linux-next/include/linux/if_team.h
Ziyang Xuan 4920327601 team: fix null-ptr-deref when team device type is changed
Get a null-ptr-deref bug as follows with reproducer [1].

BUG: kernel NULL pointer dereference, address: 0000000000000228
...
RIP: 0010:vlan_dev_hard_header+0x35/0x140 [8021q]
...
Call Trace:
 <TASK>
 ? __die+0x24/0x70
 ? page_fault_oops+0x82/0x150
 ? exc_page_fault+0x69/0x150
 ? asm_exc_page_fault+0x26/0x30
 ? vlan_dev_hard_header+0x35/0x140 [8021q]
 ? vlan_dev_hard_header+0x8e/0x140 [8021q]
 neigh_connected_output+0xb2/0x100
 ip6_finish_output2+0x1cb/0x520
 ? nf_hook_slow+0x43/0xc0
 ? ip6_mtu+0x46/0x80
 ip6_finish_output+0x2a/0xb0
 mld_sendpack+0x18f/0x250
 mld_ifc_work+0x39/0x160
 process_one_work+0x1e6/0x3f0
 worker_thread+0x4d/0x2f0
 ? __pfx_worker_thread+0x10/0x10
 kthread+0xe5/0x120
 ? __pfx_kthread+0x10/0x10
 ret_from_fork+0x34/0x50
 ? __pfx_kthread+0x10/0x10
 ret_from_fork_asm+0x1b/0x30

[1]
$ teamd -t team0 -d -c '{"runner": {"name": "loadbalance"}}'
$ ip link add name t-dummy type dummy
$ ip link add link t-dummy name t-dummy.100 type vlan id 100
$ ip link add name t-nlmon type nlmon
$ ip link set t-nlmon master team0
$ ip link set t-nlmon nomaster
$ ip link set t-dummy up
$ ip link set team0 up
$ ip link set t-dummy.100 down
$ ip link set t-dummy.100 master team0

When enslave a vlan device to team device and team device type is changed
from non-ether to ether, header_ops of team device is changed to
vlan_header_ops. That is incorrect and will trigger null-ptr-deref
for vlan->real_dev in vlan_dev_hard_header() because team device is not
a vlan device.

Cache eth_header_ops in team_setup(), then assign cached header_ops to
header_ops of team net device when its type is changed from non-ether
to ether to fix the bug.

Fixes: 1d76efe157 ("team: add support for non-ethernet devices")
Suggested-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: Ziyang Xuan <william.xuanziyang@huawei.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20230918123011.1884401-1-william.xuanziyang@huawei.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2023-09-19 16:28:37 +02:00

319 lines
7.9 KiB
C

/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* include/linux/if_team.h - Network team device driver header
* Copyright (c) 2011 Jiri Pirko <jpirko@redhat.com>
*/
#ifndef _LINUX_IF_TEAM_H_
#define _LINUX_IF_TEAM_H_
#include <linux/netpoll.h>
#include <net/sch_generic.h>
#include <linux/types.h>
#include <uapi/linux/if_team.h>
struct team_pcpu_stats {
u64_stats_t rx_packets;
u64_stats_t rx_bytes;
u64_stats_t rx_multicast;
u64_stats_t tx_packets;
u64_stats_t tx_bytes;
struct u64_stats_sync syncp;
u32 rx_dropped;
u32 tx_dropped;
u32 rx_nohandler;
};
struct team;
struct team_port {
struct net_device *dev;
struct hlist_node hlist; /* node in enabled ports hash list */
struct list_head list; /* node in ordinary list */
struct team *team;
int index; /* index of enabled port. If disabled, it's set to -1 */
bool linkup; /* either state.linkup or user.linkup */
struct {
bool linkup;
u32 speed;
u8 duplex;
} state;
/* Values set by userspace */
struct {
bool linkup;
bool linkup_enabled;
} user;
/* Custom gennetlink interface related flags */
bool changed;
bool removed;
/*
* A place for storing original values of the device before it
* become a port.
*/
struct {
unsigned char dev_addr[MAX_ADDR_LEN];
unsigned int mtu;
} orig;
#ifdef CONFIG_NET_POLL_CONTROLLER
struct netpoll *np;
#endif
s32 priority; /* lower number ~ higher priority */
u16 queue_id;
struct list_head qom_list; /* node in queue override mapping list */
struct rcu_head rcu;
long mode_priv[];
};
static inline struct team_port *team_port_get_rcu(const struct net_device *dev)
{
return rcu_dereference(dev->rx_handler_data);
}
static inline bool team_port_enabled(struct team_port *port)
{
return port->index != -1;
}
static inline bool team_port_txable(struct team_port *port)
{
return port->linkup && team_port_enabled(port);
}
static inline bool team_port_dev_txable(const struct net_device *port_dev)
{
struct team_port *port;
bool txable;
rcu_read_lock();
port = team_port_get_rcu(port_dev);
txable = port ? team_port_txable(port) : false;
rcu_read_unlock();
return txable;
}
#ifdef CONFIG_NET_POLL_CONTROLLER
static inline void team_netpoll_send_skb(struct team_port *port,
struct sk_buff *skb)
{
netpoll_send_skb(port->np, skb);
}
#else
static inline void team_netpoll_send_skb(struct team_port *port,
struct sk_buff *skb)
{
}
#endif
struct team_mode_ops {
int (*init)(struct team *team);
void (*exit)(struct team *team);
rx_handler_result_t (*receive)(struct team *team,
struct team_port *port,
struct sk_buff *skb);
bool (*transmit)(struct team *team, struct sk_buff *skb);
int (*port_enter)(struct team *team, struct team_port *port);
void (*port_leave)(struct team *team, struct team_port *port);
void (*port_change_dev_addr)(struct team *team, struct team_port *port);
void (*port_enabled)(struct team *team, struct team_port *port);
void (*port_disabled)(struct team *team, struct team_port *port);
};
extern int team_modeop_port_enter(struct team *team, struct team_port *port);
extern void team_modeop_port_change_dev_addr(struct team *team,
struct team_port *port);
enum team_option_type {
TEAM_OPTION_TYPE_U32,
TEAM_OPTION_TYPE_STRING,
TEAM_OPTION_TYPE_BINARY,
TEAM_OPTION_TYPE_BOOL,
TEAM_OPTION_TYPE_S32,
};
struct team_option_inst_info {
u32 array_index;
struct team_port *port; /* != NULL if per-port */
};
struct team_gsetter_ctx {
union {
u32 u32_val;
const char *str_val;
struct {
const void *ptr;
u32 len;
} bin_val;
bool bool_val;
s32 s32_val;
} data;
struct team_option_inst_info *info;
};
struct team_option {
struct list_head list;
const char *name;
bool per_port;
unsigned int array_size; /* != 0 means the option is array */
enum team_option_type type;
void (*init)(struct team *team, struct team_option_inst_info *info);
void (*getter)(struct team *team, struct team_gsetter_ctx *ctx);
int (*setter)(struct team *team, struct team_gsetter_ctx *ctx);
};
extern void team_option_inst_set_change(struct team_option_inst_info *opt_inst_info);
extern void team_options_change_check(struct team *team);
struct team_mode {
const char *kind;
struct module *owner;
size_t priv_size;
size_t port_priv_size;
const struct team_mode_ops *ops;
enum netdev_lag_tx_type lag_tx_type;
};
#define TEAM_PORT_HASHBITS 4
#define TEAM_PORT_HASHENTRIES (1 << TEAM_PORT_HASHBITS)
#define TEAM_MODE_PRIV_LONGS 4
#define TEAM_MODE_PRIV_SIZE (sizeof(long) * TEAM_MODE_PRIV_LONGS)
struct team {
struct net_device *dev; /* associated netdevice */
struct team_pcpu_stats __percpu *pcpu_stats;
const struct header_ops *header_ops_cache;
struct mutex lock; /* used for overall locking, e.g. port lists write */
/*
* List of enabled ports and their count
*/
int en_port_count;
struct hlist_head en_port_hlist[TEAM_PORT_HASHENTRIES];
struct list_head port_list; /* list of all ports */
struct list_head option_list;
struct list_head option_inst_list; /* list of option instances */
const struct team_mode *mode;
struct team_mode_ops ops;
bool user_carrier_enabled;
bool queue_override_enabled;
struct list_head *qom_lists; /* array of queue override mapping lists */
bool port_mtu_change_allowed;
bool notifier_ctx;
struct {
unsigned int count;
unsigned int interval; /* in ms */
atomic_t count_pending;
struct delayed_work dw;
} notify_peers;
struct {
unsigned int count;
unsigned int interval; /* in ms */
atomic_t count_pending;
struct delayed_work dw;
} mcast_rejoin;
struct lock_class_key team_lock_key;
long mode_priv[TEAM_MODE_PRIV_LONGS];
};
static inline int team_dev_queue_xmit(struct team *team, struct team_port *port,
struct sk_buff *skb)
{
BUILD_BUG_ON(sizeof(skb->queue_mapping) !=
sizeof(qdisc_skb_cb(skb)->slave_dev_queue_mapping));
skb_set_queue_mapping(skb, qdisc_skb_cb(skb)->slave_dev_queue_mapping);
skb->dev = port->dev;
if (unlikely(netpoll_tx_running(team->dev))) {
team_netpoll_send_skb(port, skb);
return 0;
}
return dev_queue_xmit(skb);
}
static inline struct hlist_head *team_port_index_hash(struct team *team,
int port_index)
{
return &team->en_port_hlist[port_index & (TEAM_PORT_HASHENTRIES - 1)];
}
static inline struct team_port *team_get_port_by_index(struct team *team,
int port_index)
{
struct team_port *port;
struct hlist_head *head = team_port_index_hash(team, port_index);
hlist_for_each_entry(port, head, hlist)
if (port->index == port_index)
return port;
return NULL;
}
static inline int team_num_to_port_index(struct team *team, unsigned int num)
{
int en_port_count = READ_ONCE(team->en_port_count);
if (unlikely(!en_port_count))
return 0;
return num % en_port_count;
}
static inline struct team_port *team_get_port_by_index_rcu(struct team *team,
int port_index)
{
struct team_port *port;
struct hlist_head *head = team_port_index_hash(team, port_index);
hlist_for_each_entry_rcu(port, head, hlist)
if (port->index == port_index)
return port;
return NULL;
}
static inline struct team_port *
team_get_first_port_txable_rcu(struct team *team, struct team_port *port)
{
struct team_port *cur;
if (likely(team_port_txable(port)))
return port;
cur = port;
list_for_each_entry_continue_rcu(cur, &team->port_list, list)
if (team_port_txable(cur))
return cur;
list_for_each_entry_rcu(cur, &team->port_list, list) {
if (cur == port)
break;
if (team_port_txable(cur))
return cur;
}
return NULL;
}
extern int team_options_register(struct team *team,
const struct team_option *option,
size_t option_count);
extern void team_options_unregister(struct team *team,
const struct team_option *option,
size_t option_count);
extern int team_mode_register(const struct team_mode *mode);
extern void team_mode_unregister(const struct team_mode *mode);
#define TEAM_DEFAULT_NUM_TX_QUEUES 16
#define TEAM_DEFAULT_NUM_RX_QUEUES 16
#define MODULE_ALIAS_TEAM_MODE(kind) MODULE_ALIAS("team-mode-" kind)
#endif /* _LINUX_IF_TEAM_H_ */