#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/list.h>
+#include <net/net_namespace.h>
+#include <net/sock.h>
#include <net/fib_rules.h>
-static LIST_HEAD(rules_ops);
-static DEFINE_SPINLOCK(rules_mod_lock);
+int fib_default_rule_add(struct fib_rules_ops *ops,
+ u32 pref, u32 table, u32 flags)
+{
+ struct fib_rule *r;
+
+ r = kzalloc(ops->rule_size, GFP_KERNEL);
+ if (r == NULL)
+ return -ENOMEM;
+
+ atomic_set(&r->refcnt, 1);
+ r->action = FR_ACT_TO_TBL;
+ r->pref = pref;
+ r->table = table;
+ r->flags = flags;
+ r->fr_net = hold_net(ops->fro_net);
+
+ /* The lock is not required here, the list in unreacheable
+ * at the moment this function is called */
+ list_add_tail(&r->list, &ops->rules_list);
+ return 0;
+}
+EXPORT_SYMBOL(fib_default_rule_add);
static void notify_rule_change(int event, struct fib_rule *rule,
struct fib_rules_ops *ops, struct nlmsghdr *nlh,
u32 pid);
-static struct fib_rules_ops *lookup_rules_ops(int family)
+static struct fib_rules_ops *lookup_rules_ops(struct net *net, int family)
{
struct fib_rules_ops *ops;
rcu_read_lock();
- list_for_each_entry_rcu(ops, &rules_ops, list) {
+ list_for_each_entry_rcu(ops, &net->rules_ops, list) {
if (ops->family == family) {
if (!try_module_get(ops->owner))
ops = NULL;
module_put(ops->owner);
}
+static void flush_route_cache(struct fib_rules_ops *ops)
+{
+ if (ops->flush_cache)
+ ops->flush_cache();
+}
+
int fib_rules_register(struct fib_rules_ops *ops)
{
int err = -EEXIST;
struct fib_rules_ops *o;
+ struct net *net;
+
+ net = ops->fro_net;
if (ops->rule_size < sizeof(struct fib_rule))
return -EINVAL;
ops->action == NULL)
return -EINVAL;
- spin_lock(&rules_mod_lock);
- list_for_each_entry(o, &rules_ops, list)
+ spin_lock(&net->rules_mod_lock);
+ list_for_each_entry(o, &net->rules_ops, list)
if (ops->family == o->family)
goto errout;
- list_add_tail_rcu(&ops->list, &rules_ops);
+ hold_net(net);
+ list_add_tail_rcu(&ops->list, &net->rules_ops);
err = 0;
errout:
- spin_unlock(&rules_mod_lock);
+ spin_unlock(&net->rules_mod_lock);
return err;
}
EXPORT_SYMBOL_GPL(fib_rules_register);
-static void cleanup_ops(struct fib_rules_ops *ops)
+void fib_rules_cleanup_ops(struct fib_rules_ops *ops)
{
struct fib_rule *rule, *tmp;
- list_for_each_entry_safe(rule, tmp, ops->rules_list, list) {
+ list_for_each_entry_safe(rule, tmp, &ops->rules_list, list) {
list_del_rcu(&rule->list);
fib_rule_put(rule);
}
}
+EXPORT_SYMBOL_GPL(fib_rules_cleanup_ops);
-int fib_rules_unregister(struct fib_rules_ops *ops)
+void fib_rules_unregister(struct fib_rules_ops *ops)
{
- int err = 0;
- struct fib_rules_ops *o;
+ struct net *net = ops->fro_net;
- spin_lock(&rules_mod_lock);
- list_for_each_entry(o, &rules_ops, list) {
- if (o == ops) {
- list_del_rcu(&o->list);
- cleanup_ops(ops);
- goto out;
- }
- }
-
- err = -ENOENT;
-out:
- spin_unlock(&rules_mod_lock);
+ spin_lock(&net->rules_mod_lock);
+ list_del_rcu(&ops->list);
+ fib_rules_cleanup_ops(ops);
+ spin_unlock(&net->rules_mod_lock);
synchronize_rcu();
-
- return err;
+ release_net(net);
}
EXPORT_SYMBOL_GPL(fib_rules_unregister);
rcu_read_lock();
- list_for_each_entry_rcu(rule, ops->rules_list, list) {
+ list_for_each_entry_rcu(rule, &ops->rules_list, list) {
+jumped:
if (!fib_rule_match(rule, ops, fl, flags))
continue;
- err = ops->action(rule, fl, flags, arg);
+ if (rule->action == FR_ACT_GOTO) {
+ struct fib_rule *target;
+
+ target = rcu_dereference(rule->ctarget);
+ if (target == NULL) {
+ continue;
+ } else {
+ rule = target;
+ goto jumped;
+ }
+ } else if (rule->action == FR_ACT_NOP)
+ continue;
+ else
+ err = ops->action(rule, fl, flags, arg);
+
if (err != -EAGAIN) {
fib_rule_get(rule);
arg->rule = rule;
return err;
}
-int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
+static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
{
+ struct net *net = sock_net(skb->sk);
struct fib_rule_hdr *frh = nlmsg_data(nlh);
struct fib_rules_ops *ops = NULL;
struct fib_rule *rule, *r, *last = NULL;
struct nlattr *tb[FRA_MAX+1];
- int err = -EINVAL;
+ int err = -EINVAL, unresolved = 0;
if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh)))
goto errout;
- ops = lookup_rules_ops(frh->family);
+ ops = lookup_rules_ops(net, frh->family);
if (ops == NULL) {
- err = EAFNOSUPPORT;
+ err = -EAFNOSUPPORT;
goto errout;
}
err = -ENOMEM;
goto errout;
}
+ rule->fr_net = hold_net(net);
if (tb[FRA_PRIORITY])
rule->pref = nla_get_u32(tb[FRA_PRIORITY]);
rule->ifindex = -1;
nla_strlcpy(rule->ifname, tb[FRA_IFNAME], IFNAMSIZ);
- dev = __dev_get_by_name(rule->ifname);
+ dev = __dev_get_by_name(net, rule->ifname);
if (dev)
rule->ifindex = dev->ifindex;
}
rule->table = frh_get_table(frh, tb);
if (!rule->pref && ops->default_pref)
- rule->pref = ops->default_pref();
+ rule->pref = ops->default_pref(ops);
+
+ err = -EINVAL;
+ if (tb[FRA_GOTO]) {
+ if (rule->action != FR_ACT_GOTO)
+ goto errout_free;
+
+ rule->target = nla_get_u32(tb[FRA_GOTO]);
+ /* Backward jumps are prohibited to avoid endless loops */
+ if (rule->target <= rule->pref)
+ goto errout_free;
+
+ list_for_each_entry(r, &ops->rules_list, list) {
+ if (r->pref == rule->target) {
+ rule->ctarget = r;
+ break;
+ }
+ }
+
+ if (rule->ctarget == NULL)
+ unresolved = 1;
+ } else if (rule->action == FR_ACT_GOTO)
+ goto errout_free;
err = ops->configure(rule, skb, nlh, frh, tb);
if (err < 0)
goto errout_free;
- list_for_each_entry(r, ops->rules_list, list) {
+ list_for_each_entry(r, &ops->rules_list, list) {
if (r->pref > rule->pref)
break;
last = r;
fib_rule_get(rule);
+ if (ops->unresolved_rules) {
+ /*
+ * There are unresolved goto rules in the list, check if
+ * any of them are pointing to this new rule.
+ */
+ list_for_each_entry(r, &ops->rules_list, list) {
+ if (r->action == FR_ACT_GOTO &&
+ r->target == rule->pref) {
+ BUG_ON(r->ctarget != NULL);
+ rcu_assign_pointer(r->ctarget, rule);
+ if (--ops->unresolved_rules == 0)
+ break;
+ }
+ }
+ }
+
+ if (rule->action == FR_ACT_GOTO)
+ ops->nr_goto_rules++;
+
+ if (unresolved)
+ ops->unresolved_rules++;
+
if (last)
list_add_rcu(&rule->list, &last->list);
else
- list_add_rcu(&rule->list, ops->rules_list);
+ list_add_rcu(&rule->list, &ops->rules_list);
notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).pid);
+ flush_route_cache(ops);
rules_ops_put(ops);
return 0;
errout_free:
+ release_net(rule->fr_net);
kfree(rule);
errout:
rules_ops_put(ops);
return err;
}
-int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
+static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
{
+ struct net *net = sock_net(skb->sk);
struct fib_rule_hdr *frh = nlmsg_data(nlh);
struct fib_rules_ops *ops = NULL;
- struct fib_rule *rule;
+ struct fib_rule *rule, *tmp;
struct nlattr *tb[FRA_MAX+1];
int err = -EINVAL;
if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh)))
goto errout;
- ops = lookup_rules_ops(frh->family);
+ ops = lookup_rules_ops(net, frh->family);
if (ops == NULL) {
- err = EAFNOSUPPORT;
+ err = -EAFNOSUPPORT;
goto errout;
}
if (err < 0)
goto errout;
- list_for_each_entry(rule, ops->rules_list, list) {
+ list_for_each_entry(rule, &ops->rules_list, list) {
if (frh->action && (frh->action != rule->action))
continue;
}
list_del_rcu(&rule->list);
+
+ if (rule->action == FR_ACT_GOTO)
+ ops->nr_goto_rules--;
+
+ /*
+ * Check if this rule is a target to any of them. If so,
+ * disable them. As this operation is eventually very
+ * expensive, it is only performed if goto rules have
+ * actually been added.
+ */
+ if (ops->nr_goto_rules > 0) {
+ list_for_each_entry(tmp, &ops->rules_list, list) {
+ if (tmp->ctarget == rule) {
+ rcu_assign_pointer(tmp->ctarget, NULL);
+ ops->unresolved_rules++;
+ }
+ }
+ }
+
synchronize_rcu();
notify_rule_change(RTM_DELRULE, rule, ops, nlh,
NETLINK_CB(skb).pid);
fib_rule_put(rule);
+ flush_route_cache(ops);
rules_ops_put(ops);
return 0;
}
frh->action = rule->action;
frh->flags = rule->flags;
- if (rule->ifname[0])
+ if (rule->action == FR_ACT_GOTO && rule->ctarget == NULL)
+ frh->flags |= FIB_RULE_UNRESOLVED;
+
+ if (rule->ifname[0]) {
NLA_PUT_STRING(skb, FRA_IFNAME, rule->ifname);
+ if (rule->ifindex == -1)
+ frh->flags |= FIB_RULE_DEV_DETACHED;
+ }
+
if (rule->pref)
NLA_PUT_U32(skb, FRA_PRIORITY, rule->pref);
if (rule->mark_mask || rule->mark)
NLA_PUT_U32(skb, FRA_FWMASK, rule->mark_mask);
+ if (rule->target)
+ NLA_PUT_U32(skb, FRA_GOTO, rule->target);
+
if (ops->fill(rule, skb, nlh, frh) < 0)
goto nla_put_failure;
return -EMSGSIZE;
}
-int fib_rules_dump(struct sk_buff *skb, struct netlink_callback *cb, int family)
+static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb,
+ struct fib_rules_ops *ops)
{
int idx = 0;
struct fib_rule *rule;
- struct fib_rules_ops *ops;
- ops = lookup_rules_ops(family);
- if (ops == NULL)
- return -EAFNOSUPPORT;
-
- rcu_read_lock();
- list_for_each_entry_rcu(rule, ops->rules_list, list) {
- if (idx < cb->args[0])
+ list_for_each_entry(rule, &ops->rules_list, list) {
+ if (idx < cb->args[1])
goto skip;
if (fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).pid,
skip:
idx++;
}
- rcu_read_unlock();
- cb->args[0] = idx;
+ cb->args[1] = idx;
rules_ops_put(ops);
return skb->len;
}
-EXPORT_SYMBOL_GPL(fib_rules_dump);
+static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct net *net = sock_net(skb->sk);
+ struct fib_rules_ops *ops;
+ int idx = 0, family;
+
+ family = rtnl_msg_family(cb->nlh);
+ if (family != AF_UNSPEC) {
+ /* Protocol specific dump request */
+ ops = lookup_rules_ops(net, family);
+ if (ops == NULL)
+ return -EAFNOSUPPORT;
+
+ return dump_rules(skb, cb, ops);
+ }
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(ops, &net->rules_ops, list) {
+ if (idx < cb->args[0] || !try_module_get(ops->owner))
+ goto skip;
+
+ if (dump_rules(skb, cb, ops) < 0)
+ break;
+
+ cb->args[1] = 0;
+ skip:
+ idx++;
+ }
+ rcu_read_unlock();
+ cb->args[0] = idx;
+
+ return skb->len;
+}
static void notify_rule_change(int event, struct fib_rule *rule,
struct fib_rules_ops *ops, struct nlmsghdr *nlh,
u32 pid)
{
+ struct net *net;
struct sk_buff *skb;
int err = -ENOBUFS;
+ net = ops->fro_net;
skb = nlmsg_new(fib_rule_nlmsg_size(ops, rule), GFP_KERNEL);
if (skb == NULL)
goto errout;
kfree_skb(skb);
goto errout;
}
- err = rtnl_notify(skb, pid, ops->nlgroup, nlh, GFP_KERNEL);
+
+ err = rtnl_notify(skb, net, pid, ops->nlgroup, nlh, GFP_KERNEL);
errout:
if (err < 0)
- rtnl_set_sk_err(ops->nlgroup, err);
+ rtnl_set_sk_err(net, ops->nlgroup, err);
}
static void attach_rules(struct list_head *rules, struct net_device *dev)
void *ptr)
{
struct net_device *dev = ptr;
+ struct net *net = dev_net(dev);
struct fib_rules_ops *ops;
ASSERT_RTNL();
switch (event) {
case NETDEV_REGISTER:
- list_for_each_entry(ops, &rules_ops, list)
- attach_rules(ops->rules_list, dev);
+ list_for_each_entry(ops, &net->rules_ops, list)
+ attach_rules(&ops->rules_list, dev);
break;
case NETDEV_UNREGISTER:
- list_for_each_entry(ops, &rules_ops, list)
- detach_rules(ops->rules_list, dev);
+ list_for_each_entry(ops, &net->rules_ops, list)
+ detach_rules(&ops->rules_list, dev);
break;
}
.notifier_call = fib_rules_event,
};
+static int fib_rules_net_init(struct net *net)
+{
+ INIT_LIST_HEAD(&net->rules_ops);
+ spin_lock_init(&net->rules_mod_lock);
+ return 0;
+}
+
+static struct pernet_operations fib_rules_net_ops = {
+ .init = fib_rules_net_init,
+};
+
static int __init fib_rules_init(void)
{
- return register_netdevice_notifier(&fib_rules_notifier);
+ int err;
+ rtnl_register(PF_UNSPEC, RTM_NEWRULE, fib_nl_newrule, NULL);
+ rtnl_register(PF_UNSPEC, RTM_DELRULE, fib_nl_delrule, NULL);
+ rtnl_register(PF_UNSPEC, RTM_GETRULE, NULL, fib_nl_dumprule);
+
+ err = register_netdevice_notifier(&fib_rules_notifier);
+ if (err < 0)
+ goto fail;
+
+ err = register_pernet_subsys(&fib_rules_net_ops);
+ if (err < 0)
+ goto fail_unregister;
+ return 0;
+
+fail_unregister:
+ unregister_netdevice_notifier(&fib_rules_notifier);
+fail:
+ rtnl_unregister(PF_UNSPEC, RTM_NEWRULE);
+ rtnl_unregister(PF_UNSPEC, RTM_DELRULE);
+ rtnl_unregister(PF_UNSPEC, RTM_GETRULE);
+ return err;
}
subsys_initcall(fib_rules_init);