summaryrefslogtreecommitdiff
path: root/net/ipv6/route.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6/route.c')
-rw-r--r--net/ipv6/route.c264
1 files changed, 155 insertions, 109 deletions
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index ef815ba583a8..15ce21afc8c6 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -87,7 +87,8 @@ struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie);
static unsigned int ip6_default_advmss(const struct dst_entry *dst);
INDIRECT_CALLABLE_SCOPE
unsigned int ip6_mtu(const struct dst_entry *dst);
-static struct dst_entry *ip6_negative_advice(struct dst_entry *);
+static void ip6_negative_advice(struct sock *sk,
+ struct dst_entry *dst);
static void ip6_dst_destroy(struct dst_entry *);
static void ip6_dst_ifdown(struct dst_entry *,
struct net_device *dev);
@@ -130,7 +131,6 @@ static struct fib6_info *rt6_get_route_info(struct net *net,
struct uncached_list {
spinlock_t lock;
struct list_head head;
- struct list_head quarantine;
};
static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt6_uncached_list);
@@ -174,7 +174,7 @@ static void rt6_uncached_list_flush_dev(struct net_device *dev)
struct net_device *rt_dev = rt->dst.dev;
bool handled = false;
- if (rt_idev->dev == dev) {
+ if (rt_idev && rt_idev->dev == dev) {
rt->rt6i_idev = in6_dev_get(blackhole_netdev);
in6_dev_put(rt_idev);
handled = true;
@@ -188,8 +188,7 @@ static void rt6_uncached_list_flush_dev(struct net_device *dev)
handled = true;
}
if (handled)
- list_move(&rt->dst.rt_uncached,
- &ul->quarantine);
+ list_del_init(&rt->dst.rt_uncached);
}
spin_unlock_bh(&ul->lock);
}
@@ -226,7 +225,7 @@ static struct neighbour *ip6_dst_neigh_lookup(const struct dst_entry *dst,
struct sk_buff *skb,
const void *daddr)
{
- const struct rt6_info *rt = container_of(dst, struct rt6_info, dst);
+ const struct rt6_info *rt = dst_rt6_info(dst);
return ip6_neigh_lookup(rt6_nexthop(rt, &in6addr_any),
dst->dev, skb, daddr);
@@ -234,8 +233,8 @@ static struct neighbour *ip6_dst_neigh_lookup(const struct dst_entry *dst,
static void ip6_confirm_neigh(const struct dst_entry *dst, const void *daddr)
{
+ const struct rt6_info *rt = dst_rt6_info(dst);
struct net_device *dev = dst->dev;
- struct rt6_info *rt = (struct rt6_info *)dst;
daddr = choose_neigh_daddr(rt6_nexthop(rt, &in6addr_any), NULL, daddr);
if (!daddr)
@@ -354,7 +353,7 @@ EXPORT_SYMBOL(ip6_dst_alloc);
static void ip6_dst_destroy(struct dst_entry *dst)
{
- struct rt6_info *rt = (struct rt6_info *)dst;
+ struct rt6_info *rt = dst_rt6_info(dst);
struct fib6_info *from;
struct inet6_dev *idev;
@@ -367,14 +366,15 @@ static void ip6_dst_destroy(struct dst_entry *dst)
in6_dev_put(idev);
}
- from = xchg((__force struct fib6_info **)&rt->from, NULL);
+ from = unrcu_pointer(xchg(&rt->from, NULL));
fib6_info_release(from);
}
static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev)
{
- struct rt6_info *rt = (struct rt6_info *)dst;
+ struct rt6_info *rt = dst_rt6_info(dst);
struct inet6_dev *idev = rt->rt6i_idev;
+ struct fib6_info *from;
if (idev && idev->dev != blackhole_netdev) {
struct inet6_dev *blackhole_idev = in6_dev_get(blackhole_netdev);
@@ -384,6 +384,8 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev)
in6_dev_put(idev);
}
}
+ from = unrcu_pointer(xchg(&rt->from, NULL));
+ fib6_info_release(from);
}
static bool __rt6_check_expired(const struct rt6_info *rt)
@@ -414,8 +416,8 @@ void fib6_select_path(const struct net *net, struct fib6_result *res,
struct flowi6 *fl6, int oif, bool have_oif_match,
const struct sk_buff *skb, int strict)
{
- struct fib6_info *sibling, *next_sibling;
struct fib6_info *match = res->f6i;
+ struct fib6_info *sibling;
if (!match->nh && (!match->fib6_nsiblings || have_oif_match))
goto out;
@@ -441,8 +443,8 @@ void fib6_select_path(const struct net *net, struct fib6_result *res,
if (fl6->mp_hash <= atomic_read(&match->fib6_nh->fib_nh_upper_bound))
goto out;
- list_for_each_entry_safe(sibling, next_sibling, &match->fib6_siblings,
- fib6_siblings) {
+ list_for_each_entry_rcu(sibling, &match->fib6_siblings,
+ fib6_siblings) {
const struct fib6_nh *nh = sibling->fib6_nh;
int nh_upper_bound;
@@ -637,6 +639,8 @@ static void rt6_probe(struct fib6_nh *fib6_nh)
rcu_read_lock();
last_probe = READ_ONCE(fib6_nh->last_probe);
idev = __in6_dev_get(dev);
+ if (!idev)
+ goto out;
neigh = __ipv6_neigh_lookup_noref(dev, nh_gw);
if (neigh) {
if (READ_ONCE(neigh->nud_state) & NUD_VALID)
@@ -645,14 +649,15 @@ static void rt6_probe(struct fib6_nh *fib6_nh)
write_lock_bh(&neigh->lock);
if (!(neigh->nud_state & NUD_VALID) &&
time_after(jiffies,
- neigh->updated + idev->cnf.rtr_probe_interval)) {
+ neigh->updated +
+ READ_ONCE(idev->cnf.rtr_probe_interval))) {
work = kmalloc(sizeof(*work), GFP_ATOMIC);
if (work)
__neigh_set_probe_once(neigh);
}
write_unlock_bh(&neigh->lock);
} else if (time_after(jiffies, last_probe +
- idev->cnf.rtr_probe_interval)) {
+ READ_ONCE(idev->cnf.rtr_probe_interval))) {
work = kmalloc(sizeof(*work), GFP_ATOMIC);
}
@@ -931,6 +936,7 @@ 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 +995,18 @@ 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);
}
@@ -1278,7 +1292,7 @@ struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr,
dst = fib6_rule_lookup(net, &fl6, skb, flags, ip6_pol_route_lookup);
if (dst->error == 0)
- return (struct rt6_info *) dst;
+ return dst_rt6_info(dst);
dst_release(dst);
@@ -1398,6 +1412,7 @@ static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res)
struct rt6_info *prev, **p;
p = this_cpu_ptr(res->nh->rt6i_pcpu);
+ /* Paired with READ_ONCE() in __fib6_drop_pcpu_from() */
prev = xchg(p, NULL);
if (prev) {
dst_dev_put(&prev->dst);
@@ -1426,7 +1441,7 @@ static struct rt6_info *rt6_make_pcpu_route(struct net *net,
if (res->f6i->fib6_destroying) {
struct fib6_info *from;
- from = xchg((__force struct fib6_info **)&pcpu_rt->from, NULL);
+ from = unrcu_pointer(xchg(&pcpu_rt->from, NULL));
fib6_info_release(from);
}
@@ -1443,7 +1458,6 @@ static DEFINE_SPINLOCK(rt6_exception_lock);
static void rt6_remove_exception(struct rt6_exception_bucket *bucket,
struct rt6_exception *rt6_ex)
{
- struct fib6_info *from;
struct net *net;
if (!bucket || !rt6_ex)
@@ -1455,8 +1469,6 @@ static void rt6_remove_exception(struct rt6_exception_bucket *bucket,
/* purge completely the exception to allow releasing the held resources:
* some [sk] cache may keep the dst around for unlimited time
*/
- from = xchg((__force struct fib6_info **)&rt6_ex->rt6i->from, NULL);
- fib6_info_release(from);
dst_dev_put(&rt6_ex->rt6i->dst);
hlist_del_rcu(&rt6_ex->hlist);
@@ -1587,7 +1599,7 @@ static unsigned int fib6_mtu(const struct fib6_result *res)
rcu_read_lock();
idev = __in6_dev_get(dev);
- mtu = idev->cnf.mtu6;
+ mtu = READ_ONCE(idev->cnf.mtu6);
rcu_read_unlock();
}
@@ -2085,12 +2097,12 @@ 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 +2113,8 @@ 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;
}
@@ -2211,7 +2223,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
strict |= flags & RT6_LOOKUP_F_IFACE;
strict |= flags & RT6_LOOKUP_F_IGNORE_LINKSTATE;
- if (net->ipv6.devconf_all->forwarding == 0)
+ if (READ_ONCE(net->ipv6.devconf_all->forwarding) == 0)
strict |= RT6_LOOKUP_F_REACHABLE;
rcu_read_lock();
@@ -2362,7 +2374,7 @@ static u32 rt6_multipath_custom_hash_outer(const struct net *net,
hash_keys.ports.dst = keys.ports.dst;
*p_has_inner = !!(keys.control.flags & FLOW_DIS_ENCAPSULATION);
- return flow_hash_from_keys(&hash_keys);
+ return fib_multipath_hash_from_keys(net, &hash_keys);
}
static u32 rt6_multipath_custom_hash_inner(const struct net *net,
@@ -2411,7 +2423,7 @@ static u32 rt6_multipath_custom_hash_inner(const struct net *net,
if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT)
hash_keys.ports.dst = keys.ports.dst;
- return flow_hash_from_keys(&hash_keys);
+ return fib_multipath_hash_from_keys(net, &hash_keys);
}
static u32 rt6_multipath_custom_hash_skb(const struct net *net,
@@ -2450,7 +2462,7 @@ static u32 rt6_multipath_custom_hash_fl6(const struct net *net,
if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT)
hash_keys.ports.dst = fl6->fl6_dport;
- return flow_hash_from_keys(&hash_keys);
+ return fib_multipath_hash_from_keys(net, &hash_keys);
}
/* if skb is set it will be used and fl6 can be NULL */
@@ -2472,7 +2484,7 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6,
hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6);
hash_keys.basic.ip_proto = fl6->flowi6_proto;
}
- mhash = flow_hash_from_keys(&hash_keys);
+ mhash = fib_multipath_hash_from_keys(net, &hash_keys);
break;
case 1:
if (skb) {
@@ -2504,7 +2516,7 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6,
hash_keys.ports.dst = fl6->fl6_dport;
hash_keys.basic.ip_proto = fl6->flowi6_proto;
}
- mhash = flow_hash_from_keys(&hash_keys);
+ mhash = fib_multipath_hash_from_keys(net, &hash_keys);
break;
case 2:
memset(&hash_keys, 0, sizeof(hash_keys));
@@ -2541,7 +2553,7 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6,
hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6);
hash_keys.basic.ip_proto = fl6->flowi6_proto;
}
- mhash = flow_hash_from_keys(&hash_keys);
+ mhash = fib_multipath_hash_from_keys(net, &hash_keys);
break;
case 3:
if (skb)
@@ -2637,7 +2649,7 @@ struct dst_entry *ip6_route_output_flags(struct net *net,
rcu_read_lock();
dst = ip6_route_output_flags_noref(net, sk, fl6, flags);
- rt6 = (struct rt6_info *)dst;
+ rt6 = dst_rt6_info(dst);
/* For dst cached in uncached_list, refcnt is already taken. */
if (list_empty(&rt6->dst.rt_uncached) && !dst_hold_safe(dst)) {
dst = &net->ipv6.ip6_null_entry->dst;
@@ -2651,7 +2663,7 @@ EXPORT_SYMBOL_GPL(ip6_route_output_flags);
struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig)
{
- struct rt6_info *rt, *ort = (struct rt6_info *) dst_orig;
+ struct rt6_info *rt, *ort = dst_rt6_info(dst_orig);
struct net_device *loopback_dev = net->loopback_dev;
struct dst_entry *new = NULL;
@@ -2734,7 +2746,7 @@ INDIRECT_CALLABLE_SCOPE struct dst_entry *ip6_dst_check(struct dst_entry *dst,
struct fib6_info *from;
struct rt6_info *rt;
- rt = container_of(dst, struct rt6_info, dst);
+ rt = dst_rt6_info(dst);
if (rt->sernum)
return rt6_is_valid(rt) ? dst : NULL;
@@ -2760,24 +2772,24 @@ INDIRECT_CALLABLE_SCOPE struct dst_entry *ip6_dst_check(struct dst_entry *dst,
}
EXPORT_INDIRECT_CALLABLE(ip6_dst_check);
-static struct dst_entry *ip6_negative_advice(struct dst_entry *dst)
+static void ip6_negative_advice(struct sock *sk,
+ struct dst_entry *dst)
{
- struct rt6_info *rt = (struct rt6_info *) dst;
+ struct rt6_info *rt = dst_rt6_info(dst);
- if (rt) {
- if (rt->rt6i_flags & RTF_CACHE) {
- rcu_read_lock();
- if (rt6_check_expired(rt)) {
- rt6_remove_exception_rt(rt);
- dst = NULL;
- }
- rcu_read_unlock();
- } else {
- dst_release(dst);
- dst = NULL;
+ if (rt->rt6i_flags & RTF_CACHE) {
+ rcu_read_lock();
+ if (rt6_check_expired(rt)) {
+ /* rt/dst can not be destroyed yet,
+ * because of rcu_read_lock()
+ */
+ sk_dst_reset(sk);
+ rt6_remove_exception_rt(rt);
}
+ rcu_read_unlock();
+ return;
}
- return dst;
+ sk_dst_reset(sk);
}
static void ip6_link_failure(struct sk_buff *skb)
@@ -2786,7 +2798,7 @@ static void ip6_link_failure(struct sk_buff *skb)
icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0);
- rt = (struct rt6_info *) skb_dst(skb);
+ rt = dst_rt6_info(skb_dst(skb));
if (rt) {
rcu_read_lock();
if (rt->rt6i_flags & RTF_CACHE) {
@@ -2842,7 +2854,7 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
bool confirm_neigh)
{
const struct in6_addr *daddr, *saddr;
- struct rt6_info *rt6 = (struct rt6_info *)dst;
+ struct rt6_info *rt6 = dst_rt6_info(dst);
/* Note: do *NOT* check dst_metric_locked(dst, RTAX_MTU)
* IPv6 pmtu discovery isn't optional, so 'mtu lock' cannot disable it.
@@ -3184,13 +3196,18 @@ static unsigned int ip6_default_advmss(const struct dst_entry *dst)
{
struct net_device *dev = dst->dev;
unsigned int mtu = dst_mtu(dst);
- struct net *net = dev_net(dev);
+ struct net *net;
mtu -= sizeof(struct ipv6hdr) + sizeof(struct tcphdr);
+ rcu_read_lock();
+
+ net = dev_net_rcu(dev);
if (mtu < net->ipv6.sysctl.ip6_rt_min_advmss)
mtu = net->ipv6.sysctl.ip6_rt_min_advmss;
+ rcu_read_unlock();
+
/*
* Maximal non-jumbo IPv6 payload is IPV6_MAXPLEN and
* corresponding MSS is IPV6_MAXPLEN - tcp_header_size.
@@ -3240,8 +3257,8 @@ u32 ip6_mtu_from_fib6(const struct fib6_result *res,
mtu = IPV6_MIN_MTU;
idev = __in6_dev_get(dev);
- if (idev && idev->cnf.mtu6 > mtu)
- mtu = idev->cnf.mtu6;
+ if (idev)
+ mtu = max_t(u32, mtu, READ_ONCE(idev->cnf.mtu6));
}
mtu = min_t(unsigned int, mtu, IP6_MAX_MTU);
@@ -3591,7 +3608,7 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
if (!dev)
goto out;
- if (idev->cnf.disable_ipv6) {
+ if (!idev || idev->cnf.disable_ipv6) {
NL_SET_ERR_MSG(extack, "IPv6 is disabled on nexthop device");
err = -EACCES;
goto out;
@@ -3627,7 +3644,8 @@ out:
in6_dev_put(idev);
if (err) {
- lwtstate_put(fib6_nh->fib_nh_lws);
+ fib_nh_common_release(&fib6_nh->nh_common);
+ fib6_nh->nh_common.nhc_pcpu_rth_output = NULL;
fib6_nh->fib_nh_lws = NULL;
netdev_put(dev, dev_tracker);
}
@@ -3750,7 +3768,7 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
if (!rt)
goto out;
- rt->fib6_metrics = ip_fib_metrics_init(net, cfg->fc_mx, cfg->fc_mx_len,
+ rt->fib6_metrics = ip_fib_metrics_init(cfg->fc_mx, cfg->fc_mx_len,
extack);
if (IS_ERR(rt->fib6_metrics)) {
err = PTR_ERR(rt->fib6_metrics);
@@ -3765,8 +3783,6 @@ 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;
@@ -3787,10 +3803,12 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
if (nh) {
if (rt->fib6_src.plen) {
NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing");
+ err = -EINVAL;
goto out_free;
}
if (!nexthop_get(nh)) {
NL_SET_ERR_MSG(extack, "Nexthop has been deleted");
+ err = -ENOENT;
goto out_free;
}
rt->nh = nh;
@@ -4142,7 +4160,8 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
in6_dev = __in6_dev_get(skb->dev);
if (!in6_dev)
return;
- if (in6_dev->cnf.forwarding || !in6_dev->cnf.accept_redirects)
+ if (READ_ONCE(in6_dev->cnf.forwarding) ||
+ !READ_ONCE(in6_dev->cnf.accept_redirects))
return;
/* RFC2461 8.1:
@@ -4165,7 +4184,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
}
}
- rt = (struct rt6_info *) dst;
+ rt = dst_rt6_info(dst);
if (rt->rt6i_flags & RTF_REJECT) {
net_dbg_ratelimited("rt6_redirect: source isn't a valid nexthop for redirect target\n");
return;
@@ -4355,7 +4374,8 @@ 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 +4388,7 @@ 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;
@@ -4434,7 +4455,7 @@ static void rtmsg_to_fib6_config(struct net *net,
.fc_table = l3mdev_fib_table_by_index(net, rtmsg->rtmsg_ifindex) ?
: RT6_TABLE_MAIN,
.fc_ifindex = rtmsg->rtmsg_ifindex,
- .fc_metric = rtmsg->rtmsg_metric ? : IP6_RT_PRIO_USER,
+ .fc_metric = rtmsg->rtmsg_metric,
.fc_expires = rtmsg->rtmsg_info,
.fc_dst_len = rtmsg->rtmsg_dst_len,
.fc_src_len = rtmsg->rtmsg_src_len,
@@ -4464,6 +4485,9 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, struct in6_rtmsg *rtmsg)
rtnl_lock();
switch (cmd) {
case SIOCADDRT:
+ /* Only do the default setting of fc_metric in route adding */
+ if (cfg.fc_metric == 0)
+ cfg.fc_metric = IP6_RT_PRIO_USER;
err = ip6_route_add(&cfg, GFP_KERNEL, NULL);
break;
case SIOCDELRT:
@@ -4574,8 +4598,8 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net,
f6i->dst_nocount = true;
if (!anycast &&
- (net->ipv6.devconf_all->disable_policy ||
- idev->cnf.disable_policy))
+ (READ_ONCE(net->ipv6.devconf_all->disable_policy) ||
+ READ_ONCE(idev->cnf.disable_policy)))
f6i->dst_nopolicy = true;
}
@@ -4989,6 +5013,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
[RTA_SPORT] = { .type = NLA_U16 },
[RTA_DPORT] = { .type = NLA_U16 },
[RTA_NH_ID] = { .type = NLA_U32 },
+ [RTA_FLOWLABEL] = { .type = NLA_BE32 },
};
static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -5014,6 +5039,12 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
goto errout;
}
+ if (tb[RTA_FLOWLABEL]) {
+ NL_SET_ERR_MSG_ATTR(extack, tb[RTA_FLOWLABEL],
+ "Flow label cannot be specified for this operation");
+ goto errout;
+ }
+
*cfg = (struct fib6_config){
.fc_table = rtm->rtm_table,
.fc_dst_len = rtm->rtm_dst_len,
@@ -5179,14 +5210,18 @@ static void ip6_route_mpath_notify(struct fib6_info *rt,
* nexthop. Since sibling routes are always added at the end of
* the list, find the first sibling of the last route appended
*/
+ rcu_read_lock();
+
if ((nlflags & NLM_F_APPEND) && rt_last && rt_last->fib6_nsiblings) {
- rt = list_first_entry(&rt_last->fib6_siblings,
- struct fib6_info,
- fib6_siblings);
+ rt = list_first_or_null_rcu(&rt_last->fib6_siblings,
+ struct fib6_info,
+ fib6_siblings);
}
if (rt)
inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags);
+
+ rcu_read_unlock();
}
static bool ip6_route_mpath_should_notify(const struct fib6_info *rt)
@@ -5531,17 +5566,21 @@ static size_t rt6_nlmsg_size(struct fib6_info *f6i)
nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_nlmsg_size,
&nexthop_len);
} else {
- struct fib6_info *sibling, *next_sibling;
struct fib6_nh *nh = f6i->fib6_nh;
+ struct fib6_info *sibling;
nexthop_len = 0;
if (f6i->fib6_nsiblings) {
rt6_nh_nlmsg_size(nh, &nexthop_len);
- list_for_each_entry_safe(sibling, next_sibling,
- &f6i->fib6_siblings, fib6_siblings) {
+ rcu_read_lock();
+
+ list_for_each_entry_rcu(sibling, &f6i->fib6_siblings,
+ fib6_siblings) {
rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len);
}
+
+ rcu_read_unlock();
}
nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws);
}
@@ -5597,7 +5636,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
int iif, int type, u32 portid, u32 seq,
unsigned int flags)
{
- struct rt6_info *rt6 = (struct rt6_info *)dst;
+ struct rt6_info *rt6 = dst_rt6_info(dst);
struct rt6key *rt6_dst, *rt6_src;
u32 *pmetrics, table, rt6_flags;
unsigned char nh_flags = 0;
@@ -5671,7 +5710,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
goto nla_put_failure;
} else if (dest) {
struct in6_addr saddr_buf;
- if (ip6_route_get_saddr(net, rt, dest, 0, &saddr_buf) == 0 &&
+ if (ip6_route_get_saddr(net, rt, dest, 0, 0, &saddr_buf) == 0 &&
nla_put_in6_addr(skb, RTA_PREFSRC, &saddr_buf))
goto nla_put_failure;
}
@@ -5705,7 +5744,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
lwtunnel_fill_encap(skb, dst->lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0)
goto nla_put_failure;
} else if (rt->fib6_nsiblings) {
- struct fib6_info *sibling, *next_sibling;
+ struct fib6_info *sibling;
struct nlattr *mp;
mp = nla_nest_start_noflag(skb, RTA_MULTIPATH);
@@ -5717,14 +5756,21 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
0) < 0)
goto nla_put_failure;
- list_for_each_entry_safe(sibling, next_sibling,
- &rt->fib6_siblings, fib6_siblings) {
+ rcu_read_lock();
+
+ list_for_each_entry_rcu(sibling, &rt->fib6_siblings,
+ fib6_siblings) {
if (fib_add_nexthop(skb, &sibling->fib6_nh->nh_common,
sibling->fib6_nh->fib_nh_weight,
- AF_INET6, 0) < 0)
+ AF_INET6, 0) < 0) {
+ rcu_read_unlock();
+
goto nla_put_failure;
+ }
}
+ rcu_read_unlock();
+
nla_nest_end(skb, mp);
} else if (rt->nh) {
if (nla_put_u32(skb, RTA_NH_ID, rt->nh->id))
@@ -5982,6 +6028,13 @@ static int inet6_rtm_valid_getroute_req(struct sk_buff *skb,
return -EINVAL;
}
+ if (tb[RTA_FLOWLABEL] &&
+ (nla_get_be32(tb[RTA_FLOWLABEL]) & ~IPV6_FLOWLABEL_MASK)) {
+ NL_SET_ERR_MSG_ATTR(extack, tb[RTA_FLOWLABEL],
+ "Invalid flow label");
+ return -EINVAL;
+ }
+
for (i = 0; i <= RTA_MAX; i++) {
if (!tb[i])
continue;
@@ -5996,6 +6049,7 @@ static int inet6_rtm_valid_getroute_req(struct sk_buff *skb,
case RTA_SPORT:
case RTA_DPORT:
case RTA_IP_PROTO:
+ case RTA_FLOWLABEL:
break;
default:
NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in get route request");
@@ -6018,6 +6072,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
struct sk_buff *skb;
struct rtmsg *rtm;
struct flowi6 fl6 = {};
+ __be32 flowlabel;
bool fibmatch;
err = inet6_rtm_valid_getroute_req(in_skb, nlh, tb, extack);
@@ -6026,7 +6081,6 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
err = -EINVAL;
rtm = nlmsg_data(nlh);
- fl6.flowlabel = ip6_make_flowinfo(rtm->rtm_tos, 0);
fibmatch = !!(rtm->rtm_flags & RTM_F_FIB_MATCH);
if (tb[RTA_SRC]) {
@@ -6072,6 +6126,9 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
goto errout;
}
+ flowlabel = nla_get_be32_default(tb[RTA_FLOWLABEL], 0);
+ fl6.flowlabel = ip6_make_flowinfo(rtm->rtm_tos, flowlabel);
+
if (iif) {
struct net_device *dev;
int flags = 0;
@@ -6100,7 +6157,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
}
- rt = container_of(dst, struct rt6_info, dst);
+ rt = dst_rt6_info(dst);
if (rt->dst.error) {
err = rt->dst.error;
ip6_rt_put(rt);
@@ -6161,7 +6218,7 @@ void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
err = -ENOBUFS;
seq = info->nlh ? info->nlh->nlmsg_seq : 0;
- skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any());
+ skb = nlmsg_new(rt6_nlmsg_size(rt), GFP_ATOMIC);
if (!skb)
goto errout;
@@ -6174,11 +6231,10 @@ void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
goto errout;
}
rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE,
- info->nlh, gfp_any());
+ info->nlh, GFP_ATOMIC);
return;
errout:
- if (err < 0)
- rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err);
+ rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err);
}
void fib6_rt_update(struct net *net, struct fib6_info *rt,
@@ -6204,8 +6260,7 @@ void fib6_rt_update(struct net *net, struct fib6_info *rt,
info->nlh, gfp_any());
return;
errout:
- if (err < 0)
- rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err);
+ rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err);
}
void fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i,
@@ -6318,7 +6373,7 @@ static int rt6_stats_seq_show(struct seq_file *seq, void *v)
#ifdef CONFIG_SYSCTL
-static int ipv6_sysctl_rtcache_flush(struct ctl_table *ctl, int write,
+static int ipv6_sysctl_rtcache_flush(const struct ctl_table *ctl, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
struct net *net;
@@ -6327,12 +6382,12 @@ static int ipv6_sysctl_rtcache_flush(struct ctl_table *ctl, int write,
if (!write)
return -EINVAL;
- net = (struct net *)ctl->extra1;
- delay = net->ipv6.sysctl.flush_delay;
ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
if (ret)
return ret;
+ net = (struct net *)ctl->extra1;
+ delay = net->ipv6.sysctl.flush_delay;
fib6_run_gc(delay <= 0 ? 0 : (unsigned long)delay, net, delay > 0);
return 0;
}
@@ -6417,7 +6472,6 @@ static struct ctl_table ipv6_route_table_template[] = {
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE,
},
- { }
};
struct ctl_table * __net_init ipv6_route_sysctl_init(struct net *net)
@@ -6441,10 +6495,6 @@ struct ctl_table * __net_init ipv6_route_sysctl_init(struct net *net)
table[8].data = &net->ipv6.sysctl.ip6_rt_min_advmss;
table[9].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval;
table[10].data = &net->ipv6.sysctl.skip_notify_on_dev_down;
-
- /* Don't export sysctls to unprivileged users */
- if (net->user_ns != &init_user_ns)
- table[1].procname = NULL;
}
return table;
@@ -6671,6 +6721,15 @@ static void bpf_iter_unregister(void)
#endif
#endif
+static const struct rtnl_msg_handler ip6_route_rtnl_msg_handlers[] __initconst_or_module = {
+ {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_NEWROUTE,
+ .doit = inet6_rtm_newroute},
+ {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_DELROUTE,
+ .doit = inet6_rtm_delroute},
+ {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_GETROUTE,
+ .doit = inet6_rtm_getroute, .flags = RTNL_FLAG_DOIT_UNLOCKED},
+};
+
int __init ip6_route_init(void)
{
int ret;
@@ -6713,19 +6772,7 @@ int __init ip6_route_init(void)
if (ret)
goto fib6_rules_init;
- ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_NEWROUTE,
- inet6_rtm_newroute, NULL, 0);
- if (ret < 0)
- goto out_register_late_subsys;
-
- ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_DELROUTE,
- inet6_rtm_delroute, NULL, 0);
- if (ret < 0)
- goto out_register_late_subsys;
-
- ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETROUTE,
- inet6_rtm_getroute, NULL,
- RTNL_FLAG_DOIT_UNLOCKED);
+ ret = rtnl_register_many(ip6_route_rtnl_msg_handlers);
if (ret < 0)
goto out_register_late_subsys;
@@ -6745,7 +6792,6 @@ int __init ip6_route_init(void)
struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu);
INIT_LIST_HEAD(&ul->head);
- INIT_LIST_HEAD(&ul->quarantine);
spin_lock_init(&ul->lock);
}
generated by cgit (git 2.34.1) at 2025-07-25 18:16:54 +0000