 vid,
struct bridge_vlan_info *p_vinfo);
bool br_mst_enabled(const struct net_device *dev);
int br_mst_get_info(const struct net_device *dev, u16 msti, unsigned long *vids);
int br_mst_get_state(const struct net_device *dev, u16 msti, u8 *state);
#else
static inline bool br_vlan_enabled(const struct net_device *dev)
{
return false;
}
static inline int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid)
{
return -EINVAL;
}
static inline int br_vlan_get_proto(const struct net_device *dev, u16 *p_proto)
{
return -EINVAL;
}
static inline int br_vlan_get_pvid_rcu(const struct net_device *dev, u16 *p_pvid)
{
return -EINVAL;
}
static inline int br_vlan_get_info(const struct net_device *dev, u16 vid,
struct bridge_vlan_info *p_vinfo)
{
return -EINVAL;
}
static inline int br_vlan_get_info_rcu(const struct net_device *dev, u16 vid,
struct bridge_vlan_info *p_vinfo)
{
return -EINVAL;
}
static inline bool br_mst_enabled(const struct net_device *dev)
{
return false;
}
static inline int br_mst_get_info(const struct net_device *dev, u16 msti,
unsigned long *vids)
{
return -EINVAL;
}
static inline int br_mst_get_state(const struct net_device *dev, u16 msti,
u8 *state)
{
return -EINVAL;
}
#endif
#if IS_ENABLED(CONFIG_BRIDGE)
struct net_device *br_fdb_find_port(const struct net_device *br_dev,
const unsigned char *addr,
__u16 vid);
void br_fdb_clear_offload(const struct net_device *dev, u16 vid);
bool br_port_flag_is_set(const struct net_device *dev, unsigned long flag);
u8 br_port_get_stp_state(const struct net_device *dev);
clock_t br_get_ageing_time(const struct net_device *br_dev);
#else
static inline struct net_device *
br_fdb_find_port(const struct net_device *br_dev,
const unsigned char *addr,
__u16 vid)
{
return NULL;
}
static inline void br_fdb_clear_offload(const struct net_device *dev, u16 vid)
{
}
static inline bool
br_port_flag_is_set(const struct net_device *dev, unsigned long flag)
{
return false;
}
static inline u8 br_port_get_stp_state(const struct net_device *dev)
{
return BR_STATE_DISABLED;
}
static inline clock_t br_get_ageing_time(const struct net_device *br_dev)
{
return 0;
}
#endif
#endif
View git blame Copy permalink