linux/include/net/addrconf.h
Amerigo Wang 8965779d2c ipv6,mcast: always hold idev->lock before mca_lock
dingtianhong reported the following deadlock detected by lockdep:

 ======================================================
 [ INFO: possible circular locking dependency detected ]
 3.4.24.05-0.1-default #1 Not tainted
 -------------------------------------------------------
 ksoftirqd/0/3 is trying to acquire lock:
  (&ndev->lock){+.+...}, at: [<ffffffff8147f804>] ipv6_get_lladdr+0x74/0x120

 but task is already holding lock:
  (&mc->mca_lock){+.+...}, at: [<ffffffff8149d130>] mld_send_report+0x40/0x150

 which lock already depends on the new lock.

 the existing dependency chain (in reverse order) is:

 -> #1 (&mc->mca_lock){+.+...}:
        [<ffffffff810a8027>] validate_chain+0x637/0x730
        [<ffffffff810a8417>] __lock_acquire+0x2f7/0x500
        [<ffffffff810a8734>] lock_acquire+0x114/0x150
        [<ffffffff814f691a>] rt_spin_lock+0x4a/0x60
        [<ffffffff8149e4bb>] igmp6_group_added+0x3b/0x120
        [<ffffffff8149e5d8>] ipv6_mc_up+0x38/0x60
        [<ffffffff81480a4d>] ipv6_find_idev+0x3d/0x80
        [<ffffffff81483175>] addrconf_notify+0x3d5/0x4b0
        [<ffffffff814fae3f>] notifier_call_chain+0x3f/0x80
        [<ffffffff81073471>] raw_notifier_call_chain+0x11/0x20
        [<ffffffff813d8722>] call_netdevice_notifiers+0x32/0x60
        [<ffffffff813d92d4>] __dev_notify_flags+0x34/0x80
        [<ffffffff813d9360>] dev_change_flags+0x40/0x70
        [<ffffffff813ea627>] do_setlink+0x237/0x8a0
        [<ffffffff813ebb6c>] rtnl_newlink+0x3ec/0x600
        [<ffffffff813eb4d0>] rtnetlink_rcv_msg+0x160/0x310
        [<ffffffff814040b9>] netlink_rcv_skb+0x89/0xb0
        [<ffffffff813eb357>] rtnetlink_rcv+0x27/0x40
        [<ffffffff81403e20>] netlink_unicast+0x140/0x180
        [<ffffffff81404a9e>] netlink_sendmsg+0x33e/0x380
        [<ffffffff813c4252>] sock_sendmsg+0x112/0x130
        [<ffffffff813c537e>] __sys_sendmsg+0x44e/0x460
        [<ffffffff813c5544>] sys_sendmsg+0x44/0x70
        [<ffffffff814feab9>] system_call_fastpath+0x16/0x1b

 -> #0 (&ndev->lock){+.+...}:
        [<ffffffff810a798e>] check_prev_add+0x3de/0x440
        [<ffffffff810a8027>] validate_chain+0x637/0x730
        [<ffffffff810a8417>] __lock_acquire+0x2f7/0x500
        [<ffffffff810a8734>] lock_acquire+0x114/0x150
        [<ffffffff814f6c82>] rt_read_lock+0x42/0x60
        [<ffffffff8147f804>] ipv6_get_lladdr+0x74/0x120
        [<ffffffff8149b036>] mld_newpack+0xb6/0x160
        [<ffffffff8149b18b>] add_grhead+0xab/0xc0
        [<ffffffff8149d03b>] add_grec+0x3ab/0x460
        [<ffffffff8149d14a>] mld_send_report+0x5a/0x150
        [<ffffffff8149f99e>] igmp6_timer_handler+0x4e/0xb0
        [<ffffffff8105705a>] call_timer_fn+0xca/0x1d0
        [<ffffffff81057b9f>] run_timer_softirq+0x1df/0x2e0
        [<ffffffff8104e8c7>] handle_pending_softirqs+0xf7/0x1f0
        [<ffffffff8104ea3b>] __do_softirq_common+0x7b/0xf0
        [<ffffffff8104f07f>] __thread_do_softirq+0x1af/0x210
        [<ffffffff8104f1c1>] run_ksoftirqd+0xe1/0x1f0
        [<ffffffff8106c7de>] kthread+0xae/0xc0
        [<ffffffff814fff74>] kernel_thread_helper+0x4/0x10

actually we can just hold idev->lock before taking pmc->mca_lock,
and avoid taking idev->lock again when iterating idev->addr_list,
since the upper callers of mld_newpack() already take
read_lock_bh(&idev->lock).

Reported-by: dingtianhong <dingtianhong@huawei.com>
Cc: dingtianhong <dingtianhong@huawei.com>
Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
Cc: David S. Miller <davem@davemloft.net>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Tested-by: Ding Tianhong <dingtianhong@huawei.com>
Tested-by: Chen Weilong <chenweilong@huawei.com>
Signed-off-by: Cong Wang <amwang@redhat.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-07-01 23:39:21 -07:00

348 lines
9.6 KiB
C

#ifndef _ADDRCONF_H
#define _ADDRCONF_H
#define MAX_RTR_SOLICITATIONS 3
#define RTR_SOLICITATION_INTERVAL (4*HZ)
#define MIN_VALID_LIFETIME (2*3600) /* 2 hours */
#define TEMP_VALID_LIFETIME (7*86400)
#define TEMP_PREFERRED_LIFETIME (86400)
#define REGEN_MAX_RETRY (3)
#define MAX_DESYNC_FACTOR (600)
#define ADDR_CHECK_FREQUENCY (120*HZ)
#define IPV6_MAX_ADDRESSES 16
#define ADDRCONF_TIMER_FUZZ_MINUS (HZ > 50 ? HZ / 50 : 1)
#define ADDRCONF_TIMER_FUZZ (HZ / 4)
#define ADDRCONF_TIMER_FUZZ_MAX (HZ)
#include <linux/in.h>
#include <linux/in6.h>
struct prefix_info {
__u8 type;
__u8 length;
__u8 prefix_len;
#if defined(__BIG_ENDIAN_BITFIELD)
__u8 onlink : 1,
autoconf : 1,
reserved : 6;
#elif defined(__LITTLE_ENDIAN_BITFIELD)
__u8 reserved : 6,
autoconf : 1,
onlink : 1;
#else
#error "Please fix <asm/byteorder.h>"
#endif
__be32 valid;
__be32 prefered;
__be32 reserved2;
struct in6_addr prefix;
};
#include <linux/netdevice.h>
#include <net/if_inet6.h>
#include <net/ipv6.h>
#define IN6_ADDR_HSIZE_SHIFT 4
#define IN6_ADDR_HSIZE (1 << IN6_ADDR_HSIZE_SHIFT)
extern int addrconf_init(void);
extern void addrconf_cleanup(void);
extern int addrconf_add_ifaddr(struct net *net,
void __user *arg);
extern int addrconf_del_ifaddr(struct net *net,
void __user *arg);
extern int addrconf_set_dstaddr(struct net *net,
void __user *arg);
extern int ipv6_chk_addr(struct net *net,
const struct in6_addr *addr,
const struct net_device *dev,
int strict);
#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
extern int ipv6_chk_home_addr(struct net *net,
const struct in6_addr *addr);
#endif
extern int ipv6_chk_prefix(const struct in6_addr *addr,
struct net_device *dev);
extern struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net,
const struct in6_addr *addr,
struct net_device *dev,
int strict);
extern int ipv6_dev_get_saddr(struct net *net,
const struct net_device *dev,
const struct in6_addr *daddr,
unsigned int srcprefs,
struct in6_addr *saddr);
extern int __ipv6_get_lladdr(struct inet6_dev *idev,
struct in6_addr *addr,
unsigned char banned_flags);
extern int ipv6_get_lladdr(struct net_device *dev,
struct in6_addr *addr,
unsigned char banned_flags);
extern int ipv6_rcv_saddr_equal(const struct sock *sk,
const struct sock *sk2);
extern void addrconf_join_solict(struct net_device *dev,
const struct in6_addr *addr);
extern void addrconf_leave_solict(struct inet6_dev *idev,
const struct in6_addr *addr);
static inline unsigned long addrconf_timeout_fixup(u32 timeout,
unsigned int unit)
{
if (timeout == 0xffffffff)
return ~0UL;
/*
* Avoid arithmetic overflow.
* Assuming unit is constant and non-zero, this "if" statement
* will go away on 64bit archs.
*/
if (0xfffffffe > LONG_MAX / unit && timeout > LONG_MAX / unit)
return LONG_MAX / unit;
return timeout;
}
static inline int addrconf_finite_timeout(unsigned long timeout)
{
return ~timeout;
}
/*
* IPv6 Address Label subsystem (addrlabel.c)
*/
extern int ipv6_addr_label_init(void);
extern void ipv6_addr_label_cleanup(void);
extern void ipv6_addr_label_rtnl_register(void);
extern u32 ipv6_addr_label(struct net *net,
const struct in6_addr *addr,
int type, int ifindex);
/*
* multicast prototypes (mcast.c)
*/
extern int ipv6_sock_mc_join(struct sock *sk, int ifindex,
const struct in6_addr *addr);
extern int ipv6_sock_mc_drop(struct sock *sk, int ifindex,
const struct in6_addr *addr);
extern void ipv6_sock_mc_close(struct sock *sk);
extern bool inet6_mc_check(struct sock *sk,
const struct in6_addr *mc_addr,
const struct in6_addr *src_addr);
extern int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr);
extern int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr);
extern int ipv6_dev_mc_dec(struct net_device *dev, const struct in6_addr *addr);
extern void ipv6_mc_up(struct inet6_dev *idev);
extern void ipv6_mc_down(struct inet6_dev *idev);
extern void ipv6_mc_unmap(struct inet6_dev *idev);
extern void ipv6_mc_remap(struct inet6_dev *idev);
extern void ipv6_mc_init_dev(struct inet6_dev *idev);
extern void ipv6_mc_destroy_dev(struct inet6_dev *idev);
extern void addrconf_dad_failure(struct inet6_ifaddr *ifp);
extern bool ipv6_chk_mcast_addr(struct net_device *dev,
const struct in6_addr *group,
const struct in6_addr *src_addr);
extern void ipv6_mc_dad_complete(struct inet6_dev *idev);
/*
* identify MLD packets for MLD filter exceptions
*/
static inline bool ipv6_is_mld(struct sk_buff *skb, int nexthdr, int offset)
{
struct icmp6hdr *hdr;
if (nexthdr != IPPROTO_ICMPV6 ||
!pskb_network_may_pull(skb, offset + sizeof(struct icmp6hdr)))
return false;
hdr = (struct icmp6hdr *)(skb_network_header(skb) + offset);
switch (hdr->icmp6_type) {
case ICMPV6_MGM_QUERY:
case ICMPV6_MGM_REPORT:
case ICMPV6_MGM_REDUCTION:
case ICMPV6_MLD2_REPORT:
return true;
default:
break;
}
return false;
}
extern void addrconf_prefix_rcv(struct net_device *dev,
u8 *opt, int len, bool sllao);
/*
* anycast prototypes (anycast.c)
*/
extern int ipv6_sock_ac_join(struct sock *sk,int ifindex, const struct in6_addr *addr);
extern int ipv6_sock_ac_drop(struct sock *sk,int ifindex, const struct in6_addr *addr);
extern void ipv6_sock_ac_close(struct sock *sk);
extern int ipv6_dev_ac_inc(struct net_device *dev, const struct in6_addr *addr);
extern int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr);
extern bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev,
const struct in6_addr *addr);
/* Device notifier */
extern int register_inet6addr_notifier(struct notifier_block *nb);
extern int unregister_inet6addr_notifier(struct notifier_block *nb);
extern int inet6addr_notifier_call_chain(unsigned long val, void *v);
extern void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex,
struct ipv6_devconf *devconf);
/**
* __in6_dev_get - get inet6_dev pointer from netdevice
* @dev: network device
*
* Caller must hold rcu_read_lock or RTNL, because this function
* does not take a reference on the inet6_dev.
*/
static inline struct inet6_dev *__in6_dev_get(const struct net_device *dev)
{
return rcu_dereference_rtnl(dev->ip6_ptr);
}
/**
* in6_dev_get - get inet6_dev pointer from netdevice
* @dev: network device
*
* This version can be used in any context, and takes a reference
* on the inet6_dev. Callers must use in6_dev_put() later to
* release this reference.
*/
static inline struct inet6_dev *in6_dev_get(const struct net_device *dev)
{
struct inet6_dev *idev;
rcu_read_lock();
idev = rcu_dereference(dev->ip6_ptr);
if (idev)
atomic_inc(&idev->refcnt);
rcu_read_unlock();
return idev;
}
extern void in6_dev_finish_destroy(struct inet6_dev *idev);
static inline void in6_dev_put(struct inet6_dev *idev)
{
if (atomic_dec_and_test(&idev->refcnt))
in6_dev_finish_destroy(idev);
}
static inline void __in6_dev_put(struct inet6_dev *idev)
{
atomic_dec(&idev->refcnt);
}
static inline void in6_dev_hold(struct inet6_dev *idev)
{
atomic_inc(&idev->refcnt);
}
extern void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp);
static inline void in6_ifa_put(struct inet6_ifaddr *ifp)
{
if (atomic_dec_and_test(&ifp->refcnt))
inet6_ifa_finish_destroy(ifp);
}
static inline void __in6_ifa_put(struct inet6_ifaddr *ifp)
{
atomic_dec(&ifp->refcnt);
}
static inline void in6_ifa_hold(struct inet6_ifaddr *ifp)
{
atomic_inc(&ifp->refcnt);
}
/*
* compute link-local solicited-node multicast address
*/
static inline void addrconf_addr_solict_mult(const struct in6_addr *addr,
struct in6_addr *solicited)
{
ipv6_addr_set(solicited,
htonl(0xFF020000), 0,
htonl(0x1),
htonl(0xFF000000) | addr->s6_addr32[3]);
}
static inline bool ipv6_addr_is_multicast(const struct in6_addr *addr)
{
return (addr->s6_addr32[0] & htonl(0xFF000000)) == htonl(0xFF000000);
}
static inline bool ipv6_addr_is_ll_all_nodes(const struct in6_addr *addr)
{
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
__u64 *p = (__u64 *)addr;
return ((p[0] ^ cpu_to_be64(0xff02000000000000UL)) | (p[1] ^ cpu_to_be64(1))) == 0UL;
#else
return ((addr->s6_addr32[0] ^ htonl(0xff020000)) |
addr->s6_addr32[1] | addr->s6_addr32[2] |
(addr->s6_addr32[3] ^ htonl(0x00000001))) == 0;
#endif
}
static inline bool ipv6_addr_is_ll_all_routers(const struct in6_addr *addr)
{
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
__u64 *p = (__u64 *)addr;
return ((p[0] ^ cpu_to_be64(0xff02000000000000UL)) | (p[1] ^ cpu_to_be64(2))) == 0UL;
#else
return ((addr->s6_addr32[0] ^ htonl(0xff020000)) |
addr->s6_addr32[1] | addr->s6_addr32[2] |
(addr->s6_addr32[3] ^ htonl(0x00000002))) == 0;
#endif
}
static inline bool ipv6_addr_is_isatap(const struct in6_addr *addr)
{
return (addr->s6_addr32[2] | htonl(0x02000000)) == htonl(0x02005EFE);
}
static inline bool ipv6_addr_is_solict_mult(const struct in6_addr *addr)
{
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
__u64 *p = (__u64 *)addr;
return ((p[0] ^ cpu_to_be64(0xff02000000000000UL)) |
((p[1] ^ cpu_to_be64(0x00000001ff000000UL)) &
cpu_to_be64(0xffffffffff000000UL))) == 0UL;
#else
return ((addr->s6_addr32[0] ^ htonl(0xff020000)) |
addr->s6_addr32[1] |
(addr->s6_addr32[2] ^ htonl(0x00000001)) |
(addr->s6_addr[12] ^ 0xff)) == 0;
#endif
}
#ifdef CONFIG_PROC_FS
extern int if6_proc_init(void);
extern void if6_proc_exit(void);
#endif
#endif