summaryrefslogtreecommitdiff
path: root/net/ipv6/addrconf.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6/addrconf.c')
-rw-r--r--net/ipv6/addrconf.c169
1 files changed, 131 insertions, 38 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 036b39eb1220..ef222a4bc1a5 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -112,6 +112,27 @@ static inline u32 cstamp_delta(unsigned long cstamp)
return (cstamp - INITIAL_JIFFIES) * 100UL / HZ;
}
+static inline s32 rfc3315_s14_backoff_init(s32 irt)
+{
+ /* multiply 'initial retransmission time' by 0.9 .. 1.1 */
+ u64 tmp = (900000 + prandom_u32() % 200001) * (u64)irt;
+ do_div(tmp, 1000000);
+ return (s32)tmp;
+}
+
+static inline s32 rfc3315_s14_backoff_update(s32 rt, s32 mrt)
+{
+ /* multiply 'retransmission timeout' by 1.9 .. 2.1 */
+ u64 tmp = (1900000 + prandom_u32() % 200001) * (u64)rt;
+ do_div(tmp, 1000000);
+ if ((s32)tmp > mrt) {
+ /* multiply 'maximum retransmission time' by 0.9 .. 1.1 */
+ tmp = (900000 + prandom_u32() % 200001) * (u64)mrt;
+ do_div(tmp, 1000000);
+ }
+ return (s32)tmp;
+}
+
#ifdef CONFIG_SYSCTL
static int addrconf_sysctl_register(struct inet6_dev *idev);
static void addrconf_sysctl_unregister(struct inet6_dev *idev);
@@ -187,6 +208,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
.dad_transmits = 1,
.rtr_solicits = MAX_RTR_SOLICITATIONS,
.rtr_solicit_interval = RTR_SOLICITATION_INTERVAL,
+ .rtr_solicit_max_interval = RTR_SOLICITATION_MAX_INTERVAL,
.rtr_solicit_delay = MAX_RTR_SOLICITATION_DELAY,
.use_tempaddr = 0,
.temp_valid_lft = TEMP_VALID_LIFETIME,
@@ -202,9 +224,11 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
.accept_ra_rtr_pref = 1,
.rtr_probe_interval = 60 * HZ,
#ifdef CONFIG_IPV6_ROUTE_INFO
+ .accept_ra_rt_info_min_plen = 0,
.accept_ra_rt_info_max_plen = 0,
#endif
#endif
+ .accept_ra_rt_table = 0,
.proxy_ndp = 0,
.accept_source_route = 0, /* we do not accept RH0 by default. */
.disable_ipv6 = 0,
@@ -231,6 +255,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
.dad_transmits = 1,
.rtr_solicits = MAX_RTR_SOLICITATIONS,
.rtr_solicit_interval = RTR_SOLICITATION_INTERVAL,
+ .rtr_solicit_max_interval = RTR_SOLICITATION_MAX_INTERVAL,
.rtr_solicit_delay = MAX_RTR_SOLICITATION_DELAY,
.use_tempaddr = 0,
.temp_valid_lft = TEMP_VALID_LIFETIME,
@@ -246,9 +271,11 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
.accept_ra_rtr_pref = 1,
.rtr_probe_interval = 60 * HZ,
#ifdef CONFIG_IPV6_ROUTE_INFO
+ .accept_ra_rt_info_min_plen = 0,
.accept_ra_rt_info_max_plen = 0,
#endif
#endif
+ .accept_ra_rt_table = 0,
.proxy_ndp = 0,
.accept_source_route = 0, /* we do not accept RH0 by default. */
.disable_ipv6 = 0,
@@ -291,9 +318,9 @@ static void addrconf_mod_rs_timer(struct inet6_dev *idev,
static void addrconf_mod_dad_work(struct inet6_ifaddr *ifp,
unsigned long delay)
{
- if (!delayed_work_pending(&ifp->dad_work))
- in6_ifa_hold(ifp);
- mod_delayed_work(addrconf_wq, &ifp->dad_work, delay);
+ in6_ifa_hold(ifp);
+ if (mod_delayed_work(addrconf_wq, &ifp->dad_work, delay))
+ in6_ifa_put(ifp);
}
static int snmp6_alloc_dev(struct inet6_dev *idev)
@@ -957,7 +984,10 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
INIT_HLIST_NODE(&ifa->addr_lst);
ifa->scope = scope;
ifa->prefix_len = pfxlen;
- ifa->flags = flags | IFA_F_TENTATIVE;
+ ifa->flags = flags;
+ /* No need to add the TENTATIVE flag for addresses with NODAD */
+ if (!(flags & IFA_F_NODAD))
+ ifa->flags |= IFA_F_TENTATIVE;
ifa->valid_lft = valid_lft;
ifa->prefered_lft = prefered_lft;
ifa->cstamp = ifa->tstamp = jiffies;
@@ -1772,17 +1802,7 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add
static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed)
{
- if (ifp->flags&IFA_F_PERMANENT) {
- spin_lock_bh(&ifp->lock);
- addrconf_del_dad_work(ifp);
- ifp->flags |= IFA_F_TENTATIVE;
- if (dad_failed)
- ifp->flags |= IFA_F_DADFAILED;
- spin_unlock_bh(&ifp->lock);
- if (dad_failed)
- ipv6_ifa_notify(0, ifp);
- in6_ifa_put(ifp);
- } else if (ifp->flags&IFA_F_TEMPORARY) {
+ if (ifp->flags&IFA_F_TEMPORARY) {
struct inet6_ifaddr *ifpub;
spin_lock_bh(&ifp->lock);
ifpub = ifp->ifpub;
@@ -1795,6 +1815,16 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed)
spin_unlock_bh(&ifp->lock);
}
ipv6_del_addr(ifp);
+ } else if (ifp->flags&IFA_F_PERMANENT || !dad_failed) {
+ spin_lock_bh(&ifp->lock);
+ addrconf_del_dad_work(ifp);
+ ifp->flags |= IFA_F_TENTATIVE;
+ if (dad_failed)
+ ifp->flags |= IFA_F_DADFAILED;
+ spin_unlock_bh(&ifp->lock);
+ if (dad_failed)
+ ipv6_ifa_notify(0, ifp);
+ in6_ifa_put(ifp);
} else {
ipv6_del_addr(ifp);
}
@@ -2146,6 +2176,31 @@ static void __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmp
__ipv6_regen_rndid(idev);
}
+u32 addrconf_rt_table(const struct net_device *dev, u32 default_table) {
+ /* Determines into what table to put autoconf PIO/RIO/default routes
+ * learned on this device.
+ *
+ * - If 0, use the same table for every device. This puts routes into
+ * one of RT_TABLE_{PREFIX,INFO,DFLT} depending on the type of route
+ * (but note that these three are currently all equal to
+ * RT6_TABLE_MAIN).
+ * - If > 0, use the specified table.
+ * - If < 0, put routes into table dev->ifindex + (-rt_table).
+ */
+ struct inet6_dev *idev = in6_dev_get(dev);
+ u32 table;
+ int sysctl = idev->cnf.accept_ra_rt_table;
+ if (sysctl == 0) {
+ table = default_table;
+ } else if (sysctl > 0) {
+ table = (u32) sysctl;
+ } else {
+ table = (unsigned) dev->ifindex + (-sysctl);
+ }
+ in6_dev_put(idev);
+ return table;
+}
+
/*
* Add prefix route.
*/
@@ -2155,7 +2210,7 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev,
unsigned long expires, u32 flags)
{
struct fib6_config cfg = {
- .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_PREFIX,
+ .fc_table = l3mdev_fib_table(dev) ? : addrconf_rt_table(dev, RT6_TABLE_PREFIX),
.fc_metric = IP6_RT_PRIO_ADDRCONF,
.fc_ifindex = dev->ifindex,
.fc_expires = expires,
@@ -2188,7 +2243,7 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
struct fib6_node *fn;
struct rt6_info *rt = NULL;
struct fib6_table *table;
- u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_PREFIX;
+ u32 tb_id = l3mdev_fib_table(dev) ? : addrconf_rt_table(dev, RT6_TABLE_PREFIX);
table = fib6_get_table(dev_net(dev), tb_id);
if (!table)
@@ -2916,7 +2971,7 @@ static void init_loopback(struct net_device *dev)
* lo device down, release this obsolete dst and
* reallocate a new router for ifa.
*/
- if (sp_ifa->rt->dst.obsolete > 0) {
+ if (!atomic_read(&sp_ifa->rt->rt6i_ref)) {
ip6_rt_put(sp_ifa->rt);
sp_ifa->rt = NULL;
} else {
@@ -3143,6 +3198,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct inet6_dev *idev = __in6_dev_get(dev);
+ struct net *net = dev_net(dev);
int run_pending = 0;
int err;
@@ -3158,7 +3214,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
case NETDEV_CHANGEMTU:
/* if MTU under IPV6_MIN_MTU stop IPv6 on this interface. */
if (dev->mtu < IPV6_MIN_MTU) {
- addrconf_ifdown(dev, 1);
+ addrconf_ifdown(dev, dev != net->loopback_dev);
break;
}
@@ -3211,9 +3267,15 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
}
if (idev) {
- if (idev->if_flags & IF_READY)
- /* device is already configured. */
+ if (idev->if_flags & IF_READY) {
+ /* device is already configured -
+ * but resend MLD reports, we might
+ * have roamed and need to update
+ * multicast snooping switches
+ */
+ ipv6_mc_up(idev);
break;
+ }
idev->if_flags |= IF_READY;
}
@@ -3265,7 +3327,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
* IPV6_MIN_MTU stop IPv6 on this interface.
*/
if (dev->mtu < IPV6_MIN_MTU)
- addrconf_ifdown(dev, 1);
+ addrconf_ifdown(dev, dev != net->loopback_dev);
}
break;
@@ -3306,6 +3368,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
*/
static struct notifier_block ipv6_dev_notf = {
.notifier_call = addrconf_notify,
+ .priority = ADDRCONF_NOTIFY_PRIORITY,
};
static void addrconf_type_change(struct net_device *dev, unsigned long event)
@@ -3458,7 +3521,7 @@ static void addrconf_rs_timer(unsigned long data)
if (idev->if_flags & IF_RA_RCVD)
goto out;
- if (idev->rs_probes++ < idev->cnf.rtr_solicits) {
+ if (idev->rs_probes++ < idev->cnf.rtr_solicits || idev->cnf.rtr_solicits < 0) {
write_unlock(&idev->lock);
if (!ipv6_get_lladdr(dev, &lladdr, IFA_F_TENTATIVE))
ndisc_send_rs(dev, &lladdr,
@@ -3467,11 +3530,13 @@ static void addrconf_rs_timer(unsigned long data)
goto put;
write_lock(&idev->lock);
+ idev->rs_interval = rfc3315_s14_backoff_update(
+ idev->rs_interval, idev->cnf.rtr_solicit_max_interval);
/* The wait after the last probe can be shorter */
addrconf_mod_rs_timer(idev, (idev->rs_probes ==
idev->cnf.rtr_solicits) ?
idev->cnf.rtr_solicit_delay :
- idev->cnf.rtr_solicit_interval);
+ idev->rs_interval);
} else {
/*
* Note: we do not support deprecated "all on-link"
@@ -3699,7 +3764,7 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp)
send_mld = ifp->scope == IFA_LINK && ipv6_lonely_lladdr(ifp);
send_rs = send_mld &&
ipv6_accept_ra(ifp->idev) &&
- ifp->idev->cnf.rtr_solicits > 0 &&
+ ifp->idev->cnf.rtr_solicits != 0 &&
(dev->flags&IFF_LOOPBACK) == 0;
read_unlock_bh(&ifp->idev->lock);
@@ -3721,10 +3786,11 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp)
write_lock_bh(&ifp->idev->lock);
spin_lock(&ifp->lock);
+ ifp->idev->rs_interval = rfc3315_s14_backoff_init(
+ ifp->idev->cnf.rtr_solicit_interval);
ifp->idev->rs_probes = 1;
ifp->idev->if_flags |= IF_RS_SENT;
- addrconf_mod_rs_timer(ifp->idev,
- ifp->idev->cnf.rtr_solicit_interval);
+ addrconf_mod_rs_timer(ifp->idev, ifp->idev->rs_interval);
spin_unlock(&ifp->lock);
write_unlock_bh(&ifp->idev->lock);
}
@@ -3775,7 +3841,6 @@ static struct inet6_ifaddr *if6_get_first(struct seq_file *seq, loff_t pos)
p++;
continue;
}
- state->offset++;
return ifa;
}
@@ -3799,13 +3864,12 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq,
return ifa;
}
+ state->offset = 0;
while (++state->bucket < IN6_ADDR_HSIZE) {
- state->offset = 0;
hlist_for_each_entry_rcu_bh(ifa,
&inet6_addr_lst[state->bucket], addr_lst) {
if (!net_eq(dev_net(ifa->idev->dev), net))
continue;
- state->offset++;
return ifa;
}
}
@@ -4430,8 +4494,8 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb,
/* unicast address incl. temp addr */
list_for_each_entry(ifa, &idev->addr_list, if_list) {
- if (++ip_idx < s_ip_idx)
- continue;
+ if (ip_idx < s_ip_idx)
+ goto next;
err = inet6_fill_ifaddr(skb, ifa,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
@@ -4440,6 +4504,8 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb,
if (err < 0)
break;
nl_dump_check_consistent(cb, nlmsg_hdr(skb));
+next:
+ ip_idx++;
}
break;
}
@@ -4641,6 +4707,8 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
array[DEVCONF_RTR_SOLICITS] = cnf->rtr_solicits;
array[DEVCONF_RTR_SOLICIT_INTERVAL] =
jiffies_to_msecs(cnf->rtr_solicit_interval);
+ array[DEVCONF_RTR_SOLICIT_MAX_INTERVAL] =
+ jiffies_to_msecs(cnf->rtr_solicit_max_interval);
array[DEVCONF_RTR_SOLICIT_DELAY] =
jiffies_to_msecs(cnf->rtr_solicit_delay);
array[DEVCONF_FORCE_MLD_VERSION] = cnf->force_mld_version;
@@ -4662,9 +4730,11 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
array[DEVCONF_RTR_PROBE_INTERVAL] =
jiffies_to_msecs(cnf->rtr_probe_interval);
#ifdef CONFIG_IPV6_ROUTE_INFO
+ array[DEVCONF_ACCEPT_RA_RT_INFO_MIN_PLEN] = cnf->accept_ra_rt_info_min_plen;
array[DEVCONF_ACCEPT_RA_RT_INFO_MAX_PLEN] = cnf->accept_ra_rt_info_max_plen;
#endif
#endif
+ array[DEVCONF_ACCEPT_RA_RT_TABLE] = cnf->accept_ra_rt_table;
array[DEVCONF_PROXY_NDP] = cnf->proxy_ndp;
array[DEVCONF_ACCEPT_SOURCE_ROUTE] = cnf->accept_source_route;
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
@@ -4848,7 +4918,7 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token)
return -EINVAL;
if (!ipv6_accept_ra(idev))
return -EINVAL;
- if (idev->cnf.rtr_solicits <= 0)
+ if (idev->cnf.rtr_solicits == 0)
return -EINVAL;
write_lock_bh(&idev->lock);
@@ -4873,8 +4943,10 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token)
if (update_rs) {
idev->if_flags |= IF_RS_SENT;
+ idev->rs_interval = rfc3315_s14_backoff_init(
+ idev->cnf.rtr_solicit_interval);
idev->rs_probes = 1;
- addrconf_mod_rs_timer(idev, idev->cnf.rtr_solicit_interval);
+ addrconf_mod_rs_timer(idev, idev->rs_interval);
}
/* Well, that's kinda nasty ... */
@@ -5144,7 +5216,7 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
* our DAD process, so we don't need
* to do it again
*/
- if (!(ifp->rt->rt6i_node))
+ if (!rcu_access_pointer(ifp->rt->rt6i_node))
ip6_ins_rt(ifp->rt);
if (ifp->idev->cnf.forwarding)
addrconf_join_anycast(ifp);
@@ -5244,8 +5316,7 @@ static void addrconf_disable_change(struct net *net, __s32 newf)
struct net_device *dev;
struct inet6_dev *idev;
- rcu_read_lock();
- for_each_netdev_rcu(net, dev) {
+ for_each_netdev(net, dev) {
idev = __in6_dev_get(dev);
if (idev) {
int changed = (!idev->cnf.disable_ipv6) ^ (!newf);
@@ -5254,7 +5325,6 @@ static void addrconf_disable_change(struct net *net, __s32 newf)
dev_disable_change(idev);
}
}
- rcu_read_unlock();
}
static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf)
@@ -5514,6 +5584,13 @@ static struct addrconf_sysctl_table
.proc_handler = proc_dointvec_jiffies,
},
{
+ .procname = "router_solicitation_max_interval",
+ .data = &ipv6_devconf.rtr_solicit_max_interval,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_jiffies,
+ },
+ {
.procname = "router_solicitation_delay",
.data = &ipv6_devconf.rtr_solicit_delay,
.maxlen = sizeof(int),
@@ -5623,6 +5700,13 @@ static struct addrconf_sysctl_table
},
#ifdef CONFIG_IPV6_ROUTE_INFO
{
+ .procname = "accept_ra_rt_info_min_plen",
+ .data = &ipv6_devconf.accept_ra_rt_info_min_plen,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
.procname = "accept_ra_rt_info_max_plen",
.data = &ipv6_devconf.accept_ra_rt_info_max_plen,
.maxlen = sizeof(int),
@@ -5632,6 +5716,13 @@ static struct addrconf_sysctl_table
#endif
#endif
{
+ .procname = "accept_ra_rt_table",
+ .data = &ipv6_devconf.accept_ra_rt_table,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
.procname = "proxy_ndp",
.data = &ipv6_devconf.proxy_ndp,
.maxlen = sizeof(int),
@@ -5942,6 +6033,8 @@ int __init addrconf_init(void)
goto errlo;
}
+ ip6_route_init_special_entries();
+
for (i = 0; i < IN6_ADDR_HSIZE; i++)
INIT_HLIST_HEAD(&inet6_addr_lst[i]);
generated by cgit v1.2.3 (git 2.25.1) at 2025-10-24 20:25:16 +0000