summaryrefslogtreecommitdiff
path: root/net/ipv6
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/addrconf.c113
-rw-r--r--net/ipv6/af_inet6.c2
-rw-r--r--net/ipv6/ip6_fib.c85
-rw-r--r--net/ipv6/ip6_gre.c14
-rw-r--r--net/ipv6/ip6_tunnel.c13
-rw-r--r--net/ipv6/ip6_vti.c13
-rw-r--r--net/ipv6/ip6mr.c5
-rw-r--r--net/ipv6/mcast.c1
-rw-r--r--net/ipv6/ndisc.c13
-rw-r--r--net/ipv6/netfilter/Kconfig20
-rw-r--r--net/ipv6/netfilter/Makefile2
-rw-r--r--net/ipv6/route.c27
-rw-r--r--net/ipv6/sit.c14
-rw-r--r--net/ipv6/syncookies.c13
14 files changed, 235 insertions, 100 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 5a839c5fb1a5..c669ea266ab7 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -195,6 +195,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
.use_tempaddr = 0,
.temp_valid_lft = TEMP_VALID_LIFETIME,
.temp_prefered_lft = TEMP_PREFERRED_LIFETIME,
+ .regen_min_advance = REGEN_MIN_ADVANCE,
.regen_max_retry = REGEN_MAX_RETRY,
.max_desync_factor = MAX_DESYNC_FACTOR,
.max_addresses = IPV6_MAX_ADDRESSES,
@@ -257,6 +258,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
.use_tempaddr = 0,
.temp_valid_lft = TEMP_VALID_LIFETIME,
.temp_prefered_lft = TEMP_PREFERRED_LIFETIME,
+ .regen_min_advance = REGEN_MIN_ADVANCE,
.regen_max_retry = REGEN_MAX_RETRY,
.max_desync_factor = MAX_DESYNC_FACTOR,
.max_addresses = IPV6_MAX_ADDRESSES,
@@ -1270,6 +1272,7 @@ static void
cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires,
bool del_rt, bool del_peer)
{
+ struct fib6_table *table;
struct fib6_info *f6i;
f6i = addrconf_get_prefix_route(del_peer ? &ifp->peer_addr : &ifp->addr,
@@ -1279,8 +1282,15 @@ cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires,
if (del_rt)
ip6_del_rt(dev_net(ifp->idev->dev), f6i, false);
else {
- if (!(f6i->fib6_flags & RTF_EXPIRES))
+ if (!(f6i->fib6_flags & RTF_EXPIRES)) {
+ table = f6i->fib6_table;
+ spin_lock_bh(&table->tb6_lock);
+
fib6_set_expires(f6i, expires);
+ fib6_add_gc_list(f6i);
+
+ spin_unlock_bh(&table->tb6_lock);
+ }
fib6_info_release(f6i);
}
}
@@ -1346,12 +1356,20 @@ out:
in6_ifa_put(ifp);
}
+static unsigned long ipv6_get_regen_advance(struct inet6_dev *idev)
+{
+ return idev->cnf.regen_min_advance + idev->cnf.regen_max_retry *
+ idev->cnf.dad_transmits *
+ max(NEIGH_VAR(idev->nd_parms, RETRANS_TIME), HZ/100) / HZ;
+}
+
static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, bool block)
{
struct inet6_dev *idev = ifp->idev;
unsigned long tmp_tstamp, age;
unsigned long regen_advance;
unsigned long now = jiffies;
+ u32 if_public_preferred_lft;
s32 cnf_temp_preferred_lft;
struct inet6_ifaddr *ift;
struct ifa6_config cfg;
@@ -1387,9 +1405,7 @@ retry:
age = (now - ifp->tstamp) / HZ;
- regen_advance = idev->cnf.regen_max_retry *
- idev->cnf.dad_transmits *
- max(NEIGH_VAR(idev->nd_parms, RETRANS_TIME), HZ/100) / HZ;
+ regen_advance = ipv6_get_regen_advance(idev);
/* recalculate max_desync_factor each time and update
* idev->desync_factor if it's larger
@@ -1409,11 +1425,13 @@ retry:
}
}
+ if_public_preferred_lft = ifp->prefered_lft;
+
memset(&cfg, 0, sizeof(cfg));
cfg.valid_lft = min_t(__u32, ifp->valid_lft,
idev->cnf.temp_valid_lft + age);
cfg.preferred_lft = cnf_temp_preferred_lft + age - idev->desync_factor;
- cfg.preferred_lft = min_t(__u32, ifp->prefered_lft, cfg.preferred_lft);
+ cfg.preferred_lft = min_t(__u32, if_public_preferred_lft, cfg.preferred_lft);
cfg.preferred_lft = min_t(__u32, cfg.valid_lft, cfg.preferred_lft);
cfg.plen = ifp->prefix_len;
@@ -1422,19 +1440,41 @@ retry:
write_unlock_bh(&idev->lock);
- /* A temporary address is created only if this calculated Preferred
- * Lifetime is greater than REGEN_ADVANCE time units. In particular,
- * an implementation must not create a temporary address with a zero
- * Preferred Lifetime.
+ /* From RFC 4941:
+ *
+ * A temporary address is created only if this calculated Preferred
+ * Lifetime is greater than REGEN_ADVANCE time units. In
+ * particular, an implementation must not create a temporary address
+ * with a zero Preferred Lifetime.
+ *
+ * ...
+ *
+ * When creating a temporary address, the lifetime values MUST be
+ * derived from the corresponding prefix as follows:
+ *
+ * ...
+ *
+ * * Its Preferred Lifetime is the lower of the Preferred Lifetime
+ * of the public address or TEMP_PREFERRED_LIFETIME -
+ * DESYNC_FACTOR.
+ *
+ * To comply with the RFC's requirements, clamp the preferred lifetime
+ * to a minimum of regen_advance, unless that would exceed valid_lft or
+ * ifp->prefered_lft.
+ *
* Use age calculation as in addrconf_verify to avoid unnecessary
* temporary addresses being generated.
*/
age = (now - tmp_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ;
if (cfg.preferred_lft <= regen_advance + age) {
- in6_ifa_put(ifp);
- in6_dev_put(idev);
- ret = -1;
- goto out;
+ cfg.preferred_lft = regen_advance + age + 1;
+ if (cfg.preferred_lft > cfg.valid_lft ||
+ cfg.preferred_lft > if_public_preferred_lft) {
+ in6_ifa_put(ifp);
+ in6_dev_put(idev);
+ ret = -1;
+ goto out;
+ }
}
cfg.ifa_flags = IFA_F_TEMPORARY;
@@ -2721,6 +2761,7 @@ EXPORT_SYMBOL_GPL(addrconf_prefix_rcv_add_addr);
void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
{
struct prefix_info *pinfo;
+ struct fib6_table *table;
__u32 valid_lft;
__u32 prefered_lft;
int addr_type, err;
@@ -2797,11 +2838,20 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
if (valid_lft == 0) {
ip6_del_rt(net, rt, false);
rt = NULL;
- } else if (addrconf_finite_timeout(rt_expires)) {
- /* not infinity */
- fib6_set_expires(rt, jiffies + rt_expires);
} else {
- fib6_clean_expires(rt);
+ table = rt->fib6_table;
+ spin_lock_bh(&table->tb6_lock);
+
+ if (addrconf_finite_timeout(rt_expires)) {
+ /* not infinity */
+ fib6_set_expires(rt, jiffies + rt_expires);
+ fib6_add_gc_list(rt);
+ } else {
+ fib6_clean_expires(rt);
+ fib6_remove_gc_list(rt);
+ }
+
+ spin_unlock_bh(&table->tb6_lock);
}
} else if (valid_lft) {
clock_t expires = 0;
@@ -4592,9 +4642,7 @@ restart:
!ifp->regen_count && ifp->ifpub) {
/* This is a non-regenerated temporary addr. */
- unsigned long regen_advance = ifp->idev->cnf.regen_max_retry *
- ifp->idev->cnf.dad_transmits *
- max(NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME), HZ/100) / HZ;
+ unsigned long regen_advance = ipv6_get_regen_advance(ifp->idev);
if (age + regen_advance >= ifp->prefered_lft) {
struct inet6_ifaddr *ifpub = ifp->ifpub;
@@ -4756,6 +4804,7 @@ static int modify_prefix_route(struct inet6_ifaddr *ifp,
unsigned long expires, u32 flags,
bool modify_peer)
{
+ struct fib6_table *table;
struct fib6_info *f6i;
u32 prio;
@@ -4776,10 +4825,18 @@ static int modify_prefix_route(struct inet6_ifaddr *ifp,
ifp->rt_priority, ifp->idev->dev,
expires, flags, GFP_KERNEL);
} else {
- if (!expires)
+ table = f6i->fib6_table;
+ spin_lock_bh(&table->tb6_lock);
+
+ if (!(flags & RTF_EXPIRES)) {
fib6_clean_expires(f6i);
- else
+ fib6_remove_gc_list(f6i);
+ } else {
fib6_set_expires(f6i, expires);
+ fib6_add_gc_list(f6i);
+ }
+
+ spin_unlock_bh(&table->tb6_lock);
fib6_info_release(f6i);
}
@@ -6013,7 +6070,7 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev,
(dev->ifindex != dev_get_iflink(dev) &&
nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev))) ||
nla_put_u8(skb, IFLA_OPERSTATE,
- netif_running(dev) ? dev->operstate : IF_OPER_DOWN))
+ netif_running(dev) ? READ_ONCE(dev->operstate) : IF_OPER_DOWN))
goto nla_put_failure;
protoinfo = nla_nest_start_noflag(skb, IFLA_PROTINFO);
if (!protoinfo)
@@ -6805,6 +6862,13 @@ static const struct ctl_table addrconf_sysctl[] = {
.proc_handler = proc_dointvec,
},
{
+ .procname = "regen_min_advance",
+ .data = &ipv6_devconf.regen_min_advance,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
.procname = "regen_max_retry",
.data = &ipv6_devconf.regen_max_retry,
.maxlen = sizeof(int),
@@ -7364,7 +7428,8 @@ int __init addrconf_init(void)
if (err < 0)
goto out_addrlabel;
- addrconf_wq = create_workqueue("ipv6_addrconf");
+ /* All works using addrconf_wq need to lock rtnl. */
+ addrconf_wq = create_singlethread_workqueue("ipv6_addrconf");
if (!addrconf_wq) {
err = -ENOMEM;
goto out_nowq;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 959bfd9f6344..b90d46533cdc 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -736,7 +736,7 @@ const struct proto_ops inet6_dgram_ops = {
.recvmsg = inet6_recvmsg, /* retpoline's sake */
.read_skb = udp_read_skb,
.mmap = sock_no_mmap,
- .set_peek_off = sk_set_peek_off,
+ .set_peek_off = udp_set_peek_off,
#ifdef CONFIG_COMPAT
.compat_ioctl = inet6_compat_ioctl,
#endif
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 4fc2cae0d116..6540d877d369 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -160,6 +160,8 @@ struct fib6_info *fib6_info_alloc(gfp_t gfp_flags, bool with_fib6_nh)
INIT_LIST_HEAD(&f6i->fib6_siblings);
refcount_set(&f6i->fib6_ref, 1);
+ INIT_HLIST_NODE(&f6i->gc_link);
+
return f6i;
}
@@ -246,6 +248,7 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id)
net->ipv6.fib6_null_entry);
table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
inet_peer_base_init(&table->tb6_peers);
+ INIT_HLIST_HEAD(&table->tb6_gc_hlist);
}
return table;
@@ -751,8 +754,6 @@ static struct fib6_node *fib6_add_1(struct net *net,
int bit;
__be32 dir = 0;
- RT6_TRACE("fib6_add_1\n");
-
/* insert node in tree */
fn = root;
@@ -1057,6 +1058,9 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn,
lockdep_is_held(&table->tb6_lock));
}
}
+
+ fib6_clean_expires(rt);
+ fib6_remove_gc_list(rt);
}
/*
@@ -1117,10 +1121,13 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
rt->fib6_nsiblings = 0;
if (!(iter->fib6_flags & RTF_EXPIRES))
return -EEXIST;
- if (!(rt->fib6_flags & RTF_EXPIRES))
+ if (!(rt->fib6_flags & RTF_EXPIRES)) {
fib6_clean_expires(iter);
- else
+ fib6_remove_gc_list(iter);
+ } else {
fib6_set_expires(iter, rt->expires);
+ fib6_add_gc_list(iter);
+ }
if (rt->fib6_pmtu)
fib6_metric_set(iter, RTAX_MTU,
@@ -1479,6 +1486,10 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt,
if (rt->nh)
list_add(&rt->nh_list, &rt->nh->f6i_list);
__fib6_update_sernum_upto_root(rt, fib6_new_sernum(info->nl_net));
+
+ if (rt->fib6_flags & RTF_EXPIRES)
+ fib6_add_gc_list(rt);
+
fib6_start_gc(info->nl_net, rt);
}
@@ -1803,7 +1814,7 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
lockdep_is_held(&table->tb6_lock));
struct fib6_info *new_fn_leaf;
- RT6_TRACE("fixing tree: plen=%d iter=%d\n", fn->fn_bit, iter);
+ pr_debug("fixing tree: plen=%d iter=%d\n", fn->fn_bit, iter);
iter++;
WARN_ON(fn->fn_flags & RTN_RTINFO);
@@ -1866,7 +1877,8 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
FOR_WALKERS(net, w) {
if (!child) {
if (w->node == fn) {
- RT6_TRACE("W %p adjusted by delnode 1, s=%d/%d\n", w, w->state, nstate);
+ pr_debug("W %p adjusted by delnode 1, s=%d/%d\n",
+ w, w->state, nstate);
w->node = pn;
w->state = nstate;
}
@@ -1874,10 +1886,12 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
if (w->node == fn) {
w->node = child;
if (children&2) {
- RT6_TRACE("W %p adjusted by delnode 2, s=%d\n", w, w->state);
+ pr_debug("W %p adjusted by delnode 2, s=%d\n",
+ w, w->state);
w->state = w->state >= FWS_R ? FWS_U : FWS_INIT;
} else {
- RT6_TRACE("W %p adjusted by delnode 2, s=%d\n", w, w->state);
+ pr_debug("W %p adjusted by delnode 2, s=%d\n",
+ w, w->state);
w->state = w->state >= FWS_C ? FWS_U : FWS_INIT;
}
}
@@ -1905,8 +1919,6 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
struct net *net = info->nl_net;
bool notify_del = false;
- RT6_TRACE("fib6_del_route\n");
-
/* If the deleted route is the first in the node and it is not part of
* a multipath route, then we need to replace it with the next route
* in the node, if exists.
@@ -1955,7 +1967,7 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
read_lock(&net->ipv6.fib6_walker_lock);
FOR_WALKERS(net, w) {
if (w->state == FWS_C && w->leaf == rt) {
- RT6_TRACE("walker %p adjusted by delroute\n", w);
+ pr_debug("walker %p adjusted by delroute\n", w);
w->leaf = rcu_dereference_protected(rt->fib6_next,
lockdep_is_held(&table->tb6_lock));
if (!w->leaf)
@@ -2281,9 +2293,8 @@ static void fib6_flush_trees(struct net *net)
* Garbage collection
*/
-static int fib6_age(struct fib6_info *rt, void *arg)
+static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args)
{
- struct fib6_gc_args *gc_args = arg;
unsigned long now = jiffies;
/*
@@ -2293,7 +2304,7 @@ static int fib6_age(struct fib6_info *rt, void *arg)
if (rt->fib6_flags & RTF_EXPIRES && rt->expires) {
if (time_after(now, rt->expires)) {
- RT6_TRACE("expiring %p\n", rt);
+ pr_debug("expiring %p\n", rt);
return -1;
}
gc_args->more++;
@@ -2308,6 +2319,42 @@ static int fib6_age(struct fib6_info *rt, void *arg)
return 0;
}
+static void fib6_gc_table(struct net *net,
+ struct fib6_table *tb6,
+ struct fib6_gc_args *gc_args)
+{
+ struct fib6_info *rt;
+ struct hlist_node *n;
+ struct nl_info info = {
+ .nl_net = net,
+ .skip_notify = false,
+ };
+
+ hlist_for_each_entry_safe(rt, n, &tb6->tb6_gc_hlist, gc_link)
+ if (fib6_age(rt, gc_args) == -1)
+ fib6_del(rt, &info);
+}
+
+static void fib6_gc_all(struct net *net, struct fib6_gc_args *gc_args)
+{
+ struct fib6_table *table;
+ struct hlist_head *head;
+ unsigned int h;
+
+ rcu_read_lock();
+ for (h = 0; h < FIB6_TABLE_HASHSZ; h++) {
+ head = &net->ipv6.fib_table_hash[h];
+ hlist_for_each_entry_rcu(table, head, tb6_hlist) {
+ spin_lock_bh(&table->tb6_lock);
+
+ fib6_gc_table(net, table, gc_args);
+
+ spin_unlock_bh(&table->tb6_lock);
+ }
+ }
+ rcu_read_unlock();
+}
+
void fib6_run_gc(unsigned long expires, struct net *net, bool force)
{
struct fib6_gc_args gc_args;
@@ -2323,7 +2370,7 @@ void fib6_run_gc(unsigned long expires, struct net *net, bool force)
net->ipv6.sysctl.ip6_rt_gc_interval;
gc_args.more = 0;
- fib6_clean_all(net, fib6_age, &gc_args);
+ fib6_gc_all(net, &gc_args);
now = jiffies;
net->ipv6.ip6_rt_last_gc = now;
@@ -2383,6 +2430,7 @@ static int __net_init fib6_net_init(struct net *net)
net->ipv6.fib6_main_tbl->tb6_root.fn_flags =
RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
inet_peer_base_init(&net->ipv6.fib6_main_tbl->tb6_peers);
+ INIT_HLIST_HEAD(&net->ipv6.fib6_main_tbl->tb6_gc_hlist);
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
net->ipv6.fib6_local_tbl = kzalloc(sizeof(*net->ipv6.fib6_local_tbl),
@@ -2395,6 +2443,7 @@ static int __net_init fib6_net_init(struct net *net)
net->ipv6.fib6_local_tbl->tb6_root.fn_flags =
RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
inet_peer_base_init(&net->ipv6.fib6_local_tbl->tb6_peers);
+ INIT_HLIST_HEAD(&net->ipv6.fib6_local_tbl->tb6_gc_hlist);
#endif
fib6_tables_init(net);
@@ -2444,10 +2493,8 @@ int __init fib6_init(void)
{
int ret = -ENOMEM;
- fib6_node_kmem = kmem_cache_create("fib6_nodes",
- sizeof(struct fib6_node), 0,
- SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT,
- NULL);
+ fib6_node_kmem = KMEM_CACHE(fib6_node,
+ SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT);
if (!fib6_node_kmem)
goto out;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 070d87abf7c0..5e97e0aa8e07 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1511,6 +1511,7 @@ static int ip6gre_tunnel_init_common(struct net_device *dev)
ip6gre_tnl_init_features(dev);
netdev_hold(dev, &tunnel->dev_tracker, GFP_KERNEL);
+ netdev_lockdep_set_classes(dev);
return 0;
cleanup_dst_cache_init:
@@ -1632,21 +1633,19 @@ err_alloc_dev:
return err;
}
-static void __net_exit ip6gre_exit_batch_net(struct list_head *net_list)
+static void __net_exit ip6gre_exit_batch_rtnl(struct list_head *net_list,
+ struct list_head *dev_to_kill)
{
struct net *net;
- LIST_HEAD(list);
- rtnl_lock();
+ ASSERT_RTNL();
list_for_each_entry(net, net_list, exit_list)
- ip6gre_destroy_tunnels(net, &list);
- unregister_netdevice_many(&list);
- rtnl_unlock();
+ ip6gre_destroy_tunnels(net, dev_to_kill);
}
static struct pernet_operations ip6gre_net_ops = {
.init = ip6gre_init_net,
- .exit_batch = ip6gre_exit_batch_net,
+ .exit_batch_rtnl = ip6gre_exit_batch_rtnl,
.id = &ip6gre_net_id,
.size = sizeof(struct ip6gre_net),
};
@@ -1903,6 +1902,7 @@ static int ip6erspan_tap_init(struct net_device *dev)
ip6erspan_tnl_link_config(tunnel, 1);
netdev_hold(dev, &tunnel->dev_tracker, GFP_KERNEL);
+ netdev_lockdep_set_classes(dev);
return 0;
cleanup_dst_cache_init:
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 9bbabf750a21..44406c28445d 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1898,6 +1898,7 @@ ip6_tnl_dev_init_gen(struct net_device *dev)
dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len;
netdev_hold(dev, &t->dev_tracker, GFP_KERNEL);
+ netdev_lockdep_set_classes(dev);
return 0;
destroy_dst:
@@ -2282,21 +2283,19 @@ err_alloc_dev:
return err;
}
-static void __net_exit ip6_tnl_exit_batch_net(struct list_head *net_list)
+static void __net_exit ip6_tnl_exit_batch_rtnl(struct list_head *net_list,
+ struct list_head *dev_to_kill)
{
struct net *net;
- LIST_HEAD(list);
- rtnl_lock();
+ ASSERT_RTNL();
list_for_each_entry(net, net_list, exit_list)
- ip6_tnl_destroy_tunnels(net, &list);
- unregister_netdevice_many(&list);
- rtnl_unlock();
+ ip6_tnl_destroy_tunnels(net, dev_to_kill);
}
static struct pernet_operations ip6_tnl_net_ops = {
.init = ip6_tnl_init_net,
- .exit_batch = ip6_tnl_exit_batch_net,
+ .exit_batch_rtnl = ip6_tnl_exit_batch_rtnl,
.id = &ip6_tnl_net_id,
.size = sizeof(struct ip6_tnl_net),
};
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index e550240c85e1..7f4f976aa24a 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -935,6 +935,7 @@ static inline int vti6_dev_init_gen(struct net_device *dev)
if (!dev->tstats)
return -ENOMEM;
netdev_hold(dev, &t->dev_tracker, GFP_KERNEL);
+ netdev_lockdep_set_classes(dev);
return 0;
}
@@ -1174,24 +1175,22 @@ err_alloc_dev:
return err;
}
-static void __net_exit vti6_exit_batch_net(struct list_head *net_list)
+static void __net_exit vti6_exit_batch_rtnl(struct list_head *net_list,
+ struct list_head *dev_to_kill)
{
struct vti6_net *ip6n;
struct net *net;
- LIST_HEAD(list);
- rtnl_lock();
+ ASSERT_RTNL();
list_for_each_entry(net, net_list, exit_list) {
ip6n = net_generic(net, vti6_net_id);
- vti6_destroy_tunnels(ip6n, &list);
+ vti6_destroy_tunnels(ip6n, dev_to_kill);
}
- unregister_netdevice_many(&list);
- rtnl_unlock();
}
static struct pernet_operations vti6_net_ops = {
.init = vti6_init_net,
- .exit_batch = vti6_exit_batch_net,
+ .exit_batch_rtnl = vti6_exit_batch_rtnl,
.id = &vti6_net_id,
.size = sizeof(struct vti6_net),
};
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 9782c180fee6..1f19743f2540 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1373,10 +1373,7 @@ int __init ip6_mr_init(void)
{
int err;
- mrt_cachep = kmem_cache_create("ip6_mrt_cache",
- sizeof(struct mfc6_cache),
- 0, SLAB_HWCACHE_ALIGN,
- NULL);
+ mrt_cachep = KMEM_CACHE(mfc6_cache, SLAB_HWCACHE_ALIGN);
if (!mrt_cachep)
return -ENOMEM;
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index bc6e0a0bad3c..76ee1615ff2a 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -2719,7 +2719,6 @@ void ipv6_mc_down(struct inet6_dev *idev)
/* Should stop work after group drop. or we will
* start work again in mld_ifc_event()
*/
- synchronize_net();
mld_query_stop_work(idev);
mld_report_stop_work(idev);
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index a19999b30bc0..73cb31afe935 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1237,6 +1237,7 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb)
struct ndisc_options ndopts;
struct fib6_info *rt = NULL;
struct inet6_dev *in6_dev;
+ struct fib6_table *table;
u32 defrtr_usr_metric;
unsigned int pref = 0;
__u32 old_if_flags;
@@ -1382,7 +1383,8 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb)
neigh_release(neigh);
rt = rt6_add_dflt_router(net, &ipv6_hdr(skb)->saddr,
- skb->dev, pref, defrtr_usr_metric);
+ skb->dev, pref, defrtr_usr_metric,
+ lifetime);
if (!rt) {
ND_PRINTK(0, err,
"RA: %s failed to add default route\n",
@@ -1409,8 +1411,15 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb)
inet6_rt_notify(RTM_NEWROUTE, rt, &nlinfo, NLM_F_REPLACE);
}
- if (rt)
+ if (rt) {
+ table = rt->fib6_table;
+ spin_lock_bh(&table->tb6_lock);
+
fib6_set_expires(rt, jiffies + (HZ * lifetime));
+ fib6_add_gc_list(rt);
+
+ spin_unlock_bh(&table->tb6_lock);
+ }
if (in6_dev->cnf.accept_ra_min_hop_limit < 256 &&
ra_msg->icmph.icmp6_hop_limit) {
if (in6_dev->cnf.accept_ra_min_hop_limit <= ra_msg->icmph.icmp6_hop_limit) {
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 0ba62f4868f9..f3c8e2d918e1 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -6,6 +6,10 @@
menu "IPv6: Netfilter Configuration"
depends on INET && IPV6 && NETFILTER
+# old sockopt interface and eval loop
+config IP6_NF_IPTABLES_LEGACY
+ tristate
+
config NF_SOCKET_IPV6
tristate "IPv6 socket lookup support"
help
@@ -147,7 +151,7 @@ config IP6_NF_MATCH_MH
config IP6_NF_MATCH_RPFILTER
tristate '"rpfilter" reverse path filter match support'
depends on NETFILTER_ADVANCED
- depends on IP6_NF_MANGLE || IP6_NF_RAW
+ depends on IP6_NF_MANGLE || IP6_NF_RAW || NFT_COMPAT
help
This option allows you to match packets whose replies would
go out via the interface the packet came in.
@@ -186,6 +190,8 @@ config IP6_NF_TARGET_HL
config IP6_NF_FILTER
tristate "Packet filtering"
default m if NETFILTER_ADVANCED=n
+ select IP6_NF_IPTABLES_LEGACY
+ tristate
help
Packet filtering defines a table `filter', which has a series of
rules for simple packet filtering at local input, forwarding and
@@ -195,7 +201,7 @@ config IP6_NF_FILTER
config IP6_NF_TARGET_REJECT
tristate "REJECT target support"
- depends on IP6_NF_FILTER
+ depends on IP6_NF_FILTER || NFT_COMPAT
select NF_REJECT_IPV6
default m if NETFILTER_ADVANCED=n
help
@@ -221,6 +227,7 @@ config IP6_NF_TARGET_SYNPROXY
config IP6_NF_MANGLE
tristate "Packet mangling"
default m if NETFILTER_ADVANCED=n
+ select IP6_NF_IPTABLES_LEGACY
help
This option adds a `mangle' table to iptables: see the man page for
iptables(8). This table is used for various packet alterations
@@ -230,6 +237,7 @@ config IP6_NF_MANGLE
config IP6_NF_RAW
tristate 'raw table support (required for TRACE)'
+ select IP6_NF_IPTABLES_LEGACY
help
This option adds a `raw' table to ip6tables. This table is the very
first in the netfilter framework and hooks in at the PREROUTING
@@ -243,6 +251,7 @@ config IP6_NF_SECURITY
tristate "Security table"
depends on SECURITY
depends on NETFILTER_ADVANCED
+ select IP6_NF_IPTABLES_LEGACY
help
This option adds a `security' table to iptables, for use
with Mandatory Access Control (MAC) policy.
@@ -254,6 +263,7 @@ config IP6_NF_NAT
depends on NF_CONNTRACK
depends on NETFILTER_ADVANCED
select NF_NAT
+ select IP6_NF_IPTABLES_LEGACY
select NETFILTER_XT_NAT
help
This enables the `nat' table in ip6tables. This allows masquerading,
@@ -262,25 +272,23 @@ config IP6_NF_NAT
To compile it as a module, choose M here. If unsure, say N.
-if IP6_NF_NAT
-
config IP6_NF_TARGET_MASQUERADE
tristate "MASQUERADE target support"
select NETFILTER_XT_TARGET_MASQUERADE
+ depends on IP6_NF_NAT
help
This is a backwards-compat option for the user's convenience
(e.g. when running oldconfig). It selects NETFILTER_XT_TARGET_MASQUERADE.
config IP6_NF_TARGET_NPT
tristate "NPT (Network Prefix translation) target support"
+ depends on IP6_NF_NAT || NFT_COMPAT
help
This option adds the `SNPT' and `DNPT' target, which perform
stateless IPv6-to-IPv6 Network Prefix Translation per RFC 6296.
To compile it as a module, choose M here. If unsure, say N.
-endif # IP6_NF_NAT
-
endif # IP6_NF_IPTABLES
endmenu
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index b8d6dc9aeeb6..66ce6fa5b2f5 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -4,7 +4,7 @@
#
# Link order matters here.
-obj-$(CONFIG_IP6_NF_IPTABLES) += ip6_tables.o
+obj-$(CONFIG_IP6_NF_IPTABLES_LEGACY) += ip6_tables.o
obj-$(CONFIG_IP6_NF_FILTER) += ip6table_filter.o
obj-$(CONFIG_IP6_NF_MANGLE) += ip6table_mangle.o
obj-$(CONFIG_IP6_NF_RAW) += ip6table_raw.o
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index ea1dec8448fc..707d65bc9c0e 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -931,6 +931,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
struct net *net = dev_net(dev);
struct route_info *rinfo = (struct route_info *) opt;
struct in6_addr prefix_buf, *prefix;
+ struct fib6_table *table;
unsigned int pref;
unsigned long lifetime;
struct fib6_info *rt;
@@ -989,10 +990,18 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
(rt->fib6_flags & ~RTF_PREF_MASK) | RTF_PREF(pref);
if (rt) {
- if (!addrconf_finite_timeout(lifetime))
+ table = rt->fib6_table;
+ spin_lock_bh(&table->tb6_lock);
+
+ if (!addrconf_finite_timeout(lifetime)) {
fib6_clean_expires(rt);
- else
+ fib6_remove_gc_list(rt);
+ } else {
fib6_set_expires(rt, jiffies + HZ * lifetime);
+ fib6_add_gc_list(rt);
+ }
+
+ spin_unlock_bh(&table->tb6_lock);
fib6_info_release(rt);
}
@@ -2085,12 +2094,12 @@ static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket,
*/
if (!(rt->rt6i_flags & RTF_EXPIRES)) {
if (time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) {
- RT6_TRACE("aging clone %p\n", rt);
+ pr_debug("aging clone %p\n", rt);
rt6_remove_exception(bucket, rt6_ex);
return;
}
} else if (time_after(jiffies, rt->dst.expires)) {
- RT6_TRACE("purging expired route %p\n", rt);
+ pr_debug("purging expired route %p\n", rt);
rt6_remove_exception(bucket, rt6_ex);
return;
}
@@ -2101,8 +2110,8 @@ static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket,
neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway);
if (!(neigh && (neigh->flags & NTF_ROUTER))) {
- RT6_TRACE("purging route %p via non-router but gateway\n",
- rt);
+ pr_debug("purging route %p via non-router but gateway\n",
+ rt);
rt6_remove_exception(bucket, rt6_ex);
return;
}
@@ -3765,8 +3774,6 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
if (cfg->fc_flags & RTF_EXPIRES)
fib6_set_expires(rt, jiffies +
clock_t_to_jiffies(cfg->fc_expires));
- else
- fib6_clean_expires(rt);
if (cfg->fc_protocol == RTPROT_UNSPEC)
cfg->fc_protocol = RTPROT_BOOT;
@@ -4355,7 +4362,8 @@ struct fib6_info *rt6_add_dflt_router(struct net *net,
const struct in6_addr *gwaddr,
struct net_device *dev,
unsigned int pref,
- u32 defrtr_usr_metric)
+ u32 defrtr_usr_metric,
+ int lifetime)
{
struct fib6_config cfg = {
.fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT,
@@ -4368,6 +4376,7 @@ struct fib6_info *rt6_add_dflt_router(struct net *net,
.fc_nlinfo.portid = 0,
.fc_nlinfo.nlh = NULL,
.fc_nlinfo.nl_net = net,
+ .fc_expires = jiffies_to_clock_t(lifetime * HZ),
};
cfg.fc_gateway = *gwaddr;
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 5e9f625b76e3..ed3a44aa1e9d 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1460,6 +1460,7 @@ static int ipip6_tunnel_init(struct net_device *dev)
return err;
}
netdev_hold(dev, &tunnel->dev_tracker, GFP_KERNEL);
+ netdev_lockdep_set_classes(dev);
return 0;
}
@@ -1875,22 +1876,19 @@ err_alloc_dev:
return err;
}
-static void __net_exit sit_exit_batch_net(struct list_head *net_list)
+static void __net_exit sit_exit_batch_rtnl(struct list_head *net_list,
+ struct list_head *dev_to_kill)
{
- LIST_HEAD(list);
struct net *net;
- rtnl_lock();
+ ASSERT_RTNL();
list_for_each_entry(net, net_list, exit_list)
- sit_destroy_tunnels(net, &list);
-
- unregister_netdevice_many(&list);
- rtnl_unlock();
+ sit_destroy_tunnels(net, dev_to_kill);
}
static struct pernet_operations sit_net_ops = {
.init = sit_init_net,
- .exit_batch = sit_exit_batch_net,
+ .exit_batch_rtnl = sit_exit_batch_rtnl,
.id = &sit_net_id,
.size = sizeof(struct sit_net),
};
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index c8d2ca27220c..6b9c69278819 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -182,9 +182,13 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
!th->ack || th->rst)
goto out;
- req = cookie_tcp_check(net, sk, skb);
- if (IS_ERR(req))
- goto out;
+ if (cookie_bpf_ok(skb)) {
+ req = cookie_bpf_check(sk, skb);
+ } else {
+ req = cookie_tcp_check(net, sk, skb);
+ if (IS_ERR(req))
+ goto out;
+ }
if (!req)
goto out_drop;
@@ -247,7 +251,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
ireq->wscale_ok, &rcv_wscale,
dst_metric(dst, RTAX_INITRWND));
- ireq->rcv_wscale = rcv_wscale;
+ if (!req->syncookie)
+ ireq->rcv_wscale = rcv_wscale;
ireq->ecn_ok &= cookie_ecn_ok(net, dst);
ret = tcp_get_cookie_sock(sk, skb, req, dst);