linux_dsm_epyc7002/include/net/if_inet6.h
Hannes Frederic Sowa c15b1ccadb ipv6: move DAD and addrconf_verify processing to workqueue
addrconf_join_solict and addrconf_join_anycast may cause actions which
need rtnl locked, especially on first address creation.

A new DAD state is introduced which defers processing of the initial
DAD processing into a workqueue.

To get rtnl lock we need to push the code paths which depend on those
calls up to workqueues, specifically addrconf_verify and the DAD
processing.

(v2)
addrconf_dad_failure needs to be queued up to the workqueue, too. This
patch introduces a new DAD state and stop the DAD processing in the
workqueue (this is because of the possible ipv6_del_addr processing
which removes the solicited multicast address from the device).

addrconf_verify_lock is removed, too. After the transition it is not
needed any more.

As we are not processing in bottom half anymore we need to be a bit more
careful about disabling bottom half out when we lock spin_locks which are also
used in bh.

Relevant backtrace:
[  541.030090] RTNL: assertion failed at net/core/dev.c (4496)
[  541.031143] CPU: 0 PID: 0 Comm: swapper/0 Tainted: G           O 3.10.33-1-amd64-vyatta #1
[  541.031145] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2007
[  541.031146]  ffffffff8148a9f0 000000000000002f ffffffff813c98c1 ffff88007c4451f8
[  541.031148]  0000000000000000 0000000000000000 ffffffff813d3540 ffff88007fc03d18
[  541.031150]  0000880000000006 ffff88007c445000 ffffffffa0194160 0000000000000000
[  541.031152] Call Trace:
[  541.031153]  <IRQ>  [<ffffffff8148a9f0>] ? dump_stack+0xd/0x17
[  541.031180]  [<ffffffff813c98c1>] ? __dev_set_promiscuity+0x101/0x180
[  541.031183]  [<ffffffff813d3540>] ? __hw_addr_create_ex+0x60/0xc0
[  541.031185]  [<ffffffff813cfe1a>] ? __dev_set_rx_mode+0xaa/0xc0
[  541.031189]  [<ffffffff813d3a81>] ? __dev_mc_add+0x61/0x90
[  541.031198]  [<ffffffffa01dcf9c>] ? igmp6_group_added+0xfc/0x1a0 [ipv6]
[  541.031208]  [<ffffffff8111237b>] ? kmem_cache_alloc+0xcb/0xd0
[  541.031212]  [<ffffffffa01ddcd7>] ? ipv6_dev_mc_inc+0x267/0x300 [ipv6]
[  541.031216]  [<ffffffffa01c2fae>] ? addrconf_join_solict+0x2e/0x40 [ipv6]
[  541.031219]  [<ffffffffa01ba2e9>] ? ipv6_dev_ac_inc+0x159/0x1f0 [ipv6]
[  541.031223]  [<ffffffffa01c0772>] ? addrconf_join_anycast+0x92/0xa0 [ipv6]
[  541.031226]  [<ffffffffa01c311e>] ? __ipv6_ifa_notify+0x11e/0x1e0 [ipv6]
[  541.031229]  [<ffffffffa01c3213>] ? ipv6_ifa_notify+0x33/0x50 [ipv6]
[  541.031233]  [<ffffffffa01c36c8>] ? addrconf_dad_completed+0x28/0x100 [ipv6]
[  541.031241]  [<ffffffff81075c1d>] ? task_cputime+0x2d/0x50
[  541.031244]  [<ffffffffa01c38d6>] ? addrconf_dad_timer+0x136/0x150 [ipv6]
[  541.031247]  [<ffffffffa01c37a0>] ? addrconf_dad_completed+0x100/0x100 [ipv6]
[  541.031255]  [<ffffffff8105313a>] ? call_timer_fn.isra.22+0x2a/0x90
[  541.031258]  [<ffffffffa01c37a0>] ? addrconf_dad_completed+0x100/0x100 [ipv6]

Hunks and backtrace stolen from a patch by Stephen Hemminger.

Reported-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-28 16:54:50 -04:00

265 lines
6.1 KiB
C

/*
* inet6 interface/address list definitions
* Linux INET6 implementation
*
* Authors:
* Pedro Roque <roque@di.fc.ul.pt>
*
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#ifndef _NET_IF_INET6_H
#define _NET_IF_INET6_H
#include <net/snmp.h>
#include <linux/ipv6.h>
/* inet6_dev.if_flags */
#define IF_RA_OTHERCONF 0x80
#define IF_RA_MANAGED 0x40
#define IF_RA_RCVD 0x20
#define IF_RS_SENT 0x10
#define IF_READY 0x80000000
/* prefix flags */
#define IF_PREFIX_ONLINK 0x01
#define IF_PREFIX_AUTOCONF 0x02
enum {
INET6_IFADDR_STATE_PREDAD,
INET6_IFADDR_STATE_DAD,
INET6_IFADDR_STATE_POSTDAD,
INET6_IFADDR_STATE_ERRDAD,
INET6_IFADDR_STATE_UP,
INET6_IFADDR_STATE_DEAD,
};
struct inet6_ifaddr {
struct in6_addr addr;
__u32 prefix_len;
/* In seconds, relative to tstamp. Expiry is at tstamp + HZ * lft. */
__u32 valid_lft;
__u32 prefered_lft;
atomic_t refcnt;
spinlock_t lock;
spinlock_t state_lock;
int state;
__u32 flags;
__u8 dad_probes;
__u16 scope;
unsigned long cstamp; /* created timestamp */
unsigned long tstamp; /* updated timestamp */
struct delayed_work dad_work;
struct inet6_dev *idev;
struct rt6_info *rt;
struct hlist_node addr_lst;
struct list_head if_list;
struct list_head tmp_list;
struct inet6_ifaddr *ifpub;
int regen_count;
bool tokenized;
struct rcu_head rcu;
struct in6_addr peer_addr;
};
struct ip6_sf_socklist {
unsigned int sl_max;
unsigned int sl_count;
struct in6_addr sl_addr[0];
};
#define IP6_SFLSIZE(count) (sizeof(struct ip6_sf_socklist) + \
(count) * sizeof(struct in6_addr))
#define IP6_SFBLOCK 10 /* allocate this many at once */
struct ipv6_mc_socklist {
struct in6_addr addr;
int ifindex;
struct ipv6_mc_socklist __rcu *next;
rwlock_t sflock;
unsigned int sfmode; /* MCAST_{INCLUDE,EXCLUDE} */
struct ip6_sf_socklist *sflist;
struct rcu_head rcu;
};
struct ip6_sf_list {
struct ip6_sf_list *sf_next;
struct in6_addr sf_addr;
unsigned long sf_count[2]; /* include/exclude counts */
unsigned char sf_gsresp; /* include in g & s response? */
unsigned char sf_oldin; /* change state */
unsigned char sf_crcount; /* retrans. left to send */
};
#define MAF_TIMER_RUNNING 0x01
#define MAF_LAST_REPORTER 0x02
#define MAF_LOADED 0x04
#define MAF_NOREPORT 0x08
#define MAF_GSQUERY 0x10
struct ifmcaddr6 {
struct in6_addr mca_addr;
struct inet6_dev *idev;
struct ifmcaddr6 *next;
struct ip6_sf_list *mca_sources;
struct ip6_sf_list *mca_tomb;
unsigned int mca_sfmode;
unsigned char mca_crcount;
unsigned long mca_sfcount[2];
struct timer_list mca_timer;
unsigned int mca_flags;
int mca_users;
atomic_t mca_refcnt;
spinlock_t mca_lock;
unsigned long mca_cstamp;
unsigned long mca_tstamp;
};
/* Anycast stuff */
struct ipv6_ac_socklist {
struct in6_addr acl_addr;
int acl_ifindex;
struct ipv6_ac_socklist *acl_next;
};
struct ifacaddr6 {
struct in6_addr aca_addr;
struct inet6_dev *aca_idev;
struct rt6_info *aca_rt;
struct ifacaddr6 *aca_next;
int aca_users;
atomic_t aca_refcnt;
spinlock_t aca_lock;
unsigned long aca_cstamp;
unsigned long aca_tstamp;
};
#define IFA_HOST IPV6_ADDR_LOOPBACK
#define IFA_LINK IPV6_ADDR_LINKLOCAL
#define IFA_SITE IPV6_ADDR_SITELOCAL
struct ipv6_devstat {
struct proc_dir_entry *proc_dir_entry;
DEFINE_SNMP_STAT(struct ipstats_mib, ipv6);
DEFINE_SNMP_STAT_ATOMIC(struct icmpv6_mib_device, icmpv6dev);
DEFINE_SNMP_STAT_ATOMIC(struct icmpv6msg_mib_device, icmpv6msgdev);
};
struct inet6_dev {
struct net_device *dev;
struct list_head addr_list;
struct ifmcaddr6 *mc_list;
struct ifmcaddr6 *mc_tomb;
spinlock_t mc_lock;
unsigned char mc_qrv; /* Query Robustness Variable */
unsigned char mc_gq_running;
unsigned char mc_ifc_count;
unsigned char mc_dad_count;
unsigned long mc_v1_seen; /* Max time we stay in MLDv1 mode */
unsigned long mc_qi; /* Query Interval */
unsigned long mc_qri; /* Query Response Interval */
unsigned long mc_maxdelay;
struct timer_list mc_gq_timer; /* general query timer */
struct timer_list mc_ifc_timer; /* interface change timer */
struct timer_list mc_dad_timer; /* dad complete mc timer */
struct ifacaddr6 *ac_list;
rwlock_t lock;
atomic_t refcnt;
__u32 if_flags;
int dead;
u8 rndid[8];
struct timer_list regen_timer;
struct list_head tempaddr_list;
struct in6_addr token;
struct neigh_parms *nd_parms;
struct ipv6_devconf cnf;
struct ipv6_devstat stats;
struct timer_list rs_timer;
__u8 rs_probes;
unsigned long tstamp; /* ipv6InterfaceTable update timestamp */
struct rcu_head rcu;
};
static inline void ipv6_eth_mc_map(const struct in6_addr *addr, char *buf)
{
/*
* +-------+-------+-------+-------+-------+-------+
* | 33 | 33 | DST13 | DST14 | DST15 | DST16 |
* +-------+-------+-------+-------+-------+-------+
*/
buf[0]= 0x33;
buf[1]= 0x33;
memcpy(buf + 2, &addr->s6_addr32[3], sizeof(__u32));
}
static inline void ipv6_arcnet_mc_map(const struct in6_addr *addr, char *buf)
{
buf[0] = 0x00;
}
static inline void ipv6_ib_mc_map(const struct in6_addr *addr,
const unsigned char *broadcast, char *buf)
{
unsigned char scope = broadcast[5] & 0xF;
buf[0] = 0; /* Reserved */
buf[1] = 0xff; /* Multicast QPN */
buf[2] = 0xff;
buf[3] = 0xff;
buf[4] = 0xff;
buf[5] = 0x10 | scope; /* scope from broadcast address */
buf[6] = 0x60; /* IPv6 signature */
buf[7] = 0x1b;
buf[8] = broadcast[8]; /* P_Key */
buf[9] = broadcast[9];
memcpy(buf + 10, addr->s6_addr + 6, 10);
}
static inline int ipv6_ipgre_mc_map(const struct in6_addr *addr,
const unsigned char *broadcast, char *buf)
{
if ((broadcast[0] | broadcast[1] | broadcast[2] | broadcast[3]) != 0) {
memcpy(buf, broadcast, 4);
} else {
/* v4mapped? */
if ((addr->s6_addr32[0] | addr->s6_addr32[1] |
(addr->s6_addr32[2] ^ htonl(0x0000ffff))) != 0)
return -EINVAL;
memcpy(buf, &addr->s6_addr32[3], 4);
}
return 0;
}
#endif