linux/include/net/if_inet6.h

262 lines
5.9 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* inet6 interface/address list definitions
* Linux INET6 implementation
*
* Authors:
* Pedro Roque <roque@di.fc.ul.pt>
*/
#ifndef _NET_IF_INET6_H
#define _NET_IF_INET6_H
#include <net/snmp.h>
#include <linux/ipv6.h>
#include <linux/refcount.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 {
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 01:28:07 +08:00
INET6_IFADDR_STATE_PREDAD,
INET6_IFADDR_STATE_DAD,
INET6_IFADDR_STATE_POSTDAD,
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 01:28:07 +08:00
INET6_IFADDR_STATE_ERRDAD,
INET6_IFADDR_STATE_DEAD,
};
struct inet6_ifaddr {
struct in6_addr addr;
__u32 prefix_len;
__u32 rt_priority;
/* In seconds, relative to tstamp. Expiry is at tstamp + HZ * lft. */
__u32 valid_lft;
__u32 prefered_lft;
refcount_t refcnt;
spinlock_t lock;
int state;
__u32 flags;
__u8 dad_probes;
__u8 stable_privacy_retry;
__u16 scope;
__u64 dad_nonce;
unsigned long cstamp; /* created timestamp */
unsigned long tstamp; /* updated timestamp */
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 01:28:07 +08:00
struct delayed_work dad_work;
struct inet6_dev *idev;
struct fib6_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;
ipv6: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-08 03:02:16 +08:00
struct in6_addr sl_addr[];
};
#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;
unsigned int sfmode; /* MCAST_{INCLUDE,EXCLUDE} */
struct ipv6_mc_socklist __rcu *next;
rwlock_t sflock;
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;
refcount_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 fib6_info *aca_rt;
struct ifacaddr6 *aca_next;
struct hlist_node aca_addr_lst;
int aca_users;
refcount_t aca_refcnt;
unsigned long aca_cstamp;
unsigned long aca_tstamp;
struct rcu_head rcu;
};
#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;
net: ipv6: mld: fix v1/v2 switchback timeout to rfc3810, 9.12. i) RFC3810, 9.2. Query Interval [QI] says: The Query Interval variable denotes the interval between General Queries sent by the Querier. Default value: 125 seconds. [...] ii) RFC3810, 9.3. Query Response Interval [QRI] says: The Maximum Response Delay used to calculate the Maximum Response Code inserted into the periodic General Queries. Default value: 10000 (10 seconds) [...] The number of seconds represented by the [Query Response Interval] must be less than the [Query Interval]. iii) RFC3810, 9.12. Older Version Querier Present Timeout [OVQPT] says: The Older Version Querier Present Timeout is the time-out for transitioning a host back to MLDv2 Host Compatibility Mode. When an MLDv1 query is received, MLDv2 hosts set their Older Version Querier Present Timer to [Older Version Querier Present Timeout]. This value MUST be ([Robustness Variable] times (the [Query Interval] in the last Query received)) plus ([Query Response Interval]). Hence, on *default* the timeout results in: [RV] = 2, [QI] = 125sec, [QRI] = 10sec [OVQPT] = [RV] * [QI] + [QRI] = 260sec Having that said, we currently calculate [OVQPT] (here given as 'switchback' variable) as ... switchback = (idev->mc_qrv + 1) * max_delay RFC3810, 9.12. says "the [Query Interval] in the last Query received". In section "9.14. Configuring timers", it is said: This section is meant to provide advice to network administrators on how to tune these settings to their network. Ambitious router implementations might tune these settings dynamically based upon changing characteristics of the network. [...] iv) RFC38010, 9.14.2. Query Interval: The overall level of periodic MLD traffic is inversely proportional to the Query Interval. A longer Query Interval results in a lower overall level of MLD traffic. The value of the Query Interval MUST be equal to or greater than the Maximum Response Delay used to calculate the Maximum Response Code inserted in General Query messages. I assume that was why switchback is calculated as is (3 * max_delay), although this setting seems to be meant for routers only to configure their [QI] interval for non-default intervals. So usage here like this is clearly wrong. Concluding, the current behaviour in IPv6's multicast code is not conform to the RFC as switch back is calculated wrongly. That is, it has a too small value, so MLDv2 hosts switch back again to MLDv2 way too early, i.e. ~30secs instead of ~260secs on default. Hence, introduce necessary helper functions and fix this up properly as it should be. Introduced in 06da92283 ("[IPV6]: Add MLDv2 support."). Credits to Hannes Frederic Sowa who also had a hand in this as well. Also thanks to Hangbin Liu who did initial testing. Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Cc: David Stevens <dlstevens@us.ibm.com> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-09-04 06:19:37 +08:00
unsigned char mc_qrv; /* Query Robustness Variable */
unsigned char mc_gq_running;
unsigned char mc_ifc_count;
unsigned char mc_dad_count;
net: ipv6: mld: fix v1/v2 switchback timeout to rfc3810, 9.12. i) RFC3810, 9.2. Query Interval [QI] says: The Query Interval variable denotes the interval between General Queries sent by the Querier. Default value: 125 seconds. [...] ii) RFC3810, 9.3. Query Response Interval [QRI] says: The Maximum Response Delay used to calculate the Maximum Response Code inserted into the periodic General Queries. Default value: 10000 (10 seconds) [...] The number of seconds represented by the [Query Response Interval] must be less than the [Query Interval]. iii) RFC3810, 9.12. Older Version Querier Present Timeout [OVQPT] says: The Older Version Querier Present Timeout is the time-out for transitioning a host back to MLDv2 Host Compatibility Mode. When an MLDv1 query is received, MLDv2 hosts set their Older Version Querier Present Timer to [Older Version Querier Present Timeout]. This value MUST be ([Robustness Variable] times (the [Query Interval] in the last Query received)) plus ([Query Response Interval]). Hence, on *default* the timeout results in: [RV] = 2, [QI] = 125sec, [QRI] = 10sec [OVQPT] = [RV] * [QI] + [QRI] = 260sec Having that said, we currently calculate [OVQPT] (here given as 'switchback' variable) as ... switchback = (idev->mc_qrv + 1) * max_delay RFC3810, 9.12. says "the [Query Interval] in the last Query received". In section "9.14. Configuring timers", it is said: This section is meant to provide advice to network administrators on how to tune these settings to their network. Ambitious router implementations might tune these settings dynamically based upon changing characteristics of the network. [...] iv) RFC38010, 9.14.2. Query Interval: The overall level of periodic MLD traffic is inversely proportional to the Query Interval. A longer Query Interval results in a lower overall level of MLD traffic. The value of the Query Interval MUST be equal to or greater than the Maximum Response Delay used to calculate the Maximum Response Code inserted in General Query messages. I assume that was why switchback is calculated as is (3 * max_delay), although this setting seems to be meant for routers only to configure their [QI] interval for non-default intervals. So usage here like this is clearly wrong. Concluding, the current behaviour in IPv6's multicast code is not conform to the RFC as switch back is calculated wrongly. That is, it has a too small value, so MLDv2 hosts switch back again to MLDv2 way too early, i.e. ~30secs instead of ~260secs on default. Hence, introduce necessary helper functions and fix this up properly as it should be. Introduced in 06da92283 ("[IPV6]: Add MLDv2 support."). Credits to Hannes Frederic Sowa who also had a hand in this as well. Also thanks to Hangbin Liu who did initial testing. Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Cc: David Stevens <dlstevens@us.ibm.com> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-09-04 06:19:37 +08:00
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;
net: ipv6: mld: fix v1/v2 switchback timeout to rfc3810, 9.12. i) RFC3810, 9.2. Query Interval [QI] says: The Query Interval variable denotes the interval between General Queries sent by the Querier. Default value: 125 seconds. [...] ii) RFC3810, 9.3. Query Response Interval [QRI] says: The Maximum Response Delay used to calculate the Maximum Response Code inserted into the periodic General Queries. Default value: 10000 (10 seconds) [...] The number of seconds represented by the [Query Response Interval] must be less than the [Query Interval]. iii) RFC3810, 9.12. Older Version Querier Present Timeout [OVQPT] says: The Older Version Querier Present Timeout is the time-out for transitioning a host back to MLDv2 Host Compatibility Mode. When an MLDv1 query is received, MLDv2 hosts set their Older Version Querier Present Timer to [Older Version Querier Present Timeout]. This value MUST be ([Robustness Variable] times (the [Query Interval] in the last Query received)) plus ([Query Response Interval]). Hence, on *default* the timeout results in: [RV] = 2, [QI] = 125sec, [QRI] = 10sec [OVQPT] = [RV] * [QI] + [QRI] = 260sec Having that said, we currently calculate [OVQPT] (here given as 'switchback' variable) as ... switchback = (idev->mc_qrv + 1) * max_delay RFC3810, 9.12. says "the [Query Interval] in the last Query received". In section "9.14. Configuring timers", it is said: This section is meant to provide advice to network administrators on how to tune these settings to their network. Ambitious router implementations might tune these settings dynamically based upon changing characteristics of the network. [...] iv) RFC38010, 9.14.2. Query Interval: The overall level of periodic MLD traffic is inversely proportional to the Query Interval. A longer Query Interval results in a lower overall level of MLD traffic. The value of the Query Interval MUST be equal to or greater than the Maximum Response Delay used to calculate the Maximum Response Code inserted in General Query messages. I assume that was why switchback is calculated as is (3 * max_delay), although this setting seems to be meant for routers only to configure their [QI] interval for non-default intervals. So usage here like this is clearly wrong. Concluding, the current behaviour in IPv6's multicast code is not conform to the RFC as switch back is calculated wrongly. That is, it has a too small value, so MLDv2 hosts switch back again to MLDv2 way too early, i.e. ~30secs instead of ~260secs on default. Hence, introduce necessary helper functions and fix this up properly as it should be. Introduced in 06da92283 ("[IPV6]: Add MLDv2 support."). Credits to Hannes Frederic Sowa who also had a hand in this as well. Also thanks to Hangbin Liu who did initial testing. Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Cc: David Stevens <dlstevens@us.ibm.com> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-09-04 06:19:37 +08:00
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;
refcount_t refcnt;
__u32 if_flags;
int dead;
IPv6: fix DESYNC_FACTOR The IPv6 temporary address generation uses a variable called DESYNC_FACTOR to prevent hosts updating the addresses at the same time. Quoting RFC 4941: ... The value DESYNC_FACTOR is a random value (different for each client) that ensures that clients don't synchronize with each other and generate new addresses at exactly the same time ... DESYNC_FACTOR is defined as: DESYNC_FACTOR -- A random value within the range 0 - MAX_DESYNC_FACTOR. It is computed once at system start (rather than each time it is used) and must never be greater than (TEMP_VALID_LIFETIME - REGEN_ADVANCE). First, I believe the RFC has a typo in it and meant to say: "and must never be greater than (TEMP_PREFERRED_LIFETIME - REGEN_ADVANCE)" The reason is that at various places in the RFC, DESYNC_FACTOR is used in a calculation like (TEMP_PREFERRED_LIFETIME - DESYNC_FACTOR) or (TEMP_PREFERRED_LIFETIME - REGEN_ADVANCE - DESYNC_FACTOR). It needs to be smaller than (TEMP_PREFERRED_LIFETIME - REGEN_ADVANCE) for the result of these calculations to be larger than zero. It's never used in a calculation together with TEMP_VALID_LIFETIME. I already submitted an errata to the rfc-editor: https://www.rfc-editor.org/errata_search.php?rfc=4941 The Linux implementation of DESYNC_FACTOR is very wrong: max_desync_factor is used in places DESYNC_FACTOR should be used. max_desync_factor is initialized to the RFC-recommended value for MAX_DESYNC_FACTOR (600) but the whole point is to get a _random_ value. And nothing ensures that the value used is not greater than (TEMP_PREFERRED_LIFETIME - REGEN_ADVANCE), which leads to underflows. The effect can easily be observed when setting the temp_prefered_lft sysctl e.g. to 60. The preferred lifetime of the temporary addresses will be bogus. TEMP_PREFERRED_LIFETIME and REGEN_ADVANCE are not constants and can be influenced by these three sysctls: regen_max_retry, dad_transmits and temp_prefered_lft. Thus, the upper bound for desync_factor needs to be re-calculated each time a new address is generated and if desync_factor is larger than the new upper bound, a new random value needs to be re-generated. And since we already have max_desync_factor configurable per interface, we also need to calculate and store desync_factor per interface. Signed-off-by: Jiri Bohac <jbohac@suse.cz> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-14 00:52:15 +08:00
u32 desync_factor;
struct list_head tempaddr_list;
net: ipv6: add tokenized interface identifier support This patch adds support for IPv6 tokenized IIDs, that allow for administrators to assign well-known host-part addresses to nodes whilst still obtaining global network prefix from Router Advertisements. It is currently in draft status. The primary target for such support is server platforms where addresses are usually manually configured, rather than using DHCPv6 or SLAAC. By using tokenised identifiers, hosts can still determine their network prefix by use of SLAAC, but more readily be automatically renumbered should their network prefix change. [...] The disadvantage with static addresses is that they are likely to require manual editing should the network prefix in use change. If instead there were a method to only manually configure the static identifier part of the IPv6 address, then the address could be automatically updated when a new prefix was introduced, as described in [RFC4192] for example. In such cases a DNS server might be configured with such a tokenised interface identifier of ::53, and SLAAC would use the token in constructing the interface address, using the advertised prefix. [...] http://tools.ietf.org/html/draft-chown-6man-tokenised-ipv6-identifiers-02 The implementation is partially based on top of Mark K. Thompson's proof of concept. However, it uses the Netlink interface for configuration resp. data retrival, so that it can be easily extended in future. Successfully tested by myself. Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> Cc: Thomas Graf <tgraf@suug.ch> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-04-08 12:01:30 +08:00
struct in6_addr token;
struct neigh_parms *nd_parms;
struct ipv6_devconf cnf;
struct ipv6_devstat stats;
struct timer_list rs_timer;
__s32 rs_interval; /* in jiffies */
__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